diff options
1405 files changed, 19488 insertions, 10094 deletions
@@ -82,7 +82,10 @@ Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@gmail.com> Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com> Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com> <dev.kurt@vandijck-laurijssen.be> <kurt.van.dijck@eia.be> -Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> +Dmitry Baryshkov <dbaryshkov@gmail.com> +Dmitry Baryshkov <dbaryshkov@gmail.com> <[dbaryshkov@gmail.com]> +Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_baryshkov@mentor.com> +Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_eremin@mentor.com> Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com> Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com> Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com> @@ -287,6 +290,7 @@ Santosh Shilimkar <ssantosh@kernel.org> Sarangdhar Joshi <spjoshi@codeaurora.org> Sascha Hauer <s.hauer@pengutronix.de> S.ÇaÄŸlar Onur <caglar@pardus.org.tr> +Sean Christopherson <seanjc@google.com> <sean.j.christopherson@intel.com> Sean Nyekjaer <sean@geanix.com> <sean.nyekjaer@prevas.dk> Sebastian Reichel <sre@kernel.org> <sebastian.reichel@collabora.co.uk> Sebastian Reichel <sre@kernel.org> <sre@debian.org> @@ -318,6 +322,8 @@ TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn> Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com> Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws> Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de> +Uwe Kleine-König <u.kleine-koenig@pengutronix.de> +Uwe Kleine-König <ukleinek@strlen.de> Uwe Kleine-König <ukl@pengutronix.de> Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com> Valdis Kletnieks <Valdis.Kletnieks@vt.edu> @@ -98,7 +98,7 @@ N: Erik Andersen E: andersen@codepoet.org W: https://www.codepoet.org/ P: 1024D/30D39057 1BC4 2742 E885 E4DE 9301 0C82 5F9B 643E 30D3 9057 -D: Maintainer of ide-cd and Uniform CD-ROM driver, +D: Maintainer of ide-cd and Uniform CD-ROM driver, D: ATAPI CD-Changer support, Major 2.1.x CD-ROM update. S: 352 North 525 East S: Springville, Utah 84663 @@ -263,7 +263,7 @@ N: Paul Barton-Davis E: pbd@op.net D: Driver for WaveFront soundcards (Turtle Beach Maui, Tropez, Tropez+) D: Various bugfixes and changes to sound drivers -S: USA +S: USA N: Carlos Henrique Bauer E: chbauer@acm.org @@ -740,6 +740,11 @@ S: (ask for current address) S: Portland, Oregon S: USA +N: Jason Cooper +D: ARM/Marvell SOC co-maintainer +D: irqchip co-maintainer +D: MVEBU PCI DRIVER co-maintainer + N: Robin Cornelius E: robincornelius@users.sourceforge.net D: Ralink rt2x00 WLAN driver @@ -849,6 +854,12 @@ D: trivial hack to add variable address length routing to Rose. D: AX25-HOWTO, HAM-HOWTO, IPX-HOWTO, NET-2-HOWTO D: ax25-utils maintainer. +N: Kamil Debski +E: kamil@wypas.org +D: Samsung S5P 2D graphics acceleration and Multi Format Codec drivers +D: Samsung USB2 phy drivers +D: PWM fan driver + N: Helge Deller E: deller@gmx.de W: http://www.parisc-linux.org/ @@ -1199,7 +1210,7 @@ N: Daniel J. Frasnelli E: dfrasnel@alphalinux.org W: http://www.alphalinux.org/ P: 1024/3EF87611 B9 F1 44 50 D3 E8 C2 80 DA E5 55 AA 56 7C 42 DA -D: DEC Alpha hacker +D: DEC Alpha hacker D: Miscellaneous bug squisher N: Jim Freeman @@ -1299,7 +1310,7 @@ S: P.O. Box 76, Epping S: New South Wales, 2121 S: Australia -N: Carlos E. Gorges +N: Carlos E. Gorges E: carlos@techlinux.com.br D: fix smp support on cmpci driver P: 2048G/EA3C4B19 FF31 33A6 0362 4915 B7EB E541 17D0 0379 EA3C 4B19 @@ -1340,7 +1351,7 @@ E: wgreathouse@smva.com E: wgreathouse@myfavoritei.com D: Current Belkin USB Serial Adapter F5U103 hacker D: Kernel hacker, embedded systems -S: 7802 Fitzwater Road +S: 7802 Fitzwater Road S: Brecksville, OH 44141-1334 S: USA @@ -1381,7 +1392,7 @@ N: Grant Guenther E: grant@torque.net W: http://www.torque.net/linux-pp.html D: original author of ppa driver for parallel port ZIP drive -D: original architect of the parallel-port sharing scheme +D: original architect of the parallel-port sharing scheme D: PARIDE subsystem: drivers for parallel port IDE & ATAPI devices S: 44 St. Joseph Street, Suite 506 S: Toronto, Ontario, M4Y 2W4 @@ -1523,7 +1534,7 @@ N: Benjamin Herrenschmidt E: benh@kernel.crashing.org D: Various parts of PPC/PPC64 & PowerMac S: 312/107 Canberra Avenue -S: Griffith, ACT 2603 +S: Griffith, ACT 2603 S: Australia N: Andreas Herrmann @@ -1825,7 +1836,7 @@ S: Hungary N: Bernhard Kaindl E: bkaindl@netway.at E: edv@bartelt.via.at -D: Author of a menu based configuration tool, kmenu, which +D: Author of a menu based configuration tool, kmenu, which D: is the predecessor of 'make menuconfig' and 'make xconfig'. D: digiboard driver update(modularisation work and 2.1.x upd) S: Tallak 95 @@ -2016,7 +2027,7 @@ W: http://www.xos.nl/ D: IP transparent proxy support S: X/OS Experts in Open Systems BV S: Kruislaan 419 -S: 1098 VA Amsterdam +S: 1098 VA Amsterdam S: The Netherlands N: Goran Koruga @@ -2088,7 +2099,7 @@ S: Germany N: Andrzej M. Krzysztofowicz E: ankry@mif.pg.gda.pl -D: Some 8-bit XT disk driver and devfs hacking +D: Some 8-bit XT disk driver and devfs hacking D: Aladdin 1533/1543(C) chipset IDE D: PIIX chipset IDE S: ul. Matemblewska 1B/10 @@ -2463,7 +2474,7 @@ E: mge@EZ-Darmstadt.Telekom.de D: Logical Volume Manager S: Bartningstr. 12 S: 64289 Darmstadt -S: Germany +S: Germany N: Mark W. McClelland E: mmcclell@bigfoot.com @@ -2547,7 +2558,7 @@ E: meskes@debian.org P: 1024/04B6E8F5 6C 77 33 CA CC D6 22 03 AB AB 15 A3 AE AD 39 7D D: Kernel hacker. PostgreSQL hacker. Software watchdog daemon. D: Maintainer of several Debian packages -S: Th.-Heuss-Str. 61 +S: Th.-Heuss-Str. 61 S: D-41812 Erkelenz S: Germany @@ -2785,7 +2796,7 @@ E: neuffer@goofy.zdv.uni-mainz.de W: http://www.i-Connect.Net/~mike/ D: Developer and maintainer of the EATA-DMA SCSI driver D: Co-developer EATA-PIO SCSI driver -D: /proc/scsi and assorted other snippets +D: /proc/scsi and assorted other snippets S: Zum Schiersteiner Grund 2 S: 55127 Mainz S: Germany @@ -2852,6 +2863,10 @@ D: IPX development and support N: Venkatesh Pallipadi (Venki) D: x86/HPET +N: Kyungmin Park +E: kyungmin.park@samsung.com +D: Samsung S5Pv210 and Exynos4210 mobile platforms + N: David Parsons E: orc@pell.chi.il.us D: improved memory detection code. @@ -3019,7 +3034,7 @@ D: Embedded PowerPC 4xx/6xx/7xx/74xx support S: Chandler, Arizona 85249 S: USA -N: Frederic Potter +N: Frederic Potter E: fpotter@cirpack.com D: Some PCI kernel support @@ -3452,21 +3467,21 @@ S: Klosterweg 28 / i309 S: 76131 Karlsruhe S: Germany -N: James Simmons +N: James Simmons E: jsimmons@infradead.org -E: jsimmons@users.sf.net +E: jsimmons@users.sf.net D: Frame buffer device maintainer D: input layer development D: tty/console layer -D: various mipsel devices -S: 115 Carmel Avenue +D: various mipsel devices +S: 115 Carmel Avenue S: El Cerrito CA 94530 -S: USA +S: USA N: Jaspreet Singh E: jaspreet@sangoma.com W: www.sangoma.com -D: WANPIPE drivers & API Support for Sangoma S508/FT1 cards +D: WANPIPE drivers & API Support for Sangoma S508/FT1 cards S: Sangoma Technologies Inc., S: 1001 Denison Street S: Suite 101 @@ -3490,7 +3505,7 @@ N: Craig Small E: csmall@triode.apana.org.au E: vk2xlz@gonzo.vk2xlz.ampr.org (packet radio) D: Gracilis PackeTwin device driver -D: RSPF daemon +D: RSPF daemon S: 10 Stockalls Place S: Minto, NSW, 2566 S: Australia @@ -3700,7 +3715,7 @@ N: Tsu-Sheng Tsao E: tsusheng@scf.usc.edu D: IGMP(Internet Group Management Protocol) version 2 S: 2F 14 ALY 31 LN 166 SEC 1 SHIH-PEI RD -S: Taipei +S: Taipei S: Taiwan 112 S: Republic of China S: 24335 Delta Drive @@ -3861,7 +3876,7 @@ D: Produced the Slackware distribution, updated the SVGAlib D: patches for ghostscript, worked on color 'ls', etc. S: 301 15th Street S. S: Moorhead, Minnesota 56560 -S: USA +S: USA N: Jos Vos E: jos@xos.nl @@ -3869,7 +3884,7 @@ W: http://www.xos.nl/ D: Various IP firewall updates, ipfwadm S: X/OS Experts in Open Systems BV S: Kruislaan 419 -S: 1098 VA Amsterdam +S: 1098 VA Amsterdam S: The Netherlands N: Jeroen Vreeken @@ -4107,7 +4122,7 @@ S: People's Repulic of China N: Victor Yodaiken E: yodaiken@fsmlabs.com D: RTLinux (RealTime Linux) -S: POB 1822 +S: POB 1822 S: Socorro NM, 87801 S: USA @@ -4205,7 +4220,7 @@ D: EISA/sysfs subsystem S: France # Don't add your name here, unless you really _are_ after Marc -# alphabetically. Leonard used to be very proud of being the +# alphabetically. Leonard used to be very proud of being the # last entry, and he'll get positively pissed if he can't even # be second-to-last. (and this file really _is_ supposed to be # in alphabetic order) diff --git a/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 b/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 index a10a4de3e5fe..c4a4497c249a 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 +++ b/Documentation/ABI/testing/sysfs-bus-iio-timer-stm32 @@ -109,30 +109,6 @@ Description: When counting down the counter start from preset value and fire event when reach 0. -What: /sys/bus/iio/devices/iio:deviceX/in_count_quadrature_mode_available -KernelVersion: 4.12 -Contact: benjamin.gaignard@st.com -Description: - Reading returns the list possible quadrature modes. - -What: /sys/bus/iio/devices/iio:deviceX/in_count0_quadrature_mode -KernelVersion: 4.12 -Contact: benjamin.gaignard@st.com -Description: - Configure the device counter quadrature modes: - - channel_A: - Encoder A input servers as the count input and B as - the UP/DOWN direction control input. - - channel_B: - Encoder B input serves as the count input and A as - the UP/DOWN direction control input. - - quadrature: - Encoder A and B inputs are mixed to get direction - and count with a scale of 0.25. - What: /sys/bus/iio/devices/iio:deviceX/in_count_enable_mode_available KernelVersion: 4.12 Contact: benjamin.gaignard@st.com diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst index a22024f9175e..9b90efcc3a35 100644 --- a/Documentation/admin-guide/bootconfig.rst +++ b/Documentation/admin-guide/bootconfig.rst @@ -137,15 +137,24 @@ Boot Kernel With a Boot Config ============================== Since the boot configuration file is loaded with initrd, it will be added -to the end of the initrd (initramfs) image file with size, checksum and -12-byte magic word as below. +to the end of the initrd (initramfs) image file with padding, size, +checksum and 12-byte magic word as below. -[initrd][bootconfig][size(u32)][checksum(u32)][#BOOTCONFIG\n] +[initrd][bootconfig][padding][size(le32)][checksum(le32)][#BOOTCONFIG\n] + +The size and checksum fields are unsigned 32bit little endian value. + +When the boot configuration is added to the initrd image, the total +file size is aligned to 4 bytes. To fill the gap, null characters +(``\0``) will be added. Thus the ``size`` is the length of the bootconfig +file + padding bytes. The Linux kernel decodes the last part of the initrd image in memory to get the boot configuration data. Because of this "piggyback" method, there is no need to change or -update the boot loader and the kernel image itself. +update the boot loader and the kernel image itself as long as the boot +loader passes the correct initrd file size. If by any chance, the boot +loader passes a longer size, the kernel feils to find the bootconfig data. To do this operation, Linux kernel provides "bootconfig" command under tools/bootconfig, which allows admin to apply or delete the config file @@ -176,7 +185,8 @@ up to 512 key-value pairs. If keys contains 3 words in average, it can contain 256 key-value pairs. In most cases, the number of config items will be under 100 entries and smaller than 8KB, so it would be enough. If the node number exceeds 1024, parser returns an error even if the file -size is smaller than 32KB. +size is smaller than 32KB. (Note that this maximum size is not including +the padding null characters.) Anyway, since bootconfig command verifies it when appending a boot config to initrd image, user can notice it before boot. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 526d65d8573a..44fde25bb221 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2858,6 +2858,8 @@ mds=off [X86] tsx_async_abort=off [X86] kvm.nx_huge_pages=off [X86] + no_entry_flush [PPC] + no_uaccess_flush [PPC] Exceptions: This does not have any effect on @@ -3186,6 +3188,8 @@ noefi Disable EFI runtime services support. + no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel. + noexec [IA-64] noexec [X86] @@ -3235,6 +3239,9 @@ nospec_store_bypass_disable [HW] Disable all mitigations for the Speculative Store Bypass vulnerability + no_uaccess_flush + [PPC] Don't flush the L1-D cache after accessing user data. + noxsave [BUGS=X86] Disables x86 extended register state save and restore using xsave. The kernel will fallback to enabling legacy floating-point and sse state. diff --git a/Documentation/dev-tools/kunit/faq.rst b/Documentation/dev-tools/kunit/faq.rst index 1628862e7024..8d5029ad210a 100644 --- a/Documentation/dev-tools/kunit/faq.rst +++ b/Documentation/dev-tools/kunit/faq.rst @@ -90,7 +90,7 @@ things to try. re-run kunit_tool. 5. Try to run ``make ARCH=um defconfig`` before running ``kunit.py run``. This may help clean up any residual config items which could be causing problems. -6. Finally, try running KUnit outside UML. KUnit and KUnit tests can run be +6. Finally, try running KUnit outside UML. KUnit and KUnit tests can be built into any kernel, or can be built as a module and loaded at runtime. Doing so should allow you to determine if UML is causing the issue you're seeing. When tests are built-in, they will execute when the kernel boots, and diff --git a/Documentation/dev-tools/kunit/style.rst b/Documentation/dev-tools/kunit/style.rst index da1d6f0ed6bc..8dbcdc552606 100644 --- a/Documentation/dev-tools/kunit/style.rst +++ b/Documentation/dev-tools/kunit/style.rst @@ -175,17 +175,17 @@ An example Kconfig entry: .. code-block:: none - config FOO_KUNIT_TEST - tristate "KUnit test for foo" if !KUNIT_ALL_TESTS - depends on KUNIT - default KUNIT_ALL_TESTS - help - This builds unit tests for foo. + config FOO_KUNIT_TEST + tristate "KUnit test for foo" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + This builds unit tests for foo. - For more information on KUnit and unit tests in general, please refer - to the KUnit documentation in Documentation/dev-tools/kunit + For more information on KUnit and unit tests in general, please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. - If unsure, say N + If unsure, say N. Test File and Module Names diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst index 62142a47488c..9c28c518e6a3 100644 --- a/Documentation/dev-tools/kunit/usage.rst +++ b/Documentation/dev-tools/kunit/usage.rst @@ -92,7 +92,7 @@ behavior of a function called ``add``; the first parameter is always of type the second parameter, in this case, is what the value is expected to be; the last value is what the value actually is. If ``add`` passes all of these expectations, the test case, ``add_test_basic`` will pass; if any one of these -expectations fail, the test case will fail. +expectations fails, the test case will fail. It is important to understand that a test case *fails* when any expectation is violated; however, the test will continue running, potentially trying other @@ -202,7 +202,7 @@ Example: kunit_test_suite(example_test_suite); In the above example the test suite, ``example_test_suite``, would run the test -cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``, +cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``; each would have ``example_test_init`` called immediately before it and would have ``example_test_exit`` called immediately after it. ``kunit_test_suite(example_test_suite)`` registers the test suite with the @@ -229,7 +229,7 @@ through some sort of indirection where a function is exposed as part of an API such that the definition of that function can be changed without affecting the rest of the code base. In the kernel this primarily comes from two constructs, classes, structs that contain function pointers that are provided by the -implementer, and architecture specific functions which have definitions selected +implementer, and architecture-specific functions which have definitions selected at compile time. Classes @@ -459,7 +459,7 @@ KUnit on non-UML architectures By default KUnit uses UML as a way to provide dependencies for code under test. Under most circumstances KUnit's usage of UML should be treated as an implementation detail of how KUnit works under the hood. Nevertheless, there -are instances where being able to run architecture specific code or test +are instances where being able to run architecture-specific code or test against real hardware is desirable. For these reasons KUnit supports running on other architectures. @@ -599,7 +599,7 @@ writing normal KUnit tests. One special caveat is that you have to reset hardware state in between test cases; if this is not possible, you may only be able to run one test case per invocation. -.. TODO(brendanhiggins@google.com): Add an actual example of an architecture +.. TODO(brendanhiggins@google.com): Add an actual example of an architecture- dependent KUnit test. KUnit debugfs representation diff --git a/Documentation/devicetree/bindings/clock/imx5-clock.yaml b/Documentation/devicetree/bindings/clock/imx5-clock.yaml index 4d9e7c73dce9..90775c2669b8 100644 --- a/Documentation/devicetree/bindings/clock/imx5-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx5-clock.yaml @@ -57,7 +57,7 @@ examples: }; can@53fc8000 { - compatible = "fsl,imx53-flexcan", "fsl,p1010-flexcan"; + compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan"; reg = <0x53fc8000 0x4000>; interrupts = <82>; clocks = <&clks IMX5_CLK_CAN1_IPG_GATE>, <&clks IMX5_CLK_CAN1_SERIAL_GATE>; diff --git a/Documentation/devicetree/bindings/display/brcm,bcm2711-hdmi.yaml b/Documentation/devicetree/bindings/display/brcm,bcm2711-hdmi.yaml index 03a76729d26c..7ce06f9f9f8e 100644 --- a/Documentation/devicetree/bindings/display/brcm,bcm2711-hdmi.yaml +++ b/Documentation/devicetree/bindings/display/brcm,bcm2711-hdmi.yaml @@ -76,6 +76,12 @@ properties: resets: maxItems: 1 + wifi-2.4ghz-coexistence: + type: boolean + description: > + Should the pixel frequencies in the WiFi frequencies range be + avoided? + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml index 43df15ba8fa4..13875eab2ed6 100644 --- a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml +++ b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml @@ -20,8 +20,6 @@ properties: - fsl,imx8qm-flexcan - fsl,imx8mp-flexcan - fsl,imx6q-flexcan - - fsl,imx53-flexcan - - fsl,imx35-flexcan - fsl,imx28-flexcan - fsl,imx25-flexcan - fsl,p1010-flexcan @@ -30,6 +28,11 @@ properties: - fsl,lx2160ar1-flexcan - items: - enum: + - fsl,imx53-flexcan + - fsl,imx35-flexcan + - const: fsl,imx25-flexcan + - items: + - enum: - fsl,imx7d-flexcan - fsl,imx6ul-flexcan - fsl,imx6sx-flexcan @@ -81,11 +84,12 @@ properties: req_bit is the bit offset of CAN stop request. $ref: /schemas/types.yaml#/definitions/phandle-array items: - - description: The 'gpr' is the phandle to general purpose register node. - - description: The 'req_gpr' is the gpr register offset of CAN stop request. - maximum: 0xff - - description: The 'req_bit' is the bit offset of CAN stop request. - maximum: 0x1f + items: + - description: The 'gpr' is the phandle to general purpose register node. + - description: The 'req_gpr' is the gpr register offset of CAN stop request. + maximum: 0xff + - description: The 'req_bit' is the bit offset of CAN stop request. + maximum: 0x1f fsl,clk-source: description: | diff --git a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt index 3613c2c8f75d..0968b40aef1e 100644 --- a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt +++ b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt @@ -33,7 +33,7 @@ tcan4x5x: tcan4x5x@0 { spi-max-frequency = <10000000>; bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>; interrupt-parent = <&gpio1>; - interrupts = <14 GPIO_ACTIVE_LOW>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>; device-state-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; device-wake-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; reset-gpios = <&gpio1 27 GPIO_ACTIVE_HIGH>; diff --git a/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt b/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt index cfaf88998918..9e4dc510a40a 100644 --- a/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt +++ b/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt @@ -25,7 +25,7 @@ Example (for ARM-based BeagleBone with NPC100 NFC controller on I2C2): clock-frequency = <100000>; interrupt-parent = <&gpio1>; - interrupts = <29 GPIO_ACTIVE_HIGH>; + interrupts = <29 IRQ_TYPE_LEVEL_HIGH>; enable-gpios = <&gpio0 30 GPIO_ACTIVE_HIGH>; firmware-gpios = <&gpio0 31 GPIO_ACTIVE_HIGH>; diff --git a/Documentation/devicetree/bindings/net/nfc/pn544.txt b/Documentation/devicetree/bindings/net/nfc/pn544.txt index 92f399ec22b8..2bd82562ce8e 100644 --- a/Documentation/devicetree/bindings/net/nfc/pn544.txt +++ b/Documentation/devicetree/bindings/net/nfc/pn544.txt @@ -25,7 +25,7 @@ Example (for ARM-based BeagleBone with PN544 on I2C2): clock-frequency = <400000>; interrupt-parent = <&gpio1>; - interrupts = <17 GPIO_ACTIVE_HIGH>; + interrupts = <17 IRQ_TYPE_LEVEL_HIGH>; enable-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; firmware-gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>; diff --git a/Documentation/devicetree/bindings/sound/rt1015.txt b/Documentation/devicetree/bindings/sound/rt1015.txt index fcfd02d8d32f..e498966d436f 100644 --- a/Documentation/devicetree/bindings/sound/rt1015.txt +++ b/Documentation/devicetree/bindings/sound/rt1015.txt @@ -8,10 +8,16 @@ Required properties: - reg : The I2C address of the device. +Optional properties: + +- realtek,power-up-delay-ms + Set a delay time for flush work to be completed, + this value is adjustable depending on platform. Example: rt1015: codec@28 { compatible = "realtek,rt1015"; reg = <0x28>; + realtek,power-up-delay-ms = <50>; }; diff --git a/Documentation/driver-api/media/drivers/vidtv.rst b/Documentation/driver-api/media/drivers/vidtv.rst index 65115448c52d..673bdff919ea 100644 --- a/Documentation/driver-api/media/drivers/vidtv.rst +++ b/Documentation/driver-api/media/drivers/vidtv.rst @@ -149,11 +149,11 @@ vidtv_psi.[ch] Because the generator is implemented in a separate file, it can be reused elsewhere in the media subsystem. - Currently vidtv supports working with 3 PSI tables: PAT, PMT and - SDT. + Currently vidtv supports working with 5 PSI tables: PAT, PMT, + SDT, NIT and EIT. The specification for PAT and PMT can be found in *ISO 13818-1: - Systems*, while the specification for the SDT can be found in *ETSI + Systems*, while the specification for the SDT, NIT, EIT can be found in *ETSI EN 300 468: Specification for Service Information (SI) in DVB systems*. @@ -197,6 +197,8 @@ vidtv_channel.[ch] #. Their programs will be concatenated to populate the PAT + #. Their events will be concatenated to populate the EIT + #. For each program in the PAT, a PMT section will be created #. The PMT section for a channel will be assigned its streams. @@ -256,6 +258,42 @@ Using dvb-fe-tool The first step to check whether the demod loaded successfully is to run:: $ dvb-fe-tool + Device Dummy demod for DVB-T/T2/C/S/S2 (/dev/dvb/adapter0/frontend0) capabilities: + CAN_FEC_1_2 + CAN_FEC_2_3 + CAN_FEC_3_4 + CAN_FEC_4_5 + CAN_FEC_5_6 + CAN_FEC_6_7 + CAN_FEC_7_8 + CAN_FEC_8_9 + CAN_FEC_AUTO + CAN_GUARD_INTERVAL_AUTO + CAN_HIERARCHY_AUTO + CAN_INVERSION_AUTO + CAN_QAM_16 + CAN_QAM_32 + CAN_QAM_64 + CAN_QAM_128 + CAN_QAM_256 + CAN_QAM_AUTO + CAN_QPSK + CAN_TRANSMISSION_MODE_AUTO + DVB API Version 5.11, Current v5 delivery system: DVBC/ANNEX_A + Supported delivery systems: + DVBT + DVBT2 + [DVBC/ANNEX_A] + DVBS + DVBS2 + Frequency range for the current standard: + From: 51.0 MHz + To: 2.15 GHz + Step: 62.5 kHz + Tolerance: 29.5 MHz + Symbol rate ranges for the current standard: + From: 1.00 MBauds + To: 45.0 MBauds This should return what is currently set up at the demod struct, i.e.:: @@ -314,7 +352,7 @@ For this, one should provide a configuration file known as a 'scan file', here's an example:: [Channel] - FREQUENCY = 330000000 + FREQUENCY = 474000000 MODULATION = QAM/AUTO SYMBOL_RATE = 6940000 INNER_FEC = AUTO @@ -335,6 +373,14 @@ You can browse scan tables online here: `dvb-scan-tables Assuming this channel is named 'channel.conf', you can then run:: $ dvbv5-scan channel.conf + dvbv5-scan ~/vidtv.conf + ERROR command BANDWIDTH_HZ (5) not found during retrieve + Cannot calc frequency shift. Either bandwidth/symbol-rate is unavailable (yet). + Scanning frequency #1 330000000 + (0x00) Signal= -68.00dBm + Scanning frequency #2 474000000 + Lock (0x1f) Signal= -34.45dBm C/N= 33.74dB UCB= 0 + Service Beethoven, provider LinuxTV.org: digital television For more information on dvb-scan, check its documentation online here: `dvb-scan Documentation <https://www.linuxtv.org/wiki/index.php/Dvbscan>`_. @@ -344,23 +390,38 @@ Using dvb-zap dvbv5-zap is a command line tool that can be used to record MPEG-TS to disk. The typical use is to tune into a channel and put it into record mode. The example -below - which is taken from the documentation - illustrates that:: +below - which is taken from the documentation - illustrates that\ [1]_:: - $ dvbv5-zap -c dvb_channel.conf "trilhas sonoras" -r - using demux '/dev/dvb/adapter0/demux0' + $ dvbv5-zap -c dvb_channel.conf "beethoven" -o music.ts -P -t 10 + using demux 'dvb0.demux0' reading channels from file 'dvb_channel.conf' - service has pid type 05: 204 - tuning to 573000000 Hz - audio pid 104 - dvb_set_pesfilter 104 - Lock (0x1f) Quality= Good Signal= 100.00% C/N= -13.80dB UCB= 70 postBER= 3.14x10^-3 PER= 0 - DVR interface '/dev/dvb/adapter0/dvr0' can now be opened + tuning to 474000000 Hz + pass all PID's to TS + dvb_set_pesfilter 8192 + dvb_dev_set_bufsize: buffer set to 6160384 + Lock (0x1f) Quality= Good Signal= -34.66dBm C/N= 33.41dB UCB= 0 postBER= 0 preBER= 1.05x10^-3 PER= 0 + Lock (0x1f) Quality= Good Signal= -34.57dBm C/N= 33.46dB UCB= 0 postBER= 0 preBER= 1.05x10^-3 PER= 0 + Record to file 'music.ts' started + received 24587768 bytes (2401 Kbytes/sec) + Lock (0x1f) Quality= Good Signal= -34.42dBm C/N= 33.89dB UCB= 0 postBER= 0 preBER= 2.44x10^-3 PER= 0 + +.. [1] In this example, it records 10 seconds with all program ID's stored + at the music.ts file. + -The channel can be watched by playing the contents of the DVR interface, with -some player that recognizes the MPEG-TS format, such as *mplayer* or *vlc*. +The channel can be watched by playing the contents of the stream with some +player that recognizes the MPEG-TS format, such as ``mplayer`` or ``vlc``. By playing the contents of the stream one can visually inspect the workings of -vidtv, e.g.:: +vidtv, e.g., to play a recorded TS file with:: + + $ mplayer music.ts + +or, alternatively, running this command on one terminal:: + + $ dvbv5-zap -c dvb_channel.conf "beethoven" -P -r & + +And, on a second terminal, playing the contents from DVR interface with:: $ mplayer /dev/dvb/adapter0/dvr0 @@ -423,3 +484,30 @@ A nice addition is to simulate some noise when the signal quality is bad by: - Updating the error statistics accordingly (e.g. BER, etc). - Simulating some noise in the encoded data. + +Functions and structs used within vidtv +--------------------------------------- + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_bridge.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_channel.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_demod.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_encoder.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_mux.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_pes.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_psi.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_s302m.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_ts.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_tuner.h + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_common.c + +.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_tuner.c diff --git a/Documentation/filesystems/ext4/journal.rst b/Documentation/filesystems/ext4/journal.rst index 805a1e9ea3a5..849d5b119eb8 100644 --- a/Documentation/filesystems/ext4/journal.rst +++ b/Documentation/filesystems/ext4/journal.rst @@ -256,6 +256,10 @@ which is 1024 bytes long: - s\_padding2 - * - 0x54 + - \_\_be32 + - s\_num\_fc\_blocks + - Number of fast commit blocks in the journal. + * - 0x58 - \_\_u32 - s\_padding[42] - @@ -310,6 +314,8 @@ The journal incompat features are any combination of the following: - This journal uses v3 of the checksum on-disk format. This is the same as v2, but the journal block tag size is fixed regardless of the size of block numbers. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3) + * - 0x20 + - Journal has fast commit blocks. (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) .. _jbd2_checksum_type: diff --git a/Documentation/filesystems/ext4/super.rst b/Documentation/filesystems/ext4/super.rst index 93e55d7c1d40..2eb1ab20498d 100644 --- a/Documentation/filesystems/ext4/super.rst +++ b/Documentation/filesystems/ext4/super.rst @@ -596,6 +596,13 @@ following: - Sparse Super Block, v2. If this flag is set, the SB field s\_backup\_bgs points to the two block groups that contain backup superblocks (COMPAT\_SPARSE\_SUPER2). + * - 0x400 + - Fast commits supported. Although fast commits blocks are + backward incompatible, fast commit blocks are not always + present in the journal. If fast commit blocks are present in + the journal, JBD2 incompat feature + (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) gets + set (COMPAT\_FAST\_COMMIT). .. _super_incompat: diff --git a/Documentation/filesystems/journalling.rst b/Documentation/filesystems/journalling.rst index 5a5f70b4063e..e18f90ffc6fd 100644 --- a/Documentation/filesystems/journalling.rst +++ b/Documentation/filesystems/journalling.rst @@ -136,10 +136,8 @@ Fast commits ~~~~~~~~~~~~ JBD2 to also allows you to perform file-system specific delta commits known as -fast commits. In order to use fast commits, you first need to call -:c:func:`jbd2_fc_init` and tell how many blocks at the end of journal -area should be reserved for fast commits. Along with that, you will also need -to set following callbacks that perform correspodning work: +fast commits. In order to use fast commits, you will need to set following +callbacks that perform correspodning work: `journal->j_fc_cleanup_cb`: Cleanup function called after every full commit and fast commit. diff --git a/Documentation/firmware-guide/acpi/acpi-lid.rst b/Documentation/firmware-guide/acpi/acpi-lid.rst index 874ce0ed340d..71b9af13a048 100644 --- a/Documentation/firmware-guide/acpi/acpi-lid.rst +++ b/Documentation/firmware-guide/acpi/acpi-lid.rst @@ -19,9 +19,9 @@ report the "current" state of the lid as either "opened" or "closed". For most platforms, both the _LID method and the lid notifications are reliable. However, there are exceptions. In order to work with these -exceptional buggy platforms, special restrictions and expections should be +exceptional buggy platforms, special restrictions and exceptions should be taken into account. This document describes the restrictions and the -expections of the Linux ACPI lid device driver. +exceptions of the Linux ACPI lid device driver. Restrictions of the returning value of the _LID control method @@ -46,7 +46,7 @@ state is changed to "closed". The "closed" notification is normally used to trigger some system power saving operations on Windows. Since it is fully tested, it is reliable from all AML tables. -Expections for the userspace users of the ACPI lid device driver +Exceptions for the userspace users of the ACPI lid device driver ================================================================ The ACPI button driver exports the lid state to the userspace via the @@ -100,7 +100,7 @@ use the following kernel parameter: C. button.lid_init_state=ignore: When this option is specified, the ACPI button driver never reports the initial lid state and there is a compensation mechanism implemented to - ensure that the reliable "closed" notifications can always be delievered + ensure that the reliable "closed" notifications can always be delivered to the userspace by always pairing "closed" input events with complement "opened" input events. But there is still no guarantee that the "opened" notifications can be delivered to the userspace when the lid is actually diff --git a/Documentation/firmware-guide/acpi/gpio-properties.rst b/Documentation/firmware-guide/acpi/gpio-properties.rst index bb6d74f23ee0..59aad6138b6e 100644 --- a/Documentation/firmware-guide/acpi/gpio-properties.rst +++ b/Documentation/firmware-guide/acpi/gpio-properties.rst @@ -20,9 +20,9 @@ index, like the ASL example below shows:: Name (_CRS, ResourceTemplate () { - GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionInputOnly, + GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionOutputOnly, "\\_SB.GPO0", 0, ResourceConsumer) {15} - GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionInputOnly, + GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionOutputOnly, "\\_SB.GPO0", 0, ResourceConsumer) {27, 31} }) @@ -49,15 +49,41 @@ index pin Pin in the GpioIo()/GpioInt() resource. Typically this is zero. active_low - If 1 the GPIO is marked as active_low. + If 1, the GPIO is marked as active_low. Since ACPI GpioIo() resource does not have a field saying whether it is active low or high, the "active_low" argument can be used here. Setting it to 1 marks the GPIO as active low. +Note, active_low in _DSD does not make sense for GpioInt() resource and +must be 0. GpioInt() resource has its own means of defining it. + In our Bluetooth example the "reset-gpios" refers to the second GpioIo() resource, second pin in that resource with the GPIO number of 31. +The GpioIo() resource unfortunately doesn't explicitly provide an initial +state of the output pin which driver should use during its initialization. + +Linux tries to use common sense here and derives the state from the bias +and polarity settings. The table below shows the expectations: + +========= ============= ============== +Pull Bias Polarity Requested... +========= ============= ============== +Implicit x AS IS (assumed firmware configured for us) +Explicit x (no _DSD) as Pull Bias (Up == High, Down == Low), + assuming non-active (Polarity = !Pull Bias) +Down Low as low, assuming active +Down High as low, assuming non-active +Up Low as high, assuming non-active +Up High as high, assuming active +========= ============= ============== + +That said, for our above example the both GPIOs, since the bias setting +is explicit and _DSD is present, will be treated as active with a high +polarity and Linux will configure the pins in this state until a driver +reprograms them differently. + It is possible to leave holes in the array of GPIOs. This is useful in cases like with SPI host controllers where some chip selects may be implemented as GPIOs and some as native signals. For example a SPI host @@ -112,8 +138,8 @@ Example:: Package () { "gpio-line-names", Package () { - "SPI0_CS_N", "EXP2_INT", "MUX6_IO", "UART0_RXD", "MUX7_IO", - "LVL_C_A1", "MUX0_IO", "SPI1_MISO" + "SPI0_CS_N", "EXP2_INT", "MUX6_IO", "UART0_RXD", + "MUX7_IO", "LVL_C_A1", "MUX0_IO", "SPI1_MISO", } } @@ -137,7 +163,7 @@ to the GPIO lines it is going to use and provide the GPIO subsystem with a mapping between those names and the ACPI GPIO resources corresponding to them. To do that, the driver needs to define a mapping table as a NULL-terminated -array of struct acpi_gpio_mapping objects that each contain a name, a pointer +array of struct acpi_gpio_mapping objects that each contains a name, a pointer to an array of line data (struct acpi_gpio_params) objects and the size of that array. Each struct acpi_gpio_params object consists of three fields, crs_entry_index, line_index, active_low, representing the index of the target @@ -154,13 +180,14 @@ question would look like this:: static const struct acpi_gpio_mapping bluetooth_acpi_gpios[] = { { "reset-gpios", &reset_gpio, 1 }, { "shutdown-gpios", &shutdown_gpio, 1 }, - { }, + { } }; Next, the mapping table needs to be passed as the second argument to -acpi_dev_add_driver_gpios() that will register it with the ACPI device object -pointed to by its first argument. That should be done in the driver's .probe() -routine. On removal, the driver should unregister its GPIO mapping table by +acpi_dev_add_driver_gpios() or its managed analogue that will +register it with the ACPI device object pointed to by its first +argument. That should be done in the driver's .probe() routine. +On removal, the driver should unregister its GPIO mapping table by calling acpi_dev_remove_driver_gpios() on the ACPI device object where that table was previously registered. @@ -191,12 +218,12 @@ The driver might expect to get the right GPIO when it does:: but since there is no way to know the mapping between "reset" and the GpioIo() in _CRS desc will hold ERR_PTR(-ENOENT). -The driver author can solve this by passing the mapping explictly -(the recommended way and documented in the above chapter). +The driver author can solve this by passing the mapping explicitly +(this is the recommended way and it's documented in the above chapter). The ACPI GPIO mapping tables should not contaminate drivers that are not knowing about which exact device they are servicing on. It implies that -the ACPI GPIO mapping tables are hardly linked to ACPI ID and certain +the ACPI GPIO mapping tables are hardly linked to an ACPI ID and certain objects, as listed in the above chapter, of the device in question. Getting GPIO descriptor @@ -229,5 +256,5 @@ Case 2 explicitly tells GPIO core to look for resources in _CRS. Be aware that gpiod_get_index() in cases 1 and 2, assuming that there are two versions of ACPI device description provided and no mapping is present in the driver, will return different resources. That's why a -certain driver has to handle them carefully as explained in previous +certain driver has to handle them carefully as explained in the previous chapter. diff --git a/Documentation/firmware-guide/acpi/method-tracing.rst b/Documentation/firmware-guide/acpi/method-tracing.rst index 0aa7e2c5d32a..6ab6c0964042 100644 --- a/Documentation/firmware-guide/acpi/method-tracing.rst +++ b/Documentation/firmware-guide/acpi/method-tracing.rst @@ -98,7 +98,7 @@ subject to change:: [ 0.188903] exdebug-0398 ex_trace_point : Method End [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution. Developers can utilize these special log entries to track the AML -interpretion, thus can aid issue debugging and performance tuning. Note +interpretation, thus can aid issue debugging and performance tuning. Note that, as the "AML tracer" logs are implemented via ACPI_DEBUG_PRINT() macro, CONFIG_ACPI_DEBUG is also required to be enabled for enabling "AML tracer" logs. diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst index cf3ca236d2cc..21c847890d03 100644 --- a/Documentation/kbuild/llvm.rst +++ b/Documentation/kbuild/llvm.rst @@ -57,9 +57,8 @@ to enable them. :: They can be enabled individually. The full list of the parameters: :: make CC=clang LD=ld.lld AR=llvm-ar NM=llvm-nm STRIP=llvm-strip \ - OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump OBJSIZE=llvm-size \ - READELF=llvm-readelf HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar \ - HOSTLD=ld.lld + OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump READELF=llvm-readelf \ + HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar HOSTLD=ld.lld Currently, the integrated assembler is disabled by default. You can pass ``LLVM_IAS=1`` to enable it. diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst index d5c9320901c3..4b9ed5874d5a 100644 --- a/Documentation/networking/netdev-FAQ.rst +++ b/Documentation/networking/netdev-FAQ.rst @@ -110,7 +110,7 @@ Q: I sent a patch and I'm wondering what happened to it? Q: How can I tell whether it got merged? A: Start by looking at the main patchworks queue for netdev: - http://patchwork.ozlabs.org/project/netdev/list/ + https://patchwork.kernel.org/project/netdevbpf/list/ The "State" field will tell you exactly where things are at with your patch. @@ -152,7 +152,7 @@ networking subsystem, and then hands them off to Greg. There is a patchworks queue that you can see here: - http://patchwork.ozlabs.org/bundle/davem/stable/?state=* + https://patchwork.kernel.org/bundle/netdev/stable/?state=* It contains the patches which Dave has selected, but not yet handed off to Greg. If Greg already has the patch, then it will be here: @@ -254,6 +254,32 @@ you will have done run-time testing specific to your change, but at a minimum, your changes should survive an ``allyesconfig`` and an ``allmodconfig`` build without new warnings or failures. +Q: How do I post corresponding changes to user space components? +---------------------------------------------------------------- +A: User space code exercising kernel features should be posted +alongside kernel patches. This gives reviewers a chance to see +how any new interface is used and how well it works. + +When user space tools reside in the kernel repo itself all changes +should generally come as one series. If series becomes too large +or the user space project is not reviewed on netdev include a link +to a public repo where user space patches can be seen. + +In case user space tooling lives in a separate repository but is +reviewed on netdev (e.g. patches to `iproute2` tools) kernel and +user space patches should form separate series (threads) when posted +to the mailing list, e.g.:: + + [PATCH net-next 0/3] net: some feature cover letter + └─ [PATCH net-next 1/3] net: some feature prep + └─ [PATCH net-next 2/3] net: some feature do it + └─ [PATCH net-next 3/3] selftest: net: some feature + + [PATCH iproute2-next] ip: add support for some feature + +Posting as one thread is discouraged because it confuses patchwork +(as of patchwork 2.2.2). + Q: Any other tips to help ensure my net/net-next patch gets OK'd? ----------------------------------------------------------------- A: Attention to detail. Re-read your own work as if you were the diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index 256106054c8c..b2f7ec794bc8 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -247,8 +247,8 @@ Some of the interface modes are described below: speeds (see below.) ``PHY_INTERFACE_MODE_2500BASEX`` - This defines a variant of 1000BASE-X which is clocked 2.5 times faster, - than the 802.3 standard giving a fixed bit rate of 3.125Gbaud. + This defines a variant of 1000BASE-X which is clocked 2.5 times as fast + as the 802.3 standard, giving a fixed bit rate of 3.125Gbaud. ``PHY_INTERFACE_MODE_SGMII`` This is used for Cisco SGMII, which is a modification of 1000BASE-X diff --git a/Documentation/process/stable-kernel-rules.rst b/Documentation/process/stable-kernel-rules.rst index 06f743b612c4..3973556250e1 100644 --- a/Documentation/process/stable-kernel-rules.rst +++ b/Documentation/process/stable-kernel-rules.rst @@ -39,7 +39,7 @@ Procedure for submitting patches to the -stable tree submission guidelines as described in :ref:`Documentation/networking/netdev-FAQ.rst <netdev-FAQ>` after first checking the stable networking queue at - https://patchwork.ozlabs.org/bundle/davem/stable/?series=&submitter=&state=*&q=&archive= + https://patchwork.kernel.org/bundle/netdev/stable/?state=* to ensure the requested patch is not already queued up. - Security patches should not be handled (solely) by the -stable review process but should follow the procedures in diff --git a/Documentation/translations/it_IT/process/stable-kernel-rules.rst b/Documentation/translations/it_IT/process/stable-kernel-rules.rst index 4f206cee31a7..283d62541c4f 100644 --- a/Documentation/translations/it_IT/process/stable-kernel-rules.rst +++ b/Documentation/translations/it_IT/process/stable-kernel-rules.rst @@ -46,7 +46,7 @@ Procedura per sottomettere patch per i sorgenti -stable :ref:`Documentation/translations/it_IT/networking/netdev-FAQ.rst <it_netdev-FAQ>`; ma solo dopo aver verificato al seguente indirizzo che la patch non sia già in coda: - https://patchwork.ozlabs.org/bundle/davem/stable/?series=&submitter=&state=*&q=&archive= + https://patchwork.kernel.org/bundle/netdev/stable/?state=* - Una patch di sicurezza non dovrebbero essere gestite (solamente) dal processo di revisione -stable, ma dovrebbe seguire le procedure descritte in :ref:`Documentation/translations/it_IT/admin-guide/security-bugs.rst <it_securitybugs>`. diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 36d5f1f3c6dd..e00a66d72372 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6367,7 +6367,7 @@ accesses that would usually trigger a #GP by KVM into the guest will instead get bounced to user space through the KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exit notifications. -8.25 KVM_X86_SET_MSR_FILTER +8.27 KVM_X86_SET_MSR_FILTER --------------------------- :Architectures: x86 @@ -6381,8 +6381,7 @@ In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to trap and emulate MSRs that are outside of the scope of KVM as well as limit the attack surface on KVM's MSR emulation code. - -8.26 KVM_CAP_ENFORCE_PV_CPUID +8.28 KVM_CAP_ENFORCE_PV_CPUID ----------------------------- Architectures: x86 diff --git a/Documentation/virt/kvm/mmu.rst b/Documentation/virt/kvm/mmu.rst index 1c030dbac7c4..5bfe28b0728e 100644 --- a/Documentation/virt/kvm/mmu.rst +++ b/Documentation/virt/kvm/mmu.rst @@ -455,7 +455,7 @@ If the generation number of the spte does not equal the global generation number, it will ignore the cached MMIO information and handle the page fault through the slow path. -Since only 19 bits are used to store generation-number on mmio spte, all +Since only 18 bits are used to store generation-number on mmio spte, all pages are zapped when there is an overflow. Unfortunately, a single memory access might access kvm_memslots(kvm) multiple diff --git a/Documentation/xtensa/mmu.rst b/Documentation/xtensa/mmu.rst index e52a12960fdc..450573afa31a 100644 --- a/Documentation/xtensa/mmu.rst +++ b/Documentation/xtensa/mmu.rst @@ -82,7 +82,8 @@ Default MMUv2-compatible layout:: +------------------+ | VMALLOC area | VMALLOC_START 0xc0000000 128MB - 64KB +------------------+ VMALLOC_END - | Cache aliasing | TLBTEMP_BASE_1 0xc7ff0000 DCACHE_WAY_SIZE + +------------------+ + | Cache aliasing | TLBTEMP_BASE_1 0xc8000000 DCACHE_WAY_SIZE | remap area 1 | +------------------+ | Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE @@ -124,7 +125,8 @@ Default MMUv2-compatible layout:: +------------------+ | VMALLOC area | VMALLOC_START 0xa0000000 128MB - 64KB +------------------+ VMALLOC_END - | Cache aliasing | TLBTEMP_BASE_1 0xa7ff0000 DCACHE_WAY_SIZE + +------------------+ + | Cache aliasing | TLBTEMP_BASE_1 0xa8000000 DCACHE_WAY_SIZE | remap area 1 | +------------------+ | Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE @@ -167,7 +169,8 @@ Default MMUv2-compatible layout:: +------------------+ | VMALLOC area | VMALLOC_START 0x90000000 128MB - 64KB +------------------+ VMALLOC_END - | Cache aliasing | TLBTEMP_BASE_1 0x97ff0000 DCACHE_WAY_SIZE + +------------------+ + | Cache aliasing | TLBTEMP_BASE_1 0x98000000 DCACHE_WAY_SIZE | remap area 1 | +------------------+ | Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE diff --git a/MAINTAINERS b/MAINTAINERS index 3da6d8c154e4..281de213ef47 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1279,7 +1279,7 @@ M: Igor Russkikh <irusskikh@marvell.com> L: netdev@vger.kernel.org S: Supported W: https://www.marvell.com/ -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst F: drivers/net/ethernet/aquantia/atlantic/ @@ -1486,10 +1486,20 @@ F: Documentation/devicetree/bindings/iommu/arm,smmu* F: drivers/iommu/arm/ F: drivers/iommu/io-pgtable-arm* +ARM AND ARM64 SoC SUB-ARCHITECTURES (COMMON PARTS) +M: Arnd Bergmann <arnd@arndb.de> +M: Olof Johansson <olof@lixom.net> +M: soc@kernel.org +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc.git +F: arch/arm/boot/dts/Makefile +F: arch/arm64/boot/dts/Makefile + ARM SUB-ARCHITECTURES L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc.git F: arch/arm/mach-*/ F: arch/arm/plat-*/ @@ -1546,6 +1556,7 @@ F: drivers/clk/sunxi/ ARM/Allwinner sunXi SoC support M: Maxime Ripard <mripard@kernel.org> M: Chen-Yu Tsai <wens@csie.org> +R: Jernej Skrabec <jernej.skrabec@siol.net> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git @@ -1723,11 +1734,13 @@ F: arch/arm/mach-ep93xx/micro9.c ARM/CORESIGHT FRAMEWORK AND DRIVERS M: Mathieu Poirier <mathieu.poirier@linaro.org> -R: Suzuki K Poulose <suzuki.poulose@arm.com> +M: Suzuki K Poulose <suzuki.poulose@arm.com> R: Mike Leach <mike.leach@linaro.org> +R: Leo Yan <leo.yan@linaro.org> L: coresight@lists.linaro.org (moderated for non-subscribers) L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/coresight/linux.git F: Documentation/ABI/testing/sysfs-bus-coresight-devices-* F: Documentation/devicetree/bindings/arm/coresight-cpu-debug.txt F: Documentation/devicetree/bindings/arm/coresight-cti.yaml @@ -1994,7 +2007,6 @@ N: lpc18xx ARM/LPC32XX SOC SUPPORT M: Vladimir Zapolskiy <vz@mleia.com> -M: Sylvain Lemieux <slemieux.tyco@gmail.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://github.com/vzapolskiy/linux-lpc32xx.git @@ -2012,7 +2024,6 @@ M: Philipp Zabel <philipp.zabel@gmail.com> S: Maintained ARM/Marvell Dove/MV78xx0/Orion SOC support -M: Jason Cooper <jason@lakedaemon.net> M: Andrew Lunn <andrew@lunn.ch> M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> M: Gregory Clement <gregory.clement@bootlin.com> @@ -2029,7 +2040,6 @@ F: arch/arm/plat-orion/ F: drivers/soc/dove/ ARM/Marvell Kirkwood and Armada 370, 375, 38x, 39x, XP, 3700, 7K/8K, CN9130 SOC support -M: Jason Cooper <jason@lakedaemon.net> M: Andrew Lunn <andrew@lunn.ch> M: Gregory Clement <gregory.clement@bootlin.com> M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> @@ -2374,7 +2384,7 @@ F: drivers/i2c/busses/i2c-rk3x.c F: sound/soc/rockchip/ N: rockchip -ARM/SAMSUNG EXYNOS ARM ARCHITECTURES +ARM/SAMSUNG S3C, S5P AND EXYNOS ARM ARCHITECTURES M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org @@ -2403,15 +2413,7 @@ N: s3c2410 N: s3c64xx N: s5pv210 -ARM/SAMSUNG MOBILE MACHINE SUPPORT -M: Kyungmin Park <kyungmin.park@samsung.com> -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained -F: arch/arm/mach-s5pv210/ - ARM/SAMSUNG S5P SERIES 2D GRAPHICS ACCELERATION (G2D) SUPPORT -M: Kyungmin Park <kyungmin.park@samsung.com> -M: Kamil Debski <kamil@wypas.org> M: Andrzej Hajda <a.hajda@samsung.com> L: linux-arm-kernel@lists.infradead.org L: linux-media@vger.kernel.org @@ -2436,9 +2438,6 @@ S: Maintained F: drivers/media/platform/s5p-jpeg/ ARM/SAMSUNG S5P SERIES Multi Format Codec (MFC) SUPPORT -M: Kyungmin Park <kyungmin.park@samsung.com> -M: Kamil Debski <kamil@wypas.org> -M: Jeongtae Park <jtp.park@samsung.com> M: Andrzej Hajda <a.hajda@samsung.com> L: linux-arm-kernel@lists.infradead.org L: linux-media@vger.kernel.org @@ -3243,12 +3242,12 @@ F: drivers/iio/accel/bma400* BPF (Safe dynamic programs and tools) M: Alexei Starovoitov <ast@kernel.org> M: Daniel Borkmann <daniel@iogearbox.net> +M: Andrii Nakryiko <andrii@kernel.org> R: Martin KaFai Lau <kafai@fb.com> R: Song Liu <songliubraving@fb.com> R: Yonghong Song <yhs@fb.com> -R: Andrii Nakryiko <andrii@kernel.org> R: John Fastabend <john.fastabend@gmail.com> -R: KP Singh <kpsingh@chromium.org> +R: KP Singh <kpsingh@kernel.org> L: netdev@vger.kernel.org L: bpf@vger.kernel.org S: Supported @@ -3366,6 +3365,17 @@ S: Supported F: arch/x86/net/ X: arch/x86/net/bpf_jit_comp32.c +BPF LSM (Security Audit and Enforcement using BPF) +M: KP Singh <kpsingh@kernel.org> +R: Florent Revest <revest@chromium.org> +R: Brendan Jackman <jackmanb@chromium.org> +L: bpf@vger.kernel.org +S: Maintained +F: Documentation/bpf/bpf_lsm.rst +F: include/linux/bpf_lsm.h +F: kernel/bpf/bpf_lsm.c +F: security/bpf/ + BROADCOM B44 10/100 ETHERNET DRIVER M: Michael Chan <michael.chan@broadcom.com> L: netdev@vger.kernel.org @@ -3538,11 +3548,12 @@ BROADCOM BRCM80211 IEEE802.11n WIRELESS DRIVER M: Arend van Spriel <arend.vanspriel@broadcom.com> M: Franky Lin <franky.lin@broadcom.com> M: Hante Meuleman <hante.meuleman@broadcom.com> -M: Chi-Hsien Lin <chi-hsien.lin@cypress.com> -M: Wright Feng <wright.feng@cypress.com> +M: Chi-hsien Lin <chi-hsien.lin@infineon.com> +M: Wright Feng <wright.feng@infineon.com> +M: Chung-hsien Hsu <chung-hsien.hsu@infineon.com> L: linux-wireless@vger.kernel.org L: brcm80211-dev-list.pdl@broadcom.com -L: brcm80211-dev-list@cypress.com +L: SHA-cyfmac-dev-list@infineon.com S: Supported F: drivers/net/wireless/broadcom/brcm80211/ @@ -4284,6 +4295,7 @@ B: https://github.com/ClangBuiltLinux/linux/issues C: irc://chat.freenode.net/clangbuiltlinux F: Documentation/kbuild/llvm.rst F: scripts/clang-tools/ +F: scripts/lld-version.sh K: \b(?i:clang|llvm)\b CLEANCACHE API @@ -4710,7 +4722,7 @@ T: git git://linuxtv.org/anttip/media_tree.git F: drivers/media/dvb-frontends/cxd2820r* CXGB3 ETHERNET DRIVER (CXGB3) -M: Vishal Kulkarni <vishal@chelsio.com> +M: Raju Rangoju <rajur@chelsio.com> L: netdev@vger.kernel.org S: Supported W: http://www.chelsio.com @@ -4742,7 +4754,7 @@ W: http://www.chelsio.com F: drivers/net/ethernet/chelsio/inline_crypto/ CXGB4 ETHERNET DRIVER (CXGB4) -M: Vishal Kulkarni <vishal@chelsio.com> +M: Raju Rangoju <rajur@chelsio.com> L: netdev@vger.kernel.org S: Supported W: http://www.chelsio.com @@ -4764,7 +4776,7 @@ F: drivers/infiniband/hw/cxgb4/ F: include/uapi/rdma/cxgb4-abi.h CXGB4VF ETHERNET DRIVER (CXGB4VF) -M: Vishal Kulkarni <vishal@gmail.com> +M: Raju Rangoju <rajur@chelsio.com> L: netdev@vger.kernel.org S: Supported W: http://www.chelsio.com @@ -6614,6 +6626,7 @@ Q: http://patchwork.ozlabs.org/project/linux-ext4/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4.git F: Documentation/filesystems/ext4/ F: fs/ext4/ +F: include/trace/events/ext4.h Extended Verification Module (EVM) M: Mimi Zohar <zohar@linux.ibm.com> @@ -8829,8 +8842,8 @@ S: Supported W: http://www.intel.com/support/feedback.htm W: http://e1000.sourceforge.net/ Q: http://patchwork.ozlabs.org/project/intel-wired-lan/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue.git F: Documentation/networking/device_drivers/ethernet/intel/ F: drivers/net/ethernet/intel/ F: drivers/net/ethernet/intel/*/ @@ -9076,10 +9089,7 @@ S: Supported F: drivers/net/wireless/intel/iwlegacy/ INTEL WIRELESS WIFI LINK (iwlwifi) -M: Johannes Berg <johannes.berg@intel.com> -M: Emmanuel Grumbach <emmanuel.grumbach@intel.com> M: Luca Coelho <luciano.coelho@intel.com> -M: Intel Linux Wireless <linuxwifi@intel.com> L: linux-wireless@vger.kernel.org S: Supported W: https://wireless.wiki.kernel.org/en/users/drivers/iwlwifi @@ -9171,6 +9181,7 @@ F: include/linux/iomap.h IOMMU DRIVERS M: Joerg Roedel <joro@8bytes.org> +M: Will Deacon <will@kernel.org> L: iommu@lists.linux-foundation.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git @@ -9254,7 +9265,6 @@ F: kernel/irq/ IRQCHIP DRIVERS M: Thomas Gleixner <tglx@linutronix.de> -M: Jason Cooper <jason@lakedaemon.net> M: Marc Zyngier <maz@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained @@ -9654,6 +9664,7 @@ F: Documentation/virt/kvm/s390* F: arch/s390/include/asm/gmap.h F: arch/s390/include/asm/kvm* F: arch/s390/include/uapi/asm/kvm* +F: arch/s390/kernel/uv.c F: arch/s390/kvm/ F: arch/s390/mm/gmap.c F: tools/testing/selftests/kvm/*/s390x/ @@ -9842,13 +9853,6 @@ S: Maintained F: arch/mips/lantiq F: drivers/soc/lantiq -LAPB module -L: linux-x25@vger.kernel.org -S: Orphan -F: Documentation/networking/lapb-module.rst -F: include/*/lapb.h -F: net/lapb/ - LASI 53c700 driver for PARISC M: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> L: linux-scsi@vger.kernel.org @@ -10559,6 +10563,13 @@ S: Supported F: Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst F: drivers/net/ethernet/marvell/octeontx2/af/ +MARVELL PRESTERA ETHERNET SWITCH DRIVER +M: Vadym Kochan <vkochan@marvell.com> +M: Taras Chornyi <tchornyi@marvell.com> +S: Supported +W: https://github.com/Marvell-switching/switchdev-prestera +F: drivers/net/ethernet/marvell/prestera/ + MARVELL SOC MMC/SD/SDIO CONTROLLER DRIVER M: Nicolas Pitre <nico@fluxnic.net> S: Odd Fixes @@ -11173,7 +11184,7 @@ M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/en_* MELLANOX ETHERNET DRIVER (mlx5e) @@ -11181,7 +11192,7 @@ M: Saeed Mahameed <saeedm@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_* MELLANOX ETHERNET INNOVA DRIVERS @@ -11189,7 +11200,7 @@ R: Boris Pismenny <borisp@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/accel/* F: drivers/net/ethernet/mellanox/mlx5/core/en_accel/* F: drivers/net/ethernet/mellanox/mlx5/core/fpga/* @@ -11201,7 +11212,7 @@ M: Ido Schimmel <idosch@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlxsw/ F: tools/testing/selftests/drivers/net/mlxsw/ @@ -11210,7 +11221,7 @@ M: mlxsw@nvidia.com L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlxfw/ MELLANOX HARDWARE PLATFORM SUPPORT @@ -11229,7 +11240,7 @@ L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/ F: include/linux/mlx4/ @@ -11250,7 +11261,7 @@ L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: Documentation/networking/device_drivers/ethernet/mellanox/ F: drivers/net/ethernet/mellanox/mlx5/core/ F: include/linux/mlx5/ @@ -12130,7 +12141,7 @@ M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org S: Maintained W: http://www.linuxfoundation.org/en/Net -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/devicetree/bindings/net/ @@ -12175,7 +12186,7 @@ M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org S: Maintained W: http://www.linuxfoundation.org/en/Net -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ B: mailto:netdev@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git @@ -13176,7 +13187,9 @@ M: Jesper Dangaard Brouer <hawk@kernel.org> M: Ilias Apalodimas <ilias.apalodimas@linaro.org> L: netdev@vger.kernel.org S: Supported +F: Documentation/networking/page_pool.rst F: include/net/page_pool.h +F: include/trace/events/page_pool.h F: net/core/page_pool.c PANASONIC LAPTOP ACPI EXTRAS DRIVER @@ -13404,7 +13417,6 @@ F: drivers/pci/controller/mobiveil/pcie-mobiveil* PCI DRIVER FOR MVEBU (Marvell Armada 370 and Armada XP SOC support) M: Thomas Petazzoni <thomas.petazzoni@bootlin.com> -M: Jason Cooper <jason@lakedaemon.net> L: linux-pci@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -14210,7 +14222,6 @@ F: drivers/media/usb/pwc/* F: include/trace/events/pwc.h PWM FAN DRIVER -M: Kamil Debski <kamil@wypas.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-hwmon@vger.kernel.org S: Supported @@ -14819,7 +14830,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.g F: drivers/net/wireless/realtek/rtlwifi/ REALTEK WIRELESS DRIVER (rtw88) -M: Yan-Hsuan Chuang <yhchuang@realtek.com> +M: Yan-Hsuan Chuang <tony0620emma@gmail.com> L: linux-wireless@vger.kernel.org S: Maintained F: drivers/net/wireless/realtek/rtw88/ @@ -15246,7 +15257,6 @@ F: drivers/iommu/s390-iommu.c S390 IUCV NETWORK LAYER M: Julian Wiedmann <jwi@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> -M: Ursula Braun <ubraun@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ @@ -15257,7 +15267,6 @@ F: net/iucv/ S390 NETWORK DRIVERS M: Julian Wiedmann <jwi@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> -M: Ursula Braun <ubraun@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ @@ -15426,14 +15435,12 @@ F: Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml F: drivers/nfc/s3fwrn5 SAMSUNG S5C73M3 CAMERA DRIVER -M: Kyungmin Park <kyungmin.park@samsung.com> M: Andrzej Hajda <a.hajda@samsung.com> L: linux-media@vger.kernel.org S: Supported F: drivers/media/i2c/s5c73m3/* SAMSUNG S5K5BAF CAMERA DRIVER -M: Kyungmin Park <kyungmin.park@samsung.com> M: Andrzej Hajda <a.hajda@samsung.com> L: linux-media@vger.kernel.org S: Supported @@ -15451,7 +15458,6 @@ F: Documentation/devicetree/bindings/crypto/samsung-sss.yaml F: drivers/crypto/s5p-sss.c SAMSUNG S5P/EXYNOS4 SOC SERIES CAMERA SUBSYSTEM DRIVERS -M: Kyungmin Park <kyungmin.park@samsung.com> M: Sylwester Nawrocki <s.nawrocki@samsung.com> L: linux-media@vger.kernel.org S: Supported @@ -15499,7 +15505,6 @@ T: git https://github.com/lmajewski/linux-samsung-thermal.git F: drivers/thermal/samsung/ SAMSUNG USB2 PHY DRIVER -M: Kamil Debski <kamil@wypas.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> L: linux-kernel@vger.kernel.org S: Supported @@ -15798,9 +15803,8 @@ F: drivers/slimbus/ F: include/linux/slimbus.h SFC NETWORK DRIVER -M: Solarflare linux maintainers <linux-net-drivers@solarflare.com> -M: Edward Cree <ecree@solarflare.com> -M: Martin Habets <mhabets@solarflare.com> +M: Edward Cree <ecree.xilinx@gmail.com> +M: Martin Habets <habetsm.xilinx@gmail.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/sfc/ @@ -15828,7 +15832,6 @@ S: Maintained F: drivers/misc/sgi-xp/ SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS -M: Ursula Braun <ubraun@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported @@ -18175,6 +18178,14 @@ L: linux-usb@vger.kernel.org S: Supported F: drivers/usb/class/usblp.c +USB RAW GADGET DRIVER +R: Andrey Konovalov <andreyknvl@gmail.com> +L: linux-usb@vger.kernel.org +S: Maintained +F: Documentation/usb/raw-gadget.rst +F: drivers/usb/gadget/legacy/raw_gadget.c +F: include/uapi/linux/usb/raw_gadget.h + USB QMI WWAN NETWORK DRIVER M: Bjørn Mork <bjorn@mork.no> L: netdev@vger.kernel.org @@ -19000,12 +19011,18 @@ L: linux-kernel@vger.kernel.org S: Maintained N: axp[128] -X.25 NETWORK LAYER -M: Andrew Hendry <andrew.hendry@gmail.com> +X.25 STACK +M: Martin Schiller <ms@dev.tdt.de> L: linux-x25@vger.kernel.org -S: Odd Fixes +S: Maintained +F: Documentation/networking/lapb-module.rst F: Documentation/networking/x25* +F: drivers/net/wan/hdlc_x25.c +F: drivers/net/wan/lapbether.c +F: include/*/lapb.h F: include/net/x25* +F: include/uapi/linux/x25.h +F: net/lapb/ F: net/x25/ X86 ARCHITECTURE (32-BIT AND 64-BIT) @@ -19119,12 +19136,17 @@ L: netdev@vger.kernel.org L: bpf@vger.kernel.org S: Supported F: include/net/xdp.h +F: include/net/xdp_priv.h F: include/trace/events/xdp.h F: kernel/bpf/cpumap.c F: kernel/bpf/devmap.c F: net/core/xdp.c -N: xdp -K: xdp +F: samples/bpf/xdp* +F: tools/testing/selftests/bpf/*xdp* +F: tools/testing/selftests/bpf/*/*xdp* +F: drivers/net/ethernet/*/*/*/*/*xdp* +F: drivers/net/ethernet/*/*/*xdp* +K: (?:\b|_)xdp(?:\b|_) XDP SOCKETS (AF_XDP) M: Björn Töpel <bjorn.topel@intel.com> @@ -19133,9 +19155,12 @@ R: Jonathan Lemon <jonathan.lemon@gmail.com> L: netdev@vger.kernel.org L: bpf@vger.kernel.org S: Maintained +F: Documentation/networking/af_xdp.rst F: include/net/xdp_sock* F: include/net/xsk_buff_pool.h F: include/uapi/linux/if_xdp.h +F: include/uapi/linux/xdp_diag.h +F: include/net/netns/xdp.h F: net/xdp/ F: samples/bpf/xdpsock* F: tools/lib/bpf/xsk* @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 0 -EXTRAVERSION = -rc3 +SUBLEVEL = 1 +EXTRAVERSION = NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -433,7 +433,6 @@ NM = llvm-nm OBJCOPY = llvm-objcopy OBJDUMP = llvm-objdump READELF = llvm-readelf -OBJSIZE = llvm-size STRIP = llvm-strip else CC = $(CROSS_COMPILE)gcc @@ -443,7 +442,6 @@ NM = $(CROSS_COMPILE)nm OBJCOPY = $(CROSS_COMPILE)objcopy OBJDUMP = $(CROSS_COMPILE)objdump READELF = $(CROSS_COMPILE)readelf -OBJSIZE = $(CROSS_COMPILE)size STRIP = $(CROSS_COMPILE)strip endif PAHOLE = pahole @@ -509,7 +507,7 @@ KBUILD_LDFLAGS := CLANG_FLAGS := export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE LD CC -export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL +export CPP AR NM STRIP OBJCOPY OBJDUMP READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL export PERL PYTHON PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ ZSTD export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE @@ -828,7 +826,9 @@ else DEBUG_CFLAGS += -g endif +ifneq ($(LLVM_IAS),1) KBUILD_AFLAGS += -Wa,-gdwarf-2 +endif ifdef CONFIG_DEBUG_INFO_DWARF4 DEBUG_CFLAGS += -gdwarf-4 @@ -946,7 +946,7 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=incompatible-pointer-types) KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init) # change __FILE__ to the relative path from the srctree -KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) +KBUILD_CPPFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) # ensure -fcf-protection is disabled when using retpoline as it is # incompatible with -mindirect-branch=thunk-extern @@ -984,6 +984,12 @@ ifeq ($(CONFIG_RELR),y) LDFLAGS_vmlinux += --pack-dyn-relocs=relr endif +# We never want expected sections to be placed heuristically by the +# linker. All sections should be explicitly named in the linker script. +ifdef CONFIG_LD_ORPHAN_WARN +LDFLAGS_vmlinux += --orphan-handling=warn +endif + # Align the bit size of userspace programs with the kernel KBUILD_USERCFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS)) KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS)) diff --git a/arch/Kconfig b/arch/Kconfig index 56b6ccc0e32d..ba4e966484ab 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1028,6 +1028,15 @@ config HAVE_STATIC_CALL_INLINE bool depends on HAVE_STATIC_CALL +config ARCH_WANT_LD_ORPHAN_WARN + bool + help + An arch should select this symbol once all linker sections are explicitly + included, size-asserted, or discarded in the linker scripts. This is + important because we never want expected sections to be placed heuristically + by the linker, since the locations of such sections can change between linker + versions. + source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 7462a7911002..4c7b0414a3ff 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -57,7 +57,7 @@ EXPORT_SYMBOL(pm_power_off); void arch_cpu_idle(void) { wtint(0); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_dead(void) diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h index c6606f4d20d6..fb98440c0bd4 100644 --- a/arch/arc/include/asm/bitops.h +++ b/arch/arc/include/asm/bitops.h @@ -243,10 +243,8 @@ static inline int constant_fls(unsigned int x) x <<= 2; r -= 2; } - if (!(x & 0x80000000u)) { - x <<= 1; + if (!(x & 0x80000000u)) r -= 1; - } return r; } diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index f1ed17edb085..163641726a2b 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -134,8 +134,10 @@ #ifdef CONFIG_ARC_HAS_PAE40 #define PTE_BITS_NON_RWX_IN_PD1 (0xff00000000 | PAGE_MASK | _PAGE_CACHEABLE) +#define MAX_POSSIBLE_PHYSMEM_BITS 40 #else #define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /************************************************************************** diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index b23986f98450..f73da203b170 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -38,15 +38,27 @@ #ifdef CONFIG_ARC_DW2_UNWIND -static void seed_unwind_frame_info(struct task_struct *tsk, - struct pt_regs *regs, - struct unwind_frame_info *frame_info) +static int +seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs, + struct unwind_frame_info *frame_info) { - /* - * synchronous unwinding (e.g. dump_stack) - * - uses current values of SP and friends - */ - if (tsk == NULL && regs == NULL) { + if (regs) { + /* + * Asynchronous unwinding of intr/exception + * - Just uses the pt_regs passed + */ + frame_info->task = tsk; + + frame_info->regs.r27 = regs->fp; + frame_info->regs.r28 = regs->sp; + frame_info->regs.r31 = regs->blink; + frame_info->regs.r63 = regs->ret; + frame_info->call_frame = 0; + } else if (tsk == NULL || tsk == current) { + /* + * synchronous unwinding (e.g. dump_stack) + * - uses current values of SP and friends + */ unsigned long fp, sp, blink, ret; frame_info->task = current; @@ -63,13 +75,17 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->regs.r31 = blink; frame_info->regs.r63 = ret; frame_info->call_frame = 0; - } else if (regs == NULL) { + } else { /* - * Asynchronous unwinding of sleeping task - * - Gets SP etc from task's pt_regs (saved bottom of kernel - * mode stack of task) + * Asynchronous unwinding of a likely sleeping task + * - first ensure it is actually sleeping + * - if so, it will be in __switch_to, kernel mode SP of task + * is safe-kept and BLINK at a well known location in there */ + if (tsk->state == TASK_RUNNING) + return -1; + frame_info->task = tsk; frame_info->regs.r27 = TSK_K_FP(tsk); @@ -90,19 +106,8 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->regs.r28 += 60; frame_info->call_frame = 0; - } else { - /* - * Asynchronous unwinding of intr/exception - * - Just uses the pt_regs passed - */ - frame_info->task = tsk; - - frame_info->regs.r27 = regs->fp; - frame_info->regs.r28 = regs->sp; - frame_info->regs.r31 = regs->blink; - frame_info->regs.r63 = regs->ret; - frame_info->call_frame = 0; } + return 0; } #endif @@ -116,7 +121,8 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, unsigned int address; struct unwind_frame_info frame_info; - seed_unwind_frame_info(tsk, regs, &frame_info); + if (seed_unwind_frame_info(tsk, regs, &frame_info)) + return 0; while (1) { address = UNW_PC(&frame_info); diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index c340acd989a0..9bb3c24f3677 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -30,14 +30,14 @@ * -Changes related to MMU v2 (Rel 4.8) * * Vineetg: Aug 29th 2008 - * -In TLB Flush operations (Metal Fix MMU) there is a explict command to + * -In TLB Flush operations (Metal Fix MMU) there is a explicit command to * flush Micro-TLBS. If TLB Index Reg is invalid prior to TLBIVUTLB cmd, * it fails. Thus need to load it with ANY valid value before invoking * TLBIVUTLB cmd * * Vineetg: Aug 21th 2008: * -Reduced the duration of IRQ lockouts in TLB Flush routines - * -Multiple copies of TLB erase code seperated into a "single" function + * -Multiple copies of TLB erase code separated into a "single" function * -In TLB Flush routines, interrupt disabling moved UP to retrieve ASID * in interrupt-safe region. * @@ -66,7 +66,7 @@ * * Although J-TLB is 2 way set assoc, ARC700 caches J-TLB into uTLBS which has * much higher associativity. u-D-TLB is 8 ways, u-I-TLB is 4 ways. - * Given this, the thrasing problem should never happen because once the 3 + * Given this, the thrashing problem should never happen because once the 3 * J-TLB entries are created (even though 3rd will knock out one of the prev * two), the u-D-TLB and u-I-TLB will have what is required to accomplish memcpy * @@ -127,7 +127,7 @@ static void utlb_invalidate(void) * There was however an obscure hardware bug, where uTLB flush would * fail when a prior probe for J-TLB (both totally unrelated) would * return lkup err - because the entry didn't exist in MMU. - * The Workround was to set Index reg with some valid value, prior to + * The Workaround was to set Index reg with some valid value, prior to * flush. This was fixed in MMU v3 */ unsigned int idx; @@ -272,7 +272,7 @@ noinline void local_flush_tlb_all(void) } /* - * Flush the entrie MM for userland. The fastest way is to move to Next ASID + * Flush the entire MM for userland. The fastest way is to move to Next ASID */ noinline void local_flush_tlb_mm(struct mm_struct *mm) { @@ -303,7 +303,7 @@ noinline void local_flush_tlb_mm(struct mm_struct *mm) * Difference between this and Kernel Range Flush is * -Here the fastest way (if range is too large) is to move to next ASID * without doing any explicit Shootdown - * -In case of kernel Flush, entry has to be shot down explictly + * -In case of kernel Flush, entry has to be shot down explicitly */ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) @@ -620,7 +620,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, * Super Page size is configurable in hardware (4K to 16M), but fixed once * RTL builds. * - * The exact THP size a Linx configuration will support is a function of: + * The exact THP size a Linux configuration will support is a function of: * - MMU page size (typical 8K, RTL fixed) * - software page walker address split between PGD:PTE:PFN (typical * 11:8:13, but can be changed with 1 line) @@ -698,7 +698,7 @@ void local_flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, #endif -/* Read the Cache Build Confuration Registers, Decode them and save into +/* Read the Cache Build Configuration Registers, Decode them and save into * the cpuinfo structure for later use. * No Validation is done here, simply read/convert the BCRs */ @@ -803,13 +803,13 @@ void arc_mmu_init(void) pr_info("%s", arc_mmu_mumbojumbo(0, str, sizeof(str))); /* - * Can't be done in processor.h due to header include depenedencies + * Can't be done in processor.h due to header include dependencies */ BUILD_BUG_ON(!IS_ALIGNED((CONFIG_ARC_KVADDR_SIZE << 20), PMD_SIZE)); /* * stack top size sanity check, - * Can't be done in processor.h due to header include depenedencies + * Can't be done in processor.h due to header include dependencies */ BUILD_BUG_ON(!IS_ALIGNED(STACK_TOP, PMD_SIZE)); @@ -881,7 +881,7 @@ void arc_mmu_init(void) * the duplicate one. * -Knob to be verbose abt it.(TODO: hook them up to debugfs) */ -volatile int dup_pd_silent; /* Be slient abt it or complain (default) */ +volatile int dup_pd_silent; /* Be silent abt it or complain (default) */ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, struct pt_regs *regs) @@ -948,7 +948,7 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, /*********************************************************************** * Diagnostic Routines - * -Called from Low Level TLB Hanlders if things don;t look good + * -Called from Low Level TLB Handlers if things don;t look good **********************************************************************/ #ifdef CONFIG_ARC_DBG_TLB_PARANOIA diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index fe2f17eb2b50..002e0cf025f5 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -35,6 +35,7 @@ config ARM select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU select ARCH_WANT_IPC_PARSE_VERSION + select ARCH_WANT_LD_ORPHAN_WARN select BINFMT_FLAT_ARGVP_ENVP_ON_STACK select BUILDTIME_TABLE_SORT if MMU select CLONE_BACKWARDS diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 4d76eab2b22d..e15f76ca2887 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -16,10 +16,6 @@ LDFLAGS_vmlinux += --be8 KBUILD_LDFLAGS_MODULE += --be8 endif -# We never want expected sections to be placed heuristically by the -# linker. All sections should be explicitly named in the linker script. -LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn) - GZFLAGS :=-9 #KBUILD_CFLAGS +=-pipe diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 47f001ca5499..e1567418a2b1 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -129,7 +129,9 @@ LDFLAGS_vmlinux += --no-undefined # Delete all temporary local symbols LDFLAGS_vmlinux += -X # Report orphan sections -LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn) +ifdef CONFIG_LD_ORPHAN_WARN +LDFLAGS_vmlinux += --orphan-handling=warn +endif # Next argument is a linker script LDFLAGS_vmlinux += -T diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 2e04ec5b5446..caa27322a0ab 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -1472,6 +1472,9 @@ ENTRY(efi_enter_kernel) @ issued from HYP mode take us to the correct handler code. We @ will disable the MMU before jumping to the kernel proper. @ + ARM( bic r1, r1, #(1 << 30) ) @ clear HSCTLR.TE + THUMB( orr r1, r1, #(1 << 30) ) @ set HSCTLR.TE + mcr p15, 4, r1, c1, c0, 0 adr r0, __hyp_reentry_vectors mcr p15, 4, r0, c12, c0, 0 @ set HYP vector base (HVBAR) isb diff --git a/arch/arm/boot/dts/am437x-l4.dtsi b/arch/arm/boot/dts/am437x-l4.dtsi index c220dc3c4e0f..243e35f7a56c 100644 --- a/arch/arm/boot/dts/am437x-l4.dtsi +++ b/arch/arm/boot/dts/am437x-l4.dtsi @@ -521,7 +521,7 @@ ranges = <0x0 0x100000 0x8000>; mac_sw: switch@0 { - compatible = "ti,am4372-cpsw","ti,cpsw-switch"; + compatible = "ti,am4372-cpsw-switch", "ti,cpsw-switch"; reg = <0x0 0x4000>; ranges = <0 0 0x4000>; clocks = <&cpsw_125mhz_gclk>, <&dpll_clksel_mac_clk>; diff --git a/arch/arm/boot/dts/dra76x.dtsi b/arch/arm/boot/dts/dra76x.dtsi index b69c7d40f5d8..2f326151116b 100644 --- a/arch/arm/boot/dts/dra76x.dtsi +++ b/arch/arm/boot/dts/dra76x.dtsi @@ -32,8 +32,8 @@ interrupts = <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "int0", "int1"; - clocks = <&mcan_clk>, <&l3_iclk_div>; - clock-names = "cclk", "hclk"; + clocks = <&l3_iclk_div>, <&mcan_clk>; + clock-names = "hclk", "cclk"; bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>; }; }; diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi index ab291cec650a..2983e91bc7dd 100644 --- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi +++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi @@ -122,7 +122,6 @@ }; &clock { - clocks = <&clock CLK_XUSBXTI>; assigned-clocks = <&clock CLK_FOUT_EPLL>; assigned-clock-rates = <45158401>; }; diff --git a/arch/arm/boot/dts/imx50-evk.dts b/arch/arm/boot/dts/imx50-evk.dts index 878e89c20190..4ea5c23f181b 100644 --- a/arch/arm/boot/dts/imx50-evk.dts +++ b/arch/arm/boot/dts/imx50-evk.dts @@ -59,7 +59,7 @@ MX50_PAD_CSPI_MISO__CSPI_MISO 0x00 MX50_PAD_CSPI_MOSI__CSPI_MOSI 0x00 MX50_PAD_CSPI_SS0__GPIO4_11 0xc4 - MX50_PAD_ECSPI1_MOSI__CSPI_SS1 0xf4 + MX50_PAD_ECSPI1_MOSI__GPIO4_13 0x84 >; }; diff --git a/arch/arm/boot/dts/imx6q-prti6q.dts b/arch/arm/boot/dts/imx6q-prti6q.dts index d112b50f8c5d..b4605edfd2ab 100644 --- a/arch/arm/boot/dts/imx6q-prti6q.dts +++ b/arch/arm/boot/dts/imx6q-prti6q.dts @@ -213,8 +213,8 @@ #size-cells = <0>; /* Microchip KSZ9031RNX PHY */ - rgmii_phy: ethernet-phy@4 { - reg = <4>; + rgmii_phy: ethernet-phy@0 { + reg = <0>; interrupts-extended = <&gpio1 28 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; reset-assert-us = <10000>; diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi index 265f5f3dbff6..24f793ca2886 100644 --- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi @@ -551,7 +551,7 @@ pinctrl_i2c3: i2c3grp { fsl,pins = < - MX6QDL_PAD_GPIO_3__I2C3_SCL 0x4001b8b1 + MX6QDL_PAD_GPIO_5__I2C3_SCL 0x4001b8b1 MX6QDL_PAD_GPIO_16__I2C3_SDA 0x4001b8b1 >; }; diff --git a/arch/arm/boot/dts/imx6qdl-udoo.dtsi b/arch/arm/boot/dts/imx6qdl-udoo.dtsi index 828dd20cd27d..d07d8f83456d 100644 --- a/arch/arm/boot/dts/imx6qdl-udoo.dtsi +++ b/arch/arm/boot/dts/imx6qdl-udoo.dtsi @@ -98,7 +98,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-wandboard-revd1.dtsi b/arch/arm/boot/dts/imx6qdl-wandboard-revd1.dtsi index 93909796885a..b9b698f72b26 100644 --- a/arch/arm/boot/dts/imx6qdl-wandboard-revd1.dtsi +++ b/arch/arm/boot/dts/imx6qdl-wandboard-revd1.dtsi @@ -166,7 +166,6 @@ MX6QDL_PAD_RGMII_RD2__RGMII_RD2 0x1b030 MX6QDL_PAD_RGMII_RD3__RGMII_RD3 0x1b030 MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b030 - MX6QDL_PAD_GPIO_6__ENET_IRQ 0x000b1 >; }; diff --git a/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts b/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts index adde62d6fce7..342304f5653a 100644 --- a/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts +++ b/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts @@ -223,8 +223,7 @@ }; &ssp3 { - /delete-property/ #address-cells; - /delete-property/ #size-cells; + #address-cells = <0>; spi-slave; status = "okay"; ready-gpios = <&gpio 125 GPIO_ACTIVE_HIGH>; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi index 5dff24e39af8..8456f172d4b1 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi @@ -46,6 +46,16 @@ linux,code = <KEY_A>; gpios = <&gpiof 3 GPIO_ACTIVE_LOW>; }; + + /* + * The EXTi IRQ line 0 is shared with PMIC, + * so mark this as polled GPIO key. + */ + button-2 { + label = "TA3-GPIO-C"; + linux,code = <KEY_C>; + gpios = <&gpiog 0 GPIO_ACTIVE_LOW>; + }; }; gpio-keys { @@ -59,13 +69,6 @@ wakeup-source; }; - button-2 { - label = "TA3-GPIO-C"; - linux,code = <KEY_C>; - gpios = <&gpioi 11 GPIO_ACTIVE_LOW>; - wakeup-source; - }; - button-3 { label = "TA4-GPIO-D"; linux,code = <KEY_D>; @@ -79,7 +82,7 @@ led-0 { label = "green:led5"; - gpios = <&gpiog 2 GPIO_ACTIVE_HIGH>; + gpios = <&gpioc 6 GPIO_ACTIVE_HIGH>; default-state = "off"; }; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index b4b52cf634af..f796a6150313 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -68,6 +68,7 @@ gpio = <&gpiog 3 GPIO_ACTIVE_LOW>; regulator-always-on; regulator-boot-on; + vin-supply = <&vdd>; }; }; @@ -202,6 +203,7 @@ vdda: ldo1 { regulator-name = "vdda"; + regulator-always-on; regulator-min-microvolt = <2900000>; regulator-max-microvolt = <2900000>; interrupts = <IT_CURLIM_LDO1 0>; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi index 04fbb324a541..803eb8bc9c85 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi @@ -21,6 +21,10 @@ }; }; +&dts { + status = "okay"; +}; + &i2c4 { pinctrl-names = "default"; pinctrl-0 = <&i2c4_pins_a>; diff --git a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts index 049e6ab3cf56..73de34ae37fd 100644 --- a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts +++ b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts @@ -154,7 +154,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts index 32d5d45a35c0..8945dbb114a2 100644 --- a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts +++ b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts @@ -130,7 +130,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_gmac_3v3>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun7i-a20-bananapi.dts b/arch/arm/boot/dts/sun7i-a20-bananapi.dts index bb3987e101c2..0b3d9ae75650 100644 --- a/arch/arm/boot/dts/sun7i-a20-bananapi.dts +++ b/arch/arm/boot/dts/sun7i-a20-bananapi.dts @@ -132,7 +132,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_gmac_3v3>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts index 8c8dee6ea461..9109ca0919ad 100644 --- a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts +++ b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts @@ -151,7 +151,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts b/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts index fce2f7fcd084..bf38c66c1815 100644 --- a/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts +++ b/arch/arm/boot/dts/sun7i-a20-pcduino3-nano.dts @@ -1,5 +1,5 @@ /* - * Copyright 2015 Adam Sampson <ats@offog.org> + * Copyright 2015-2020 Adam Sampson <ats@offog.org> * * This file is dual-licensed: you can use it either under the terms * of the GPL or the X11 license, at your option. Note that this dual @@ -115,7 +115,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts index 9d34eabba121..431f70234d36 100644 --- a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts +++ b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts @@ -131,7 +131,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_sw>; phy-handle = <&rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; allwinner,rx-delay-ps = <700>; allwinner,tx-delay-ps = <700>; status = "okay"; diff --git a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts index d9be511f054f..d8326a5c681d 100644 --- a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts +++ b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts @@ -183,7 +183,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_dldo4>; phy-handle = <&rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts index 71fb73208939..babf4cf1b2f6 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts @@ -53,11 +53,6 @@ }; }; -&emac { - /* LEDs changed to active high on the plus */ - /delete-property/ allwinner,leds-active-low; -}; - &mmc1 { vmmc-supply = <®_vcc3v3>; bus-width = <4>; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts index 6dbf7b2e0c13..b6ca45d18e51 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts @@ -67,7 +67,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts index 2fc62ef0cb3e..a6a1087a0c9b 100644 --- a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts +++ b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts @@ -129,7 +129,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_dc1sw>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-s3-pinecube.dts b/arch/arm/boot/dts/sun8i-s3-pinecube.dts index 9bab6b7f4014..4aa0ee897a0a 100644 --- a/arch/arm/boot/dts/sun8i-s3-pinecube.dts +++ b/arch/arm/boot/dts/sun8i-s3-pinecube.dts @@ -10,7 +10,7 @@ / { model = "PineCube IP Camera"; - compatible = "pine64,pinecube", "allwinner,sun8i-s3"; + compatible = "pine64,pinecube", "sochip,s3", "allwinner,sun8i-v3"; aliases { serial0 = &uart2; diff --git a/arch/arm/boot/dts/sun8i-v3s.dtsi b/arch/arm/boot/dts/sun8i-v3s.dtsi index 0c7341676921..89abd4cc7e23 100644 --- a/arch/arm/boot/dts/sun8i-v3s.dtsi +++ b/arch/arm/boot/dts/sun8i-v3s.dtsi @@ -539,7 +539,7 @@ gic: interrupt-controller@1c81000 { compatible = "arm,gic-400"; reg = <0x01c81000 0x1000>, - <0x01c82000 0x1000>, + <0x01c82000 0x2000>, <0x01c84000 0x2000>, <0x01c86000 0x2000>; interrupt-controller; diff --git a/arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts b/arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts index 15c22b06fc4b..47954551f573 100644 --- a/arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts +++ b/arch/arm/boot/dts/sun8i-v40-bananapi-m2-berry.dts @@ -120,7 +120,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_dc1sw>; status = "okay"; }; @@ -198,16 +198,16 @@ }; ®_dc1sw { - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-name = "vcc-gmac-phy"; }; ®_dcdc1 { regulator-always-on; - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; - regulator-name = "vcc-3v0"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vcc-3v3"; }; ®_dcdc2 { diff --git a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts index d3b337b043a1..484b93df20cb 100644 --- a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts +++ b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts @@ -129,7 +129,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_cldo1>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun9i-a80-optimus.dts b/arch/arm/boot/dts/sun9i-a80-optimus.dts index bbc6335e5631..5c3580d712e4 100644 --- a/arch/arm/boot/dts/sun9i-a80-optimus.dts +++ b/arch/arm/boot/dts/sun9i-a80-optimus.dts @@ -124,7 +124,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_cldo1>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi b/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi index 39263e74fbb5..8e5cb3b3fd68 100644 --- a/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi +++ b/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi @@ -126,7 +126,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts index e500911ce0a5..6f1e0f0d4f0a 100644 --- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts +++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts @@ -406,6 +406,9 @@ }; }; +&mdio1 { + clock-frequency = <5000000>; +}; &iomuxc { pinctrl_gpio_e6185_eeprom_sel: pinctrl-gpio-e6185-eeprom-spi0 { diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 34793aabdb65..58df9fd79a76 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -81,7 +81,6 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_BINFMT_MISC=y CONFIG_CMA=y CONFIG_ZSMALLOC=m -CONFIG_ZSMALLOC_PGTABLE_MAPPING=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h index 213607a1f45c..e26a278d301a 100644 --- a/arch/arm/include/asm/kprobes.h +++ b/arch/arm/include/asm/kprobes.h @@ -44,20 +44,20 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); /* optinsn template addresses */ -extern __visible kprobe_opcode_t optprobe_template_entry; -extern __visible kprobe_opcode_t optprobe_template_val; -extern __visible kprobe_opcode_t optprobe_template_call; -extern __visible kprobe_opcode_t optprobe_template_end; -extern __visible kprobe_opcode_t optprobe_template_sub_sp; -extern __visible kprobe_opcode_t optprobe_template_add_sp; -extern __visible kprobe_opcode_t optprobe_template_restore_begin; -extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn; -extern __visible kprobe_opcode_t optprobe_template_restore_end; +extern __visible kprobe_opcode_t optprobe_template_entry[]; +extern __visible kprobe_opcode_t optprobe_template_val[]; +extern __visible kprobe_opcode_t optprobe_template_call[]; +extern __visible kprobe_opcode_t optprobe_template_end[]; +extern __visible kprobe_opcode_t optprobe_template_sub_sp[]; +extern __visible kprobe_opcode_t optprobe_template_add_sp[]; +extern __visible kprobe_opcode_t optprobe_template_restore_begin[]; +extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn[]; +extern __visible kprobe_opcode_t optprobe_template_restore_end[]; #define MAX_OPTIMIZED_LENGTH 4 #define MAX_OPTINSN_SIZE \ - ((unsigned long)&optprobe_template_end - \ - (unsigned long)&optprobe_template_entry) + ((unsigned long)optprobe_template_end - \ + (unsigned long)optprobe_template_entry) #define RELATIVEJUMP_SIZE 4 struct arch_optimized_insn { diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index 3502c2f746ca..baf7d0204eb5 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -75,6 +75,8 @@ #define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t)) #define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 + /* * PMD_SHIFT determines the size of the area a second-level page table can map * PGDIR_SHIFT determines what a third-level page table entry can map diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index fbb6693c3352..2b85d175e999 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -25,6 +25,8 @@ #define PTE_HWTABLE_OFF (0) #define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u64)) +#define MAX_POSSIBLE_PHYSMEM_BITS 40 + /* * PGDIR_SHIFT determines the size a top-level page table entry can map. */ diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c index 05fe92aa7d98..0529f90395c9 100644 --- a/arch/arm/kernel/perf_regs.c +++ b/arch/arm/kernel/perf_regs.c @@ -32,8 +32,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 8e6ace03e960..9f199b1e8383 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -71,7 +71,7 @@ void arch_cpu_idle(void) arm_pm_idle(); else cpu_do_idle(); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_prepare(void) diff --git a/arch/arm/mach-imx/anatop.c b/arch/arm/mach-imx/anatop.c index d841bed8664d..7bb47eb3fc07 100644 --- a/arch/arm/mach-imx/anatop.c +++ b/arch/arm/mach-imx/anatop.c @@ -136,7 +136,7 @@ void __init imx_init_revision_from_anatop(void) src_np = of_find_compatible_node(NULL, NULL, "fsl,imx6ul-src"); - src_base = of_iomap(np, 0); + src_base = of_iomap(src_np, 0); of_node_put(src_np); WARN_ON(!src_base); sbmr2 = readl_relaxed(src_base + SRC_SBMR2); diff --git a/arch/arm/mach-keystone/memory.h b/arch/arm/mach-keystone/memory.h index 9147565d0581..1b9ed1271e05 100644 --- a/arch/arm/mach-keystone/memory.h +++ b/arch/arm/mach-keystone/memory.h @@ -6,9 +6,6 @@ #ifndef __MEMORY_H #define __MEMORY_H -#define MAX_PHYSMEM_BITS 36 -#define SECTION_SIZE_BITS 34 - #define KEYSTONE_LOW_PHYS_START 0x80000000ULL #define KEYSTONE_LOW_PHYS_SIZE 0x80000000ULL /* 2G */ #define KEYSTONE_LOW_PHYS_END (KEYSTONE_LOW_PHYS_START + \ diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c index 144b9caa935c..a720259099ed 100644 --- a/arch/arm/mach-omap1/board-osk.c +++ b/arch/arm/mach-omap1/board-osk.c @@ -288,7 +288,7 @@ static struct gpiod_lookup_table osk_usb_gpio_table = { .dev_id = "ohci", .table = { /* Power GPIO on the I2C-attached TPS65010 */ - GPIO_LOOKUP("i2c-tps65010", 1, "power", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("tps65010", 0, "power", GPIO_ACTIVE_HIGH), GPIO_LOOKUP(OMAP_GPIO_LABEL, 9, "overcurrent", GPIO_ACTIVE_HIGH), }, diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 3ee7bdff86b2..3f62a0c9450d 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -7,7 +7,6 @@ config ARCH_OMAP2 depends on ARCH_MULTI_V6 select ARCH_OMAP2PLUS select CPU_V6 - select PM_GENERIC_DOMAINS if PM select SOC_HAS_OMAP2_SDRC config ARCH_OMAP3 @@ -106,6 +105,8 @@ config ARCH_OMAP2PLUS select OMAP_DM_TIMER select OMAP_GPMC select PINCTRL + select PM_GENERIC_DOMAINS if PM + select PM_GENERIC_DOMAINS_OF if PM select RESET_CONTROLLER select SOC_BUS select TI_SYSC diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index a92d277f81a0..c8d317fafe2e 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -175,8 +175,11 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, if (mpuss_can_lose_context) { error = cpu_cluster_pm_enter(); if (error) { - omap_set_pwrdm_state(mpu_pd, PWRDM_POWER_ON); - goto cpu_cluster_pm_out; + index = 0; + cx = state_ptr + index; + pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state); + omap_set_pwrdm_state(mpu_pd, cx->mpu_state); + mpuss_can_lose_context = 0; } } } @@ -184,7 +187,6 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, omap4_enter_lowpower(dev->cpu, cx->cpu_state); cpu_done[dev->cpu] = true; -cpu_cluster_pm_out: /* Wakeup CPU1 only if it is not offlined */ if (dev->cpu == 0 && cpumask_test_cpu(1, cpu_online_mask)) { diff --git a/arch/arm/mach-sunxi/sunxi.c b/arch/arm/mach-sunxi/sunxi.c index 06da2747a90b..19635721013d 100644 --- a/arch/arm/mach-sunxi/sunxi.c +++ b/arch/arm/mach-sunxi/sunxi.c @@ -66,6 +66,7 @@ static const char * const sun8i_board_dt_compat[] = { "allwinner,sun8i-h2-plus", "allwinner,sun8i-h3", "allwinner,sun8i-r40", + "allwinner,sun8i-v3", "allwinner,sun8i-v3s", NULL, }; diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c index 7a449df0b359..c78180172120 100644 --- a/arch/arm/probes/kprobes/opt-arm.c +++ b/arch/arm/probes/kprobes/opt-arm.c @@ -85,21 +85,21 @@ asm ( "optprobe_template_end:\n"); #define TMPL_VAL_IDX \ - ((unsigned long *)&optprobe_template_val - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_val - (unsigned long *)optprobe_template_entry) #define TMPL_CALL_IDX \ - ((unsigned long *)&optprobe_template_call - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_call - (unsigned long *)optprobe_template_entry) #define TMPL_END_IDX \ - ((unsigned long *)&optprobe_template_end - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_end - (unsigned long *)optprobe_template_entry) #define TMPL_ADD_SP \ - ((unsigned long *)&optprobe_template_add_sp - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_add_sp - (unsigned long *)optprobe_template_entry) #define TMPL_SUB_SP \ - ((unsigned long *)&optprobe_template_sub_sp - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_sub_sp - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_BEGIN \ - ((unsigned long *)&optprobe_template_restore_begin - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_begin - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_ORIGN_INSN \ - ((unsigned long *)&optprobe_template_restore_orig_insn - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_orig_insn - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_END \ - ((unsigned long *)&optprobe_template_restore_end - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_end - (unsigned long *)optprobe_template_entry) /* * ARM can always optimize an instruction when using ARM ISA, except @@ -234,7 +234,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *or } /* Copy arch-dep-instance from template. */ - memcpy(code, (unsigned long *)&optprobe_template_entry, + memcpy(code, (unsigned long *)optprobe_template_entry, TMPL_END_IDX * sizeof(kprobe_opcode_t)); /* Adjust buffer according to instruction. */ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 1515f6f153a0..a6b5b7ef40ae 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -81,6 +81,7 @@ config ARM64 select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36) + select ARCH_WANT_LD_ORPHAN_WARN select ARCH_HAS_UBSAN_SANITIZE_ALL select ARM_AMBA select ARM_ARCH_TIMER diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 5789c2d18d43..6a87d592bd00 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -28,10 +28,6 @@ LDFLAGS_vmlinux += --fix-cortex-a53-843419 endif endif -# We never want expected sections to be placed heuristically by the -# linker. All sections should be explicitly named in the linker script. -LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn) - ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS), y) ifneq ($(CONFIG_ARM64_LSE_ATOMICS), y) $(warning LSE atomics not supported by binutils) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts index 3ea5182ca489..e5e840b9fbb4 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts @@ -105,7 +105,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_dc1sw>; status = "okay"; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts index d894ec5fa8a1..70e31743f0ba 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts @@ -120,7 +120,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_gmac_3v3>; status = "okay"; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts index b26181cf9095..b54099b654c8 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts @@ -13,7 +13,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-txid"; phy-handle = <&ext_rgmii_phy>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts index 3ab0f0347bc9..0494bfaf2ffa 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts @@ -122,9 +122,6 @@ status = "okay"; port { - #address-cells = <1>; - #size-cells = <0>; - csi_ep: endpoint { remote-endpoint = <&ov5640_ep>; bus-width = <8>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts index 9ebb9e07fae3..d4069749d721 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts @@ -79,7 +79,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_dc1sw>; status = "okay"; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts index df1b9263ad0e..6e30a564c87f 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts @@ -36,7 +36,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; /delete-property/ allwinner,leds-active-low; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo-plus2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo-plus2.dts index 4f9ba53ffaae..9d93fe153689 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo-plus2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo-plus2.dts @@ -96,7 +96,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts index 7d7aad18f078..8bf2db9dcbda 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts @@ -123,7 +123,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts index cb44bfa5981f..33ab44072e6d 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts @@ -124,7 +124,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts index 3f7ceeb1a767..7c9dbde645b5 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts @@ -97,7 +97,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&ext_rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_aldo2>; status = "okay"; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-one-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-one-plus.dts index fceb298bfd53..29a081e72a9b 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-one-plus.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-one-plus.dts @@ -27,7 +27,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&ext_rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_gmac_3v3>; allwinner,rx-delay-ps = <200>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts index af85b2074867..961732c52aa0 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts @@ -100,7 +100,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&ext_rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_gmac_3v3>; allwinner,rx-delay-ps = <200>; diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts index feadd21bc0dc..46e558ab7729 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts @@ -159,7 +159,7 @@ flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00a"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts index c07966740e14..f9b4a39683cf 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts @@ -192,7 +192,7 @@ flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00a"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi index 55259f973b5a..aef8f2b00778 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi @@ -5,20 +5,20 @@ usb { compatible = "simple-bus"; dma-ranges; - #address-cells = <1>; - #size-cells = <1>; - ranges = <0x0 0x0 0x68500000 0x00400000>; + #address-cells = <2>; + #size-cells = <2>; + ranges = <0x0 0x0 0x0 0x68500000 0x0 0x00400000>; usbphy0: usb-phy@0 { compatible = "brcm,sr-usb-combo-phy"; - reg = <0x00000000 0x100>; + reg = <0x0 0x00000000 0x0 0x100>; #phy-cells = <1>; status = "disabled"; }; xhci0: usb@1000 { compatible = "generic-xhci"; - reg = <0x00001000 0x1000>; + reg = <0x0 0x00001000 0x0 0x1000>; interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy0 1>, <&usbphy0 0>; phy-names = "phy0", "phy1"; @@ -28,7 +28,7 @@ bdc0: usb@2000 { compatible = "brcm,bdc-v0.16"; - reg = <0x00002000 0x1000>; + reg = <0x0 0x00002000 0x0 0x1000>; interrupts = <GIC_SPI 259 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy0 0>, <&usbphy0 1>; phy-names = "phy0", "phy1"; @@ -38,21 +38,21 @@ usbphy1: usb-phy@10000 { compatible = "brcm,sr-usb-combo-phy"; - reg = <0x00010000 0x100>; + reg = <0x0 0x00010000 0x0 0x100>; #phy-cells = <1>; status = "disabled"; }; usbphy2: usb-phy@20000 { compatible = "brcm,sr-usb-hs-phy"; - reg = <0x00020000 0x100>; + reg = <0x0 0x00020000 0x0 0x100>; #phy-cells = <0>; status = "disabled"; }; xhci1: usb@11000 { compatible = "generic-xhci"; - reg = <0x00011000 0x1000>; + reg = <0x0 0x00011000 0x0 0x1000>; interrupts = <GIC_SPI 263 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy1 1>, <&usbphy2>, <&usbphy1 0>; phy-names = "phy0", "phy1", "phy2"; @@ -62,7 +62,7 @@ bdc1: usb@21000 { compatible = "brcm,bdc-v0.16"; - reg = <0x00021000 0x1000>; + reg = <0x0 0x00021000 0x0 0x1000>; interrupts = <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy2>; phy-names = "phy0"; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts index f46eb47cfa4d..8161dd237971 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts @@ -75,6 +75,7 @@ &enetc_port0 { phy-handle = <&phy0>; phy-connection-type = "sgmii"; + managed = "in-band-status"; status = "okay"; mdio { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index b2cc98882a6e..a113af902bab 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -1018,6 +1018,7 @@ compatible = "fsl,ls1028a-rcpm", "fsl,qoriq-rcpm-2.1+"; reg = <0x0 0x1e34040 0x0 0x1c>; #fsl,rcpm-wakeup-cells = <7>; + little-endian; }; ftm_alarm0: timer@2800000 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi index ff5805206a28..692d8f4a206d 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi @@ -805,6 +805,7 @@ compatible = "fsl,ls1088a-rcpm", "fsl,qoriq-rcpm-2.1+"; reg = <0x0 0x1e34040 0x0 0x18>; #fsl,rcpm-wakeup-cells = <6>; + little-endian; }; ftm_alarm0: timer@2800000 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi index bf72918fe545..e7abb74bd816 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi @@ -892,6 +892,7 @@ compatible = "fsl,ls208xa-rcpm", "fsl,qoriq-rcpm-2.1+"; reg = <0x0 0x1e34040 0x0 0x18>; #fsl,rcpm-wakeup-cells = <6>; + little-endian; }; ftm_alarm0: timer@2800000 { diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi index 6de86a4f0ec4..b88c3c99b007 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi @@ -72,6 +72,7 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; @@ -210,6 +211,7 @@ host-wakeup-gpios = <&gpio2 8 GPIO_ACTIVE_HIGH>; device-wakeup-gpios = <&gpio2 7 GPIO_ACTIVE_HIGH>; clocks = <&osc_32k>; + max-speed = <4000000>; clock-names = "extclk"; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi index f305a530ff6f..521eb3a5a12e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi @@ -121,6 +121,7 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi index 4107fe914d08..49082529764f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi @@ -135,13 +135,10 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio2>; - /* - * The interrupt is not correct. It should be level low, - * however with internal pull up this causes IRQ storm. - */ - interrupts = <8 IRQ_TYPE_EDGE_RISING>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; rohm,reset-snvs-powered; #clock-cells = <0>; @@ -398,7 +395,7 @@ pinctrl_pmic: pmicirqgrp { fsl,pins = < - MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8 0x41 + MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8 0x141 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index b83f400def8b..05ee062548e4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -129,7 +129,7 @@ opp-1600000000 { opp-hz = /bits/ 64 <1600000000>; - opp-microvolt = <900000>; + opp-microvolt = <950000>; opp-supported-hw = <0xc>, <0x7>; clock-latency-ns = <150000>; opp-suspend; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts index 46e76cf32b2f..7dfee715a2c4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts @@ -53,6 +53,7 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-evk.dts index 707d8486b4d8..8311b95dee49 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-evk.dts @@ -18,6 +18,7 @@ pmic: pmic@25 { compatible = "nxp,pca9450b"; reg = <0x25>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio1>; interrupts = <3 IRQ_TYPE_LEVEL_LOW>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index a2d0190921e4..7f356edf9f91 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -116,13 +116,10 @@ pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; interrupt-parent = <&gpio2>; - /* - * The interrupt is not correct. It should be level low, - * however with internal pull up this causes IRQ storm. - */ - interrupts = <8 IRQ_TYPE_EDGE_RISING>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; rohm,reset-snvs-powered; regulators { @@ -388,7 +385,7 @@ pinctrl_pmic: pmicirqgrp { fsl,pins = < - MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8 0x101 + MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8 0x141 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index 746faf1cf2fb..16c7202885d7 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -790,28 +790,6 @@ #index-cells = <1>; reg = <0x32e40200 0x200>; }; - - usbotg2: usb@32e50000 { - compatible = "fsl,imx8mn-usb", "fsl,imx7d-usb"; - reg = <0x32e50000 0x200>; - interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MN_CLK_USB1_CTRL_ROOT>; - clock-names = "usb1_ctrl_root_clk"; - assigned-clocks = <&clk IMX8MN_CLK_USB_BUS>, - <&clk IMX8MN_CLK_USB_CORE_REF>; - assigned-clock-parents = <&clk IMX8MN_SYS_PLL2_500M>, - <&clk IMX8MN_SYS_PLL1_100M>; - fsl,usbphy = <&usbphynop2>; - fsl,usbmisc = <&usbmisc2 0>; - status = "disabled"; - }; - - usbmisc2: usbmisc@32e50200 { - compatible = "fsl,imx8mn-usbmisc", "fsl,imx7d-usbmisc"; - #index-cells = <1>; - reg = <0x32e50200 0x200>; - }; - }; dma_apbh: dma-controller@33000000 { @@ -876,12 +854,4 @@ assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>; clock-names = "main_clk"; }; - - usbphynop2: usbphynop2 { - compatible = "usb-nop-xceiv"; - clocks = <&clk IMX8MN_CLK_USB_PHY_REF>; - assigned-clocks = <&clk IMX8MN_CLK_USB_PHY_REF>; - assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>; - clock-names = "main_clk"; - }; }; diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi index 8bc6caa9167d..4338db14c5da 100644 --- a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi +++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi @@ -19,6 +19,7 @@ fman0: fman@1a00000 { clock-names = "fmanclk"; fsl,qman-channel-range = <0x800 0x10>; ptimer-handle = <&ptp_timer0>; + dma-coherent; muram@0 { compatible = "fsl,fman-muram"; diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts index 96c50d48289d..a7a83f29f00b 100644 --- a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts +++ b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts @@ -110,7 +110,7 @@ flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "mt25qu02g"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts b/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts index 381a84912ba8..c28d51cc5797 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts @@ -10,18 +10,6 @@ model = "NVIDIA Jetson TX2 Developer Kit"; compatible = "nvidia,p2771-0000", "nvidia,tegra186"; - aconnect { - status = "okay"; - - dma-controller@2930000 { - status = "okay"; - }; - - interrupt-controller@2a40000 { - status = "okay"; - }; - }; - i2c@3160000 { power-monitor@42 { compatible = "ti,ina3221"; diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi index a2893be80507..0dc8304a2edd 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi @@ -54,7 +54,7 @@ status = "okay"; }; - serial@c280000 { + serial@3100000 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index e9c90f0f44ff..93438d2b9469 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -1161,7 +1161,7 @@ hsp_aon: hsp@c150000 { compatible = "nvidia,tegra194-hsp", "nvidia,tegra186-hsp"; - reg = <0x0c150000 0xa0000>; + reg = <0x0c150000 0x90000>; interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi index e18e1a9a3011..a9caaf7c0d67 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi @@ -1663,16 +1663,6 @@ vin-supply = <&vdd_5v0_sys>; }; - vdd_usb_vbus_otg: regulator@11 { - compatible = "regulator-fixed"; - regulator-name = "USB_VBUS_EN0"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - gpio = <&gpio TEGRA_GPIO(CC, 4) GPIO_ACTIVE_HIGH>; - enable-active-high; - vin-supply = <&vdd_5v0_sys>; - }; - vdd_hdmi: regulator@10 { compatible = "regulator-fixed"; regulator-name = "VDD_HDMI_5V0"; @@ -1712,4 +1702,14 @@ enable-active-high; vin-supply = <&vdd_3v3_sys>; }; + + vdd_usb_vbus_otg: regulator@14 { + compatible = "regulator-fixed"; + regulator-name = "USB_VBUS_EN0"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + gpio = <&gpio TEGRA_GPIO(CC, 4) GPIO_ACTIVE_HIGH>; + enable-active-high; + vin-supply = <&vdd_5v0_sys>; + }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts b/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts index f6e6a24829af..b5d9a5526272 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts +++ b/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts @@ -8,7 +8,7 @@ compatible = "nvidia,tegra234-vdk", "nvidia,tegra234"; aliases { - sdhci3 = "/cbb@0/sdhci@3460000"; + mmc3 = "/bus@0/mmc@3460000"; serial0 = &uarta; }; @@ -17,12 +17,12 @@ stdout-path = "serial0:115200n8"; }; - cbb@0 { + bus@0 { serial@3100000 { status = "okay"; }; - sdhci@3460000 { + mmc@3460000 { status = "okay"; bus-width = <8>; non-removable; diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi index a94dac76bf3f..59e0cbfa2214 100644 --- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi @@ -179,22 +179,22 @@ }; soc: soc { - #address-cells = <1>; - #size-cells = <1>; - ranges = <0 0 0 0xffffffff>; + #address-cells = <2>; + #size-cells = <2>; + ranges = <0 0 0 0 0x0 0xffffffff>; dma-ranges; compatible = "simple-bus"; prng: qrng@e1000 { compatible = "qcom,prng-ee"; - reg = <0xe3000 0x1000>; + reg = <0x0 0xe3000 0x0 0x1000>; clocks = <&gcc GCC_PRNG_AHB_CLK>; clock-names = "core"; }; cryptobam: dma@704000 { compatible = "qcom,bam-v1.7.0"; - reg = <0x00704000 0x20000>; + reg = <0x0 0x00704000 0x0 0x20000>; interrupts = <GIC_SPI 207 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_CRYPTO_AHB_CLK>; clock-names = "bam_clk"; @@ -206,7 +206,7 @@ crypto: crypto@73a000 { compatible = "qcom,crypto-v5.1"; - reg = <0x0073a000 0x6000>; + reg = <0x0 0x0073a000 0x0 0x6000>; clocks = <&gcc GCC_CRYPTO_AHB_CLK>, <&gcc GCC_CRYPTO_AXI_CLK>, <&gcc GCC_CRYPTO_CLK>; @@ -217,7 +217,7 @@ tlmm: pinctrl@1000000 { compatible = "qcom,ipq6018-pinctrl"; - reg = <0x01000000 0x300000>; + reg = <0x0 0x01000000 0x0 0x300000>; interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>; gpio-controller; #gpio-cells = <2>; @@ -235,7 +235,7 @@ gcc: gcc@1800000 { compatible = "qcom,gcc-ipq6018"; - reg = <0x01800000 0x80000>; + reg = <0x0 0x01800000 0x0 0x80000>; clocks = <&xo>, <&sleep_clk>; clock-names = "xo", "sleep_clk"; #clock-cells = <1>; @@ -244,17 +244,17 @@ tcsr_mutex_regs: syscon@1905000 { compatible = "syscon"; - reg = <0x01905000 0x8000>; + reg = <0x0 0x01905000 0x0 0x8000>; }; tcsr_q6: syscon@1945000 { compatible = "syscon"; - reg = <0x01945000 0xe000>; + reg = <0x0 0x01945000 0x0 0xe000>; }; blsp_dma: dma@7884000 { compatible = "qcom,bam-v1.7.0"; - reg = <0x07884000 0x2b000>; + reg = <0x0 0x07884000 0x0 0x2b000>; interrupts = <GIC_SPI 238 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_AHB_CLK>; clock-names = "bam_clk"; @@ -264,7 +264,7 @@ blsp1_uart3: serial@78b1000 { compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm"; - reg = <0x078b1000 0x200>; + reg = <0x0 0x078b1000 0x0 0x200>; interrupts = <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_UART3_APPS_CLK>, <&gcc GCC_BLSP1_AHB_CLK>; @@ -276,7 +276,7 @@ compatible = "qcom,spi-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b5000 0x600>; + reg = <0x0 0x078b5000 0x0 0x600>; interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>; spi-max-frequency = <50000000>; clocks = <&gcc GCC_BLSP1_QUP1_SPI_APPS_CLK>, @@ -291,7 +291,7 @@ compatible = "qcom,spi-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b6000 0x600>; + reg = <0x0 0x078b6000 0x0 0x600>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>; spi-max-frequency = <50000000>; clocks = <&gcc GCC_BLSP1_QUP2_SPI_APPS_CLK>, @@ -306,7 +306,7 @@ compatible = "qcom,i2c-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b6000 0x600>; + reg = <0x0 0x078b6000 0x0 0x600>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_AHB_CLK>, <&gcc GCC_BLSP1_QUP2_I2C_APPS_CLK>; @@ -321,7 +321,7 @@ compatible = "qcom,i2c-qup-v2.2.1"; #address-cells = <1>; #size-cells = <0>; - reg = <0x078b7000 0x600>; + reg = <0x0 0x078b7000 0x0 0x600>; interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>; clocks = <&gcc GCC_BLSP1_AHB_CLK>, <&gcc GCC_BLSP1_QUP3_I2C_APPS_CLK>; @@ -336,24 +336,24 @@ compatible = "qcom,msm-qgic2"; interrupt-controller; #interrupt-cells = <0x3>; - reg = <0x0b000000 0x1000>, /*GICD*/ - <0x0b002000 0x1000>, /*GICC*/ - <0x0b001000 0x1000>, /*GICH*/ - <0x0b004000 0x1000>; /*GICV*/ + reg = <0x0 0x0b000000 0x0 0x1000>, /*GICD*/ + <0x0 0x0b002000 0x0 0x1000>, /*GICC*/ + <0x0 0x0b001000 0x0 0x1000>, /*GICH*/ + <0x0 0x0b004000 0x0 0x1000>; /*GICV*/ interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>; }; watchdog@b017000 { compatible = "qcom,kpss-wdt"; interrupts = <GIC_SPI 3 IRQ_TYPE_EDGE_RISING>; - reg = <0x0b017000 0x40>; + reg = <0x0 0x0b017000 0x0 0x40>; clocks = <&sleep_clk>; timeout-sec = <10>; }; apcs_glb: mailbox@b111000 { compatible = "qcom,ipq6018-apcs-apps-global"; - reg = <0x0b111000 0x1000>; + reg = <0x0 0x0b111000 0x0 0x1000>; #clock-cells = <1>; clocks = <&a53pll>, <&xo>; clock-names = "pll", "xo"; @@ -362,7 +362,7 @@ a53pll: clock@b116000 { compatible = "qcom,ipq6018-a53pll"; - reg = <0x0b116000 0x40>; + reg = <0x0 0x0b116000 0x0 0x40>; #clock-cells = <0>; clocks = <&xo>; clock-names = "xo"; @@ -377,68 +377,68 @@ }; timer@b120000 { - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; ranges; compatible = "arm,armv7-timer-mem"; - reg = <0x0b120000 0x1000>; + reg = <0x0 0x0b120000 0x0 0x1000>; clock-frequency = <19200000>; frame@b120000 { frame-number = <0>; interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b121000 0x1000>, - <0x0b122000 0x1000>; + reg = <0x0 0x0b121000 0x0 0x1000>, + <0x0 0x0b122000 0x0 0x1000>; }; frame@b123000 { frame-number = <1>; interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>; - reg = <0xb123000 0x1000>; + reg = <0x0 0xb123000 0x0 0x1000>; status = "disabled"; }; frame@b124000 { frame-number = <2>; interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b124000 0x1000>; + reg = <0x0 0x0b124000 0x0 0x1000>; status = "disabled"; }; frame@b125000 { frame-number = <3>; interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b125000 0x1000>; + reg = <0x0 0x0b125000 0x0 0x1000>; status = "disabled"; }; frame@b126000 { frame-number = <4>; interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b126000 0x1000>; + reg = <0x0 0x0b126000 0x0 0x1000>; status = "disabled"; }; frame@b127000 { frame-number = <5>; interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b127000 0x1000>; + reg = <0x0 0x0b127000 0x0 0x1000>; status = "disabled"; }; frame@b128000 { frame-number = <6>; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; - reg = <0x0b128000 0x1000>; + reg = <0x0 0x0b128000 0x0 0x1000>; status = "disabled"; }; }; q6v5_wcss: remoteproc@cd00000 { compatible = "qcom,ipq8074-wcss-pil"; - reg = <0x0cd00000 0x4040>, - <0x004ab000 0x20>; + reg = <0x0 0x0cd00000 0x0 0x4040>, + <0x0 0x004ab000 0x0 0x20>; reg-names = "qdsp6", "rmb"; interrupts-extended = <&intc GIC_SPI 325 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi index 9cbf963aa068..c29643442e91 100644 --- a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi @@ -28,6 +28,12 @@ clock-frequency = <0>; }; + audio_clk_b: audio_clk_b { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + audio_clk_c: audio_clk_c { compatible = "fixed-clock"; #clock-cells = <0>; diff --git a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts index 35bd6b904b9c..337681038519 100644 --- a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts +++ b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go2.dts @@ -243,7 +243,6 @@ interrupts = <RK_PB2 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&pmic_int>; - rockchip,system-power-controller; wakeup-source; #clock-cells = <1>; clock-output-names = "rk808-clkout1", "xin32k"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts index be7a31d81632..2ee07d15a6e3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts @@ -20,7 +20,7 @@ gmac_clk: gmac-clock { compatible = "fixed-clock"; clock-frequency = <125000000>; - clock-output-names = "gmac_clk"; + clock-output-names = "gmac_clkin"; #clock-cells = <0>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi index e7a459fa4322..20309076dbac 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc.dtsi @@ -74,14 +74,14 @@ label = "red:diy"; gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>; default-state = "off"; - linux,default-trigger = "mmc1"; + linux,default-trigger = "mmc2"; }; yellow_led: led-2 { label = "yellow:yellow-led"; gpios = <&gpio0 RK_PA2 GPIO_ACTIVE_HIGH>; default-state = "off"; - linux,default-trigger = "mmc0"; + linux,default-trigger = "mmc1"; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index ada724b12f01..7a9a7aca86c6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -29,6 +29,9 @@ i2c6 = &i2c6; i2c7 = &i2c7; i2c8 = &i2c8; + mmc0 = &sdio0; + mmc1 = &sdmmc; + mmc2 = &sdhci; serial0 = &uart0; serial1 = &uart1; serial2 = &uart2; diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 97244d4feca9..da250e4741bd 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -268,6 +268,8 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; /* * CPU feature detected at boot time based on feature of one or more CPUs. * All possible conflicts for a late CPU are ignored. + * NOTE: this means that a late CPU with the feature will *not* cause the + * capability to be advertised by cpus_have_*cap()! */ #define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 9e2e9a63c7b6..ef5b040dee44 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -86,6 +86,8 @@ #define QCOM_CPU_PART_FALKOR_V1 0x800 #define QCOM_CPU_PART_FALKOR 0xC00 #define QCOM_CPU_PART_KRYO 0x200 +#define QCOM_CPU_PART_KRYO_2XX_GOLD 0x800 +#define QCOM_CPU_PART_KRYO_2XX_SILVER 0x801 #define QCOM_CPU_PART_KRYO_3XX_SILVER 0x803 #define QCOM_CPU_PART_KRYO_4XX_GOLD 0x804 #define QCOM_CPU_PART_KRYO_4XX_SILVER 0x805 @@ -116,6 +118,8 @@ #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO) +#define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD) +#define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER) #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER) #define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD) #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER) diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index ec213b4a1650..1c26d7baa67f 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -128,6 +128,9 @@ static inline void local_daif_inherit(struct pt_regs *regs) { unsigned long flags = regs->pstate & DAIF_MASK; + if (interrupts_enabled(regs)) + trace_hardirqs_on(); + /* * We can't use local_daif_restore(regs->pstate) here as * system_has_prio_mask_debugging() won't restore the I bit if it can diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 22c81f1edda2..85a3e49f92f4 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -104,6 +104,7 @@ /* Shared ISS fault status code(IFSC/DFSC) for Data/Instruction aborts */ #define ESR_ELx_FSC (0x3F) #define ESR_ELx_FSC_TYPE (0x3C) +#define ESR_ELx_FSC_LEVEL (0x03) #define ESR_ELx_FSC_EXTABT (0x10) #define ESR_ELx_FSC_SERROR (0x11) #define ESR_ELx_FSC_ACCESS (0x08) diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 99b9383cd036..0756191f44f6 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -31,7 +31,12 @@ static inline u32 disr_to_esr(u64 disr) return esr; } +asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs); +asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs); asmlinkage void enter_from_user_mode(void); +asmlinkage void exit_to_user_mode(void); +void arm64_enter_nmi(struct pt_regs *regs); +void arm64_exit_nmi(struct pt_regs *regs); void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); void do_undefinstr(struct pt_regs *regs); void do_bti(struct pt_regs *regs); diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 5ef2669ccd6c..00bc6f1234ba 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -350,6 +350,11 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vc return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE; } +static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_LEVEL; +} + static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu) { switch (kvm_vcpu_trap_get_fault(vcpu)) { diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 781d029b8aa8..0cd9f0f75c13 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -118,6 +118,8 @@ struct kvm_arch { */ unsigned long *pmu_filter; unsigned int pmuver; + + u8 pfr0_csv2; }; struct kvm_vcpu_fault_info { diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 4ff12a7adcfd..5628289b9d5e 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -115,8 +115,6 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) -#define pte_valid_young(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) #define pte_valid_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) @@ -124,9 +122,12 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; * Could the pte be present in the TLB? We must check mm_tlb_flush_pending * so that we don't erroneously return false for pages that have been * remapped as PROT_NONE but are yet to be flushed from the TLB. + * Note that we can't make any assumptions based on the state of the access + * flag, since ptep_clear_flush_young() elides a DSB when invalidating the + * TLB. */ #define pte_accessible(mm, pte) \ - (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte)) + (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) /* * p??_access_permitted() is true for valid user mappings (subject to the @@ -164,13 +165,6 @@ static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot) return pmd; } -static inline pte_t pte_wrprotect(pte_t pte) -{ - pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); - pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); - return pte; -} - static inline pte_t pte_mkwrite(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); @@ -196,6 +190,20 @@ static inline pte_t pte_mkdirty(pte_t pte) return pte; } +static inline pte_t pte_wrprotect(pte_t pte) +{ + /* + * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY + * clear), set the PTE_DIRTY bit. + */ + if (pte_hw_dirty(pte)) + pte = pte_mkdirty(pte); + + pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); + pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); + return pte; +} + static inline pte_t pte_mkold(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_AF)); @@ -845,12 +853,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres pte = READ_ONCE(*ptep); do { old_pte = pte; - /* - * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY - * clear), set the PTE_DIRTY bit. - */ - if (pte_hw_dirty(pte)) - pte = pte_mkdirty(pte); pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); diff --git a/arch/arm64/include/asm/probes.h b/arch/arm64/include/asm/probes.h index 4266262101fe..006946745352 100644 --- a/arch/arm64/include/asm/probes.h +++ b/arch/arm64/include/asm/probes.h @@ -7,6 +7,8 @@ #ifndef _ARM_PROBES_H #define _ARM_PROBES_H +#include <asm/insn.h> + typedef u32 probe_opcode_t; typedef void (probes_handler_t) (u32 opcode, long addr, struct pt_regs *); diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 997cf8c8cd52..28c85b87b8cd 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -193,6 +193,10 @@ struct pt_regs { /* Only valid when ARM64_HAS_IRQ_PRIO_MASKING is enabled. */ u64 pmr_save; u64 stackframe[2]; + + /* Only valid for some EL1 exceptions. */ + u64 lockdep_hardirqs; + u64 exit_rcu; }; static inline bool in_syscall(struct pt_regs const *regs) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 174817ba119c..801861d05426 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -372,6 +372,8 @@ #define SYS_CONTEXTIDR_EL1 sys_reg(3, 0, 13, 0, 1) #define SYS_TPIDR_EL1 sys_reg(3, 0, 13, 0, 4) +#define SYS_SCXTNUM_EL1 sys_reg(3, 0, 13, 0, 7) + #define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0) #define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0) @@ -404,6 +406,8 @@ #define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2) #define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3) +#define SYS_SCXTNUM_EL0 sys_reg(3, 3, 13, 0, 7) + /* Definitions for system register interface to AMU for ARMv8.4 onwards */ #define SYS_AM_EL0(crm, op2) sys_reg(3, 3, 13, (crm), (op2)) #define SYS_AMCR_EL0 SYS_AM_EL0(2, 0) @@ -983,7 +987,7 @@ #define SYS_TFSR_EL1_TF0_SHIFT 0 #define SYS_TFSR_EL1_TF1_SHIFT 1 #define SYS_TFSR_EL1_TF0 (UL(1) << SYS_TFSR_EL1_TF0_SHIFT) -#define SYS_TFSR_EL1_TF1 (UK(2) << SYS_TFSR_EL1_TF1_SHIFT) +#define SYS_TFSR_EL1_TF1 (UL(1) << SYS_TFSR_EL1_TF1_SHIFT) /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */ #define SYS_MPIDR_SAFE_VAL (BIT(31)) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 61314fd70f13..cafaf0da05b7 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -299,6 +299,8 @@ static const struct midr_range erratum_845719_list[] = { MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4), /* Brahma-B53 r0p[0] */ MIDR_REV(MIDR_BRAHMA_B53, 0, 0), + /* Kryo2XX Silver rAp4 */ + MIDR_REV(MIDR_QCOM_KRYO_2XX_SILVER, 0xa, 0x4), {}, }; #endif diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index dcc165b3fc04..6f36c4f62f69 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1337,6 +1337,8 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_GOLD), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 43d4c329775f..70e0a7591245 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -17,40 +17,164 @@ #include <asm/mmu.h> #include <asm/sysreg.h> -static void notrace el1_abort(struct pt_regs *regs, unsigned long esr) +/* + * This is intended to match the logic in irqentry_enter(), handling the kernel + * mode transitions only. + */ +static void noinstr enter_from_kernel_mode(struct pt_regs *regs) +{ + regs->exit_rcu = false; + + if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) { + lockdep_hardirqs_off(CALLER_ADDR0); + rcu_irq_enter(); + trace_hardirqs_off_finish(); + + regs->exit_rcu = true; + return; + } + + lockdep_hardirqs_off(CALLER_ADDR0); + rcu_irq_enter_check_tick(); + trace_hardirqs_off_finish(); +} + +/* + * This is intended to match the logic in irqentry_exit(), handling the kernel + * mode transitions only, and with preemption handled elsewhere. + */ +static void noinstr exit_to_kernel_mode(struct pt_regs *regs) +{ + lockdep_assert_irqs_disabled(); + + if (interrupts_enabled(regs)) { + if (regs->exit_rcu) { + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + rcu_irq_exit(); + lockdep_hardirqs_on(CALLER_ADDR0); + return; + } + + trace_hardirqs_on(); + } else { + if (regs->exit_rcu) + rcu_irq_exit(); + } +} + +void noinstr arm64_enter_nmi(struct pt_regs *regs) +{ + regs->lockdep_hardirqs = lockdep_hardirqs_enabled(); + + __nmi_enter(); + lockdep_hardirqs_off(CALLER_ADDR0); + lockdep_hardirq_enter(); + rcu_nmi_enter(); + + trace_hardirqs_off_finish(); + ftrace_nmi_enter(); +} + +void noinstr arm64_exit_nmi(struct pt_regs *regs) +{ + bool restore = regs->lockdep_hardirqs; + + ftrace_nmi_exit(); + if (restore) { + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + } + + rcu_nmi_exit(); + lockdep_hardirq_exit(); + if (restore) + lockdep_hardirqs_on(CALLER_ADDR0); + __nmi_exit(); +} + +asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs)) + arm64_enter_nmi(regs); + else + enter_from_kernel_mode(regs); +} + +asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs)) + arm64_exit_nmi(regs); + else + exit_to_kernel_mode(regs); +} + +static void noinstr el1_abort(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); + enter_from_kernel_mode(regs); local_daif_inherit(regs); far = untagged_addr(far); do_mem_abort(far, esr, regs); + local_daif_mask(); + exit_to_kernel_mode(regs); } -NOKPROBE_SYMBOL(el1_abort); -static void notrace el1_pc(struct pt_regs *regs, unsigned long esr) +static void noinstr el1_pc(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); + enter_from_kernel_mode(regs); local_daif_inherit(regs); do_sp_pc_abort(far, esr, regs); + local_daif_mask(); + exit_to_kernel_mode(regs); } -NOKPROBE_SYMBOL(el1_pc); -static void notrace el1_undef(struct pt_regs *regs) +static void noinstr el1_undef(struct pt_regs *regs) { + enter_from_kernel_mode(regs); local_daif_inherit(regs); do_undefinstr(regs); + local_daif_mask(); + exit_to_kernel_mode(regs); } -NOKPROBE_SYMBOL(el1_undef); -static void notrace el1_inv(struct pt_regs *regs, unsigned long esr) +static void noinstr el1_inv(struct pt_regs *regs, unsigned long esr) { + enter_from_kernel_mode(regs); local_daif_inherit(regs); bad_mode(regs, 0, esr); + local_daif_mask(); + exit_to_kernel_mode(regs); } -NOKPROBE_SYMBOL(el1_inv); -static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr) +static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs) +{ + regs->lockdep_hardirqs = lockdep_hardirqs_enabled(); + + lockdep_hardirqs_off(CALLER_ADDR0); + rcu_nmi_enter(); + + trace_hardirqs_off_finish(); +} + +static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs) +{ + bool restore = regs->lockdep_hardirqs; + + if (restore) { + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + } + + rcu_nmi_exit(); + if (restore) + lockdep_hardirqs_on(CALLER_ADDR0); +} + +static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); @@ -62,18 +186,21 @@ static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr) if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + arm64_enter_el1_dbg(regs); do_debug_exception(far, esr, regs); + arm64_exit_el1_dbg(regs); } -NOKPROBE_SYMBOL(el1_dbg); -static void notrace el1_fpac(struct pt_regs *regs, unsigned long esr) +static void noinstr el1_fpac(struct pt_regs *regs, unsigned long esr) { + enter_from_kernel_mode(regs); local_daif_inherit(regs); do_ptrauth_fault(regs, esr); + local_daif_mask(); + exit_to_kernel_mode(regs); } -NOKPROBE_SYMBOL(el1_fpac); -asmlinkage void notrace el1_sync_handler(struct pt_regs *regs) +asmlinkage void noinstr el1_sync_handler(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); @@ -106,20 +233,34 @@ asmlinkage void notrace el1_sync_handler(struct pt_regs *regs) el1_inv(regs, esr); } } -NOKPROBE_SYMBOL(el1_sync_handler); -static void notrace el0_da(struct pt_regs *regs, unsigned long esr) +asmlinkage void noinstr enter_from_user_mode(void) +{ + lockdep_hardirqs_off(CALLER_ADDR0); + CT_WARN_ON(ct_state() != CONTEXT_USER); + user_exit_irqoff(); + trace_hardirqs_off_finish(); +} + +asmlinkage void noinstr exit_to_user_mode(void) +{ + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + user_enter_irqoff(); + lockdep_hardirqs_on(CALLER_ADDR0); +} + +static void noinstr el0_da(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); far = untagged_addr(far); do_mem_abort(far, esr, regs); } -NOKPROBE_SYMBOL(el0_da); -static void notrace el0_ia(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_ia(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); @@ -131,90 +272,80 @@ static void notrace el0_ia(struct pt_regs *regs, unsigned long esr) if (!is_ttbr0_addr(far)) arm64_apply_bp_hardening(); - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_mem_abort(far, esr, regs); } -NOKPROBE_SYMBOL(el0_ia); -static void notrace el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_fpsimd_acc(esr, regs); } -NOKPROBE_SYMBOL(el0_fpsimd_acc); -static void notrace el0_sve_acc(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_sve_acc(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_sve_acc(esr, regs); } -NOKPROBE_SYMBOL(el0_sve_acc); -static void notrace el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_fpsimd_exc(esr, regs); } -NOKPROBE_SYMBOL(el0_fpsimd_exc); -static void notrace el0_sys(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_sys(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_sysinstr(esr, regs); } -NOKPROBE_SYMBOL(el0_sys); -static void notrace el0_pc(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_pc(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); if (!is_ttbr0_addr(instruction_pointer(regs))) arm64_apply_bp_hardening(); - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_sp_pc_abort(far, esr, regs); } -NOKPROBE_SYMBOL(el0_pc); -static void notrace el0_sp(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_sp(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_sp_pc_abort(regs->sp, esr, regs); } -NOKPROBE_SYMBOL(el0_sp); -static void notrace el0_undef(struct pt_regs *regs) +static void noinstr el0_undef(struct pt_regs *regs) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_undefinstr(regs); } -NOKPROBE_SYMBOL(el0_undef); -static void notrace el0_bti(struct pt_regs *regs) +static void noinstr el0_bti(struct pt_regs *regs) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_bti(regs); } -NOKPROBE_SYMBOL(el0_bti); -static void notrace el0_inv(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_inv(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); bad_el0_sync(regs, 0, esr); } -NOKPROBE_SYMBOL(el0_inv); -static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_dbg(struct pt_regs *regs, unsigned long esr) { /* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */ unsigned long far = read_sysreg(far_el1); @@ -222,30 +353,28 @@ static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr) if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - user_exit_irqoff(); + enter_from_user_mode(); do_debug_exception(far, esr, regs); local_daif_restore(DAIF_PROCCTX_NOIRQ); } -NOKPROBE_SYMBOL(el0_dbg); -static void notrace el0_svc(struct pt_regs *regs) +static void noinstr el0_svc(struct pt_regs *regs) { if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + enter_from_user_mode(); do_el0_svc(regs); } -NOKPROBE_SYMBOL(el0_svc); -static void notrace el0_fpac(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_fpac(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_ptrauth_fault(regs, esr); } -NOKPROBE_SYMBOL(el0_fpac); -asmlinkage void notrace el0_sync_handler(struct pt_regs *regs) +asmlinkage void noinstr el0_sync_handler(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); @@ -297,27 +426,25 @@ asmlinkage void notrace el0_sync_handler(struct pt_regs *regs) el0_inv(regs, esr); } } -NOKPROBE_SYMBOL(el0_sync_handler); #ifdef CONFIG_COMPAT -static void notrace el0_cp15(struct pt_regs *regs, unsigned long esr) +static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr) { - user_exit_irqoff(); + enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); do_cp15instr(esr, regs); } -NOKPROBE_SYMBOL(el0_cp15); -static void notrace el0_svc_compat(struct pt_regs *regs) +static void noinstr el0_svc_compat(struct pt_regs *regs) { if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + enter_from_user_mode(); do_el0_svc_compat(regs); } -NOKPROBE_SYMBOL(el0_svc_compat); -asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs) +asmlinkage void noinstr el0_sync_compat_handler(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); @@ -360,5 +487,4 @@ asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs) el0_inv(regs, esr); } } -NOKPROBE_SYMBOL(el0_sync_compat_handler); #endif /* CONFIG_COMPAT */ diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index b295fb912b12..d72c818b019c 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -30,18 +30,18 @@ #include <asm/unistd.h> /* - * Context tracking subsystem. Used to instrument transitions - * between user and kernel mode. + * Context tracking and irqflag tracing need to instrument transitions between + * user and kernel mode. */ - .macro ct_user_exit_irqoff -#ifdef CONFIG_CONTEXT_TRACKING + .macro user_exit_irqoff +#if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS) bl enter_from_user_mode #endif .endm - .macro ct_user_enter -#ifdef CONFIG_CONTEXT_TRACKING - bl context_tracking_user_enter + .macro user_enter_irqoff +#if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS) + bl exit_to_user_mode #endif .endm @@ -298,9 +298,6 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING alternative_else_nop_endif ldp x21, x22, [sp, #S_PC] // load ELR, SPSR - .if \el == 0 - ct_user_enter - .endif #ifdef CONFIG_ARM64_SW_TTBR0_PAN alternative_if_not ARM64_HAS_PAN @@ -637,16 +634,8 @@ SYM_CODE_START_LOCAL_NOALIGN(el1_irq) gic_prio_irq_setup pmr=x20, tmp=x1 enable_da_f -#ifdef CONFIG_ARM64_PSEUDO_NMI - test_irqs_unmasked res=x0, pmr=x20 - cbz x0, 1f - bl asm_nmi_enter -1: -#endif - -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif + mov x0, sp + bl enter_el1_irq_or_nmi irq_handler @@ -665,26 +654,8 @@ alternative_else_nop_endif 1: #endif -#ifdef CONFIG_ARM64_PSEUDO_NMI - /* - * When using IRQ priority masking, we can get spurious interrupts while - * PMR is set to GIC_PRIO_IRQOFF. An NMI might also have occurred in a - * section with interrupts disabled. Skip tracing in those cases. - */ - test_irqs_unmasked res=x0, pmr=x20 - cbz x0, 1f - bl asm_nmi_exit -1: -#endif - -#ifdef CONFIG_TRACE_IRQFLAGS -#ifdef CONFIG_ARM64_PSEUDO_NMI - test_irqs_unmasked res=x0, pmr=x20 - cbnz x0, 1f -#endif - bl trace_hardirqs_on -1: -#endif + mov x0, sp + bl exit_el1_irq_or_nmi kernel_exit 1 SYM_CODE_END(el1_irq) @@ -726,21 +697,14 @@ SYM_CODE_START_LOCAL_NOALIGN(el0_irq) kernel_entry 0 el0_irq_naked: gic_prio_irq_setup pmr=x20, tmp=x0 - ct_user_exit_irqoff + user_exit_irqoff enable_da_f -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif - tbz x22, #55, 1f bl do_el0_irq_bp_hardening 1: irq_handler -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_on -#endif b ret_to_user SYM_CODE_END(el0_irq) @@ -759,7 +723,7 @@ SYM_CODE_START_LOCAL(el0_error) el0_error_naked: mrs x25, esr_el1 gic_prio_kentry_setup tmp=x2 - ct_user_exit_irqoff + user_exit_irqoff enable_dbg mov x0, sp mov x1, x25 @@ -774,13 +738,17 @@ SYM_CODE_END(el0_error) SYM_CODE_START_LOCAL(ret_to_user) disable_daif gic_prio_kentry_setup tmp=x3 - ldr x1, [tsk, #TSK_TI_FLAGS] - and x2, x1, #_TIF_WORK_MASK +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off +#endif + ldr x19, [tsk, #TSK_TI_FLAGS] + and x2, x19, #_TIF_WORK_MASK cbnz x2, work_pending finish_ret_to_user: + user_enter_irqoff /* Ignore asynchronous tag check faults in the uaccess routines */ clear_mte_async_tcf - enable_step_tsk x1, x2 + enable_step_tsk x19, x2 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK bl stackleak_erase #endif @@ -791,11 +759,9 @@ finish_ret_to_user: */ work_pending: mov x0, sp // 'regs' + mov x1, x19 bl do_notify_resume -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_on // enabled while in userspace -#endif - ldr x1, [tsk, #TSK_TI_FLAGS] // re-check for single-step + ldr x19, [tsk, #TSK_TI_FLAGS] // re-check for single-step b finish_ret_to_user SYM_CODE_END(ret_to_user) diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 9cf2fb87584a..60456a62da11 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -67,18 +67,3 @@ void __init init_IRQ(void) local_daif_restore(DAIF_PROCCTX_NOIRQ); } } - -/* - * Stubs to make nmi_enter/exit() code callable from ASM - */ -asmlinkage void notrace asm_nmi_enter(void) -{ - nmi_enter(); -} -NOKPROBE_SYMBOL(asm_nmi_enter); - -asmlinkage void notrace asm_nmi_exit(void) -{ - nmi_exit(); -} -NOKPROBE_SYMBOL(asm_nmi_exit); diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c index 66adee8b5fc8..9ec34690e255 100644 --- a/arch/arm64/kernel/kexec_image.c +++ b/arch/arm64/kernel/kexec_image.c @@ -127,7 +127,7 @@ static void *image_load(struct kimage *image, kernel_segment->mem, kbuf.bufsz, kernel_segment->memsz); - return 0; + return NULL; } #ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 94e8718e7229..f6f58e6265df 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -73,8 +73,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 4784011cecac..ed919f633ed8 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -72,13 +72,13 @@ EXPORT_SYMBOL_GPL(pm_power_off); void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd); -static void __cpu_do_idle(void) +static void noinstr __cpu_do_idle(void) { dsb(sy); wfi(); } -static void __cpu_do_idle_irqprio(void) +static void noinstr __cpu_do_idle_irqprio(void) { unsigned long pmr; unsigned long daif_bits; @@ -108,7 +108,7 @@ static void __cpu_do_idle_irqprio(void) * ensure that interrupts are not masked at the PMR (because the core will * not wake up if we block the wake up signal in the interrupt controller). */ -void cpu_do_idle(void) +void noinstr cpu_do_idle(void) { if (system_uses_irq_prio_masking()) __cpu_do_idle_irqprio(); @@ -119,14 +119,14 @@ void cpu_do_idle(void) /* * This is our default idle handler. */ -void arch_cpu_idle(void) +void noinstr arch_cpu_idle(void) { /* * This should do all the clock switching and wait for interrupt * tricks */ cpu_do_idle(); - local_irq_enable(); + raw_local_irq_enable(); } #ifdef CONFIG_HOTPLUG_CPU @@ -522,14 +522,13 @@ static void erratum_1418040_thread_switch(struct task_struct *prev, bool prev32, next32; u64 val; - if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) && - cpus_have_const_cap(ARM64_WORKAROUND_1418040))) + if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040)) return; prev32 = is_compat_thread(task_thread_info(prev)); next32 = is_compat_thread(task_thread_info(next)); - if (prev32 == next32) + if (prev32 == next32 || !this_cpu_has_cap(ARM64_WORKAROUND_1418040)) return; val = read_sysreg(cntkctl_el1); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index c18eb7d41274..f6e4e3737405 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -118,6 +118,7 @@ static enum mitigation_state spectre_v2_get_cpu_hw_mitigation_state(void) MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 43ae4e0c968f..62d2bda7adb8 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -66,7 +66,6 @@ static int cpu_psci_cpu_disable(unsigned int cpu) static void cpu_psci_cpu_die(unsigned int cpu) { - int ret; /* * There are no known implementations of PSCI actually using the * power state field, pass a sensible default for now. @@ -74,9 +73,7 @@ static void cpu_psci_cpu_die(unsigned int cpu) u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN << PSCI_0_2_POWER_STATE_TYPE_SHIFT; - ret = psci_ops.cpu_off(state); - - pr_crit("unable to power off CPU%u (%d)\n", cpu, ret); + psci_ops.cpu_off(state); } static int cpu_psci_cpu_kill(unsigned int cpu) diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index 7689f2031c0c..793c46d6a447 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -10,6 +10,7 @@ #include <linux/uaccess.h> #include <asm/alternative.h> +#include <asm/exception.h> #include <asm/kprobes.h> #include <asm/mmu.h> #include <asm/ptrace.h> @@ -223,16 +224,16 @@ static __kprobes unsigned long _sdei_handler(struct pt_regs *regs, } -asmlinkage __kprobes notrace unsigned long +asmlinkage noinstr unsigned long __sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg) { unsigned long ret; - nmi_enter(); + arm64_enter_nmi(regs); ret = _sdei_handler(regs, arg); - nmi_exit(); + arm64_exit_nmi(regs); return ret; } diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 09c96f57818c..18e9727d3f64 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -413,6 +413,7 @@ void cpu_die_early(void) /* Mark this CPU absent */ set_cpu_present(cpu, 0); + rcu_report_dead(cpu); if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) { update_cpu_boot_status(CPU_KILL_ME); diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index e4c0dadf0d92..f8f758e4a306 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -121,7 +121,6 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, cortex_a76_erratum_1463225_svc_handler(); local_daif_restore(DAIF_PROCCTX); - user_exit(); if (system_supports_mte() && (flags & _TIF_MTE_ASYNC_FAULT)) { /* diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 8af4e0e85736..2059d8f43f55 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -34,6 +34,7 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/esr.h> +#include <asm/exception.h> #include <asm/extable.h> #include <asm/insn.h> #include <asm/kprobes.h> @@ -753,8 +754,10 @@ const char *esr_get_class_string(u32 esr) * bad_mode handles the impossible case in the exception vector. This is always * fatal. */ -asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) +asmlinkage void notrace bad_mode(struct pt_regs *regs, int reason, unsigned int esr) { + arm64_enter_nmi(regs); + console_verbose(); pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n", @@ -786,7 +789,7 @@ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack) __aligned(16); -asmlinkage void handle_bad_stack(struct pt_regs *regs) +asmlinkage void noinstr handle_bad_stack(struct pt_regs *regs) { unsigned long tsk_stk = (unsigned long)current->stack; unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr); @@ -794,6 +797,8 @@ asmlinkage void handle_bad_stack(struct pt_regs *regs) unsigned int esr = read_sysreg(esr_el1); unsigned long far = read_sysreg(far_el1); + arm64_enter_nmi(regs); + console_verbose(); pr_emerg("Insufficient stack space to handle exception!"); @@ -865,23 +870,16 @@ bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr) } } -asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr) +asmlinkage void noinstr do_serror(struct pt_regs *regs, unsigned int esr) { - nmi_enter(); + arm64_enter_nmi(regs); /* non-RAS errors are not containable */ if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr)) arm64_serror_panic(regs, esr); - nmi_exit(); -} - -asmlinkage void enter_from_user_mode(void) -{ - CT_WARN_ON(ct_state() != CONTEXT_USER); - user_exit_irqoff(); + arm64_exit_nmi(regs); } -NOKPROBE_SYMBOL(enter_from_user_mode); /* GENERIC_BUG traps */ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 908df2698a1c..de3ecc34a291 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -102,6 +102,20 @@ static int kvm_arm_default_max_vcpus(void) return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS; } +static void set_default_csv2(struct kvm *kvm) +{ + /* + * The default is to expose CSV2 == 1 if the HW isn't affected. + * Although this is a per-CPU feature, we make it global because + * asymmetric systems are just a nuisance. + * + * Userspace can override this as long as it doesn't promise + * the impossible. + */ + if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED) + kvm->arch.pfr0_csv2 = 1; +} + /** * kvm_arch_init_vm - initializes a VM data structure * @kvm: pointer to the KVM struct @@ -127,6 +141,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) /* The maximum number of VCPUs is limited by the host's GIC model */ kvm->arch.max_vcpus = kvm_arm_default_max_vcpus(); + set_default_csv2(kvm); + return ret; out_free_stage2_pgd: kvm_free_stage2_pgd(&kvm->arch.mmu); diff --git a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S index bb2d986ff696..a797abace13f 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S @@ -13,6 +13,11 @@ SECTIONS { HYP_SECTION(.text) + /* + * .hyp..data..percpu needs to be page aligned to maintain the same + * alignment for when linking into vmlinux. + */ + . = ALIGN(PAGE_SIZE); HYP_SECTION_NAME(.data..percpu) : { PERCPU_INPUT(L1_CACHE_BYTES) } diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 0271b4a3b9fe..bdf8e55ed308 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -470,6 +470,15 @@ static bool stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level, if (!kvm_block_mapping_supported(addr, end, phys, level)) return false; + /* + * If the PTE was already valid, drop the refcount on the table + * early, as it will be bumped-up again in stage2_map_walk_leaf(). + * This ensures that the refcount stays constant across a valid to + * valid PTE update. + */ + if (kvm_pte_valid(*ptep)) + put_page(virt_to_page(ptep)); + if (kvm_set_valid_leaf_pte(ptep, phys, data->attr, level)) goto out; @@ -493,7 +502,13 @@ static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level, return 0; kvm_set_invalid_pte(ptep); - kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, data->mmu, addr, 0); + + /* + * Invalidate the whole stage-2, as we may have numerous leaf + * entries below us which would otherwise need invalidating + * individually. + */ + kvm_call_hyp(__kvm_tlb_flush_vmid, data->mmu); data->anchor = ptep; return 0; } diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 57972bdb213a..75814a02d189 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -754,10 +754,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, gfn_t gfn; kvm_pfn_t pfn; bool logging_active = memslot_is_logging(memslot); - unsigned long vma_pagesize; + unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu); + unsigned long vma_pagesize, fault_granule; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; struct kvm_pgtable *pgt; + fault_granule = 1UL << ARM64_HW_PGTABLE_LEVEL_SHIFT(fault_level); write_fault = kvm_is_write_fault(vcpu); exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); VM_BUG_ON(write_fault && exec_fault); @@ -788,10 +790,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, } switch (vma_shift) { +#ifndef __PAGETABLE_PMD_FOLDED case PUD_SHIFT: if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE)) break; fallthrough; +#endif case CONT_PMD_SHIFT: vma_shift = PMD_SHIFT; fallthrough; @@ -894,7 +898,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, else if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC)) prot |= KVM_PGTABLE_PROT_X; - if (fault_status == FSC_PERM && !(logging_active && writable)) { + /* + * Under the premise of getting a FSC_PERM fault, we just need to relax + * permissions only if vma_pagesize equals fault_granule. Otherwise, + * kvm_pgtable_stage2_map() should be called to change block size. + */ + if (fault_status == FSC_PERM && vma_pagesize == fault_granule) { ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot); } else { ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize, diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index fb12d3ef423a..c1fac9836af1 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1038,8 +1038,8 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { SYS_DESC(SYS_PMEVTYPERn_EL0(n)), \ access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), } -static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p, - const struct sys_reg_desc *r) +static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) { kvm_inject_undefined(vcpu); @@ -1047,33 +1047,25 @@ static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p, } /* Macro to expand the AMU counter and type registers*/ -#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu } -#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), access_amu } -#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu } -#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), access_amu } - -static bool trap_ptrauth(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) -{ - /* - * If we land here, that is because we didn't fixup the access on exit - * by allowing the PtrAuth sysregs. The only way this happens is when - * the guest does not have PtrAuth support enabled. - */ - kvm_inject_undefined(vcpu); - - return false; -} +#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), undef_access } +#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), undef_access } +#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), undef_access } +#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), undef_access } static unsigned int ptrauth_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN_USER | REG_HIDDEN_GUEST; + return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN; } +/* + * If we land here on a PtrAuth access, that is because we didn't + * fixup the access on exit by allowing the PtrAuth sysregs. The only + * way this happens is when the guest does not have PtrAuth support + * enabled. + */ #define __PTRAUTH_KEY(k) \ - { SYS_DESC(SYS_## k), trap_ptrauth, reset_unknown, k, \ + { SYS_DESC(SYS_## k), undef_access, reset_unknown, k, \ .visibility = ptrauth_visibility} #define PTRAUTH_KEY(k) \ @@ -1128,9 +1120,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, if (!vcpu_has_sve(vcpu)) val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT); val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT); - if (!(val & (0xfUL << ID_AA64PFR0_CSV2_SHIFT)) && - arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED) - val |= (1UL << ID_AA64PFR0_CSV2_SHIFT); + val &= ~(0xfUL << ID_AA64PFR0_CSV2_SHIFT); + val |= ((u64)vcpu->kvm->arch.pfr0_csv2 << ID_AA64PFR0_CSV2_SHIFT); } else if (id == SYS_ID_AA64PFR1_EL1) { val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT); } else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) { @@ -1153,6 +1144,22 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, return val; } +static unsigned int id_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) +{ + u32 id = sys_reg((u32)r->Op0, (u32)r->Op1, + (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + + switch (id) { + case SYS_ID_AA64ZFR0_EL1: + if (!vcpu_has_sve(vcpu)) + return REG_RAZ; + break; + } + + return 0; +} + /* cpufeature ID register access trap handlers */ static bool __access_id_reg(struct kvm_vcpu *vcpu, @@ -1171,7 +1178,9 @@ static bool access_id_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - return __access_id_reg(vcpu, p, r, false); + bool raz = sysreg_visible_as_raz(vcpu, r); + + return __access_id_reg(vcpu, p, r, raz); } static bool access_raz_id_reg(struct kvm_vcpu *vcpu, @@ -1192,71 +1201,40 @@ static unsigned int sve_visibility(const struct kvm_vcpu *vcpu, if (vcpu_has_sve(vcpu)) return 0; - return REG_HIDDEN_USER | REG_HIDDEN_GUEST; -} - -/* Visibility overrides for SVE-specific ID registers */ -static unsigned int sve_id_visibility(const struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd) -{ - if (vcpu_has_sve(vcpu)) - return 0; - - return REG_HIDDEN_USER; + return REG_HIDDEN; } -/* Generate the emulated ID_AA64ZFR0_EL1 value exposed to the guest */ -static u64 guest_id_aa64zfr0_el1(const struct kvm_vcpu *vcpu) -{ - if (!vcpu_has_sve(vcpu)) - return 0; - - return read_sanitised_ftr_reg(SYS_ID_AA64ZFR0_EL1); -} - -static bool access_id_aa64zfr0_el1(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) -{ - if (p->is_write) - return write_to_read_only(vcpu, p, rd); - - p->regval = guest_id_aa64zfr0_el1(vcpu); - return true; -} - -static int get_id_aa64zfr0_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd, - const struct kvm_one_reg *reg, void __user *uaddr) -{ - u64 val; - - if (WARN_ON(!vcpu_has_sve(vcpu))) - return -ENOENT; - - val = guest_id_aa64zfr0_el1(vcpu); - return reg_to_user(uaddr, &val, reg->id); -} - -static int set_id_aa64zfr0_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd, - const struct kvm_one_reg *reg, void __user *uaddr) +static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) { const u64 id = sys_reg_to_index(rd); int err; u64 val; - - if (WARN_ON(!vcpu_has_sve(vcpu))) - return -ENOENT; + u8 csv2; err = reg_from_user(&val, uaddr, id); if (err) return err; - /* This is what we mean by invariant: you can't change it. */ - if (val != guest_id_aa64zfr0_el1(vcpu)) + /* + * Allow AA64PFR0_EL1.CSV2 to be set from userspace as long as + * it doesn't promise more than what is actually provided (the + * guest could otherwise be covered in ectoplasmic residue). + */ + csv2 = cpuid_feature_extract_unsigned_field(val, ID_AA64PFR0_CSV2_SHIFT); + if (csv2 > 1 || + (csv2 && arm64_get_spectre_v2_state() != SPECTRE_UNAFFECTED)) return -EINVAL; + /* We can only differ with CSV2, and anything else is an error */ + val ^= read_id_reg(vcpu, rd, false); + val &= ~(0xFUL << ID_AA64PFR0_CSV2_SHIFT); + if (val) + return -EINVAL; + + vcpu->kvm->arch.pfr0_csv2 = csv2; + return 0; } @@ -1299,13 +1277,17 @@ static int __set_id_reg(const struct kvm_vcpu *vcpu, static int get_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - return __get_id_reg(vcpu, rd, uaddr, false); + bool raz = sysreg_visible_as_raz(vcpu, rd); + + return __get_id_reg(vcpu, rd, uaddr, raz); } static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - return __set_id_reg(vcpu, rd, uaddr, false); + bool raz = sysreg_visible_as_raz(vcpu, rd); + + return __set_id_reg(vcpu, rd, uaddr, raz); } static int get_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, @@ -1384,19 +1366,13 @@ static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return true; } -static bool access_mte_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p, - const struct sys_reg_desc *r) -{ - kvm_inject_undefined(vcpu); - return false; -} - /* sys_reg_desc initialiser for known cpufeature ID registers */ #define ID_SANITISED(name) { \ SYS_DESC(SYS_##name), \ .access = access_id_reg, \ .get_user = get_id_reg, \ .set_user = set_id_reg, \ + .visibility = id_visibility, \ } /* @@ -1514,11 +1490,12 @@ static const struct sys_reg_desc sys_reg_descs[] = { /* AArch64 ID registers */ /* CRm=4 */ - ID_SANITISED(ID_AA64PFR0_EL1), + { SYS_DESC(SYS_ID_AA64PFR0_EL1), .access = access_id_reg, + .get_user = get_id_reg, .set_user = set_id_aa64pfr0_el1, }, ID_SANITISED(ID_AA64PFR1_EL1), ID_UNALLOCATED(4,2), ID_UNALLOCATED(4,3), - { SYS_DESC(SYS_ID_AA64ZFR0_EL1), access_id_aa64zfr0_el1, .get_user = get_id_aa64zfr0_el1, .set_user = set_id_aa64zfr0_el1, .visibility = sve_id_visibility }, + ID_SANITISED(ID_AA64ZFR0_EL1), ID_UNALLOCATED(4,5), ID_UNALLOCATED(4,6), ID_UNALLOCATED(4,7), @@ -1557,8 +1534,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 }, { SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 }, - { SYS_DESC(SYS_RGSR_EL1), access_mte_regs }, - { SYS_DESC(SYS_GCR_EL1), access_mte_regs }, + { SYS_DESC(SYS_RGSR_EL1), undef_access }, + { SYS_DESC(SYS_GCR_EL1), undef_access }, { SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility }, { SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 }, @@ -1584,8 +1561,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi }, { SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi }, - { SYS_DESC(SYS_TFSR_EL1), access_mte_regs }, - { SYS_DESC(SYS_TFSRE0_EL1), access_mte_regs }, + { SYS_DESC(SYS_TFSR_EL1), undef_access }, + { SYS_DESC(SYS_TFSRE0_EL1), undef_access }, { SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 }, { SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 }, @@ -1621,6 +1598,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 }, { SYS_DESC(SYS_TPIDR_EL1), NULL, reset_unknown, TPIDR_EL1 }, + { SYS_DESC(SYS_SCXTNUM_EL1), undef_access }, + { SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0}, { SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr }, @@ -1649,14 +1628,16 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, - { SYS_DESC(SYS_AMCR_EL0), access_amu }, - { SYS_DESC(SYS_AMCFGR_EL0), access_amu }, - { SYS_DESC(SYS_AMCGCR_EL0), access_amu }, - { SYS_DESC(SYS_AMUSERENR_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENCLR0_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENSET0_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENCLR1_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENSET1_EL0), access_amu }, + { SYS_DESC(SYS_SCXTNUM_EL0), undef_access }, + + { SYS_DESC(SYS_AMCR_EL0), undef_access }, + { SYS_DESC(SYS_AMCFGR_EL0), undef_access }, + { SYS_DESC(SYS_AMCGCR_EL0), undef_access }, + { SYS_DESC(SYS_AMUSERENR_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENCLR0_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENSET0_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENCLR1_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENSET1_EL0), undef_access }, AMU_AMEVCNTR0_EL0(0), AMU_AMEVCNTR0_EL0(1), AMU_AMEVCNTR0_EL0(2), @@ -2185,7 +2166,7 @@ static void perform_access(struct kvm_vcpu *vcpu, trace_kvm_sys_access(*vcpu_pc(vcpu), params, r); /* Check for regs disabled by runtime config */ - if (sysreg_hidden_from_guest(vcpu, r)) { + if (sysreg_hidden(vcpu, r)) { kvm_inject_undefined(vcpu); return; } @@ -2684,7 +2665,7 @@ int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg return get_invariant_sys_reg(reg->id, uaddr); /* Check for regs disabled by runtime config */ - if (sysreg_hidden_from_user(vcpu, r)) + if (sysreg_hidden(vcpu, r)) return -ENOENT; if (r->get_user) @@ -2709,7 +2690,7 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg return set_invariant_sys_reg(reg->id, uaddr); /* Check for regs disabled by runtime config */ - if (sysreg_hidden_from_user(vcpu, r)) + if (sysreg_hidden(vcpu, r)) return -ENOENT; if (r->set_user) @@ -2780,7 +2761,7 @@ static int walk_one_sys_reg(const struct kvm_vcpu *vcpu, if (!(rd->reg || rd->get_user)) return 0; - if (sysreg_hidden_from_user(vcpu, rd)) + if (sysreg_hidden(vcpu, rd)) return 0; if (!copy_reg_to_user(rd, uind)) diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index 5a6fc30f5989..0f95964339b1 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -59,8 +59,8 @@ struct sys_reg_desc { const struct sys_reg_desc *rd); }; -#define REG_HIDDEN_USER (1 << 0) /* hidden from userspace ioctls */ -#define REG_HIDDEN_GUEST (1 << 1) /* hidden from guest */ +#define REG_HIDDEN (1 << 0) /* hidden from userspace and guest */ +#define REG_RAZ (1 << 1) /* RAZ from userspace and guest */ static __printf(2, 3) inline void print_sys_reg_msg(const struct sys_reg_params *p, @@ -111,22 +111,22 @@ static inline void reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r __vcpu_sys_reg(vcpu, r->reg) = r->val; } -static inline bool sysreg_hidden_from_guest(const struct kvm_vcpu *vcpu, - const struct sys_reg_desc *r) +static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) { if (likely(!r->visibility)) return false; - return r->visibility(vcpu, r) & REG_HIDDEN_GUEST; + return r->visibility(vcpu, r) & REG_HIDDEN; } -static inline bool sysreg_hidden_from_user(const struct kvm_vcpu *vcpu, - const struct sys_reg_desc *r) +static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) { if (likely(!r->visibility)) return false; - return r->visibility(vcpu, r) & REG_HIDDEN_USER; + return r->visibility(vcpu, r) & REG_RAZ; } static inline int cmp_sys_reg(const struct sys_reg_desc *i1, diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 52d6f24f65dc..15a6c98ee92f 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -273,6 +273,23 @@ static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu, return extract_bytes(value, addr & 7, len); } +static unsigned long vgic_uaccess_read_v3r_typer(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu); + int target_vcpu_id = vcpu->vcpu_id; + u64 value; + + value = (u64)(mpidr & GENMASK(23, 0)) << 32; + value |= ((target_vcpu_id & 0xffff) << 8); + + if (vgic_has_its(vcpu->kvm)) + value |= GICR_TYPER_PLPIS; + + /* reporting of the Last bit is not supported for userspace */ + return extract_bytes(value, addr & 7, len); +} + static unsigned long vgic_mmio_read_v3r_iidr(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { @@ -593,8 +610,9 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { REGISTER_DESC_WITH_LENGTH(GICR_IIDR, vgic_mmio_read_v3r_iidr, vgic_mmio_write_wi, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_TYPER, - vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, 8, + REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_TYPER, + vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, + vgic_uaccess_read_v3r_typer, vgic_mmio_uaccess_write_wi, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_WAKER, vgic_mmio_read_raz, vgic_mmio_write_wi, 4, diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 1ee94002801f..795d224f184f 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -789,25 +789,6 @@ void __init hook_debug_fault_code(int nr, */ static void debug_exception_enter(struct pt_regs *regs) { - /* - * Tell lockdep we disabled irqs in entry.S. Do nothing if they were - * already disabled to preserve the last enabled/disabled addresses. - */ - if (interrupts_enabled(regs)) - trace_hardirqs_off(); - - if (user_mode(regs)) { - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - } else { - /* - * We might have interrupted pretty much anything. In - * fact, if we're a debug exception, we can even interrupt - * NMI processing. We don't want this code makes in_nmi() - * to return true, but we need to notify RCU. - */ - rcu_nmi_enter(); - } - preempt_disable(); /* This code is a bit fragile. Test it. */ @@ -818,12 +799,6 @@ NOKPROBE_SYMBOL(debug_exception_enter); static void debug_exception_exit(struct pt_regs *regs) { preempt_enable_no_resched(); - - if (!user_mode(regs)) - rcu_nmi_exit(); - - if (interrupts_enabled(regs)) - trace_hardirqs_on(); } NOKPROBE_SYMBOL(debug_exception_exit); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 1c0f3e02f731..ca692a815731 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1444,11 +1444,28 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size) free_empty_tables(start, end, PAGE_OFFSET, PAGE_END); } +static bool inside_linear_region(u64 start, u64 size) +{ + /* + * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)] + * accommodating both its ends but excluding PAGE_END. Max physical + * range which can be mapped inside this linear mapping range, must + * also be derived from its end points. + */ + return start >= __pa(_PAGE_OFFSET(vabits_actual)) && + (start + size - 1) <= __pa(PAGE_END - 1); +} + int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params) { int ret, flags = 0; + if (!inside_linear_region(start, size)) { + pr_err("[%llx %llx] is outside linear mapping region\n", start, start + size); + return -EINVAL; + } + if (rodata_full || debug_pagealloc_enabled()) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; diff --git a/arch/csky/kernel/perf_regs.c b/arch/csky/kernel/perf_regs.c index eb32838b8210..09b7f88a2d6a 100644 --- a/arch/csky/kernel/perf_regs.c +++ b/arch/csky/kernel/perf_regs.c @@ -32,8 +32,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index f730869e21ee..69af6bc87e64 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -102,6 +102,6 @@ void arch_cpu_idle(void) #ifdef CONFIG_CPU_PM_STOP asm volatile("stop\n"); #endif - local_irq_enable(); + raw_local_irq_enable(); } #endif diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index aea0a40b77a9..bc1364db58fe 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -57,7 +57,7 @@ asmlinkage void ret_from_kernel_thread(void); */ void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); __asm__("sleep"); } diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index 5a0a95d93ddb..67767c5ed98c 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -44,7 +44,7 @@ void arch_cpu_idle(void) { __vmwait(); /* interrupts wake us up, but irqs are still disabled */ - local_irq_enable(); + raw_local_irq_enable(); } /* diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h index 336d0570e1fa..dd8c166ffd7b 100644 --- a/arch/ia64/include/asm/sparsemem.h +++ b/arch/ia64/include/asm/sparsemem.h @@ -18,4 +18,10 @@ #endif #endif /* CONFIG_SPARSEMEM */ + +#ifdef CONFIG_MEMORY_HOTPLUG +int memory_add_physaddr_to_nid(u64 addr); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif + #endif /* _ASM_IA64_SPARSEMEM_H */ diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 6b61a703bcf5..c9ff8796b509 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -239,7 +239,7 @@ void arch_cpu_idle(void) if (mark_idle) (*mark_idle)(1); - safe_halt(); + raw_safe_halt(); if (mark_idle) (*mark_idle)(0); diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index a9e46e525cd0..f99860771ff4 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -149,5 +149,5 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpregs) void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); } diff --git a/arch/mips/alchemy/common/clock.c b/arch/mips/alchemy/common/clock.c index a95a894aceaf..f0c830337104 100644 --- a/arch/mips/alchemy/common/clock.c +++ b/arch/mips/alchemy/common/clock.c @@ -152,6 +152,7 @@ static struct clk __init *alchemy_clk_setup_cpu(const char *parent_name, { struct clk_init_data id; struct clk_hw *h; + struct clk *clk; h = kzalloc(sizeof(*h), GFP_KERNEL); if (!h) @@ -164,7 +165,13 @@ static struct clk __init *alchemy_clk_setup_cpu(const char *parent_name, id.ops = &alchemy_clkops_cpu; h->init = &id; - return clk_register(NULL, h); + clk = clk_register(NULL, h); + if (IS_ERR(clk)) { + pr_err("failed to register clock\n"); + kfree(h); + } + + return clk; } /* AUXPLLs ************************************************************/ diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index a950fc1ddb4d..6c0532d7b211 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -154,6 +154,7 @@ static inline void pmd_clear(pmd_t *pmdp) #if defined(CONFIG_XPA) +#define MAX_POSSIBLE_PHYSMEM_BITS 40 #define pte_pfn(x) (((unsigned long)((x).pte_high >> _PFN_SHIFT)) | (unsigned long)((x).pte_low << _PAGE_PRESENT_SHIFT)) static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) @@ -169,6 +170,7 @@ pfn_pte(unsigned long pfn, pgprot_t prot) #elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #define pte_pfn(x) ((unsigned long)((x).pte_high >> 6)) static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) @@ -183,6 +185,7 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) #else +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #ifdef CONFIG_CPU_VR41XX #define pte_pfn(x) ((unsigned long)((x).pte >> (PAGE_SHIFT + 2))) #define pfn_pte(pfn, prot) __pte(((pfn) << (PAGE_SHIFT + 2)) | pgprot_val(prot)) diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c index 5bc3b04693c7..18e69ebf5691 100644 --- a/arch/mips/kernel/idle.c +++ b/arch/mips/kernel/idle.c @@ -33,19 +33,19 @@ static void __cpuidle r3081_wait(void) { unsigned long cfg = read_c0_conf(); write_c0_conf(cfg | R30XX_CONF_HALT); - local_irq_enable(); + raw_local_irq_enable(); } static void __cpuidle r39xx_wait(void) { if (!need_resched()) write_c0_conf(read_c0_conf() | TX39_CONF_HALT); - local_irq_enable(); + raw_local_irq_enable(); } void __cpuidle r4k_wait(void) { - local_irq_enable(); + raw_local_irq_enable(); __r4k_wait(); } @@ -64,7 +64,7 @@ void __cpuidle r4k_wait_irqoff(void) " .set arch=r4000 \n" " wait \n" " .set pop \n"); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -84,7 +84,7 @@ static void __cpuidle rm7k_wait_irqoff(void) " wait \n" " mtc0 $1, $12 # stalls until W stage \n" " .set pop \n"); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -257,7 +257,7 @@ void arch_cpu_idle(void) if (cpu_wait) cpu_wait(); else - local_irq_enable(); + raw_local_irq_enable(); } #ifdef CONFIG_CPU_IDLE diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 0d4253208bde..ca579deef939 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -262,8 +262,8 @@ static void __init bootmem_init(void) static void __init bootmem_init(void) { phys_addr_t ramstart, ramend; - phys_addr_t start, end; - u64 i; + unsigned long start, end; + int i; ramstart = memblock_start_of_DRAM(); ramend = memblock_end_of_DRAM(); @@ -300,7 +300,7 @@ static void __init bootmem_init(void) min_low_pfn = ARCH_PFN_OFFSET; max_pfn = PFN_DOWN(ramend); - for_each_mem_range(i, &start, &end) { + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) { /* * Skip highmem here so we get an accurate max_low_pfn if low * memory stops short of high memory. diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index 38e2894d5fa3..1b939abbe4ca 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -438,6 +438,7 @@ int has_transparent_hugepage(void) } return mask == PM_HUGE_MASK; } +EXPORT_SYMBOL(has_transparent_hugepage); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c index 4ffe857e6ada..50b4eb19a6cc 100644 --- a/arch/nios2/kernel/process.c +++ b/arch/nios2/kernel/process.c @@ -33,7 +33,7 @@ EXPORT_SYMBOL(pm_power_off); void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); } /* diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 0ff391f00334..3c98728cce24 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -79,7 +79,7 @@ void machine_power_off(void) */ void arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); if (mfspr(SPR_UPR) & SPR_UPR_PMP) mtspr(SPR_PMR, mfspr(SPR_PMR) | SPR_PMR_DME); } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index f196d96e2f9f..a92a23d6acd9 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -169,7 +169,7 @@ void __cpuidle arch_cpu_idle_dead(void) void __cpuidle arch_cpu_idle(void) { - local_irq_enable(); + raw_local_irq_enable(); /* nop on real hardware, qemu will idle sleep. */ asm volatile("or %%r10,%%r10,%%r10\n":::); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 20dfdd30b9af..4f7ef3de453f 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -153,6 +153,7 @@ config PPC select ARCH_USE_QUEUED_SPINLOCKS if PPC_QUEUED_SPINLOCKS select ARCH_WANT_IPC_PARSE_VERSION select ARCH_WANT_IRQS_OFF_ACTIVATE_MM + select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WEAK_RELEASE_ACQUIRE select BINFMT_ELF select BUILDTIME_TABLE_SORT diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index a4d56f0a41d9..5c8c06215dd4 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -123,7 +123,6 @@ endif LDFLAGS_vmlinux-y := -Bstatic LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) := -pie LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y) -LDFLAGS_vmlinux += $(call ld-option,--orphan-handling=warn) ifdef CONFIG_PPC64 ifeq ($(call cc-option-yn,-mcmodel=medium),y) @@ -248,7 +247,6 @@ KBUILD_CFLAGS += $(call cc-option,-mno-string) cpu-as-$(CONFIG_40x) += -Wa,-m405 cpu-as-$(CONFIG_44x) += -Wa,-m440 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) -cpu-as-$(CONFIG_E200) += -Wa,-me200 cpu-as-$(CONFIG_E500) += -Wa,-me500 # When using '-many -mpower4' gas will first try and find a matching power4 diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 36443cda8dcf..1376be95e975 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -36,8 +36,10 @@ static inline bool pte_user(pte_t pte) */ #ifdef CONFIG_PTE_64BIT #define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #else #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /* diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h index 3ee1ec60be84..a39e2d193fdc 100644 --- a/arch/powerpc/include/asm/book3s/64/kup-radix.h +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -27,6 +27,7 @@ #endif .endm +#ifdef CONFIG_PPC_KUAP .macro kuap_check_amr gpr1, gpr2 #ifdef CONFIG_PPC_KUAP_DEBUG BEGIN_MMU_FTR_SECTION_NESTED(67) @@ -38,6 +39,7 @@ END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67) #endif .endm +#endif .macro kuap_save_amr_and_lock gpr1, gpr2, use_cr, msr_pr_cr #ifdef CONFIG_PPC_KUAP @@ -61,6 +63,10 @@ #else /* !__ASSEMBLY__ */ +#include <linux/jump_label.h> + +DECLARE_STATIC_KEY_FALSE(uaccess_flush_key); + #ifdef CONFIG_PPC_KUAP #include <asm/mmu.h> @@ -103,8 +109,16 @@ static inline void kuap_check_amr(void) static inline unsigned long get_kuap(void) { + /* + * We return AMR_KUAP_BLOCKED when we don't support KUAP because + * prevent_user_access_return needs to return AMR_KUAP_BLOCKED to + * cause restore_user_access to do a flush. + * + * This has no effect in terms of actually blocking things on hash, + * so it doesn't break anything. + */ if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP)) - return 0; + return AMR_KUAP_BLOCKED; return mfspr(SPRN_AMR); } @@ -123,6 +137,29 @@ static inline void set_kuap(unsigned long value) isync(); } +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) && + (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)), + "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read"); +} +#else /* CONFIG_PPC_KUAP */ +static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr) { } + +static inline unsigned long kuap_get_and_check_amr(void) +{ + return 0UL; +} + +static inline unsigned long get_kuap(void) +{ + return AMR_KUAP_BLOCKED; +} + +static inline void set_kuap(unsigned long value) { } +#endif /* !CONFIG_PPC_KUAP */ + static __always_inline void allow_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { @@ -142,6 +179,8 @@ static inline void prevent_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { set_kuap(AMR_KUAP_BLOCKED); + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); } static inline unsigned long prevent_user_access_return(void) @@ -149,6 +188,8 @@ static inline unsigned long prevent_user_access_return(void) unsigned long flags = get_kuap(); set_kuap(AMR_KUAP_BLOCKED); + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); return flags; } @@ -156,30 +197,9 @@ static inline unsigned long prevent_user_access_return(void) static inline void restore_user_access(unsigned long flags) { set_kuap(flags); + if (static_branch_unlikely(&uaccess_flush_key) && flags == AMR_KUAP_BLOCKED) + do_uaccess_flush(); } - -static inline bool -bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) -{ - return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) && - (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)), - "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read"); -} -#else /* CONFIG_PPC_KUAP */ -static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr) -{ -} - -static inline void kuap_check_amr(void) -{ -} - -static inline unsigned long kuap_get_and_check_amr(void) -{ - return 0; -} -#endif /* CONFIG_PPC_KUAP */ - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */ diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index e0b52940e43c..750918451dd2 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -242,6 +242,18 @@ extern void radix_init_pseries(void); static inline void radix_init_pseries(void) { }; #endif +#ifdef CONFIG_HOTPLUG_CPU +#define arch_clear_mm_cpumask_cpu(cpu, mm) \ + do { \ + if (cpumask_test_cpu(cpu, mm_cpumask(mm))) { \ + atomic_dec(&(mm)->context.active_cpus); \ + cpumask_clear_cpu(cpu, mm_cpumask(mm)); \ + } \ + } while (0) + +void cleanup_cpu_mmu_context(void); +#endif + static inline int get_user_context(mm_context_t *ctx, unsigned long ea) { int index = ea >> MAX_EA_BITS_PER_CONTEXT; diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index ebe95aa04d53..1d32b174ab6a 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -57,11 +57,18 @@ nop; \ nop +#define ENTRY_FLUSH_SLOT \ + ENTRY_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop; + /* * r10 must be free to use, r13 must be paca */ #define INTERRUPT_TO_KERNEL \ - STF_ENTRY_BARRIER_SLOT + STF_ENTRY_BARRIER_SLOT; \ + ENTRY_FLUSH_SLOT /* * Macros for annotating the expected destination of (h)rfid @@ -137,6 +144,9 @@ RFSCV; \ b rfscv_flush_fallback +#else /* __ASSEMBLY__ */ +/* Prototype for function defined in exceptions-64s.S */ +void do_uaccess_flush(void); #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_EXCEPTION_H */ diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index b0af97add751..fbd406cd6916 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -205,6 +205,22 @@ label##3: \ FTR_ENTRY_OFFSET 955b-956b; \ .popsection; +#define UACCESS_FLUSH_FIXUP_SECTION \ +959: \ + .pushsection __uaccess_flush_fixup,"a"; \ + .align 2; \ +960: \ + FTR_ENTRY_OFFSET 959b-960b; \ + .popsection; + +#define ENTRY_FLUSH_FIXUP_SECTION \ +957: \ + .pushsection __entry_flush_fixup,"a"; \ + .align 2; \ +958: \ + FTR_ENTRY_OFFSET 957b-958b; \ + .popsection; + #define RFI_FLUSH_FIXUP_SECTION \ 951: \ .pushsection __rfi_flush_fixup,"a"; \ @@ -237,8 +253,11 @@ label##3: \ #include <linux/types.h> extern long stf_barrier_fallback; +extern long entry_flush_fallback; extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; +extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup; +extern long __start___entry_flush_fixup, __stop___entry_flush_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h index 1d0f7d838b2e..0d93331d0fab 100644 --- a/arch/powerpc/include/asm/kup.h +++ b/arch/powerpc/include/asm/kup.h @@ -14,7 +14,7 @@ #define KUAP_CURRENT_WRITE 8 #define KUAP_CURRENT (KUAP_CURRENT_READ | KUAP_CURRENT_WRITE) -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S_64 #include <asm/book3s/64/kup-radix.h> #endif #ifdef CONFIG_PPC_8xx @@ -35,6 +35,9 @@ .macro kuap_check current, gpr .endm +.macro kuap_check_amr gpr1, gpr2 +.endm + #endif #else /* !__ASSEMBLY__ */ @@ -53,17 +56,28 @@ static inline void setup_kuep(bool disabled) { } void setup_kuap(bool disabled); #else static inline void setup_kuap(bool disabled) { } + +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + return false; +} + +static inline void kuap_check_amr(void) { } + +/* + * book3s/64/kup-radix.h defines these functions for the !KUAP case to flush + * the L1D cache after user accesses. Only include the empty stubs for other + * platforms. + */ +#ifndef CONFIG_PPC_BOOK3S_64 static inline void allow_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { } static inline void prevent_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) { } static inline unsigned long prevent_user_access_return(void) { return 0UL; } static inline void restore_user_access(unsigned long flags) { } -static inline bool -bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) -{ - return false; -} +#endif /* CONFIG_PPC_BOOK3S_64 */ #endif /* CONFIG_PPC_KUAP */ static inline void allow_read_from_user(const void __user *from, unsigned long size) diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 91c69ff53a8a..6cda76b57c5d 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -46,5 +46,10 @@ u64 memory_hotplug_max(void); #define __HAVE_ARCH_RESERVED_KERNEL_PAGES #endif +#ifdef CONFIG_MEMORY_HOTPLUG +extern int create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot); +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_MMZONE_H_ */ diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index ee2243ba96cf..96522f7f0618 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -153,8 +153,10 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); */ #if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) #define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #else #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif /* diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index fbb8fa32150f..b774a4477d5f 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -86,12 +86,19 @@ static inline bool security_ftr_enabled(u64 feature) // Software required to flush link stack on context switch #define SEC_FTR_FLUSH_LINK_STACK 0x0000000000001000ull +// The L1-D cache should be flushed when entering the kernel +#define SEC_FTR_L1D_FLUSH_ENTRY 0x0000000000004000ull + +// The L1-D cache should be flushed after user accesses from the kernel +#define SEC_FTR_L1D_FLUSH_UACCESS 0x0000000000008000ull // Features enabled by default #define SEC_FTR_DEFAULT \ (SEC_FTR_L1D_FLUSH_HV | \ SEC_FTR_L1D_FLUSH_PR | \ SEC_FTR_BNDS_CHK_SPEC_BAR | \ + SEC_FTR_L1D_FLUSH_ENTRY | \ + SEC_FTR_L1D_FLUSH_UACCESS | \ SEC_FTR_FAVOUR_SECURITY) #endif /* _ASM_POWERPC_SECURITY_FEATURES_H */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 9efbddee2bca..a466749703f1 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -52,12 +52,16 @@ enum l1d_flush_type { }; void setup_rfi_flush(enum l1d_flush_type, bool enable); +void setup_entry_flush(bool enable); +void setup_uaccess_flush(bool enable); void do_rfi_flush_fixups(enum l1d_flush_type types); #ifdef CONFIG_PPC_BARRIER_NOSPEC void setup_barrier_nospec(void); #else static inline void setup_barrier_nospec(void) { }; #endif +void do_uaccess_flush_fixups(enum l1d_flush_type types); +void do_entry_flush_fixups(enum l1d_flush_type types); void do_barrier_nospec_fixups(bool enable); extern bool barrier_nospec_enabled; diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index 1e6fa371cc38..d072866842e4 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -13,9 +13,9 @@ #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_MEMORY_HOTPLUG -extern int create_section_mapping(unsigned long start, unsigned long end, - int nid, pgprot_t prot); extern int remove_section_mapping(unsigned long start, unsigned long end); +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid #ifdef CONFIG_NUMA extern int hot_add_scn_to_nid(unsigned long scn_addr); @@ -26,6 +26,5 @@ static inline int hot_add_scn_to_nid(unsigned long scn_addr) } #endif /* CONFIG_NUMA */ #endif /* CONFIG_MEMORY_HOTPLUG */ - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_SPARSEMEM_H */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index f7d748b88705..4d01f09ecf80 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1000,8 +1000,6 @@ TRAMP_REAL_BEGIN(system_reset_idle_wake) * Vectors for the FWNMI option. Share common code. */ TRAMP_REAL_BEGIN(system_reset_fwnmi) - /* XXX: fwnmi guest could run a nested/PR guest, so why no test? */ - __IKVM_REAL(system_reset)=0 GEN_INT_ENTRY system_reset, virt=0 #endif /* CONFIG_PPC_PSERIES */ @@ -1412,6 +1410,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) * If none is found, do a Linux page fault. Linux page faults can happen in * kernel mode due to user copy operations of course. * + * KVM: The KVM HDSI handler may perform a load with MSR[DR]=1 in guest + * MMU context, which may cause a DSI in the host, which must go to the + * KVM handler. MSR[IR] is not enabled, so the real-mode handler will + * always be used regardless of AIL setting. + * * - Radix MMU * The hardware loads from the Linux page table directly, so a fault goes * immediately to Linux page fault. @@ -1422,10 +1425,8 @@ INT_DEFINE_BEGIN(data_access) IVEC=0x300 IDAR=1 IDSISR=1 -#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE IKVM_SKIP=1 IKVM_REAL=1 -#endif INT_DEFINE_END(data_access) EXC_REAL_BEGIN(data_access, 0x300, 0x80) @@ -1464,6 +1465,8 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) * ppc64_bolted_size (first segment). The kernel handler must avoid stomping * on user-handler data structures. * + * KVM: Same as 0x300, DSLB must test for KVM guest. + * * A dedicated save area EXSLB is used (XXX: but it actually need not be * these days, we could use EXGEN). */ @@ -1472,10 +1475,8 @@ INT_DEFINE_BEGIN(data_access_slb) IAREA=PACA_EXSLB IRECONCILE=0 IDAR=1 -#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE IKVM_SKIP=1 IKVM_REAL=1 -#endif INT_DEFINE_END(data_access_slb) EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80) @@ -2951,15 +2952,8 @@ TRAMP_REAL_BEGIN(stf_barrier_fallback) .endr blr -TRAMP_REAL_BEGIN(rfi_flush_fallback) - SET_SCRATCH0(r13); - GET_PACA(r13); - std r1,PACA_EXRFI+EX_R12(r13) - ld r1,PACAKSAVE(r13) - std r9,PACA_EXRFI+EX_R9(r13) - std r10,PACA_EXRFI+EX_R10(r13) - std r11,PACA_EXRFI+EX_R11(r13) - mfctr r9 +/* Clobbers r10, r11, ctr */ +.macro L1D_DISPLACEMENT_FLUSH ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) ld r11,PACA_L1D_FLUSH_SIZE(r13) srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ @@ -2970,7 +2964,7 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) sync /* - * The load adresses are at staggered offsets within cachelines, + * The load addresses are at staggered offsets within cachelines, * which suits some pipelines better (on others it should not * hurt). */ @@ -2985,7 +2979,30 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) ld r11,(0x80 + 8)*7(r10) addi r10,r10,0x80*8 bdnz 1b +.endm +TRAMP_REAL_BEGIN(entry_flush_fallback) + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + L1D_DISPLACEMENT_FLUSH + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + blr + +TRAMP_REAL_BEGIN(rfi_flush_fallback) + SET_SCRATCH0(r13); + GET_PACA(r13); + std r1,PACA_EXRFI+EX_R12(r13) + ld r1,PACAKSAVE(r13) + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + L1D_DISPLACEMENT_FLUSH mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) @@ -3003,32 +3020,7 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) std r10,PACA_EXRFI+EX_R10(r13) std r11,PACA_EXRFI+EX_R11(r13) mfctr r9 - ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) - ld r11,PACA_L1D_FLUSH_SIZE(r13) - srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ - mtctr r11 - DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ - - /* order ld/st prior to dcbt stop all streams with flushing */ - sync - - /* - * The load adresses are at staggered offsets within cachelines, - * which suits some pipelines better (on others it should not - * hurt). - */ -1: - ld r11,(0x80 + 8)*0(r10) - ld r11,(0x80 + 8)*1(r10) - ld r11,(0x80 + 8)*2(r10) - ld r11,(0x80 + 8)*3(r10) - ld r11,(0x80 + 8)*4(r10) - ld r11,(0x80 + 8)*5(r10) - ld r11,(0x80 + 8)*6(r10) - ld r11,(0x80 + 8)*7(r10) - addi r10,r10,0x80*8 - bdnz 1b - + L1D_DISPLACEMENT_FLUSH mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) @@ -3079,8 +3071,21 @@ TRAMP_REAL_BEGIN(rfscv_flush_fallback) RFSCV USE_TEXT_SECTION() - MASKED_INTERRUPT - MASKED_INTERRUPT hsrr=1 + +_GLOBAL(do_uaccess_flush) + UACCESS_FLUSH_FIXUP_SECTION + nop + nop + nop + blr + L1D_DISPLACEMENT_FLUSH + blr +_ASM_NOKPROBE_SYMBOL(do_uaccess_flush) +EXPORT_SYMBOL(do_uaccess_flush) + + +MASKED_INTERRUPT +MASKED_INTERRUPT hsrr=1 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER kvmppc_skip_interrupt: diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 2aa16d5368e1..a0dda2a1f2df 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -156,6 +156,7 @@ __after_mmu_off: bl initial_bats bl load_segment_registers BEGIN_MMU_FTR_SECTION + bl reloc_offset bl early_hash_table END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) #if defined(CONFIG_BOOTX_TEXT) @@ -920,7 +921,7 @@ early_hash_table: ori r6, r6, 3 /* 256kB table */ mtspr SPRN_SDR1, r6 lis r6, early_hash@h - lis r3, Hash@ha + addis r3, r3, Hash@ha stw r6, Hash@l(r3) blr diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index ae0e2632393d..1f835539fda4 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -52,9 +52,9 @@ void arch_cpu_idle(void) * interrupts enabled, some don't. */ if (irqs_disabled()) - local_irq_enable(); + raw_local_irq_enable(); } else { - local_irq_enable(); + raw_local_irq_enable(); /* * Go into low thread priority and possibly * low power mode. diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index bb9cab3641d7..74fd47f46fa5 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -945,7 +945,13 @@ early_initcall(disable_hardlockup_detector); static enum l1d_flush_type enabled_flush_types; static void *l1d_flush_fallback_area; static bool no_rfi_flush; +static bool no_entry_flush; +static bool no_uaccess_flush; bool rfi_flush; +bool entry_flush; +bool uaccess_flush; +DEFINE_STATIC_KEY_FALSE(uaccess_flush_key); +EXPORT_SYMBOL(uaccess_flush_key); static int __init handle_no_rfi_flush(char *p) { @@ -955,6 +961,22 @@ static int __init handle_no_rfi_flush(char *p) } early_param("no_rfi_flush", handle_no_rfi_flush); +static int __init handle_no_entry_flush(char *p) +{ + pr_info("entry-flush: disabled on command line."); + no_entry_flush = true; + return 0; +} +early_param("no_entry_flush", handle_no_entry_flush); + +static int __init handle_no_uaccess_flush(char *p) +{ + pr_info("uaccess-flush: disabled on command line."); + no_uaccess_flush = true; + return 0; +} +early_param("no_uaccess_flush", handle_no_uaccess_flush); + /* * The RFI flush is not KPTI, but because users will see doco that says to use * nopti we hijack that option here to also disable the RFI flush. @@ -986,6 +1008,32 @@ void rfi_flush_enable(bool enable) rfi_flush = enable; } +void entry_flush_enable(bool enable) +{ + if (enable) { + do_entry_flush_fixups(enabled_flush_types); + on_each_cpu(do_nothing, NULL, 1); + } else { + do_entry_flush_fixups(L1D_FLUSH_NONE); + } + + entry_flush = enable; +} + +void uaccess_flush_enable(bool enable) +{ + if (enable) { + do_uaccess_flush_fixups(enabled_flush_types); + static_branch_enable(&uaccess_flush_key); + on_each_cpu(do_nothing, NULL, 1); + } else { + static_branch_disable(&uaccess_flush_key); + do_uaccess_flush_fixups(L1D_FLUSH_NONE); + } + + uaccess_flush = enable; +} + static void __ref init_fallback_flush(void) { u64 l1d_size, limit; @@ -1044,10 +1092,28 @@ void setup_rfi_flush(enum l1d_flush_type types, bool enable) enabled_flush_types = types; - if (!no_rfi_flush && !cpu_mitigations_off()) + if (!cpu_mitigations_off() && !no_rfi_flush) rfi_flush_enable(enable); } +void setup_entry_flush(bool enable) +{ + if (cpu_mitigations_off()) + return; + + if (!no_entry_flush) + entry_flush_enable(enable); +} + +void setup_uaccess_flush(bool enable) +{ + if (cpu_mitigations_off()) + return; + + if (!no_uaccess_flush) + uaccess_flush_enable(enable); +} + #ifdef CONFIG_DEBUG_FS static int rfi_flush_set(void *data, u64 val) { @@ -1075,9 +1141,63 @@ static int rfi_flush_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n"); +static int entry_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + /* Only do anything if we're changing state */ + if (enable != entry_flush) + entry_flush_enable(enable); + + return 0; +} + +static int entry_flush_get(void *data, u64 *val) +{ + *val = entry_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n"); + +static int uaccess_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + /* Only do anything if we're changing state */ + if (enable != uaccess_flush) + uaccess_flush_enable(enable); + + return 0; +} + +static int uaccess_flush_get(void *data, u64 *val) +{ + *val = uaccess_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set, "%llu\n"); + static __init int rfi_flush_debugfs_init(void) { debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush); + debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush); + debugfs_create_file("uaccess_flush", 0600, powerpc_debugfs_root, NULL, &fops_uaccess_flush); return 0; } device_initcall(rfi_flush_debugfs_init); diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c index 8e50818aa50b..310bcd768cd5 100644 --- a/arch/powerpc/kernel/syscall_64.c +++ b/arch/powerpc/kernel/syscall_64.c @@ -2,7 +2,7 @@ #include <linux/err.h> #include <asm/asm-prototypes.h> -#include <asm/book3s/64/kup-radix.h> +#include <asm/kup.h> #include <asm/cputime.h> #include <asm/hw_irq.h> #include <asm/kprobes.h> diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index e0548b4950de..6db90cdf11da 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -132,6 +132,20 @@ SECTIONS } . = ALIGN(8); + __uaccess_flush_fixup : AT(ADDR(__uaccess_flush_fixup) - LOAD_OFFSET) { + __start___uaccess_flush_fixup = .; + *(__uaccess_flush_fixup) + __stop___uaccess_flush_fixup = .; + } + + . = ALIGN(8); + __entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) { + __start___entry_flush_fixup = .; + *(__entry_flush_fixup) + __stop___entry_flush_fixup = .; + } + + . = ALIGN(8); __stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) { __start___stf_exit_barrier_fixup = .; *(__stf_exit_barrier_fixup) diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 85215e79db42..a0ebc29f30b2 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1214,12 +1214,9 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu) static bool kvmppc_xive_vcpu_id_valid(struct kvmppc_xive *xive, u32 cpu) { /* We have a block of xive->nr_servers VPs. We just need to check - * raw vCPU ids are below the expected limit for this guest's - * core stride ; kvmppc_pack_vcpu_id() will pack them down to an - * index that can be safely used to compute a VP id that belongs - * to the VP block. + * packed vCPU ids are below that. */ - return cpu < xive->nr_servers * xive->kvm->arch.emul_smt_mode; + return kvmppc_pack_vcpu_id(xive->kvm, cpu) < xive->nr_servers; } int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp) diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index d0c2db0e07fa..a59a94f02733 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -251,6 +251,13 @@ static vm_fault_t xive_native_esb_fault(struct vm_fault *vmf) } state = &sb->irq_state[src]; + + /* Some sanity checking */ + if (!state->valid) { + pr_devel("%s: source %lx invalid !\n", __func__, irq); + return VM_FAULT_SIGBUS; + } + kvmppc_xive_select_irq(state, &hw_num, &xd); arch_spin_lock(&sb->lock); diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 4c0a7ee9fa00..321c12a9ef6b 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -234,6 +234,110 @@ void do_stf_barrier_fixups(enum stf_barrier_type types) do_stf_exit_barrier_fixups(types); } +void do_uaccess_flush_fixups(enum l1d_flush_type types) +{ + unsigned int instrs[4], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___uaccess_flush_fixup); + end = PTRRELOC(&__stop___uaccess_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + instrs[3] = 0x4e800020; /* blr */ + + i = 0; + if (types == L1D_FLUSH_FALLBACK) { + instrs[3] = 0x60000000; /* nop */ + /* fallthrough to fallback flush */ + } + + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)(dest + 3), ppc_inst(instrs[3])); + } + + printk(KERN_DEBUG "uaccess-flush: patched %d locations (%s flush)\n", i, + (types == L1D_FLUSH_NONE) ? "no" : + (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : + (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG) + ? "ori+mttrig type" + : "ori type" : + (types & L1D_FLUSH_MTTRIG) ? "mttrig type" + : "unknown"); +} + +void do_entry_flush_fixups(enum l1d_flush_type types) +{ + unsigned int instrs[3], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___entry_flush_fixup); + end = PTRRELOC(&__stop___entry_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + + i = 0; + if (types == L1D_FLUSH_FALLBACK) { + instrs[i++] = 0x7d4802a6; /* mflr r10 */ + instrs[i++] = 0x60000000; /* branch patched below */ + instrs[i++] = 0x7d4803a6; /* mtlr r10 */ + } + + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + + if (types == L1D_FLUSH_FALLBACK) + patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&entry_flush_fallback, + BRANCH_SET_LINK); + else + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + } + + printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i, + (types == L1D_FLUSH_NONE) ? "no" : + (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : + (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG) + ? "ori+mttrig type" + : "ori type" : + (types & L1D_FLUSH_MTTRIG) ? "mttrig type" + : "unknown"); +} + void do_rfi_flush_fixups(enum l1d_flush_type types) { unsigned int instrs[3], *dest; diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 5e147986400d..55b4a8bd408a 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -5,7 +5,7 @@ ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) -obj-y := fault.o mem.o pgtable.o mmap.o \ +obj-y := fault.o mem.o pgtable.o mmap.o maccess.o \ init_$(BITS).o pgtable_$(BITS).o \ pgtable-frag.o ioremap.o ioremap_$(BITS).o \ init-common.o mmu_context.o drmem.o diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c index 0203cdf48c54..52e170bd95ae 100644 --- a/arch/powerpc/mm/book3s64/hash_native.c +++ b/arch/powerpc/mm/book3s64/hash_native.c @@ -68,7 +68,7 @@ static __always_inline void tlbiel_hash_set_isa300(unsigned int set, unsigned in rs = ((unsigned long)pid << PPC_BITLSHIFT(31)); asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) - : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "r"(r) + : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "i"(r) : "memory"); } @@ -92,16 +92,15 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) asm volatile("ptesync": : :"memory"); /* - * Flush the first set of the TLB, and any caching of partition table - * entries. Then flush the remaining sets of the TLB. Hash mode uses - * partition scoped TLB translations. + * Flush the partition table cache if this is HV mode. */ - tlbiel_hash_set_isa300(0, is, 0, 2, 0); - for (set = 1; set < num_sets; set++) - tlbiel_hash_set_isa300(set, is, 0, 0, 0); + if (early_cpu_has_feature(CPU_FTR_HVMODE)) + tlbiel_hash_set_isa300(0, is, 0, 2, 0); /* - * Now invalidate the process table cache. + * Now invalidate the process table cache. UPRT=0 HPT modes (what + * current hardware implements) do not use the process table, but + * add the flushes anyway. * * From ISA v3.0B p. 1078: * The following forms are invalid. @@ -110,6 +109,14 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) */ tlbiel_hash_set_isa300(0, is, 0, 2, 1); + /* + * Then flush the sets of the TLB proper. Hash mode uses + * partition scoped TLB translations, which may be flushed + * in !HV mode. + */ + for (set = 0; set < num_sets; set++) + tlbiel_hash_set_isa300(set, is, 0, 0, 0); + ppc_after_tlbiel_barrier(); asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory"); diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c index 1c54821de7bf..0c8557220ae2 100644 --- a/arch/powerpc/mm/book3s64/mmu_context.c +++ b/arch/powerpc/mm/book3s64/mmu_context.c @@ -17,6 +17,7 @@ #include <linux/export.h> #include <linux/gfp.h> #include <linux/slab.h> +#include <linux/cpu.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> @@ -307,3 +308,22 @@ void radix__switch_mmu_context(struct mm_struct *prev, struct mm_struct *next) isync(); } #endif + +/** + * cleanup_cpu_mmu_context - Clean up MMU details for this CPU (newly offlined) + * + * This clears the CPU from mm_cpumask for all processes, and then flushes the + * local TLB to ensure TLB coherency in case the CPU is onlined again. + * + * KVM guest translations are not necessarily flushed here. If KVM started + * using mm_cpumask or the Linux APIs which do, this would have to be resolved. + */ +#ifdef CONFIG_HOTPLUG_CPU +void cleanup_cpu_mmu_context(void) +{ + int cpu = smp_processor_id(); + + clear_tasks_mm_cpumask(cpu); + tlbiel_all(); +} +#endif diff --git a/arch/powerpc/mm/maccess.c b/arch/powerpc/mm/maccess.c new file mode 100644 index 000000000000..fa9a7a718fc6 --- /dev/null +++ b/arch/powerpc/mm/maccess.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/uaccess.h> +#include <linux/kernel.h> + +bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) +{ + return is_kernel_addr((unsigned long)unsafe_src); +} diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 01ec2a252f09..3fc325bebe4d 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -50,6 +50,7 @@ #include <asm/rtas.h> #include <asm/kasan.h> #include <asm/svm.h> +#include <asm/mmzone.h> #include <mm/mmu_decl.h> diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 63f61d8b55e5..f2bf98bdcea2 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -742,8 +742,7 @@ static int __init parse_numa_properties(void) of_node_put(cpu); } - if (likely(nid > 0)) - node_set_online(nid); + node_set_online(nid); } get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells); diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 9ed4fcccf8a9..7b25548ec42b 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -1336,7 +1336,7 @@ static void dump_trace_imc_data(struct perf_event *event) /* If this is a valid record, create the sample */ struct perf_output_handle handle; - if (perf_output_begin(&handle, event, header.size)) + if (perf_output_begin(&handle, &data, event, header.size)) return; perf_output_sample(&handle, &header, &data, event); diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index 8e53f2fc3fe0..6f681b105eec 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -144,8 +144,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) : diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index 74ebe664b016..adae2a6712e1 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -911,6 +911,8 @@ static int smp_core99_cpu_disable(void) mpic_cpu_set_priority(0xf); + cleanup_cpu_mmu_context(); + return 0; } diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 9acaa0f131b9..4426a109ec2f 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -98,7 +98,7 @@ static void init_fw_feat_flags(struct device_node *np) security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR); } -static void pnv_setup_rfi_flush(void) +static void pnv_setup_security_mitigations(void) { struct device_node *np, *fw_features; enum l1d_flush_type type; @@ -122,12 +122,31 @@ static void pnv_setup_rfi_flush(void) type = L1D_FLUSH_ORI; } + /* + * If we are non-Power9 bare metal, we don't need to flush on kernel + * entry or after user access: they fix a P9 specific vulnerability. + */ + if (!pvr_version_is(PVR_POWER9)) { + security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY); + security_ftr_clear(SEC_FTR_L1D_FLUSH_UACCESS); + } + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \ (security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR) || \ security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV)); setup_rfi_flush(type, enable); setup_count_cache_flush(); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY); + setup_entry_flush(enable); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS); + setup_uaccess_flush(enable); + + setup_stf_barrier(); } static void __init pnv_check_guarded_cores(void) @@ -156,8 +175,7 @@ static void __init pnv_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); - pnv_setup_rfi_flush(); - setup_stf_barrier(); + pnv_setup_security_mitigations(); /* Initialize SMP */ pnv_smp_init(); @@ -193,11 +211,16 @@ static void __init pnv_init(void) add_preferred_console("hvc", 0, NULL); if (!radix_enabled()) { + size_t size = sizeof(struct slb_entry) * mmu_slb_size; int i; /* Allocate per cpu area to save old slb contents during MCE */ - for_each_possible_cpu(i) - paca_ptrs[i]->mce_faulty_slbs = memblock_alloc_node(mmu_slb_size, __alignof__(*paca_ptrs[i]->mce_faulty_slbs), cpu_to_node(i)); + for_each_possible_cpu(i) { + paca_ptrs[i]->mce_faulty_slbs = + memblock_alloc_node(size, + __alignof__(struct slb_entry), + cpu_to_node(i)); + } } } diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 54c4ba45c7ce..cbb67813cd5d 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -143,6 +143,9 @@ static int pnv_smp_cpu_disable(void) xive_smp_disable_cpu(); else xics_migrate_irqs_away(); + + cleanup_cpu_mmu_context(); + return 0; } diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index f2837e33bf5d..a02012f1b04a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -90,6 +90,9 @@ static int pseries_cpu_disable(void) xive_smp_disable_cpu(); else xics_migrate_irqs_away(); + + cleanup_cpu_mmu_context(); + return 0; } diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index d6f4162478a5..2f73cb5bf12d 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -349,8 +349,8 @@ void post_mobility_fixup(void) cpus_read_unlock(); - /* Possibly switch to a new RFI flush type */ - pseries_setup_rfi_flush(); + /* Possibly switch to a new L1 flush type */ + pseries_setup_security_mitigations(); /* Reinitialise system information for hv-24x7 */ read_24x7_sys_info(); diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 133f6adcb39c..b3ac2455faad 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -458,7 +458,8 @@ again: return hwirq; } - virq = irq_create_mapping(NULL, hwirq); + virq = irq_create_mapping_affinity(NULL, hwirq, + entry->affinity); if (!virq) { pr_debug("rtas_msi: Failed mapping hwirq %d\n", hwirq); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 13fa370a87e4..593840847cd3 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -111,7 +111,7 @@ static inline unsigned long cmo_get_page_size(void) int dlpar_workqueue_init(void); -void pseries_setup_rfi_flush(void); +void pseries_setup_security_mitigations(void); void pseries_lpar_read_hblkrm_characteristics(void); #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 633c45ec406d..090c13f6c881 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -542,7 +542,7 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result) security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR); } -void pseries_setup_rfi_flush(void) +void pseries_setup_security_mitigations(void) { struct h_cpu_char_result result; enum l1d_flush_type types; @@ -579,6 +579,16 @@ void pseries_setup_rfi_flush(void) setup_rfi_flush(types, enable); setup_count_cache_flush(); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY); + setup_entry_flush(enable); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS); + setup_uaccess_flush(enable); + + setup_stf_barrier(); } #ifdef CONFIG_PCI_IOV @@ -768,8 +778,7 @@ static void __init pSeries_setup_arch(void) fwnmi_init(); - pseries_setup_rfi_flush(); - setup_stf_barrier(); + pseries_setup_security_mitigations(); pseries_lpar_read_hblkrm_characteristics(); /* By default, only probe PCI (can be overridden by rtas_pci) */ diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h index b0ab66e5fdb1..5b2e79e5bfa5 100644 --- a/arch/riscv/include/asm/pgtable-32.h +++ b/arch/riscv/include/asm/pgtable-32.h @@ -14,4 +14,6 @@ #define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE - 1)) +#define MAX_POSSIBLE_PHYSMEM_BITS 34 + #endif /* _ASM_RISCV_PGTABLE_32_H */ diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h index ab104905d4db..81de51e6aa32 100644 --- a/arch/riscv/include/asm/timex.h +++ b/arch/riscv/include/asm/timex.h @@ -60,6 +60,8 @@ static inline u32 get_cycles_hi(void) } #define get_cycles_hi get_cycles_hi +#endif /* !CONFIG_RISCV_M_MODE */ + #ifdef CONFIG_64BIT static inline u64 get_cycles64(void) { @@ -79,8 +81,6 @@ static inline u64 get_cycles64(void) } #endif /* CONFIG_64BIT */ -#endif /* !CONFIG_RISCV_M_MODE */ - #define ARCH_HAS_READ_CURRENT_TIMER static inline int read_current_timer(unsigned long *timer_val) { diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h index 82a5693b1861..134388cbaaa1 100644 --- a/arch/riscv/include/asm/vdso/processor.h +++ b/arch/riscv/include/asm/vdso/processor.h @@ -4,6 +4,8 @@ #ifndef __ASSEMBLY__ +#include <asm/barrier.h> + static inline void cpu_relax(void) { #ifdef __riscv_muldiv diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c index 04a38fbeb9c7..fd304a248de6 100644 --- a/arch/riscv/kernel/perf_regs.c +++ b/arch/riscv/kernel/perf_regs.c @@ -36,8 +36,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 19225ec65db6..dd5f985b1f40 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -36,7 +36,7 @@ extern asmlinkage void ret_from_kernel_thread(void); void arch_cpu_idle(void) { wait_for_interrupt(); - local_irq_enable(); + raw_local_irq_enable(); } void show_regs(struct pt_regs *regs) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index c424cc6dd833..117f3212a8e4 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -75,6 +75,7 @@ void __init setup_arch(char **cmdline_p) *cmdline_p = boot_command_line; early_ioremap_setup(); + jump_label_init(); parse_early_param(); efi_init(); diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index cb8f9e4cfcbf..0cfd6da784f8 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -44,7 +44,7 @@ SYSCFLAGS_vdso.so.dbg = $(c_flags) $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold) SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ - -Wl,--build-id -Wl,--hash-style=both + -Wl,--build-id=sha1 -Wl,--hash-style=both # We also create a special relocatable object that should mirror the symbol # table and layout of the linked DSO. With ld --just-symbols we can then diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index a4d3c578fbd8..fe6f529ac82c 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -1,3 +1,4 @@ +CONFIG_UAPI_HEADER_TEST=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_WATCH_QUEUE=y diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 2012c1cf0853..483051e10db3 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -53,11 +53,11 @@ int main(void) /* stack_frame offsets */ OFFSET(__SF_BACKCHAIN, stack_frame, back_chain); OFFSET(__SF_GPRS, stack_frame, gprs); - OFFSET(__SF_EMPTY, stack_frame, empty1); - OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[0]); - OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[1]); - OFFSET(__SF_SIE_REASON, stack_frame, empty1[2]); - OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[3]); + OFFSET(__SF_EMPTY, stack_frame, empty1[0]); + OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[1]); + OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[2]); + OFFSET(__SF_SIE_REASON, stack_frame, empty1[3]); + OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[4]); BLANK(); OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val); BLANK(); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 86235919c2d1..92beb1444644 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -422,6 +422,7 @@ ENTRY(system_call) #endif LOCKDEP_SYS_EXIT .Lsysc_tif: + DISABLE_INTS TSTMSK __PT_FLAGS(%r11),_PIF_WORK jnz .Lsysc_work TSTMSK __TI_flags(%r12),_TIF_WORK @@ -444,6 +445,7 @@ ENTRY(system_call) # One of the work bits is on. Find out which one. # .Lsysc_work: + ENABLE_INTS TSTMSK __TI_flags(%r12),_TIF_NEED_RESCHED jo .Lsysc_reschedule TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART @@ -761,12 +763,7 @@ ENTRY(io_int_handler) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ jo .Lio_restore -#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) - tmhh %r8,0x300 - jz 1f TRACE_IRQS_OFF -1: -#endif xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) .Lio_loop: lgr %r2,%r11 # pass pointer to pt_regs @@ -789,12 +786,7 @@ ENTRY(io_int_handler) TSTMSK __LC_CPU_FLAGS,_CIF_WORK jnz .Lio_work .Lio_restore: -#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) - tm __PT_PSW(%r11),3 - jno 0f TRACE_IRQS_ON -0: -#endif mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) tm __PT_PSW+1(%r11),0x01 # returning to user ? jno .Lio_exit_kernel @@ -974,12 +966,7 @@ ENTRY(ext_int_handler) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ jo .Lio_restore -#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) - tmhh %r8,0x300 - jz 1f TRACE_IRQS_OFF -1: -#endif xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs lghi %r3,EXT_INTERRUPT @@ -1066,6 +1053,7 @@ EXPORT_SYMBOL(save_fpu_regs) * %r4 */ load_fpu_regs: + stnsm __SF_EMPTY(%r15),0xfc lg %r4,__LC_CURRENT aghi %r4,__TASK_thread TSTMSK __LC_CPU_FLAGS,_CIF_FPU @@ -1097,6 +1085,7 @@ load_fpu_regs: .Lload_fpu_regs_done: ni __LC_CPU_FLAGS+7,255-_CIF_FPU .Lload_fpu_regs_exit: + ssm __SF_EMPTY(%r15) BR_EX %r14 .Lload_fpu_regs_end: ENDPROC(load_fpu_regs) diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index f7f1e64e0d98..2b85096964f8 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -33,10 +33,10 @@ void enabled_wait(void) PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; clear_cpu_flag(CIF_NOHZ_DELAY); - local_irq_save(flags); + raw_local_irq_save(flags); /* Call the assembler magic in entry.S */ psw_idle(idle, psw_mask); - local_irq_restore(flags); + raw_local_irq_restore(flags); /* Account time spent with enabled wait psw loaded as idle time. */ raw_write_seqcount_begin(&idle->seqcount); @@ -123,7 +123,7 @@ void arch_cpu_idle_enter(void) void arch_cpu_idle(void) { enabled_wait(); - local_irq_enable(); + raw_local_irq_enable(); } void arch_cpu_idle_exit(void) diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 4f9e4626df55..19cd7b961c45 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -672,7 +672,7 @@ static void cpumsf_output_event_pid(struct perf_event *event, rcu_read_lock(); perf_prepare_sample(&header, data, event, regs); - if (perf_output_begin(&handle, event, header.size)) + if (perf_output_begin(&handle, data, event, header.size)) goto out; /* Update the process ID (see also kernel/events/core.c) */ @@ -2228,4 +2228,4 @@ out: } arch_initcall(init_cpum_sampling_pmu); -core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640); +core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0644); diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c index 4352a504f235..6e9e5d5e927e 100644 --- a/arch/s390/kernel/perf_regs.c +++ b/arch/s390/kernel/perf_regs.c @@ -53,8 +53,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { /* * Use the regs from the first interruption and let diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 14bd9d58edc9..883bfed9f5c2 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -129,8 +129,15 @@ int uv_destroy_page(unsigned long paddr) .paddr = paddr }; - if (uv_call(0, (u64)&uvcb)) + if (uv_call(0, (u64)&uvcb)) { + /* + * Older firmware uses 107/d as an indication of a non secure + * page. Let us emulate the newer variant (no-op). + */ + if (uvcb.header.rc == 0x107 && uvcb.header.rrc == 0xd) + return 0; return -EINVAL; + } return 0; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 6b74b92c1a58..425d3d75320b 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2312,7 +2312,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) struct kvm_s390_pv_unp unp = {}; r = -EINVAL; - if (!kvm_s390_pv_is_protected(kvm)) + if (!kvm_s390_pv_is_protected(kvm) || !mm_is_protected(kvm->mm)) break; r = -EFAULT; @@ -3564,7 +3564,6 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->pp = 0; vcpu->arch.sie_block->fpf &= ~FPF_BPBC; vcpu->arch.sie_block->todpr = 0; - vcpu->arch.sie_block->cpnc = 0; } } @@ -3582,7 +3581,6 @@ static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu) regs->etoken = 0; regs->etoken_extension = 0; - regs->diag318 = 0; } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index eb99e2f95ebe..f5847f9dec7c 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -208,7 +208,6 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) return -EIO; } kvm->arch.gmap->guest_handle = uvcb.guest_handle; - atomic_set(&kvm->mm->context.is_protected, 1); return 0; } @@ -228,6 +227,8 @@ int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, *rrc = uvcb.header.rrc; KVM_UV_EVENT(kvm, 3, "PROTVIRT VM SET PARMS: rc %x rrc %x", *rc, *rrc); + if (!cc) + atomic_set(&kvm->mm->context.is_protected, 1); return cc ? -EINVAL : 0; } diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index daca7bad66de..8c0c68e7770e 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -33,7 +33,7 @@ EXPORT_SYMBOL(__delay); static void __udelay_disabled(unsigned long long usecs) { - unsigned long cr0, cr0_new, psw_mask, flags; + unsigned long cr0, cr0_new, psw_mask; struct s390_idle_data idle; u64 end; @@ -45,9 +45,8 @@ static void __udelay_disabled(unsigned long long usecs) psw_mask = __extract_psw() | PSW_MASK_EXT | PSW_MASK_WAIT; set_clock_comparator(end); set_cpu_flag(CIF_IGNORE_IRQ); - local_irq_save(flags); psw_idle(&idle, psw_mask); - local_irq_restore(flags); + trace_hardirqs_off(); clear_cpu_flag(CIF_IGNORE_IRQ); set_clock_comparator(S390_lowcore.clock_comparator); __ctl_load(cr0, 0, 0); diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index cfb0017f33a7..64795d034926 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2690,6 +2690,8 @@ static const struct mm_walk_ops reset_acc_walk_ops = { #include <linux/sched/mm.h> void s390_reset_acc(struct mm_struct *mm) { + if (!mm_is_protected(mm)) + return; /* * we might be called during * reset: we walk the pages and clear diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 743f257cf2cb..75217fb63d7b 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -103,9 +103,10 @@ static int zpci_set_irq_affinity(struct irq_data *data, const struct cpumask *de { struct msi_desc *entry = irq_get_msi_desc(data->irq); struct msi_msg msg = entry->msg; + int cpu_addr = smp_cpu_get_cpu_address(cpumask_first(dest)); msg.address_lo &= 0xff0000ff; - msg.address_lo |= (cpumask_first(dest) << 8); + msg.address_lo |= (cpu_addr << 8); pci_write_msi_msg(data->irq, &msg); return IRQ_SET_MASK_OK; @@ -238,6 +239,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) unsigned long bit; struct msi_desc *msi; struct msi_msg msg; + int cpu_addr; int rc, irq; zdev->aisb = -1UL; @@ -287,9 +289,15 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) handle_percpu_irq); msg.data = hwirq - bit; if (irq_delivery == DIRECTED) { + if (msi->affinity) + cpu = cpumask_first(&msi->affinity->mask); + else + cpu = 0; + cpu_addr = smp_cpu_get_cpu_address(cpu); + msg.address_lo = zdev->msi_addr & 0xff0000ff; - msg.address_lo |= msi->affinity ? - (cpumask_first(&msi->affinity->mask) << 8) : 0; + msg.address_lo |= (cpu_addr << 8); + for_each_possible_cpu(cpu) { airq_iv_set_data(zpci_ibv[cpu], hwirq, irq); } diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 0dc0f52f9bb8..f59814983bd5 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -22,7 +22,7 @@ static void (*sh_idle)(void); void default_idle(void) { set_bl_bit(); - local_irq_enable(); + raw_local_irq_enable(); /* Isn't this racy ? */ cpu_sleep(); clear_bl_bit(); diff --git a/arch/sparc/kernel/leon_pmc.c b/arch/sparc/kernel/leon_pmc.c index 065e2d4b7290..396f46bca52e 100644 --- a/arch/sparc/kernel/leon_pmc.c +++ b/arch/sparc/kernel/leon_pmc.c @@ -50,7 +50,7 @@ static void pmc_leon_idle_fixup(void) register unsigned int address = (unsigned int)leon3_irqctrl_regs; /* Interrupts need to be enabled to not hang the CPU */ - local_irq_enable(); + raw_local_irq_enable(); __asm__ __volatile__ ( "wr %%g0, %%asr19\n" @@ -66,7 +66,7 @@ static void pmc_leon_idle_fixup(void) static void pmc_leon_idle(void) { /* Interrupts need to be enabled to not hang the CPU */ - local_irq_enable(); + raw_local_irq_enable(); /* For systems without power-down, this will be no-op */ __asm__ __volatile__ ("wr %g0, %asr19\n\t"); diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index adfcaeab3ddc..a02363735915 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -74,7 +74,7 @@ void arch_cpu_idle(void) { if (sparc_idle) (*sparc_idle)(); - local_irq_enable(); + raw_local_irq_enable(); } /* XXX cli/sti -> local_irq_xxx here, check this works once SMP is fixed. */ diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index a75093b993f9..6f8c7822fc06 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -62,11 +62,11 @@ void arch_cpu_idle(void) { if (tlb_type != hypervisor) { touch_nmi_watchdog(); - local_irq_enable(); + raw_local_irq_enable(); } else { unsigned long pstate; - local_irq_enable(); + raw_local_irq_enable(); /* The sun4v sleeping code requires that we have PSTATE.IE cleared over * the cpu sleep hypervisor call. diff --git a/arch/sparc/lib/csum_copy.S b/arch/sparc/lib/csum_copy.S index 0c0268e77155..d839956407a7 100644 --- a/arch/sparc/lib/csum_copy.S +++ b/arch/sparc/lib/csum_copy.S @@ -71,7 +71,7 @@ FUNC_NAME: /* %o0=src, %o1=dst, %o2=len */ LOAD(prefetch, %o0 + 0x000, #n_reads) xor %o0, %o1, %g1 - mov 1, %o3 + mov -1, %o3 clr %o4 andcc %g1, 0x3, %g0 bne,pn %icc, 95f diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h index 5393e13e07e0..2bbf28cf3aa9 100644 --- a/arch/um/include/asm/pgalloc.h +++ b/arch/um/include/asm/pgalloc.h @@ -33,7 +33,13 @@ do { \ } while (0) #ifdef CONFIG_3_LEVEL_PGTABLES -#define __pmd_free_tlb(tlb,x, address) tlb_remove_page((tlb),virt_to_page(x)) + +#define __pmd_free_tlb(tlb, pmd, address) \ +do { \ + pgtable_pmd_page_dtor(virt_to_page(pmd)); \ + tlb_remove_page((tlb),virt_to_page(pmd)); \ +} while (0) \ + #endif #endif diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 3bed09538dd9..9505a7e87396 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -217,7 +217,7 @@ void arch_cpu_idle(void) { cpu_tasks[current_thread_info()->cpu].pid = os_getpid(); um_idle_sleep(); - local_irq_enable(); + raw_local_irq_enable(); } int __cant_sleep(void) { diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f6946b81f74a..fbf26e0f7a6a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -100,6 +100,7 @@ config X86 select ARCH_WANT_DEFAULT_BPF_JIT if X86_64 select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANT_HUGE_PMD_SHARE + select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANTS_THP_SWAP if X86_64 select BUILDTIME_TABLE_SORT select CLKEVT_I8253 diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 154259f18b8b..1bf21746f4ce 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -209,9 +209,6 @@ ifdef CONFIG_X86_64 LDFLAGS_vmlinux += -z max-page-size=0x200000 endif -# We never want expected sections to be placed heuristically by the -# linker. All sections should be explicitly named in the linker script. -LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn) archscripts: scripts_basic $(Q)$(MAKE) $(build)=arch/x86/tools relocs diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index ee249088cbfe..40b8fd375d52 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -61,7 +61,9 @@ KBUILD_LDFLAGS += $(call ld-option,--no-ld-generated-unwind-info) # Compressed kernel should be built as PIE since it may be loaded at any # address by the bootloader. LDFLAGS_vmlinux := -pie $(call ld-option, --no-dynamic-linker) -LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn) +ifdef CONFIG_LD_ORPHAN_WARN +LDFLAGS_vmlinux += --orphan-handling=warn +endif LDFLAGS_vmlinux += -T hostprogs := mkpiggy diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index 954cb2702e23..27826c265aab 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -32,13 +32,12 @@ struct ghcb *boot_ghcb; */ static bool insn_has_rep_prefix(struct insn *insn) { + insn_byte_t p; int i; insn_get_prefixes(insn); - for (i = 0; i < insn->prefixes.nbytes; i++) { - insn_byte_t p = insn->prefixes.bytes[i]; - + for_each_insn_prefix(insn, i, p) { if (p == 0xf2 || p == 0xf3) return true; } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index f1926e9f2143..af457f8cb29d 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2630,7 +2630,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) u64 pebs_enabled = cpuc->pebs_enabled; handled++; - x86_pmu.drain_pebs(regs); + x86_pmu.drain_pebs(regs, &data); status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; /* @@ -4987,6 +4987,12 @@ __init int intel_pmu_init(void) x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */ + if (version >= 5) { + x86_pmu.intel_cap.anythread_deprecated = edx.split.anythread_deprecated; + if (x86_pmu.intel_cap.anythread_deprecated) + pr_cont(" AnyThread deprecated, "); + } + /* * Install the hw-cache-events table: */ @@ -5512,6 +5518,10 @@ __init int intel_pmu_init(void) x86_pmu.intel_ctrl |= ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED; + /* AnyThread may be deprecated on arch perfmon v5 or later */ + if (x86_pmu.intel_cap.anythread_deprecated) + x86_pmu.format_attrs = intel_arch_formats_attr; + if (x86_pmu.event_constraints) { /* * event on fixed counter2 (REF_CYCLES) only works on this diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 442e1ed4acd4..4eb7ee5fed72 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -107,14 +107,14 @@ MODULE_LICENSE("GPL"); #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __cstate_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ +static ssize_t __cstate_##_var##_show(struct device *dev, \ + struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ -static struct kobj_attribute format_attr_##_var = \ +static struct device_attribute format_attr_##_var = \ __ATTR(_name, 0444, __cstate_##_var##_show, NULL) static ssize_t cstate_get_attr_cpumask(struct device *dev, diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 404315df1e16..485c5066f8b8 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -642,8 +642,8 @@ int intel_pmu_drain_bts_buffer(void) rcu_read_lock(); perf_prepare_sample(&header, &data, event, ®s); - if (perf_output_begin(&handle, event, header.size * - (top - base - skip))) + if (perf_output_begin(&handle, &data, event, + header.size * (top - base - skip))) goto unlock; for (at = base; at < top; at++) { @@ -670,7 +670,9 @@ unlock: static inline void intel_pmu_drain_pebs_buffer(void) { - x86_pmu.drain_pebs(NULL); + struct perf_sample_data data; + + x86_pmu.drain_pebs(NULL, &data); } /* @@ -1719,23 +1721,24 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) return 0; } -static void __intel_pmu_pebs_event(struct perf_event *event, - struct pt_regs *iregs, - void *base, void *top, - int bit, int count, - void (*setup_sample)(struct perf_event *, - struct pt_regs *, - void *, - struct perf_sample_data *, - struct pt_regs *)) +static __always_inline void +__intel_pmu_pebs_event(struct perf_event *event, + struct pt_regs *iregs, + struct perf_sample_data *data, + void *base, void *top, + int bit, int count, + void (*setup_sample)(struct perf_event *, + struct pt_regs *, + void *, + struct perf_sample_data *, + struct pt_regs *)) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - struct perf_sample_data data; struct x86_perf_regs perf_regs; struct pt_regs *regs = &perf_regs.regs; void *at = get_next_pebs_record_by_bit(base, top, bit); - struct pt_regs dummy_iregs; + static struct pt_regs dummy_iregs; if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { /* @@ -1752,14 +1755,14 @@ static void __intel_pmu_pebs_event(struct perf_event *event, iregs = &dummy_iregs; while (count > 1) { - setup_sample(event, iregs, at, &data, regs); - perf_event_output(event, &data, regs); + setup_sample(event, iregs, at, data, regs); + perf_event_output(event, data, regs); at += cpuc->pebs_record_size; at = get_next_pebs_record_by_bit(at, top, bit); count--; } - setup_sample(event, iregs, at, &data, regs); + setup_sample(event, iregs, at, data, regs); if (iregs == &dummy_iregs) { /* * The PEBS records may be drained in the non-overflow context, @@ -1767,18 +1770,18 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * last record the same as other PEBS records, and doesn't * invoke the generic overflow handler. */ - perf_event_output(event, &data, regs); + perf_event_output(event, data, regs); } else { /* * All but the last records are processed. * The last one is left to be able to call the overflow handler. */ - if (perf_event_overflow(event, &data, regs)) + if (perf_event_overflow(event, data, regs)) x86_pmu_stop(event, 0); } } -static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) +static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; @@ -1812,7 +1815,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) return; } - __intel_pmu_pebs_event(event, iregs, at, top, 0, n, + __intel_pmu_pebs_event(event, iregs, data, at, top, 0, n, setup_pebs_fixed_sample_data); } @@ -1835,7 +1838,7 @@ static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int } } -static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) +static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_data *data) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; @@ -1913,7 +1916,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * that caused the PEBS record. It's called collision. * If collision happened, the record will be dropped. */ - if (p->status != (1ULL << bit)) { + if (pebs_status != (1ULL << bit)) { for_each_set_bit(i, (unsigned long *)&pebs_status, size) error[i]++; continue; @@ -1937,19 +1940,19 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) if (error[bit]) { perf_log_lost_samples(event, error[bit]); - if (perf_event_account_interrupt(event)) + if (iregs && perf_event_account_interrupt(event)) x86_pmu_stop(event, 0); } if (counts[bit]) { - __intel_pmu_pebs_event(event, iregs, base, + __intel_pmu_pebs_event(event, iregs, data, base, top, bit, counts[bit], setup_pebs_fixed_sample_data); } } } -static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs) +static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data) { short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -1997,7 +2000,7 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs) if (WARN_ON_ONCE(!event->attr.precise_ip)) continue; - __intel_pmu_pebs_event(event, iregs, base, + __intel_pmu_pebs_event(event, iregs, data, base, top, bit, counts[bit], setup_pebs_adaptive_sample_data); } diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 86d012b3e0b4..80d52cbe2fde 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -94,8 +94,8 @@ end: return map; } -ssize_t uncore_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) +ssize_t uncore_event_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct uncore_event_desc *event = container_of(attr, struct uncore_event_desc, attr); diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 83d2a7d490e0..9efea154349d 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -157,7 +157,7 @@ struct intel_uncore_box { #define UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS 2 struct uncore_event_desc { - struct kobj_attribute attr; + struct device_attribute attr; const char *config; }; @@ -179,8 +179,8 @@ struct pci2phy_map { struct pci2phy_map *__find_pci2phy_map(int segment); int uncore_pcibus_to_physid(struct pci_bus *bus); -ssize_t uncore_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf); +ssize_t uncore_event_show(struct device *dev, + struct device_attribute *attr, char *buf); static inline struct intel_uncore_pmu *dev_to_uncore_pmu(struct device *dev) { @@ -201,14 +201,14 @@ extern int __uncore_max_dies; } #define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __uncore_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ +static ssize_t __uncore_##_var##_show(struct device *dev, \ + struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ -static struct kobj_attribute format_attr_##_var = \ +static struct device_attribute format_attr_##_var = \ __ATTR(_name, 0444, __uncore_##_var##_show, NULL) static inline bool uncore_pmc_fixed(int idx) diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 39e632ed6ca9..bbd1120ae161 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -475,7 +475,7 @@ enum perf_snb_uncore_imc_freerunning_types { static struct freerunning_counters snb_uncore_imc_freerunning[] = { [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x0, 0x0, 1, 32 }, - [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, + [SNB_PCI_UNCORE_IMC_DATA_WRITES] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, 0x0, 0x0, 1, 32 }, [SNB_PCI_UNCORE_IMC_GT_REQUESTS] = { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE, 0x0, 0x0, 1, 32 }, diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ee2b9b9fc2a5..6a8edfe59b09 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -585,6 +585,7 @@ union perf_capabilities { u64 pebs_baseline:1; u64 perf_metrics:1; u64 pebs_output_pt_available:1; + u64 anythread_deprecated:1; }; u64 capabilities; }; @@ -727,7 +728,7 @@ struct x86_pmu { int pebs_record_size; int pebs_buffer_size; int max_pebs_events; - void (*drain_pebs)(struct pt_regs *regs); + void (*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); unsigned long large_pebs_flags; diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 7c0120e2e957..7dbbeaacd995 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -93,18 +93,6 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { * any other bit is reserved */ #define RAPL_EVENT_MASK 0xFFULL - -#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __rapl_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ - char *page) \ -{ \ - BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ - return sprintf(page, _format "\n"); \ -} \ -static struct kobj_attribute format_attr_##_var = \ - __ATTR(_name, 0444, __rapl_##_var##_show, NULL) - #define RAPL_CNTR_WIDTH 32 #define RAPL_EVENT_ATTR_STR(_name, v, str) \ @@ -441,7 +429,7 @@ static struct attribute_group rapl_pmu_events_group = { .attrs = attrs_empty, }; -DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7"); +PMU_FORMAT_ATTR(event, "config:0-7"); static struct attribute *rapl_formats_attr[] = { &format_attr_event.attr, NULL, diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index 5c1ae3eff9d4..a8c3d284fa46 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -201,6 +201,21 @@ static inline int insn_offset_immediate(struct insn *insn) return insn_offset_displacement(insn) + insn->displacement.nbytes; } +/** + * for_each_insn_prefix() -- Iterate prefixes in the instruction + * @insn: Pointer to struct insn. + * @idx: Index storage. + * @prefix: Prefix byte. + * + * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix + * and the index is stored in @idx (note that this @idx is just for a cursor, + * do not change it.) + * Since prefixes.nbytes can be bigger than 4 if some prefixes + * are repeated, it cannot be used for looping over the prefixes. + */ +#define for_each_insn_prefix(insn, idx, prefix) \ + for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++) + #define POP_SS_OPCODE 0x1f #define MOV_SREG_OPCODE 0x8e diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d44858b69353..7e5f33a0d0e2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -639,6 +639,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; + unsigned long cr3_lm_rsvd_bits; int maxphyaddr; int max_tdp_level; @@ -1655,6 +1656,7 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); +int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index e039a933aca3..29dd27b5a339 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -88,8 +88,6 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx, static inline void __sti_mwait(unsigned long eax, unsigned long ecx) { - trace_hardirqs_on(); - mds_idle_clear_cpu_buffers(); /* "mwait %eax, %ecx;" */ asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 6960cd6d1f23..b9a7fd0a27e2 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -137,7 +137,9 @@ union cpuid10_edx { struct { unsigned int num_counters_fixed:5; unsigned int bit_width_fixed:8; - unsigned int reserved:19; + unsigned int reserved1:2; + unsigned int anythread_deprecated:1; + unsigned int reserved2:16; } split; unsigned int full; }; diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 816b31c68550..394757ee030a 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -155,6 +155,7 @@ enum page_cache_mode { #define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) #define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT) +#define _PAGE_LARGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT_LARGE) #define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC)) #define _PAGE_CACHE_WP (cachemode2protval(_PAGE_CACHE_MODE_WP)) diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 6bfc878f6771..6a9ccc1b2be5 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -28,4 +28,14 @@ #endif #endif /* CONFIG_SPARSEMEM */ + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_NUMA_KEEP_MEMINFO +extern int phys_to_target_node(phys_addr_t start); +#define phys_to_target_node phys_to_target_node +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif +#endif /* __ASSEMBLY__ */ + #endif /* _ASM_X86_SPARSEMEM_H */ diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h index 0fd4a9dfb29c..ab7382f92aff 100644 --- a/arch/x86/include/asm/sync_core.h +++ b/arch/x86/include/asm/sync_core.h @@ -98,12 +98,13 @@ static inline void sync_core_before_usermode(void) /* With PTI, we unconditionally serialize before running user code. */ if (static_cpu_has(X86_FEATURE_PTI)) return; + /* - * Return from interrupt and NMI is done through iret, which is core - * serializing. + * Even if we're in an interrupt, we might reschedule before returning, + * in which case we could switch to a different thread in the same mm + * and return using SYSRET or SYSEXIT. Instead of trying to keep + * track of our need to sync the core, just sync right away. */ - if (in_irq() || in_nmi()) - return; sync_core(); } diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 172d3e4a9e4b..648eb23fe7f0 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -2,14 +2,8 @@ #ifndef _ASM_X86_UV_UV_H #define _ASM_X86_UV_UV_H -#include <asm/tlbflush.h> - enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC}; -struct cpumask; -struct mm_struct; -struct flush_tlb_info; - #ifdef CONFIG_X86_UV #include <linux/efi.h> @@ -44,10 +38,6 @@ static inline int is_uv_system(void) { return 0; } static inline int is_uv_hubbed(int uv) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } -static inline const struct cpumask * -uv_flush_tlb_others(const struct cpumask *cpumask, - const struct flush_tlb_info *info) -{ return cpumask; } #endif /* X86_UV */ diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 1eac53632786..758bbf25ef74 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -273,20 +273,24 @@ static int assign_irq_vector_any_locked(struct irq_data *irqd) const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd); int node = irq_data_get_node(irqd); - if (node == NUMA_NO_NODE) - goto all; - /* Try the intersection of @affmsk and node mask */ - cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk); - if (!assign_vector_locked(irqd, vector_searchmask)) - return 0; - /* Try the node mask */ - if (!assign_vector_locked(irqd, cpumask_of_node(node))) - return 0; -all: + if (node != NUMA_NO_NODE) { + /* Try the intersection of @affmsk and node mask */ + cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk); + if (!assign_vector_locked(irqd, vector_searchmask)) + return 0; + } + /* Try the full affinity mask */ cpumask_and(vector_searchmask, affmsk, cpu_online_mask); if (!assign_vector_locked(irqd, vector_searchmask)) return 0; + + if (node != NUMA_NO_NODE) { + /* Try the node mask */ + if (!assign_vector_locked(irqd, cpumask_of_node(node))) + return 0; + } + /* Try the full online mask */ return assign_vector_locked(irqd, cpu_online_mask); } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 3115caa7d7d0..235f5cde06fc 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -33,7 +33,7 @@ static union uvh_apicid uvh_apicid; static int uv_node_id; /* Unpack AT/OEM/TABLE ID's to be NULL terminated strings */ -static u8 uv_archtype[UV_AT_SIZE]; +static u8 uv_archtype[UV_AT_SIZE + 1]; static u8 oem_id[ACPI_OEM_ID_SIZE + 1]; static u8 oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1]; @@ -161,7 +161,7 @@ static int __init early_set_hub_type(void) /* UV4/4A only have a revision difference */ case UV4_HUB_PART_NUMBER: uv_min_hub_revision_id = node_id.s.revision - + UV4_HUB_REVISION_BASE; + + UV4_HUB_REVISION_BASE - 1; uv_hub_type_set(UV4); if (uv_min_hub_revision_id == UV4A_HUB_REVISION_BASE) uv_hub_type_set(UV4|UV4A); @@ -320,7 +320,7 @@ static int __init decode_arch_type(unsigned long ptr) if (n > 0 && n < sizeof(uv_ate->archtype)) { pr_info("UV: UVarchtype received from BIOS\n"); - uv_stringify(UV_AT_SIZE, uv_archtype, uv_ate->archtype); + uv_stringify(sizeof(uv_archtype), uv_archtype, uv_ate->archtype); return 1; } return 0; @@ -378,7 +378,7 @@ static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id) if (!early_get_arch_type()) /* If not use OEM ID for UVarchtype */ - uv_stringify(UV_AT_SIZE, uv_archtype, _oem_id); + uv_stringify(sizeof(uv_archtype), uv_archtype, oem_id); /* Check if not hubbed */ if (strncmp(uv_archtype, "SGI", 3) != 0) { diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 581fb7223ad0..d41b70fe4918 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -739,11 +739,13 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + spectre_v2_user_ibpb = mode; switch (cmd) { case SPECTRE_V2_USER_CMD_FORCE: case SPECTRE_V2_USER_CMD_PRCTL_IBPB: case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: static_branch_enable(&switch_mm_always_ibpb); + spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT; break; case SPECTRE_V2_USER_CMD_PRCTL: case SPECTRE_V2_USER_CMD_AUTO: @@ -757,8 +759,6 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n", static_key_enabled(&switch_mm_always_ibpb) ? "always-on" : "conditional"); - - spectre_v2_user_ibpb = mode; } /* diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 4102b866e7c0..32b7099e3511 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1384,8 +1384,10 @@ noinstr void do_machine_check(struct pt_regs *regs) * When there's any problem use only local no_way_out state. */ if (!lmce) { - if (mce_end(order) < 0) - no_way_out = worst >= MCE_PANIC_SEVERITY; + if (mce_end(order) < 0) { + if (!no_way_out) + no_way_out = worst >= MCE_PANIC_SEVERITY; + } } else { /* * If there was a fatal machine check we should have diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 6a99535d7f37..7e8e07bddd5f 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -100,53 +100,6 @@ static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev return find_matching_signature(mc, csig, cpf); } -/* - * Given CPU signature and a microcode patch, this function finds if the - * microcode patch has matching family and model with the CPU. - * - * %true - if there's a match - * %false - otherwise - */ -static bool microcode_matches(struct microcode_header_intel *mc_header, - unsigned long sig) -{ - unsigned long total_size = get_totalsize(mc_header); - unsigned long data_size = get_datasize(mc_header); - struct extended_sigtable *ext_header; - unsigned int fam_ucode, model_ucode; - struct extended_signature *ext_sig; - unsigned int fam, model; - int ext_sigcount, i; - - fam = x86_family(sig); - model = x86_model(sig); - - fam_ucode = x86_family(mc_header->sig); - model_ucode = x86_model(mc_header->sig); - - if (fam == fam_ucode && model == model_ucode) - return true; - - /* Look for ext. headers: */ - if (total_size <= data_size + MC_HEADER_SIZE) - return false; - - ext_header = (void *) mc_header + data_size + MC_HEADER_SIZE; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; - ext_sigcount = ext_header->count; - - for (i = 0; i < ext_sigcount; i++) { - fam_ucode = x86_family(ext_sig->sig); - model_ucode = x86_model(ext_sig->sig); - - if (fam == fam_ucode && model == model_ucode) - return true; - - ext_sig++; - } - return false; -} - static struct ucode_patch *memdup_patch(void *data, unsigned int size) { struct ucode_patch *p; @@ -164,7 +117,7 @@ static struct ucode_patch *memdup_patch(void *data, unsigned int size) return p; } -static void save_microcode_patch(void *data, unsigned int size) +static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigned int size) { struct microcode_header_intel *mc_hdr, *mc_saved_hdr; struct ucode_patch *iter, *tmp, *p = NULL; @@ -210,6 +163,9 @@ static void save_microcode_patch(void *data, unsigned int size) if (!p) return; + if (!find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf)) + return; + /* * Save for early loading. On 32-bit, that needs to be a physical * address as the APs are running from physical addresses, before @@ -344,13 +300,14 @@ scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save) size -= mc_size; - if (!microcode_matches(mc_header, uci->cpu_sig.sig)) { + if (!find_matching_signature(data, uci->cpu_sig.sig, + uci->cpu_sig.pf)) { data += mc_size; continue; } if (save) { - save_microcode_patch(data, mc_size); + save_microcode_patch(uci, data, mc_size); goto next; } @@ -483,14 +440,14 @@ static void show_saved_mc(void) * Save this microcode patch. It will be loaded early when a CPU is * hot-added or resumes. */ -static void save_mc_for_early(u8 *mc, unsigned int size) +static void save_mc_for_early(struct ucode_cpu_info *uci, u8 *mc, unsigned int size) { /* Synchronization during CPU hotplug. */ static DEFINE_MUTEX(x86_cpu_microcode_mutex); mutex_lock(&x86_cpu_microcode_mutex); - save_microcode_patch(mc, size); + save_microcode_patch(uci, mc, size); show_saved_mc(); mutex_unlock(&x86_cpu_microcode_mutex); @@ -935,7 +892,7 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter) * permanent memory. So it will be loaded early when a CPU is hot added * or resumes. */ - save_mc_for_early(new_mc, new_mc_size); + save_mc_for_early(uci, new_mc, new_mc_size); pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index e5f4ee8f4c3b..e8b5f1cf1ae8 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -570,6 +570,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) if (d) { cpumask_set_cpu(cpu, &d->cpu_mask); + if (r->cache.arch_has_per_cpu_cfg) + rdt_domain_reconfigure_cdp(r); return; } @@ -923,6 +925,7 @@ static __init void rdt_init_res_defs_intel(void) r->rid == RDT_RESOURCE_L2CODE) { r->cache.arch_has_sparse_bitmaps = false; r->cache.arch_has_empty_bitmaps = false; + r->cache.arch_has_per_cpu_cfg = false; } else if (r->rid == RDT_RESOURCE_MBA) { r->msr_base = MSR_IA32_MBA_THRTL_BASE; r->msr_update = mba_wrmsr_intel; @@ -943,6 +946,7 @@ static __init void rdt_init_res_defs_amd(void) r->rid == RDT_RESOURCE_L2CODE) { r->cache.arch_has_sparse_bitmaps = true; r->cache.arch_has_empty_bitmaps = true; + r->cache.arch_has_per_cpu_cfg = true; } else if (r->rid == RDT_RESOURCE_MBA) { r->msr_base = MSR_IA32_MBA_BW_BASE; r->msr_update = mba_wrmsr_amd; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 80fa997fae60..f65d3c0dbc41 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -360,6 +360,8 @@ struct msr_param { * executing entities * @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid. * @arch_has_empty_bitmaps: True if the '0' bitmap is valid. + * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache + * level has CPU scope. */ struct rdt_cache { unsigned int cbm_len; @@ -369,6 +371,7 @@ struct rdt_cache { unsigned int shareable_bits; bool arch_has_sparse_bitmaps; bool arch_has_empty_bitmaps; + bool arch_has_per_cpu_cfg; }; /** diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 54dffe574e67..a98519a3a2e6 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -279,7 +279,6 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) return; chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width); - m->chunks += chunks; cur_bw = (chunks * r->mon_scale) >> 20; if (m->delta_comp) @@ -450,15 +449,14 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) } if (is_mbm_local_enabled()) { rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; + __mon_event_count(rmid, &rr); /* * Call the MBA software controller only for the * control groups and when user has enabled * the software controller explicitly. */ - if (!is_mba_sc(NULL)) - __mon_event_count(rmid, &rr); - else + if (is_mba_sc(NULL)) mbm_bw_count(rmid, &rr); } } diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index af323e2e3100..f3418428682b 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -507,6 +507,24 @@ unlock: return ret ?: nbytes; } +/** + * rdtgroup_remove - the helper to remove resource group safely + * @rdtgrp: resource group to remove + * + * On resource group creation via a mkdir, an extra kernfs_node reference is + * taken to ensure that the rdtgroup structure remains accessible for the + * rdtgroup_kn_unlock() calls where it is removed. + * + * Drop the extra reference here, then free the rdtgroup structure. + * + * Return: void + */ +static void rdtgroup_remove(struct rdtgroup *rdtgrp) +{ + kernfs_put(rdtgrp->kn); + kfree(rdtgrp); +} + struct task_move_callback { struct callback_head work; struct rdtgroup *rdtgrp; @@ -529,7 +547,7 @@ static void move_myself(struct callback_head *head) (rdtgrp->flags & RDT_DELETED)) { current->closid = 0; current->rmid = 0; - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } if (unlikely(current->flags & PF_EXITING)) @@ -1769,7 +1787,6 @@ static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, if (IS_ERR(kn_subdir)) return PTR_ERR(kn_subdir); - kernfs_get(kn_subdir); ret = rdtgroup_kn_set_ugid(kn_subdir); if (ret) return ret; @@ -1792,7 +1809,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); if (IS_ERR(kn_info)) return PTR_ERR(kn_info); - kernfs_get(kn_info); ret = rdtgroup_add_files(kn_info, RF_TOP_INFO); if (ret) @@ -1813,12 +1829,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) goto out_destroy; } - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that @rdtgrp->kn is always accessible. - */ - kernfs_get(kn_info); - ret = rdtgroup_kn_set_ugid(kn_info); if (ret) goto out_destroy; @@ -1847,12 +1857,6 @@ mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, if (dest_kn) *dest_kn = kn; - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that @rdtgrp->kn is always accessible. - */ - kernfs_get(kn); - ret = rdtgroup_kn_set_ugid(kn); if (ret) goto out_destroy; @@ -1905,8 +1909,13 @@ static int set_cache_qos_cfg(int level, bool enable) r_l = &rdt_resources_all[level]; list_for_each_entry(d, &r_l->domains, list) { - /* Pick one CPU from each domain instance to update MSR */ - cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + if (r_l->cache.arch_has_per_cpu_cfg) + /* Pick all the CPUs in the domain instance */ + for_each_cpu(cpu, &d->cpu_mask) + cpumask_set_cpu(cpu, cpu_mask); + else + /* Pick one CPU from each domain instance to update MSR */ + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); } cpu = get_cpu(); /* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */ @@ -2079,8 +2088,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) rdtgroup_pseudo_lock_remove(rdtgrp); kernfs_unbreak_active_protection(kn); - kernfs_put(rdtgrp->kn); - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } else { kernfs_unbreak_active_protection(kn); } @@ -2139,13 +2147,11 @@ static int rdt_get_tree(struct fs_context *fc) &kn_mongrp); if (ret < 0) goto out_info; - kernfs_get(kn_mongrp); ret = mkdir_mondata_all(rdtgroup_default.kn, &rdtgroup_default, &kn_mondata); if (ret < 0) goto out_mongrp; - kernfs_get(kn_mondata); rdtgroup_default.mon.mon_data_kn = kn_mondata; } @@ -2357,7 +2363,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) if (atomic_read(&sentry->waitcount) != 0) sentry->flags = RDT_DELETED; else - kfree(sentry); + rdtgroup_remove(sentry); } } @@ -2399,7 +2405,7 @@ static void rmdir_all_sub(void) if (atomic_read(&rdtgrp->waitcount) != 0) rdtgrp->flags = RDT_DELETED; else - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ update_closid_rmid(cpu_online_mask, &rdtgroup_default); @@ -2499,11 +2505,6 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, if (IS_ERR(kn)) return PTR_ERR(kn); - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that kn is always accessible. - */ - kernfs_get(kn); ret = rdtgroup_kn_set_ugid(kn); if (ret) goto out_destroy; @@ -2838,8 +2839,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, /* * kernfs_remove() will drop the reference count on "kn" which * will free it. But we still need it to stick around for the - * rdtgroup_kn_unlock(kn} call below. Take one extra reference - * here, which will be dropped inside rdtgroup_kn_unlock(). + * rdtgroup_kn_unlock(kn) call. Take one extra reference here, + * which will be dropped by kernfs_put() in rdtgroup_remove(). */ kernfs_get(kn); @@ -2880,6 +2881,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, out_idfree: free_rmid(rdtgrp->mon.rmid); out_destroy: + kernfs_put(rdtgrp->kn); kernfs_remove(rdtgrp->kn); out_free_rgrp: kfree(rdtgrp); @@ -2892,7 +2894,7 @@ static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) { kernfs_remove(rgrp->kn); free_rmid(rgrp->mon.rmid); - kfree(rgrp); + rdtgroup_remove(rgrp); } /* @@ -3049,11 +3051,6 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); list_del(&rdtgrp->mon.crdtgrp_list); - /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); kernfs_remove(rdtgrp->kn); return 0; @@ -3065,11 +3062,6 @@ static int rdtgroup_ctrl_remove(struct kernfs_node *kn, rdtgrp->flags = RDT_DELETED; list_del(&rdtgrp->rdtgroup_list); - /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); kernfs_remove(rdtgrp->kn); return 0; } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 25c06b67e7e0..97aa900386cb 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -78,6 +78,9 @@ static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, if (!user_mode(regs)) return copy_from_kernel_nofault(buf, (u8 *)src, nbytes); + /* The user space code from other tasks cannot be accessed. */ + if (regs != task_pt_regs(current)) + return -EPERM; /* * Make sure userspace isn't trying to trick us into dumping kernel * memory by pointing the userspace instruction pointer at it. @@ -85,6 +88,12 @@ static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX)) return -EINVAL; + /* + * Even if named copy_from_user_nmi() this can be invoked from + * other contexts and will not try to resolve a pagefault, which is + * the correct thing to do here as this code can be called from any + * context. + */ return copy_from_user_nmi(buf, (void __user *)src, nbytes); } @@ -115,13 +124,19 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) u8 opcodes[OPCODE_BUFSIZE]; unsigned long prologue = regs->ip - PROLOGUE_SIZE; - if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { - printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", - loglvl, prologue); - } else { + switch (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { + case 0: printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes, opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1); + break; + case -EPERM: + /* No access to the user space stack of other tasks. Ignore. */ + break; + default: + printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", + loglvl, prologue); + break; } } diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 041f0b50bc27..08eb23074f92 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -272,6 +272,19 @@ static int insn_is_indirect_jump(struct insn *insn) return ret; } +static bool is_padding_int3(unsigned long addr, unsigned long eaddr) +{ + unsigned char ops; + + for (; addr < eaddr; addr++) { + if (get_kernel_nofault(ops, (void *)addr) < 0 || + ops != INT3_INSN_OPCODE) + return false; + } + + return true; +} + /* Decode whole function to ensure any instructions don't jump into target */ static int can_optimize(unsigned long paddr) { @@ -310,9 +323,14 @@ static int can_optimize(unsigned long paddr) return 0; kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); insn_get_length(&insn); - /* Another subsystem puts a breakpoint */ + /* + * In the case of detecting unknown breakpoint, this could be + * a padding INT3 between functions. Let's check that all the + * rest of the bytes are also INT3. + */ if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) - return 0; + return is_padding_int3(addr, paddr - offset + size) ? 1 : 0; + /* Recover address */ insn.kaddr = (void *)addr; insn.next_byte = (void *)(addr + insn.length); diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index bb7e1132290b..f9e5352b3bef 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -101,8 +101,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); @@ -129,12 +128,20 @@ u64 perf_reg_abi(struct task_struct *task) return PERF_SAMPLE_REGS_ABI_64; } +static DEFINE_PER_CPU(struct pt_regs, nmi_user_regs); + void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { + struct pt_regs *regs_user_copy = this_cpu_ptr(&nmi_user_regs); struct pt_regs *user_regs = task_pt_regs(current); + if (!in_nmi()) { + regs_user->regs = user_regs; + regs_user->abi = perf_reg_abi(current); + return; + } + /* * If we're in an NMI that interrupted task_pt_regs setup, then * we can't sample user regs at all. This check isn't really diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ba4593a913fa..145a7ac0c19a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -685,7 +685,7 @@ void arch_cpu_idle(void) */ void __cpuidle default_idle(void) { - safe_halt(); + raw_safe_halt(); } #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) EXPORT_SYMBOL(default_idle); @@ -736,6 +736,8 @@ void stop_this_cpu(void *dummy) /* * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power * states (local apic timer and TSC stop). + * + * XXX this function is completely buggered vs RCU and tracing. */ static void amd_e400_idle(void) { @@ -757,9 +759,9 @@ static void amd_e400_idle(void) * The switch back from broadcast mode needs to be called with * interrupts disabled. */ - local_irq_disable(); + raw_local_irq_disable(); tick_broadcast_exit(); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -801,9 +803,9 @@ static __cpuidle void mwait_idle(void) if (!need_resched()) __sti_mwait(0, 0); else - local_irq_enable(); + raw_local_irq_enable(); } else { - local_irq_enable(); + raw_local_irq_enable(); } __current_clr_polling(); } diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 992fb1415c0f..ae64f98ec2ab 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -514,16 +514,10 @@ int tboot_force_iommu(void) if (!tboot_enabled()) return 0; - if (intel_iommu_tboot_noforce) - return 1; - - if (no_iommu || swiotlb || dmar_disabled) + if (no_iommu || dmar_disabled) pr_warn("Forcing Intel-IOMMU to enabled\n"); dmar_disabled = 0; -#ifdef CONFIG_SWIOTLB - swiotlb = 0; -#endif no_iommu = 0; return 1; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 3fdaa042823d..138bdb1fd136 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -255,12 +255,13 @@ static volatile u32 good_2byte_insns[256 / 32] = { static bool is_prefix_bad(struct insn *insn) { + insn_byte_t p; int i; - for (i = 0; i < insn->prefixes.nbytes; i++) { + for_each_insn_prefix(insn, i, p) { insn_attr_t attr; - attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]); + attr = inat_get_opcode_attribute(p); switch (attr) { case INAT_MAKE_PREFIX(INAT_PFX_ES): case INAT_MAKE_PREFIX(INAT_PFX_CS): @@ -715,6 +716,7 @@ static const struct uprobe_xol_ops push_xol_ops = { static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) { u8 opc1 = OPCODE1(insn); + insn_byte_t p; int i; switch (opc1) { @@ -746,8 +748,8 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) * Intel and AMD behavior differ in 64-bit mode: Intel ignores 66 prefix. * No one uses these insns, reject any branch insns with such prefix. */ - for (i = 0; i < insn->prefixes.nbytes; i++) { - if (insn->prefixes.bytes[i] == 0x66) + for_each_insn_prefix(insn, i, p) { + if (p == 0x66) return -ENOTSUPP; } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 06a278b3701d..83637a2ff605 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -90,6 +90,20 @@ static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent) return 0; } +void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0); + + /* + * save the feature bitmap to avoid cpuid lookup for every PV + * operation + */ + if (best) + vcpu->arch.pv_cpuid.features = best->eax; +} + void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -124,13 +138,6 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) (best->eax & (1 << KVM_FEATURE_PV_UNHALT))) best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); - /* - * save the feature bitmap to avoid cpuid lookup for every PV - * operation - */ - if (best) - vcpu->arch.pv_cpuid.features = best->eax; - if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { best = kvm_find_cpuid_entry(vcpu, 0x1, 0); if (best) @@ -162,6 +169,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.guest_supported_xcr0 = (best->eax | ((u64)best->edx << 32)) & supported_xcr0; + kvm_update_pv_runtime(vcpu); + vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); kvm_mmu_reset_context(vcpu); @@ -169,6 +178,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(guest_cpuid_has, vcpu); + vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); + /* Invoke the vendor callback only after the above state is updated. */ kvm_x86_ops.vcpu_after_set_cpuid(vcpu); } @@ -672,7 +683,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS); edx.split.bit_width_fixed = cap.bit_width_fixed; - edx.split.reserved = 0; + edx.split.anythread_deprecated = 1; + edx.split.reserved1 = 0; + edx.split.reserved2 = 0; entry->eax = eax.full; entry->ebx = cap.events_mask; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index bf8577947ed2..f7a6e8f83783 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -11,6 +11,7 @@ extern u32 kvm_cpu_caps[NCAPINTS] __read_mostly; void kvm_set_cpu_caps(void); void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu); +void kvm_update_pv_runtime(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function, u32 index); int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 0d917eb70319..56cae1ff9e3f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4046,6 +4046,12 @@ static int em_clflush(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_clflushopt(struct x86_emulate_ctxt *ctxt) +{ + /* emulating clflushopt regardless of cpuid */ + return X86EMUL_CONTINUE; +} + static int em_movsxd(struct x86_emulate_ctxt *ctxt) { ctxt->dst.val = (s32) ctxt->src.val; @@ -4585,7 +4591,7 @@ static const struct opcode group11[] = { }; static const struct gprefix pfx_0f_ae_7 = { - I(SrcMem | ByteOp, em_clflush), N, N, N, + I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N, }; static const struct group_dual group15 = { { diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 99d118ffc67d..814698e5b152 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -40,29 +40,10 @@ static int pending_userspace_extint(struct kvm_vcpu *v) * check if there is pending interrupt from * non-APIC source without intack. */ -static int kvm_cpu_has_extint(struct kvm_vcpu *v) -{ - u8 accept = kvm_apic_accept_pic_intr(v); - - if (accept) { - if (irqchip_split(v->kvm)) - return pending_userspace_extint(v); - else - return v->kvm->arch.vpic->output; - } else - return 0; -} - -/* - * check if there is injectable interrupt: - * when virtual interrupt delivery enabled, - * interrupt from apic will handled by hardware, - * we don't need to check it here. - */ -int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) +int kvm_cpu_has_extint(struct kvm_vcpu *v) { /* - * FIXME: interrupt.injected represents an interrupt that it's + * FIXME: interrupt.injected represents an interrupt whose * side-effects have already been applied (e.g. bit from IRR * already moved to ISR). Therefore, it is incorrect to rely * on interrupt.injected to know if there is a pending @@ -75,6 +56,23 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) if (!lapic_in_kernel(v)) return v->arch.interrupt.injected; + if (!kvm_apic_accept_pic_intr(v)) + return 0; + + if (irqchip_split(v->kvm)) + return pending_userspace_extint(v); + else + return v->kvm->arch.vpic->output; +} + +/* + * check if there is injectable interrupt: + * when virtual interrupt delivery enabled, + * interrupt from apic will handled by hardware, + * we don't need to check it here. + */ +int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) +{ if (kvm_cpu_has_extint(v)) return 1; @@ -91,20 +89,6 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_injectable_intr); */ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) { - /* - * FIXME: interrupt.injected represents an interrupt that it's - * side-effects have already been applied (e.g. bit from IRR - * already moved to ISR). Therefore, it is incorrect to rely - * on interrupt.injected to know if there is a pending - * interrupt in the user-mode LAPIC. - * This leads to nVMX/nSVM not be able to distinguish - * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on - * pending interrupt or should re-inject an injected - * interrupt. - */ - if (!lapic_in_kernel(v)) - return v->arch.interrupt.injected; - if (kvm_cpu_has_extint(v)) return 1; @@ -118,16 +102,21 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); */ static int kvm_cpu_get_extint(struct kvm_vcpu *v) { - if (kvm_cpu_has_extint(v)) { - if (irqchip_split(v->kvm)) { - int vector = v->arch.pending_external_vector; - - v->arch.pending_external_vector = -1; - return vector; - } else - return kvm_pic_read_irq(v->kvm); /* PIC */ - } else + if (!kvm_cpu_has_extint(v)) { + WARN_ON(!lapic_in_kernel(v)); return -1; + } + + if (!lapic_in_kernel(v)) + return v->arch.interrupt.nr; + + if (irqchip_split(v->kvm)) { + int vector = v->arch.pending_external_vector; + + v->arch.pending_external_vector = -1; + return vector; + } else + return kvm_pic_read_irq(v->kvm); /* PIC */ } /* @@ -135,13 +124,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) */ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) { - int vector; - - if (!lapic_in_kernel(v)) - return v->arch.interrupt.nr; - - vector = kvm_cpu_get_extint(v); - + int vector = kvm_cpu_get_extint(v); if (vector != -1) return vector; /* PIC */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 105e7859d1f2..86c33d53c90a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2465,7 +2465,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; u32 ppr; - if (!kvm_apic_hw_enabled(apic)) + if (!kvm_apic_present(vcpu)) return -1; __apic_update_ppr(apic, &ppr); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 769162e190b1..1f5834b197b5 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -856,12 +856,14 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, } else { rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); - while (desc->sptes[PTE_LIST_EXT-1] && desc->more) { - desc = desc->more; + while (desc->sptes[PTE_LIST_EXT-1]) { count += PTE_LIST_EXT; - } - if (desc->sptes[PTE_LIST_EXT-1]) { - desc->more = mmu_alloc_pte_list_desc(vcpu); + + if (!desc->more) { + desc->more = mmu_alloc_pte_list_desc(vcpu); + desc = desc->more; + break; + } desc = desc->more; } for (i = 0; desc->sptes[i]; ++i) @@ -3515,7 +3517,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { u64 sptes[PT64_ROOT_MAX_LEVEL]; struct rsvd_bits_validate *rsvd_check; - int root = vcpu->arch.mmu->root_level; + int root = vcpu->arch.mmu->shadow_root_level; int leaf; int level; bool reserved = false; diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index fcac2cac78fe..c51ad544f25b 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -40,8 +40,8 @@ static u64 generation_mmio_spte_mask(u64 gen) WARN_ON(gen & ~MMIO_SPTE_GEN_MASK); BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK); - mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK; - mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK; + mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK; + mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK; return mask; } diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 5c75a451c000..2b3a30bd38b0 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -56,11 +56,11 @@ #define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1)) /* - * Due to limited space in PTEs, the MMIO generation is a 19 bit subset of + * Due to limited space in PTEs, the MMIO generation is a 18 bit subset of * the memslots generation and is derived as follows: * * Bits 0-8 of the MMIO generation are propagated to spte bits 3-11 - * Bits 9-18 of the MMIO generation are propagated to spte bits 52-61 + * Bits 9-17 of the MMIO generation are propagated to spte bits 54-62 * * The KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS flag is intentionally not included in * the MMIO generation number, as doing so would require stealing a bit from @@ -69,18 +69,29 @@ * requires a full MMU zap). The flag is instead explicitly queried when * checking for MMIO spte cache hits. */ -#define MMIO_SPTE_GEN_MASK GENMASK_ULL(17, 0) #define MMIO_SPTE_GEN_LOW_START 3 #define MMIO_SPTE_GEN_LOW_END 11 -#define MMIO_SPTE_GEN_LOW_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \ - MMIO_SPTE_GEN_LOW_START) #define MMIO_SPTE_GEN_HIGH_START PT64_SECOND_AVAIL_BITS_SHIFT #define MMIO_SPTE_GEN_HIGH_END 62 + +#define MMIO_SPTE_GEN_LOW_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \ + MMIO_SPTE_GEN_LOW_START) #define MMIO_SPTE_GEN_HIGH_MASK GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \ MMIO_SPTE_GEN_HIGH_START) +#define MMIO_SPTE_GEN_LOW_BITS (MMIO_SPTE_GEN_LOW_END - MMIO_SPTE_GEN_LOW_START + 1) +#define MMIO_SPTE_GEN_HIGH_BITS (MMIO_SPTE_GEN_HIGH_END - MMIO_SPTE_GEN_HIGH_START + 1) + +/* remember to adjust the comment above as well if you change these */ +static_assert(MMIO_SPTE_GEN_LOW_BITS == 9 && MMIO_SPTE_GEN_HIGH_BITS == 9); + +#define MMIO_SPTE_GEN_LOW_SHIFT (MMIO_SPTE_GEN_LOW_START - 0) +#define MMIO_SPTE_GEN_HIGH_SHIFT (MMIO_SPTE_GEN_HIGH_START - MMIO_SPTE_GEN_LOW_BITS) + +#define MMIO_SPTE_GEN_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0) + extern u64 __read_mostly shadow_nx_mask; extern u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */ extern u64 __read_mostly shadow_user_mask; @@ -228,8 +239,8 @@ static inline u64 get_mmio_spte_generation(u64 spte) { u64 gen; - gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START; - gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START; + gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_SHIFT; + gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_SHIFT; return gen; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 27e381c9da6c..84c8f06bec26 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -49,7 +49,14 @@ bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa) { struct kvm_mmu_page *sp; + if (!kvm->arch.tdp_mmu_enabled) + return false; + if (WARN_ON(!VALID_PAGE(hpa))) + return false; + sp = to_shadow_page(hpa); + if (WARN_ON(!sp)) + return false; return sp->tdp_mmu_page && sp->root_count; } @@ -59,7 +66,7 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root) { - gfn_t max_gfn = 1ULL << (boot_cpu_data.x86_phys_bits - PAGE_SHIFT); + gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); lockdep_assert_held(&kvm->mmu_lock); @@ -449,7 +456,7 @@ bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end) void kvm_tdp_mmu_zap_all(struct kvm *kvm) { - gfn_t max_gfn = 1ULL << (boot_cpu_data.x86_phys_bits - PAGE_SHIFT); + gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); bool flush; flush = kvm_tdp_mmu_zap_gfn_range(kvm, 0, max_gfn); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index c0b14106258a..566f4d18185b 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -642,8 +642,8 @@ static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, * Its safe to read more than we are asked, caller should ensure that * destination has enough space. */ - src_paddr = round_down(src_paddr, 16); offset = src_paddr & 15; + src_paddr = round_down(src_paddr, 16); sz = round_up(sz + offset, 16); return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2f32fd09e259..da7eb4aaf44f 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -530,12 +530,12 @@ static int svm_hardware_enable(void) static void svm_cpu_uninit(int cpu) { - struct svm_cpu_data *sd = per_cpu(svm_data, raw_smp_processor_id()); + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); if (!sd) return; - per_cpu(svm_data, raw_smp_processor_id()) = NULL; + per_cpu(svm_data, cpu) = NULL; kfree(sd->sev_vmcbs); __free_page(sd->save_area); kfree(sd); @@ -1309,8 +1309,10 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm->avic_is_running = true; svm->msrpm = svm_vcpu_alloc_msrpm(); - if (!svm->msrpm) + if (!svm->msrpm) { + err = -ENOMEM; goto error_free_vmcb_page; + } svm_vcpu_init_msrpm(vcpu, svm->msrpm); @@ -3741,6 +3743,7 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_cpuid_entry2 *best; vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && boot_cpu_has(X86_FEATURE_XSAVE) && @@ -3753,6 +3756,13 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) /* Check again if INVPCID interception if required */ svm_check_invpcid(svm); + /* For sev guests, the memory encryption bit is not reserved in CR3. */ + if (sev_guest(vcpu->kvm)) { + best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0); + if (best) + vcpu->arch.cr3_lm_rsvd_bits &= ~(1UL << (best->ebx & 0x3f)); + } + if (!kvm_vcpu_apicv_active(vcpu)) return; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 48b228bbcf16..45e285d3e6e9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -255,11 +255,10 @@ static struct kmem_cache *x86_emulator_cache; /* * When called, it means the previous get/set msr reached an invalid msr. - * Return 0 if we want to ignore/silent this failed msr access, or 1 if we want - * to fail the caller. + * Return true if we want to ignore/silent this failed msr access. */ -static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, - u64 data, bool write) +static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, + u64 data, bool write) { const char *op = write ? "wrmsr" : "rdmsr"; @@ -268,11 +267,11 @@ static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", op, msr, data); /* Mask the error */ - return 0; + return true; } else { kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n", op, msr, data); - return -ENOENT; + return false; } } @@ -1042,7 +1041,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) } if (is_long_mode(vcpu) && - (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63))) + (cr3 & vcpu->arch.cr3_lm_rsvd_bits)) return 1; else if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) @@ -1418,7 +1417,8 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) if (r == KVM_MSR_RET_INVALID) { /* Unconditionally clear the output for simplicity */ *data = 0; - r = kvm_msr_ignored_check(vcpu, index, 0, false); + if (kvm_msr_ignored_check(vcpu, index, 0, false)) + r = 0; } if (r) @@ -1542,7 +1542,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, struct msr_data msr; if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) - return -EPERM; + return KVM_MSR_RET_FILTERED; switch (index) { case MSR_FS_BASE: @@ -1583,7 +1583,8 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, int ret = __kvm_set_msr(vcpu, index, data, host_initiated); if (ret == KVM_MSR_RET_INVALID) - ret = kvm_msr_ignored_check(vcpu, index, data, true); + if (kvm_msr_ignored_check(vcpu, index, data, true)) + ret = 0; return ret; } @@ -1601,7 +1602,7 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, int ret; if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) - return -EPERM; + return KVM_MSR_RET_FILTERED; msr.index = index; msr.host_initiated = host_initiated; @@ -1620,7 +1621,8 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, if (ret == KVM_MSR_RET_INVALID) { /* Unconditionally clear *data for simplicity */ *data = 0; - ret = kvm_msr_ignored_check(vcpu, index, 0, false); + if (kvm_msr_ignored_check(vcpu, index, 0, false)) + ret = 0; } return ret; @@ -1664,9 +1666,9 @@ static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu) static u64 kvm_msr_reason(int r) { switch (r) { - case -ENOENT: + case KVM_MSR_RET_INVALID: return KVM_MSR_EXIT_REASON_UNKNOWN; - case -EPERM: + case KVM_MSR_RET_FILTERED: return KVM_MSR_EXIT_REASON_FILTER; default: return KVM_MSR_EXIT_REASON_INVAL; @@ -1967,7 +1969,7 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time, struct kvm_arch *ka = &vcpu->kvm->arch; if (vcpu->vcpu_id == 0 && !host_initiated) { - if (ka->boot_vcpu_runs_old_kvmclock && old_msr) + if (ka->boot_vcpu_runs_old_kvmclock != old_msr) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); ka->boot_vcpu_runs_old_kvmclock = old_msr; @@ -3065,9 +3067,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* Values other than LBR and BTF are vendor-specific, thus reserved and should throw a #GP */ return 1; - } - vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); + } else if (report_ignored_msrs) + vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", + __func__, data); break; case 0x200 ... 0x2ff: return kvm_mtrr_set_msr(vcpu, msr, data); @@ -3465,29 +3467,63 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.efer; break; case MSR_KVM_WALL_CLOCK: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) + return 1; + + msr_info->data = vcpu->kvm->arch.wall_clock; + break; case MSR_KVM_WALL_CLOCK_NEW: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) + return 1; + msr_info->data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_SYSTEM_TIME: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) + return 1; + + msr_info->data = vcpu->arch.time; + break; case MSR_KVM_SYSTEM_TIME_NEW: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) + return 1; + msr_info->data = vcpu->arch.time; break; case MSR_KVM_ASYNC_PF_EN: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + return 1; + msr_info->data = vcpu->arch.apf.msr_en_val; break; case MSR_KVM_ASYNC_PF_INT: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) + return 1; + msr_info->data = vcpu->arch.apf.msr_int_val; break; case MSR_KVM_ASYNC_PF_ACK: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + return 1; + msr_info->data = 0; break; case MSR_KVM_STEAL_TIME: + if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME)) + return 1; + msr_info->data = vcpu->arch.st.msr_val; break; case MSR_KVM_PV_EOI_EN: + if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI)) + return 1; + msr_info->data = vcpu->arch.pv_eoi.msr_val; break; case MSR_KVM_POLL_CONTROL: + if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL)) + return 1; + msr_info->data = vcpu->arch.msr_kvm_poll_control; break; case MSR_IA32_P5_MC_ADDR: @@ -4017,21 +4053,23 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) { + /* + * We can accept userspace's request for interrupt injection + * as long as we have a place to store the interrupt number. + * The actual injection will happen when the CPU is able to + * deliver the interrupt. + */ + if (kvm_cpu_has_extint(vcpu)) + return false; + + /* Acknowledging ExtINT does not happen if LINT0 is masked. */ return (!lapic_in_kernel(vcpu) || kvm_apic_accept_pic_intr(vcpu)); } -/* - * if userspace requested an interrupt window, check that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) { return kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && - !kvm_event_needs_reinjection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); } @@ -4577,6 +4615,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; + if (vcpu->arch.pv_cpuid.enforce) + kvm_update_pv_runtime(vcpu); return 0; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 3900ab0c6004..e7ca622a468f 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -376,7 +376,13 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva); bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type); -#define KVM_MSR_RET_INVALID 2 +/* + * Internal error codes that are used to indicate that MSR emulation encountered + * an error that should result in #GP in the guest, unless userspace + * handles it. + */ +#define KVM_MSR_RET_INVALID 2 /* in-kernel MSR emulation #GP condition */ +#define KVM_MSR_RET_FILTERED 3 /* #GP due to userspace MSR filter */ #define __cr4_reserved_bits(__cpu_has, __c) \ ({ \ diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 58f7fb95c7f4..4229950a5d78 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -63,13 +63,12 @@ static bool is_string_insn(struct insn *insn) */ bool insn_has_rep_prefix(struct insn *insn) { + insn_byte_t p; int i; insn_get_prefixes(insn); - for (i = 0; i < insn->prefixes.nbytes; i++) { - insn_byte_t p = insn->prefixes.bytes[i]; - + for_each_insn_prefix(insn, i, p) { if (p == 0xf2 || p == 0xf3) return true; } @@ -95,14 +94,15 @@ static int get_seg_reg_override_idx(struct insn *insn) { int idx = INAT_SEG_REG_DEFAULT; int num_overrides = 0, i; + insn_byte_t p; insn_get_prefixes(insn); /* Look for any segment override prefixes. */ - for (i = 0; i < insn->prefixes.nbytes; i++) { + for_each_insn_prefix(insn, i, p) { insn_attr_t attr; - attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]); + attr = inat_get_opcode_attribute(p); switch (attr) { case INAT_MAKE_PREFIX(INAT_PFX_CS): idx = INAT_SEG_REG_CS; diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index 733b983f3a89..6c5eb6f3f14f 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -45,8 +45,8 @@ #define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) #define PMD_FLAGS_DEC PMD_FLAGS_LARGE -#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ - (_PAGE_PAT | _PAGE_PWT)) +#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_LARGE_CACHE_MASK) | \ + (_PAGE_PAT_LARGE | _PAGE_PWT)) #define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC) diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 44148691d78b..5eb4dc2b97da 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -938,6 +938,7 @@ int phys_to_target_node(phys_addr_t start) return meminfo_to_nid(&numa_reserved_meminfo, start); } +EXPORT_SYMBOL_GPL(phys_to_target_node); int memory_add_physaddr_to_nid(u64 start) { @@ -947,4 +948,5 @@ int memory_add_physaddr_to_nid(u64 start) nid = numa_meminfo.blk[0].nid; return nid; } +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 11666ba19b62..569ac1d57f55 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -474,8 +474,14 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, /* * The membarrier system call requires a full memory barrier and * core serialization before returning to user-space, after - * storing to rq->curr. Writing to CR3 provides that full - * memory barrier and core serializing instruction. + * storing to rq->curr, when changing mm. This is because + * membarrier() sends IPIs to all CPUs that are in the target mm + * to make them issue memory barriers. However, if another CPU + * switches to/from the target mm concurrently with + * membarrier(), it can cause that CPU not to receive an IPI + * when it really should issue a memory barrier. Writing to CR3 + * provides that full memory barrier and core serializing + * instruction. */ if (real_prev == next) { VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 8f5759df7776..e1e8d4e3a213 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -78,28 +78,30 @@ int __init efi_alloc_page_tables(void) gfp_mask = GFP_KERNEL | __GFP_ZERO; efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER); if (!efi_pgd) - return -ENOMEM; + goto fail; pgd = efi_pgd + pgd_index(EFI_VA_END); p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END); - if (!p4d) { - free_page((unsigned long)efi_pgd); - return -ENOMEM; - } + if (!p4d) + goto free_pgd; pud = pud_alloc(&init_mm, p4d, EFI_VA_END); - if (!pud) { - if (pgtable_l5_enabled()) - free_page((unsigned long) pgd_page_vaddr(*pgd)); - free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); - return -ENOMEM; - } + if (!pud) + goto free_p4d; efi_mm.pgd = efi_pgd; mm_init_cpumask(&efi_mm); init_new_context(NULL, &efi_mm); return 0; + +free_p4d: + if (pgtable_l5_enabled()) + free_page((unsigned long)pgd_page_vaddr(*pgd)); +free_pgd: + free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); +fail: + return -ENOMEM; } /* diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 799f4eba0a62..043c73dfd2c9 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -93,10 +93,20 @@ void xen_init_lock_cpu(int cpu) void xen_uninit_lock_cpu(int cpu) { + int irq; + if (!xen_pvspin) return; - unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL); + /* + * When booting the kernel with 'mitigations=auto,nosmt', the secondary + * CPUs are not activated, and lock_kicker_irq is not initialized. + */ + irq = per_cpu(lock_kicker_irq, cpu); + if (irq == -1) + return; + + unbind_from_irqhandler(irq, NULL); per_cpu(lock_kicker_irq, cpu) = -1; kfree(per_cpu(irq_name, cpu)); per_cpu(irq_name, cpu) = NULL; diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index fa054a1772e1..4dc04e6c01d7 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -69,7 +69,7 @@ */ #define VMALLOC_START (XCHAL_KSEG_CACHED_VADDR - 0x10000000) #define VMALLOC_END (VMALLOC_START + 0x07FEFFFF) -#define TLBTEMP_BASE_1 (VMALLOC_END + 1) +#define TLBTEMP_BASE_1 (VMALLOC_START + 0x08000000) #define TLBTEMP_BASE_2 (TLBTEMP_BASE_1 + DCACHE_WAY_SIZE) #if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE #define TLBTEMP_SIZE (2 * DCACHE_WAY_SIZE) diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h index b9758119feca..5c9fb8005aa8 100644 --- a/arch/xtensa/include/asm/uaccess.h +++ b/arch/xtensa/include/asm/uaccess.h @@ -302,7 +302,7 @@ strncpy_from_user(char *dst, const char __user *src, long count) return -EFAULT; } #else -long strncpy_from_user(char *dst, const char *src, long count); +long strncpy_from_user(char *dst, const char __user *src, long count); #endif /* diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index 5835406b3cec..085b8c77b9d9 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -70,8 +70,10 @@ static inline void kmap_invalidate_coherent(struct page *page, kvaddr = TLBTEMP_BASE_1 + (page_to_phys(page) & DCACHE_ALIAS_MASK); + preempt_disable(); __invalidate_dcache_page_alias(kvaddr, page_to_phys(page)); + preempt_enable(); } } } @@ -156,6 +158,7 @@ void flush_dcache_page(struct page *page) if (!alias && !mapping) return; + preempt_disable(); virt = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(virt, phys); @@ -166,6 +169,7 @@ void flush_dcache_page(struct page *page) if (mapping) __invalidate_icache_page_alias(virt, phys); + preempt_enable(); } /* There shouldn't be an entry in the cache for this page anymore. */ @@ -199,8 +203,10 @@ void local_flush_cache_page(struct vm_area_struct *vma, unsigned long address, unsigned long phys = page_to_phys(pfn_to_page(pfn)); unsigned long virt = TLBTEMP_BASE_1 + (address & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(virt, phys); __invalidate_icache_page_alias(virt, phys); + preempt_enable(); } EXPORT_SYMBOL(local_flush_cache_page); @@ -227,11 +233,13 @@ update_mmu_cache(struct vm_area_struct * vma, unsigned long addr, pte_t *ptep) unsigned long phys = page_to_phys(page); unsigned long tmp; + preempt_disable(); tmp = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(tmp, phys); tmp = TLBTEMP_BASE_1 + (addr & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(tmp, phys); __invalidate_icache_page_alias(tmp, phys); + preempt_enable(); clear_bit(PG_arch_1, &page->flags); } @@ -265,7 +273,9 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(t, phys); + preempt_enable(); } /* Copy data */ @@ -280,9 +290,11 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_range((unsigned long) dst, len); if ((vma->vm_flags & VM_EXEC) != 0) __invalidate_icache_page_alias(t, phys); + preempt_enable(); } else if ((vma->vm_flags & VM_EXEC) != 0) { __flush_dcache_range((unsigned long)dst,len); @@ -304,7 +316,9 @@ extern void copy_from_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(t, phys); + preempt_enable(); } memcpy(dst, src, len); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c68bdf58c9a6..54fbe1e80cc4 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -849,6 +849,7 @@ static void blkcg_fill_root_iostats(void) blkg_iostat_set(&blkg->iostat.cur, &tmp); u64_stats_update_end(&blkg->iostat.sync); } + disk_put_part(part); } } diff --git a/block/blk-flush.c b/block/blk-flush.c index e32958f0b687..fd5cee9f1a3b 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -225,13 +225,18 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) /* release the tag's ownership to the req cloned from */ spin_lock_irqsave(&fq->mq_flush_lock, flags); - WRITE_ONCE(flush_rq->state, MQ_RQ_IDLE); if (!refcount_dec_and_test(&flush_rq->ref)) { fq->rq_status = error; spin_unlock_irqrestore(&fq->mq_flush_lock, flags); return; } + /* + * Flush request has to be marked as IDLE when it is really ended + * because its .end_io() is called from timeout code path too for + * avoiding use-after-free. + */ + WRITE_ONCE(flush_rq->state, MQ_RQ_IDLE); if (fq->rq_status != BLK_STS_OK) error = fq->rq_status; diff --git a/block/blk-merge.c b/block/blk-merge.c index bcf5e4580603..97b7c2821565 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -144,7 +144,7 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q, static inline unsigned get_max_io_size(struct request_queue *q, struct bio *bio) { - unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector); + unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector, 0); unsigned max_sectors = sectors; unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT; unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT; diff --git a/block/blk-settings.c b/block/blk-settings.c index 9741d1d83e98..659cdb8a07fe 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -547,7 +547,10 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->io_min = max(t->io_min, b->io_min); t->io_opt = lcm_not_zero(t->io_opt, b->io_opt); - t->chunk_sectors = lcm_not_zero(t->chunk_sectors, b->chunk_sectors); + + /* Set non-power-of-2 compatible chunk_sectors boundary */ + if (b->chunk_sectors) + t->chunk_sectors = gcd(t->chunk_sectors, b->chunk_sectors); /* Physical block size a multiple of the logical block size? */ if (t->physical_block_size & (t->logical_block_size - 1)) { diff --git a/block/genhd.c b/block/genhd.c index 0a273211fec2..9387f050c248 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -49,7 +49,7 @@ static void disk_release_events(struct gendisk *disk); * Set disk capacity and notify if the size is not currently * zero and will not be set to zero */ -void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, +bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, bool update_bdev) { sector_t capacity = get_capacity(disk); @@ -62,7 +62,10 @@ void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, char *envp[] = { "RESIZE=1", NULL }; kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); + return true; } + + return false; } EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify); diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c index 35abcb1ec051..86f8195d8039 100644 --- a/block/keyslot-manager.c +++ b/block/keyslot-manager.c @@ -103,6 +103,13 @@ int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots) spin_lock_init(&ksm->idle_slots_lock); slot_hashtable_size = roundup_pow_of_two(num_slots); + /* + * hash_ptr() assumes bits != 0, so ensure the hash table has at least 2 + * buckets. This only makes a difference when there is only 1 keyslot. + */ + if (slot_hashtable_size < 2) + slot_hashtable_size = 2; + ksm->log_slot_ht_size = ilog2(slot_hashtable_size); ksm->slot_hashtable = kvmalloc_array(slot_hashtable_size, sizeof(ksm->slot_hashtable[0]), diff --git a/drivers/Makefile b/drivers/Makefile index c0cd1b9075e3..576228037718 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -145,6 +145,7 @@ obj-$(CONFIG_OF) += of/ obj-$(CONFIG_SSB) += ssb/ obj-$(CONFIG_BCMA) += bcma/ obj-$(CONFIG_VHOST_RING) += vhost/ +obj-$(CONFIG_VHOST_IOTLB) += vhost/ obj-$(CONFIG_VHOST) += vhost/ obj-$(CONFIG_VLYNQ) += vlynq/ obj-$(CONFIG_GREYBUS) += greybus/ diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c index be79b2135fac..48019660a096 100644 --- a/drivers/accessibility/speakup/main.c +++ b/drivers/accessibility/speakup/main.c @@ -357,7 +357,6 @@ static void speakup_cut(struct vc_data *vc) mark_cut_flag = 0; synth_printf("%s\n", spk_msg_get(MSG_CUT)); - speakup_clear_selection(); ret = speakup_set_selection(tty); switch (ret) { diff --git a/drivers/accessibility/speakup/selection.c b/drivers/accessibility/speakup/selection.c index 032f3264fba1..7df7afad5ab4 100644 --- a/drivers/accessibility/speakup/selection.c +++ b/drivers/accessibility/speakup/selection.c @@ -22,13 +22,6 @@ struct speakup_selection_work { struct tty_struct *tty; }; -void speakup_clear_selection(void) -{ - console_lock(); - clear_selection(); - console_unlock(); -} - static void __speakup_set_selection(struct work_struct *work) { struct speakup_selection_work *ssw = @@ -51,6 +44,10 @@ static void __speakup_set_selection(struct work_struct *work) goto unref; } + console_lock(); + clear_selection(); + console_unlock(); + set_selection_kernel(&sel, tty); unref: diff --git a/drivers/accessibility/speakup/speakup.h b/drivers/accessibility/speakup/speakup.h index 74fe49c2c511..33594f5a7983 100644 --- a/drivers/accessibility/speakup/speakup.h +++ b/drivers/accessibility/speakup/speakup.h @@ -70,7 +70,6 @@ void spk_do_flush(void); void speakup_start_ttys(void); void synth_buffer_add(u16 ch); void synth_buffer_clear(void); -void speakup_clear_selection(void); int speakup_set_selection(struct tty_struct *tty); void speakup_cancel_selection(void); int speakup_paste_selection(struct tty_struct *tty); diff --git a/drivers/accessibility/speakup/spk_ttyio.c b/drivers/accessibility/speakup/spk_ttyio.c index a831ff64f8ba..6284aff434a1 100644 --- a/drivers/accessibility/speakup/spk_ttyio.c +++ b/drivers/accessibility/speakup/spk_ttyio.c @@ -47,9 +47,12 @@ static int spk_ttyio_ldisc_open(struct tty_struct *tty) { struct spk_ldisc_data *ldisc_data; + if (tty != speakup_tty) + /* Somebody tried to use this line discipline outside speakup */ + return -ENODEV; + if (!tty->ops->write) return -EOPNOTSUPP; - speakup_tty = tty; ldisc_data = kmalloc(sizeof(*ldisc_data), GFP_KERNEL); if (!ldisc_data) @@ -57,7 +60,7 @@ static int spk_ttyio_ldisc_open(struct tty_struct *tty) init_completion(&ldisc_data->completion); ldisc_data->buf_free = true; - speakup_tty->disc_data = ldisc_data; + tty->disc_data = ldisc_data; return 0; } @@ -181,9 +184,25 @@ static int spk_ttyio_initialise_ldisc(struct spk_synth *synth) tty_unlock(tty); + mutex_lock(&speakup_tty_mutex); + speakup_tty = tty; ret = tty_set_ldisc(tty, N_SPEAKUP); if (ret) - pr_err("speakup: Failed to set N_SPEAKUP on tty\n"); + speakup_tty = NULL; + mutex_unlock(&speakup_tty_mutex); + + if (!ret) + /* Success */ + return 0; + + pr_err("speakup: Failed to set N_SPEAKUP on tty\n"); + + tty_lock(tty); + if (tty->ops->close) + tty->ops->close(tty, NULL); + tty_unlock(tty); + + tty_kclose(tty); return ret; } @@ -298,11 +317,13 @@ static unsigned char ttyio_in(int timeout) struct spk_ldisc_data *ldisc_data = speakup_tty->disc_data; char rv; - if (wait_for_completion_timeout(&ldisc_data->completion, + if (!timeout) { + if (!try_wait_for_completion(&ldisc_data->completion)) + return 0xff; + } else if (wait_for_completion_timeout(&ldisc_data->completion, usecs_to_jiffies(timeout)) == 0) { - if (timeout) - pr_warn("spk_ttyio: timeout (%d) while waiting for input\n", - timeout); + pr_warn("spk_ttyio: timeout (%d) while waiting for input\n", + timeout); return 0xff; } diff --git a/drivers/accessibility/speakup/spk_types.h b/drivers/accessibility/speakup/spk_types.h index 7398f1196e10..91fca3033a45 100644 --- a/drivers/accessibility/speakup/spk_types.h +++ b/drivers/accessibility/speakup/spk_types.h @@ -32,6 +32,10 @@ enum { E_NEW_DEFAULT, }; +/* + * Note: add new members at the end, speakupmap.h depends on the values of the + * enum starting from SPELL_DELAY (see inc_dec_var) + */ enum var_id_t { VERSION = 0, SYNTH, SILENT, SYNTH_DIRECT, KEYMAP, CHARS, @@ -42,9 +46,9 @@ enum var_id_t { SAY_CONTROL, SAY_WORD_CTL, NO_INTERRUPT, KEY_ECHO, SPELL_DELAY, PUNC_LEVEL, READING_PUNC, ATTRIB_BLEEP, BLEEPS, - RATE, PITCH, INFLECTION, VOL, TONE, PUNCT, VOICE, FREQUENCY, LANG, + RATE, PITCH, VOL, TONE, PUNCT, VOICE, FREQUENCY, LANG, DIRECT, PAUSE, - CAPS_START, CAPS_STOP, CHARTAB, + CAPS_START, CAPS_STOP, CHARTAB, INFLECTION, MAXVARS }; diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index bc96457c9e25..a322a7bd286b 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -578,7 +578,7 @@ acpi_video_bqc_value_to_level(struct acpi_video_device *device, ACPI_VIDEO_FIRST_LEVEL - 1 - bqc_value; level = device->brightness->levels[bqc_value + - ACPI_VIDEO_FIRST_LEVEL]; + ACPI_VIDEO_FIRST_LEVEL]; } else { level = bqc_value; } @@ -990,8 +990,8 @@ set_level: goto out_free_levels; ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "found %d brightness levels\n", - br->count - ACPI_VIDEO_FIRST_LEVEL)); + "found %d brightness levels\n", + br->count - ACPI_VIDEO_FIRST_LEVEL)); return 0; out_free_levels: diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index 552fd9ffaca4..3294cc8dc073 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -633,6 +633,10 @@ int apei_map_generic_address(struct acpi_generic_address *reg) if (rc) return rc; + /* IO space doesn't need mapping */ + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) + return 0; + if (!acpi_os_map_generic_address(reg)) return -ENXIO; diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 9929ff50c0c0..770d84071a32 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -44,7 +44,7 @@ static DEFINE_SPINLOCK(iort_fwnode_lock); * iort_set_fwnode() - Create iort_fwnode and use it to register * iommu data in the iort_fwnode_list * - * @node: IORT table node associated with the IOMMU + * @iort_node: IORT table node associated with the IOMMU * @fwnode: fwnode associated with the IORT node * * Returns: 0 on success @@ -673,7 +673,8 @@ static int iort_dev_find_its_id(struct device *dev, u32 id, /** * iort_get_device_domain() - Find MSI domain related to a device * @dev: The device. - * @req_id: Requester ID for the device. + * @id: Requester ID for the device. + * @bus_token: irq domain bus token. * * Returns: the MSI domain for this device, NULL otherwise */ @@ -1136,7 +1137,7 @@ static int rc_dma_get_range(struct device *dev, u64 *size) * * @dev: device to configure * @dma_addr: device DMA address result pointer - * @size: DMA range size result pointer + * @dma_size: DMA range size result pointer */ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size) { @@ -1526,6 +1527,7 @@ static __init const struct iort_dev_config *iort_get_dev_cfg( /** * iort_add_platform_device() - Allocate a platform device for IORT node * @node: Pointer to device ACPI IORT node + * @ops: Pointer to IORT device config struct * * Returns: 0 on success, <0 failure */ diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index cab4af532f36..08ee1c7b12e0 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -987,7 +987,7 @@ static int acpi_battery_update(struct acpi_battery *battery, bool resume) */ if ((battery->state & ACPI_BATTERY_STATE_CRITICAL) || (test_bit(ACPI_BATTERY_ALARM_PRESENT, &battery->flags) && - (battery->capacity_now <= battery->alarm))) + (battery->capacity_now <= battery->alarm))) acpi_pm_wakeup_event(&battery->device->dev); return result; diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 0761529cac05..0d93a5ef4d07 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -89,7 +89,18 @@ static const struct dmi_system_id dmi_lid_quirks[] = { */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), - DMI_MATCH(DMI_PRODUCT_NAME, "E2215T MD60198"), + DMI_MATCH(DMI_PRODUCT_NAME, "E2215T"), + }, + .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, + }, + { + /* + * Medion Akoya E2228T, notification of the LID device only + * happens on close, not on open and _LID always returns closed. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), + DMI_MATCH(DMI_PRODUCT_NAME, "E2228T"), }, .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, }, diff --git a/drivers/acpi/dptf/dptf_pch_fivr.c b/drivers/acpi/dptf/dptf_pch_fivr.c index 4c1992fce150..5fca18296bf6 100644 --- a/drivers/acpi/dptf/dptf_pch_fivr.c +++ b/drivers/acpi/dptf/dptf_pch_fivr.c @@ -106,6 +106,7 @@ static int pch_fivr_remove(struct platform_device *pdev) static const struct acpi_device_id pch_fivr_device_ids[] = { {"INTC1045", 0}, + {"INTC1049", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, pch_fivr_device_ids); diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c index 06741305fc77..a24d5d7aa117 100644 --- a/drivers/acpi/dptf/dptf_power.c +++ b/drivers/acpi/dptf/dptf_power.c @@ -229,6 +229,8 @@ static const struct acpi_device_id int3407_device_ids[] = { {"INT3532", 0}, {"INTC1047", 0}, {"INTC1050", 0}, + {"INTC1060", 0}, + {"INTC1061", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, int3407_device_ids); diff --git a/drivers/acpi/dptf/int340x_thermal.c b/drivers/acpi/dptf/int340x_thermal.c index 8d420c7e7178..d14025a85ce8 100644 --- a/drivers/acpi/dptf/int340x_thermal.c +++ b/drivers/acpi/dptf/int340x_thermal.c @@ -25,10 +25,16 @@ static const struct acpi_device_id int340x_thermal_device_ids[] = { {"INT340A"}, {"INT340B"}, {"INTC1040"}, + {"INTC1041"}, {"INTC1043"}, {"INTC1044"}, {"INTC1045"}, + {"INTC1046"}, {"INTC1047"}, + {"INTC1048"}, + {"INTC1049"}, + {"INTC1060"}, + {"INTC1061"}, {""}, }; diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c index 170643927044..92e59f45329b 100644 --- a/drivers/acpi/event.c +++ b/drivers/acpi/event.c @@ -31,7 +31,7 @@ int acpi_notifier_call_chain(struct acpi_device *dev, u32 type, u32 data) event.type = type; event.data = data; return (blocking_notifier_call_chain(&acpi_chain_head, 0, (void *)&event) - == NOTIFY_BAD) ? -EINVAL : 0; + == NOTIFY_BAD) ? -EINVAL : 0; } EXPORT_SYMBOL(acpi_notifier_call_chain); diff --git a/drivers/acpi/evged.c b/drivers/acpi/evged.c index b1a7f8d6965e..fe6b6792c8bb 100644 --- a/drivers/acpi/evged.c +++ b/drivers/acpi/evged.c @@ -101,7 +101,7 @@ static acpi_status acpi_ged_request_interrupt(struct acpi_resource *ares, switch (gsi) { case 0 ... 255: - sprintf(ev_name, "_%c%02hhX", + sprintf(ev_name, "_%c%02X", trigger == ACPI_EDGE_SENSITIVE ? 'E' : 'L', gsi); if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle))) diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c index 62873388b24f..66c3983f0ccc 100644 --- a/drivers/acpi/fan.c +++ b/drivers/acpi/fan.c @@ -27,6 +27,7 @@ static const struct acpi_device_id fan_device_ids[] = { {"PNP0C0B", 0}, {"INT3404", 0}, {"INTC1044", 0}, + {"INTC1048", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, fan_device_ids); @@ -351,6 +352,7 @@ static int acpi_fan_get_fps(struct acpi_device *device) struct acpi_fan_fps *fps = &fan->fps[i]; snprintf(fps->name, ACPI_FPS_NAME_LEN, "state%d", i); + sysfs_attr_init(&fps->dev_attr.attr); fps->dev_attr.show = show_state; fps->dev_attr.store = NULL; fps->dev_attr.attr.name = fps->name; diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 43411a7457cd..e3638bafb941 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -134,7 +134,7 @@ int acpi_add_power_resource(acpi_handle handle); void acpi_power_add_remove_device(struct acpi_device *adev, bool add); int acpi_power_wakeup_list_init(struct list_head *list, int *system_level); int acpi_device_sleep_wake(struct acpi_device *dev, - int enable, int sleep_state, int dev_state); + int enable, int sleep_state, int dev_state); int acpi_power_get_inferred_state(struct acpi_device *device, int *state); int acpi_power_on_resources(struct acpi_device *device, int state); int acpi_power_transition(struct acpi_device *device, int state); diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 3a3c209ed3d3..442608220b5c 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2175,10 +2175,10 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) * these commands. */ enum nfit_aux_cmds { - NFIT_CMD_TRANSLATE_SPA = 5, - NFIT_CMD_ARS_INJECT_SET = 7, - NFIT_CMD_ARS_INJECT_CLEAR = 8, - NFIT_CMD_ARS_INJECT_GET = 9, + NFIT_CMD_TRANSLATE_SPA = 5, + NFIT_CMD_ARS_INJECT_SET = 7, + NFIT_CMD_ARS_INJECT_CLEAR = 8, + NFIT_CMD_ARS_INJECT_GET = 9, }; static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) @@ -2632,7 +2632,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, nfit_blk->bdw_offset = nfit_mem->bdw->offset; mmio = &nfit_blk->mmio[BDW]; mmio->addr.base = devm_nvdimm_memremap(dev, nfit_mem->spa_bdw->address, - nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr)); + nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr)); if (!mmio->addr.base) { dev_dbg(dev, "%s failed to map bdw\n", nvdimm_name(nvdimm)); diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index dea8a60e18a4..14ee631cb7cf 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -175,7 +175,7 @@ static int acpi_pci_irq_check_entry(acpi_handle handle, struct pci_dev *dev, * configure the IRQ assigned to this slot|dev|pin. The 'source_index' * indicates which resource descriptor in the resource template (of * the link device) this interrupt is allocated from. - * + * * NOTE: Don't query the Link Device for IRQ information at this time * because Link Device enumeration may not have occurred yet * (e.g. exists somewhere 'below' this _PRT entry in the ACPI diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index 606da5d77ad3..fb4c5632a232 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -6,8 +6,8 @@ * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> * Copyright (C) 2002 Dominik Brodowski <devel@brodo.de> * - * TBD: - * 1. Support more than one IRQ resource entry per link device (index). + * TBD: + * 1. Support more than one IRQ resource entry per link device (index). * 2. Implement start/stop mechanism and use ACPI Bus Driver facilities * for IRQ management (e.g. start()->_SRS). */ @@ -249,8 +249,8 @@ static int acpi_pci_link_get_current(struct acpi_pci_link *link) } } - /* - * Query and parse _CRS to get the current IRQ assignment. + /* + * Query and parse _CRS to get the current IRQ assignment. */ status = acpi_walk_resources(link->device->handle, METHOD_NAME__CRS, @@ -396,7 +396,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq) /* * "acpi_irq_balance" (default in APIC mode) enables ACPI to use PIC Interrupt * Link Devices to move the PIRQs around to minimize sharing. - * + * * "acpi_irq_nobalance" (default in PIC mode) tells ACPI not to move any PIC IRQs * that the BIOS has already set to active. This is necessary because * ACPI has no automatic means of knowing what ISA IRQs are used. Note that @@ -414,7 +414,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq) * * Note that PCI IRQ routers have a list of possible IRQs, * which may not include the IRQs this table says are available. - * + * * Since this heuristic can't tell the difference between a link * that no device will attach to, vs. a link which may be shared * by multiple active devices -- it is not optimal. diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c index 7ddd57abadd1..95f23acd5b80 100644 --- a/drivers/acpi/pci_mcfg.c +++ b/drivers/acpi/pci_mcfg.c @@ -173,7 +173,7 @@ static int pci_mcfg_quirk_matches(struct mcfg_fixup *f, u16 segment, { if (!memcmp(f->oem_id, mcfg_oem_id, ACPI_OEM_ID_SIZE) && !memcmp(f->oem_table_id, mcfg_oem_table_id, - ACPI_OEM_TABLE_ID_SIZE) && + ACPI_OEM_TABLE_ID_SIZE) && f->oem_revision == mcfg_oem_revision && f->segment == segment && resource_contains(&f->bus_range, bus_range)) diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 837b875d075e..8048da85b7e0 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -13,7 +13,7 @@ * 1. via "Device Specific (D-State) Control" * 2. via "Power Resource Control". * The code below deals with ACPI Power Resources control. - * + * * An ACPI "power resource object" represents a software controllable power * plane, clock plane, or other resource depended on by a device. * @@ -645,7 +645,7 @@ int acpi_power_wakeup_list_init(struct list_head *list, int *system_level_p) * -ENODEV if the execution of either _DSW or _PSW has failed */ int acpi_device_sleep_wake(struct acpi_device *dev, - int enable, int sleep_state, int dev_state) + int enable, int sleep_state, int dev_state) { union acpi_object in_arg[3]; struct acpi_object_list arg_list = { 3, in_arg }; @@ -690,7 +690,7 @@ int acpi_device_sleep_wake(struct acpi_device *dev, /* * Prepare a wakeup device, two steps (Ref ACPI 2.0:P229): - * 1. Power on the power resources required for the wakeup device + * 1. Power on the power resources required for the wakeup device * 2. Execute _DSW (Device Sleep Wake) or (deprecated in ACPI 3.0) _PSW (Power * State Wake) for the device, if present */ diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 5909e8fa4013..b04a68950ff1 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -354,7 +354,7 @@ static int acpi_processor_get_performance_states(struct acpi_processor *pr) (u32) px->control, (u32) px->status)); /* - * Check that ACPI's u64 MHz will be valid as u32 KHz in cpufreq + * Check that ACPI's u64 MHz will be valid as u32 KHz in cpufreq */ if (!px->core_frequency || ((u32)(px->core_frequency * 1000) != @@ -627,7 +627,7 @@ int acpi_processor_preregister_performance( goto err_ret; /* - * Now that we have _PSD data from all CPUs, lets setup P-state + * Now that we have _PSD data from all CPUs, lets setup P-state * domain info. */ for_each_possible_cpu(i) { @@ -693,7 +693,7 @@ int acpi_processor_preregister_performance( if (match_pdomain->domain != pdomain->domain) continue; - match_pr->performance->shared_type = + match_pr->performance->shared_type = pr->performance->shared_type; cpumask_copy(match_pr->performance->shared_cpu_map, pr->performance->shared_cpu_map); diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index f158b8c30113..e6d9f4de2800 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -366,7 +366,7 @@ static int acpi_battery_get_state(struct acpi_battery *battery) state_readers[i].mode, ACPI_SBS_BATTERY, state_readers[i].command, - (u8 *)battery + + (u8 *)battery + state_readers[i].offset); if (result) goto end; diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c index 87b74e9015e5..53c2862c4c75 100644 --- a/drivers/acpi/sbshc.c +++ b/drivers/acpi/sbshc.c @@ -176,7 +176,7 @@ int acpi_smbus_write(struct acpi_smb_hc *hc, u8 protocol, u8 address, EXPORT_SYMBOL_GPL(acpi_smbus_write); int acpi_smbus_register_callback(struct acpi_smb_hc *hc, - smbus_alarm_callback callback, void *context) + smbus_alarm_callback callback, void *context) { mutex_lock(&hc->lock); hc->callback = callback; diff --git a/drivers/acpi/sbshc.h b/drivers/acpi/sbshc.h index c3522bb82792..695c390e2884 100644 --- a/drivers/acpi/sbshc.h +++ b/drivers/acpi/sbshc.h @@ -24,9 +24,9 @@ enum acpi_sbs_device_addr { typedef void (*smbus_alarm_callback)(void *context); extern int acpi_smbus_read(struct acpi_smb_hc *hc, u8 protocol, u8 address, - u8 command, u8 * data); + u8 command, u8 *data); extern int acpi_smbus_write(struct acpi_smb_hc *hc, u8 protocol, u8 slave_address, - u8 command, u8 * data, u8 length); + u8 command, u8 *data, u8 length); extern int acpi_smbus_register_callback(struct acpi_smb_hc *hc, - smbus_alarm_callback callback, void *context); + smbus_alarm_callback callback, void *context); extern int acpi_smbus_unregister_callback(struct acpi_smb_hc *hc); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index a896e5e87c93..bc6a79e33220 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1453,7 +1453,7 @@ int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset, } /** - * acpi_dma_configure - Set-up DMA configuration for the device. + * acpi_dma_configure_id - Set-up DMA configuration for the device. * @dev: The pointer to the device * @attr: device dma attributes * @input_id: input device id const value pointer diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 3a032afd9d05..4f5463b2a217 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -178,14 +178,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201s"), }, }, - { - .callback = video_detect_force_video, - .ident = "ThinkPad X201T", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"), - }, - }, + { + .callback = video_detect_force_video, + .ident = "ThinkPad X201T", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"), + }, + }, /* The native backlight controls do not work on some older machines */ { diff --git a/drivers/acpi/wakeup.c b/drivers/acpi/wakeup.c index f89dd9a99e6e..b02bf770aead 100644 --- a/drivers/acpi/wakeup.c +++ b/drivers/acpi/wakeup.c @@ -44,7 +44,7 @@ void acpi_enable_wakeup_devices(u8 sleep_state) if (!dev->wakeup.flags.valid || sleep_state > (u32) dev->wakeup.sleep_state || !(device_may_wakeup(&dev->dev) - || dev->wakeup.prepare_count)) + || dev->wakeup.prepare_count)) continue; if (device_may_wakeup(&dev->dev)) @@ -69,7 +69,7 @@ void acpi_disable_wakeup_devices(u8 sleep_state) if (!dev->wakeup.flags.valid || sleep_state > (u32) dev->wakeup.sleep_state || !(device_may_wakeup(&dev->dev) - || dev->wakeup.prepare_count)) + || dev->wakeup.prepare_count)) continue; acpi_set_gpe_wake_mask(dev->wakeup.gpe_device, dev->wakeup.gpe_number, diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c index 7af74fb450a0..09ad73361879 100644 --- a/drivers/atm/nicstar.c +++ b/drivers/atm/nicstar.c @@ -1706,6 +1706,8 @@ static int ns_send(struct atm_vcc *vcc, struct sk_buff *skb) if (push_scqe(card, vc, scq, &scqe, skb) != 0) { atomic_inc(&vcc->stats->tx_err); + dma_unmap_single(&card->pcidev->dev, NS_PRV_DMA(skb), skb->len, + DMA_TO_DEVICE); dev_kfree_skb_any(skb); return -EIO; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index cb1191d6e945..a58084c2ed7c 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -255,7 +255,8 @@ static void loop_set_size(struct loop_device *lo, loff_t size) bd_set_nr_sectors(bdev, size); - set_capacity_revalidate_and_notify(lo->lo_disk, size, false); + if (!set_capacity_revalidate_and_notify(lo->lo_disk, size, false)) + kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); } static inline int diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index c4f9ccf5cc2a..aaae9220f3a0 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1518,6 +1518,7 @@ static void nbd_release(struct gendisk *disk, fmode_t mode) if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) && bdev->bd_openers == 0) nbd_disconnect_and_put(nbd); + bdput(bdev); nbd_config_put(nbd); nbd_put(nbd); diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 501e9dacfff9..9ebf53903d7b 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -132,73 +132,12 @@ module_param(log_stats, int, 0644); #define BLKBACK_INVALID_HANDLE (~0) -/* Number of free pages to remove on each call to gnttab_free_pages */ -#define NUM_BATCH_FREE_PAGES 10 - static inline bool persistent_gnt_timeout(struct persistent_gnt *persistent_gnt) { return pgrant_timeout && (jiffies - persistent_gnt->last_used >= HZ * pgrant_timeout); } -static inline int get_free_page(struct xen_blkif_ring *ring, struct page **page) -{ - unsigned long flags; - - spin_lock_irqsave(&ring->free_pages_lock, flags); - if (list_empty(&ring->free_pages)) { - BUG_ON(ring->free_pages_num != 0); - spin_unlock_irqrestore(&ring->free_pages_lock, flags); - return gnttab_alloc_pages(1, page); - } - BUG_ON(ring->free_pages_num == 0); - page[0] = list_first_entry(&ring->free_pages, struct page, lru); - list_del(&page[0]->lru); - ring->free_pages_num--; - spin_unlock_irqrestore(&ring->free_pages_lock, flags); - - return 0; -} - -static inline void put_free_pages(struct xen_blkif_ring *ring, struct page **page, - int num) -{ - unsigned long flags; - int i; - - spin_lock_irqsave(&ring->free_pages_lock, flags); - for (i = 0; i < num; i++) - list_add(&page[i]->lru, &ring->free_pages); - ring->free_pages_num += num; - spin_unlock_irqrestore(&ring->free_pages_lock, flags); -} - -static inline void shrink_free_pagepool(struct xen_blkif_ring *ring, int num) -{ - /* Remove requested pages in batches of NUM_BATCH_FREE_PAGES */ - struct page *page[NUM_BATCH_FREE_PAGES]; - unsigned int num_pages = 0; - unsigned long flags; - - spin_lock_irqsave(&ring->free_pages_lock, flags); - while (ring->free_pages_num > num) { - BUG_ON(list_empty(&ring->free_pages)); - page[num_pages] = list_first_entry(&ring->free_pages, - struct page, lru); - list_del(&page[num_pages]->lru); - ring->free_pages_num--; - if (++num_pages == NUM_BATCH_FREE_PAGES) { - spin_unlock_irqrestore(&ring->free_pages_lock, flags); - gnttab_free_pages(num_pages, page); - spin_lock_irqsave(&ring->free_pages_lock, flags); - num_pages = 0; - } - } - spin_unlock_irqrestore(&ring->free_pages_lock, flags); - if (num_pages != 0) - gnttab_free_pages(num_pages, page); -} - #define vaddr(page) ((unsigned long)pfn_to_kaddr(page_to_pfn(page))) static int do_block_io_op(struct xen_blkif_ring *ring, unsigned int *eoi_flags); @@ -331,7 +270,8 @@ static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *ro unmap_data.count = segs_to_unmap; BUG_ON(gnttab_unmap_refs_sync(&unmap_data)); - put_free_pages(ring, pages, segs_to_unmap); + gnttab_page_cache_put(&ring->free_pages, pages, + segs_to_unmap); segs_to_unmap = 0; } @@ -371,7 +311,8 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work) if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST) { unmap_data.count = segs_to_unmap; BUG_ON(gnttab_unmap_refs_sync(&unmap_data)); - put_free_pages(ring, pages, segs_to_unmap); + gnttab_page_cache_put(&ring->free_pages, pages, + segs_to_unmap); segs_to_unmap = 0; } kfree(persistent_gnt); @@ -379,7 +320,7 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work) if (segs_to_unmap > 0) { unmap_data.count = segs_to_unmap; BUG_ON(gnttab_unmap_refs_sync(&unmap_data)); - put_free_pages(ring, pages, segs_to_unmap); + gnttab_page_cache_put(&ring->free_pages, pages, segs_to_unmap); } } @@ -664,9 +605,10 @@ purge_gnt_list: /* Shrink the free pages pool if it is too large. */ if (time_before(jiffies, blkif->buffer_squeeze_end)) - shrink_free_pagepool(ring, 0); + gnttab_page_cache_shrink(&ring->free_pages, 0); else - shrink_free_pagepool(ring, max_buffer_pages); + gnttab_page_cache_shrink(&ring->free_pages, + max_buffer_pages); if (log_stats && time_after(jiffies, ring->st_print)) print_stats(ring); @@ -697,7 +639,7 @@ void xen_blkbk_free_caches(struct xen_blkif_ring *ring) ring->persistent_gnt_c = 0; /* Since we are shutting down remove all pages from the buffer */ - shrink_free_pagepool(ring, 0 /* All */); + gnttab_page_cache_shrink(&ring->free_pages, 0 /* All */); } static unsigned int xen_blkbk_unmap_prepare( @@ -736,7 +678,7 @@ static void xen_blkbk_unmap_and_respond_callback(int result, struct gntab_unmap_ but is this the best way to deal with this? */ BUG_ON(result); - put_free_pages(ring, data->pages, data->count); + gnttab_page_cache_put(&ring->free_pages, data->pages, data->count); make_response(ring, pending_req->id, pending_req->operation, pending_req->status); free_req(ring, pending_req); @@ -803,7 +745,8 @@ static void xen_blkbk_unmap(struct xen_blkif_ring *ring, if (invcount) { ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount); BUG_ON(ret); - put_free_pages(ring, unmap_pages, invcount); + gnttab_page_cache_put(&ring->free_pages, unmap_pages, + invcount); } pages += batch; num -= batch; @@ -850,7 +793,8 @@ again: pages[i]->page = persistent_gnt->page; pages[i]->persistent_gnt = persistent_gnt; } else { - if (get_free_page(ring, &pages[i]->page)) + if (gnttab_page_cache_get(&ring->free_pages, + &pages[i]->page)) goto out_of_memory; addr = vaddr(pages[i]->page); pages_to_gnt[segs_to_map] = pages[i]->page; @@ -883,7 +827,8 @@ again: BUG_ON(new_map_idx >= segs_to_map); if (unlikely(map[new_map_idx].status != 0)) { pr_debug("invalid buffer -- could not remap it\n"); - put_free_pages(ring, &pages[seg_idx]->page, 1); + gnttab_page_cache_put(&ring->free_pages, + &pages[seg_idx]->page, 1); pages[seg_idx]->handle = BLKBACK_INVALID_HANDLE; ret |= 1; goto next; @@ -944,7 +889,7 @@ next: out_of_memory: pr_alert("%s: out of memory\n", __func__); - put_free_pages(ring, pages_to_gnt, segs_to_map); + gnttab_page_cache_put(&ring->free_pages, pages_to_gnt, segs_to_map); for (i = last_map; i < num; i++) pages[i]->handle = BLKBACK_INVALID_HANDLE; return -ENOMEM; diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index c6ea5d38c509..a1b9df2c4ef1 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -288,9 +288,7 @@ struct xen_blkif_ring { struct work_struct persistent_purge_work; /* Buffer of free pages to map grant refs. */ - spinlock_t free_pages_lock; - int free_pages_num; - struct list_head free_pages; + struct gnttab_page_cache free_pages; struct work_struct free_work; /* Thread shutdown wait queue. */ diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index f5705569e2a7..76912c584a76 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -144,8 +144,7 @@ static int xen_blkif_alloc_rings(struct xen_blkif *blkif) INIT_LIST_HEAD(&ring->pending_free); INIT_LIST_HEAD(&ring->persistent_purge_list); INIT_WORK(&ring->persistent_purge_work, xen_blkbk_unmap_purged_grants); - spin_lock_init(&ring->free_pages_lock); - INIT_LIST_HEAD(&ring->free_pages); + gnttab_page_cache_init(&ring->free_pages); spin_lock_init(&ring->pending_free_lock); init_waitqueue_head(&ring->pending_free_wq); @@ -317,8 +316,7 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) BUG_ON(atomic_read(&ring->persistent_gnt_in_use) != 0); BUG_ON(!list_empty(&ring->persistent_purge_list)); BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts)); - BUG_ON(!list_empty(&ring->free_pages)); - BUG_ON(ring->free_pages_num != 0); + BUG_ON(ring->free_pages.num_pages != 0); BUG_ON(ring->persistent_gnt_c != 0); WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages)); ring->active = false; diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index efb088df1276..92ecf1a78ec7 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -227,6 +227,9 @@ static int sysc_wait_softreset(struct sysc *ddata) u32 sysc_mask, syss_done, rstval; int syss_offset, error = 0; + if (ddata->cap->regbits->srst_shift < 0) + return 0; + syss_offset = ddata->offsets[SYSC_SYSSTATUS]; sysc_mask = BIT(ddata->cap->regbits->srst_shift); @@ -970,9 +973,15 @@ static int sysc_enable_module(struct device *dev) return error; } } - error = sysc_wait_softreset(ddata); - if (error) - dev_warn(ddata->dev, "OCP softreset timed out\n"); + /* + * Some modules like i2c and hdq1w have unusable reset status unless + * the module reset quirk is enabled. Skip status check on enable. + */ + if (!(ddata->cfg.quirks & SYSC_MODULE_QUIRK_ENA_RESETDONE)) { + error = sysc_wait_softreset(ddata); + if (error) + dev_warn(ddata->dev, "OCP softreset timed out\n"); + } if (ddata->cfg.quirks & SYSC_QUIRK_OPT_CLKS_IN_RESET) sysc_disable_opt_clocks(ddata); @@ -1373,17 +1382,17 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK("hdmi", 0, 0, 0x10, -ENODEV, 0x50030200, 0xffffffff, SYSC_QUIRK_OPT_CLKS_NEEDED), SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x00000006, 0xffffffff, - SYSC_MODULE_QUIRK_HDQ1W), + SYSC_MODULE_QUIRK_HDQ1W | SYSC_MODULE_QUIRK_ENA_RESETDONE), SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x0000000a, 0xffffffff, - SYSC_MODULE_QUIRK_HDQ1W), + SYSC_MODULE_QUIRK_HDQ1W | SYSC_MODULE_QUIRK_ENA_RESETDONE), SYSC_QUIRK("i2c", 0, 0, 0x20, 0x10, 0x00000036, 0x000000ff, - SYSC_MODULE_QUIRK_I2C), + SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE), SYSC_QUIRK("i2c", 0, 0, 0x20, 0x10, 0x0000003c, 0x000000ff, - SYSC_MODULE_QUIRK_I2C), + SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE), SYSC_QUIRK("i2c", 0, 0, 0x20, 0x10, 0x00000040, 0x000000ff, - SYSC_MODULE_QUIRK_I2C), + SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE), SYSC_QUIRK("i2c", 0, 0, 0x10, 0x90, 0x5040000a, 0xfffff0f0, - SYSC_MODULE_QUIRK_I2C), + SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE), SYSC_QUIRK("gpu", 0x50000000, 0x14, -ENODEV, -ENODEV, 0x00010201, 0xffffffff, 0), SYSC_QUIRK("gpu", 0x50000000, 0xfe00, 0xfe10, -ENODEV, 0x40000000 , 0xffffffff, SYSC_MODULE_QUIRK_SGX), @@ -2880,7 +2889,7 @@ static int sysc_check_active_timer(struct sysc *ddata) if ((ddata->cfg.quirks & SYSC_QUIRK_NO_RESET_ON_INIT) && (ddata->cfg.quirks & SYSC_QUIRK_NO_IDLE)) - return -EBUSY; + return -ENXIO; return 0; } diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index a2da8f768b94..1836cc56e357 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -435,12 +435,12 @@ static struct port_buffer *alloc_buf(struct virtio_device *vdev, size_t buf_size /* * Allocate DMA memory from ancestor. When a virtio * device is created by remoteproc, the DMA memory is - * associated with the grandparent device: - * vdev => rproc => platform-dev. + * associated with the parent device: + * virtioY => remoteprocX#vdevYbuffer. */ - if (!vdev->dev.parent || !vdev->dev.parent->parent) + buf->dev = vdev->dev.parent; + if (!buf->dev) goto free_buf; - buf->dev = vdev->dev.parent->parent; /* Increase device refcnt to avoid freeing it */ get_device(buf->dev); diff --git a/drivers/clk/imx/Kconfig b/drivers/clk/imx/Kconfig index 3b393cb07295..3061896503f3 100644 --- a/drivers/clk/imx/Kconfig +++ b/drivers/clk/imx/Kconfig @@ -5,8 +5,8 @@ config MXC_CLK depends on ARCH_MXC || COMPILE_TEST config MXC_CLK_SCU - tristate "IMX SCU clock" - depends on ARCH_MXC || COMPILE_TEST + tristate + depends on ARCH_MXC depends on IMX_SCU && HAVE_ARM_SMCCC config CLK_IMX1 diff --git a/drivers/clk/imx/clk-imx8mm.c b/drivers/clk/imx/clk-imx8mm.c index 0de0be0cf548..f358ad907299 100644 --- a/drivers/clk/imx/clk-imx8mm.c +++ b/drivers/clk/imx/clk-imx8mm.c @@ -443,9 +443,9 @@ static int imx8mm_clocks_probe(struct platform_device *pdev) hws[IMX8MM_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mm_a53_core_sels, ARRAY_SIZE(imx8mm_a53_core_sels)); /* BUS */ - hws[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mm_main_axi_sels, base + 0x8800); + hws[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mm_main_axi_sels, base + 0x8800); hws[IMX8MM_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mm_enet_axi_sels, base + 0x8880); - hws[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900); + hws[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900); hws[IMX8MM_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mm_vpu_bus_sels, base + 0x8980); hws[IMX8MM_CLK_DISP_AXI] = imx8m_clk_hw_composite_bus("disp_axi", imx8mm_disp_axi_sels, base + 0x8a00); hws[IMX8MM_CLK_DISP_APB] = imx8m_clk_hw_composite_bus("disp_apb", imx8mm_disp_apb_sels, base + 0x8a80); @@ -453,11 +453,11 @@ static int imx8mm_clocks_probe(struct platform_device *pdev) hws[IMX8MM_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mm_usb_bus_sels, base + 0x8b80); hws[IMX8MM_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mm_gpu_axi_sels, base + 0x8c00); hws[IMX8MM_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mm_gpu_ahb_sels, base + 0x8c80); - hws[IMX8MM_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mm_noc_sels, base + 0x8d00); - hws[IMX8MM_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80); + hws[IMX8MM_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mm_noc_sels, base + 0x8d00); + hws[IMX8MM_CLK_NOC_APB] = imx8m_clk_hw_composite_bus_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80); /* AHB */ - hws[IMX8MM_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mm_ahb_sels, base + 0x9000); + hws[IMX8MM_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mm_ahb_sels, base + 0x9000); hws[IMX8MM_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mm_audio_ahb_sels, base + 0x9100); /* IPG */ diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c index e984de543f0b..f3c5e6cf55dd 100644 --- a/drivers/clk/imx/clk-imx8mn.c +++ b/drivers/clk/imx/clk-imx8mn.c @@ -431,7 +431,7 @@ static int imx8mn_clocks_probe(struct platform_device *pdev) hws[IMX8MN_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mn_a53_core_sels, ARRAY_SIZE(imx8mn_a53_core_sels)); /* BUS */ - hws[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800); + hws[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800); hws[IMX8MN_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mn_enet_axi_sels, base + 0x8880); hws[IMX8MN_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus("nand_usdhc_bus", imx8mn_nand_usdhc_sels, base + 0x8900); hws[IMX8MN_CLK_DISP_AXI] = imx8m_clk_hw_composite_bus("disp_axi", imx8mn_disp_axi_sels, base + 0x8a00); @@ -439,9 +439,9 @@ static int imx8mn_clocks_probe(struct platform_device *pdev) hws[IMX8MN_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mn_usb_bus_sels, base + 0x8b80); hws[IMX8MN_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mn_gpu_axi_sels, base + 0x8c00); hws[IMX8MN_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mn_gpu_ahb_sels, base + 0x8c80); - hws[IMX8MN_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mn_noc_sels, base + 0x8d00); + hws[IMX8MN_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mn_noc_sels, base + 0x8d00); - hws[IMX8MN_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mn_ahb_sels, base + 0x9000); + hws[IMX8MN_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mn_ahb_sels, base + 0x9000); hws[IMX8MN_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mn_audio_ahb_sels, base + 0x9100); hws[IMX8MN_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb", base + 0x9080, 0, 1); hws[IMX8MN_CLK_IPG_AUDIO_ROOT] = imx_clk_hw_divider2("ipg_audio_root", "audio_ahb", base + 0x9180, 0, 1); diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 12ce4770f702..48e212477f52 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -557,9 +557,9 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) /* CORE SEL */ hws[IMX8MP_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", ccm_base + 0x9880, 24, 1, imx8mp_a53_core_sels, ARRAY_SIZE(imx8mp_a53_core_sels)); - hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800); + hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800); hws[IMX8MP_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mp_enet_axi_sels, ccm_base + 0x8880); - hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900); + hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900); hws[IMX8MP_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mp_vpu_bus_sels, ccm_base + 0x8980); hws[IMX8MP_CLK_MEDIA_AXI] = imx8m_clk_hw_composite_bus("media_axi", imx8mp_media_axi_sels, ccm_base + 0x8a00); hws[IMX8MP_CLK_MEDIA_APB] = imx8m_clk_hw_composite_bus("media_apb", imx8mp_media_apb_sels, ccm_base + 0x8a80); @@ -567,12 +567,12 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) hws[IMX8MP_CLK_HDMI_AXI] = imx8m_clk_hw_composite_bus("hdmi_axi", imx8mp_media_axi_sels, ccm_base + 0x8b80); hws[IMX8MP_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mp_gpu_axi_sels, ccm_base + 0x8c00); hws[IMX8MP_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mp_gpu_ahb_sels, ccm_base + 0x8c80); - hws[IMX8MP_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mp_noc_sels, ccm_base + 0x8d00); - hws[IMX8MP_CLK_NOC_IO] = imx8m_clk_hw_composite_critical("noc_io", imx8mp_noc_io_sels, ccm_base + 0x8d80); + hws[IMX8MP_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mp_noc_sels, ccm_base + 0x8d00); + hws[IMX8MP_CLK_NOC_IO] = imx8m_clk_hw_composite_bus_critical("noc_io", imx8mp_noc_io_sels, ccm_base + 0x8d80); hws[IMX8MP_CLK_ML_AXI] = imx8m_clk_hw_composite_bus("ml_axi", imx8mp_ml_axi_sels, ccm_base + 0x8e00); hws[IMX8MP_CLK_ML_AHB] = imx8m_clk_hw_composite_bus("ml_ahb", imx8mp_ml_ahb_sels, ccm_base + 0x8e80); - hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000); + hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000); hws[IMX8MP_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mp_audio_ahb_sels, ccm_base + 0x9100); hws[IMX8MP_CLK_MIPI_DSI_ESC_RX] = imx8m_clk_hw_composite_bus("mipi_dsi_esc_rx", imx8mp_mipi_dsi_esc_rx_sels, ccm_base + 0x9200); diff --git a/drivers/clk/imx/clk-imx8mq.c b/drivers/clk/imx/clk-imx8mq.c index 8265d1d48af4..06292d4a98ff 100644 --- a/drivers/clk/imx/clk-imx8mq.c +++ b/drivers/clk/imx/clk-imx8mq.c @@ -431,7 +431,7 @@ static int imx8mq_clocks_probe(struct platform_device *pdev) hws[IMX8MQ_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mq_a53_core_sels, ARRAY_SIZE(imx8mq_a53_core_sels)); /* BUS */ - hws[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800); + hws[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800); hws[IMX8MQ_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mq_enet_axi_sels, base + 0x8880); hws[IMX8MQ_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus("nand_usdhc_bus", imx8mq_nand_usdhc_sels, base + 0x8900); hws[IMX8MQ_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mq_vpu_bus_sels, base + 0x8980); @@ -441,12 +441,12 @@ static int imx8mq_clocks_probe(struct platform_device *pdev) hws[IMX8MQ_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mq_usb_bus_sels, base + 0x8b80); hws[IMX8MQ_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mq_gpu_axi_sels, base + 0x8c00); hws[IMX8MQ_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mq_gpu_ahb_sels, base + 0x8c80); - hws[IMX8MQ_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mq_noc_sels, base + 0x8d00); - hws[IMX8MQ_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80); + hws[IMX8MQ_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mq_noc_sels, base + 0x8d00); + hws[IMX8MQ_CLK_NOC_APB] = imx8m_clk_hw_composite_bus_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80); /* AHB */ /* AHB clock is used by the AHB bus therefore marked as critical */ - hws[IMX8MQ_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mq_ahb_sels, base + 0x9000); + hws[IMX8MQ_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mq_ahb_sels, base + 0x9000); hws[IMX8MQ_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mq_audio_ahb_sels, base + 0x9100); /* IPG */ diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h index 3b796b3da249..1d7be0c86538 100644 --- a/drivers/clk/imx/clk.h +++ b/drivers/clk/imx/clk.h @@ -549,6 +549,11 @@ struct clk_hw *imx8m_clk_hw_composite_flags(const char *name, IMX_COMPOSITE_BUS, \ CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE) +#define imx8m_clk_hw_composite_bus_critical(name, parent_names, reg) \ + imx8m_clk_hw_composite_flags(name, parent_names, ARRAY_SIZE(parent_names), reg, \ + IMX_COMPOSITE_BUS, \ + CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE | CLK_IS_CRITICAL) + #define imx8m_clk_hw_composite_core(name, parent_names, reg) \ imx8m_clk_hw_composite_flags(name, parent_names, \ ARRAY_SIZE(parent_names), reg, \ diff --git a/drivers/clk/meson/clk-regmap.h b/drivers/clk/meson/clk-regmap.h index c4a39604cffd..e365312da54e 100644 --- a/drivers/clk/meson/clk-regmap.h +++ b/drivers/clk/meson/clk-regmap.h @@ -26,7 +26,10 @@ struct clk_regmap { void *data; }; -#define to_clk_regmap(_hw) container_of(_hw, struct clk_regmap, hw) +static inline struct clk_regmap *to_clk_regmap(struct clk_hw *hw) +{ + return container_of(hw, struct clk_regmap, hw); +} /** * struct clk_regmap_gate_data - regmap backed gate specific data diff --git a/drivers/clk/qcom/clk-regmap.h b/drivers/clk/qcom/clk-regmap.h index 6cfc1bccb255..14ec659a3a77 100644 --- a/drivers/clk/qcom/clk-regmap.h +++ b/drivers/clk/qcom/clk-regmap.h @@ -24,7 +24,11 @@ struct clk_regmap { unsigned int enable_mask; bool enable_is_inverted; }; -#define to_clk_regmap(_hw) container_of(_hw, struct clk_regmap, hw) + +static inline struct clk_regmap *to_clk_regmap(struct clk_hw *hw) +{ + return container_of(hw, struct clk_regmap, hw); +} int clk_is_enabled_regmap(struct clk_hw *hw); int clk_enable_regmap(struct clk_hw *hw); diff --git a/drivers/clk/renesas/r9a06g032-clocks.c b/drivers/clk/renesas/r9a06g032-clocks.c index d900f6bf53d0..892e91b92f2c 100644 --- a/drivers/clk/renesas/r9a06g032-clocks.c +++ b/drivers/clk/renesas/r9a06g032-clocks.c @@ -55,7 +55,7 @@ struct r9a06g032_clkdesc { u16 sel, g1, r1, g2, r2; } dual; }; -} __packed; +}; #define I_GATE(_clk, _rst, _rdy, _midle, _scon, _mirack, _mistat) \ { .gate = _clk, .reset = _rst, \ diff --git a/drivers/counter/ti-eqep.c b/drivers/counter/ti-eqep.c index e27771df8e23..a60aee1a1a29 100644 --- a/drivers/counter/ti-eqep.c +++ b/drivers/counter/ti-eqep.c @@ -368,7 +368,7 @@ static const struct regmap_config ti_eqep_regmap32_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, - .max_register = 0x24, + .max_register = QUPRD, }; static const struct regmap_config ti_eqep_regmap16_config = { @@ -376,7 +376,7 @@ static const struct regmap_config ti_eqep_regmap16_config = { .reg_bits = 16, .val_bits = 16, .reg_stride = 2, - .max_register = 0x1e, + .max_register = QCPRDLAT, }; static int ti_eqep_probe(struct platform_device *pdev) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 336b5e94cbc8..1e7e3f2ff09f 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2254,7 +2254,7 @@ static int cpufreq_init_governor(struct cpufreq_policy *policy) return -EINVAL; /* Platform doesn't want dynamic frequency switching ? */ - if (policy->governor->dynamic_switching && + if (policy->governor->flags & CPUFREQ_GOV_DYNAMIC_SWITCHING && cpufreq_driver->flags & CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING) { struct cpufreq_governor *gov = cpufreq_fallback_governor(); @@ -2280,6 +2280,8 @@ static int cpufreq_init_governor(struct cpufreq_policy *policy) } } + policy->strict_target = !!(policy->governor->flags & CPUFREQ_GOV_STRICT_TARGET); + return 0; } diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h index c56773c25757..bab8e6140377 100644 --- a/drivers/cpufreq/cpufreq_governor.h +++ b/drivers/cpufreq/cpufreq_governor.h @@ -156,7 +156,7 @@ void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy); #define CPUFREQ_DBS_GOVERNOR_INITIALIZER(_name_) \ { \ .name = _name_, \ - .dynamic_switching = true, \ + .flags = CPUFREQ_GOV_DYNAMIC_SWITCHING, \ .owner = THIS_MODULE, \ .init = cpufreq_dbs_governor_init, \ .exit = cpufreq_dbs_governor_exit, \ diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c index 71c1d9aba772..addd93f2a420 100644 --- a/drivers/cpufreq/cpufreq_performance.c +++ b/drivers/cpufreq/cpufreq_performance.c @@ -20,6 +20,7 @@ static void cpufreq_gov_performance_limits(struct cpufreq_policy *policy) static struct cpufreq_governor cpufreq_gov_performance = { .name = "performance", .owner = THIS_MODULE, + .flags = CPUFREQ_GOV_STRICT_TARGET, .limits = cpufreq_gov_performance_limits, }; diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c index 7749522355b5..8d830d860e91 100644 --- a/drivers/cpufreq/cpufreq_powersave.c +++ b/drivers/cpufreq/cpufreq_powersave.c @@ -21,6 +21,7 @@ static struct cpufreq_governor cpufreq_gov_powersave = { .name = "powersave", .limits = cpufreq_gov_powersave_limits, .owner = THIS_MODULE, + .flags = CPUFREQ_GOV_STRICT_TARGET, }; MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>"); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b7a9779250aa..36a3ccfe6d3d 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2527,7 +2527,7 @@ static void intel_cpufreq_trace(struct cpudata *cpu, unsigned int trace_type, in } static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate, - bool fast_switch) + bool strict, bool fast_switch) { u64 prev = READ_ONCE(cpu->hwp_req_cached), value = prev; @@ -2539,7 +2539,7 @@ static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate, * field in it, so opportunistically update the max too if needed. */ value &= ~HWP_MAX_PERF(~0L); - value |= HWP_MAX_PERF(cpu->max_perf_ratio); + value |= HWP_MAX_PERF(strict ? target_pstate : cpu->max_perf_ratio); if (value == prev) return; @@ -2562,14 +2562,16 @@ static void intel_cpufreq_adjust_perf_ctl(struct cpudata *cpu, pstate_funcs.get_val(cpu, target_pstate)); } -static int intel_cpufreq_update_pstate(struct cpudata *cpu, int target_pstate, - bool fast_switch) +static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy, + int target_pstate, bool fast_switch) { + struct cpudata *cpu = all_cpu_data[policy->cpu]; int old_pstate = cpu->pstate.current_pstate; target_pstate = intel_pstate_prepare_request(cpu, target_pstate); if (hwp_active) { - intel_cpufreq_adjust_hwp(cpu, target_pstate, fast_switch); + intel_cpufreq_adjust_hwp(cpu, target_pstate, + policy->strict_target, fast_switch); cpu->pstate.current_pstate = target_pstate; } else if (target_pstate != old_pstate) { intel_cpufreq_adjust_perf_ctl(cpu, target_pstate, fast_switch); @@ -2609,7 +2611,7 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy, break; } - target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, false); + target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, false); freqs.new = target_pstate * cpu->pstate.scaling; @@ -2628,7 +2630,7 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy, target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling); - target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, true); + target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true); return target_pstate * cpu->pstate.scaling; } diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index e855e8612a67..8286205c7165 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -8,6 +8,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/clk-provider.h> #include <linux/cpu.h> #include <linux/cpufreq.h> #include <linux/cpumask.h> @@ -228,15 +229,22 @@ static struct cpufreq_driver scmi_cpufreq_driver = { static int scmi_cpufreq_probe(struct scmi_device *sdev) { int ret; + struct device *dev = &sdev->dev; handle = sdev->handle; if (!handle || !handle->perf_ops) return -ENODEV; +#ifdef CONFIG_COMMON_CLK + /* dummy clock provider as needed by OPP if clocks property is used */ + if (of_find_property(dev->of_node, "#clock-cells", NULL)) + devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL); +#endif + ret = cpufreq_register_driver(&scmi_cpufreq_driver); if (ret) { - dev_err(&sdev->dev, "%s: registering cpufreq failed, err: %d\n", + dev_err(dev, "%s: registering cpufreq failed, err: %d\n", __func__, ret); } diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index 4b4079f51559..7eb2c56c65de 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -42,6 +42,8 @@ static const struct tegra186_cpufreq_cluster_info tegra186_clusters[] = { struct tegra186_cpufreq_cluster { const struct tegra186_cpufreq_cluster_info *info; struct cpufreq_frequency_table *table; + u32 ref_clk_khz; + u32 div; }; struct tegra186_cpufreq_data { @@ -94,7 +96,7 @@ static int tegra186_cpufreq_set_target(struct cpufreq_policy *policy, static unsigned int tegra186_cpufreq_get(unsigned int cpu) { - struct cpufreq_frequency_table *tbl; + struct tegra186_cpufreq_data *data = cpufreq_get_driver_data(); struct cpufreq_policy *policy; void __iomem *edvd_reg; unsigned int i, freq = 0; @@ -104,17 +106,23 @@ static unsigned int tegra186_cpufreq_get(unsigned int cpu) if (!policy) return 0; - tbl = policy->freq_table; edvd_reg = policy->driver_data; ndiv = readl(edvd_reg) & EDVD_CORE_VOLT_FREQ_F_MASK; - for (i = 0; tbl[i].frequency != CPUFREQ_TABLE_END; i++) { - if ((tbl[i].driver_data & EDVD_CORE_VOLT_FREQ_F_MASK) == ndiv) { - freq = tbl[i].frequency; - break; + for (i = 0; i < data->num_clusters; i++) { + struct tegra186_cpufreq_cluster *cluster = &data->clusters[i]; + int core; + + for (core = 0; core < ARRAY_SIZE(cluster->info->cpus); core++) { + if (cluster->info->cpus[core] != policy->cpu) + continue; + + freq = (cluster->ref_clk_khz * ndiv) / cluster->div; + goto out; } } +out: cpufreq_cpu_put(policy); return freq; @@ -133,7 +141,7 @@ static struct cpufreq_driver tegra186_cpufreq_driver = { static struct cpufreq_frequency_table *init_vhint_table( struct platform_device *pdev, struct tegra_bpmp *bpmp, - unsigned int cluster_id) + struct tegra186_cpufreq_cluster *cluster) { struct cpufreq_frequency_table *table; struct mrq_cpu_vhint_request req; @@ -152,7 +160,7 @@ static struct cpufreq_frequency_table *init_vhint_table( memset(&req, 0, sizeof(req)); req.addr = phys; - req.cluster_id = cluster_id; + req.cluster_id = cluster->info->bpmp_cluster_id; memset(&msg, 0, sizeof(msg)); msg.mrq = MRQ_CPU_VHINT; @@ -185,6 +193,9 @@ static struct cpufreq_frequency_table *init_vhint_table( goto free; } + cluster->ref_clk_khz = data->ref_clk_hz / 1000; + cluster->div = data->pdiv * data->mdiv; + for (i = data->vfloor, j = 0; i <= data->vceil; i++) { struct cpufreq_frequency_table *point; u16 ndiv = data->ndiv[i]; @@ -202,8 +213,7 @@ static struct cpufreq_frequency_table *init_vhint_table( point = &table[j++]; point->driver_data = edvd_val; - point->frequency = data->ref_clk_hz * ndiv / data->pdiv / - data->mdiv / 1000; + point->frequency = (cluster->ref_clk_khz * ndiv) / cluster->div; } table[j].frequency = CPUFREQ_TABLE_END; @@ -245,8 +255,7 @@ static int tegra186_cpufreq_probe(struct platform_device *pdev) struct tegra186_cpufreq_cluster *cluster = &data->clusters[i]; cluster->info = &tegra186_clusters[i]; - cluster->table = init_vhint_table( - pdev, bpmp, cluster->info->bpmp_cluster_id); + cluster->table = init_vhint_table(pdev, bpmp, cluster); if (IS_ERR(cluster->table)) { err = PTR_ERR(cluster->table); goto put_bpmp; diff --git a/drivers/cpuidle/cpuidle-tegra.c b/drivers/cpuidle/cpuidle-tegra.c index e8956706a291..191966dc8d02 100644 --- a/drivers/cpuidle/cpuidle-tegra.c +++ b/drivers/cpuidle/cpuidle-tegra.c @@ -189,7 +189,7 @@ static int tegra_cpuidle_state_enter(struct cpuidle_device *dev, } local_fiq_disable(); - tegra_pm_set_cpu_in_lp2(); + RCU_NONIDLE(tegra_pm_set_cpu_in_lp2()); cpu_pm_enter(); switch (index) { @@ -207,7 +207,7 @@ static int tegra_cpuidle_state_enter(struct cpuidle_device *dev, } cpu_pm_exit(); - tegra_pm_clear_cpu_in_lp2(); + RCU_NONIDLE(tegra_pm_clear_cpu_in_lp2()); local_fiq_enable(); return err ?: index; diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig index 567428e10b7b..d2834c2cfa10 100644 --- a/drivers/dax/Kconfig +++ b/drivers/dax/Kconfig @@ -50,7 +50,6 @@ config DEV_DAX_HMEM Say M if unsure. config DEV_DAX_HMEM_DEVICES - depends on NUMA_KEEP_MEMINFO # for phys_to_target_node() depends on DEV_DAX_HMEM && DAX=y def_bool y diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 7974fa0400d8..962cbb5e5f7f 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -1039,16 +1039,15 @@ static int get_dma_id(struct dma_device *device) static int __dma_async_device_channel_register(struct dma_device *device, struct dma_chan *chan) { - int rc = 0; + int rc; chan->local = alloc_percpu(typeof(*chan->local)); if (!chan->local) - goto err_out; + return -ENOMEM; chan->dev = kzalloc(sizeof(*chan->dev), GFP_KERNEL); if (!chan->dev) { - free_percpu(chan->local); - chan->local = NULL; - goto err_out; + rc = -ENOMEM; + goto err_free_local; } /* @@ -1061,7 +1060,8 @@ static int __dma_async_device_channel_register(struct dma_device *device, if (chan->chan_id < 0) { pr_err("%s: unable to alloc ida for chan: %d\n", __func__, chan->chan_id); - goto err_out; + rc = chan->chan_id; + goto err_free_dev; } chan->dev->device.class = &dma_devclass; @@ -1082,9 +1082,10 @@ static int __dma_async_device_channel_register(struct dma_device *device, mutex_lock(&device->chan_mutex); ida_free(&device->chan_ida, chan->chan_id); mutex_unlock(&device->chan_mutex); - err_out: - free_percpu(chan->local); + err_free_dev: kfree(chan->dev); + err_free_local: + free_percpu(chan->local); return rc; } diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 200b9109cacf..663344987e3f 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -271,7 +271,7 @@ int idxd_wq_map_portal(struct idxd_wq *wq) resource_size_t start; start = pci_resource_start(pdev, IDXD_WQ_BAR); - start = start + wq->id * IDXD_PORTAL_SIZE; + start += idxd_get_wq_portal_full_offset(wq->id, IDXD_PORTAL_LIMITED); wq->dportal = devm_ioremap(dev, start, IDXD_PORTAL_SIZE); if (!wq->dportal) @@ -295,7 +295,7 @@ void idxd_wq_disable_cleanup(struct idxd_wq *wq) int i, wq_offset; lockdep_assert_held(&idxd->dev_lock); - memset(&wq->wqcfg, 0, sizeof(wq->wqcfg)); + memset(wq->wqcfg, 0, idxd->wqcfg_size); wq->type = IDXD_WQT_NONE; wq->size = 0; wq->group = NULL; @@ -304,8 +304,8 @@ void idxd_wq_disable_cleanup(struct idxd_wq *wq) clear_bit(WQ_FLAG_DEDICATED, &wq->flags); memset(wq->name, 0, WQ_NAME_SIZE); - for (i = 0; i < 8; i++) { - wq_offset = idxd->wqcfg_offset + wq->id * 32 + i * sizeof(u32); + for (i = 0; i < WQCFG_STRIDES(idxd); i++) { + wq_offset = WQCFG_OFFSET(idxd, wq->id, i); iowrite32(0, idxd->reg_base + wq_offset); dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n", wq->id, i, wq_offset, @@ -539,10 +539,10 @@ static int idxd_wq_config_write(struct idxd_wq *wq) if (!wq->group) return 0; - memset(&wq->wqcfg, 0, sizeof(union wqcfg)); + memset(wq->wqcfg, 0, idxd->wqcfg_size); /* byte 0-3 */ - wq->wqcfg.wq_size = wq->size; + wq->wqcfg->wq_size = wq->size; if (wq->size == 0) { dev_warn(dev, "Incorrect work queue size: 0\n"); @@ -550,22 +550,21 @@ static int idxd_wq_config_write(struct idxd_wq *wq) } /* bytes 4-7 */ - wq->wqcfg.wq_thresh = wq->threshold; + wq->wqcfg->wq_thresh = wq->threshold; /* byte 8-11 */ - wq->wqcfg.priv = !!(wq->type == IDXD_WQT_KERNEL); - wq->wqcfg.mode = 1; - - wq->wqcfg.priority = wq->priority; + wq->wqcfg->priv = !!(wq->type == IDXD_WQT_KERNEL); + wq->wqcfg->mode = 1; + wq->wqcfg->priority = wq->priority; /* bytes 12-15 */ - wq->wqcfg.max_xfer_shift = ilog2(wq->max_xfer_bytes); - wq->wqcfg.max_batch_shift = ilog2(wq->max_batch_size); + wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes); + wq->wqcfg->max_batch_shift = ilog2(wq->max_batch_size); dev_dbg(dev, "WQ %d CFGs\n", wq->id); - for (i = 0; i < 8; i++) { - wq_offset = idxd->wqcfg_offset + wq->id * 32 + i * sizeof(u32); - iowrite32(wq->wqcfg.bits[i], idxd->reg_base + wq_offset); + for (i = 0; i < WQCFG_STRIDES(idxd); i++) { + wq_offset = WQCFG_OFFSET(idxd, wq->id, i); + iowrite32(wq->wqcfg->bits[i], idxd->reg_base + wq_offset); dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n", wq->id, i, wq_offset, ioread32(idxd->reg_base + wq_offset)); diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index c64df197e724..d48f193daacc 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -103,7 +103,7 @@ struct idxd_wq { u32 priority; enum idxd_wq_state state; unsigned long flags; - union wqcfg wqcfg; + union wqcfg *wqcfg; u32 vec_ptr; /* interrupt steering */ struct dsa_hw_desc **hw_descs; int num_descs; @@ -183,6 +183,7 @@ struct idxd_device { int max_wq_size; int token_limit; int nr_tokens; /* non-reserved tokens */ + unsigned int wqcfg_size; union sw_err_reg sw_err; wait_queue_head_t cmd_waitq; diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 11e5ce168177..0a4432b063b5 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -178,6 +178,9 @@ static int idxd_setup_internals(struct idxd_device *idxd) wq->idxd_cdev.minor = -1; wq->max_xfer_bytes = idxd->max_xfer_bytes; wq->max_batch_size = idxd->max_batch_size; + wq->wqcfg = devm_kzalloc(dev, idxd->wqcfg_size, GFP_KERNEL); + if (!wq->wqcfg) + return -ENOMEM; } for (i = 0; i < idxd->max_engines; i++) { @@ -251,6 +254,8 @@ static void idxd_read_caps(struct idxd_device *idxd) dev_dbg(dev, "total workqueue size: %u\n", idxd->max_wq_size); idxd->max_wqs = idxd->hw.wq_cap.num_wqs; dev_dbg(dev, "max workqueues: %u\n", idxd->max_wqs); + idxd->wqcfg_size = 1 << (idxd->hw.wq_cap.wqcfg_size + IDXD_WQCFG_MIN); + dev_dbg(dev, "wqcfg size: %u\n", idxd->wqcfg_size); /* reading operation capabilities */ for (i = 0; i < 4; i++) { diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index a39e7ae6b3d9..54390334c243 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -8,7 +8,7 @@ #define IDXD_MMIO_BAR 0 #define IDXD_WQ_BAR 2 -#define IDXD_PORTAL_SIZE 0x4000 +#define IDXD_PORTAL_SIZE PAGE_SIZE /* MMIO Device BAR0 Registers */ #define IDXD_VER_OFFSET 0x00 @@ -43,7 +43,8 @@ union wq_cap_reg { struct { u64 total_wq_size:16; u64 num_wqs:8; - u64 rsvd:24; + u64 wqcfg_size:4; + u64 rsvd:20; u64 shared_mode:1; u64 dedicated_mode:1; u64 rsvd2:1; @@ -55,6 +56,7 @@ union wq_cap_reg { u64 bits; } __packed; #define IDXD_WQCAP_OFFSET 0x20 +#define IDXD_WQCFG_MIN 5 union group_cap_reg { struct { @@ -333,4 +335,23 @@ union wqcfg { }; u32 bits[8]; } __packed; + +/* + * This macro calculates the offset into the WQCFG register + * idxd - struct idxd * + * n - wq id + * ofs - the index of the 32b dword for the config register + * + * The WQCFG register block is divided into groups per each wq. The n index + * allows us to move to the register group that's for that particular wq. + * Each register is 32bits. The ofs gives us the number of register to access. + */ +#define WQCFG_OFFSET(_idxd_dev, n, ofs) \ +({\ + typeof(_idxd_dev) __idxd_dev = (_idxd_dev); \ + (__idxd_dev)->wqcfg_offset + (n) * (__idxd_dev)->wqcfg_size + sizeof(u32) * (ofs); \ +}) + +#define WQCFG_STRIDES(_idxd_dev) ((_idxd_dev)->wqcfg_size / sizeof(u32)) + #endif diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index 156a1ee233aa..417048e3c42a 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -74,7 +74,7 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) if (idxd->state != IDXD_DEV_ENABLED) return -EIO; - portal = wq->dportal + idxd_get_wq_portal_offset(IDXD_PORTAL_UNLIMITED); + portal = wq->dportal; /* * The wmb() flushes writes to coherent DMA data before possibly * triggering a DMA read. The wmb() is necessary even on UP because diff --git a/drivers/dma/ioat/dca.c b/drivers/dma/ioat/dca.c index 0be385587c4c..289c59ed74b9 100644 --- a/drivers/dma/ioat/dca.c +++ b/drivers/dma/ioat/dca.c @@ -40,16 +40,6 @@ #define DCA2_TAG_MAP_BYTE3 0x82 #define DCA2_TAG_MAP_BYTE4 0x82 -/* verify if tag map matches expected values */ -static inline int dca2_tag_map_valid(u8 *tag_map) -{ - return ((tag_map[0] == DCA2_TAG_MAP_BYTE0) && - (tag_map[1] == DCA2_TAG_MAP_BYTE1) && - (tag_map[2] == DCA2_TAG_MAP_BYTE2) && - (tag_map[3] == DCA2_TAG_MAP_BYTE3) && - (tag_map[4] == DCA2_TAG_MAP_BYTE4)); -} - /* * "Legacy" DCA systems do not implement the DCA register set in the * I/OAT device. Software needs direct support for their tag mappings. diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index e9f0101d92fa..0f5c19370f6d 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -2799,7 +2799,7 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst, * If burst size is smaller than bus width then make sure we only * transfer one at a time to avoid a burst stradling an MFIFO entry. */ - if (desc->rqcfg.brst_size * 8 < pl330->pcfg.data_bus_width) + if (burst * 8 < pl330->pcfg.data_bus_width) desc->rqcfg.brst_len = 1; desc->bytes_requested = len; diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c index aa24e554f7b4..8563a392f30b 100644 --- a/drivers/dma/ti/k3-udma-private.c +++ b/drivers/dma/ti/k3-udma-private.c @@ -83,7 +83,7 @@ EXPORT_SYMBOL(xudma_rflow_is_gp); #define XUDMA_GET_PUT_RESOURCE(res) \ struct udma_##res *xudma_##res##_get(struct udma_dev *ud, int id) \ { \ - return __udma_reserve_##res(ud, false, id); \ + return __udma_reserve_##res(ud, UDMA_TP_NORMAL, id); \ } \ EXPORT_SYMBOL(xudma_##res##_get); \ \ diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c index c9fe5e3a6b55..268a08058714 100644 --- a/drivers/dma/ti/omap-dma.c +++ b/drivers/dma/ti/omap-dma.c @@ -1522,29 +1522,38 @@ static void omap_dma_free(struct omap_dmadev *od) } } +/* Currently used by omap2 & 3 to block deeper SoC idle states */ +static bool omap_dma_busy(struct omap_dmadev *od) +{ + struct omap_chan *c; + int lch = -1; + + while (1) { + lch = find_next_bit(od->lch_bitmap, od->lch_count, lch + 1); + if (lch >= od->lch_count) + break; + c = od->lch_map[lch]; + if (!c) + continue; + if (omap_dma_chan_read(c, CCR) & CCR_ENABLE) + return true; + } + + return false; +} + /* Currently only used for omap2. For omap1, also a check for lcd_dma is needed */ static int omap_dma_busy_notifier(struct notifier_block *nb, unsigned long cmd, void *v) { struct omap_dmadev *od; - struct omap_chan *c; - int lch = -1; od = container_of(nb, struct omap_dmadev, nb); switch (cmd) { case CPU_CLUSTER_PM_ENTER: - while (1) { - lch = find_next_bit(od->lch_bitmap, od->lch_count, - lch + 1); - if (lch >= od->lch_count) - break; - c = od->lch_map[lch]; - if (!c) - continue; - if (omap_dma_chan_read(c, CCR) & CCR_ENABLE) - return NOTIFY_BAD; - } + if (omap_dma_busy(od)) + return NOTIFY_BAD; break; case CPU_CLUSTER_PM_ENTER_FAILED: case CPU_CLUSTER_PM_EXIT: @@ -1595,6 +1604,8 @@ static int omap_dma_context_notifier(struct notifier_block *nb, switch (cmd) { case CPU_CLUSTER_PM_ENTER: + if (omap_dma_busy(od)) + return NOTIFY_BAD; omap_dma_context_save(od); break; case CPU_CLUSTER_PM_ENTER_FAILED: diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index ecff35402860..22faea653ea8 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -517,8 +517,8 @@ struct xilinx_dma_device { #define to_dma_tx_descriptor(tx) \ container_of(tx, struct xilinx_dma_tx_descriptor, async_tx) #define xilinx_dma_poll_timeout(chan, reg, val, cond, delay_us, timeout_us) \ - readl_poll_timeout(chan->xdev->regs + chan->ctrl_offset + reg, val, \ - cond, delay_us, timeout_us) + readl_poll_timeout_atomic(chan->xdev->regs + chan->ctrl_offset + reg, \ + val, cond, delay_us, timeout_us) /* IO accessors */ static inline u32 dma_read(struct xilinx_dma_chan *chan, u32 reg) @@ -948,8 +948,10 @@ static u32 xilinx_dma_get_residue(struct xilinx_dma_chan *chan, { struct xilinx_cdma_tx_segment *cdma_seg; struct xilinx_axidma_tx_segment *axidma_seg; + struct xilinx_aximcdma_tx_segment *aximcdma_seg; struct xilinx_cdma_desc_hw *cdma_hw; struct xilinx_axidma_desc_hw *axidma_hw; + struct xilinx_aximcdma_desc_hw *aximcdma_hw; struct list_head *entry; u32 residue = 0; @@ -961,13 +963,23 @@ static u32 xilinx_dma_get_residue(struct xilinx_dma_chan *chan, cdma_hw = &cdma_seg->hw; residue += (cdma_hw->control - cdma_hw->status) & chan->xdev->max_buffer_len; - } else { + } else if (chan->xdev->dma_config->dmatype == + XDMA_TYPE_AXIDMA) { axidma_seg = list_entry(entry, struct xilinx_axidma_tx_segment, node); axidma_hw = &axidma_seg->hw; residue += (axidma_hw->control - axidma_hw->status) & chan->xdev->max_buffer_len; + } else { + aximcdma_seg = + list_entry(entry, + struct xilinx_aximcdma_tx_segment, + node); + aximcdma_hw = &aximcdma_seg->hw; + residue += + (aximcdma_hw->control - aximcdma_hw->status) & + chan->xdev->max_buffer_len; } } @@ -1135,7 +1147,7 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan) upper_32_bits(chan->seg_p + sizeof(*chan->seg_mv) * ((i + 1) % XILINX_DMA_NUM_DESCS)); chan->seg_mv[i].phys = chan->seg_p + - sizeof(*chan->seg_v) * i; + sizeof(*chan->seg_mv) * i; list_add_tail(&chan->seg_mv[i].node, &chan->free_seg_list); } @@ -1560,7 +1572,7 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan) static void xilinx_mcdma_start_transfer(struct xilinx_dma_chan *chan) { struct xilinx_dma_tx_descriptor *head_desc, *tail_desc; - struct xilinx_axidma_tx_segment *tail_segment; + struct xilinx_aximcdma_tx_segment *tail_segment; u32 reg; /* @@ -1582,7 +1594,7 @@ static void xilinx_mcdma_start_transfer(struct xilinx_dma_chan *chan) tail_desc = list_last_entry(&chan->pending_list, struct xilinx_dma_tx_descriptor, node); tail_segment = list_last_entry(&tail_desc->segments, - struct xilinx_axidma_tx_segment, node); + struct xilinx_aximcdma_tx_segment, node); reg = dma_ctrl_read(chan, XILINX_MCDMA_CHAN_CR_OFFSET(chan->tdest)); @@ -1864,6 +1876,7 @@ static void append_desc_queue(struct xilinx_dma_chan *chan, struct xilinx_vdma_tx_segment *tail_segment; struct xilinx_dma_tx_descriptor *tail_desc; struct xilinx_axidma_tx_segment *axidma_tail_segment; + struct xilinx_aximcdma_tx_segment *aximcdma_tail_segment; struct xilinx_cdma_tx_segment *cdma_tail_segment; if (list_empty(&chan->pending_list)) @@ -1885,11 +1898,17 @@ static void append_desc_queue(struct xilinx_dma_chan *chan, struct xilinx_cdma_tx_segment, node); cdma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys; - } else { + } else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) { axidma_tail_segment = list_last_entry(&tail_desc->segments, struct xilinx_axidma_tx_segment, node); axidma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys; + } else { + aximcdma_tail_segment = + list_last_entry(&tail_desc->segments, + struct xilinx_aximcdma_tx_segment, + node); + aximcdma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys; } /* @@ -2836,10 +2855,11 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev, chan->stop_transfer = xilinx_dma_stop_transfer; } - /* check if SG is enabled (only for AXIDMA and CDMA) */ + /* check if SG is enabled (only for AXIDMA, AXIMCDMA, and CDMA) */ if (xdev->dma_config->dmatype != XDMA_TYPE_VDMA) { - if (dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) & - XILINX_DMA_DMASR_SG_MASK) + if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA || + dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) & + XILINX_DMA_DMASR_SG_MASK) chan->has_sg = true; dev_dbg(chan->dev, "ch %d: SG %s\n", chan->id, chan->has_sg ? "enabled" : "disabled"); diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index 36ec1f718893..d9895491ff34 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -270,7 +270,7 @@ config EFI_DEV_PATH_PARSER config EFI_EARLYCON def_bool y - depends on SERIAL_EARLYCON && !ARM && !IA64 + depends on EFI && SERIAL_EARLYCON && !ARM && !IA64 select FONT_SUPPORT select ARCH_USE_MEMREMAP_PROT diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 5e5480a0a32d..6c6eec044a97 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -390,10 +390,10 @@ static int __init efisubsys_init(void) if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE | EFI_RT_SUPPORTED_GET_NEXT_VARIABLE_NAME)) { - efivar_ssdt_load(); error = generic_ops_register(); if (error) goto err_put; + efivar_ssdt_load(); platform_device_register_simple("efivars", 0, NULL, 0); } diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 8d1ff2454e2e..fd95edeb702b 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -20,12 +20,28 @@ #include <linux/of_platform.h> #include <linux/slab.h> #include <linux/uaccess.h> +#include <linux/hashtable.h> #include <linux/firmware/xlnx-zynqmp.h> #include "zynqmp-debug.h" +/* Max HashMap Order for PM API feature check (1<<7 = 128) */ +#define PM_API_FEATURE_CHECK_MAX_ORDER 7 + static bool feature_check_enabled; -static u32 zynqmp_pm_features[PM_API_MAX]; +static DEFINE_HASHTABLE(pm_api_features_map, PM_API_FEATURE_CHECK_MAX_ORDER); + +/** + * struct pm_api_feature_data - PM API Feature data + * @pm_api_id: PM API Id, used as key to index into hashmap + * @feature_status: status of PM API feature: valid, invalid + * @hentry: hlist_node that hooks this entry into hashtable + */ +struct pm_api_feature_data { + u32 pm_api_id; + int feature_status; + struct hlist_node hentry; +}; static const struct mfd_cell firmware_devs[] = { { @@ -142,26 +158,37 @@ static int zynqmp_pm_feature(u32 api_id) int ret; u32 ret_payload[PAYLOAD_ARG_CNT]; u64 smc_arg[2]; + struct pm_api_feature_data *feature_data; if (!feature_check_enabled) return 0; - /* Return value if feature is already checked */ - if (zynqmp_pm_features[api_id] != PM_FEATURE_UNCHECKED) - return zynqmp_pm_features[api_id]; + /* Check for existing entry in hash table for given api */ + hash_for_each_possible(pm_api_features_map, feature_data, hentry, + api_id) { + if (feature_data->pm_api_id == api_id) + return feature_data->feature_status; + } + + /* Add new entry if not present */ + feature_data = kmalloc(sizeof(*feature_data), GFP_KERNEL); + if (!feature_data) + return -ENOMEM; + feature_data->pm_api_id = api_id; smc_arg[0] = PM_SIP_SVC | PM_FEATURE_CHECK; smc_arg[1] = api_id; ret = do_fw_call(smc_arg[0], smc_arg[1], 0, ret_payload); - if (ret) { - zynqmp_pm_features[api_id] = PM_FEATURE_INVALID; - return PM_FEATURE_INVALID; - } + if (ret) + ret = -EOPNOTSUPP; + else + ret = ret_payload[1]; - zynqmp_pm_features[api_id] = ret_payload[1]; + feature_data->feature_status = ret; + hash_add(pm_api_features_map, &feature_data->hentry, api_id); - return zynqmp_pm_features[api_id]; + return ret; } /** @@ -197,9 +224,12 @@ int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1, * Make sure to stay in x0 register */ u64 smc_arg[4]; + int ret; - if (zynqmp_pm_feature(pm_api_id) == PM_FEATURE_INVALID) - return -ENOTSUPP; + /* Check if feature is supported or not */ + ret = zynqmp_pm_feature(pm_api_id); + if (ret < 0) + return ret; smc_arg[0] = PM_SIP_SVC | pm_api_id; smc_arg[1] = ((u64)arg1 << 32) | arg0; @@ -612,7 +642,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_tapdelay); */ int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type) { - return zynqmp_pm_invoke_fn(PM_IOCTL, node_id, IOCTL_SET_SD_TAPDELAY, + return zynqmp_pm_invoke_fn(PM_IOCTL, node_id, IOCTL_SD_DLL_RESET, type, 0, NULL); } EXPORT_SYMBOL_GPL(zynqmp_pm_sd_dll_reset); @@ -1249,9 +1279,17 @@ static int zynqmp_firmware_probe(struct platform_device *pdev) static int zynqmp_firmware_remove(struct platform_device *pdev) { + struct pm_api_feature_data *feature_data; + int i; + mfd_remove_devices(&pdev->dev); zynqmp_pm_api_debugfs_exit(); + hash_for_each(pm_api_features_map, i, feature_data, hentry) { + hash_del(&feature_data->hentry); + kfree(feature_data); + } + return 0; } diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig index 7cd5a29fc437..5645226ca3ce 100644 --- a/drivers/fpga/Kconfig +++ b/drivers/fpga/Kconfig @@ -142,6 +142,7 @@ config FPGA_DFL tristate "FPGA Device Feature List (DFL) support" select FPGA_BRIDGE select FPGA_REGION + depends on HAS_IOMEM help Device Feature List (DFL) defines a feature list structure that creates a linked list of feature headers within the MMIO space diff --git a/drivers/gpio/gpio-arizona.c b/drivers/gpio/gpio-arizona.c index 5bda38e0780f..2bc173c352ce 100644 --- a/drivers/gpio/gpio-arizona.c +++ b/drivers/gpio/gpio-arizona.c @@ -192,6 +192,7 @@ static int arizona_gpio_probe(struct platform_device *pdev) ret = devm_gpiochip_add_data(&pdev->dev, &arizona_gpio->gpio_chip, arizona_gpio); if (ret < 0) { + pm_runtime_disable(&pdev->dev); dev_err(&pdev->dev, "Could not register gpiochip, %d\n", ret); return ret; diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index e44d5de2a120..b966f5e28ebf 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -1114,6 +1114,7 @@ static const struct aspeed_gpio_config ast2500_config = static const struct aspeed_bank_props ast2600_bank_props[] = { /* input output */ + {4, 0xffffffff, 0x00ffffff}, /* Q/R/S/T */ {5, 0xffffffff, 0xffffff00}, /* U/V/W/X */ {6, 0x0000ffff, 0x0000ffff}, /* Y/Z */ { }, diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index a5b326754124..4275c18a097a 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -343,8 +343,8 @@ static int dwapb_irq_set_type(struct irq_data *d, u32 type) #ifdef CONFIG_PM_SLEEP static int dwapb_irq_set_wake(struct irq_data *d, unsigned int enable) { - struct irq_chip_generic *igc = irq_data_get_irq_chip_data(d); - struct dwapb_gpio *gpio = igc->private; + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct dwapb_gpio *gpio = to_dwapb_gpio(gc); struct dwapb_context *ctx = gpio->ports[0].ctx; irq_hw_number_t bit = irqd_to_hwirq(d); @@ -724,6 +724,8 @@ static int dwapb_gpio_probe(struct platform_device *pdev) return err; } + platform_set_drvdata(pdev, gpio); + return 0; } diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c index ad61daf6c212..865ab2b34fdd 100644 --- a/drivers/gpio/gpio-eic-sprd.c +++ b/drivers/gpio/gpio-eic-sprd.c @@ -598,7 +598,7 @@ static int sprd_eic_probe(struct platform_device *pdev) */ res = platform_get_resource(pdev, IORESOURCE_MEM, i); if (!res) - continue; + break; sprd_eic->base[i] = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(sprd_eic->base[i])) diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index 433e2c3f3fd5..2f245594a90a 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -1197,6 +1197,13 @@ static int mvebu_gpio_probe(struct platform_device *pdev) devm_gpiochip_add_data(&pdev->dev, &mvchip->chip, mvchip); + /* Some MVEBU SoCs have simple PWM support for GPIO lines */ + if (IS_ENABLED(CONFIG_PWM)) { + err = mvebu_pwm_probe(pdev, mvchip, id); + if (err) + return err; + } + /* Some gpio controllers do not provide irq support */ if (!have_irqs) return 0; @@ -1206,7 +1213,8 @@ static int mvebu_gpio_probe(struct platform_device *pdev) if (!mvchip->domain) { dev_err(&pdev->dev, "couldn't allocate irq domain %s (DT).\n", mvchip->chip.label); - return -ENODEV; + err = -ENODEV; + goto err_pwm; } err = irq_alloc_domain_generic_chips( @@ -1254,14 +1262,12 @@ static int mvebu_gpio_probe(struct platform_device *pdev) mvchip); } - /* Some MVEBU SoCs have simple PWM support for GPIO lines */ - if (IS_ENABLED(CONFIG_PWM)) - return mvebu_pwm_probe(pdev, mvchip, id); - return 0; err_domain: irq_domain_remove(mvchip->domain); +err_pwm: + pwmchip_remove(&mvchip->mvpwm->chip); return err; } diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index 6d59e3a43761..f7ceb2b11afc 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -1114,13 +1114,23 @@ static void omap_gpio_idle(struct gpio_bank *bank, bool may_lose_context) { struct device *dev = bank->chip.parent; void __iomem *base = bank->base; - u32 nowake; + u32 mask, nowake; bank->saved_datain = readl_relaxed(base + bank->regs->datain); if (!bank->enabled_non_wakeup_gpios) goto update_gpio_context_count; + /* Check for pending EDGE_FALLING, ignore EDGE_BOTH */ + mask = bank->enabled_non_wakeup_gpios & bank->context.fallingdetect; + mask &= ~bank->context.risingdetect; + bank->saved_datain |= mask; + + /* Check for pending EDGE_RISING, ignore EDGE_BOTH */ + mask = bank->enabled_non_wakeup_gpios & bank->context.risingdetect; + mask &= ~bank->context.fallingdetect; + bank->saved_datain &= ~mask; + if (!may_lose_context) goto update_gpio_context_count; diff --git a/drivers/gpio/gpio-pcie-idio-24.c b/drivers/gpio/gpio-pcie-idio-24.c index a68941d19ac6..2a07fd96707e 100644 --- a/drivers/gpio/gpio-pcie-idio-24.c +++ b/drivers/gpio/gpio-pcie-idio-24.c @@ -28,6 +28,47 @@ #include <linux/spinlock.h> #include <linux/types.h> +/* + * PLX PEX8311 PCI LCS_INTCSR Interrupt Control/Status + * + * Bit: Description + * 0: Enable Interrupt Sources (Bit 0) + * 1: Enable Interrupt Sources (Bit 1) + * 2: Generate Internal PCI Bus Internal SERR# Interrupt + * 3: Mailbox Interrupt Enable + * 4: Power Management Interrupt Enable + * 5: Power Management Interrupt + * 6: Slave Read Local Data Parity Check Error Enable + * 7: Slave Read Local Data Parity Check Error Status + * 8: Internal PCI Wire Interrupt Enable + * 9: PCI Express Doorbell Interrupt Enable + * 10: PCI Abort Interrupt Enable + * 11: Local Interrupt Input Enable + * 12: Retry Abort Enable + * 13: PCI Express Doorbell Interrupt Active + * 14: PCI Abort Interrupt Active + * 15: Local Interrupt Input Active + * 16: Local Interrupt Output Enable + * 17: Local Doorbell Interrupt Enable + * 18: DMA Channel 0 Interrupt Enable + * 19: DMA Channel 1 Interrupt Enable + * 20: Local Doorbell Interrupt Active + * 21: DMA Channel 0 Interrupt Active + * 22: DMA Channel 1 Interrupt Active + * 23: Built-In Self-Test (BIST) Interrupt Active + * 24: Direct Master was the Bus Master during a Master or Target Abort + * 25: DMA Channel 0 was the Bus Master during a Master or Target Abort + * 26: DMA Channel 1 was the Bus Master during a Master or Target Abort + * 27: Target Abort after internal 256 consecutive Master Retrys + * 28: PCI Bus wrote data to LCS_MBOX0 + * 29: PCI Bus wrote data to LCS_MBOX1 + * 30: PCI Bus wrote data to LCS_MBOX2 + * 31: PCI Bus wrote data to LCS_MBOX3 + */ +#define PLX_PEX8311_PCI_LCS_INTCSR 0x68 +#define INTCSR_INTERNAL_PCI_WIRE BIT(8) +#define INTCSR_LOCAL_INPUT BIT(11) + /** * struct idio_24_gpio_reg - GPIO device registers structure * @out0_7: Read: FET Outputs 0-7 @@ -92,6 +133,7 @@ struct idio_24_gpio_reg { struct idio_24_gpio { struct gpio_chip chip; raw_spinlock_t lock; + __u8 __iomem *plx; struct idio_24_gpio_reg __iomem *reg; unsigned long irq_mask; }; @@ -334,13 +376,13 @@ static void idio_24_irq_mask(struct irq_data *data) unsigned long flags; const unsigned long bit_offset = irqd_to_hwirq(data) - 24; unsigned char new_irq_mask; - const unsigned long bank_offset = bit_offset/8 * 8; + const unsigned long bank_offset = bit_offset / 8; unsigned char cos_enable_state; raw_spin_lock_irqsave(&idio24gpio->lock, flags); - idio24gpio->irq_mask &= BIT(bit_offset); - new_irq_mask = idio24gpio->irq_mask >> bank_offset; + idio24gpio->irq_mask &= ~BIT(bit_offset); + new_irq_mask = idio24gpio->irq_mask >> bank_offset * 8; if (!new_irq_mask) { cos_enable_state = ioread8(&idio24gpio->reg->cos_enable); @@ -363,12 +405,12 @@ static void idio_24_irq_unmask(struct irq_data *data) unsigned long flags; unsigned char prev_irq_mask; const unsigned long bit_offset = irqd_to_hwirq(data) - 24; - const unsigned long bank_offset = bit_offset/8 * 8; + const unsigned long bank_offset = bit_offset / 8; unsigned char cos_enable_state; raw_spin_lock_irqsave(&idio24gpio->lock, flags); - prev_irq_mask = idio24gpio->irq_mask >> bank_offset; + prev_irq_mask = idio24gpio->irq_mask >> bank_offset * 8; idio24gpio->irq_mask |= BIT(bit_offset); if (!prev_irq_mask) { @@ -455,6 +497,7 @@ static int idio_24_probe(struct pci_dev *pdev, const struct pci_device_id *id) struct device *const dev = &pdev->dev; struct idio_24_gpio *idio24gpio; int err; + const size_t pci_plx_bar_index = 1; const size_t pci_bar_index = 2; const char *const name = pci_name(pdev); struct gpio_irq_chip *girq; @@ -469,12 +512,13 @@ static int idio_24_probe(struct pci_dev *pdev, const struct pci_device_id *id) return err; } - err = pcim_iomap_regions(pdev, BIT(pci_bar_index), name); + err = pcim_iomap_regions(pdev, BIT(pci_plx_bar_index) | BIT(pci_bar_index), name); if (err) { dev_err(dev, "Unable to map PCI I/O addresses (%d)\n", err); return err; } + idio24gpio->plx = pcim_iomap_table(pdev)[pci_plx_bar_index]; idio24gpio->reg = pcim_iomap_table(pdev)[pci_bar_index]; idio24gpio->chip.label = name; @@ -504,6 +548,12 @@ static int idio_24_probe(struct pci_dev *pdev, const struct pci_device_id *id) /* Software board reset */ iowrite8(0, &idio24gpio->reg->soft_reset); + /* + * enable PLX PEX8311 internal PCI wire interrupt and local interrupt + * input + */ + iowrite8((INTCSR_INTERNAL_PCI_WIRE | INTCSR_LOCAL_INPUT) >> 8, + idio24gpio->plx + PLX_PEX8311_PCI_LCS_INTCSR + 1); err = devm_gpiochip_add_data(dev, &idio24gpio->chip, idio24gpio); if (err) { diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c index c54dd08f2cbf..d5eb9ca11901 100644 --- a/drivers/gpio/gpio-sifive.c +++ b/drivers/gpio/gpio-sifive.c @@ -183,7 +183,7 @@ static int sifive_gpio_probe(struct platform_device *pdev) return PTR_ERR(chip->regs); ngpio = of_irq_count(node); - if (ngpio >= SIFIVE_GPIO_MAX) { + if (ngpio > SIFIVE_GPIO_MAX) { dev_err(dev, "Too many GPIO interrupts (max=%d)\n", SIFIVE_GPIO_MAX); return -ENXIO; diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c index 0b5a17ab996f..3521c1dc3ac0 100644 --- a/drivers/gpio/gpio-zynq.c +++ b/drivers/gpio/gpio-zynq.c @@ -574,7 +574,7 @@ static int zynq_gpio_irq_reqres(struct irq_data *d) struct gpio_chip *chip = irq_data_get_irq_chip_data(d); int ret; - ret = pm_runtime_get_sync(chip->parent); + ret = pm_runtime_resume_and_get(chip->parent); if (ret < 0) return ret; @@ -942,7 +942,7 @@ static int zynq_gpio_probe(struct platform_device *pdev) pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) goto err_pm_dis; diff --git a/drivers/gpio/gpiolib-cdev.h b/drivers/gpio/gpiolib-cdev.h index cb41dd757338..b42644cbffb8 100644 --- a/drivers/gpio/gpiolib-cdev.h +++ b/drivers/gpio/gpiolib-cdev.h @@ -7,22 +7,7 @@ struct gpio_device; -#ifdef CONFIG_GPIO_CDEV - int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt); void gpiolib_cdev_unregister(struct gpio_device *gdev); -#else - -static inline int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt) -{ - return 0; -} - -static inline void gpiolib_cdev_unregister(struct gpio_device *gdev) -{ -} - -#endif /* CONFIG_GPIO_CDEV */ - #endif /* GPIOLIB_CDEV_H */ diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 3cdf9effc13a..6e3c4d7a7d14 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -480,11 +480,23 @@ static void gpiodevice_release(struct device *dev) kfree(gdev); } +#ifdef CONFIG_GPIO_CDEV +#define gcdev_register(gdev, devt) gpiolib_cdev_register((gdev), (devt)) +#define gcdev_unregister(gdev) gpiolib_cdev_unregister((gdev)) +#else +/* + * gpiolib_cdev_register() indirectly calls device_add(), which is still + * required even when cdev is not selected. + */ +#define gcdev_register(gdev, devt) device_add(&(gdev)->dev) +#define gcdev_unregister(gdev) device_del(&(gdev)->dev) +#endif + static int gpiochip_setup_dev(struct gpio_device *gdev) { int ret; - ret = gpiolib_cdev_register(gdev, gpio_devt); + ret = gcdev_register(gdev, gpio_devt); if (ret) return ret; @@ -500,7 +512,7 @@ static int gpiochip_setup_dev(struct gpio_device *gdev) return 0; err_remove_device: - gpiolib_cdev_unregister(gdev); + gcdev_unregister(gdev); return ret; } @@ -825,7 +837,7 @@ void gpiochip_remove(struct gpio_chip *gc) * be removed, else it will be dangling until the last user is * gone. */ - gpiolib_cdev_unregister(gdev); + gcdev_unregister(gdev); put_device(&gdev->dev); } EXPORT_SYMBOL_GPL(gpiochip_remove); @@ -1794,6 +1806,11 @@ EXPORT_SYMBOL_GPL(gpiochip_generic_request); */ void gpiochip_generic_free(struct gpio_chip *gc, unsigned offset) { +#ifdef CONFIG_PINCTRL + if (list_empty(&gc->gpiodev->pin_ranges)) + return; +#endif + pinctrl_gpio_free(gc->gpiodev->base + offset); } EXPORT_SYMBOL_GPL(gpiochip_generic_free); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index e3783f5a459d..026789b466db 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4852,7 +4852,7 @@ int amdgpu_device_baco_enter(struct drm_device *dev) if (!amdgpu_device_supports_baco(adev_to_drm(adev))) return -ENOTSUPP; - if (ras && ras->supported) + if (ras && ras->supported && adev->nbio.funcs->enable_doorbell_interrupt) adev->nbio.funcs->enable_doorbell_interrupt(adev, false); return amdgpu_dpm_baco_enter(adev); @@ -4871,7 +4871,7 @@ int amdgpu_device_baco_exit(struct drm_device *dev) if (ret) return ret; - if (ras && ras->supported) + if (ras && ras->supported && adev->nbio.funcs->enable_doorbell_interrupt) adev->nbio.funcs->enable_doorbell_interrupt(adev, true); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 957934926b24..1b56dbc1f304 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -459,6 +459,7 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) struct amdgpu_device *adev = drm_to_adev(dev); struct amdgpu_bo *bo; struct amdgpu_bo_param bp; + struct drm_gem_object *gobj; int ret; memset(&bp, 0, sizeof(bp)); @@ -469,17 +470,20 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) bp.type = ttm_bo_type_sg; bp.resv = resv; dma_resv_lock(resv, NULL); - ret = amdgpu_bo_create(adev, &bp, &bo); + ret = amdgpu_gem_object_create(adev, dma_buf->size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_CPU, + 0, ttm_bo_type_sg, resv, &gobj); if (ret) goto error; + bo = gem_to_amdgpu_bo(gobj); bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT; bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT; if (dma_buf->ops != &amdgpu_dmabuf_ops) bo->prime_shared_count = 1; dma_resv_unlock(resv); - return &bo->tbo.base; + return gobj; error: dma_resv_unlock(resv); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 42d9748921f5..8e988f07f085 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1055,10 +1055,10 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU}, {0x1002, 0x15d8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU}, /* Arcturus */ - {0x1002, 0x738C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7388, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x738E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7390, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x738C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, + {0x1002, 0x7388, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, + {0x1002, 0x738E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, + {0x1002, 0x7390, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, /* Navi10 */ {0x1002, 0x7310, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, {0x1002, 0x7312, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 7e8265da9f25..e8c76bd8c501 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -66,26 +66,12 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, bp.type = type; bp.resv = resv; bp.preferred_domain = initial_domain; -retry: bp.flags = flags; bp.domain = initial_domain; r = amdgpu_bo_create(adev, &bp, &bo); - if (r) { - if (r != -ERESTARTSYS) { - if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) { - flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - goto retry; - } - - if (initial_domain == AMDGPU_GEM_DOMAIN_VRAM) { - initial_domain |= AMDGPU_GEM_DOMAIN_GTT; - goto retry; - } - DRM_DEBUG("Failed to allocate GEM object (%ld, %d, %u, %d)\n", - size, initial_domain, alignment, r); - } + if (r) return r; - } + *obj = &bo->tbo.base; return 0; @@ -225,7 +211,7 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data, uint64_t size = args->in.bo_size; struct dma_resv *resv = NULL; struct drm_gem_object *gobj; - uint32_t handle; + uint32_t handle, initial_domain; int r; /* reject invalid gem flags */ @@ -269,9 +255,28 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data, resv = vm->root.base.bo->tbo.base.resv; } +retry: + initial_domain = (u32)(0xffffffff & args->in.domains); r = amdgpu_gem_object_create(adev, size, args->in.alignment, - (u32)(0xffffffff & args->in.domains), + initial_domain, flags, ttm_bo_type_device, resv, &gobj); + if (r) { + if (r != -ERESTARTSYS) { + if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) { + flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; + goto retry; + } + + if (initial_domain == AMDGPU_GEM_DOMAIN_VRAM) { + initial_domain |= AMDGPU_GEM_DOMAIN_GTT; + goto retry; + } + DRM_DEBUG("Failed to allocate GEM object (%llu, %d, %llu, %d)\n", + size, initial_domain, args->in.alignment, r); + } + return r; + } + if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) { if (!r) { struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 36604d751d62..3e4892b7b7d3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -499,6 +499,9 @@ void amdgpu_gmc_get_vbios_allocations(struct amdgpu_device *adev) else size = amdgpu_gmc_get_vbios_fb_size(adev); + if (adev->mman.keep_stolen_vga_memory) + size = max(size, (unsigned)AMDGPU_VBIOS_VGA_ALLOCATION); + /* set to 0 if the pre-OS buffer uses up most of vram */ if ((adev->gmc.real_vram_size - size) < (8 * 1024 * 1024)) size = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 4e36551ab50b..82cd8e55595a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1172,7 +1172,7 @@ static void amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *adev) con->dir, &con->disable_ras_err_cnt_harvest); } -void amdgpu_ras_debugfs_create(struct amdgpu_device *adev, +static void amdgpu_ras_debugfs_create(struct amdgpu_device *adev, struct ras_fs_if *head) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); @@ -1194,7 +1194,6 @@ void amdgpu_ras_debugfs_create(struct amdgpu_device *adev, void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev) { -#if defined(CONFIG_DEBUG_FS) struct amdgpu_ras *con = amdgpu_ras_get_context(adev); struct ras_manager *obj; struct ras_fs_if fs_info; @@ -1203,7 +1202,7 @@ void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev) * it won't be called in resume path, no need to check * suspend and gpu reset status */ - if (!con) + if (!IS_ENABLED(CONFIG_DEBUG_FS) || !con) return; amdgpu_ras_debugfs_create_ctrl_node(adev); @@ -1217,10 +1216,9 @@ void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev) amdgpu_ras_debugfs_create(adev, &fs_info); } } -#endif } -void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev, +static void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev, struct ras_common_if *head) { struct ras_manager *obj = amdgpu_ras_find_obj(adev, head); @@ -1234,7 +1232,6 @@ void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev, static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev) { -#if defined(CONFIG_DEBUG_FS) struct amdgpu_ras *con = amdgpu_ras_get_context(adev); struct ras_manager *obj, *tmp; @@ -1243,7 +1240,6 @@ static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev) } con->dir = NULL; -#endif } /* debugfs end */ @@ -1291,7 +1287,8 @@ static int amdgpu_ras_fs_init(struct amdgpu_device *adev) static int amdgpu_ras_fs_fini(struct amdgpu_device *adev) { - amdgpu_ras_debugfs_remove_all(adev); + if (IS_ENABLED(CONFIG_DEBUG_FS)) + amdgpu_ras_debugfs_remove_all(adev); amdgpu_ras_sysfs_remove_all(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h index 6b8d7bb83bb3..ec398ed7deb8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h @@ -607,14 +607,8 @@ int amdgpu_ras_sysfs_create(struct amdgpu_device *adev, int amdgpu_ras_sysfs_remove(struct amdgpu_device *adev, struct ras_common_if *head); -void amdgpu_ras_debugfs_create(struct amdgpu_device *adev, - struct ras_fs_if *head); - void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev); -void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev, - struct ras_common_if *head); - int amdgpu_ras_error_query(struct amdgpu_device *adev, struct ras_query_if *info); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 8039d2399584..a0248d78190f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -69,10 +69,10 @@ static int amdgpu_ttm_backend_bind(struct ttm_bo_device *bdev, static int amdgpu_ttm_init_on_chip(struct amdgpu_device *adev, unsigned int type, - uint64_t size) + uint64_t size_in_page) { return ttm_range_man_init(&adev->mman.bdev, type, - false, size >> PAGE_SHIFT); + false, size_in_page); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h index 5eb63288d157..edbb8194ee81 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h @@ -67,6 +67,7 @@ struct amdgpu_uvd { unsigned harvest_config; /* store image width to adjust nb memory state */ unsigned decode_image_width; + uint32_t keyselect; }; int amdgpu_uvd_sw_init(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 3579565e0eab..55f4b8c3b933 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3105,6 +3105,8 @@ static const struct soc15_reg_golden golden_settings_gc_10_3[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_EXCEPTION_CONTROL, 0x7fff0f1f, 0x00b80000), + SOC15_REG_GOLDEN_VALUE(GC, 0 ,mmGCEA_SDP_TAG_RESERVE0, 0xffffffff, 0x10100100), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCEA_SDP_TAG_RESERVE1, 0xffffffff, 0x17000088), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Sienna_Cichlid, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGE_PC_CNTL, 0x003fffff, 0x00280400), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf), diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index d5715c1d177b..8eeba8096493 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -492,8 +492,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev) if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block); #if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev) && - !nv_is_headless_sku(adev->pdev)) + else if (amdgpu_device_has_dc_support(adev)) amdgpu_device_ip_block_add(adev, &dm_ip_block); #endif amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block); diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c index dff5c15b4858..c4828bd3264b 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c @@ -40,6 +40,7 @@ MODULE_FIRMWARE("amdgpu/renoir_asd.bin"); MODULE_FIRMWARE("amdgpu/renoir_ta.bin"); MODULE_FIRMWARE("amdgpu/green_sardine_asd.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_ta.bin"); /* address block */ #define smnMP1_FIRMWARE_FLAGS 0x3010024 diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 9f3952723c63..2a485052e3ab 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -186,7 +186,7 @@ static int sdma_v5_2_init_microcode(struct amdgpu_device *adev) if (err) goto out; - err = sdma_v5_2_init_inst_ctx(&adev->sdma.instance[0]); + err = sdma_v5_2_init_inst_ctx(&adev->sdma.instance[i]); if (err) goto out; } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c index 7cf4b11a65c5..41800fcad410 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c @@ -277,15 +277,8 @@ static void uvd_v3_1_mc_resume(struct amdgpu_device *adev) */ static int uvd_v3_1_fw_validate(struct amdgpu_device *adev) { - void *ptr; - uint32_t ucode_len, i; - uint32_t keysel; - - ptr = adev->uvd.inst[0].cpu_addr; - ptr += 192 + 16; - memcpy(&ucode_len, ptr, 4); - ptr += ucode_len; - memcpy(&keysel, ptr, 4); + int i; + uint32_t keysel = adev->uvd.keyselect; WREG32(mmUVD_FW_START, keysel); @@ -550,6 +543,8 @@ static int uvd_v3_1_sw_init(void *handle) struct amdgpu_ring *ring; struct amdgpu_device *adev = (struct amdgpu_device *)handle; int r; + void *ptr; + uint32_t ucode_len; /* UVD TRAP */ r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq); @@ -571,6 +566,13 @@ static int uvd_v3_1_sw_init(void *handle) if (r) return r; + /* Retrieval firmware validate key */ + ptr = adev->uvd.inst[0].cpu_addr; + ptr += 192 + 16; + memcpy(&ucode_len, ptr, 4); + ptr += ucode_len; + memcpy(&adev->uvd.keyselect, ptr, 4); + r = amdgpu_uvd_entity_init(adev); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index e074f7ed388c..b5f8f3d731cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1011,6 +1011,11 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1); WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_CNTL, tmp); + /* Stall DPG before WPTR/RPTR reset */ + WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS), + UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK, + ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); + /* set the write pointer delay */ WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR_CNTL, 0); @@ -1033,6 +1038,10 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr)); + /* Unstall DPG */ + WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS), + 0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); + return 0; } @@ -1556,8 +1565,14 @@ static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev, UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK, UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK); + /* Stall DPG before WPTR/RPTR reset */ + WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS), + UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK, + ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); + /* Restore */ ring = &adev->vcn.inst[inst_idx].ring_enc[0]; + ring->wptr = 0; WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_LO, ring->gpu_addr); WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); WREG32_SOC15(VCN, inst_idx, mmUVD_RB_SIZE, ring->ring_size / 4); @@ -1565,14 +1580,16 @@ static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev, WREG32_SOC15(VCN, inst_idx, mmUVD_RB_WPTR, lower_32_bits(ring->wptr)); ring = &adev->vcn.inst[inst_idx].ring_enc[1]; + ring->wptr = 0; WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_LO2, ring->gpu_addr); WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr)); WREG32_SOC15(VCN, inst_idx, mmUVD_RB_SIZE2, ring->ring_size / 4); WREG32_SOC15(VCN, inst_idx, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr)); WREG32_SOC15(VCN, inst_idx, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr)); - WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR, - RREG32_SOC15(VCN, inst_idx, mmUVD_SCRATCH2) & 0x7FFFFFFF); + /* Unstall DPG */ + WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS), + 0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); @@ -1630,10 +1647,6 @@ static void vcn_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - WREG32_SOC15(VCN, ring->me, mmUVD_SCRATCH2, - lower_32_bits(ring->wptr) | 0x80000000); - if (ring->use_doorbell) { adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr); WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr)); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 222f1df1a6b6..8cc51cec988a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1736,6 +1736,7 @@ static int kfd_ioctl_import_dmabuf(struct file *filep, } mutex_unlock(&p->mutex); + dma_buf_put(dmabuf); args->handle = MAKE_HANDLE(args->gpu_id, idr_handle); @@ -1745,6 +1746,7 @@ err_free: amdgpu_amdkfd_gpuvm_free_memory_of_gpu(dev->kgd, (struct kgd_mem *)mem, NULL); err_unlock: mutex_unlock(&p->mutex); + dma_buf_put(dmabuf); return r; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index e93e18c06c0e..0f7749e9424d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1041,7 +1041,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) amdgpu_dm_init_color_mod(); #ifdef CONFIG_DRM_AMD_DC_HDCP - if (adev->asic_type >= CHIP_RAVEN) { + if (adev->dm.dc->caps.max_links > 0 && adev->asic_type >= CHIP_RAVEN) { adev->dm.hdcp_workqueue = hdcp_create_workqueue(adev, &init_params.cp_psp, adev->dm.dc); if (!adev->dm.hdcp_workqueue) @@ -1058,9 +1058,6 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) goto error; } - /* Update the actual used number of crtc */ - adev->mode_info.num_crtc = adev->dm.display_indexes_num; - /* create fake encoders for MST */ dm_dp_create_fake_mst_encoders(adev); @@ -3251,6 +3248,10 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) enum dc_connection_type new_connection_type = dc_connection_none; const struct dc_plane_cap *plane; + dm->display_indexes_num = dm->dc->caps.max_streams; + /* Update the actual used number of crtc */ + adev->mode_info.num_crtc = adev->dm.display_indexes_num; + link_cnt = dm->dc->caps.max_links; if (amdgpu_dm_mode_config_init(dm->adev)) { DRM_ERROR("DM: Failed to initialize mode config\n"); @@ -3312,8 +3313,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) goto fail; } - dm->display_indexes_num = dm->dc->caps.max_streams; - /* loops over all connectors on the board */ for (i = 0; i < link_cnt; i++) { struct dc_link *link = NULL; @@ -7506,7 +7505,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) bool mode_set_reset_required = false; drm_atomic_helper_update_legacy_modeset_state(dev, state); - drm_atomic_helper_calc_timestamping_constants(state); dm_state = dm_atomic_get_new_state(state); if (dm_state && dm_state->context) { @@ -7533,6 +7531,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) } } + drm_atomic_helper_calc_timestamping_constants(state); + /* update changed items */ for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index 2f8fee05547a..6b431db146cd 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -163,8 +163,17 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base, new_clocks->dppclk_khz = 100000; } - if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) { - if (clk_mgr->base.clks.dppclk_khz > new_clocks->dppclk_khz) + /* + * Temporally ignore thew 0 cases for disp and dpp clks. + * We may have a new feature that requires 0 clks in the future. + */ + if (new_clocks->dppclk_khz == 0 || new_clocks->dispclk_khz == 0) { + new_clocks->dppclk_khz = clk_mgr_base->clks.dppclk_khz; + new_clocks->dispclk_khz = clk_mgr_base->clks.dispclk_khz; + } + + if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr_base->clks.dppclk_khz)) { + if (clk_mgr_base->clks.dppclk_khz > new_clocks->dppclk_khz) dpp_clock_lowered = true; clk_mgr_base->clks.dppclk_khz = new_clocks->dppclk_khz; update_dppclk = true; @@ -570,7 +579,7 @@ static struct clk_bw_params rn_bw_params = { }; -static struct wm_table ddr4_wm_table = { +static struct wm_table ddr4_wm_table_gs = { .entries = { { .wm_inst = WM_A, @@ -607,7 +616,7 @@ static struct wm_table ddr4_wm_table = { } }; -static struct wm_table lpddr4_wm_table = { +static struct wm_table lpddr4_wm_table_gs = { .entries = { { .wm_inst = WM_A, @@ -681,6 +690,80 @@ static struct wm_table lpddr4_wm_table_with_disabled_ppt = { } }; +static struct wm_table ddr4_wm_table_rn = { + .entries = { + { + .wm_inst = WM_A, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 9.09, + .sr_enter_plus_exit_time_us = 10.14, + .valid = true, + }, + { + .wm_inst = WM_B, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 10.12, + .sr_enter_plus_exit_time_us = 11.48, + .valid = true, + }, + { + .wm_inst = WM_C, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 10.12, + .sr_enter_plus_exit_time_us = 11.48, + .valid = true, + }, + { + .wm_inst = WM_D, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 10.12, + .sr_enter_plus_exit_time_us = 11.48, + .valid = true, + }, + } +}; + +static struct wm_table lpddr4_wm_table_rn = { + .entries = { + { + .wm_inst = WM_A, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 7.32, + .sr_enter_plus_exit_time_us = 8.38, + .valid = true, + }, + { + .wm_inst = WM_B, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.82, + .sr_enter_plus_exit_time_us = 11.196, + .valid = true, + }, + { + .wm_inst = WM_C, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.89, + .sr_enter_plus_exit_time_us = 11.24, + .valid = true, + }, + { + .wm_inst = WM_D, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.65333, + .sr_exit_time_us = 9.748, + .sr_enter_plus_exit_time_us = 11.102, + .valid = true, + }, + } +}; + static unsigned int find_dcfclk_for_voltage(struct dpm_clocks *clock_table, unsigned int voltage) { int i; @@ -762,6 +845,11 @@ void rn_clk_mgr_construct( struct dc_debug_options *debug = &ctx->dc->debug; struct dpm_clocks clock_table = { 0 }; enum pp_smu_status status = 0; + int is_green_sardine = 0; + +#if defined(CONFIG_DRM_AMD_DC_DCN) + is_green_sardine = ASICREV_IS_GREEN_SARDINE(ctx->asic_id.hw_internal_rev); +#endif clk_mgr->base.ctx = ctx; clk_mgr->base.funcs = &dcn21_funcs; @@ -802,10 +890,16 @@ void rn_clk_mgr_construct( if (clk_mgr->periodic_retraining_disabled) { rn_bw_params.wm_table = lpddr4_wm_table_with_disabled_ppt; } else { - rn_bw_params.wm_table = lpddr4_wm_table; + if (is_green_sardine) + rn_bw_params.wm_table = lpddr4_wm_table_gs; + else + rn_bw_params.wm_table = lpddr4_wm_table_rn; } } else { - rn_bw_params.wm_table = ddr4_wm_table; + if (is_green_sardine) + rn_bw_params.wm_table = ddr4_wm_table_gs; + else + rn_bw_params.wm_table = ddr4_wm_table_rn; } /* Saved clocks configured at boot for debug purposes */ rn_dump_clk_registers(&clk_mgr->base.boot_snapshot, &clk_mgr->base, &log_info); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index fec87a2e210c..5b0cedfa824a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -3394,10 +3394,13 @@ uint32_t dc_bandwidth_in_kbps_from_timing( { uint32_t bits_per_channel = 0; uint32_t kbps; + struct fixed31_32 link_bw_kbps; if (timing->flags.DSC) { - kbps = (timing->pix_clk_100hz * timing->dsc_cfg.bits_per_pixel); - kbps = kbps / 160 + ((kbps % 160) ? 1 : 0); + link_bw_kbps = dc_fixpt_from_int(timing->pix_clk_100hz); + link_bw_kbps = dc_fixpt_div_int(link_bw_kbps, 160); + link_bw_kbps = dc_fixpt_mul_int(link_bw_kbps, timing->dsc_cfg.bits_per_pixel); + kbps = dc_fixpt_ceil(link_bw_kbps); return kbps; } diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c index 2a1fea501f8c..3f1e7a196a23 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c @@ -299,8 +299,8 @@ irq_source_info_dcn20[DAL_IRQ_SOURCES_NUMBER] = { pflip_int_entry(1), pflip_int_entry(2), pflip_int_entry(3), - [DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(), - [DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(), + pflip_int_entry(4), + pflip_int_entry(5), [DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(), gpio_pad_int_entry(0), gpio_pad_int_entry(1), diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c index 49689f71f4f1..0effbb2bd74a 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c @@ -306,8 +306,8 @@ irq_source_info_dcn30[DAL_IRQ_SOURCES_NUMBER] = { pflip_int_entry(1), pflip_int_entry(2), pflip_int_entry(3), - [DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(), - [DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(), + pflip_int_entry(4), + pflip_int_entry(5), [DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(), gpio_pad_int_entry(0), gpio_pad_int_entry(1), diff --git a/drivers/gpu/drm/amd/pm/inc/smu10.h b/drivers/gpu/drm/amd/pm/inc/smu10.h index b96520528240..9e837a5014c5 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu10.h +++ b/drivers/gpu/drm/amd/pm/inc/smu10.h @@ -136,14 +136,12 @@ #define FEATURE_CORE_CSTATES_MASK (1 << FEATURE_CORE_CSTATES_BIT) /* Workload bits */ -#define WORKLOAD_DEFAULT_BIT 0 -#define WORKLOAD_PPLIB_FULL_SCREEN_3D_BIT 1 -#define WORKLOAD_PPLIB_POWER_SAVING_BIT 2 -#define WORKLOAD_PPLIB_VIDEO_BIT 3 -#define WORKLOAD_PPLIB_VR_BIT 4 -#define WORKLOAD_PPLIB_COMPUTE_BIT 5 -#define WORKLOAD_PPLIB_CUSTOM_BIT 6 -#define WORKLOAD_PPLIB_COUNT 7 +#define WORKLOAD_PPLIB_FULL_SCREEN_3D_BIT 0 +#define WORKLOAD_PPLIB_VIDEO_BIT 2 +#define WORKLOAD_PPLIB_VR_BIT 3 +#define WORKLOAD_PPLIB_COMPUTE_BIT 4 +#define WORKLOAD_PPLIB_CUSTOM_BIT 5 +#define WORKLOAD_PPLIB_COUNT 6 typedef struct { /* MP1_EXT_SCRATCH0 */ diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c index 719597c5d27d..6606511891e3 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c @@ -24,6 +24,8 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> +#include <linux/pci.h> + #include <drm/amdgpu_drm.h> #include "processpptables.h" #include <atom-types.h> @@ -984,6 +986,8 @@ static int init_thermal_controller( struct pp_hwmgr *hwmgr, const ATOM_PPLIB_POWERPLAYTABLE *powerplay_table) { + struct amdgpu_device *adev = hwmgr->adev; + hwmgr->thermal_controller.ucType = powerplay_table->sThermalController.ucType; hwmgr->thermal_controller.ucI2cLine = @@ -1008,7 +1012,104 @@ static int init_thermal_controller( ATOM_PP_THERMALCONTROLLER_NONE != hwmgr->thermal_controller.ucType, PHM_PlatformCaps_ThermalController); - hwmgr->thermal_controller.use_hw_fan_control = 1; + if (powerplay_table->usTableSize >= sizeof(ATOM_PPLIB_POWERPLAYTABLE3)) { + const ATOM_PPLIB_POWERPLAYTABLE3 *powerplay_table3 = + (const ATOM_PPLIB_POWERPLAYTABLE3 *)powerplay_table; + + if (0 == le16_to_cpu(powerplay_table3->usFanTableOffset)) { + hwmgr->thermal_controller.use_hw_fan_control = 1; + return 0; + } else { + const ATOM_PPLIB_FANTABLE *fan_table = + (const ATOM_PPLIB_FANTABLE *)(((unsigned long)powerplay_table) + + le16_to_cpu(powerplay_table3->usFanTableOffset)); + + if (1 <= fan_table->ucFanTableFormat) { + hwmgr->thermal_controller.advanceFanControlParameters.ucTHyst = + fan_table->ucTHyst; + hwmgr->thermal_controller.advanceFanControlParameters.usTMin = + le16_to_cpu(fan_table->usTMin); + hwmgr->thermal_controller.advanceFanControlParameters.usTMed = + le16_to_cpu(fan_table->usTMed); + hwmgr->thermal_controller.advanceFanControlParameters.usTHigh = + le16_to_cpu(fan_table->usTHigh); + hwmgr->thermal_controller.advanceFanControlParameters.usPWMMin = + le16_to_cpu(fan_table->usPWMMin); + hwmgr->thermal_controller.advanceFanControlParameters.usPWMMed = + le16_to_cpu(fan_table->usPWMMed); + hwmgr->thermal_controller.advanceFanControlParameters.usPWMHigh = + le16_to_cpu(fan_table->usPWMHigh); + hwmgr->thermal_controller.advanceFanControlParameters.usTMax = 10900; + hwmgr->thermal_controller.advanceFanControlParameters.ulCycleDelay = 100000; + + phm_cap_set(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_MicrocodeFanControl); + } + + if (2 <= fan_table->ucFanTableFormat) { + const ATOM_PPLIB_FANTABLE2 *fan_table2 = + (const ATOM_PPLIB_FANTABLE2 *)(((unsigned long)powerplay_table) + + le16_to_cpu(powerplay_table3->usFanTableOffset)); + hwmgr->thermal_controller.advanceFanControlParameters.usTMax = + le16_to_cpu(fan_table2->usTMax); + } + + if (3 <= fan_table->ucFanTableFormat) { + const ATOM_PPLIB_FANTABLE3 *fan_table3 = + (const ATOM_PPLIB_FANTABLE3 *) (((unsigned long)powerplay_table) + + le16_to_cpu(powerplay_table3->usFanTableOffset)); + + hwmgr->thermal_controller.advanceFanControlParameters.ucFanControlMode = + fan_table3->ucFanControlMode; + + if ((3 == fan_table->ucFanTableFormat) && + (0x67B1 == adev->pdev->device)) + hwmgr->thermal_controller.advanceFanControlParameters.usDefaultMaxFanPWM = + 47; + else + hwmgr->thermal_controller.advanceFanControlParameters.usDefaultMaxFanPWM = + le16_to_cpu(fan_table3->usFanPWMMax); + + hwmgr->thermal_controller.advanceFanControlParameters.usDefaultFanOutputSensitivity = + 4836; + hwmgr->thermal_controller.advanceFanControlParameters.usFanOutputSensitivity = + le16_to_cpu(fan_table3->usFanOutputSensitivity); + } + + if (6 <= fan_table->ucFanTableFormat) { + const ATOM_PPLIB_FANTABLE4 *fan_table4 = + (const ATOM_PPLIB_FANTABLE4 *)(((unsigned long)powerplay_table) + + le16_to_cpu(powerplay_table3->usFanTableOffset)); + + phm_cap_set(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_FanSpeedInTableIsRPM); + + hwmgr->thermal_controller.advanceFanControlParameters.usDefaultMaxFanRPM = + le16_to_cpu(fan_table4->usFanRPMMax); + } + + if (7 <= fan_table->ucFanTableFormat) { + const ATOM_PPLIB_FANTABLE5 *fan_table5 = + (const ATOM_PPLIB_FANTABLE5 *)(((unsigned long)powerplay_table) + + le16_to_cpu(powerplay_table3->usFanTableOffset)); + + if (0x67A2 == adev->pdev->device || + 0x67A9 == adev->pdev->device || + 0x67B9 == adev->pdev->device) { + phm_cap_set(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_GeminiRegulatorFanControlSupport); + hwmgr->thermal_controller.advanceFanControlParameters.usFanCurrentLow = + le16_to_cpu(fan_table5->usFanCurrentLow); + hwmgr->thermal_controller.advanceFanControlParameters.usFanCurrentHigh = + le16_to_cpu(fan_table5->usFanCurrentHigh); + hwmgr->thermal_controller.advanceFanControlParameters.usFanRPMLow = + le16_to_cpu(fan_table5->usFanRPMLow); + hwmgr->thermal_controller.advanceFanControlParameters.usFanRPMHigh = + le16_to_cpu(fan_table5->usFanRPMHigh); + } + } + } + } return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index cf60f3992303..e6f40ee9f313 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -1297,15 +1297,9 @@ static int conv_power_profile_to_pplib_workload(int power_profile) int pplib_workload = 0; switch (power_profile) { - case PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT: - pplib_workload = WORKLOAD_DEFAULT_BIT; - break; case PP_SMC_POWER_PROFILE_FULLSCREEN3D: pplib_workload = WORKLOAD_PPLIB_FULL_SCREEN_3D_BIT; break; - case PP_SMC_POWER_PROFILE_POWERSAVING: - pplib_workload = WORKLOAD_PPLIB_POWER_SAVING_BIT; - break; case PP_SMC_POWER_PROFILE_VIDEO: pplib_workload = WORKLOAD_PPLIB_VIDEO_BIT; break; @@ -1315,6 +1309,9 @@ static int conv_power_profile_to_pplib_workload(int power_profile) case PP_SMC_POWER_PROFILE_COMPUTE: pplib_workload = WORKLOAD_PPLIB_COMPUTE_BIT; break; + case PP_SMC_POWER_PROFILE_CUSTOM: + pplib_workload = WORKLOAD_PPLIB_CUSTOM_BIT; + break; } return pplib_workload; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 895d89bea7fa..cf7c4f0e0a0b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -217,7 +217,7 @@ static struct cmn2asic_mapping sienna_cichlid_workload_map[PP_SMC_POWER_PROFILE_ WORKLOAD_MAP(PP_SMC_POWER_PROFILE_POWERSAVING, WORKLOAD_PPLIB_POWER_SAVING_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO, WORKLOAD_PPLIB_VIDEO_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR, WORKLOAD_PPLIB_VR_BIT), - WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_CUSTOM_BIT), + WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_COMPUTE_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT), }; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index 2380759ddf48..6db96fa1df09 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -1164,7 +1164,12 @@ int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu, if (ret) return ret; - crystal_clock_freq = amdgpu_asic_get_xclk(adev); + /* + * crystal_clock_freq div by 4 is required since the fan control + * module refers to 25MHz + */ + + crystal_clock_freq = amdgpu_asic_get_xclk(adev) / 4; tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed); WREG32_SOC15(THM, 0, mmCG_TACH_CTRL, REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_TACH_CTRL), diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 834a156e3a75..0a1e1cf57e19 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -742,7 +742,6 @@ static void ast_crtc_dpms(struct drm_crtc *crtc, int mode) case DRM_MODE_DPMS_SUSPEND: if (ast->tx_chip_type == AST_TX_DP501) ast_set_dp501_video_output(crtc->dev, 1); - ast_crtc_load_lut(ast, crtc); break; case DRM_MODE_DPMS_OFF: if (ast->tx_chip_type == AST_TX_DP501) @@ -778,6 +777,21 @@ static int ast_crtc_helper_atomic_check(struct drm_crtc *crtc, } static void +ast_crtc_helper_atomic_flush(struct drm_crtc *crtc, struct drm_crtc_state *old_crtc_state) +{ + struct ast_private *ast = to_ast_private(crtc->dev); + struct ast_crtc_state *ast_crtc_state = to_ast_crtc_state(crtc->state); + struct ast_crtc_state *old_ast_crtc_state = to_ast_crtc_state(old_crtc_state); + + /* + * The gamma LUT has to be reloaded after changing the primary + * plane's color format. + */ + if (old_ast_crtc_state->format != ast_crtc_state->format) + ast_crtc_load_lut(ast, crtc); +} + +static void ast_crtc_helper_atomic_enable(struct drm_crtc *crtc, struct drm_crtc_state *old_crtc_state) { @@ -830,6 +844,7 @@ ast_crtc_helper_atomic_disable(struct drm_crtc *crtc, static const struct drm_crtc_helper_funcs ast_crtc_helper_funcs = { .atomic_check = ast_crtc_helper_atomic_check, + .atomic_flush = ast_crtc_helper_atomic_flush, .atomic_enable = ast_crtc_helper_atomic_enable, .atomic_disable = ast_crtc_helper_atomic_disable, }; diff --git a/drivers/gpu/drm/bridge/cadence/Kconfig b/drivers/gpu/drm/bridge/cadence/Kconfig index 511d67b16d14..ef8c230e0f62 100644 --- a/drivers/gpu/drm/bridge/cadence/Kconfig +++ b/drivers/gpu/drm/bridge/cadence/Kconfig @@ -13,7 +13,7 @@ config DRM_CDNS_MHDP8546 if DRM_CDNS_MHDP8546 config DRM_CDNS_MHDP8546_J721E - depends on ARCH_K3_J721E_SOC || COMPILE_TEST + depends on ARCH_K3 || COMPILE_TEST bool "J721E Cadence DPI/DP wrapper support" default y help diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index 748df1cacd2b..0c79a9ba48bb 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -2327,12 +2327,6 @@ static enum drm_connector_status dw_hdmi_detect(struct dw_hdmi *hdmi) { enum drm_connector_status result; - mutex_lock(&hdmi->mutex); - hdmi->force = DRM_FORCE_UNSPECIFIED; - dw_hdmi_update_power(hdmi); - dw_hdmi_update_phy_mask(hdmi); - mutex_unlock(&hdmi->mutex); - result = hdmi->phy.ops->read_hpd(hdmi, hdmi->phy.data); mutex_lock(&hdmi->mutex); diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 50cad0e4a92e..375c79e23ca5 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -140,7 +140,7 @@ static void drm_gem_vram_placement(struct drm_gem_vram_object *gbo, unsigned int c = 0; if (pl_flag & DRM_GEM_VRAM_PL_FLAG_TOPDOWN) - pl_flag = TTM_PL_FLAG_TOPDOWN; + invariant_flags = TTM_PL_FLAG_TOPDOWN; gbo->placement.placement = gbo->placements; gbo->placement.busy_placement = gbo->placements; diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig index 6417f374b923..951d5f708e92 100644 --- a/drivers/gpu/drm/exynos/Kconfig +++ b/drivers/gpu/drm/exynos/Kconfig @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only config DRM_EXYNOS tristate "DRM Support for Samsung SoC Exynos Series" - depends on OF && DRM && (ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM || COMPILE_TEST) + depends on OF && DRM && COMMON_CLK + depends on ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM || COMPILE_TEST depends on MMU select DRM_KMS_HELPER select VIDEOMODE_HELPERS diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c index 15eb3770d817..361e3a0c5ab6 100644 --- a/drivers/gpu/drm/gma500/psb_irq.c +++ b/drivers/gpu/drm/gma500/psb_irq.c @@ -347,6 +347,7 @@ int psb_irq_postinstall(struct drm_device *dev) { struct drm_psb_private *dev_priv = dev->dev_private; unsigned long irqflags; + unsigned int i; spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags); @@ -359,20 +360,12 @@ int psb_irq_postinstall(struct drm_device *dev) PSB_WVDC32(dev_priv->vdc_irq_mask, PSB_INT_ENABLE_R); PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM); - if (dev->vblank[0].enabled) - psb_enable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE); - else - psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE); - - if (dev->vblank[1].enabled) - psb_enable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE); - else - psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE); - - if (dev->vblank[2].enabled) - psb_enable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE); - else - psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE); + for (i = 0; i < dev->num_crtcs; ++i) { + if (dev->vblank[i].enabled) + psb_enable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); + else + psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); + } if (dev_priv->ops->hotplug_enable) dev_priv->ops->hotplug_enable(dev, true); @@ -385,6 +378,7 @@ void psb_irq_uninstall(struct drm_device *dev) { struct drm_psb_private *dev_priv = dev->dev_private; unsigned long irqflags; + unsigned int i; spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags); @@ -393,14 +387,10 @@ void psb_irq_uninstall(struct drm_device *dev) PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM); - if (dev->vblank[0].enabled) - psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE); - - if (dev->vblank[1].enabled) - psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE); - - if (dev->vblank[2].enabled) - psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE); + for (i = 0; i < dev->num_crtcs; ++i) { + if (dev->vblank[i].enabled) + psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); + } dev_priv->vdc_irq_mask &= _PSB_IRQ_SGX_FLAG | _PSB_IRQ_MSVDX_FLAG | diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 023aa3ebca3c..4bd51b794a30 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -12878,10 +12878,11 @@ compute_sink_pipe_bpp(const struct drm_connector_state *conn_state, case 10 ... 11: bpp = 10 * 3; break; - case 12: + case 12 ... 16: bpp = 12 * 3; break; default: + MISSING_CASE(conn_state->max_bpc); return -EINVAL; } @@ -18020,16 +18021,6 @@ int intel_modeset_init_nogem(struct drm_i915_private *i915) if (!HAS_GMCH(i915)) sanitize_watermarks(i915); - /* - * Force all active planes to recompute their states. So that on - * mode_setcrtc after probe, all the intel_plane_state variables - * are already calculated and there is no assert_plane warnings - * during bootup. - */ - ret = intel_initial_commit(dev); - if (ret) - drm_dbg_kms(&i915->drm, "Initial commit in probe failed.\n"); - return 0; } @@ -18038,11 +18029,21 @@ int intel_modeset_init(struct drm_i915_private *i915) { int ret; - intel_overlay_setup(i915); - if (!HAS_DISPLAY(i915)) return 0; + /* + * Force all active planes to recompute their states. So that on + * mode_setcrtc after probe, all the intel_plane_state variables + * are already calculated and there is no assert_plane warnings + * during bootup. + */ + ret = intel_initial_commit(&i915->drm); + if (ret) + drm_dbg_kms(&i915->drm, "Initial modeset failed, %d\n", ret); + + intel_overlay_setup(i915); + ret = intel_fbdev_init(&i915->drm); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index bf1e9cf1c0f3..9bc59fd2f95f 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -573,7 +573,7 @@ static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, return 0; } /* Also take into account max slice width */ - min_slice_count = min_t(u8, min_slice_count, + min_slice_count = max_t(u8, min_slice_count, DIV_ROUND_UP(mode_hdisplay, max_slice_width)); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 1904e6e5ea64..b07dc1156a0e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -3097,7 +3097,7 @@ static void retire_requests(struct intel_timeline *tl, struct i915_request *end) break; } -static void eb_request_add(struct i915_execbuffer *eb) +static int eb_request_add(struct i915_execbuffer *eb, int err) { struct i915_request *rq = eb->request; struct intel_timeline * const tl = i915_request_timeline(rq); @@ -3118,6 +3118,7 @@ static void eb_request_add(struct i915_execbuffer *eb) /* Serialise with context_close via the add_to_timeline */ i915_request_set_error_once(rq, -ENOENT); __i915_request_skip(rq); + err = -ENOENT; /* override any transient errors */ } __i915_request_queue(rq, &attr); @@ -3127,6 +3128,8 @@ static void eb_request_add(struct i915_execbuffer *eb) retire_requests(tl, prev); mutex_unlock(&tl->mutex); + + return err; } static const i915_user_extension_fn execbuf_extensions[] = { @@ -3332,7 +3335,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, err = eb_submit(&eb, batch); err_request: i915_request_get(eb.request); - eb_request_add(&eb); + err = eb_request_add(&eb, err); if (eb.fences) signal_fence_array(&eb); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index b5c15557cc87..d6711caa7f39 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -56,6 +56,8 @@ struct drm_i915_gem_object_ops { void (*truncate)(struct drm_i915_gem_object *obj); void (*writeback)(struct drm_i915_gem_object *obj); + int (*pread)(struct drm_i915_gem_object *obj, + const struct drm_i915_gem_pread *arg); int (*pwrite)(struct drm_i915_gem_object *obj, const struct drm_i915_gem_pwrite *arg); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c index 28147aab47b9..3a4dfe2ef1da 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c @@ -134,6 +134,58 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj, vaddr, dma); } +static int +phys_pwrite(struct drm_i915_gem_object *obj, + const struct drm_i915_gem_pwrite *args) +{ + void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; + char __user *user_data = u64_to_user_ptr(args->data_ptr); + int err; + + err = i915_gem_object_wait(obj, + I915_WAIT_INTERRUPTIBLE | + I915_WAIT_ALL, + MAX_SCHEDULE_TIMEOUT); + if (err) + return err; + + /* + * We manually control the domain here and pretend that it + * remains coherent i.e. in the GTT domain, like shmem_pwrite. + */ + i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU); + + if (copy_from_user(vaddr, user_data, args->size)) + return -EFAULT; + + drm_clflush_virt_range(vaddr, args->size); + intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt); + + i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); + return 0; +} + +static int +phys_pread(struct drm_i915_gem_object *obj, + const struct drm_i915_gem_pread *args) +{ + void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; + char __user *user_data = u64_to_user_ptr(args->data_ptr); + int err; + + err = i915_gem_object_wait(obj, + I915_WAIT_INTERRUPTIBLE, + MAX_SCHEDULE_TIMEOUT); + if (err) + return err; + + drm_clflush_virt_range(vaddr, args->size); + if (copy_to_user(user_data, vaddr, args->size)) + return -EFAULT; + + return 0; +} + static void phys_release(struct drm_i915_gem_object *obj) { fput(obj->base.filp); @@ -144,6 +196,9 @@ static const struct drm_i915_gem_object_ops i915_gem_phys_ops = { .get_pages = i915_gem_object_get_pages_phys, .put_pages = i915_gem_object_put_pages_phys, + .pread = phys_pread, + .pwrite = phys_pwrite, + .release = phys_release, }; diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index d8b206e53660..a24cc1ff08a0 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -30,18 +30,21 @@ #include "i915_trace.h" #include "intel_breadcrumbs.h" #include "intel_context.h" +#include "intel_engine_pm.h" #include "intel_gt_pm.h" #include "intel_gt_requests.h" -static void irq_enable(struct intel_engine_cs *engine) +static bool irq_enable(struct intel_engine_cs *engine) { if (!engine->irq_enable) - return; + return false; /* Caller disables interrupts */ spin_lock(&engine->gt->irq_lock); engine->irq_enable(engine); spin_unlock(&engine->gt->irq_lock); + + return true; } static void irq_disable(struct intel_engine_cs *engine) @@ -57,12 +60,11 @@ static void irq_disable(struct intel_engine_cs *engine) static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b) { - lockdep_assert_held(&b->irq_lock); - - if (!b->irq_engine || b->irq_armed) - return; - - if (!intel_gt_pm_get_if_awake(b->irq_engine->gt)) + /* + * Since we are waiting on a request, the GPU should be busy + * and should have its own rpm reference. + */ + if (GEM_WARN_ON(!intel_gt_pm_get_if_awake(b->irq_engine->gt))) return; /* @@ -73,25 +75,24 @@ static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b) */ WRITE_ONCE(b->irq_armed, true); - /* - * Since we are waiting on a request, the GPU should be busy - * and should have its own rpm reference. This is tracked - * by i915->gt.awake, we can forgo holding our own wakref - * for the interrupt as before i915->gt.awake is released (when - * the driver is idle) we disarm the breadcrumbs. - */ - - if (!b->irq_enabled++) - irq_enable(b->irq_engine); + /* Requests may have completed before we could enable the interrupt. */ + if (!b->irq_enabled++ && irq_enable(b->irq_engine)) + irq_work_queue(&b->irq_work); } -static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) +static void intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b) { - lockdep_assert_held(&b->irq_lock); - - if (!b->irq_engine || !b->irq_armed) + if (!b->irq_engine) return; + spin_lock(&b->irq_lock); + if (!b->irq_armed) + __intel_breadcrumbs_arm_irq(b); + spin_unlock(&b->irq_lock); +} + +static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) +{ GEM_BUG_ON(!b->irq_enabled); if (!--b->irq_enabled) irq_disable(b->irq_engine); @@ -100,20 +101,37 @@ static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) intel_gt_pm_put_async(b->irq_engine->gt); } +static void intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) +{ + spin_lock(&b->irq_lock); + if (b->irq_armed) + __intel_breadcrumbs_disarm_irq(b); + spin_unlock(&b->irq_lock); +} + static void add_signaling_context(struct intel_breadcrumbs *b, struct intel_context *ce) { - intel_context_get(ce); - list_add_tail(&ce->signal_link, &b->signalers); - if (list_is_first(&ce->signal_link, &b->signalers)) - __intel_breadcrumbs_arm_irq(b); + lockdep_assert_held(&ce->signal_lock); + + spin_lock(&b->signalers_lock); + list_add_rcu(&ce->signal_link, &b->signalers); + spin_unlock(&b->signalers_lock); } -static void remove_signaling_context(struct intel_breadcrumbs *b, +static bool remove_signaling_context(struct intel_breadcrumbs *b, struct intel_context *ce) { - list_del(&ce->signal_link); - intel_context_put(ce); + lockdep_assert_held(&ce->signal_lock); + + if (!list_empty(&ce->signals)) + return false; + + spin_lock(&b->signalers_lock); + list_del_rcu(&ce->signal_link); + spin_unlock(&b->signalers_lock); + + return true; } static inline bool __request_completed(const struct i915_request *rq) @@ -174,73 +192,103 @@ static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl) intel_engine_add_retire(b->irq_engine, tl); } -static bool __signal_request(struct i915_request *rq, struct list_head *signals) +static bool __signal_request(struct i915_request *rq) { - clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); + GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)); if (!__dma_fence_signal(&rq->fence)) { i915_request_put(rq); return false; } - list_add_tail(&rq->signal_link, signals); return true; } +static struct llist_node * +slist_add(struct llist_node *node, struct llist_node *head) +{ + node->next = head; + return node; +} + static void signal_irq_work(struct irq_work *work) { struct intel_breadcrumbs *b = container_of(work, typeof(*b), irq_work); const ktime_t timestamp = ktime_get(); - struct intel_context *ce, *cn; - struct list_head *pos, *next; - LIST_HEAD(signal); - - spin_lock(&b->irq_lock); + struct llist_node *signal, *sn; + struct intel_context *ce; - if (list_empty(&b->signalers)) - __intel_breadcrumbs_disarm_irq(b); + signal = NULL; + if (unlikely(!llist_empty(&b->signaled_requests))) + signal = llist_del_all(&b->signaled_requests); - list_splice_init(&b->signaled_requests, &signal); + /* + * Keep the irq armed until the interrupt after all listeners are gone. + * + * Enabling/disabling the interrupt is rather costly, roughly a couple + * of hundred microseconds. If we are proactive and enable/disable + * the interrupt around every request that wants a breadcrumb, we + * quickly drown in the extra orders of magnitude of latency imposed + * on request submission. + * + * So we try to be lazy, and keep the interrupts enabled until no + * more listeners appear within a breadcrumb interrupt interval (that + * is until a request completes that no one cares about). The + * observation is that listeners come in batches, and will often + * listen to a bunch of requests in succession. Though note on icl+, + * interrupts are always enabled due to concerns with rc6 being + * dysfunctional with per-engine interrupt masking. + * + * We also try to avoid raising too many interrupts, as they may + * be generated by userspace batches and it is unfortunately rather + * too easy to drown the CPU under a flood of GPU interrupts. Thus + * whenever no one appears to be listening, we turn off the interrupts. + * Fewer interrupts should conserve power -- at the very least, fewer + * interrupt draw less ire from other users of the system and tools + * like powertop. + */ + if (!signal && READ_ONCE(b->irq_armed) && list_empty(&b->signalers)) + intel_breadcrumbs_disarm_irq(b); - list_for_each_entry_safe(ce, cn, &b->signalers, signal_link) { - GEM_BUG_ON(list_empty(&ce->signals)); + rcu_read_lock(); + list_for_each_entry_rcu(ce, &b->signalers, signal_link) { + struct i915_request *rq; - list_for_each_safe(pos, next, &ce->signals) { - struct i915_request *rq = - list_entry(pos, typeof(*rq), signal_link); + list_for_each_entry_rcu(rq, &ce->signals, signal_link) { + bool release; - GEM_BUG_ON(!check_signal_order(ce, rq)); if (!__request_completed(rq)) break; + if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, + &rq->fence.flags)) + break; + /* * Queue for execution after dropping the signaling * spinlock as the callback chain may end up adding * more signalers to the same context or engine. */ - __signal_request(rq, &signal); - } + spin_lock(&ce->signal_lock); + list_del_rcu(&rq->signal_link); + release = remove_signaling_context(b, ce); + spin_unlock(&ce->signal_lock); - /* - * We process the list deletion in bulk, only using a list_add - * (not list_move) above but keeping the status of - * rq->signal_link known with the I915_FENCE_FLAG_SIGNAL bit. - */ - if (!list_is_first(pos, &ce->signals)) { - /* Advance the list to the first incomplete request */ - __list_del_many(&ce->signals, pos); - if (&ce->signals == pos) { /* now empty */ + if (__signal_request(rq)) + /* We own signal_node now, xfer to local list */ + signal = slist_add(&rq->signal_node, signal); + + if (release) { add_retire(b, ce->timeline); - remove_signaling_context(b, ce); + intel_context_put(ce); } } } + rcu_read_unlock(); - spin_unlock(&b->irq_lock); - - list_for_each_safe(pos, next, &signal) { + llist_for_each_safe(signal, sn, signal) { struct i915_request *rq = - list_entry(pos, typeof(*rq), signal_link); + llist_entry(signal, typeof(*rq), signal_node); struct list_head cb_list; spin_lock(&rq->lock); @@ -251,6 +299,9 @@ static void signal_irq_work(struct irq_work *work) i915_request_put(rq); } + + if (!READ_ONCE(b->irq_armed) && !list_empty(&b->signalers)) + intel_breadcrumbs_arm_irq(b); } struct intel_breadcrumbs * @@ -262,14 +313,15 @@ intel_breadcrumbs_create(struct intel_engine_cs *irq_engine) if (!b) return NULL; - spin_lock_init(&b->irq_lock); + b->irq_engine = irq_engine; + + spin_lock_init(&b->signalers_lock); INIT_LIST_HEAD(&b->signalers); - INIT_LIST_HEAD(&b->signaled_requests); + init_llist_head(&b->signaled_requests); + spin_lock_init(&b->irq_lock); init_irq_work(&b->irq_work, signal_irq_work); - b->irq_engine = irq_engine; - return b; } @@ -292,27 +344,28 @@ void intel_breadcrumbs_reset(struct intel_breadcrumbs *b) void intel_breadcrumbs_park(struct intel_breadcrumbs *b) { - unsigned long flags; - - if (!READ_ONCE(b->irq_armed)) - return; - - spin_lock_irqsave(&b->irq_lock, flags); - __intel_breadcrumbs_disarm_irq(b); - spin_unlock_irqrestore(&b->irq_lock, flags); - - if (!list_empty(&b->signalers)) - irq_work_queue(&b->irq_work); + /* Kick the work once more to drain the signalers */ + irq_work_sync(&b->irq_work); + while (unlikely(READ_ONCE(b->irq_armed))) { + local_irq_disable(); + signal_irq_work(&b->irq_work); + local_irq_enable(); + cond_resched(); + } + GEM_BUG_ON(!list_empty(&b->signalers)); } void intel_breadcrumbs_free(struct intel_breadcrumbs *b) { + irq_work_sync(&b->irq_work); + GEM_BUG_ON(!list_empty(&b->signalers)); + GEM_BUG_ON(b->irq_armed); kfree(b); } -static void insert_breadcrumb(struct i915_request *rq, - struct intel_breadcrumbs *b) +static void insert_breadcrumb(struct i915_request *rq) { + struct intel_breadcrumbs *b = READ_ONCE(rq->engine)->breadcrumbs; struct intel_context *ce = rq->context; struct list_head *pos; @@ -327,12 +380,14 @@ static void insert_breadcrumb(struct i915_request *rq, * its signal completion. */ if (__request_completed(rq)) { - if (__signal_request(rq, &b->signaled_requests)) + if (__signal_request(rq) && + llist_add(&rq->signal_node, &b->signaled_requests)) irq_work_queue(&b->irq_work); return; } if (list_empty(&ce->signals)) { + intel_context_get(ce); add_signaling_context(b, ce); pos = &ce->signals; } else { @@ -358,18 +413,22 @@ static void insert_breadcrumb(struct i915_request *rq, break; } } - list_add(&rq->signal_link, pos); + list_add_rcu(&rq->signal_link, pos); GEM_BUG_ON(!check_signal_order(ce, rq)); + GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags)); set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); - /* Check after attaching to irq, interrupt may have already fired. */ - if (__request_completed(rq)) - irq_work_queue(&b->irq_work); + /* + * Defer enabling the interrupt to after HW submission and recheck + * the request as it may have completed and raised the interrupt as + * we were attaching it into the lists. + */ + irq_work_queue(&b->irq_work); } bool i915_request_enable_breadcrumb(struct i915_request *rq) { - struct intel_breadcrumbs *b; + struct intel_context *ce = rq->context; /* Serialises with i915_request_retire() using rq->lock */ if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags)) @@ -384,67 +443,30 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq) if (!test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) return true; - /* - * rq->engine is locked by rq->engine->active.lock. That however - * is not known until after rq->engine has been dereferenced and - * the lock acquired. Hence we acquire the lock and then validate - * that rq->engine still matches the lock we hold for it. - * - * Here, we are using the breadcrumb lock as a proxy for the - * rq->engine->active.lock, and we know that since the breadcrumb - * will be serialised within i915_request_submit/i915_request_unsubmit, - * the engine cannot change while active as long as we hold the - * breadcrumb lock on that engine. - * - * From the dma_fence_enable_signaling() path, we are outside of the - * request submit/unsubmit path, and so we must be more careful to - * acquire the right lock. - */ - b = READ_ONCE(rq->engine)->breadcrumbs; - spin_lock(&b->irq_lock); - while (unlikely(b != READ_ONCE(rq->engine)->breadcrumbs)) { - spin_unlock(&b->irq_lock); - b = READ_ONCE(rq->engine)->breadcrumbs; - spin_lock(&b->irq_lock); - } - - /* - * Now that we are finally serialised with request submit/unsubmit, - * [with b->irq_lock] and with i915_request_retire() [via checking - * SIGNALED with rq->lock] confirm the request is indeed active. If - * it is no longer active, the breadcrumb will be attached upon - * i915_request_submit(). - */ + spin_lock(&ce->signal_lock); if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) - insert_breadcrumb(rq, b); - - spin_unlock(&b->irq_lock); + insert_breadcrumb(rq); + spin_unlock(&ce->signal_lock); return true; } void i915_request_cancel_breadcrumb(struct i915_request *rq) { - struct intel_breadcrumbs *b = rq->engine->breadcrumbs; + struct intel_context *ce = rq->context; + bool release; - /* - * We must wait for b->irq_lock so that we know the interrupt handler - * has released its reference to the intel_context and has completed - * the DMA_FENCE_FLAG_SIGNALED_BIT/I915_FENCE_FLAG_SIGNAL dance (if - * required). - */ - spin_lock(&b->irq_lock); - if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) { - struct intel_context *ce = rq->context; + if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) + return; - list_del(&rq->signal_link); - if (list_empty(&ce->signals)) - remove_signaling_context(b, ce); + spin_lock(&ce->signal_lock); + list_del_rcu(&rq->signal_link); + release = remove_signaling_context(rq->engine->breadcrumbs, ce); + spin_unlock(&ce->signal_lock); + if (release) + intel_context_put(ce); - clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); - i915_request_put(rq); - } - spin_unlock(&b->irq_lock); + i915_request_put(rq); } static void print_signals(struct intel_breadcrumbs *b, struct drm_printer *p) @@ -454,18 +476,17 @@ static void print_signals(struct intel_breadcrumbs *b, struct drm_printer *p) drm_printf(p, "Signals:\n"); - spin_lock_irq(&b->irq_lock); - list_for_each_entry(ce, &b->signalers, signal_link) { - list_for_each_entry(rq, &ce->signals, signal_link) { + rcu_read_lock(); + list_for_each_entry_rcu(ce, &b->signalers, signal_link) { + list_for_each_entry_rcu(rq, &ce->signals, signal_link) drm_printf(p, "\t[%llx:%llx%s] @ %dms\n", rq->fence.context, rq->fence.seqno, i915_request_completed(rq) ? "!" : i915_request_started(rq) ? "*" : "", jiffies_to_msecs(jiffies - rq->emitted_jiffies)); - } } - spin_unlock_irq(&b->irq_lock); + rcu_read_unlock(); } void intel_engine_print_breadcrumbs(struct intel_engine_cs *engine, diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h index 8e53b9942695..a74bb3062bd8 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h @@ -29,18 +29,16 @@ * the overhead of waking that client is much preferred. */ struct intel_breadcrumbs { - spinlock_t irq_lock; /* protects the lists used in hardirq context */ - /* Not all breadcrumbs are attached to physical HW */ struct intel_engine_cs *irq_engine; + spinlock_t signalers_lock; /* protects the list of signalers */ struct list_head signalers; - struct list_head signaled_requests; + struct llist_head signaled_requests; + spinlock_t irq_lock; /* protects the interrupt from hardirq context */ struct irq_work irq_work; /* for use from inside irq_lock */ - unsigned int irq_enabled; - bool irq_armed; }; diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 92a3f25c4006..349e7fa1488d 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -25,11 +25,18 @@ static struct intel_context *intel_context_alloc(void) return kmem_cache_zalloc(global.slab_ce, GFP_KERNEL); } -void intel_context_free(struct intel_context *ce) +static void rcu_context_free(struct rcu_head *rcu) { + struct intel_context *ce = container_of(rcu, typeof(*ce), rcu); + kmem_cache_free(global.slab_ce, ce); } +void intel_context_free(struct intel_context *ce) +{ + call_rcu(&ce->rcu, rcu_context_free); +} + struct intel_context * intel_context_create(struct intel_engine_cs *engine) { @@ -356,8 +363,7 @@ static int __intel_context_active(struct i915_active *active) } void -intel_context_init(struct intel_context *ce, - struct intel_engine_cs *engine) +intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine) { GEM_BUG_ON(!engine->cops); GEM_BUG_ON(!engine->gt->vm); @@ -373,7 +379,8 @@ intel_context_init(struct intel_context *ce, ce->vm = i915_vm_get(engine->gt->vm); - INIT_LIST_HEAD(&ce->signal_link); + /* NB ce->signal_link/lock is used under RCU */ + spin_lock_init(&ce->signal_lock); INIT_LIST_HEAD(&ce->signals); mutex_init(&ce->pin_mutex); diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 552cb57a2e8c..52fa9c132746 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -25,6 +25,7 @@ DECLARE_EWMA(runtime, 3, 8); struct i915_gem_context; struct i915_gem_ww_ctx; struct i915_vma; +struct intel_breadcrumbs; struct intel_context; struct intel_ring; @@ -44,7 +45,16 @@ struct intel_context_ops { }; struct intel_context { - struct kref ref; + /* + * Note: Some fields may be accessed under RCU. + * + * Unless otherwise noted a field can safely be assumed to be protected + * by strong reference counting. + */ + union { + struct kref ref; /* no kref_get_unless_zero()! */ + struct rcu_head rcu; + }; struct intel_engine_cs *engine; struct intel_engine_cs *inflight; @@ -54,8 +64,15 @@ struct intel_context { struct i915_address_space *vm; struct i915_gem_context __rcu *gem_context; - struct list_head signal_link; - struct list_head signals; + /* + * @signal_lock protects the list of requests that need signaling, + * @signals. While there are any requests that need signaling, + * we add the context to the breadcrumbs worker, and remove it + * upon completion/cancellation of the last request. + */ + struct list_head signal_link; /* Accessed under RCU */ + struct list_head signals; /* Guarded by signal_lock */ + spinlock_t signal_lock; /* protects signals, the list of requests */ struct i915_vma *state; struct intel_ring *ring; diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 5bfb5f7ed02c..efdeb7b7b2a0 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -371,7 +371,8 @@ static void __setup_engine_capabilities(struct intel_engine_cs *engine) * instances. */ if ((INTEL_GEN(i915) >= 11 && - engine->gt->info.vdbox_sfc_access & engine->mask) || + (engine->gt->info.vdbox_sfc_access & + BIT(engine->instance))) || (INTEL_GEN(i915) >= 9 && engine->instance == 0)) engine->uabi_capabilities |= I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC; diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index f82c6dd1de18..724b2cb897d3 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -182,6 +182,7 @@ struct virtual_engine { struct intel_engine_cs base; struct intel_context context; + struct rcu_work rcu; /* * We allow only a single request through the virtual engine at a time @@ -2787,6 +2788,9 @@ static void __execlists_hold(struct i915_request *rq) static bool execlists_hold(struct intel_engine_cs *engine, struct i915_request *rq) { + if (i915_request_on_hold(rq)) + return false; + spin_lock_irq(&engine->active.lock); if (i915_request_completed(rq)) { /* too late! */ @@ -3168,8 +3172,10 @@ static void execlists_submission_tasklet(unsigned long data) spin_unlock_irqrestore(&engine->active.lock, flags); /* Recheck after serialising with direct-submission */ - if (unlikely(timeout && preempt_timeout(engine))) + if (unlikely(timeout && preempt_timeout(engine))) { + cancel_timer(&engine->execlists.preempt); execlists_reset(engine, "preemption time out"); + } } } @@ -5425,44 +5431,90 @@ static struct list_head *virtual_queue(struct virtual_engine *ve) return &ve->base.execlists.default_priolist.requests[0]; } -static void virtual_context_destroy(struct kref *kref) +static void rcu_virtual_context_destroy(struct work_struct *wrk) { struct virtual_engine *ve = - container_of(kref, typeof(*ve), context.ref); + container_of(wrk, typeof(*ve), rcu.work); unsigned int n; - GEM_BUG_ON(!list_empty(virtual_queue(ve))); - GEM_BUG_ON(ve->request); GEM_BUG_ON(ve->context.inflight); + /* Preempt-to-busy may leave a stale request behind. */ + if (unlikely(ve->request)) { + struct i915_request *old; + + spin_lock_irq(&ve->base.active.lock); + + old = fetch_and_zero(&ve->request); + if (old) { + GEM_BUG_ON(!i915_request_completed(old)); + __i915_request_submit(old); + i915_request_put(old); + } + + spin_unlock_irq(&ve->base.active.lock); + } + + /* + * Flush the tasklet in case it is still running on another core. + * + * This needs to be done before we remove ourselves from the siblings' + * rbtrees as in the case it is running in parallel, it may reinsert + * the rb_node into a sibling. + */ + tasklet_kill(&ve->base.execlists.tasklet); + + /* Decouple ourselves from the siblings, no more access allowed. */ for (n = 0; n < ve->num_siblings; n++) { struct intel_engine_cs *sibling = ve->siblings[n]; struct rb_node *node = &ve->nodes[sibling->id].rb; - unsigned long flags; if (RB_EMPTY_NODE(node)) continue; - spin_lock_irqsave(&sibling->active.lock, flags); + spin_lock_irq(&sibling->active.lock); /* Detachment is lazily performed in the execlists tasklet */ if (!RB_EMPTY_NODE(node)) rb_erase_cached(node, &sibling->execlists.virtual); - spin_unlock_irqrestore(&sibling->active.lock, flags); + spin_unlock_irq(&sibling->active.lock); } GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.execlists.tasklet)); + GEM_BUG_ON(!list_empty(virtual_queue(ve))); if (ve->context.state) __execlists_context_fini(&ve->context); intel_context_fini(&ve->context); + intel_breadcrumbs_free(ve->base.breadcrumbs); intel_engine_free_request_pool(&ve->base); kfree(ve->bonds); kfree(ve); } +static void virtual_context_destroy(struct kref *kref) +{ + struct virtual_engine *ve = + container_of(kref, typeof(*ve), context.ref); + + GEM_BUG_ON(!list_empty(&ve->context.signals)); + + /* + * When destroying the virtual engine, we have to be aware that + * it may still be in use from an hardirq/softirq context causing + * the resubmission of a completed request (background completion + * due to preempt-to-busy). Before we can free the engine, we need + * to flush the submission code and tasklets that are still potentially + * accessing the engine. Flushing the tasklets requires process context, + * and since we can guard the resubmit onto the engine with an RCU read + * lock, we can delegate the free of the engine to an RCU worker. + */ + INIT_RCU_WORK(&ve->rcu, rcu_virtual_context_destroy); + queue_rcu_work(system_wq, &ve->rcu); +} + static void virtual_engine_initial_hint(struct virtual_engine *ve) { int swp; diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index b8f56e62158e..413dadfac2d1 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -59,8 +59,7 @@ struct drm_i915_mocs_table { #define _L3_CACHEABILITY(value) ((value) << 4) /* Helper defines */ -#define GEN9_NUM_MOCS_ENTRIES 62 /* 62 out of 64 - 63 & 64 are reserved. */ -#define GEN11_NUM_MOCS_ENTRIES 64 /* 63-64 are reserved, but configured. */ +#define GEN9_NUM_MOCS_ENTRIES 64 /* 63-64 are reserved, but configured. */ /* (e)LLC caching options */ /* @@ -131,7 +130,19 @@ static const struct drm_i915_mocs_entry skl_mocs_table[] = { GEN9_MOCS_ENTRIES, MOCS_ENTRY(I915_MOCS_CACHED, LE_3_WB | LE_TC_2_LLC_ELLC | LE_LRUM(3), - L3_3_WB) + L3_3_WB), + + /* + * mocs:63 + * - used by the L3 for all of its evictions. + * Thus it is expected to allow LLC cacheability to enable coherent + * flows to be maintained. + * - used to force L3 uncachable cycles. + * Thus it is expected to make the surface L3 uncacheable. + */ + MOCS_ENTRY(63, + LE_3_WB | LE_TC_1_LLC | LE_LRUM(3), + L3_1_UC) }; /* NOTE: the LE_TGT_CACHE is not used on Broxton */ @@ -243,8 +254,9 @@ static const struct drm_i915_mocs_entry tgl_mocs_table[] = { * only, __init_mocs_table() take care to program unused index with * this entry. */ - MOCS_ENTRY(1, LE_3_WB | LE_TC_1_LLC | LE_LRUM(3), - L3_3_WB), + MOCS_ENTRY(I915_MOCS_PTE, + LE_0_PAGETABLE | LE_TC_0_PAGETABLE, + L3_1_UC), GEN11_MOCS_ENTRIES, /* Implicitly enable L1 - HDC:L1 + L3 + LLC */ @@ -315,11 +327,11 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915, if (INTEL_GEN(i915) >= 12) { table->size = ARRAY_SIZE(tgl_mocs_table); table->table = tgl_mocs_table; - table->n_entries = GEN11_NUM_MOCS_ENTRIES; + table->n_entries = GEN9_NUM_MOCS_ENTRIES; } else if (IS_GEN(i915, 11)) { table->size = ARRAY_SIZE(icl_mocs_table); table->table = icl_mocs_table; - table->n_entries = GEN11_NUM_MOCS_ENTRIES; + table->n_entries = GEN9_NUM_MOCS_ENTRIES; } else if (IS_GEN9_BC(i915) || IS_CANNONLAKE(i915)) { table->size = ARRAY_SIZE(skl_mocs_table); table->n_entries = GEN9_NUM_MOCS_ENTRIES; diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index ab675d35030d..d7b8e4457fc2 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -56,9 +56,12 @@ static inline void set(struct intel_uncore *uncore, i915_reg_t reg, u32 val) static void gen11_rc6_enable(struct intel_rc6 *rc6) { - struct intel_uncore *uncore = rc6_to_uncore(rc6); + struct intel_gt *gt = rc6_to_gt(rc6); + struct intel_uncore *uncore = gt->uncore; struct intel_engine_cs *engine; enum intel_engine_id id; + u32 pg_enable; + int i; /* 2b: Program RC6 thresholds.*/ set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85); @@ -102,10 +105,19 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6) GEN6_RC_CTL_RC6_ENABLE | GEN6_RC_CTL_EI_MODE(1); - set(uncore, GEN9_PG_ENABLE, - GEN9_RENDER_PG_ENABLE | - GEN9_MEDIA_PG_ENABLE | - GEN11_MEDIA_SAMPLER_PG_ENABLE); + pg_enable = + GEN9_RENDER_PG_ENABLE | + GEN9_MEDIA_PG_ENABLE | + GEN11_MEDIA_SAMPLER_PG_ENABLE; + + if (INTEL_GEN(gt->i915) >= 12) { + for (i = 0; i < I915_MAX_VCS; i++) + if (HAS_ENGINE(gt, _VCS(i))) + pg_enable |= (VDN_HCP_POWERGATE_ENABLE(i) | + VDN_MFX_POWERGATE_ENABLE(i)); + } + + set(uncore, GEN9_PG_ENABLE, pg_enable); } static void gen9_rc6_enable(struct intel_rc6 *rc6) diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index e6a00eea0631..c1c9cc0ad3b9 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -883,6 +883,10 @@ void intel_rps_park(struct intel_rps *rps) adj = -2; rps->last_adj = adj; rps->cur_freq = max_t(int, rps->cur_freq + adj, rps->min_freq); + if (rps->cur_freq < rps->efficient_freq) { + rps->cur_freq = rps->efficient_freq; + rps->last_adj = 0; + } GT_TRACE(rps_to_gt(rps), "park:%x\n", rps->cur_freq); } diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 6c580d0d9ea8..4a3bde7c9f21 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -131,8 +131,10 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) return; } - if (wal->list) + if (wal->list) { memcpy(list, wal->list, sizeof(*wa) * wal->count); + kfree(wal->list); + } wal->list = list; } diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c index f011ea42487e..5982b62f913d 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.c +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c @@ -73,7 +73,7 @@ void *shmem_pin_map(struct file *file) mapping_set_unevictable(file->f_mapping); return vaddr; err_page: - while (--i >= 0) + while (i--) put_page(pages[i]); kvfree(pages); return NULL; @@ -103,10 +103,13 @@ static int __shmem_rw(struct file *file, loff_t off, return PTR_ERR(page); vaddr = kmap(page); - if (write) + if (write) { memcpy(vaddr + offset_in_page(off), ptr, this); - else + set_page_dirty(page); + } else { memcpy(ptr, vaddr + offset_in_page(off), this); + } + mark_page_accessed(page); kunmap(page); put_page(page); diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index 7ba16ddfe75f..d7898e87791f 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -164,7 +164,7 @@ static unsigned char virtual_dp_monitor_edid[GVT_EDID_NUM][EDID_SIZE] = { /* let the virtual display supports DP1.2 */ static u8 dpcd_fix_data[DPCD_HEADER_SIZE] = { - 0x12, 0x014, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 + 0x12, 0x014, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; static void emulate_monitor_status_change(struct intel_vgpu *vgpu) diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 9831361f181e..a81cf0f01e78 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -255,7 +255,7 @@ struct intel_gvt_mmio { #define F_CMD_ACCESS (1 << 3) /* This reg has been accessed by a VM */ #define F_ACCESSED (1 << 4) -/* This reg has been accessed through GPU commands */ +/* This reg could be accessed by unaligned address */ #define F_UNALIGN (1 << 6) /* This reg is in GVT's mmio save-restor list and in hardware * logical context image diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index ad8a9df49f29..778eb8cab610 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -829,8 +829,10 @@ static int intel_vgpu_open(struct mdev_device *mdev) /* Take a module reference as mdev core doesn't take * a reference for vendor driver. */ - if (!try_module_get(THIS_MODULE)) + if (!try_module_get(THIS_MODULE)) { + ret = -ENODEV; goto undo_group; + } ret = kvmgt_guest_init(mdev); if (ret) diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index f6d7e33c7099..399582aeeefb 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -439,7 +439,8 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (IS_BROADWELL(dev_priv)) ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B); - else + /* FixMe: Re-enable APL/BXT once vfio_edid enabled */ + else if (!IS_BROXTON(dev_priv)) ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); if (ret) goto out_clean_sched_policy; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index bb0c12975f38..58276694c848 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -180,30 +180,6 @@ try_again: } static int -i915_gem_phys_pwrite(struct drm_i915_gem_object *obj, - struct drm_i915_gem_pwrite *args, - struct drm_file *file) -{ - void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; - char __user *user_data = u64_to_user_ptr(args->data_ptr); - - /* - * We manually control the domain here and pretend that it - * remains coherent i.e. in the GTT domain, like shmem_pwrite. - */ - i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU); - - if (copy_from_user(vaddr, user_data, args->size)) - return -EFAULT; - - drm_clflush_virt_range(vaddr, args->size); - intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt); - - i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); - return 0; -} - -static int i915_gem_create(struct drm_file *file, struct intel_memory_region *mr, u64 *size_p, @@ -527,6 +503,12 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data, trace_i915_gem_object_pread(obj, args->offset, args->size); + ret = -ENODEV; + if (obj->ops->pread) + ret = obj->ops->pread(obj, args); + if (ret != -ENODEV) + goto out; + ret = i915_gem_object_wait(obj, I915_WAIT_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); @@ -866,8 +848,6 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, if (ret == -EFAULT || ret == -ENOSPC) { if (i915_gem_object_has_struct_page(obj)) ret = i915_gem_shmem_pwrite(obj, args); - else - ret = i915_gem_phys_pwrite(obj, args, file); } i915_gem_object_unpin_pages(obj); diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index e94976976571..3640d0e229d2 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -909,8 +909,13 @@ static int gen8_oa_read(struct i915_perf_stream *stream, DRM_I915_PERF_RECORD_OA_REPORT_LOST); if (ret) return ret; - intel_uncore_write(uncore, oastatus_reg, - oastatus & ~GEN8_OASTATUS_REPORT_LOST); + + intel_uncore_rmw(uncore, oastatus_reg, + GEN8_OASTATUS_COUNTER_OVERFLOW | + GEN8_OASTATUS_REPORT_LOST, + IS_GEN_RANGE(uncore->i915, 8, 10) ? + (GEN8_OASTATUS_HEAD_POINTER_WRAP | + GEN8_OASTATUS_TAIL_POINTER_WRAP) : 0); } return gen8_append_oa_reports(stream, buf, count, offset); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index d805d4da6181..5cd83eac940c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -676,6 +676,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN7_OASTATUS2_MEM_SELECT_GGTT (1 << 0) /* 0: PPGTT, 1: GGTT */ #define GEN8_OASTATUS _MMIO(0x2b08) +#define GEN8_OASTATUS_TAIL_POINTER_WRAP (1 << 17) +#define GEN8_OASTATUS_HEAD_POINTER_WRAP (1 << 16) #define GEN8_OASTATUS_OVERRUN_STATUS (1 << 3) #define GEN8_OASTATUS_COUNTER_OVERFLOW (1 << 2) #define GEN8_OASTATUS_OABUFFER_OVERFLOW (1 << 1) @@ -8971,10 +8973,6 @@ enum { #define GEN9_PWRGT_MEDIA_STATUS_MASK (1 << 0) #define GEN9_PWRGT_RENDER_STATUS_MASK (1 << 1) -#define POWERGATE_ENABLE _MMIO(0xa210) -#define VDN_HCP_POWERGATE_ENABLE(n) BIT(((n) * 2) + 3) -#define VDN_MFX_POWERGATE_ENABLE(n) BIT(((n) * 2) + 4) - #define GTFIFODBG _MMIO(0x120000) #define GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV (0x1f << 20) #define GT_FIFO_FREE_ENTRIES_CHV (0x7f << 13) @@ -9114,9 +9112,11 @@ enum { #define GEN9_MEDIA_PG_IDLE_HYSTERESIS _MMIO(0xA0C4) #define GEN9_RENDER_PG_IDLE_HYSTERESIS _MMIO(0xA0C8) #define GEN9_PG_ENABLE _MMIO(0xA210) -#define GEN9_RENDER_PG_ENABLE REG_BIT(0) -#define GEN9_MEDIA_PG_ENABLE REG_BIT(1) -#define GEN11_MEDIA_SAMPLER_PG_ENABLE REG_BIT(2) +#define GEN9_RENDER_PG_ENABLE REG_BIT(0) +#define GEN9_MEDIA_PG_ENABLE REG_BIT(1) +#define GEN11_MEDIA_SAMPLER_PG_ENABLE REG_BIT(2) +#define VDN_HCP_POWERGATE_ENABLE(n) REG_BIT(3 + 2 * (n)) +#define VDN_MFX_POWERGATE_ENABLE(n) REG_BIT(4 + 2 * (n)) #define GEN8_PUSHBUS_CONTROL _MMIO(0xA248) #define GEN8_PUSHBUS_ENABLE _MMIO(0xA250) #define GEN8_PUSHBUS_SHIFT _MMIO(0xA25C) diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 16b721080195..620b6fab2c5c 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -176,7 +176,9 @@ struct i915_request { struct intel_context *context; struct intel_ring *ring; struct intel_timeline __rcu *timeline; + struct list_head signal_link; + struct llist_node signal_node; /* * The rcu epoch of when this request was allocated. Used to judiciously diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 34e0d22d456b..cfb806767fc5 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -7118,23 +7118,10 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv) static void tgl_init_clock_gating(struct drm_i915_private *dev_priv) { - u32 vd_pg_enable = 0; - unsigned int i; - /* Wa_1409120013:tgl */ I915_WRITE(ILK_DPFC_CHICKEN, ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL); - /* This is not a WA. Enable VD HCP & MFX_ENC powergate */ - for (i = 0; i < I915_MAX_VCS; i++) { - if (HAS_ENGINE(&dev_priv->gt, _VCS(i))) - vd_pg_enable |= VDN_HCP_POWERGATE_ENABLE(i) | - VDN_MFX_POWERGATE_ENABLE(i); - } - - I915_WRITE(POWERGATE_ENABLE, - I915_READ(POWERGATE_ENABLE) | vd_pg_enable); - /* Wa_1409825376:tgl (pre-prod)*/ if (IS_TGL_DISP_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_B1)) I915_WRITE(GEN9_CLKGATE_DIS_3, I915_READ(GEN9_CLKGATE_DIS_3) | diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c index 23a6132c5f4e..412e21604a05 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem.c @@ -211,8 +211,8 @@ static int igt_gem_ww_ctx(void *arg) return PTR_ERR(obj); obj2 = i915_gem_object_create_internal(i915, PAGE_SIZE); - if (IS_ERR(obj)) { - err = PTR_ERR(obj); + if (IS_ERR(obj2)) { + err = PTR_ERR(obj2); goto put1; } diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index 64bbb8288249..e424a6d1a68c 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -2293,8 +2293,10 @@ static int perf_request_latency(void *arg) struct intel_context *ce; ce = intel_context_create(engine); - if (IS_ERR(ce)) + if (IS_ERR(ce)) { + err = PTR_ERR(ce); goto out; + } err = intel_context_pin(ce); if (err) { @@ -2467,8 +2469,10 @@ static int perf_series_engines(void *arg) struct intel_context *ce; ce = intel_context_create(engine); - if (IS_ERR(ce)) + if (IS_ERR(ce)) { + err = PTR_ERR(ce); goto out; + } err = intel_context_pin(ce); if (err) { diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c index c592957ed07f..92f8bd907193 100644 --- a/drivers/gpu/drm/mcde/mcde_drv.c +++ b/drivers/gpu/drm/mcde/mcde_drv.c @@ -413,7 +413,13 @@ static int mcde_probe(struct platform_device *pdev) match); if (ret) { dev_err(dev, "failed to add component master\n"); - goto clk_disable; + /* + * The EPOD regulator is already disabled at this point so some + * special errorpath code is needed + */ + clk_disable_unprepare(mcde->mcde_clk); + regulator_disable(mcde->vana); + return ret; } return 0; diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index cf11c4850b40..52f11a63a330 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -522,15 +522,6 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi, return 0; } -static void mtk_dpi_encoder_destroy(struct drm_encoder *encoder) -{ - drm_encoder_cleanup(encoder); -} - -static const struct drm_encoder_funcs mtk_dpi_encoder_funcs = { - .destroy = mtk_dpi_encoder_destroy, -}; - static int mtk_dpi_bridge_attach(struct drm_bridge *bridge, enum drm_bridge_attach_flags flags) { diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 4a188a942c38..65fd99c528af 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -444,7 +444,10 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi) u32 horizontal_sync_active_byte; u32 horizontal_backporch_byte; u32 horizontal_frontporch_byte; + u32 horizontal_front_back_byte; + u32 data_phy_cycles_byte; u32 dsi_tmp_buf_bpp, data_phy_cycles; + u32 delta; struct mtk_phy_timing *timing = &dsi->phy_timing; struct videomode *vm = &dsi->vm; @@ -466,50 +469,30 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi) horizontal_sync_active_byte = (vm->hsync_len * dsi_tmp_buf_bpp - 10); if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) - horizontal_backporch_byte = vm->hback_porch * dsi_tmp_buf_bpp; + horizontal_backporch_byte = vm->hback_porch * dsi_tmp_buf_bpp - 10; else horizontal_backporch_byte = (vm->hback_porch + vm->hsync_len) * - dsi_tmp_buf_bpp; + dsi_tmp_buf_bpp - 10; data_phy_cycles = timing->lpx + timing->da_hs_prepare + - timing->da_hs_zero + timing->da_hs_exit; - - if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) { - if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp > - data_phy_cycles * dsi->lanes + 18) { - horizontal_frontporch_byte = - vm->hfront_porch * dsi_tmp_buf_bpp - - (data_phy_cycles * dsi->lanes + 18) * - vm->hfront_porch / - (vm->hfront_porch + vm->hback_porch); - - horizontal_backporch_byte = - horizontal_backporch_byte - - (data_phy_cycles * dsi->lanes + 18) * - vm->hback_porch / - (vm->hfront_porch + vm->hback_porch); - } else { - DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n"); - horizontal_frontporch_byte = vm->hfront_porch * - dsi_tmp_buf_bpp; - } + timing->da_hs_zero + timing->da_hs_exit + 3; + + delta = dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST ? 18 : 12; + + horizontal_frontporch_byte = vm->hfront_porch * dsi_tmp_buf_bpp; + horizontal_front_back_byte = horizontal_frontporch_byte + horizontal_backporch_byte; + data_phy_cycles_byte = data_phy_cycles * dsi->lanes + delta; + + if (horizontal_front_back_byte > data_phy_cycles_byte) { + horizontal_frontporch_byte -= data_phy_cycles_byte * + horizontal_frontporch_byte / + horizontal_front_back_byte; + + horizontal_backporch_byte -= data_phy_cycles_byte * + horizontal_backporch_byte / + horizontal_front_back_byte; } else { - if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp > - data_phy_cycles * dsi->lanes + 12) { - horizontal_frontporch_byte = - vm->hfront_porch * dsi_tmp_buf_bpp - - (data_phy_cycles * dsi->lanes + 12) * - vm->hfront_porch / - (vm->hfront_porch + vm->hback_porch); - horizontal_backporch_byte = horizontal_backporch_byte - - (data_phy_cycles * dsi->lanes + 12) * - vm->hback_porch / - (vm->hfront_porch + vm->hback_porch); - } else { - DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n"); - horizontal_frontporch_byte = vm->hfront_porch * - dsi_tmp_buf_bpp; - } + DRM_WARN("HFP + HBP less than d-phy, FPS will under 60Hz\n"); } writel(horizontal_sync_active_byte, dsi->regs + DSI_HSA_WC); diff --git a/drivers/gpu/drm/mxsfb/mxsfb_kms.c b/drivers/gpu/drm/mxsfb/mxsfb_kms.c index b721b8b262ce..9e1224d54729 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_kms.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_kms.c @@ -22,6 +22,7 @@ #include <drm/drm_fb_cma_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_gem_cma_helper.h> +#include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_plane.h> #include <drm/drm_plane_helper.h> #include <drm/drm_vblank.h> @@ -484,17 +485,27 @@ static void mxsfb_plane_overlay_atomic_update(struct drm_plane *plane, writel(ctrl, mxsfb->base + LCDC_AS_CTRL); } +static bool mxsfb_format_mod_supported(struct drm_plane *plane, + uint32_t format, + uint64_t modifier) +{ + return modifier == DRM_FORMAT_MOD_LINEAR; +} + static const struct drm_plane_helper_funcs mxsfb_plane_primary_helper_funcs = { + .prepare_fb = drm_gem_fb_prepare_fb, .atomic_check = mxsfb_plane_atomic_check, .atomic_update = mxsfb_plane_primary_atomic_update, }; static const struct drm_plane_helper_funcs mxsfb_plane_overlay_helper_funcs = { + .prepare_fb = drm_gem_fb_prepare_fb, .atomic_check = mxsfb_plane_atomic_check, .atomic_update = mxsfb_plane_overlay_atomic_update, }; static const struct drm_plane_funcs mxsfb_plane_funcs = { + .format_mod_supported = mxsfb_format_mod_supported, .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, .destroy = drm_plane_cleanup, diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index b111fe24a06b..36d6b6093d16 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -455,7 +455,7 @@ nv50_outp_get_old_connector(struct nouveau_encoder *outp, * DAC *****************************************************************************/ static void -nv50_dac_disable(struct drm_encoder *encoder) +nv50_dac_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nv50_core *core = nv50_disp(encoder->dev)->core; @@ -467,7 +467,7 @@ nv50_dac_disable(struct drm_encoder *encoder) } static void -nv50_dac_enable(struct drm_encoder *encoder) +nv50_dac_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc); @@ -525,8 +525,8 @@ nv50_dac_detect(struct drm_encoder *encoder, struct drm_connector *connector) static const struct drm_encoder_helper_funcs nv50_dac_help = { .atomic_check = nv50_outp_atomic_check, - .enable = nv50_dac_enable, - .disable = nv50_dac_disable, + .atomic_enable = nv50_dac_enable, + .atomic_disable = nv50_dac_disable, .detect = nv50_dac_detect }; @@ -1055,7 +1055,7 @@ nv50_dp_bpc_to_depth(unsigned int bpc) } static void -nv50_msto_enable(struct drm_encoder *encoder) +nv50_msto_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nv50_head *head = nv50_head(encoder->crtc); struct nv50_head_atom *armh = nv50_head_atom(head->base.base.state); @@ -1101,7 +1101,7 @@ nv50_msto_enable(struct drm_encoder *encoder) } static void -nv50_msto_disable(struct drm_encoder *encoder) +nv50_msto_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nv50_msto *msto = nv50_msto(encoder); struct nv50_mstc *mstc = msto->mstc; @@ -1118,8 +1118,8 @@ nv50_msto_disable(struct drm_encoder *encoder) static const struct drm_encoder_helper_funcs nv50_msto_help = { - .disable = nv50_msto_disable, - .enable = nv50_msto_enable, + .atomic_disable = nv50_msto_disable, + .atomic_enable = nv50_msto_enable, .atomic_check = nv50_msto_atomic_check, }; @@ -1645,8 +1645,7 @@ nv50_sor_disable(struct drm_encoder *encoder, } static void -nv50_sor_enable(struct drm_encoder *encoder, - struct drm_atomic_state *state) +nv50_sor_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc); @@ -1873,7 +1872,7 @@ nv50_pior_atomic_check(struct drm_encoder *encoder, } static void -nv50_pior_disable(struct drm_encoder *encoder) +nv50_pior_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nv50_core *core = nv50_disp(encoder->dev)->core; @@ -1885,7 +1884,7 @@ nv50_pior_disable(struct drm_encoder *encoder) } static void -nv50_pior_enable(struct drm_encoder *encoder) +nv50_pior_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc); @@ -1921,14 +1920,14 @@ nv50_pior_enable(struct drm_encoder *encoder) } core->func->pior->ctrl(core, nv_encoder->or, ctrl, asyh); - nv_encoder->crtc = encoder->crtc; + nv_encoder->crtc = &nv_crtc->base; } static const struct drm_encoder_helper_funcs nv50_pior_help = { .atomic_check = nv50_pior_atomic_check, - .enable = nv50_pior_enable, - .disable = nv50_pior_disable, + .atomic_enable = nv50_pior_enable, + .atomic_disable = nv50_pior_disable, }; static void diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 2ee75646ad6f..7daa12eec01b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -350,14 +350,13 @@ set_placement_list(struct nouveau_drm *drm, struct ttm_place *pl, unsigned *n, if (domain & NOUVEAU_GEM_DOMAIN_VRAM) { struct nvif_mmu *mmu = &drm->client.mmu; - const u8 type = mmu->type[drm->ttm.type_vram].type; pl[*n].mem_type = TTM_PL_VRAM; pl[*n].flags = flags & ~TTM_PL_FLAG_CACHED; /* Some BARs do not support being ioremapped WC */ if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA && - type & NVIF_MEM_UNCACHED) + mmu->type[drm->ttm.type_vram].type & NVIF_MEM_UNCACHED) pl[*n].flags &= ~TTM_PL_FLAG_WC; (*n)++; @@ -1215,8 +1214,8 @@ retry: } reg->bus.offset = handle; - ret = 0; } + ret = 0; break; default: ret = -EINVAL; diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 6f21f36719fc..8b4b3688c7ae 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -532,11 +532,13 @@ static void nouveau_connector_set_edid(struct nouveau_connector *nv_connector, struct edid *edid) { - struct edid *old_edid = nv_connector->edid; + if (nv_connector->edid != edid) { + struct edid *old_edid = nv_connector->edid; - drm_connector_update_edid_property(&nv_connector->base, edid); - kfree(old_edid); - nv_connector->edid = edid; + drm_connector_update_edid_property(&nv_connector->base, edid); + kfree(old_edid); + nv_connector->edid = edid; + } } static enum drm_connector_status @@ -669,8 +671,10 @@ nouveau_connector_detect_lvds(struct drm_connector *connector, bool force) /* Try retrieving EDID via DDC */ if (!drm->vbios.fp_no_ddc) { status = nouveau_connector_detect(connector, force); - if (status == connector_status_connected) + if (status == connector_status_connected) { + edid = nv_connector->edid; goto out; + } } /* On some laptops (Sony, i'm looking at you) there appears to diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 549bc67feabb..c2051380d18c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -558,8 +558,10 @@ nouveau_gem_pushbuf_validate(struct nouveau_channel *chan, NV_PRINTK(err, cli, "validating bo list\n"); validate_fini(op, chan, NULL, NULL); return ret; + } else if (ret > 0) { + *apply_relocs = true; } - *apply_relocs = ret; + return 0; } @@ -662,7 +664,6 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli, nouveau_bo_wr32(nvbo, r->reloc_bo_offset >> 2, data); } - u_free(reloc); return ret; } @@ -872,9 +873,10 @@ out: break; } } - u_free(reloc); } out_prevalid: + if (!IS_ERR(reloc)) + u_free(reloc); u_free(bo); u_free(push); diff --git a/drivers/gpu/drm/omapdrm/dss/sdi.c b/drivers/gpu/drm/omapdrm/dss/sdi.c index 033fd30074b0..282e4c837cd9 100644 --- a/drivers/gpu/drm/omapdrm/dss/sdi.c +++ b/drivers/gpu/drm/omapdrm/dss/sdi.c @@ -195,8 +195,7 @@ static void sdi_bridge_mode_set(struct drm_bridge *bridge, sdi->pixelclock = adjusted_mode->clock * 1000; } -static void sdi_bridge_enable(struct drm_bridge *bridge, - struct drm_bridge_state *bridge_state) +static void sdi_bridge_enable(struct drm_bridge *bridge) { struct sdi_device *sdi = drm_bridge_to_sdi(bridge); struct dispc_clock_info dispc_cinfo; @@ -259,8 +258,7 @@ err_get_dispc: regulator_disable(sdi->vdds_sdi_reg); } -static void sdi_bridge_disable(struct drm_bridge *bridge, - struct drm_bridge_state *bridge_state) +static void sdi_bridge_disable(struct drm_bridge *bridge) { struct sdi_device *sdi = drm_bridge_to_sdi(bridge); @@ -278,8 +276,8 @@ static const struct drm_bridge_funcs sdi_bridge_funcs = { .mode_valid = sdi_bridge_mode_valid, .mode_fixup = sdi_bridge_mode_fixup, .mode_set = sdi_bridge_mode_set, - .atomic_enable = sdi_bridge_enable, - .atomic_disable = sdi_bridge_disable, + .enable = sdi_bridge_enable, + .disable = sdi_bridge_disable, }; static void sdi_bridge_init(struct sdi_device *sdi) diff --git a/drivers/gpu/drm/panel/panel-sony-acx565akm.c b/drivers/gpu/drm/panel/panel-sony-acx565akm.c index e95fdfb16b6c..ba0b3ead150f 100644 --- a/drivers/gpu/drm/panel/panel-sony-acx565akm.c +++ b/drivers/gpu/drm/panel/panel-sony-acx565akm.c @@ -629,7 +629,7 @@ static int acx565akm_probe(struct spi_device *spi) lcd->spi = spi; mutex_init(&lcd->mutex); - lcd->reset_gpio = devm_gpiod_get(&spi->dev, "reset", GPIOD_OUT_LOW); + lcd->reset_gpio = devm_gpiod_get(&spi->dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(lcd->reset_gpio)) { dev_err(&spi->dev, "failed to get reset GPIO\n"); return PTR_ERR(lcd->reset_gpio); diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c index f292c6a6e20f..41edd0a421b2 100644 --- a/drivers/gpu/drm/rockchip/rockchip_lvds.c +++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c @@ -544,7 +544,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, struct device_node *port, *endpoint; int ret = 0, child_count = 0; const char *name; - u32 endpoint_id; + u32 endpoint_id = 0; lvds->drm_dev = drm_dev; port = of_graph_get_port_by_id(dev->of_node, 1); diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c index 77497b45f9a2..55960cbb1019 100644 --- a/drivers/gpu/drm/sun4i/sun4i_backend.c +++ b/drivers/gpu/drm/sun4i/sun4i_backend.c @@ -814,9 +814,15 @@ static int sun4i_backend_bind(struct device *dev, struct device *master, * * XXX(hch): this has no business in a driver and needs to move * to the device tree. + * + * If we have two subsequent calls to dma_direct_set_offset + * returns -EINVAL. Unfortunately, this happens when we have two + * backends in the system, and will result in the driver + * reporting an error while it has been setup properly before. + * Ignore EINVAL, but it should really be removed eventually. */ ret = dma_direct_set_offset(drm->dev, PHYS_OFFSET, 0, SZ_4G); - if (ret) + if (ret && ret != -EINVAL) return ret; } diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c index d4c08043dd81..92add2cef2e7 100644 --- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c +++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c @@ -208,6 +208,7 @@ static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master, phy_node = of_parse_phandle(dev->of_node, "phys", 0); if (!phy_node) { dev_err(dev, "Can't found PHY phandle\n"); + ret = -EINVAL; goto err_disable_clk_tmds; } diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index ba9d1c3e7cac..e4baf07992a4 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -90,7 +90,7 @@ static int tegra_drm_open(struct drm_device *drm, struct drm_file *filp) if (!fpriv) return -ENOMEM; - idr_init(&fpriv->contexts); + idr_init_base(&fpriv->contexts, 1); mutex_init(&fpriv->lock); filp->driver_priv = fpriv; diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c index 5a4fd0dbf4cf..47d26b5d9945 100644 --- a/drivers/gpu/drm/tegra/output.c +++ b/drivers/gpu/drm/tegra/output.c @@ -129,7 +129,6 @@ int tegra_output_probe(struct tegra_output *output) if (!output->ddc) { err = -EPROBE_DEFER; - of_node_put(ddc); return err; } } diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index e88a17c2937f..cc2aa2308a51 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -397,7 +397,6 @@ struct tegra_sor; struct tegra_sor_ops { const char *name; int (*probe)(struct tegra_sor *sor); - int (*remove)(struct tegra_sor *sor); void (*audio_enable)(struct tegra_sor *sor); void (*audio_disable)(struct tegra_sor *sor); }; @@ -2942,6 +2941,24 @@ static const struct drm_encoder_helper_funcs tegra_sor_dp_helpers = { .atomic_check = tegra_sor_encoder_atomic_check, }; +static void tegra_sor_disable_regulator(void *data) +{ + struct regulator *reg = data; + + regulator_disable(reg); +} + +static int tegra_sor_enable_regulator(struct tegra_sor *sor, struct regulator *reg) +{ + int err; + + err = regulator_enable(reg); + if (err) + return err; + + return devm_add_action_or_reset(sor->dev, tegra_sor_disable_regulator, reg); +} + static int tegra_sor_hdmi_probe(struct tegra_sor *sor) { int err; @@ -2953,7 +2970,7 @@ static int tegra_sor_hdmi_probe(struct tegra_sor *sor) return PTR_ERR(sor->avdd_io_supply); } - err = regulator_enable(sor->avdd_io_supply); + err = tegra_sor_enable_regulator(sor, sor->avdd_io_supply); if (err < 0) { dev_err(sor->dev, "failed to enable AVDD I/O supply: %d\n", err); @@ -2967,7 +2984,7 @@ static int tegra_sor_hdmi_probe(struct tegra_sor *sor) return PTR_ERR(sor->vdd_pll_supply); } - err = regulator_enable(sor->vdd_pll_supply); + err = tegra_sor_enable_regulator(sor, sor->vdd_pll_supply); if (err < 0) { dev_err(sor->dev, "failed to enable VDD PLL supply: %d\n", err); @@ -2981,7 +2998,7 @@ static int tegra_sor_hdmi_probe(struct tegra_sor *sor) return PTR_ERR(sor->hdmi_supply); } - err = regulator_enable(sor->hdmi_supply); + err = tegra_sor_enable_regulator(sor, sor->hdmi_supply); if (err < 0) { dev_err(sor->dev, "failed to enable HDMI supply: %d\n", err); return err; @@ -2992,19 +3009,9 @@ static int tegra_sor_hdmi_probe(struct tegra_sor *sor) return 0; } -static int tegra_sor_hdmi_remove(struct tegra_sor *sor) -{ - regulator_disable(sor->hdmi_supply); - regulator_disable(sor->vdd_pll_supply); - regulator_disable(sor->avdd_io_supply); - - return 0; -} - static const struct tegra_sor_ops tegra_sor_hdmi_ops = { .name = "HDMI", .probe = tegra_sor_hdmi_probe, - .remove = tegra_sor_hdmi_remove, .audio_enable = tegra_sor_hdmi_audio_enable, .audio_disable = tegra_sor_hdmi_audio_disable, }; @@ -3017,7 +3024,7 @@ static int tegra_sor_dp_probe(struct tegra_sor *sor) if (IS_ERR(sor->avdd_io_supply)) return PTR_ERR(sor->avdd_io_supply); - err = regulator_enable(sor->avdd_io_supply); + err = tegra_sor_enable_regulator(sor, sor->avdd_io_supply); if (err < 0) return err; @@ -3025,25 +3032,16 @@ static int tegra_sor_dp_probe(struct tegra_sor *sor) if (IS_ERR(sor->vdd_pll_supply)) return PTR_ERR(sor->vdd_pll_supply); - err = regulator_enable(sor->vdd_pll_supply); + err = tegra_sor_enable_regulator(sor, sor->vdd_pll_supply); if (err < 0) return err; return 0; } -static int tegra_sor_dp_remove(struct tegra_sor *sor) -{ - regulator_disable(sor->vdd_pll_supply); - regulator_disable(sor->avdd_io_supply); - - return 0; -} - static const struct tegra_sor_ops tegra_sor_dp_ops = { .name = "DP", .probe = tegra_sor_dp_probe, - .remove = tegra_sor_dp_remove, }; static int tegra_sor_init(struct host1x_client *client) @@ -3145,6 +3143,7 @@ static int tegra_sor_init(struct host1x_client *client) if (err < 0) { dev_err(sor->dev, "failed to deassert SOR reset: %d\n", err); + clk_disable_unprepare(sor->clk); return err; } @@ -3152,12 +3151,17 @@ static int tegra_sor_init(struct host1x_client *client) } err = clk_prepare_enable(sor->clk_safe); - if (err < 0) + if (err < 0) { + clk_disable_unprepare(sor->clk); return err; + } err = clk_prepare_enable(sor->clk_dp); - if (err < 0) + if (err < 0) { + clk_disable_unprepare(sor->clk_safe); + clk_disable_unprepare(sor->clk); return err; + } return 0; } @@ -3764,17 +3768,16 @@ static int tegra_sor_probe(struct platform_device *pdev) return err; err = tegra_output_probe(&sor->output); - if (err < 0) { - dev_err(&pdev->dev, "failed to probe output: %d\n", err); - return err; - } + if (err < 0) + return dev_err_probe(&pdev->dev, err, + "failed to probe output\n"); if (sor->ops && sor->ops->probe) { err = sor->ops->probe(sor); if (err < 0) { dev_err(&pdev->dev, "failed to probe %s: %d\n", sor->ops->name, err); - goto output; + goto remove; } } @@ -3955,9 +3958,6 @@ unregister: rpm_disable: pm_runtime_disable(&pdev->dev); remove: - if (sor->ops && sor->ops->remove) - sor->ops->remove(sor); -output: tegra_output_remove(&sor->output); return err; } @@ -3976,12 +3976,6 @@ static int tegra_sor_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); - if (sor->ops && sor->ops->remove) { - err = sor->ops->remove(sor); - if (err < 0) - dev_err(&pdev->dev, "failed to remove SOR: %d\n", err); - } - tegra_output_remove(&sor->output); return 0; diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h index 19b75bebd35f..c5f2944d5bc6 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.h +++ b/drivers/gpu/drm/vc4/vc4_drv.h @@ -219,6 +219,7 @@ struct vc4_dev { struct drm_modeset_lock ctm_state_lock; struct drm_private_obj ctm_manager; + struct drm_private_obj hvs_channels; struct drm_private_obj load_tracker; /* List of vc4_debugfs_info_entry for adding to debugfs once @@ -531,6 +532,9 @@ struct vc4_crtc_state { unsigned int top; unsigned int bottom; } margins; + + /* Transitional state below, only valid during atomic commits */ + bool update_muxing; }; #define VC4_HVS_CHANNEL_DISABLED ((unsigned int)-1) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 95779d50cca0..afc178b0d89f 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -760,12 +760,54 @@ static void vc4_hdmi_encoder_enable(struct drm_encoder *encoder) { } +#define WIFI_2_4GHz_CH1_MIN_FREQ 2400000000ULL +#define WIFI_2_4GHz_CH1_MAX_FREQ 2422000000ULL + +static int vc4_hdmi_encoder_atomic_check(struct drm_encoder *encoder, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) +{ + struct drm_display_mode *mode = &crtc_state->adjusted_mode; + struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); + unsigned long long pixel_rate = mode->clock * 1000; + unsigned long long tmds_rate; + + if (vc4_hdmi->variant->unsupported_odd_h_timings && + ((mode->hdisplay % 2) || (mode->hsync_start % 2) || + (mode->hsync_end % 2) || (mode->htotal % 2))) + return -EINVAL; + + /* + * The 1440p@60 pixel rate is in the same range than the first + * WiFi channel (between 2.4GHz and 2.422GHz with 22MHz + * bandwidth). Slightly lower the frequency to bring it out of + * the WiFi range. + */ + tmds_rate = pixel_rate * 10; + if (vc4_hdmi->disable_wifi_frequencies && + (tmds_rate >= WIFI_2_4GHz_CH1_MIN_FREQ && + tmds_rate <= WIFI_2_4GHz_CH1_MAX_FREQ)) { + mode->clock = 238560; + pixel_rate = mode->clock * 1000; + } + + if (pixel_rate > vc4_hdmi->variant->max_pixel_clock) + return -EINVAL; + + return 0; +} + static enum drm_mode_status vc4_hdmi_encoder_mode_valid(struct drm_encoder *encoder, const struct drm_display_mode *mode) { struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); + if (vc4_hdmi->variant->unsupported_odd_h_timings && + ((mode->hdisplay % 2) || (mode->hsync_start % 2) || + (mode->hsync_end % 2) || (mode->htotal % 2))) + return MODE_H_ILLEGAL; + if ((mode->clock * 1000) > vc4_hdmi->variant->max_pixel_clock) return MODE_CLOCK_HIGH; @@ -773,6 +815,7 @@ vc4_hdmi_encoder_mode_valid(struct drm_encoder *encoder, } static const struct drm_encoder_helper_funcs vc4_hdmi_encoder_helper_funcs = { + .atomic_check = vc4_hdmi_encoder_atomic_check, .mode_valid = vc4_hdmi_encoder_mode_valid, .disable = vc4_hdmi_encoder_disable, .enable = vc4_hdmi_encoder_enable, @@ -1694,6 +1737,9 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) vc4_hdmi->hpd_active_low = hpd_gpio_flags & OF_GPIO_ACTIVE_LOW; } + vc4_hdmi->disable_wifi_frequencies = + of_property_read_bool(dev->of_node, "wifi-2.4ghz-coexistence"); + pm_runtime_enable(dev); drm_simple_encoder_init(drm, encoder, DRM_MODE_ENCODER_TMDS); @@ -1817,6 +1863,7 @@ static const struct vc4_hdmi_variant bcm2711_hdmi0_variant = { PHY_LANE_2, PHY_LANE_CK, }, + .unsupported_odd_h_timings = true, .init_resources = vc5_hdmi_init_resources, .csc_setup = vc5_hdmi_csc_setup, @@ -1842,6 +1889,7 @@ static const struct vc4_hdmi_variant bcm2711_hdmi1_variant = { PHY_LANE_CK, PHY_LANE_2, }, + .unsupported_odd_h_timings = true, .init_resources = vc5_hdmi_init_resources, .csc_setup = vc5_hdmi_csc_setup, diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h index 63c6f8bddf1d..0526a9cf608a 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.h +++ b/drivers/gpu/drm/vc4/vc4_hdmi.h @@ -62,6 +62,9 @@ struct vc4_hdmi_variant { */ enum vc4_hdmi_phy_channel phy_lane_mapping[4]; + /* The BCM2711 cannot deal with odd horizontal pixel timings */ + bool unsupported_odd_h_timings; + /* Callback to get the resources (memory region, interrupts, * clocks, etc) for that variant. */ @@ -139,6 +142,14 @@ struct vc4_hdmi { int hpd_gpio; bool hpd_active_low; + /* + * On some systems (like the RPi4), some modes are in the same + * frequency range than the WiFi channels (1440p@60Hz for + * example). Should we take evasive actions because that system + * has a wifi adapter? + */ + bool disable_wifi_frequencies; + struct cec_adapter *cec_adap; struct cec_msg cec_rx_msg; bool cec_tx_ok; diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index 2b951cae04ad..ba310c0ab5f6 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -24,6 +24,8 @@ #include "vc4_drv.h" #include "vc4_regs.h" +#define HVS_NUM_CHANNELS 3 + struct vc4_ctm_state { struct drm_private_state base; struct drm_color_ctm *ctm; @@ -35,6 +37,17 @@ static struct vc4_ctm_state *to_vc4_ctm_state(struct drm_private_state *priv) return container_of(priv, struct vc4_ctm_state, base); } +struct vc4_hvs_state { + struct drm_private_state base; + unsigned int unassigned_channels; +}; + +static struct vc4_hvs_state * +to_vc4_hvs_state(struct drm_private_state *priv) +{ + return container_of(priv, struct vc4_hvs_state, base); +} + struct vc4_load_tracker_state { struct drm_private_state base; u64 hvs_load; @@ -113,7 +126,7 @@ static int vc4_ctm_obj_init(struct vc4_dev *vc4) drm_atomic_private_obj_init(&vc4->base, &vc4->ctm_manager, &ctm_state->base, &vc4_ctm_state_funcs); - return drmm_add_action(&vc4->base, vc4_ctm_obj_fini, NULL); + return drmm_add_action_or_reset(&vc4->base, vc4_ctm_obj_fini, NULL); } /* Converts a DRM S31.32 value to the HW S0.9 format. */ @@ -169,6 +182,19 @@ vc4_ctm_commit(struct vc4_dev *vc4, struct drm_atomic_state *state) VC4_SET_FIELD(ctm_state->fifo, SCALER_OLEDOFFS_DISPFIFO)); } +static struct vc4_hvs_state * +vc4_hvs_get_global_state(struct drm_atomic_state *state) +{ + struct vc4_dev *vc4 = to_vc4_dev(state->dev); + struct drm_private_state *priv_state; + + priv_state = drm_atomic_get_private_obj_state(state, &vc4->hvs_channels); + if (IS_ERR(priv_state)) + return ERR_CAST(priv_state); + + return to_vc4_hvs_state(priv_state); +} + static void vc4_hvs_pv_muxing_commit(struct vc4_dev *vc4, struct drm_atomic_state *state) { @@ -213,10 +239,7 @@ static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4, { struct drm_crtc_state *crtc_state; struct drm_crtc *crtc; - unsigned char dsp2_mux = 0; - unsigned char dsp3_mux = 3; - unsigned char dsp4_mux = 3; - unsigned char dsp5_mux = 3; + unsigned char mux; unsigned int i; u32 reg; @@ -224,50 +247,59 @@ static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4, struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc_state); struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); - if (!crtc_state->active) + if (!vc4_state->update_muxing) continue; switch (vc4_crtc->data->hvs_output) { case 2: - dsp2_mux = (vc4_state->assigned_channel == 2) ? 0 : 1; + mux = (vc4_state->assigned_channel == 2) ? 0 : 1; + reg = HVS_READ(SCALER_DISPECTRL); + HVS_WRITE(SCALER_DISPECTRL, + (reg & ~SCALER_DISPECTRL_DSP2_MUX_MASK) | + VC4_SET_FIELD(mux, SCALER_DISPECTRL_DSP2_MUX)); break; case 3: - dsp3_mux = vc4_state->assigned_channel; + if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED) + mux = 3; + else + mux = vc4_state->assigned_channel; + + reg = HVS_READ(SCALER_DISPCTRL); + HVS_WRITE(SCALER_DISPCTRL, + (reg & ~SCALER_DISPCTRL_DSP3_MUX_MASK) | + VC4_SET_FIELD(mux, SCALER_DISPCTRL_DSP3_MUX)); break; case 4: - dsp4_mux = vc4_state->assigned_channel; + if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED) + mux = 3; + else + mux = vc4_state->assigned_channel; + + reg = HVS_READ(SCALER_DISPEOLN); + HVS_WRITE(SCALER_DISPEOLN, + (reg & ~SCALER_DISPEOLN_DSP4_MUX_MASK) | + VC4_SET_FIELD(mux, SCALER_DISPEOLN_DSP4_MUX)); + break; case 5: - dsp5_mux = vc4_state->assigned_channel; + if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED) + mux = 3; + else + mux = vc4_state->assigned_channel; + + reg = HVS_READ(SCALER_DISPDITHER); + HVS_WRITE(SCALER_DISPDITHER, + (reg & ~SCALER_DISPDITHER_DSP5_MUX_MASK) | + VC4_SET_FIELD(mux, SCALER_DISPDITHER_DSP5_MUX)); break; default: break; } } - - reg = HVS_READ(SCALER_DISPECTRL); - HVS_WRITE(SCALER_DISPECTRL, - (reg & ~SCALER_DISPECTRL_DSP2_MUX_MASK) | - VC4_SET_FIELD(dsp2_mux, SCALER_DISPECTRL_DSP2_MUX)); - - reg = HVS_READ(SCALER_DISPCTRL); - HVS_WRITE(SCALER_DISPCTRL, - (reg & ~SCALER_DISPCTRL_DSP3_MUX_MASK) | - VC4_SET_FIELD(dsp3_mux, SCALER_DISPCTRL_DSP3_MUX)); - - reg = HVS_READ(SCALER_DISPEOLN); - HVS_WRITE(SCALER_DISPEOLN, - (reg & ~SCALER_DISPEOLN_DSP4_MUX_MASK) | - VC4_SET_FIELD(dsp4_mux, SCALER_DISPEOLN_DSP4_MUX)); - - reg = HVS_READ(SCALER_DISPDITHER); - HVS_WRITE(SCALER_DISPDITHER, - (reg & ~SCALER_DISPDITHER_DSP5_MUX_MASK) | - VC4_SET_FIELD(dsp5_mux, SCALER_DISPDITHER_DSP5_MUX)); } static void @@ -657,53 +689,123 @@ static int vc4_load_tracker_obj_init(struct vc4_dev *vc4) &load_state->base, &vc4_load_tracker_state_funcs); - return drmm_add_action(&vc4->base, vc4_load_tracker_obj_fini, NULL); + return drmm_add_action_or_reset(&vc4->base, vc4_load_tracker_obj_fini, NULL); } -#define NUM_OUTPUTS 6 -#define NUM_CHANNELS 3 +static struct drm_private_state * +vc4_hvs_channels_duplicate_state(struct drm_private_obj *obj) +{ + struct vc4_hvs_state *old_state = to_vc4_hvs_state(obj->state); + struct vc4_hvs_state *state; + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (!state) + return NULL; -static int -vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) + __drm_atomic_helper_private_obj_duplicate_state(obj, &state->base); + + state->unassigned_channels = old_state->unassigned_channels; + + return &state->base; +} + +static void vc4_hvs_channels_destroy_state(struct drm_private_obj *obj, + struct drm_private_state *state) { - unsigned long unassigned_channels = GENMASK(NUM_CHANNELS - 1, 0); - struct drm_crtc_state *old_crtc_state, *new_crtc_state; - struct drm_crtc *crtc; - int i, ret; + struct vc4_hvs_state *hvs_state = to_vc4_hvs_state(state); - /* - * Since the HVS FIFOs are shared across all the pixelvalves and - * the TXP (and thus all the CRTCs), we need to pull the current - * state of all the enabled CRTCs so that an update to a single - * CRTC still keeps the previous FIFOs enabled and assigned to - * the same CRTCs, instead of evaluating only the CRTC being - * modified. - */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - struct drm_crtc_state *crtc_state; + kfree(hvs_state); +} - if (!crtc->state->enable) - continue; +static const struct drm_private_state_funcs vc4_hvs_state_funcs = { + .atomic_duplicate_state = vc4_hvs_channels_duplicate_state, + .atomic_destroy_state = vc4_hvs_channels_destroy_state, +}; - crtc_state = drm_atomic_get_crtc_state(state, crtc); - if (IS_ERR(crtc_state)) - return PTR_ERR(crtc_state); - } +static void vc4_hvs_channels_obj_fini(struct drm_device *dev, void *unused) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + + drm_atomic_private_obj_fini(&vc4->hvs_channels); +} + +static int vc4_hvs_channels_obj_init(struct vc4_dev *vc4) +{ + struct vc4_hvs_state *state; + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (!state) + return -ENOMEM; + + state->unassigned_channels = GENMASK(HVS_NUM_CHANNELS - 1, 0); + drm_atomic_private_obj_init(&vc4->base, &vc4->hvs_channels, + &state->base, + &vc4_hvs_state_funcs); + + return drmm_add_action_or_reset(&vc4->base, vc4_hvs_channels_obj_fini, NULL); +} + +/* + * The BCM2711 HVS has up to 7 outputs connected to the pixelvalves and + * the TXP (and therefore all the CRTCs found on that platform). + * + * The naive (and our initial) implementation would just iterate over + * all the active CRTCs, try to find a suitable FIFO, and then remove it + * from the pool of available FIFOs. However, there are a few corner + * cases that need to be considered: + * + * - When running in a dual-display setup (so with two CRTCs involved), + * we can update the state of a single CRTC (for example by changing + * its mode using xrandr under X11) without affecting the other. In + * this case, the other CRTC wouldn't be in the state at all, so we + * need to consider all the running CRTCs in the DRM device to assign + * a FIFO, not just the one in the state. + * + * - To fix the above, we can't use drm_atomic_get_crtc_state on all + * enabled CRTCs to pull their CRTC state into the global state, since + * a page flip would start considering their vblank to complete. Since + * we don't have a guarantee that they are actually active, that + * vblank might never happen, and shouldn't even be considered if we + * want to do a page flip on a single CRTC. That can be tested by + * doing a modetest -v first on HDMI1 and then on HDMI0. + * + * - Since we need the pixelvalve to be disabled and enabled back when + * the FIFO is changed, we should keep the FIFO assigned for as long + * as the CRTC is enabled, only considering it free again once that + * CRTC has been disabled. This can be tested by booting X11 on a + * single display, and changing the resolution down and then back up. + */ +static int vc4_pv_muxing_atomic_check(struct drm_device *dev, + struct drm_atomic_state *state) +{ + struct vc4_hvs_state *hvs_new_state; + struct drm_crtc_state *old_crtc_state, *new_crtc_state; + struct drm_crtc *crtc; + unsigned int i; + + hvs_new_state = vc4_hvs_get_global_state(state); + if (!hvs_new_state) + return -EINVAL; for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { + struct vc4_crtc_state *old_vc4_crtc_state = + to_vc4_crtc_state(old_crtc_state); struct vc4_crtc_state *new_vc4_crtc_state = to_vc4_crtc_state(new_crtc_state); struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); unsigned int matching_channels; - if (old_crtc_state->enable && !new_crtc_state->enable) - new_vc4_crtc_state->assigned_channel = VC4_HVS_CHANNEL_DISABLED; - - if (!new_crtc_state->enable) + /* Nothing to do here, let's skip it */ + if (old_crtc_state->enable == new_crtc_state->enable) continue; - if (new_vc4_crtc_state->assigned_channel != VC4_HVS_CHANNEL_DISABLED) { - unassigned_channels &= ~BIT(new_vc4_crtc_state->assigned_channel); + /* Muxing will need to be modified, mark it as such */ + new_vc4_crtc_state->update_muxing = true; + + /* If we're disabling our CRTC, we put back our channel */ + if (!new_crtc_state->enable) { + hvs_new_state->unassigned_channels |= BIT(old_vc4_crtc_state->assigned_channel); + new_vc4_crtc_state->assigned_channel = VC4_HVS_CHANNEL_DISABLED; continue; } @@ -731,17 +833,29 @@ vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) * the future, we will need to have something smarter, * but it works so far. */ - matching_channels = unassigned_channels & vc4_crtc->data->hvs_available_channels; + matching_channels = hvs_new_state->unassigned_channels & vc4_crtc->data->hvs_available_channels; if (matching_channels) { unsigned int channel = ffs(matching_channels) - 1; new_vc4_crtc_state->assigned_channel = channel; - unassigned_channels &= ~BIT(channel); + hvs_new_state->unassigned_channels &= ~BIT(channel); } else { return -EINVAL; } } + return 0; +} + +static int +vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) +{ + int ret; + + ret = vc4_pv_muxing_atomic_check(dev, state); + if (ret) + return ret; + ret = vc4_ctm_atomic_check(dev, state); if (ret < 0) return ret; @@ -808,6 +922,10 @@ int vc4_kms_load(struct drm_device *dev) if (ret) return ret; + ret = vc4_hvs_channels_obj_init(vc4); + if (ret) + return ret; + drm_mode_config_reset(dev); drm_kms_helper_poll_init(dev); diff --git a/drivers/hid/hid-cypress.c b/drivers/hid/hid-cypress.c index a50ba4a4a1d7..b88f889b3932 100644 --- a/drivers/hid/hid-cypress.c +++ b/drivers/hid/hid-cypress.c @@ -23,19 +23,17 @@ #define CP_2WHEEL_MOUSE_HACK 0x02 #define CP_2WHEEL_MOUSE_HACK_ON 0x04 +#define VA_INVAL_LOGICAL_BOUNDARY 0x08 + /* * Some USB barcode readers from cypress have usage min and usage max in * the wrong order */ -static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc, +static __u8 *cp_rdesc_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { - unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); unsigned int i; - if (!(quirks & CP_RDESC_SWAPPED_MIN_MAX)) - return rdesc; - if (*rsize < 4) return rdesc; @@ -48,6 +46,40 @@ static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc, return rdesc; } +static __u8 *va_logical_boundary_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) +{ + /* + * Varmilo VA104M (with VID Cypress and device ID 07B1) incorrectly + * reports Logical Minimum of its Consumer Control device as 572 + * (0x02 0x3c). Fix this by setting its Logical Minimum to zero. + */ + if (*rsize == 25 && + rdesc[0] == 0x05 && rdesc[1] == 0x0c && + rdesc[2] == 0x09 && rdesc[3] == 0x01 && + rdesc[6] == 0x19 && rdesc[7] == 0x00 && + rdesc[11] == 0x16 && rdesc[12] == 0x3c && rdesc[13] == 0x02) { + hid_info(hdev, + "fixing up varmilo VA104M consumer control report descriptor\n"); + rdesc[12] = 0x00; + rdesc[13] = 0x00; + } + return rdesc; +} + +static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) +{ + unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); + + if (quirks & CP_RDESC_SWAPPED_MIN_MAX) + rdesc = cp_rdesc_fixup(hdev, rdesc, rsize); + if (quirks & VA_INVAL_LOGICAL_BOUNDARY) + rdesc = va_logical_boundary_fixup(hdev, rdesc, rsize); + + return rdesc; +} + static int cp_input_mapped(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) @@ -128,6 +160,8 @@ static const struct hid_device_id cp_devices[] = { .driver_data = CP_RDESC_SWAPPED_MIN_MAX }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_MOUSE), .driver_data = CP_2WHEEL_MOUSE_HACK }, + { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_VARMILO_VA104M_07B1), + .driver_data = VA_INVAL_LOGICAL_BOUNDARY }, { } }; MODULE_DEVICE_TABLE(hid, cp_devices); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index d69842f79fc6..f170feaac40b 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -331,6 +331,8 @@ #define USB_DEVICE_ID_CYPRESS_BARCODE_4 0xed81 #define USB_DEVICE_ID_CYPRESS_TRUETOUCH 0xc001 +#define USB_DEVICE_ID_CYPRESS_VARMILO_VA104M_07B1 0X07b1 + #define USB_VENDOR_ID_DATA_MODUL 0x7374 #define USB_VENDOR_ID_DATA_MODUL_EASYMAXTOUCH 0x1201 @@ -443,6 +445,10 @@ #define USB_VENDOR_ID_FRUCTEL 0x25B6 #define USB_DEVICE_ID_GAMETEL_MT_MODE 0x0002 +#define USB_VENDOR_ID_GAMEVICE 0x27F8 +#define USB_DEVICE_ID_GAMEVICE_GV186 0x0BBE +#define USB_DEVICE_ID_GAMEVICE_KISHI 0x0BBF + #define USB_VENDOR_ID_GAMERON 0x0810 #define USB_DEVICE_ID_GAMERON_DUAL_PSX_ADAPTOR 0x0001 #define USB_DEVICE_ID_GAMERON_DUAL_PCS_ADAPTOR 0x0002 @@ -485,6 +491,7 @@ #define USB_DEVICE_ID_PENPOWER 0x00f4 #define USB_VENDOR_ID_GREENASIA 0x0e8f +#define USB_DEVICE_ID_GREENASIA_DUAL_SAT_ADAPTOR 0x3010 #define USB_DEVICE_ID_GREENASIA_DUAL_USB_JOYPAD 0x3013 #define USB_VENDOR_ID_GRETAGMACBETH 0x0971 @@ -743,6 +750,7 @@ #define USB_VENDOR_ID_LOGITECH 0x046d #define USB_DEVICE_ID_LOGITECH_AUDIOHUB 0x0a0e #define USB_DEVICE_ID_LOGITECH_T651 0xb00c +#define USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD 0xb309 #define USB_DEVICE_ID_LOGITECH_C007 0xc007 #define USB_DEVICE_ID_LOGITECH_C077 0xc077 #define USB_DEVICE_ID_LOGITECH_RECEIVER 0xc101 @@ -1298,6 +1306,7 @@ #define USB_VENDOR_ID_UGTIZER 0x2179 #define USB_DEVICE_ID_UGTIZER_TABLET_GP0610 0x0053 +#define USB_DEVICE_ID_UGTIZER_TABLET_GT5040 0x0077 #define USB_VENDOR_ID_VIEWSONIC 0x0543 #define USB_DEVICE_ID_VIEWSONIC_PD1011 0xe621 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 9770db624bfa..4dca11392459 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -319,6 +319,9 @@ static const struct hid_device_id hid_battery_quirks[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_T100CHI_KEYBOARD), HID_BATTERY_QUIRK_IGNORE }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, + USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD), + HID_BATTERY_QUIRK_IGNORE }, {} }; diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 044a93f3c117..742c052b0110 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -11,6 +11,48 @@ #include "hid-ids.h" +#define QUIRK_TOUCHPAD_ON_OFF_REPORT BIT(0) + +static __u8 *ite_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) +{ + unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); + + if (quirks & QUIRK_TOUCHPAD_ON_OFF_REPORT) { + if (*rsize == 188 && rdesc[162] == 0x81 && rdesc[163] == 0x02) { + hid_info(hdev, "Fixing up ITE keyboard report descriptor\n"); + rdesc[163] = HID_MAIN_ITEM_RELATIVE; + } + } + + return rdesc; +} + +static int ite_input_mapping(struct hid_device *hdev, + struct hid_input *hi, struct hid_field *field, + struct hid_usage *usage, unsigned long **bit, + int *max) +{ + + unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); + + if ((quirks & QUIRK_TOUCHPAD_ON_OFF_REPORT) && + (usage->hid & HID_USAGE_PAGE) == 0x00880000) { + if (usage->hid == 0x00880078) { + /* Touchpad on, userspace expects F22 for this */ + hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_F22); + return 1; + } + if (usage->hid == 0x00880079) { + /* Touchpad off, userspace expects F23 for this */ + hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_F23); + return 1; + } + return -1; + } + + return 0; +} + static int ite_event(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage, __s32 value) { @@ -37,13 +79,27 @@ static int ite_event(struct hid_device *hdev, struct hid_field *field, return 0; } +static int ite_probe(struct hid_device *hdev, const struct hid_device_id *id) +{ + int ret; + + hid_set_drvdata(hdev, (void *)id->driver_data); + + ret = hid_open_report(hdev); + if (ret) + return ret; + + return hid_hw_start(hdev, HID_CONNECT_DEFAULT); +} + static const struct hid_device_id ite_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) }, { HID_USB_DEVICE(USB_VENDOR_ID_258A, USB_DEVICE_ID_258A_6A88) }, /* ITE8595 USB kbd ctlr, with Synaptics touchpad connected to it. */ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_SYNAPTICS, - USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) }, + USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012), + .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, /* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_SYNAPTICS, @@ -55,6 +111,9 @@ MODULE_DEVICE_TABLE(hid, ite_devices); static struct hid_driver ite_driver = { .name = "itetech", .id_table = ite_devices, + .probe = ite_probe, + .report_fixup = ite_report_fixup, + .input_mapping = ite_input_mapping, .event = ite_event, }; module_hid_driver(ite_driver); diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 72fb6e54a50a..1ffcfc9a1e03 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -328,7 +328,7 @@ static const char mse_bluetooth_descriptor[] = { 0x25, 0x01, /* LOGICAL_MAX (1) */ 0x75, 0x01, /* REPORT_SIZE (1) */ 0x95, 0x04, /* REPORT_COUNT (4) */ - 0x81, 0x06, /* INPUT */ + 0x81, 0x02, /* INPUT (Data,Var,Abs) */ 0xC0, /* END_COLLECTION */ 0xC0, /* END_COLLECTION */ }; @@ -866,11 +866,24 @@ static void logi_dj_recv_queue_notification(struct dj_receiver_dev *djrcv_dev, schedule_work(&djrcv_dev->work); } +/* + * Some quad/bluetooth keyboards have a builtin touchpad in this case we see + * only 1 paired device with a device_type of REPORT_TYPE_KEYBOARD. For the + * touchpad to work we must also forward mouse input reports to the dj_hiddev + * created for the keyboard (instead of forwarding them to a second paired + * device with a device_type of REPORT_TYPE_MOUSE as we normally would). + */ +static const u16 kbd_builtin_touchpad_ids[] = { + 0xb309, /* Dinovo Edge */ + 0xb30c, /* Dinovo Mini */ +}; + static void logi_hidpp_dev_conn_notif_equad(struct hid_device *hdev, struct hidpp_event *hidpp_report, struct dj_workitem *workitem) { struct dj_receiver_dev *djrcv_dev = hid_get_drvdata(hdev); + int i, id; workitem->type = WORKITEM_TYPE_PAIRED; workitem->device_type = hidpp_report->params[HIDPP_PARAM_DEVICE_INFO] & @@ -882,6 +895,13 @@ static void logi_hidpp_dev_conn_notif_equad(struct hid_device *hdev, workitem->reports_supported |= STD_KEYBOARD | MULTIMEDIA | POWER_KEYS | MEDIA_CENTER | HIDPP; + id = (workitem->quad_id_msb << 8) | workitem->quad_id_lsb; + for (i = 0; i < ARRAY_SIZE(kbd_builtin_touchpad_ids); i++) { + if (id == kbd_builtin_touchpad_ids[i]) { + workitem->reports_supported |= STD_MOUSE; + break; + } + } break; case REPORT_TYPE_MOUSE: workitem->reports_supported |= STD_MOUSE | HIDPP; diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index b8b53dc95e86..0ca723119547 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -93,6 +93,8 @@ MODULE_PARM_DESC(disable_tap_to_click, #define HIDPP_CAPABILITY_BATTERY_LEVEL_STATUS BIT(3) #define HIDPP_CAPABILITY_BATTERY_VOLTAGE BIT(4) +#define lg_map_key_clear(c) hid_map_usage_clear(hi, usage, bit, max, EV_KEY, (c)) + /* * There are two hidpp protocols in use, the first version hidpp10 is known * as register access protocol or RAP, the second version hidpp20 is known as @@ -2951,6 +2953,26 @@ static int g920_get_config(struct hidpp_device *hidpp, } /* -------------------------------------------------------------------------- */ +/* Logitech Dinovo Mini keyboard with builtin touchpad */ +/* -------------------------------------------------------------------------- */ +#define DINOVO_MINI_PRODUCT_ID 0xb30c + +static int lg_dinovo_input_mapping(struct hid_device *hdev, struct hid_input *hi, + struct hid_field *field, struct hid_usage *usage, + unsigned long **bit, int *max) +{ + if ((usage->hid & HID_USAGE_PAGE) != HID_UP_LOGIVENDOR) + return 0; + + switch (usage->hid & HID_USAGE) { + case 0x00d: lg_map_key_clear(KEY_MEDIA); break; + default: + return 0; + } + return 1; +} + +/* -------------------------------------------------------------------------- */ /* HID++1.0 devices which use HID++ reports for their wheels */ /* -------------------------------------------------------------------------- */ static int hidpp10_wheel_connect(struct hidpp_device *hidpp) @@ -3185,6 +3207,9 @@ static int hidpp_input_mapping(struct hid_device *hdev, struct hid_input *hi, field->application != HID_GD_MOUSE) return m560_input_mapping(hdev, hi, field, usage, bit, max); + if (hdev->product == DINOVO_MINI_PRODUCT_ID) + return lg_dinovo_input_mapping(hdev, hi, field, usage, bit, max); + return 0; } @@ -3947,6 +3972,7 @@ static const struct hid_device_id hidpp_devices[] = { LDJ_DEVICE(0x405e), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, { /* Mouse Logitech MX Anywhere 2 */ LDJ_DEVICE(0x404a), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { LDJ_DEVICE(0x4072), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, { LDJ_DEVICE(0xb013), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, { LDJ_DEVICE(0xb018), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, { LDJ_DEVICE(0xb01f), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, @@ -3971,6 +3997,9 @@ static const struct hid_device_id hidpp_devices[] = { { /* Keyboard MX5000 (Bluetooth-receiver in HID proxy mode) */ LDJ_DEVICE(0xb305), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, + { /* Dinovo Edge (Bluetooth-receiver in HID proxy mode) */ + LDJ_DEVICE(0xb309), + .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, { /* Keyboard MX5500 (Bluetooth-receiver in HID proxy mode) */ LDJ_DEVICE(0xb30b), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, @@ -4013,6 +4042,9 @@ static const struct hid_device_id hidpp_devices[] = { { /* MX5000 keyboard over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb305), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, + { /* Dinovo Edge keyboard over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb309), + .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, { /* MX5500 keyboard over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb30b), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c index 0d27ccb55dd9..4211b9839209 100644 --- a/drivers/hid/hid-mcp2221.c +++ b/drivers/hid/hid-mcp2221.c @@ -49,6 +49,36 @@ enum { MCP2221_ALT_F_NOT_GPIOD = 0xEF, }; +/* MCP GPIO direction encoding */ +enum { + MCP2221_DIR_OUT = 0x00, + MCP2221_DIR_IN = 0x01, +}; + +#define MCP_NGPIO 4 + +/* MCP GPIO set command layout */ +struct mcp_set_gpio { + u8 cmd; + u8 dummy; + struct { + u8 change_value; + u8 value; + u8 change_direction; + u8 direction; + } gpio[MCP_NGPIO]; +} __packed; + +/* MCP GPIO get command layout */ +struct mcp_get_gpio { + u8 cmd; + u8 dummy; + struct { + u8 direction; + u8 value; + } gpio[MCP_NGPIO]; +} __packed; + /* * There is no way to distinguish responses. Therefore next command * is sent only after response to previous has been received. Mutex @@ -542,7 +572,7 @@ static int mcp_gpio_get(struct gpio_chip *gc, mcp->txbuf[0] = MCP2221_GPIO_GET; - mcp->gp_idx = (offset + 1) * 2; + mcp->gp_idx = offsetof(struct mcp_get_gpio, gpio[offset].value); mutex_lock(&mcp->lock); ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1); @@ -559,7 +589,7 @@ static void mcp_gpio_set(struct gpio_chip *gc, memset(mcp->txbuf, 0, 18); mcp->txbuf[0] = MCP2221_GPIO_SET; - mcp->gp_idx = ((offset + 1) * 4) - 1; + mcp->gp_idx = offsetof(struct mcp_set_gpio, gpio[offset].value); mcp->txbuf[mcp->gp_idx - 1] = 1; mcp->txbuf[mcp->gp_idx] = !!value; @@ -575,7 +605,7 @@ static int mcp_gpio_dir_set(struct mcp2221 *mcp, memset(mcp->txbuf, 0, 18); mcp->txbuf[0] = MCP2221_GPIO_SET; - mcp->gp_idx = (offset + 1) * 5; + mcp->gp_idx = offsetof(struct mcp_set_gpio, gpio[offset].direction); mcp->txbuf[mcp->gp_idx - 1] = 1; mcp->txbuf[mcp->gp_idx] = val; @@ -590,7 +620,7 @@ static int mcp_gpio_direction_input(struct gpio_chip *gc, struct mcp2221 *mcp = gpiochip_get_data(gc); mutex_lock(&mcp->lock); - ret = mcp_gpio_dir_set(mcp, offset, 0); + ret = mcp_gpio_dir_set(mcp, offset, MCP2221_DIR_IN); mutex_unlock(&mcp->lock); return ret; @@ -603,7 +633,7 @@ static int mcp_gpio_direction_output(struct gpio_chip *gc, struct mcp2221 *mcp = gpiochip_get_data(gc); mutex_lock(&mcp->lock); - ret = mcp_gpio_dir_set(mcp, offset, 1); + ret = mcp_gpio_dir_set(mcp, offset, MCP2221_DIR_OUT); mutex_unlock(&mcp->lock); /* Can't configure as output, bailout early */ @@ -623,7 +653,7 @@ static int mcp_gpio_get_direction(struct gpio_chip *gc, mcp->txbuf[0] = MCP2221_GPIO_GET; - mcp->gp_idx = (offset + 1) * 2; + mcp->gp_idx = offsetof(struct mcp_get_gpio, gpio[offset].direction); mutex_lock(&mcp->lock); ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1); @@ -632,7 +662,7 @@ static int mcp_gpio_get_direction(struct gpio_chip *gc, if (ret) return ret; - if (mcp->gpio_dir) + if (mcp->gpio_dir == MCP2221_DIR_IN) return GPIO_LINE_DIRECTION_IN; return GPIO_LINE_DIRECTION_OUT; @@ -758,7 +788,7 @@ static int mcp2221_raw_event(struct hid_device *hdev, mcp->status = -ENOENT; } else { mcp->status = !!data[mcp->gp_idx]; - mcp->gpio_dir = !!data[mcp->gp_idx + 1]; + mcp->gpio_dir = data[mcp->gp_idx + 1]; } break; default: @@ -860,7 +890,7 @@ static int mcp2221_probe(struct hid_device *hdev, mcp->gc->get_direction = mcp_gpio_get_direction; mcp->gc->set = mcp_gpio_set; mcp->gc->get = mcp_gpio_get; - mcp->gc->ngpio = 4; + mcp->gc->ngpio = MCP_NGPIO; mcp->gc->base = -1; mcp->gc->can_sleep = 1; mcp->gc->parent = &hdev->dev; diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 7a2be0205dfd..bf7ecab5d9e5 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -83,7 +83,12 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_FUTABA, USB_DEVICE_ID_LED_DISPLAY), HID_QUIRK_NO_INIT_REPORTS }, + { HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_SAT_ADAPTOR), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_USB_JOYPAD), HID_QUIRK_MULTI_INPUT }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_GAMEVICE, USB_DEVICE_ID_GAMEVICE_GV186), + HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, + { HID_USB_DEVICE(USB_VENDOR_ID_GAMEVICE, USB_DEVICE_ID_GAMEVICE_KISHI), + HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_DRIVING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FIGHTING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FLYING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT }, diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 94c7398b5c27..3dd7d3246737 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -483,7 +483,8 @@ static int sensor_hub_raw_event(struct hid_device *hdev, return 1; ptr = raw_data; - ptr++; /* Skip report id */ + if (report->id) + ptr++; /* Skip report id */ spin_lock_irqsave(&pdata->lock, flags); diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index 86b568037cb8..8e9c9e646cb7 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -385,6 +385,8 @@ static const struct hid_device_id uclogic_devices[] = { USB_DEVICE_ID_UCLOGIC_DRAWIMAGE_G3) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610) }, + { HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, + USB_DEVICE_ID_UGTIZER_TABLET_GT5040) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_TABLET_G5) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c index 7d20d1fcf8d2..d26d8cd98efc 100644 --- a/drivers/hid/hid-uclogic-params.c +++ b/drivers/hid/hid-uclogic-params.c @@ -997,6 +997,8 @@ int uclogic_params_init(struct uclogic_params *params, break; case VID_PID(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610): + case VID_PID(USB_VENDOR_ID_UGTIZER, + USB_DEVICE_ID_UGTIZER_TABLET_GT5040): case VID_PID(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_G540): case VID_PID(USB_VENDOR_ID_UGEE, diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 786e3e9af1c9..aeff1ffb0c8b 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -943,6 +943,11 @@ static void i2c_hid_acpi_enable_wakeup(struct device *dev) } } +static void i2c_hid_acpi_shutdown(struct device *dev) +{ + acpi_device_set_power(ACPI_COMPANION(dev), ACPI_STATE_D3_COLD); +} + static const struct acpi_device_id i2c_hid_acpi_match[] = { {"ACPI0C50", 0 }, {"PNP0C50", 0 }, @@ -959,6 +964,8 @@ static inline int i2c_hid_acpi_pdata(struct i2c_client *client, static inline void i2c_hid_acpi_fix_up_power(struct device *dev) {} static inline void i2c_hid_acpi_enable_wakeup(struct device *dev) {} + +static inline void i2c_hid_acpi_shutdown(struct device *dev) {} #endif #ifdef CONFIG_OF @@ -1175,6 +1182,8 @@ static void i2c_hid_shutdown(struct i2c_client *client) i2c_hid_set_power(client, I2C_HID_PWR_SLEEP); free_irq(client->irq, ihid); + + i2c_hid_acpi_shutdown(&client->dev); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 0cde10fe0e71..f202ac7f4b3d 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -244,9 +244,13 @@ int hv_synic_cleanup(unsigned int cpu) /* * Hyper-V does not provide a way to change the connect CPU once - * it is set; we must prevent the connect CPU from going offline. + * it is set; we must prevent the connect CPU from going offline + * while the VM is running normally. But in the panic or kexec() + * path where the vmbus is already disconnected, the CPU must be + * allowed to shut down. */ - if (cpu == VMBUS_CONNECT_CPU) + if (cpu == VMBUS_CONNECT_CPU && + vmbus_connection.conn_state == CONNECTED) return -EBUSY; /* diff --git a/drivers/hwmon/amd_energy.c b/drivers/hwmon/amd_energy.c index d06597303d5a..3197cda7bcd9 100644 --- a/drivers/hwmon/amd_energy.c +++ b/drivers/hwmon/amd_energy.c @@ -171,7 +171,7 @@ static umode_t amd_energy_is_visible(const void *_data, enum hwmon_sensor_types type, u32 attr, int channel) { - return 0444; + return 0440; } static int energy_accumulator(void *p) diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index a18887990f4a..79b498f816fe 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -32,6 +32,7 @@ #include <linux/hwmon.h> #include <linux/workqueue.h> #include <linux/err.h> +#include <linux/bits.h> /* data port used by Apple SMC */ #define APPLESMC_DATA_PORT 0x300 @@ -42,10 +43,13 @@ #define APPLESMC_MAX_DATA_LENGTH 32 -/* wait up to 128 ms for a status change. */ -#define APPLESMC_MIN_WAIT 0x0010 -#define APPLESMC_RETRY_WAIT 0x0100 -#define APPLESMC_MAX_WAIT 0x20000 +/* Apple SMC status bits */ +#define SMC_STATUS_AWAITING_DATA BIT(0) /* SMC has data waiting to be read */ +#define SMC_STATUS_IB_CLOSED BIT(1) /* Will ignore any input */ +#define SMC_STATUS_BUSY BIT(2) /* Command in progress */ + +/* Initial wait is 8us */ +#define APPLESMC_MIN_WAIT 0x0008 #define APPLESMC_READ_CMD 0x10 #define APPLESMC_WRITE_CMD 0x11 @@ -151,65 +155,84 @@ static unsigned int key_at_index; static struct workqueue_struct *applesmc_led_wq; /* - * wait_read - Wait for a byte to appear on SMC port. Callers must - * hold applesmc_lock. + * Wait for specific status bits with a mask on the SMC. + * Used before all transactions. + * This does 10 fast loops of 8us then exponentially backs off for a + * minimum total wait of 262ms. Depending on usleep_range this could + * run out past 500ms. */ -static int wait_read(void) + +static int wait_status(u8 val, u8 mask) { - unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC; u8 status; int us; + int i; - for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) { - usleep_range(us, us * 16); + us = APPLESMC_MIN_WAIT; + for (i = 0; i < 24 ; i++) { status = inb(APPLESMC_CMD_PORT); - /* read: wait for smc to settle */ - if (status & 0x01) + if ((status & mask) == val) return 0; - /* timeout: give up */ - if (time_after(jiffies, end)) - break; + usleep_range(us, us * 2); + if (i > 9) + us <<= 1; } - - pr_warn("wait_read() fail: 0x%02x\n", status); return -EIO; } -/* - * send_byte - Write to SMC port, retrying when necessary. Callers - * must hold applesmc_lock. - */ +/* send_byte - Write to SMC data port. Callers must hold applesmc_lock. */ + static int send_byte(u8 cmd, u16 port) { - u8 status; - int us; - unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC; + int status; + + status = wait_status(0, SMC_STATUS_IB_CLOSED); + if (status) + return status; + /* + * This needs to be a separate read looking for bit 0x04 + * after bit 0x02 falls. If consolidated with the wait above + * this extra read may not happen if status returns both + * simultaneously and this would appear to be required. + */ + status = wait_status(SMC_STATUS_BUSY, SMC_STATUS_BUSY); + if (status) + return status; outb(cmd, port); - for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) { - usleep_range(us, us * 16); - status = inb(APPLESMC_CMD_PORT); - /* write: wait for smc to settle */ - if (status & 0x02) - continue; - /* ready: cmd accepted, return */ - if (status & 0x04) - return 0; - /* timeout: give up */ - if (time_after(jiffies, end)) - break; - /* busy: long wait and resend */ - udelay(APPLESMC_RETRY_WAIT); - outb(cmd, port); - } - - pr_warn("send_byte(0x%02x, 0x%04x) fail: 0x%02x\n", cmd, port, status); - return -EIO; + return 0; } +/* send_command - Write a command to the SMC. Callers must hold applesmc_lock. */ + static int send_command(u8 cmd) { - return send_byte(cmd, APPLESMC_CMD_PORT); + int ret; + + ret = wait_status(0, SMC_STATUS_IB_CLOSED); + if (ret) + return ret; + outb(cmd, APPLESMC_CMD_PORT); + return 0; +} + +/* + * Based on logic from the Apple driver. This is issued before any interaction + * If busy is stuck high, issue a read command to reset the SMC state machine. + * If busy is stuck high after the command then the SMC is jammed. + */ + +static int smc_sane(void) +{ + int ret; + + ret = wait_status(0, SMC_STATUS_BUSY); + if (!ret) + return ret; + ret = send_command(APPLESMC_READ_CMD); + if (ret) + return ret; + return wait_status(0, SMC_STATUS_BUSY); } static int send_argument(const char *key) @@ -226,6 +249,11 @@ static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len) { u8 status, data = 0; int i; + int ret; + + ret = smc_sane(); + if (ret) + return ret; if (send_command(cmd) || send_argument(key)) { pr_warn("%.4s: read arg fail\n", key); @@ -239,7 +267,8 @@ static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len) } for (i = 0; i < len; i++) { - if (wait_read()) { + if (wait_status(SMC_STATUS_AWAITING_DATA | SMC_STATUS_BUSY, + SMC_STATUS_AWAITING_DATA | SMC_STATUS_BUSY)) { pr_warn("%.4s: read data[%d] fail\n", key, i); return -EIO; } @@ -250,19 +279,24 @@ static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len) for (i = 0; i < 16; i++) { udelay(APPLESMC_MIN_WAIT); status = inb(APPLESMC_CMD_PORT); - if (!(status & 0x01)) + if (!(status & SMC_STATUS_AWAITING_DATA)) break; data = inb(APPLESMC_DATA_PORT); } if (i) pr_warn("flushed %d bytes, last value is: %d\n", i, data); - return 0; + return wait_status(0, SMC_STATUS_BUSY); } static int write_smc(u8 cmd, const char *key, const u8 *buffer, u8 len) { int i; + int ret; + + ret = smc_sane(); + if (ret) + return ret; if (send_command(cmd) || send_argument(key)) { pr_warn("%s: write arg fail\n", key); @@ -281,7 +315,7 @@ static int write_smc(u8 cmd, const char *key, const u8 *buffer, u8 len) } } - return 0; + return wait_status(0, SMC_STATUS_BUSY); } static int read_register_count(unsigned int *count) diff --git a/drivers/hwmon/pmbus/max20730.c b/drivers/hwmon/pmbus/max20730.c index 57923d72490c..be83b98411c7 100644 --- a/drivers/hwmon/pmbus/max20730.c +++ b/drivers/hwmon/pmbus/max20730.c @@ -122,8 +122,8 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, switch (idx) { case MAX20730_DEBUGFS_VOUT_MIN: ret = VOLT_FROM_REG(data->mfr_voutmin * 10000); - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d.%d\n", - ret / 10000, ret % 10000); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d.%d\n", + ret / 10000, ret % 10000); break; case MAX20730_DEBUGFS_FREQUENCY: val = (data->mfr_devset1 & MAX20730_MFR_DEVSET1_FSW_MASK) @@ -141,7 +141,7 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, ret = 800; else ret = 900; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_PG_DELAY: val = (data->mfr_devset1 & MAX20730_MFR_DEVSET1_TSTAT_MASK) @@ -223,7 +223,7 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, case MAX20730_DEBUGFS_OC_PROTECT_MODE: ret = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_OCPM_MASK) >> MAX20730_MFR_DEVSET2_OCPM_BIT_POS; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_SS_TIMING: val = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_SS_MASK) @@ -241,32 +241,32 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, case MAX20730_DEBUGFS_IMAX: ret = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_IMAX_MASK) >> MAX20730_MFR_DEVSET2_IMAX_BIT_POS; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_OPERATION: ret = i2c_smbus_read_byte_data(psu->client, PMBUS_OPERATION); if (ret < 0) return ret; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_ON_OFF_CONFIG: ret = i2c_smbus_read_byte_data(psu->client, PMBUS_ON_OFF_CONFIG); if (ret < 0) return ret; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_SMBALERT_MASK: ret = i2c_smbus_read_word_data(psu->client, PMBUS_SMB_ALERT_MASK); if (ret < 0) return ret; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_VOUT_MODE: ret = i2c_smbus_read_byte_data(psu->client, PMBUS_VOUT_MODE); if (ret < 0) return ret; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_VOUT_COMMAND: ret = i2c_smbus_read_word_data(psu->client, PMBUS_VOUT_COMMAND); @@ -274,8 +274,8 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, return ret; ret = VOLT_FROM_REG(ret * 10000); - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, - "%d.%d\n", ret / 10000, ret % 10000); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, + "%d.%d\n", ret / 10000, ret % 10000); break; case MAX20730_DEBUGFS_VOUT_MAX: ret = i2c_smbus_read_word_data(psu->client, PMBUS_VOUT_MAX); @@ -283,8 +283,8 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, return ret; ret = VOLT_FROM_REG(ret * 10000); - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, - "%d.%d\n", ret / 10000, ret % 10000); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, + "%d.%d\n", ret / 10000, ret % 10000); break; default: len = strlcpy(tbuf, "Invalid\n", DEBUG_FS_DATA_MAX); diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index 170a9f82ca61..b0e2820a2d57 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -941,12 +941,16 @@ static ssize_t pmbus_show_sensor(struct device *dev, struct i2c_client *client = to_i2c_client(dev->parent); struct pmbus_sensor *sensor = to_pmbus_sensor(devattr); struct pmbus_data *data = i2c_get_clientdata(client); + ssize_t ret; + mutex_lock(&data->update_lock); pmbus_update_sensor_data(client, sensor); if (sensor->data < 0) - return sensor->data; - - return snprintf(buf, PAGE_SIZE, "%lld\n", pmbus_reg2data(data, sensor)); + ret = sensor->data; + else + ret = snprintf(buf, PAGE_SIZE, "%lld\n", pmbus_reg2data(data, sensor)); + mutex_unlock(&data->update_lock); + return ret; } static ssize_t pmbus_set_sensor(struct device *dev, @@ -2012,8 +2016,11 @@ static ssize_t pmbus_show_samples(struct device *dev, int val; struct i2c_client *client = to_i2c_client(dev->parent); struct pmbus_samples_reg *reg = to_samples_reg(devattr); + struct pmbus_data *data = i2c_get_clientdata(client); + mutex_lock(&data->update_lock); val = _pmbus_read_word_data(client, reg->page, 0xff, reg->attr->reg); + mutex_unlock(&data->update_lock); if (val < 0) return val; diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c index bdba2143021a..1f63807c0399 100644 --- a/drivers/hwmon/pwm-fan.c +++ b/drivers/hwmon/pwm-fan.c @@ -54,16 +54,18 @@ static irqreturn_t pulse_handler(int irq, void *dev_id) static void sample_timer(struct timer_list *t) { struct pwm_fan_ctx *ctx = from_timer(ctx, t, rpm_timer); + unsigned int delta = ktime_ms_delta(ktime_get(), ctx->sample_start); int pulses; - u64 tmp; - pulses = atomic_read(&ctx->pulses); - atomic_sub(pulses, &ctx->pulses); - tmp = (u64)pulses * ktime_ms_delta(ktime_get(), ctx->sample_start) * 60; - do_div(tmp, ctx->pulses_per_revolution * 1000); - ctx->rpm = tmp; + if (delta) { + pulses = atomic_read(&ctx->pulses); + atomic_sub(pulses, &ctx->pulses); + ctx->rpm = (unsigned int)(pulses * 1000 * 60) / + (ctx->pulses_per_revolution * delta); + + ctx->sample_start = ktime_get(); + } - ctx->sample_start = ktime_get(); mod_timer(&ctx->rpm_timer, jiffies + HZ); } diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index a97a9d058198..a49e0ed4a599 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -734,6 +734,7 @@ config I2C_LPC2K config I2C_MLXBF tristate "Mellanox BlueField I2C controller" depends on MELLANOX_PLATFORM && ARM64 + select I2C_SLAVE help Enabling this option will add I2C SMBus support for Mellanox BlueField system. diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index c98529c76348..e6f8d6e45a15 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -412,6 +412,19 @@ static void i2c_imx_dma_free(struct imx_i2c_struct *i2c_imx) dma->chan_using = NULL; } +static void i2c_imx_clear_irq(struct imx_i2c_struct *i2c_imx, unsigned int bits) +{ + unsigned int temp; + + /* + * i2sr_clr_opcode is the value to clear all interrupts. Here we want to + * clear only <bits>, so we write ~i2sr_clr_opcode with just <bits> + * toggled. This is required because i.MX needs W0C and Vybrid uses W1C. + */ + temp = ~i2c_imx->hwdata->i2sr_clr_opcode ^ bits; + imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2SR); +} + static int i2c_imx_bus_busy(struct imx_i2c_struct *i2c_imx, int for_busy, bool atomic) { unsigned long orig_jiffies = jiffies; @@ -424,8 +437,7 @@ static int i2c_imx_bus_busy(struct imx_i2c_struct *i2c_imx, int for_busy, bool a /* check for arbitration lost */ if (temp & I2SR_IAL) { - temp &= ~I2SR_IAL; - imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2SR); + i2c_imx_clear_irq(i2c_imx, I2SR_IAL); return -EAGAIN; } @@ -469,7 +481,7 @@ static int i2c_imx_trx_complete(struct imx_i2c_struct *i2c_imx, bool atomic) */ readb_poll_timeout_atomic(addr, regval, regval & I2SR_IIF, 5, 1000 + 100); i2c_imx->i2csr = regval; - imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2SR); + i2c_imx_clear_irq(i2c_imx, I2SR_IIF | I2SR_IAL); } else { wait_event_timeout(i2c_imx->queue, i2c_imx->i2csr & I2SR_IIF, HZ / 10); } @@ -478,6 +490,16 @@ static int i2c_imx_trx_complete(struct imx_i2c_struct *i2c_imx, bool atomic) dev_dbg(&i2c_imx->adapter.dev, "<%s> Timeout\n", __func__); return -ETIMEDOUT; } + + /* check for arbitration lost */ + if (i2c_imx->i2csr & I2SR_IAL) { + dev_dbg(&i2c_imx->adapter.dev, "<%s> Arbitration lost\n", __func__); + i2c_imx_clear_irq(i2c_imx, I2SR_IAL); + + i2c_imx->i2csr = 0; + return -EAGAIN; + } + dev_dbg(&i2c_imx->adapter.dev, "<%s> TRX complete\n", __func__); i2c_imx->i2csr = 0; return 0; @@ -593,6 +615,8 @@ static void i2c_imx_stop(struct imx_i2c_struct *i2c_imx, bool atomic) /* Stop I2C transaction */ dev_dbg(&i2c_imx->adapter.dev, "<%s>\n", __func__); temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); + if (!(temp & I2CR_MSTA)) + i2c_imx->stopped = 1; temp &= ~(I2CR_MSTA | I2CR_MTX); if (i2c_imx->dma) temp &= ~I2CR_DMAEN; @@ -623,9 +647,7 @@ static irqreturn_t i2c_imx_isr(int irq, void *dev_id) if (temp & I2SR_IIF) { /* save status register */ i2c_imx->i2csr = temp; - temp &= ~I2SR_IIF; - temp |= (i2c_imx->hwdata->i2sr_clr_opcode & I2SR_IIF); - imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2SR); + i2c_imx_clear_irq(i2c_imx, I2SR_IIF); wake_up(&i2c_imx->queue); return IRQ_HANDLED; } @@ -758,9 +780,12 @@ static int i2c_imx_dma_read(struct imx_i2c_struct *i2c_imx, */ dev_dbg(dev, "<%s> clear MSTA\n", __func__); temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); + if (!(temp & I2CR_MSTA)) + i2c_imx->stopped = 1; temp &= ~(I2CR_MSTA | I2CR_MTX); imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR); - i2c_imx_bus_busy(i2c_imx, 0, false); + if (!i2c_imx->stopped) + i2c_imx_bus_busy(i2c_imx, 0, false); } else { /* * For i2c master receiver repeat restart operation like: @@ -885,9 +910,12 @@ static int i2c_imx_read(struct imx_i2c_struct *i2c_imx, struct i2c_msg *msgs, dev_dbg(&i2c_imx->adapter.dev, "<%s> clear MSTA\n", __func__); temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR); + if (!(temp & I2CR_MSTA)) + i2c_imx->stopped = 1; temp &= ~(I2CR_MSTA | I2CR_MTX); imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR); - i2c_imx_bus_busy(i2c_imx, 0, atomic); + if (!i2c_imx->stopped) + i2c_imx_bus_busy(i2c_imx, 0, atomic); } else { /* * For i2c master receiver repeat restart operation like: diff --git a/drivers/i2c/busses/i2c-mlxbf.c b/drivers/i2c/busses/i2c-mlxbf.c index 33574d40ea9c..2fb0532d8a16 100644 --- a/drivers/i2c/busses/i2c-mlxbf.c +++ b/drivers/i2c/busses/i2c-mlxbf.c @@ -1258,9 +1258,9 @@ static int mlxbf_i2c_get_gpio(struct platform_device *pdev, return -EFAULT; gpio_res->io = devm_ioremap(dev, params->start, size); - if (IS_ERR(gpio_res->io)) { + if (!gpio_res->io) { devm_release_mem_region(dev, params->start, size); - return PTR_ERR(gpio_res->io); + return -ENOMEM; } return 0; @@ -1323,9 +1323,9 @@ static int mlxbf_i2c_get_corepll(struct platform_device *pdev, return -EFAULT; corepll_res->io = devm_ioremap(dev, params->start, size); - if (IS_ERR(corepll_res->io)) { + if (!corepll_res->io) { devm_release_mem_region(dev, params->start, size); - return PTR_ERR(corepll_res->io); + return -ENOMEM; } return 0; @@ -1717,9 +1717,9 @@ static int mlxbf_i2c_init_coalesce(struct platform_device *pdev, return -EFAULT; coalesce_res->io = ioremap(params->start, size); - if (IS_ERR(coalesce_res->io)) { + if (!coalesce_res->io) { release_mem_region(params->start, size); - return PTR_ERR(coalesce_res->io); + return -ENOMEM; } priv->coalesce = coalesce_res; diff --git a/drivers/i2c/busses/i2c-qcom-cci.c b/drivers/i2c/busses/i2c-qcom-cci.c index f13735beca58..1c259b5188de 100644 --- a/drivers/i2c/busses/i2c-qcom-cci.c +++ b/drivers/i2c/busses/i2c-qcom-cci.c @@ -194,9 +194,9 @@ static irqreturn_t cci_isr(int irq, void *dev) if (unlikely(val & CCI_IRQ_STATUS_0_I2C_M1_ERROR)) { if (val & CCI_IRQ_STATUS_0_I2C_M1_Q0_NACK_ERR || val & CCI_IRQ_STATUS_0_I2C_M1_Q1_NACK_ERR) - cci->master[0].status = -ENXIO; + cci->master[1].status = -ENXIO; else - cci->master[0].status = -EIO; + cci->master[1].status = -EIO; writel(CCI_HALT_REQ_I2C_M1_Q0Q1, cci->base + CCI_HALT_REQ); ret = IRQ_HANDLED; diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c index fbc04b60cfd1..5a47915869ae 100644 --- a/drivers/i2c/busses/i2c-qup.c +++ b/drivers/i2c/busses/i2c-qup.c @@ -801,7 +801,8 @@ static int qup_i2c_bam_schedule_desc(struct qup_i2c_dev *qup) if (ret || qup->bus_err || qup->qup_err) { reinit_completion(&qup->xfer); - if (qup_i2c_change_state(qup, QUP_RUN_STATE)) { + ret = qup_i2c_change_state(qup, QUP_RUN_STATE); + if (ret) { dev_err(qup->dev, "change to run state timed out"); goto desc_err; } diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 01bace49a962..d79335506ecd 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -126,26 +126,9 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state = &drv->states[index]; unsigned long eax = flg2MWAIT(state->flags); unsigned long ecx = 1; /* break on interrupt flag */ - bool tick; - - if (!static_cpu_has(X86_FEATURE_ARAT)) { - /* - * Switch over to one-shot tick broadcast if the target C-state - * is deeper than C1. - */ - if ((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) { - tick = true; - tick_broadcast_enter(); - } else { - tick = false; - } - } mwait_idle_with_hints(eax, ecx); - if (!static_cpu_has(X86_FEATURE_ARAT) && tick) - tick_broadcast_exit(); - return index; } @@ -1157,6 +1140,20 @@ static bool __init intel_idle_max_cstate_reached(int cstate) return false; } +static bool __init intel_idle_state_needs_timer_stop(struct cpuidle_state *state) +{ + unsigned long eax = flg2MWAIT(state->flags); + + if (boot_cpu_has(X86_FEATURE_ARAT)) + return false; + + /* + * Switch over to one-shot tick broadcast if the target C-state + * is deeper than C1. + */ + return !!((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK); +} + #ifdef CONFIG_ACPI_PROCESSOR_CSTATE #include <acpi/processor.h> @@ -1269,6 +1266,9 @@ static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv) if (disabled_states_mask & BIT(cstate)) state->flags |= CPUIDLE_FLAG_OFF; + if (intel_idle_state_needs_timer_stop(state)) + state->flags |= CPUIDLE_FLAG_TIMER_STOP; + state->enter = intel_idle; state->enter_s2idle = intel_idle_s2idle; } @@ -1507,6 +1507,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) !(cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_ALWAYS_ENABLE))) drv->states[drv->state_count].flags |= CPUIDLE_FLAG_OFF; + if (intel_idle_state_needs_timer_stop(&drv->states[drv->state_count])) + drv->states[drv->state_count].flags |= CPUIDLE_FLAG_TIMER_STOP; + drv->state_count++; } diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c index beb38d9d607d..560a3373ff20 100644 --- a/drivers/iio/accel/kxcjk-1013.c +++ b/drivers/iio/accel/kxcjk-1013.c @@ -126,6 +126,12 @@ enum kx_chipset { KX_MAX_CHIPS /* this must be last */ }; +enum kx_acpi_type { + ACPI_GENERIC, + ACPI_SMO8500, + ACPI_KIOX010A, +}; + struct kxcjk1013_data { struct i2c_client *client; struct iio_trigger *dready_trig; @@ -143,7 +149,7 @@ struct kxcjk1013_data { bool motion_trigger_on; int64_t timestamp; enum kx_chipset chipset; - bool is_smo8500_device; + enum kx_acpi_type acpi_type; }; enum kxcjk1013_axis { @@ -270,6 +276,32 @@ static const struct { {19163, 1, 0}, {38326, 0, 1} }; +#ifdef CONFIG_ACPI +enum kiox010a_fn_index { + KIOX010A_SET_LAPTOP_MODE = 1, + KIOX010A_SET_TABLET_MODE = 2, +}; + +static int kiox010a_dsm(struct device *dev, int fn_index) +{ + acpi_handle handle = ACPI_HANDLE(dev); + guid_t kiox010a_dsm_guid; + union acpi_object *obj; + + if (!handle) + return -ENODEV; + + guid_parse("1f339696-d475-4e26-8cad-2e9f8e6d7a91", &kiox010a_dsm_guid); + + obj = acpi_evaluate_dsm(handle, &kiox010a_dsm_guid, 1, fn_index, NULL); + if (!obj) + return -EIO; + + ACPI_FREE(obj); + return 0; +} +#endif + static int kxcjk1013_set_mode(struct kxcjk1013_data *data, enum kxcjk1013_mode mode) { @@ -347,6 +379,13 @@ static int kxcjk1013_chip_init(struct kxcjk1013_data *data) { int ret; +#ifdef CONFIG_ACPI + if (data->acpi_type == ACPI_KIOX010A) { + /* Make sure the kbd and touchpad on 2-in-1s using 2 KXCJ91008-s work */ + kiox010a_dsm(&data->client->dev, KIOX010A_SET_LAPTOP_MODE); + } +#endif + ret = i2c_smbus_read_byte_data(data->client, KXCJK1013_REG_WHO_AM_I); if (ret < 0) { dev_err(&data->client->dev, "Error reading who_am_i\n"); @@ -1247,7 +1286,7 @@ static irqreturn_t kxcjk1013_data_rdy_trig_poll(int irq, void *private) static const char *kxcjk1013_match_acpi_device(struct device *dev, enum kx_chipset *chipset, - bool *is_smo8500_device) + enum kx_acpi_type *acpi_type) { const struct acpi_device_id *id; @@ -1256,7 +1295,9 @@ static const char *kxcjk1013_match_acpi_device(struct device *dev, return NULL; if (strcmp(id->id, "SMO8500") == 0) - *is_smo8500_device = true; + *acpi_type = ACPI_SMO8500; + else if (strcmp(id->id, "KIOX010A") == 0) + *acpi_type = ACPI_KIOX010A; *chipset = (enum kx_chipset)id->driver_data; @@ -1299,7 +1340,7 @@ static int kxcjk1013_probe(struct i2c_client *client, } else if (ACPI_HANDLE(&client->dev)) { name = kxcjk1013_match_acpi_device(&client->dev, &data->chipset, - &data->is_smo8500_device); + &data->acpi_type); } else return -ENODEV; @@ -1316,7 +1357,7 @@ static int kxcjk1013_probe(struct i2c_client *client, indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->info = &kxcjk1013_info; - if (client->irq > 0 && !data->is_smo8500_device) { + if (client->irq > 0 && data->acpi_type != ACPI_SMO8500) { ret = devm_request_threaded_irq(&client->dev, client->irq, kxcjk1013_data_rdy_trig_poll, kxcjk1013_event_handler, diff --git a/drivers/iio/adc/ingenic-adc.c b/drivers/iio/adc/ingenic-adc.c index 92b25083e23f..1aafbe2cfe67 100644 --- a/drivers/iio/adc/ingenic-adc.c +++ b/drivers/iio/adc/ingenic-adc.c @@ -71,7 +71,7 @@ #define JZ4725B_ADC_BATTERY_HIGH_VREF_BITS 10 #define JZ4740_ADC_BATTERY_HIGH_VREF (7500 * 0.986) #define JZ4740_ADC_BATTERY_HIGH_VREF_BITS 12 -#define JZ4770_ADC_BATTERY_VREF 6600 +#define JZ4770_ADC_BATTERY_VREF 1200 #define JZ4770_ADC_BATTERY_VREF_BITS 12 #define JZ_ADC_IRQ_AUX BIT(0) @@ -177,13 +177,12 @@ static void ingenic_adc_set_config(struct ingenic_adc *adc, mutex_unlock(&adc->lock); } -static void ingenic_adc_enable(struct ingenic_adc *adc, - int engine, - bool enabled) +static void ingenic_adc_enable_unlocked(struct ingenic_adc *adc, + int engine, + bool enabled) { u8 val; - mutex_lock(&adc->lock); val = readb(adc->base + JZ_ADC_REG_ENABLE); if (enabled) @@ -192,20 +191,41 @@ static void ingenic_adc_enable(struct ingenic_adc *adc, val &= ~BIT(engine); writeb(val, adc->base + JZ_ADC_REG_ENABLE); +} + +static void ingenic_adc_enable(struct ingenic_adc *adc, + int engine, + bool enabled) +{ + mutex_lock(&adc->lock); + ingenic_adc_enable_unlocked(adc, engine, enabled); mutex_unlock(&adc->lock); } static int ingenic_adc_capture(struct ingenic_adc *adc, int engine) { + u32 cfg; u8 val; int ret; - ingenic_adc_enable(adc, engine, true); + /* + * Disable CMD_SEL temporarily, because it causes wrong VBAT readings, + * probably due to the switch of VREF. We must keep the lock here to + * avoid races with the buffer enable/disable functions. + */ + mutex_lock(&adc->lock); + cfg = readl(adc->base + JZ_ADC_REG_CFG); + writel(cfg & ~JZ_ADC_REG_CFG_CMD_SEL, adc->base + JZ_ADC_REG_CFG); + + ingenic_adc_enable_unlocked(adc, engine, true); ret = readb_poll_timeout(adc->base + JZ_ADC_REG_ENABLE, val, !(val & BIT(engine)), 250, 1000); if (ret) - ingenic_adc_enable(adc, engine, false); + ingenic_adc_enable_unlocked(adc, engine, false); + + writel(cfg, adc->base + JZ_ADC_REG_CFG); + mutex_unlock(&adc->lock); return ret; } diff --git a/drivers/iio/adc/mt6577_auxadc.c b/drivers/iio/adc/mt6577_auxadc.c index ac415cb089cd..79c1dd68b909 100644 --- a/drivers/iio/adc/mt6577_auxadc.c +++ b/drivers/iio/adc/mt6577_auxadc.c @@ -9,9 +9,9 @@ #include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> -#include <linux/of.h> -#include <linux/of_device.h> +#include <linux/mod_devicetable.h> #include <linux/platform_device.h> +#include <linux/property.h> #include <linux/iopoll.h> #include <linux/io.h> #include <linux/iio/iio.h> @@ -276,6 +276,8 @@ static int mt6577_auxadc_probe(struct platform_device *pdev) goto err_disable_clk; } + adc_dev->dev_comp = device_get_match_data(&pdev->dev); + mutex_init(&adc_dev->lock); mt6577_auxadc_mod_reg(adc_dev->reg_base + MT6577_AUXADC_MISC, diff --git a/drivers/iio/adc/stm32-adc-core.c b/drivers/iio/adc/stm32-adc-core.c index cd870c089182..a83199b212a4 100644 --- a/drivers/iio/adc/stm32-adc-core.c +++ b/drivers/iio/adc/stm32-adc-core.c @@ -41,18 +41,16 @@ * struct stm32_adc_common_regs - stm32 common registers * @csr: common status register offset * @ccr: common control register offset - * @eoc1_msk: adc1 end of conversion flag in @csr - * @eoc2_msk: adc2 end of conversion flag in @csr - * @eoc3_msk: adc3 end of conversion flag in @csr + * @eoc_msk: array of eoc (end of conversion flag) masks in csr for adc1..n + * @ovr_msk: array of ovr (overrun flag) masks in csr for adc1..n * @ier: interrupt enable register offset for each adc * @eocie_msk: end of conversion interrupt enable mask in @ier */ struct stm32_adc_common_regs { u32 csr; u32 ccr; - u32 eoc1_msk; - u32 eoc2_msk; - u32 eoc3_msk; + u32 eoc_msk[STM32_ADC_MAX_ADCS]; + u32 ovr_msk[STM32_ADC_MAX_ADCS]; u32 ier; u32 eocie_msk; }; @@ -282,21 +280,20 @@ out: static const struct stm32_adc_common_regs stm32f4_adc_common_regs = { .csr = STM32F4_ADC_CSR, .ccr = STM32F4_ADC_CCR, - .eoc1_msk = STM32F4_EOC1 | STM32F4_OVR1, - .eoc2_msk = STM32F4_EOC2 | STM32F4_OVR2, - .eoc3_msk = STM32F4_EOC3 | STM32F4_OVR3, + .eoc_msk = { STM32F4_EOC1, STM32F4_EOC2, STM32F4_EOC3}, + .ovr_msk = { STM32F4_OVR1, STM32F4_OVR2, STM32F4_OVR3}, .ier = STM32F4_ADC_CR1, - .eocie_msk = STM32F4_EOCIE | STM32F4_OVRIE, + .eocie_msk = STM32F4_EOCIE, }; /* STM32H7 common registers definitions */ static const struct stm32_adc_common_regs stm32h7_adc_common_regs = { .csr = STM32H7_ADC_CSR, .ccr = STM32H7_ADC_CCR, - .eoc1_msk = STM32H7_EOC_MST | STM32H7_OVR_MST, - .eoc2_msk = STM32H7_EOC_SLV | STM32H7_OVR_SLV, + .eoc_msk = { STM32H7_EOC_MST, STM32H7_EOC_SLV}, + .ovr_msk = { STM32H7_OVR_MST, STM32H7_OVR_SLV}, .ier = STM32H7_ADC_IER, - .eocie_msk = STM32H7_EOCIE | STM32H7_OVRIE, + .eocie_msk = STM32H7_EOCIE, }; static const unsigned int stm32_adc_offset[STM32_ADC_MAX_ADCS] = { @@ -318,6 +315,7 @@ static void stm32_adc_irq_handler(struct irq_desc *desc) { struct stm32_adc_priv *priv = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); + int i; u32 status; chained_irq_enter(chip, desc); @@ -335,17 +333,12 @@ static void stm32_adc_irq_handler(struct irq_desc *desc) * before invoking the interrupt handler (e.g. call ISR only for * IRQ-enabled ADCs). */ - if (status & priv->cfg->regs->eoc1_msk && - stm32_adc_eoc_enabled(priv, 0)) - generic_handle_irq(irq_find_mapping(priv->domain, 0)); - - if (status & priv->cfg->regs->eoc2_msk && - stm32_adc_eoc_enabled(priv, 1)) - generic_handle_irq(irq_find_mapping(priv->domain, 1)); - - if (status & priv->cfg->regs->eoc3_msk && - stm32_adc_eoc_enabled(priv, 2)) - generic_handle_irq(irq_find_mapping(priv->domain, 2)); + for (i = 0; i < priv->cfg->num_irqs; i++) { + if ((status & priv->cfg->regs->eoc_msk[i] && + stm32_adc_eoc_enabled(priv, i)) || + (status & priv->cfg->regs->ovr_msk[i])) + generic_handle_irq(irq_find_mapping(priv->domain, i)); + } chained_irq_exit(chip, desc); }; diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index b3f31f147347..16c02c30dec7 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -154,6 +154,7 @@ struct stm32_adc; * @start_conv: routine to start conversions * @stop_conv: routine to stop conversions * @unprepare: optional unprepare routine (disable, power-down) + * @irq_clear: routine to clear irqs * @smp_cycles: programmable sampling time (ADC clock cycles) */ struct stm32_adc_cfg { @@ -166,6 +167,7 @@ struct stm32_adc_cfg { void (*start_conv)(struct iio_dev *, bool dma); void (*stop_conv)(struct iio_dev *); void (*unprepare)(struct iio_dev *); + void (*irq_clear)(struct iio_dev *indio_dev, u32 msk); const unsigned int *smp_cycles; }; @@ -621,6 +623,13 @@ static void stm32f4_adc_stop_conv(struct iio_dev *indio_dev) STM32F4_ADON | STM32F4_DMA | STM32F4_DDS); } +static void stm32f4_adc_irq_clear(struct iio_dev *indio_dev, u32 msk) +{ + struct stm32_adc *adc = iio_priv(indio_dev); + + stm32_adc_clr_bits(adc, adc->cfg->regs->isr_eoc.reg, msk); +} + static void stm32h7_adc_start_conv(struct iio_dev *indio_dev, bool dma) { struct stm32_adc *adc = iio_priv(indio_dev); @@ -659,6 +668,13 @@ static void stm32h7_adc_stop_conv(struct iio_dev *indio_dev) stm32_adc_clr_bits(adc, STM32H7_ADC_CFGR, STM32H7_DMNGT_MASK); } +static void stm32h7_adc_irq_clear(struct iio_dev *indio_dev, u32 msk) +{ + struct stm32_adc *adc = iio_priv(indio_dev); + /* On STM32H7 IRQs are cleared by writing 1 into ISR register */ + stm32_adc_set_bits(adc, adc->cfg->regs->isr_eoc.reg, msk); +} + static int stm32h7_adc_exit_pwr_down(struct iio_dev *indio_dev) { struct stm32_adc *adc = iio_priv(indio_dev); @@ -1235,17 +1251,40 @@ static int stm32_adc_read_raw(struct iio_dev *indio_dev, } } +static void stm32_adc_irq_clear(struct iio_dev *indio_dev, u32 msk) +{ + struct stm32_adc *adc = iio_priv(indio_dev); + + adc->cfg->irq_clear(indio_dev, msk); +} + static irqreturn_t stm32_adc_threaded_isr(int irq, void *data) { struct iio_dev *indio_dev = data; struct stm32_adc *adc = iio_priv(indio_dev); const struct stm32_adc_regspec *regs = adc->cfg->regs; u32 status = stm32_adc_readl(adc, regs->isr_eoc.reg); + u32 mask = stm32_adc_readl(adc, regs->ier_eoc.reg); - if (status & regs->isr_ovr.mask) + /* Check ovr status right now, as ovr mask should be already disabled */ + if (status & regs->isr_ovr.mask) { + /* + * Clear ovr bit to avoid subsequent calls to IRQ handler. + * This requires to stop ADC first. OVR bit state in ISR, + * is propaged to CSR register by hardware. + */ + adc->cfg->stop_conv(indio_dev); + stm32_adc_irq_clear(indio_dev, regs->isr_ovr.mask); dev_err(&indio_dev->dev, "Overrun, stopping: restart needed\n"); + return IRQ_HANDLED; + } - return IRQ_HANDLED; + if (!(status & mask)) + dev_err_ratelimited(&indio_dev->dev, + "Unexpected IRQ: IER=0x%08x, ISR=0x%08x\n", + mask, status); + + return IRQ_NONE; } static irqreturn_t stm32_adc_isr(int irq, void *data) @@ -1254,6 +1293,10 @@ static irqreturn_t stm32_adc_isr(int irq, void *data) struct stm32_adc *adc = iio_priv(indio_dev); const struct stm32_adc_regspec *regs = adc->cfg->regs; u32 status = stm32_adc_readl(adc, regs->isr_eoc.reg); + u32 mask = stm32_adc_readl(adc, regs->ier_eoc.reg); + + if (!(status & mask)) + return IRQ_WAKE_THREAD; if (status & regs->isr_ovr.mask) { /* @@ -2046,6 +2089,7 @@ static const struct stm32_adc_cfg stm32f4_adc_cfg = { .start_conv = stm32f4_adc_start_conv, .stop_conv = stm32f4_adc_stop_conv, .smp_cycles = stm32f4_adc_smp_cycles, + .irq_clear = stm32f4_adc_irq_clear, }; static const struct stm32_adc_cfg stm32h7_adc_cfg = { @@ -2057,6 +2101,7 @@ static const struct stm32_adc_cfg stm32h7_adc_cfg = { .prepare = stm32h7_adc_prepare, .unprepare = stm32h7_adc_unprepare, .smp_cycles = stm32h7_adc_smp_cycles, + .irq_clear = stm32h7_adc_irq_clear, }; static const struct stm32_adc_cfg stm32mp1_adc_cfg = { @@ -2069,6 +2114,7 @@ static const struct stm32_adc_cfg stm32mp1_adc_cfg = { .prepare = stm32h7_adc_prepare, .unprepare = stm32h7_adc_unprepare, .smp_cycles = stm32h7_adc_smp_cycles, + .irq_clear = stm32h7_adc_irq_clear, }; static const struct of_device_id stm32_adc_of_match[] = { diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c index c62cacc04672..e3f507771f17 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c @@ -256,7 +256,7 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, struct cros_ec_sensorhub *sensor_hub = dev_get_drvdata(dev->parent); struct cros_ec_dev *ec = sensor_hub->ec; struct cros_ec_sensor_platform *sensor_platform = dev_get_platdata(dev); - u32 ver_mask; + u32 ver_mask, temp; int frequencies[ARRAY_SIZE(state->frequencies) / 2] = { 0 }; int ret, i; @@ -311,10 +311,16 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, &frequencies[2], &state->fifo_max_event_count); } else { - frequencies[1] = state->resp->info_3.min_frequency; - frequencies[2] = state->resp->info_3.max_frequency; - state->fifo_max_event_count = - state->resp->info_3.fifo_max_event_count; + if (state->resp->info_3.max_frequency == 0) { + get_default_min_max_freq(state->resp->info.type, + &frequencies[1], + &frequencies[2], + &temp); + } else { + frequencies[1] = state->resp->info_3.min_frequency; + frequencies[2] = state->resp->info_3.max_frequency; + } + state->fifo_max_event_count = state->resp->info_3.fifo_max_event_count; } for (i = 0; i < ARRAY_SIZE(frequencies); i++) { state->frequencies[2 * i] = frequencies[i] / 1000; diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c index 8c8d8870ca07..99562ba85ee4 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c @@ -156,11 +156,13 @@ static const struct st_lsm6dsx_ext_dev_settings st_lsm6dsx_ext_dev_table[] = { static void st_lsm6dsx_shub_wait_complete(struct st_lsm6dsx_hw *hw) { struct st_lsm6dsx_sensor *sensor; - u32 odr; + u32 odr, timeout; sensor = iio_priv(hw->iio_devs[ST_LSM6DSX_ID_ACC]); odr = (hw->enable_mask & BIT(ST_LSM6DSX_ID_ACC)) ? sensor->odr : 12500; - msleep((2000000U / odr) + 1); + /* set 10ms as minimum timeout for i2c slave configuration */ + timeout = max_t(u32, 2000000U / odr + 1, 10); + msleep(timeout); } /* diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig index cade6dc0305b..33ad4dd0b5c7 100644 --- a/drivers/iio/light/Kconfig +++ b/drivers/iio/light/Kconfig @@ -544,6 +544,7 @@ config VCNL4000 config VCNL4035 tristate "VCNL4035 combined ALS and proximity sensor" + select IIO_BUFFER select IIO_TRIGGERED_BUFFER select REGMAP_I2C depends on I2C diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig index 32a51432ec4f..9325e189a215 100644 --- a/drivers/infiniband/Kconfig +++ b/drivers/infiniband/Kconfig @@ -73,6 +73,9 @@ config INFINIBAND_ADDR_TRANS_CONFIGFS This allows the user to config the default GID type that the CM uses for each device, when initiaing new connections. +config INFINIBAND_VIRT_DMA + def_bool !HIGHMEM + if INFINIBAND_USER_ACCESS || !INFINIBAND_USER_ACCESS source "drivers/infiniband/hw/mthca/Kconfig" source "drivers/infiniband/hw/qib/Kconfig" diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index 8017c40dd110..7989b7e1d1c0 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -1269,9 +1269,6 @@ ssize_t rdma_query_gid_table(struct ib_device *device, unsigned long flags; rdma_for_each_port(device, port_num) { - if (!rdma_ib_or_roce(device, port_num)) - continue; - table = rdma_gid_table(device, port_num); read_lock_irqsave(&table->rwlock, flags); for (i = 0; i < table->sz; i++) { diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 5740d1ba3568..5afd142fe8c7 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -859,8 +859,8 @@ static struct cm_id_private *cm_alloc_id_priv(struct ib_device *device, atomic_set(&cm_id_priv->work_count, -1); refcount_set(&cm_id_priv->refcount, 1); - ret = xa_alloc_cyclic_irq(&cm.local_id_table, &id, NULL, xa_limit_32b, - &cm.local_id_next, GFP_KERNEL); + ret = xa_alloc_cyclic(&cm.local_id_table, &id, NULL, xa_limit_32b, + &cm.local_id_next, GFP_KERNEL); if (ret < 0) goto error; cm_id_priv->id.local_id = (__force __be32)id ^ cm.random_id_operand; @@ -878,8 +878,8 @@ error: */ static void cm_finalize_id(struct cm_id_private *cm_id_priv) { - xa_store_irq(&cm.local_id_table, cm_local_id(cm_id_priv->id.local_id), - cm_id_priv, GFP_KERNEL); + xa_store(&cm.local_id_table, cm_local_id(cm_id_priv->id.local_id), + cm_id_priv, GFP_ATOMIC); } struct ib_cm_id *ib_create_cm_id(struct ib_device *device, @@ -1169,7 +1169,7 @@ retest: spin_unlock(&cm.lock); spin_unlock_irq(&cm_id_priv->lock); - xa_erase_irq(&cm.local_id_table, cm_local_id(cm_id->local_id)); + xa_erase(&cm.local_id_table, cm_local_id(cm_id->local_id)); cm_deref_id(cm_id_priv); wait_for_completion(&cm_id_priv->comp); while ((work = cm_dequeue_work(cm_id_priv)) != NULL) @@ -1522,6 +1522,7 @@ int ib_send_cm_req(struct ib_cm_id *cm_id, id.local_id); if (IS_ERR(cm_id_priv->timewait_info)) { ret = PTR_ERR(cm_id_priv->timewait_info); + cm_id_priv->timewait_info = NULL; goto out; } @@ -2114,6 +2115,7 @@ static int cm_req_handler(struct cm_work *work) id.local_id); if (IS_ERR(cm_id_priv->timewait_info)) { ret = PTR_ERR(cm_id_priv->timewait_info); + cm_id_priv->timewait_info = NULL; goto destroy; } cm_id_priv->timewait_info->work.remote_id = cm_id_priv->id.remote_id; @@ -4482,7 +4484,7 @@ static int __init ib_cm_init(void) cm.remote_id_table = RB_ROOT; cm.remote_qp_table = RB_ROOT; cm.remote_sidr_table = RB_ROOT; - xa_init_flags(&cm.local_id_table, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ); + xa_init_flags(&cm.local_id_table, XA_FLAGS_ALLOC); get_random_bytes(&cm.random_id_operand, sizeof cm.random_id_operand); INIT_LIST_HEAD(&cm.timewait_list); diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 191e0843f090..4e940fc50bba 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -940,8 +940,8 @@ int efa_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, 1); EFA_SET(¶ms.modify_mask, EFA_ADMIN_MODIFY_QP_CMD_CUR_QP_STATE, 1); - params.cur_qp_state = qp_attr->cur_qp_state; - params.qp_state = qp_attr->qp_state; + params.cur_qp_state = cur_state; + params.qp_state = new_state; } if (qp_attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY) { diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 7eaf99538216..c87b94ea2939 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -15245,7 +15245,8 @@ int hfi1_init_dd(struct hfi1_devdata *dd) & CCE_REVISION_SW_MASK); /* alloc netdev data */ - if (hfi1_netdev_alloc(dd)) + ret = hfi1_netdev_alloc(dd); + if (ret) goto bail_cleanup; ret = set_up_context_variables(dd); diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 8ca51e43cf53..329ee4f48d95 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -1,4 +1,5 @@ /* + * Copyright(c) 2020 Cornelis Networks, Inc. * Copyright(c) 2015-2020 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -206,8 +207,6 @@ static int hfi1_file_open(struct inode *inode, struct file *fp) spin_lock_init(&fd->tid_lock); spin_lock_init(&fd->invalid_lock); fd->rec_cpu_num = -1; /* no cpu affinity by default */ - fd->mm = current->mm; - mmgrab(fd->mm); fd->dd = dd; fp->private_data = fd; return 0; @@ -711,7 +710,6 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) deallocate_ctxt(uctxt); done: - mmdrop(fdata->mm); if (atomic_dec_and_test(&dd->user_refcount)) complete(&dd->user_comp); diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index b4c6bff60a4e..e09e8244a94c 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -1,6 +1,7 @@ #ifndef _HFI1_KERNEL_H #define _HFI1_KERNEL_H /* + * Copyright(c) 2020 Cornelis Networks, Inc. * Copyright(c) 2015-2020 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -1451,7 +1452,6 @@ struct hfi1_filedata { u32 invalid_tid_idx; /* protect invalid_tids array and invalid_tid_idx */ spinlock_t invalid_lock; - struct mm_struct *mm; }; extern struct xarray hfi1_dev_table; diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index 24ca17b77b72..f3fb28e3d5d7 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -1,4 +1,5 @@ /* + * Copyright(c) 2020 Cornelis Networks, Inc. * Copyright(c) 2016 - 2017 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -48,23 +49,11 @@ #include <linux/rculist.h> #include <linux/mmu_notifier.h> #include <linux/interval_tree_generic.h> +#include <linux/sched/mm.h> #include "mmu_rb.h" #include "trace.h" -struct mmu_rb_handler { - struct mmu_notifier mn; - struct rb_root_cached root; - void *ops_arg; - spinlock_t lock; /* protect the RB tree */ - struct mmu_rb_ops *ops; - struct mm_struct *mm; - struct list_head lru_list; - struct work_struct del_work; - struct list_head del_list; - struct workqueue_struct *wq; -}; - static unsigned long mmu_node_start(struct mmu_rb_node *); static unsigned long mmu_node_last(struct mmu_rb_node *); static int mmu_notifier_range_start(struct mmu_notifier *, @@ -92,37 +81,36 @@ static unsigned long mmu_node_last(struct mmu_rb_node *node) return PAGE_ALIGN(node->addr + node->len) - 1; } -int hfi1_mmu_rb_register(void *ops_arg, struct mm_struct *mm, +int hfi1_mmu_rb_register(void *ops_arg, struct mmu_rb_ops *ops, struct workqueue_struct *wq, struct mmu_rb_handler **handler) { - struct mmu_rb_handler *handlr; + struct mmu_rb_handler *h; int ret; - handlr = kmalloc(sizeof(*handlr), GFP_KERNEL); - if (!handlr) + h = kmalloc(sizeof(*h), GFP_KERNEL); + if (!h) return -ENOMEM; - handlr->root = RB_ROOT_CACHED; - handlr->ops = ops; - handlr->ops_arg = ops_arg; - INIT_HLIST_NODE(&handlr->mn.hlist); - spin_lock_init(&handlr->lock); - handlr->mn.ops = &mn_opts; - handlr->mm = mm; - INIT_WORK(&handlr->del_work, handle_remove); - INIT_LIST_HEAD(&handlr->del_list); - INIT_LIST_HEAD(&handlr->lru_list); - handlr->wq = wq; - - ret = mmu_notifier_register(&handlr->mn, handlr->mm); + h->root = RB_ROOT_CACHED; + h->ops = ops; + h->ops_arg = ops_arg; + INIT_HLIST_NODE(&h->mn.hlist); + spin_lock_init(&h->lock); + h->mn.ops = &mn_opts; + INIT_WORK(&h->del_work, handle_remove); + INIT_LIST_HEAD(&h->del_list); + INIT_LIST_HEAD(&h->lru_list); + h->wq = wq; + + ret = mmu_notifier_register(&h->mn, current->mm); if (ret) { - kfree(handlr); + kfree(h); return ret; } - *handler = handlr; + *handler = h; return 0; } @@ -134,7 +122,7 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) struct list_head del_list; /* Unregister first so we don't get any more notifications. */ - mmu_notifier_unregister(&handler->mn, handler->mm); + mmu_notifier_unregister(&handler->mn, handler->mn.mm); /* * Make sure the wq delete handler is finished running. It will not @@ -166,6 +154,10 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, int ret = 0; trace_hfi1_mmu_rb_insert(mnode->addr, mnode->len); + + if (current->mm != handler->mn.mm) + return -EPERM; + spin_lock_irqsave(&handler->lock, flags); node = __mmu_rb_search(handler, mnode->addr, mnode->len); if (node) { @@ -180,6 +172,7 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, __mmu_int_rb_remove(mnode, &handler->root); list_del(&mnode->list); /* remove from LRU list */ } + mnode->handler = handler; unlock: spin_unlock_irqrestore(&handler->lock, flags); return ret; @@ -217,6 +210,9 @@ bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler, unsigned long flags; bool ret = false; + if (current->mm != handler->mn.mm) + return ret; + spin_lock_irqsave(&handler->lock, flags); node = __mmu_rb_search(handler, addr, len); if (node) { @@ -239,6 +235,9 @@ void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) unsigned long flags; bool stop = false; + if (current->mm != handler->mn.mm) + return; + INIT_LIST_HEAD(&del_list); spin_lock_irqsave(&handler->lock, flags); @@ -272,6 +271,9 @@ void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler, { unsigned long flags; + if (current->mm != handler->mn.mm) + return; + /* Validity of handler and node pointers has been checked by caller. */ trace_hfi1_mmu_rb_remove(node->addr, node->len); spin_lock_irqsave(&handler->lock, flags); diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.h b/drivers/infiniband/hw/hfi1/mmu_rb.h index f04cec1e99d1..423aacc67e94 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.h +++ b/drivers/infiniband/hw/hfi1/mmu_rb.h @@ -1,4 +1,5 @@ /* + * Copyright(c) 2020 Cornelis Networks, Inc. * Copyright(c) 2016 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -54,6 +55,7 @@ struct mmu_rb_node { unsigned long len; unsigned long __last; struct rb_node node; + struct mmu_rb_handler *handler; struct list_head list; }; @@ -71,7 +73,19 @@ struct mmu_rb_ops { void *evict_arg, bool *stop); }; -int hfi1_mmu_rb_register(void *ops_arg, struct mm_struct *mm, +struct mmu_rb_handler { + struct mmu_notifier mn; + struct rb_root_cached root; + void *ops_arg; + spinlock_t lock; /* protect the RB tree */ + struct mmu_rb_ops *ops; + struct list_head lru_list; + struct work_struct del_work; + struct list_head del_list; + struct workqueue_struct *wq; +}; + +int hfi1_mmu_rb_register(void *ops_arg, struct mmu_rb_ops *ops, struct workqueue_struct *wq, struct mmu_rb_handler **handler); diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index f81ca20f4b69..b94fc7fd75a9 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -1,4 +1,5 @@ /* + * Copyright(c) 2020 Cornelis Networks, Inc. * Copyright(c) 2015-2018 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -173,15 +174,18 @@ static void unpin_rcv_pages(struct hfi1_filedata *fd, { struct page **pages; struct hfi1_devdata *dd = fd->uctxt->dd; + struct mm_struct *mm; if (mapped) { pci_unmap_single(dd->pcidev, node->dma_addr, node->npages * PAGE_SIZE, PCI_DMA_FROMDEVICE); pages = &node->pages[idx]; + mm = mm_from_tid_node(node); } else { pages = &tidbuf->pages[idx]; + mm = current->mm; } - hfi1_release_user_pages(fd->mm, pages, npages, mapped); + hfi1_release_user_pages(mm, pages, npages, mapped); fd->tid_n_pinned -= npages; } @@ -216,12 +220,12 @@ static int pin_rcv_pages(struct hfi1_filedata *fd, struct tid_user_buf *tidbuf) * pages, accept the amount pinned so far and program only that. * User space knows how to deal with partially programmed buffers. */ - if (!hfi1_can_pin_pages(dd, fd->mm, fd->tid_n_pinned, npages)) { + if (!hfi1_can_pin_pages(dd, current->mm, fd->tid_n_pinned, npages)) { kfree(pages); return -ENOMEM; } - pinned = hfi1_acquire_user_pages(fd->mm, vaddr, npages, true, pages); + pinned = hfi1_acquire_user_pages(current->mm, vaddr, npages, true, pages); if (pinned <= 0) { kfree(pages); return pinned; @@ -756,7 +760,7 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd, if (fd->use_mn) { ret = mmu_interval_notifier_insert( - &node->notifier, fd->mm, + &node->notifier, current->mm, tbuf->vaddr + (pageidx * PAGE_SIZE), npages * PAGE_SIZE, &tid_mn_ops); if (ret) diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.h b/drivers/infiniband/hw/hfi1/user_exp_rcv.h index 332abb446861..d45c7b6988d4 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.h +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.h @@ -1,6 +1,7 @@ #ifndef _HFI1_USER_EXP_RCV_H #define _HFI1_USER_EXP_RCV_H /* + * Copyright(c) 2020 - Cornelis Networks, Inc. * Copyright(c) 2015 - 2017 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -95,4 +96,9 @@ int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd, int hfi1_user_exp_rcv_invalid(struct hfi1_filedata *fd, struct hfi1_tid_info *tinfo); +static inline struct mm_struct *mm_from_tid_node(struct tid_rb_node *node) +{ + return node->notifier.mm; +} + #endif /* _HFI1_USER_EXP_RCV_H */ diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index a92346e88628..4a4956f96a7e 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -1,4 +1,5 @@ /* + * Copyright(c) 2020 - Cornelis Networks, Inc. * Copyright(c) 2015 - 2018 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -188,7 +189,6 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt, atomic_set(&pq->n_reqs, 0); init_waitqueue_head(&pq->wait); atomic_set(&pq->n_locked, 0); - pq->mm = fd->mm; iowait_init(&pq->busy, 0, NULL, NULL, defer_packet_queue, activate_packet_queue, NULL, NULL); @@ -230,7 +230,7 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt, cq->nentries = hfi1_sdma_comp_ring_size; - ret = hfi1_mmu_rb_register(pq, pq->mm, &sdma_rb_ops, dd->pport->hfi1_wq, + ret = hfi1_mmu_rb_register(pq, &sdma_rb_ops, dd->pport->hfi1_wq, &pq->handler); if (ret) { dd_dev_err(dd, "Failed to register with MMU %d", ret); @@ -980,13 +980,13 @@ static int pin_sdma_pages(struct user_sdma_request *req, npages -= node->npages; retry: - if (!hfi1_can_pin_pages(pq->dd, pq->mm, + if (!hfi1_can_pin_pages(pq->dd, current->mm, atomic_read(&pq->n_locked), npages)) { cleared = sdma_cache_evict(pq, npages); if (cleared >= npages) goto retry; } - pinned = hfi1_acquire_user_pages(pq->mm, + pinned = hfi1_acquire_user_pages(current->mm, ((unsigned long)iovec->iov.iov_base + (node->npages * PAGE_SIZE)), npages, 0, pages + node->npages); @@ -995,7 +995,7 @@ retry: return pinned; } if (pinned != npages) { - unpin_vector_pages(pq->mm, pages, node->npages, pinned); + unpin_vector_pages(current->mm, pages, node->npages, pinned); return -EFAULT; } kfree(node->pages); @@ -1008,7 +1008,8 @@ retry: static void unpin_sdma_pages(struct sdma_mmu_node *node) { if (node->npages) { - unpin_vector_pages(node->pq->mm, node->pages, 0, node->npages); + unpin_vector_pages(mm_from_sdma_node(node), node->pages, 0, + node->npages); atomic_sub(node->npages, &node->pq->n_locked); } } diff --git a/drivers/infiniband/hw/hfi1/user_sdma.h b/drivers/infiniband/hw/hfi1/user_sdma.h index 9972e0e6545e..1e8c02fe8ad1 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.h +++ b/drivers/infiniband/hw/hfi1/user_sdma.h @@ -1,6 +1,7 @@ #ifndef _HFI1_USER_SDMA_H #define _HFI1_USER_SDMA_H /* + * Copyright(c) 2020 - Cornelis Networks, Inc. * Copyright(c) 2015 - 2018 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or @@ -133,7 +134,6 @@ struct hfi1_user_sdma_pkt_q { unsigned long unpinned; struct mmu_rb_handler *handler; atomic_t n_locked; - struct mm_struct *mm; }; struct hfi1_user_sdma_comp_q { @@ -250,4 +250,9 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, struct iovec *iovec, unsigned long dim, unsigned long *count); +static inline struct mm_struct *mm_from_sdma_node(struct sdma_mmu_node *node) +{ + return node->rb.handler->mn.mm; +} + #endif /* _HFI1_USER_SDMA_H */ diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 6d30850696c5..0468028ffe39 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -2936,6 +2936,7 @@ static int hns_roce_v2_mw_write_mtpt(void *mb_buf, struct hns_roce_mw *mw) roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_R_INV_EN_S, 1); roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_L_INV_EN_S, 1); + roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_LW_EN_S, 1); roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_PA_S, 0); roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_MR_MW_S, 1); @@ -4989,11 +4990,11 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, V2_QPC_BYTE_28_AT_M, V2_QPC_BYTE_28_AT_S); qp_attr->retry_cnt = roce_get_field(context.byte_212_lsn, - V2_QPC_BYTE_212_RETRY_CNT_M, - V2_QPC_BYTE_212_RETRY_CNT_S); + V2_QPC_BYTE_212_RETRY_NUM_INIT_M, + V2_QPC_BYTE_212_RETRY_NUM_INIT_S); qp_attr->rnr_retry = roce_get_field(context.byte_244_rnr_rxack, - V2_QPC_BYTE_244_RNR_CNT_M, - V2_QPC_BYTE_244_RNR_CNT_S); + V2_QPC_BYTE_244_RNR_NUM_INIT_M, + V2_QPC_BYTE_244_RNR_NUM_INIT_S); done: qp_attr->cur_qp_state = qp_attr->qp_state; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 29c9dd4bcbc6..be7f2fe1e883 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -1661,7 +1661,7 @@ struct hns_roce_query_pf_caps_d { __le32 rsv_uars_rsv_qps; }; #define V2_QUERY_PF_CAPS_D_NUM_SRQS_S 0 -#define V2_QUERY_PF_CAPS_D_NUM_SRQS_M GENMASK(20, 0) +#define V2_QUERY_PF_CAPS_D_NUM_SRQS_M GENMASK(19, 0) #define V2_QUERY_PF_CAPS_D_RQWQE_HOP_NUM_S 20 #define V2_QUERY_PF_CAPS_D_RQWQE_HOP_NUM_M GENMASK(21, 20) diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index 2408b279e4c2..584932d3cc44 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -54,10 +54,6 @@ #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." __stringify(DRV_VERSION_BUILD) -static int push_mode; -module_param(push_mode, int, 0644); -MODULE_PARM_DESC(push_mode, "Low latency mode: 0=disabled (default), 1=enabled)"); - static int debug; module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "debug flags: 0=disabled (default), 0x7fffffff=all"); @@ -1580,7 +1576,6 @@ static enum i40iw_status_code i40iw_setup_init_state(struct i40iw_handler *hdl, if (status) goto exit; iwdev->obj_next = iwdev->obj_mem; - iwdev->push_mode = push_mode; init_waitqueue_head(&iwdev->vchnl_waitq); init_waitqueue_head(&dev->vf_reqs); diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 581ecbadf586..533f3caecb7a 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -167,39 +167,16 @@ static void i40iw_dealloc_ucontext(struct ib_ucontext *context) */ static int i40iw_mmap(struct ib_ucontext *context, struct vm_area_struct *vma) { - struct i40iw_ucontext *ucontext; - u64 db_addr_offset, push_offset, pfn; - - ucontext = to_ucontext(context); - if (ucontext->iwdev->sc_dev.is_pf) { - db_addr_offset = I40IW_DB_ADDR_OFFSET; - push_offset = I40IW_PUSH_OFFSET; - if (vma->vm_pgoff) - vma->vm_pgoff += I40IW_PF_FIRST_PUSH_PAGE_INDEX - 1; - } else { - db_addr_offset = I40IW_VF_DB_ADDR_OFFSET; - push_offset = I40IW_VF_PUSH_OFFSET; - if (vma->vm_pgoff) - vma->vm_pgoff += I40IW_VF_FIRST_PUSH_PAGE_INDEX - 1; - } + struct i40iw_ucontext *ucontext = to_ucontext(context); + u64 dbaddr; - vma->vm_pgoff += db_addr_offset >> PAGE_SHIFT; - - if (vma->vm_pgoff == (db_addr_offset >> PAGE_SHIFT)) { - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - } else { - if ((vma->vm_pgoff - (push_offset >> PAGE_SHIFT)) % 2) - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - else - vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); - } + if (vma->vm_pgoff || vma->vm_end - vma->vm_start != PAGE_SIZE) + return -EINVAL; - pfn = vma->vm_pgoff + - (pci_resource_start(ucontext->iwdev->ldev->pcidev, 0) >> - PAGE_SHIFT); + dbaddr = I40IW_DB_ADDR_OFFSET + pci_resource_start(ucontext->iwdev->ldev->pcidev, 0); - return rdma_user_mmap_io(context, vma, pfn, PAGE_SIZE, - vma->vm_page_prot, NULL); + return rdma_user_mmap_io(context, vma, dbaddr >> PAGE_SHIFT, PAGE_SIZE, + pgprot_noncached(vma->vm_page_prot), NULL); } /** diff --git a/drivers/infiniband/hw/mthca/mthca_cq.c b/drivers/infiniband/hw/mthca/mthca_cq.c index c3cfea243af8..119b2573c9a0 100644 --- a/drivers/infiniband/hw/mthca/mthca_cq.c +++ b/drivers/infiniband/hw/mthca/mthca_cq.c @@ -803,8 +803,10 @@ int mthca_init_cq(struct mthca_dev *dev, int nent, } mailbox = mthca_alloc_mailbox(dev, GFP_KERNEL); - if (IS_ERR(mailbox)) + if (IS_ERR(mailbox)) { + err = PTR_ERR(mailbox); goto err_out_arm; + } cq_context = mailbox->buf; @@ -846,9 +848,9 @@ int mthca_init_cq(struct mthca_dev *dev, int nent, } spin_lock_irq(&dev->cq_table.lock); - if (mthca_array_set(&dev->cq_table.cq, - cq->cqn & (dev->limits.num_cqs - 1), - cq)) { + err = mthca_array_set(&dev->cq_table.cq, + cq->cqn & (dev->limits.num_cqs - 1), cq); + if (err) { spin_unlock_irq(&dev->cq_table.lock); goto err_out_free_mr; } diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 019642ff24a7..511c95bb3d01 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1936,6 +1936,15 @@ static int qedr_create_user_qp(struct qedr_dev *dev, } if (rdma_protocol_iwarp(&dev->ibdev, 1)) { + qp->urq.db_rec_db2_addr = ctx->dpi_addr + uresp.rq_db2_offset; + + /* calculate the db_rec_db2 data since it is constant so no + * need to reflect from user + */ + qp->urq.db_rec_db2_data.data.icid = cpu_to_le16(qp->icid); + qp->urq.db_rec_db2_data.data.value = + cpu_to_le16(DQ_TCM_IWARP_POST_RQ_CF_CMD); + rc = qedr_db_recovery_add(dev, qp->urq.db_rec_db2_addr, &qp->urq.db_rec_db2_data, DB_REC_WIDTH_32B, diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c index fa2a3fa0c3e4..6895bac53990 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c @@ -266,7 +266,7 @@ static int pvrdma_register_device(struct pvrdma_dev *dev) } ret = ib_device_set_netdev(&dev->ib_dev, dev->netdev, 1); if (ret) - return ret; + goto err_srq_free; spin_lock_init(&dev->srq_tbl_lock); rdma_set_device_sysfs_group(&dev->ib_dev, &pvrdma_attr_group); diff --git a/drivers/infiniband/sw/rdmavt/Kconfig b/drivers/infiniband/sw/rdmavt/Kconfig index 9ef5f5ce1ff6..c8e268082952 100644 --- a/drivers/infiniband/sw/rdmavt/Kconfig +++ b/drivers/infiniband/sw/rdmavt/Kconfig @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only config INFINIBAND_RDMAVT tristate "RDMA verbs transport library" - depends on X86_64 && ARCH_DMA_ADDR_T_64BIT + depends on INFINIBAND_VIRT_DMA + depends on X86_64 depends on PCI select DMA_VIRT_OPS help diff --git a/drivers/infiniband/sw/rxe/Kconfig b/drivers/infiniband/sw/rxe/Kconfig index a0c6c7dfc181..8810bfa68049 100644 --- a/drivers/infiniband/sw/rxe/Kconfig +++ b/drivers/infiniband/sw/rxe/Kconfig @@ -2,7 +2,7 @@ config RDMA_RXE tristate "Software RDMA over Ethernet (RoCE) driver" depends on INET && PCI && INFINIBAND - depends on !64BIT || ARCH_DMA_ADDR_T_64BIT + depends on INFINIBAND_VIRT_DMA select NET_UDP_TUNNEL select CRYPTO_CRC32 select DMA_VIRT_OPS diff --git a/drivers/infiniband/sw/siw/Kconfig b/drivers/infiniband/sw/siw/Kconfig index b622fc62f2cd..3450ba5081df 100644 --- a/drivers/infiniband/sw/siw/Kconfig +++ b/drivers/infiniband/sw/siw/Kconfig @@ -1,6 +1,7 @@ config RDMA_SIW tristate "Software RDMA over TCP/IP (iWARP) driver" depends on INET && INFINIBAND && LIBCRC32C + depends on INFINIBAND_VIRT_DMA select DMA_VIRT_OPS help This driver implements the iWARP RDMA transport over diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index c77cdb3b62b5..8c73377ac82c 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -241,6 +241,7 @@ static const struct xpad_device { { 0x1038, 0x1430, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 }, { 0x1038, 0x1431, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 }, { 0x11c9, 0x55f0, "Nacon GC-100XF", 0, XTYPE_XBOX360 }, + { 0x1209, 0x2882, "Ardwiino Controller", 0, XTYPE_XBOX360 }, { 0x12ab, 0x0004, "Honey Bee Xbox360 dancepad", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 }, { 0x12ab, 0x0301, "PDP AFTERGLOW AX.1", 0, XTYPE_XBOX360 }, { 0x12ab, 0x0303, "Mortal Kombat Klassic FightStick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, @@ -418,6 +419,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOXONE_VENDOR(0x0f0d), /* Hori Controllers */ XPAD_XBOX360_VENDOR(0x1038), /* SteelSeries Controllers */ XPAD_XBOX360_VENDOR(0x11c9), /* Nacon GC100XF */ + XPAD_XBOX360_VENDOR(0x1209), /* Ardwiino Controllers */ XPAD_XBOX360_VENDOR(0x12ab), /* X-Box 360 dance pads */ XPAD_XBOX360_VENDOR(0x1430), /* RedOctane X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x146b), /* BigBen Interactive Controllers */ diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c index 15d17c717081..1f0d61b3c213 100644 --- a/drivers/input/keyboard/cros_ec_keyb.c +++ b/drivers/input/keyboard/cros_ec_keyb.c @@ -183,6 +183,7 @@ static void cros_ec_keyb_process(struct cros_ec_keyb *ckdev, "changed: [r%d c%d]: byte %02x\n", row, col, new_state); + input_event(idev, EV_MSC, MSC_SCAN, pos); input_report_key(idev, keycodes[pos], new_state); } diff --git a/drivers/input/keyboard/sunkbd.c b/drivers/input/keyboard/sunkbd.c index 27126e621eb6..d450f11b98a7 100644 --- a/drivers/input/keyboard/sunkbd.c +++ b/drivers/input/keyboard/sunkbd.c @@ -99,7 +99,8 @@ static irqreturn_t sunkbd_interrupt(struct serio *serio, switch (data) { case SUNKBD_RET_RESET: - schedule_work(&sunkbd->tq); + if (sunkbd->enabled) + schedule_work(&sunkbd->tq); sunkbd->reset = -1; break; @@ -200,16 +201,12 @@ static int sunkbd_initialize(struct sunkbd *sunkbd) } /* - * sunkbd_reinit() sets leds and beeps to a state the computer remembers they - * were in. + * sunkbd_set_leds_beeps() sets leds and beeps to a state the computer remembers + * they were in. */ -static void sunkbd_reinit(struct work_struct *work) +static void sunkbd_set_leds_beeps(struct sunkbd *sunkbd) { - struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq); - - wait_event_interruptible_timeout(sunkbd->wait, sunkbd->reset >= 0, HZ); - serio_write(sunkbd->serio, SUNKBD_CMD_SETLED); serio_write(sunkbd->serio, (!!test_bit(LED_CAPSL, sunkbd->dev->led) << 3) | @@ -222,11 +219,39 @@ static void sunkbd_reinit(struct work_struct *work) SUNKBD_CMD_BELLOFF - !!test_bit(SND_BELL, sunkbd->dev->snd)); } + +/* + * sunkbd_reinit() wait for the keyboard reset to complete and restores state + * of leds and beeps. + */ + +static void sunkbd_reinit(struct work_struct *work) +{ + struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq); + + /* + * It is OK that we check sunkbd->enabled without pausing serio, + * as we only want to catch true->false transition that will + * happen once and we will be woken up for it. + */ + wait_event_interruptible_timeout(sunkbd->wait, + sunkbd->reset >= 0 || !sunkbd->enabled, + HZ); + + if (sunkbd->reset >= 0 && sunkbd->enabled) + sunkbd_set_leds_beeps(sunkbd); +} + static void sunkbd_enable(struct sunkbd *sunkbd, bool enable) { serio_pause_rx(sunkbd->serio); sunkbd->enabled = enable; serio_continue_rx(sunkbd->serio); + + if (!enable) { + wake_up_interruptible(&sunkbd->wait); + cancel_work_sync(&sunkbd->tq); + } } /* diff --git a/drivers/input/misc/adxl34x.c b/drivers/input/misc/adxl34x.c index 5fe92d4ba3f0..4cc4e8ff42b3 100644 --- a/drivers/input/misc/adxl34x.c +++ b/drivers/input/misc/adxl34x.c @@ -696,7 +696,7 @@ struct adxl34x *adxl34x_probe(struct device *dev, int irq, struct input_dev *input_dev; const struct adxl34x_platform_data *pdata; int err, range, i; - unsigned char revid; + int revid; if (!irq) { dev_err(dev, "no IRQ?\n"); diff --git a/drivers/input/misc/cm109.c b/drivers/input/misc/cm109.c index e413801f0491..f515fae465c3 100644 --- a/drivers/input/misc/cm109.c +++ b/drivers/input/misc/cm109.c @@ -568,12 +568,15 @@ static int cm109_input_open(struct input_dev *idev) dev->ctl_data->byte[HID_OR2] = dev->keybit; dev->ctl_data->byte[HID_OR3] = 0x00; + dev->ctl_urb_pending = 1; error = usb_submit_urb(dev->urb_ctl, GFP_KERNEL); - if (error) + if (error) { + dev->ctl_urb_pending = 0; dev_err(&dev->intf->dev, "%s: usb_submit_urb (urb_ctl) failed %d\n", __func__, error); - else + } else { dev->open = 1; + } mutex_unlock(&dev->pm_mutex); diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index cae1a3fae83a..cb6ec59a045d 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/input.h> #include <linux/init.h> +#include <linux/irq.h> #include <linux/kernel.h> #include <linux/acpi.h> #include <linux/dmi.h> @@ -82,6 +83,17 @@ static const struct dmi_system_id dmi_use_low_level_irq[] = { DMI_MATCH(DMI_PRODUCT_NAME, "One S1003"), }, }, + { + /* + * Lenovo Yoga Tab2 1051L, something messes with the home-button + * IRQ settings, leading to a non working home-button. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "60073"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1051L"), + }, + }, {} /* Terminating entry */ }; diff --git a/drivers/input/mouse/elan_i2c.h b/drivers/input/mouse/elan_i2c.h index c75b00c45d75..36e3cd908671 100644 --- a/drivers/input/mouse/elan_i2c.h +++ b/drivers/input/mouse/elan_i2c.h @@ -78,7 +78,7 @@ struct elan_transport_ops { int (*iap_reset)(struct i2c_client *client); int (*prepare_fw_update)(struct i2c_client *client, u16 ic_type, - u8 iap_version); + u8 iap_version, u16 fw_page_size); int (*write_fw_block)(struct i2c_client *client, u16 fw_page_size, const u8 *page, u16 checksum, int idx); int (*finish_fw_update)(struct i2c_client *client, diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index c599e21a8478..61ed3f5ca219 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -497,7 +497,8 @@ static int __elan_update_firmware(struct elan_tp_data *data, u16 sw_checksum = 0, fw_checksum = 0; error = data->ops->prepare_fw_update(client, data->ic_type, - data->iap_version); + data->iap_version, + data->fw_page_size); if (error) return error; diff --git a/drivers/input/mouse/elan_i2c_i2c.c b/drivers/input/mouse/elan_i2c_i2c.c index 5a496d4ffa49..13dc097eb6c6 100644 --- a/drivers/input/mouse/elan_i2c_i2c.c +++ b/drivers/input/mouse/elan_i2c_i2c.c @@ -517,7 +517,7 @@ static int elan_i2c_set_flash_key(struct i2c_client *client) return 0; } -static int elan_read_write_iap_type(struct i2c_client *client) +static int elan_read_write_iap_type(struct i2c_client *client, u16 fw_page_size) { int error; u16 constant; @@ -526,7 +526,7 @@ static int elan_read_write_iap_type(struct i2c_client *client) do { error = elan_i2c_write_cmd(client, ETP_I2C_IAP_TYPE_CMD, - ETP_I2C_IAP_TYPE_REG); + fw_page_size / 2); if (error) { dev_err(&client->dev, "cannot write iap type: %d\n", error); @@ -543,7 +543,7 @@ static int elan_read_write_iap_type(struct i2c_client *client) constant = le16_to_cpup((__le16 *)val); dev_dbg(&client->dev, "iap type reg: 0x%04x\n", constant); - if (constant == ETP_I2C_IAP_TYPE_REG) + if (constant == fw_page_size / 2) return 0; } while (--retry > 0); @@ -553,7 +553,7 @@ static int elan_read_write_iap_type(struct i2c_client *client) } static int elan_i2c_prepare_fw_update(struct i2c_client *client, u16 ic_type, - u8 iap_version) + u8 iap_version, u16 fw_page_size) { struct device *dev = &client->dev; int error; @@ -594,7 +594,7 @@ static int elan_i2c_prepare_fw_update(struct i2c_client *client, u16 ic_type, } if (ic_type >= 0x0D && iap_version >= 1) { - error = elan_read_write_iap_type(client); + error = elan_read_write_iap_type(client, fw_page_size); if (error) return error; } diff --git a/drivers/input/mouse/elan_i2c_smbus.c b/drivers/input/mouse/elan_i2c_smbus.c index 8ff823751f3b..1820f1cfc1dc 100644 --- a/drivers/input/mouse/elan_i2c_smbus.c +++ b/drivers/input/mouse/elan_i2c_smbus.c @@ -340,7 +340,7 @@ static int elan_smbus_set_flash_key(struct i2c_client *client) } static int elan_smbus_prepare_fw_update(struct i2c_client *client, u16 ic_type, - u8 iap_version) + u8 iap_version, u16 fw_page_size) { struct device *dev = &client->dev; int len; diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index a4c9b9652560..3a2dcf0805f1 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -219,6 +219,10 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"), DMI_MATCH(DMI_PRODUCT_NAME, "C15B"), }, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ByteSpeed LLC"), + DMI_MATCH(DMI_PRODUCT_NAME, "ByteSpeed Laptop C15B"), + }, }, { } }; @@ -608,6 +612,48 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = { }, }, { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A114-31"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A314-31"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-31"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-132"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-332"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-432"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate Spin B118-RN"), + }, + }, + { /* Advent 4211 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "DIXONSXP"), diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index d3eda48032e3..abae23af0791 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -122,6 +122,7 @@ module_param_named(unmask_kbd_data, i8042_unmask_kbd_data, bool, 0600); MODULE_PARM_DESC(unmask_kbd_data, "Unconditional enable (may reveal sensitive data) of normally sanitize-filtered kbd data traffic debug log [pre-condition: i8042.debug=1 enabled]"); #endif +static bool i8042_present; static bool i8042_bypass_aux_irq_test; static char i8042_kbd_firmware_id[128]; static char i8042_aux_firmware_id[128]; @@ -343,6 +344,9 @@ int i8042_command(unsigned char *param, int command) unsigned long flags; int retval; + if (!i8042_present) + return -1; + spin_lock_irqsave(&i8042_lock, flags); retval = __i8042_command(param, command); spin_unlock_irqrestore(&i8042_lock, flags); @@ -1467,7 +1471,8 @@ static int __init i8042_setup_aux(void) if (error) goto err_free_ports; - if (aux_enable()) + error = aux_enable(); + if (error) goto err_free_irq; i8042_aux_irq_registered = true; @@ -1612,12 +1617,15 @@ static int __init i8042_init(void) err = i8042_platform_init(); if (err) - return err; + return (err == -ENODEV) ? 0 : err; err = i8042_controller_check(); if (err) goto err_platform_exit; + /* Set this before creating the dev to allow i8042_command to work right away */ + i8042_present = true; + pdev = platform_create_bundle(&i8042_driver, i8042_probe, NULL, 0, NULL, 0); if (IS_ERR(pdev)) { err = PTR_ERR(pdev); @@ -1636,6 +1644,9 @@ static int __init i8042_init(void) static void __exit i8042_exit(void) { + if (!i8042_present) + return; + platform_device_unregister(i8042_platform_device); platform_driver_unregister(&i8042_driver); i8042_platform_exit(); diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index f012fe746df0..cc18f54ea887 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -96,6 +96,7 @@ config TOUCHSCREEN_AD7879_SPI config TOUCHSCREEN_ADC tristate "Generic ADC based resistive touchscreen" depends on IIO + select IIO_BUFFER select IIO_BUFFER_CB help Say Y here if you want to use the generic ADC diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index 98f17fa3a892..b6f75367a284 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -2183,11 +2183,11 @@ static int mxt_initialize(struct mxt_data *data) msleep(MXT_FW_RESET_TIME); } - error = mxt_acquire_irq(data); + error = mxt_check_retrigen(data); if (error) return error; - error = mxt_check_retrigen(data); + error = mxt_acquire_irq(data); if (error) return error; diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index 02c75ea385e0..6612f9e2d7e8 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -193,6 +193,18 @@ static const struct dmi_system_id rotated_screen[] = { }, }, { + .ident = "Teclast X98 Pro", + .matches = { + /* + * Only match BIOS date, because the manufacturers + * BIOS does not report the board name at all + * (sometimes)... + */ + DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"), + DMI_MATCH(DMI_BIOS_DATE, "10/28/2015"), + }, + }, + { .ident = "WinBook TW100", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "WinBook"), diff --git a/drivers/input/touchscreen/raydium_i2c_ts.c b/drivers/input/touchscreen/raydium_i2c_ts.c index e694a9b2b1e5..603a948460d6 100644 --- a/drivers/input/touchscreen/raydium_i2c_ts.c +++ b/drivers/input/touchscreen/raydium_i2c_ts.c @@ -137,45 +137,25 @@ struct raydium_data { bool wake_irq_enabled; }; -static int raydium_i2c_xfer(struct i2c_client *client, - u32 addr, void *data, size_t len, bool is_read) -{ - struct raydium_bank_switch_header { - u8 cmd; - __be32 be_addr; - } __packed header = { - .cmd = RM_CMD_BANK_SWITCH, - .be_addr = cpu_to_be32(addr), - }; - - u8 reg_addr = addr & 0xff; - - struct i2c_msg xfer[] = { - { - .addr = client->addr, - .len = sizeof(header), - .buf = (u8 *)&header, - }, - { - .addr = client->addr, - .len = 1, - .buf = ®_addr, - }, - { - .addr = client->addr, - .len = len, - .buf = data, - .flags = is_read ? I2C_M_RD : 0, - } - }; +/* + * Header to be sent for RM_CMD_BANK_SWITCH command. This is used by + * raydium_i2c_{read|send} below. + */ +struct __packed raydium_bank_switch_header { + u8 cmd; + __be32 be_addr; +}; +static int raydium_i2c_xfer(struct i2c_client *client, u32 addr, + struct i2c_msg *xfer, size_t xfer_count) +{ + int ret; /* * If address is greater than 255, then RM_CMD_BANK_SWITCH needs to be * sent first. Else, skip the header i.e. xfer[0]. */ int xfer_start_idx = (addr > 0xff) ? 0 : 1; - size_t xfer_count = ARRAY_SIZE(xfer) - xfer_start_idx; - int ret; + xfer_count -= xfer_start_idx; ret = i2c_transfer(client->adapter, &xfer[xfer_start_idx], xfer_count); if (likely(ret == xfer_count)) @@ -189,10 +169,46 @@ static int raydium_i2c_send(struct i2c_client *client, { int tries = 0; int error; + u8 *tx_buf; + u8 reg_addr = addr & 0xff; + + tx_buf = kmalloc(len + 1, GFP_KERNEL); + if (!tx_buf) + return -ENOMEM; + + tx_buf[0] = reg_addr; + memcpy(tx_buf + 1, data, len); do { - error = raydium_i2c_xfer(client, addr, (void *)data, len, - false); + struct raydium_bank_switch_header header = { + .cmd = RM_CMD_BANK_SWITCH, + .be_addr = cpu_to_be32(addr), + }; + + /* + * Perform as a single i2c_transfer transaction to ensure that + * no other I2C transactions are initiated on the bus to any + * other device in between. Initiating transacations to other + * devices after RM_CMD_BANK_SWITCH is sent is known to cause + * issues. This is also why regmap infrastructure cannot be used + * for this driver. Regmap handles page(bank) switch and reads + * as separate i2c_transfer() operations. This can result in + * problems if the Raydium device is on a shared I2C bus. + */ + struct i2c_msg xfer[] = { + { + .addr = client->addr, + .len = sizeof(header), + .buf = (u8 *)&header, + }, + { + .addr = client->addr, + .len = len + 1, + .buf = tx_buf, + }, + }; + + error = raydium_i2c_xfer(client, addr, xfer, ARRAY_SIZE(xfer)); if (likely(!error)) return 0; @@ -206,12 +222,46 @@ static int raydium_i2c_send(struct i2c_client *client, static int raydium_i2c_read(struct i2c_client *client, u32 addr, void *data, size_t len) { - size_t xfer_len; int error; while (len) { - xfer_len = min_t(size_t, len, RM_MAX_READ_SIZE); - error = raydium_i2c_xfer(client, addr, data, xfer_len, true); + u8 reg_addr = addr & 0xff; + struct raydium_bank_switch_header header = { + .cmd = RM_CMD_BANK_SWITCH, + .be_addr = cpu_to_be32(addr), + }; + size_t xfer_len = min_t(size_t, len, RM_MAX_READ_SIZE); + + /* + * Perform as a single i2c_transfer transaction to ensure that + * no other I2C transactions are initiated on the bus to any + * other device in between. Initiating transacations to other + * devices after RM_CMD_BANK_SWITCH is sent is known to cause + * issues. This is also why regmap infrastructure cannot be used + * for this driver. Regmap handles page(bank) switch and writes + * as separate i2c_transfer() operations. This can result in + * problems if the Raydium device is on a shared I2C bus. + */ + struct i2c_msg xfer[] = { + { + .addr = client->addr, + .len = sizeof(header), + .buf = (u8 *)&header, + }, + { + .addr = client->addr, + .len = 1, + .buf = ®_addr, + }, + { + .addr = client->addr, + .len = xfer_len, + .buf = data, + .flags = I2C_M_RD, + } + }; + + error = raydium_i2c_xfer(client, addr, xfer, ARRAY_SIZE(xfer)); if (unlikely(error)) return error; diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 974a66725d09..5ad519c9f239 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -1083,7 +1083,6 @@ static int of_count_icc_providers(struct device_node *np) count++; count += of_count_icc_providers(child); } - of_node_put(np); return count; } diff --git a/drivers/interconnect/qcom/msm8916.c b/drivers/interconnect/qcom/msm8916.c index 42c6c5581662..e8371d40ab8d 100644 --- a/drivers/interconnect/qcom/msm8916.c +++ b/drivers/interconnect/qcom/msm8916.c @@ -182,7 +182,7 @@ DEFINE_QNODE(mas_pcnoc_sdcc_1, MSM8916_MASTER_SDCC_1, 8, -1, -1, MSM8916_PNOC_IN DEFINE_QNODE(mas_pcnoc_sdcc_2, MSM8916_MASTER_SDCC_2, 8, -1, -1, MSM8916_PNOC_INT_1); DEFINE_QNODE(mas_qdss_bam, MSM8916_MASTER_QDSS_BAM, 8, -1, -1, MSM8916_SNOC_QDSS_INT); DEFINE_QNODE(mas_qdss_etr, MSM8916_MASTER_QDSS_ETR, 8, -1, -1, MSM8916_SNOC_QDSS_INT); -DEFINE_QNODE(mas_snoc_cfg, MSM8916_MASTER_SNOC_CFG, 4, 20, -1, MSM8916_SNOC_QDSS_INT); +DEFINE_QNODE(mas_snoc_cfg, MSM8916_MASTER_SNOC_CFG, 4, -1, -1, MSM8916_SNOC_QDSS_INT); DEFINE_QNODE(mas_spdm, MSM8916_MASTER_SPDM, 4, -1, -1, MSM8916_PNOC_MAS_0); DEFINE_QNODE(mas_tcu0, MSM8916_MASTER_TCU0, 8, -1, -1, MSM8916_SLAVE_EBI_CH0, MSM8916_BIMC_SNOC_MAS, MSM8916_SLAVE_AMPSS_L2); DEFINE_QNODE(mas_tcu1, MSM8916_MASTER_TCU1, 8, -1, -1, MSM8916_SLAVE_EBI_CH0, MSM8916_BIMC_SNOC_MAS, MSM8916_SLAVE_AMPSS_L2); @@ -208,14 +208,14 @@ DEFINE_QNODE(pcnoc_snoc_mas, MSM8916_PNOC_SNOC_MAS, 8, 29, -1, MSM8916_PNOC_SNOC DEFINE_QNODE(pcnoc_snoc_slv, MSM8916_PNOC_SNOC_SLV, 8, -1, 45, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC, MSM8916_SNOC_INT_1); DEFINE_QNODE(qdss_int, MSM8916_SNOC_QDSS_INT, 8, -1, -1, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC); DEFINE_QNODE(slv_apps_l2, MSM8916_SLAVE_AMPSS_L2, 8, -1, -1, 0); -DEFINE_QNODE(slv_apss, MSM8916_SLAVE_APSS, 4, -1, 20, 0); +DEFINE_QNODE(slv_apss, MSM8916_SLAVE_APSS, 4, -1, -1, 0); DEFINE_QNODE(slv_audio, MSM8916_SLAVE_LPASS, 4, -1, -1, 0); DEFINE_QNODE(slv_bimc_cfg, MSM8916_SLAVE_BIMC_CFG, 4, -1, -1, 0); DEFINE_QNODE(slv_blsp_1, MSM8916_SLAVE_BLSP_1, 4, -1, -1, 0); DEFINE_QNODE(slv_boot_rom, MSM8916_SLAVE_BOOT_ROM, 4, -1, -1, 0); DEFINE_QNODE(slv_camera_cfg, MSM8916_SLAVE_CAMERA_CFG, 4, -1, -1, 0); -DEFINE_QNODE(slv_cats_0, MSM8916_SLAVE_CATS_128, 16, -1, 106, 0); -DEFINE_QNODE(slv_cats_1, MSM8916_SLAVE_OCMEM_64, 8, -1, 107, 0); +DEFINE_QNODE(slv_cats_0, MSM8916_SLAVE_CATS_128, 16, -1, -1, 0); +DEFINE_QNODE(slv_cats_1, MSM8916_SLAVE_OCMEM_64, 8, -1, -1, 0); DEFINE_QNODE(slv_clk_ctl, MSM8916_SLAVE_CLK_CTL, 4, -1, -1, 0); DEFINE_QNODE(slv_crypto_0_cfg, MSM8916_SLAVE_CRYPTO_0_CFG, 4, -1, -1, 0); DEFINE_QNODE(slv_dehr_cfg, MSM8916_SLAVE_DEHR_CFG, 4, -1, -1, 0); @@ -239,7 +239,7 @@ DEFINE_QNODE(slv_sdcc_2, MSM8916_SLAVE_SDCC_2, 4, -1, -1, 0); DEFINE_QNODE(slv_security, MSM8916_SLAVE_SECURITY, 4, -1, -1, 0); DEFINE_QNODE(slv_snoc_cfg, MSM8916_SLAVE_SNOC_CFG, 4, -1, -1, 0); DEFINE_QNODE(slv_spdm, MSM8916_SLAVE_SPDM, 4, -1, -1, 0); -DEFINE_QNODE(slv_srvc_snoc, MSM8916_SLAVE_SRVC_SNOC, 8, -1, 29, 0); +DEFINE_QNODE(slv_srvc_snoc, MSM8916_SLAVE_SRVC_SNOC, 8, -1, -1, 0); DEFINE_QNODE(slv_tcsr, MSM8916_SLAVE_TCSR, 4, -1, -1, 0); DEFINE_QNODE(slv_tlmm, MSM8916_SLAVE_TLMM, 4, -1, -1, 0); DEFINE_QNODE(slv_usb_hs, MSM8916_SLAVE_USB_HS, 4, -1, -1, 0); @@ -249,7 +249,7 @@ DEFINE_QNODE(snoc_bimc_0_slv, MSM8916_SNOC_BIMC_0_SLV, 8, -1, 24, MSM8916_SLAVE_ DEFINE_QNODE(snoc_bimc_1_mas, MSM8916_SNOC_BIMC_1_MAS, 16, -1, -1, MSM8916_SNOC_BIMC_1_SLV); DEFINE_QNODE(snoc_bimc_1_slv, MSM8916_SNOC_BIMC_1_SLV, 8, -1, -1, MSM8916_SLAVE_EBI_CH0); DEFINE_QNODE(snoc_int_0, MSM8916_SNOC_INT_0, 8, 99, 130, MSM8916_SLAVE_QDSS_STM, MSM8916_SLAVE_IMEM, MSM8916_SNOC_PNOC_MAS); -DEFINE_QNODE(snoc_int_1, MSM8916_SNOC_INT_1, 8, 100, 131, MSM8916_SLAVE_APSS, MSM8916_SLAVE_CATS_128, MSM8916_SLAVE_OCMEM_64); +DEFINE_QNODE(snoc_int_1, MSM8916_SNOC_INT_1, 8, -1, -1, MSM8916_SLAVE_APSS, MSM8916_SLAVE_CATS_128, MSM8916_SLAVE_OCMEM_64); DEFINE_QNODE(snoc_int_bimc, MSM8916_SNOC_INT_BIMC, 8, 101, 132, MSM8916_SNOC_BIMC_0_MAS); DEFINE_QNODE(snoc_pcnoc_mas, MSM8916_SNOC_PNOC_MAS, 8, -1, -1, MSM8916_SNOC_PNOC_SLV); DEFINE_QNODE(snoc_pcnoc_slv, MSM8916_SNOC_PNOC_SLV, 8, -1, -1, MSM8916_PNOC_INT_0); diff --git a/drivers/interconnect/qcom/msm8974.c b/drivers/interconnect/qcom/msm8974.c index 3a313e11e73d..da68ce375a89 100644 --- a/drivers/interconnect/qcom/msm8974.c +++ b/drivers/interconnect/qcom/msm8974.c @@ -618,6 +618,8 @@ static int msm8974_icc_set(struct icc_node *src, struct icc_node *dst) do_div(rate, src_qn->buswidth); + rate = min_t(u32, rate, INT_MAX); + if (src_qn->rate == rate) return 0; @@ -635,6 +637,14 @@ static int msm8974_icc_set(struct icc_node *src, struct icc_node *dst) return 0; } +static int msm8974_get_bw(struct icc_node *node, u32 *avg, u32 *peak) +{ + *avg = 0; + *peak = 0; + + return 0; +} + static int msm8974_icc_probe(struct platform_device *pdev) { const struct msm8974_icc_desc *desc; @@ -688,6 +698,7 @@ static int msm8974_icc_probe(struct platform_device *pdev) provider->aggregate = icc_std_aggregate; provider->xlate = of_icc_xlate_onecell; provider->data = data; + provider->get_bw = msm8974_get_bw; ret = icc_provider_add(provider); if (ret) { @@ -758,6 +769,7 @@ static struct platform_driver msm8974_noc_driver = { .driver = { .name = "qnoc-msm8974", .of_match_table = msm8974_noc_of_match, + .sync_state = icc_sync_state, }, }; module_platform_driver(msm8974_noc_driver); diff --git a/drivers/interconnect/qcom/qcs404.c b/drivers/interconnect/qcom/qcs404.c index d4769a5ea182..9820709b43db 100644 --- a/drivers/interconnect/qcom/qcs404.c +++ b/drivers/interconnect/qcom/qcs404.c @@ -157,8 +157,8 @@ struct qcom_icc_desc { } DEFINE_QNODE(mas_apps_proc, QCS404_MASTER_AMPSS_M0, 8, 0, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV); -DEFINE_QNODE(mas_oxili, QCS404_MASTER_GRAPHICS_3D, 8, 6, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV); -DEFINE_QNODE(mas_mdp, QCS404_MASTER_MDP_PORT0, 8, 8, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV); +DEFINE_QNODE(mas_oxili, QCS404_MASTER_GRAPHICS_3D, 8, -1, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV); +DEFINE_QNODE(mas_mdp, QCS404_MASTER_MDP_PORT0, 8, -1, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV); DEFINE_QNODE(mas_snoc_bimc_1, QCS404_SNOC_BIMC_1_MAS, 8, 76, -1, QCS404_SLAVE_EBI_CH0); DEFINE_QNODE(mas_tcu_0, QCS404_MASTER_TCU_0, 8, -1, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV); DEFINE_QNODE(mas_spdm, QCS404_MASTER_SPDM, 4, -1, -1, QCS404_PNOC_INT_3); diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 89647700bab2..494b42a31b7a 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -257,7 +257,7 @@ #define DTE_IRQ_REMAP_INTCTL_MASK (0x3ULL << 60) #define DTE_IRQ_TABLE_LEN_MASK (0xfULL << 1) #define DTE_IRQ_REMAP_INTCTL (2ULL << 60) -#define DTE_IRQ_TABLE_LEN (8ULL << 1) +#define DTE_IRQ_TABLE_LEN (9ULL << 1) #define DTE_IRQ_REMAP_ENABLE 1ULL #define PAGE_MODE_NONE 0x00 diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 82e4af8f09bb..23a790f8f550 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -29,6 +29,7 @@ #include <asm/iommu_table.h> #include <asm/io_apic.h> #include <asm/irq_remapping.h> +#include <asm/set_memory.h> #include <linux/crash_dump.h> @@ -672,11 +673,27 @@ static void __init free_command_buffer(struct amd_iommu *iommu) free_pages((unsigned long)iommu->cmd_buf, get_order(CMD_BUFFER_SIZE)); } +static void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu, + gfp_t gfp, size_t size) +{ + int order = get_order(size); + void *buf = (void *)__get_free_pages(gfp, order); + + if (buf && + iommu_feature(iommu, FEATURE_SNP) && + set_memory_4k((unsigned long)buf, (1 << order))) { + free_pages((unsigned long)buf, order); + buf = NULL; + } + + return buf; +} + /* allocates the memory where the IOMMU will log its events to */ static int __init alloc_event_buffer(struct amd_iommu *iommu) { - iommu->evt_buf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - get_order(EVT_BUFFER_SIZE)); + iommu->evt_buf = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, + EVT_BUFFER_SIZE); return iommu->evt_buf ? 0 : -ENOMEM; } @@ -715,8 +732,8 @@ static void __init free_event_buffer(struct amd_iommu *iommu) /* allocates the memory where the IOMMU will log its events to */ static int __init alloc_ppr_log(struct amd_iommu *iommu) { - iommu->ppr_log = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - get_order(PPR_LOG_SIZE)); + iommu->ppr_log = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, + PPR_LOG_SIZE); return iommu->ppr_log ? 0 : -ENOMEM; } @@ -838,7 +855,7 @@ static int iommu_init_ga(struct amd_iommu *iommu) static int __init alloc_cwwb_sem(struct amd_iommu *iommu) { - iommu->cmd_sem = (void *)get_zeroed_page(GFP_KERNEL); + iommu->cmd_sem = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, 1); return iommu->cmd_sem ? 0 : -ENOMEM; } diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index be4318044f96..702fbaa6c9ad 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -69,6 +69,10 @@ struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu) { struct qcom_smmu *qsmmu; + /* Check to make sure qcom_scm has finished probing */ + if (!qcom_scm_is_available()) + return ERR_PTR(-EPROBE_DEFER); + qsmmu = devm_kzalloc(smmu->dev, sizeof(*qsmmu), GFP_KERNEL); if (!qsmmu) return ERR_PTR(-ENOMEM); diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 404b40af31cb..b46dbfa6d0ed 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -333,6 +333,13 @@ static void dmar_pci_bus_del_dev(struct dmar_pci_notify_info *info) dmar_iommu_notify_scope_dev(info); } +static inline void vf_inherit_msi_domain(struct pci_dev *pdev) +{ + struct pci_dev *physfn = pci_physfn(pdev); + + dev_set_msi_domain(&pdev->dev, dev_get_msi_domain(&physfn->dev)); +} + static int dmar_pci_bus_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -342,8 +349,20 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb, /* Only care about add/remove events for physical functions. * For VFs we actually do the lookup based on the corresponding * PF in device_to_iommu() anyway. */ - if (pdev->is_virtfn) + if (pdev->is_virtfn) { + /* + * Ensure that the VF device inherits the irq domain of the + * PF device. Ideally the device would inherit the domain + * from the bus, but DMAR can have multiple units per bus + * which makes this impossible. The VF 'bus' could inherit + * from the PF device, but that's yet another x86'sism to + * inflict on everybody else. + */ + if (action == BUS_NOTIFY_ADD_DEVICE) + vf_inherit_msi_domain(pdev); return NOTIFY_DONE; + } + if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_REMOVED_DEVICE) return NOTIFY_DONE; @@ -967,7 +986,8 @@ static int map_iommu(struct intel_iommu *iommu, u64 phys_addr) warn_invalid_dmar(phys_addr, " returns all ones"); goto unmap; } - iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG); + if (ecap_vcs(iommu->ecap)) + iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG); /* the registers might be more than one page */ map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap), diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 1b1ca63e6bbe..a49afa11673c 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -179,7 +179,7 @@ static int rwbf_quirk; * (used when kernel is launched w/ TXT) */ static int force_on = 0; -int intel_iommu_tboot_noforce; +static int intel_iommu_tboot_noforce; static int no_platform_optin; #define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry)) @@ -1833,7 +1833,7 @@ static void free_dmar_iommu(struct intel_iommu *iommu) if (ecap_prs(iommu->ecap)) intel_svm_finish_prq(iommu); } - if (ecap_vcs(iommu->ecap) && vccap_pasid(iommu->vccap)) + if (vccap_pasid(iommu->vccap)) ioasid_unregister_allocator(&iommu->pasid_allocator); #endif @@ -3212,7 +3212,7 @@ static void register_pasid_allocator(struct intel_iommu *iommu) * is active. All vIOMMU allocators will eventually be calling the same * host allocator. */ - if (!ecap_vcs(iommu->ecap) || !vccap_pasid(iommu->vccap)) + if (!vccap_pasid(iommu->vccap)) return; pr_info("Register custom PASID allocator\n"); @@ -3818,9 +3818,8 @@ bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size, * page aligned, we don't need to use a bounce page. */ if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) { - tlb_addr = swiotlb_tbl_map_single(dev, - phys_to_dma_unencrypted(dev, io_tlb_start), - paddr, size, aligned_size, dir, attrs); + tlb_addr = swiotlb_tbl_map_single(dev, paddr, size, + aligned_size, dir, attrs); if (tlb_addr == DMA_MAPPING_ERROR) { goto swiotlb_error; } else { @@ -4885,7 +4884,8 @@ int __init intel_iommu_init(void) * Intel IOMMU is required for a TXT/tboot launch or platform * opt in, so enforce that. */ - force_on = tboot_force_iommu() || platform_optin_force_iommu(); + force_on = (!intel_iommu_tboot_noforce && tboot_force_iommu()) || + platform_optin_force_iommu(); if (iommu_init_mempool()) { if (force_on) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index b53446bb8c6b..0f4dc25d46c9 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -264,16 +264,18 @@ int iommu_probe_device(struct device *dev) */ iommu_alloc_default_domain(group, dev); - if (group->default_domain) + if (group->default_domain) { ret = __iommu_attach_device(group->default_domain, dev); + if (ret) { + iommu_group_put(group); + goto err_release; + } + } iommu_create_device_direct_mappings(group, dev); iommu_group_put(group); - if (ret) - goto err_release; - if (ops->probe_finalize) ops->probe_finalize(dev); diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 0fec31931e11..4069c215328b 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -42,7 +42,6 @@ #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING (1ULL << 0) #define ITS_FLAGS_WORKAROUND_CAVIUM_22375 (1ULL << 1) #define ITS_FLAGS_WORKAROUND_CAVIUM_23144 (1ULL << 2) -#define ITS_FLAGS_SAVE_SUSPEND_STATE (1ULL << 3) #define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING (1 << 0) #define RDIST_FLAGS_RD_TABLES_PREALLOCATED (1 << 1) @@ -4741,9 +4740,6 @@ static int its_save_disable(void) list_for_each_entry(its, &its_nodes, entry) { void __iomem *base; - if (!(its->flags & ITS_FLAGS_SAVE_SUSPEND_STATE)) - continue; - base = its->base; its->ctlr_save = readl_relaxed(base + GITS_CTLR); err = its_force_quiescent(base); @@ -4762,9 +4758,6 @@ err: list_for_each_entry_continue_reverse(its, &its_nodes, entry) { void __iomem *base; - if (!(its->flags & ITS_FLAGS_SAVE_SUSPEND_STATE)) - continue; - base = its->base; writel_relaxed(its->ctlr_save, base + GITS_CTLR); } @@ -4784,9 +4777,6 @@ static void its_restore_enable(void) void __iomem *base; int i; - if (!(its->flags & ITS_FLAGS_SAVE_SUSPEND_STATE)) - continue; - base = its->base; /* @@ -4794,7 +4784,10 @@ static void its_restore_enable(void) * don't restore it since writing to CBASER or BASER<n> * registers is undefined according to the GIC v3 ITS * Specification. + * + * Firmware resuming with the ITS enabled is terminally broken. */ + WARN_ON(readl_relaxed(base + GITS_CTLR) & GITS_CTLR_ENABLE); ret = its_force_quiescent(base); if (ret) { pr_err("ITS@%pa: failed to quiesce on resume: %d\n", @@ -5074,9 +5067,6 @@ static int __init its_probe_one(struct resource *res, ctlr |= GITS_CTLR_ImDe; writel_relaxed(ctlr, its->base + GITS_CTLR); - if (GITS_TYPER_HCC(typer)) - its->flags |= ITS_FLAGS_SAVE_SUSPEND_STATE; - err = its_init_domain(handle, its); if (err) goto out_free_tables; diff --git a/drivers/irqchip/irq-sni-exiu.c b/drivers/irqchip/irq-sni-exiu.c index 1d027623c776..abd011fcecf4 100644 --- a/drivers/irqchip/irq-sni-exiu.c +++ b/drivers/irqchip/irq-sni-exiu.c @@ -136,7 +136,7 @@ static int exiu_domain_translate(struct irq_domain *domain, if (fwspec->param_count != 2) return -EINVAL; *hwirq = fwspec->param[0]; - *type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK; + *type = fwspec->param[1] & IRQ_TYPE_SENSE_MASK; } return 0; } diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 9644424591da..4bc453f5bbaa 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -712,10 +712,6 @@ static bool block_size_is_power_of_two(struct cache *cache) return cache->sectors_per_block_shift >= 0; } -/* gcc on ARM generates spurious references to __udivdi3 and __umoddi3 */ -#if defined(CONFIG_ARM) && __GNUC__ == 4 && __GNUC_MINOR__ <= 6 -__always_inline -#endif static dm_block_t block_div(dm_block_t b, uint32_t n) { do_div(b, n); diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 3fc3757def55..5a7a1b90e671 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -3462,7 +3462,7 @@ static int get_mac(struct crypto_shash **hash, struct alg_spec *a, char **error, int r; if (a->alg_string) { - *hash = crypto_alloc_shash(a->alg_string, 0, 0); + *hash = crypto_alloc_shash(a->alg_string, 0, CRYPTO_ALG_ALLOCATES_MEMORY); if (IS_ERR(*hash)) { *error = error_alg; r = PTR_ERR(*hash); @@ -3519,7 +3519,7 @@ static int create_journal(struct dm_integrity_c *ic, char **error) struct journal_completion comp; comp.ic = ic; - ic->journal_crypt = crypto_alloc_skcipher(ic->journal_crypt_alg.alg_string, 0, 0); + ic->journal_crypt = crypto_alloc_skcipher(ic->journal_crypt_alg.alg_string, 0, CRYPTO_ALG_ALLOCATES_MEMORY); if (IS_ERR(ic->journal_crypt)) { *error = "Invalid journal cipher"; r = PTR_ERR(ic->journal_crypt); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 9c1f7c4de65b..56b723d012ac 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3728,6 +3728,15 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits) blk_limits_io_min(limits, chunk_size_bytes); blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs)); + + /* + * RAID1 and RAID10 personalities require bio splitting, + * RAID0/4/5/6 don't and process large discard bios properly. + */ + if (rs_is_raid1(rs) || rs_is_raid10(rs)) { + limits->discard_granularity = chunk_size_bytes; + limits->max_discard_sectors = rs->md.chunk_sectors; + } } static void raid_postsuspend(struct dm_target *ti) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index ce543b761be7..7eeb7c4169c9 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -18,7 +18,6 @@ #include <linux/mutex.h> #include <linux/delay.h> #include <linux/atomic.h> -#include <linux/lcm.h> #include <linux/blk-mq.h> #include <linux/mount.h> #include <linux/dax.h> @@ -1247,12 +1246,6 @@ void dm_table_event_callback(struct dm_table *t, void dm_table_event(struct dm_table *t) { - /* - * You can no longer call dm_table_event() from interrupt - * context, use a bottom half instead. - */ - BUG_ON(in_interrupt()); - mutex_lock(&_event_lock); if (t->event_fn) t->event_fn(t->event_context); @@ -1455,10 +1448,6 @@ int dm_calculate_queue_limits(struct dm_table *table, zone_sectors = ti_limits.chunk_sectors; } - /* Stack chunk_sectors if target-specific splitting is required */ - if (ti->max_io_len) - ti_limits.chunk_sectors = lcm_not_zero(ti->max_io_len, - ti_limits.chunk_sectors); /* Set I/O hints portion of queue limits */ if (ti->type->io_hints) ti->type->io_hints(ti, &ti_limits); diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 9ae4ce7df95c..d5223a0e5cc5 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -319,7 +319,7 @@ err1: #else static int persistent_memory_claim(struct dm_writecache *wc) { - BUG(); + return -EOPNOTSUPP; } #endif @@ -2041,7 +2041,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) struct wc_memory_superblock s; static struct dm_arg _args[] = { - {0, 10, "Invalid number of feature args"}, + {0, 16, "Invalid number of feature args"}, }; as.argc = argc; @@ -2479,6 +2479,8 @@ static void writecache_status(struct dm_target *ti, status_type_t type, extra_args += 2; if (wc->autocommit_time_set) extra_args += 2; + if (wc->max_age != MAX_AGE_UNSPECIFIED) + extra_args += 2; if (wc->cleaner) extra_args++; if (wc->writeback_fua_set) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c18fc2548518..4e0cbfe3f14d 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -476,8 +476,10 @@ static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, return -EAGAIN; map = dm_get_live_table(md, &srcu_idx); - if (!map) - return -EIO; + if (!map) { + ret = -EIO; + goto out; + } do { struct dm_target *tgt; @@ -507,7 +509,6 @@ out: static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx, struct block_device **bdev) - __acquires(md->io_barrier) { struct dm_target *tgt; struct dm_table *map; @@ -541,7 +542,6 @@ retry: } static void dm_unprepare_ioctl(struct mapped_device *md, int srcu_idx) - __releases(md->io_barrier) { dm_put_live_table(md, srcu_idx); } @@ -1037,15 +1037,18 @@ static sector_t max_io_len(struct dm_target *ti, sector_t sector) sector_t max_len; /* - * Does the target need to split even further? - * - q->limits.chunk_sectors reflects ti->max_io_len so - * blk_max_size_offset() provides required splitting. - * - blk_max_size_offset() also respects q->limits.max_sectors + * Does the target need to split IO even further? + * - varied (per target) IO splitting is a tenet of DM; this + * explains why stacked chunk_sectors based splitting via + * blk_max_size_offset() isn't possible here. So pass in + * ti->max_io_len to override stacked chunk_sectors. */ - max_len = blk_max_size_offset(ti->table->md->queue, - target_offset); - if (len > max_len) - len = max_len; + if (ti->max_io_len) { + max_len = blk_max_size_offset(ti->table->md->queue, + target_offset, ti->max_io_len); + if (len > max_len) + len = max_len; + } return len; } @@ -1196,11 +1199,9 @@ static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, * ->zero_page_range() is mandatory dax operation. If we are * here, something is wrong. */ - dm_put_live_table(md, srcu_idx); goto out; } ret = ti->type->dax_zero_page_range(ti, pgoff, nr_pages); - out: dm_put_live_table(md, srcu_idx); diff --git a/drivers/md/md.c b/drivers/md/md.c index 98bac4f304ae..0037c6ecab65 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8582,26 +8582,6 @@ void md_write_end(struct mddev *mddev) EXPORT_SYMBOL(md_write_end); -/* This is used by raid0 and raid10 */ -void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, - struct bio *bio, sector_t start, sector_t size) -{ - struct bio *discard_bio = NULL; - - if (__blkdev_issue_discard(rdev->bdev, start, size, - GFP_NOIO, 0, &discard_bio) || !discard_bio) - return; - - bio_chain(discard_bio, bio); - bio_clone_blkg_association(discard_bio, bio); - if (mddev->gendisk) - trace_block_bio_remap(bdev_get_queue(rdev->bdev), - discard_bio, disk_devt(mddev->gendisk), - bio->bi_iter.bi_sector); - submit_bio_noacct(discard_bio); -} -EXPORT_SYMBOL(md_submit_discard_bio); - /* md_allow_write(mddev) * Calling this ensures that the array is marked 'active' so that writes * may proceed without blocking. It is important to call this before diff --git a/drivers/md/md.h b/drivers/md/md.h index ccfb69868c2e..2175a5ac4f7c 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -713,8 +713,6 @@ extern void md_write_end(struct mddev *mddev); extern void md_done_sync(struct mddev *mddev, int blocks, int ok); extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); -extern void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, - struct bio *bio, sector_t start, sector_t size); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 6f44177593a5..35843df15b5e 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -477,6 +477,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) for (disk = 0; disk < zone->nb_dev; disk++) { sector_t dev_start, dev_end; + struct bio *discard_bio = NULL; struct md_rdev *rdev; if (disk < start_disk_index) @@ -499,9 +500,18 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) rdev = conf->devlist[(zone - conf->strip_zone) * conf->strip_zone[0].nb_dev + disk]; - md_submit_discard_bio(mddev, rdev, bio, + if (__blkdev_issue_discard(rdev->bdev, dev_start + zone->dev_start + rdev->data_offset, - dev_end - dev_start); + dev_end - dev_start, GFP_NOIO, 0, &discard_bio) || + !discard_bio) + continue; + bio_chain(discard_bio, bio); + bio_clone_blkg_association(discard_bio, bio); + if (mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(rdev->bdev), + discard_bio, disk_devt(mddev->gendisk), + bio->bi_iter.bi_sector); + submit_bio_noacct(discard_bio); } bio_endio(bio); } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index b7bca6703df8..3b598a3cb462 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -91,7 +91,7 @@ static inline struct r10bio *get_resync_r10bio(struct bio *bio) static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data) { struct r10conf *conf = data; - int size = offsetof(struct r10bio, devs[conf->geo.raid_disks]); + int size = offsetof(struct r10bio, devs[conf->copies]); /* allocate a r10bio with room for raid_disks entries in the * bios array */ @@ -238,7 +238,7 @@ static void put_all_bios(struct r10conf *conf, struct r10bio *r10_bio) { int i; - for (i = 0; i < conf->geo.raid_disks; i++) { + for (i = 0; i < conf->copies; i++) { struct bio **bio = & r10_bio->devs[i].bio; if (!BIO_SPECIAL(*bio)) bio_put(*bio); @@ -327,7 +327,7 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio, int slot; int repl = 0; - for (slot = 0; slot < conf->geo.raid_disks; slot++) { + for (slot = 0; slot < conf->copies; slot++) { if (r10_bio->devs[slot].bio == bio) break; if (r10_bio->devs[slot].repl_bio == bio) { @@ -336,6 +336,7 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio, } } + BUG_ON(slot == conf->copies); update_head_pos(slot, r10_bio); if (slotp) @@ -1275,75 +1276,12 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, } } -static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio) -{ - int i; - struct r10conf *conf = mddev->private; - struct md_rdev *blocked_rdev; - -retry_wait: - blocked_rdev = NULL; - rcu_read_lock(); - for (i = 0; i < conf->copies; i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[i].replacement); - if (rdev == rrdev) - rrdev = NULL; - if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) { - atomic_inc(&rdev->nr_pending); - blocked_rdev = rdev; - break; - } - if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) { - atomic_inc(&rrdev->nr_pending); - blocked_rdev = rrdev; - break; - } - - if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) { - sector_t first_bad; - sector_t dev_sector = r10_bio->devs[i].addr; - int bad_sectors; - int is_bad; - - /* Discard request doesn't care the write result - * so it doesn't need to wait blocked disk here. - */ - if (!r10_bio->sectors) - continue; - - is_bad = is_badblock(rdev, dev_sector, r10_bio->sectors, - &first_bad, &bad_sectors); - if (is_bad < 0) { - /* Mustn't write here until the bad block - * is acknowledged - */ - atomic_inc(&rdev->nr_pending); - set_bit(BlockedBadBlocks, &rdev->flags); - blocked_rdev = rdev; - break; - } - } - } - rcu_read_unlock(); - - if (unlikely(blocked_rdev)) { - /* Have to wait for this device to get unblocked, then retry */ - allow_barrier(conf); - raid10_log(conf->mddev, "%s wait rdev %d blocked", - __func__, blocked_rdev->raid_disk); - md_wait_for_blocked_rdev(blocked_rdev, mddev); - wait_barrier(conf); - goto retry_wait; - } -} - static void raid10_write_request(struct mddev *mddev, struct bio *bio, struct r10bio *r10_bio) { struct r10conf *conf = mddev->private; int i; + struct md_rdev *blocked_rdev; sector_t sectors; int max_sectors; @@ -1401,9 +1339,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, r10_bio->read_slot = -1; /* make sure repl_bio gets freed */ raid10_find_phys(conf, r10_bio); - - wait_blocked_dev(mddev, r10_bio); - +retry_write: + blocked_rdev = NULL; rcu_read_lock(); max_sectors = r10_bio->sectors; @@ -1414,6 +1351,16 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, conf->mirrors[d].replacement); if (rdev == rrdev) rrdev = NULL; + if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) { + atomic_inc(&rdev->nr_pending); + blocked_rdev = rdev; + break; + } + if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) { + atomic_inc(&rrdev->nr_pending); + blocked_rdev = rrdev; + break; + } if (rdev && (test_bit(Faulty, &rdev->flags))) rdev = NULL; if (rrdev && (test_bit(Faulty, &rrdev->flags))) @@ -1434,6 +1381,15 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, is_bad = is_badblock(rdev, dev_sector, max_sectors, &first_bad, &bad_sectors); + if (is_bad < 0) { + /* Mustn't write here until the bad block + * is acknowledged + */ + atomic_inc(&rdev->nr_pending); + set_bit(BlockedBadBlocks, &rdev->flags); + blocked_rdev = rdev; + break; + } if (is_bad && first_bad <= dev_sector) { /* Cannot write here at all */ bad_sectors -= (dev_sector - first_bad); @@ -1469,6 +1425,35 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, } rcu_read_unlock(); + if (unlikely(blocked_rdev)) { + /* Have to wait for this device to get unblocked, then retry */ + int j; + int d; + + for (j = 0; j < i; j++) { + if (r10_bio->devs[j].bio) { + d = r10_bio->devs[j].devnum; + rdev_dec_pending(conf->mirrors[d].rdev, mddev); + } + if (r10_bio->devs[j].repl_bio) { + struct md_rdev *rdev; + d = r10_bio->devs[j].devnum; + rdev = conf->mirrors[d].replacement; + if (!rdev) { + /* Race with remove_disk */ + smp_mb(); + rdev = conf->mirrors[d].rdev; + } + rdev_dec_pending(rdev, mddev); + } + } + allow_barrier(conf); + raid10_log(conf->mddev, "wait rdev %d blocked", blocked_rdev->raid_disk); + md_wait_for_blocked_rdev(blocked_rdev, mddev); + wait_barrier(conf); + goto retry_write; + } + if (max_sectors < r10_bio->sectors) r10_bio->sectors = max_sectors; @@ -1508,7 +1493,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors) r10_bio->mddev = mddev; r10_bio->sector = bio->bi_iter.bi_sector; r10_bio->state = 0; - memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->geo.raid_disks); + memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->copies); if (bio_data_dir(bio) == READ) raid10_read_request(mddev, bio, r10_bio); @@ -1516,296 +1501,6 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors) raid10_write_request(mddev, bio, r10_bio); } -static struct bio *raid10_split_bio(struct r10conf *conf, - struct bio *bio, sector_t sectors, bool want_first) -{ - struct bio *split; - - split = bio_split(bio, sectors, GFP_NOIO, &conf->bio_split); - bio_chain(split, bio); - allow_barrier(conf); - if (want_first) { - submit_bio_noacct(bio); - bio = split; - } else - submit_bio_noacct(split); - wait_barrier(conf); - - return bio; -} - -static void raid_end_discard_bio(struct r10bio *r10bio) -{ - struct r10conf *conf = r10bio->mddev->private; - struct r10bio *first_r10bio; - - while (atomic_dec_and_test(&r10bio->remaining)) { - - allow_barrier(conf); - - if (!test_bit(R10BIO_Discard, &r10bio->state)) { - first_r10bio = (struct r10bio *)r10bio->master_bio; - free_r10bio(r10bio); - r10bio = first_r10bio; - } else { - md_write_end(r10bio->mddev); - bio_endio(r10bio->master_bio); - free_r10bio(r10bio); - break; - } - } -} - -static void raid10_end_discard_request(struct bio *bio) -{ - struct r10bio *r10_bio = bio->bi_private; - struct r10conf *conf = r10_bio->mddev->private; - struct md_rdev *rdev = NULL; - int dev; - int slot, repl; - - /* - * We don't care the return value of discard bio - */ - if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) - set_bit(R10BIO_Uptodate, &r10_bio->state); - - dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl); - if (repl) - rdev = conf->mirrors[dev].replacement; - if (!rdev) { - /* raid10_remove_disk uses smp_mb to make sure rdev is set to - * replacement before setting replacement to NULL. It can read - * rdev first without barrier protect even replacment is NULL - */ - smp_rmb(); - rdev = conf->mirrors[dev].rdev; - } - - raid_end_discard_bio(r10_bio); - rdev_dec_pending(rdev, conf->mddev); -} - -/* There are some limitations to handle discard bio - * 1st, the discard size is bigger than stripe_size*2. - * 2st, if the discard bio spans reshape progress, we use the old way to - * handle discard bio - */ -static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) -{ - struct r10conf *conf = mddev->private; - struct geom *geo = &conf->geo; - struct r10bio *r10_bio, *first_r10bio; - int far_copies = geo->far_copies; - bool first_copy = true; - - int disk; - sector_t chunk; - unsigned int stripe_size; - sector_t split_size; - - sector_t bio_start, bio_end; - sector_t first_stripe_index, last_stripe_index; - sector_t start_disk_offset; - unsigned int start_disk_index; - sector_t end_disk_offset; - unsigned int end_disk_index; - unsigned int remainder; - - if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) - return -EAGAIN; - - wait_barrier(conf); - - /* Check reshape again to avoid reshape happens after checking - * MD_RECOVERY_RESHAPE and before wait_barrier - */ - if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) - goto out; - - stripe_size = geo->raid_disks << geo->chunk_shift; - bio_start = bio->bi_iter.bi_sector; - bio_end = bio_end_sector(bio); - - /* Maybe one discard bio is smaller than strip size or across one stripe - * and discard region is larger than one stripe size. For far offset layout, - * if the discard region is not aligned with stripe size, there is hole - * when we submit discard bio to member disk. For simplicity, we only - * handle discard bio which discard region is bigger than stripe_size*2 - */ - if (bio_sectors(bio) < stripe_size*2) - goto out; - - /* For far and far offset layout, if bio is not aligned with stripe size, - * it splits the part that is not aligned with strip size. - */ - div_u64_rem(bio_start, stripe_size, &remainder); - if ((far_copies > 1) && remainder) { - split_size = stripe_size - remainder; - bio = raid10_split_bio(conf, bio, split_size, false); - } - div_u64_rem(bio_end, stripe_size, &remainder); - if ((far_copies > 1) && remainder) { - split_size = bio_sectors(bio) - remainder; - bio = raid10_split_bio(conf, bio, split_size, true); - } - - bio_start = bio->bi_iter.bi_sector; - bio_end = bio_end_sector(bio); - - /* raid10 uses chunk as the unit to store data. It's similar like raid0. - * One stripe contains the chunks from all member disk (one chunk from - * one disk at the same HBA address). For layout detail, see 'man md 4' - */ - chunk = bio_start >> geo->chunk_shift; - chunk *= geo->near_copies; - first_stripe_index = chunk; - start_disk_index = sector_div(first_stripe_index, geo->raid_disks); - if (geo->far_offset) - first_stripe_index *= geo->far_copies; - start_disk_offset = (bio_start & geo->chunk_mask) + - (first_stripe_index << geo->chunk_shift); - - chunk = bio_end >> geo->chunk_shift; - chunk *= geo->near_copies; - last_stripe_index = chunk; - end_disk_index = sector_div(last_stripe_index, geo->raid_disks); - if (geo->far_offset) - last_stripe_index *= geo->far_copies; - end_disk_offset = (bio_end & geo->chunk_mask) + - (last_stripe_index << geo->chunk_shift); - -retry_discard: - r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO); - r10_bio->mddev = mddev; - r10_bio->state = 0; - r10_bio->sectors = 0; - memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * geo->raid_disks); - wait_blocked_dev(mddev, r10_bio); - - /* For far layout it needs more than one r10bio to cover all regions. - * Inspired by raid10_sync_request, we can use the first r10bio->master_bio - * to record the discard bio. Other r10bio->master_bio record the first - * r10bio. The first r10bio only release after all other r10bios finish. - * The discard bio returns only first r10bio finishes - */ - if (first_copy) { - r10_bio->master_bio = bio; - set_bit(R10BIO_Discard, &r10_bio->state); - first_copy = false; - first_r10bio = r10_bio; - } else - r10_bio->master_bio = (struct bio *)first_r10bio; - - rcu_read_lock(); - for (disk = 0; disk < geo->raid_disks; disk++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[disk].replacement); - - r10_bio->devs[disk].bio = NULL; - r10_bio->devs[disk].repl_bio = NULL; - - if (rdev && (test_bit(Faulty, &rdev->flags))) - rdev = NULL; - if (rrdev && (test_bit(Faulty, &rrdev->flags))) - rrdev = NULL; - if (!rdev && !rrdev) - continue; - - if (rdev) { - r10_bio->devs[disk].bio = bio; - atomic_inc(&rdev->nr_pending); - } - if (rrdev) { - r10_bio->devs[disk].repl_bio = bio; - atomic_inc(&rrdev->nr_pending); - } - } - rcu_read_unlock(); - - atomic_set(&r10_bio->remaining, 1); - for (disk = 0; disk < geo->raid_disks; disk++) { - sector_t dev_start, dev_end; - struct bio *mbio, *rbio = NULL; - struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[disk].replacement); - - /* - * Now start to calculate the start and end address for each disk. - * The space between dev_start and dev_end is the discard region. - * - * For dev_start, it needs to consider three conditions: - * 1st, the disk is before start_disk, you can imagine the disk in - * the next stripe. So the dev_start is the start address of next - * stripe. - * 2st, the disk is after start_disk, it means the disk is at the - * same stripe of first disk - * 3st, the first disk itself, we can use start_disk_offset directly - */ - if (disk < start_disk_index) - dev_start = (first_stripe_index + 1) * mddev->chunk_sectors; - else if (disk > start_disk_index) - dev_start = first_stripe_index * mddev->chunk_sectors; - else - dev_start = start_disk_offset; - - if (disk < end_disk_index) - dev_end = (last_stripe_index + 1) * mddev->chunk_sectors; - else if (disk > end_disk_index) - dev_end = last_stripe_index * mddev->chunk_sectors; - else - dev_end = end_disk_offset; - - /* It only handles discard bio which size is >= stripe size, so - * dev_end > dev_start all the time - */ - if (r10_bio->devs[disk].bio) { - mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); - mbio->bi_end_io = raid10_end_discard_request; - mbio->bi_private = r10_bio; - r10_bio->devs[disk].bio = mbio; - r10_bio->devs[disk].devnum = disk; - atomic_inc(&r10_bio->remaining); - md_submit_discard_bio(mddev, rdev, mbio, - dev_start + choose_data_offset(r10_bio, rdev), - dev_end - dev_start); - bio_endio(mbio); - } - if (r10_bio->devs[disk].repl_bio) { - rbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); - rbio->bi_end_io = raid10_end_discard_request; - rbio->bi_private = r10_bio; - r10_bio->devs[disk].repl_bio = rbio; - r10_bio->devs[disk].devnum = disk; - atomic_inc(&r10_bio->remaining); - md_submit_discard_bio(mddev, rrdev, rbio, - dev_start + choose_data_offset(r10_bio, rrdev), - dev_end - dev_start); - bio_endio(rbio); - } - } - - if (!geo->far_offset && --far_copies) { - first_stripe_index += geo->stride >> geo->chunk_shift; - start_disk_offset += geo->stride; - last_stripe_index += geo->stride >> geo->chunk_shift; - end_disk_offset += geo->stride; - atomic_inc(&first_r10bio->remaining); - raid_end_discard_bio(r10_bio); - wait_barrier(conf); - goto retry_discard; - } - - raid_end_discard_bio(r10_bio); - - return 0; -out: - allow_barrier(conf); - return -EAGAIN; -} - static bool raid10_make_request(struct mddev *mddev, struct bio *bio) { struct r10conf *conf = mddev->private; @@ -1820,10 +1515,6 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio) if (!md_write_start(mddev, bio)) return false; - if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) - if (!raid10_handle_discard(mddev, bio)) - return true; - /* * If this request crosses a chunk boundary, we need to split * it. @@ -4063,7 +3754,7 @@ static int raid10_run(struct mddev *mddev) if (mddev->queue) { blk_queue_max_discard_sectors(mddev->queue, - UINT_MAX); + mddev->chunk_sectors); blk_queue_max_write_same_sectors(mddev->queue, 0); blk_queue_max_write_zeroes_sectors(mddev->queue, 0); blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index 1461fd55311b..79cd2b7d3128 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -179,6 +179,5 @@ enum r10bio_state { R10BIO_Previous, /* failfast devices did receive failfast requests. */ R10BIO_FailFast, - R10BIO_Discard, }; #endif diff --git a/drivers/media/cec/usb/pulse8/pulse8-cec.c b/drivers/media/cec/usb/pulse8/pulse8-cec.c index e4d8446b87da..04b13cdc38d2 100644 --- a/drivers/media/cec/usb/pulse8/pulse8-cec.c +++ b/drivers/media/cec/usb/pulse8/pulse8-cec.c @@ -88,13 +88,15 @@ enum pulse8_msgcodes { MSGCODE_SET_PHYSICAL_ADDRESS, /* 0x20 */ MSGCODE_GET_DEVICE_TYPE, MSGCODE_SET_DEVICE_TYPE, - MSGCODE_GET_HDMI_VERSION, + MSGCODE_GET_HDMI_VERSION, /* Removed in FW >= 10 */ MSGCODE_SET_HDMI_VERSION, MSGCODE_GET_OSD_NAME, MSGCODE_SET_OSD_NAME, MSGCODE_WRITE_EEPROM, MSGCODE_GET_ADAPTER_TYPE, /* 0x28 */ MSGCODE_SET_ACTIVE_SOURCE, + MSGCODE_GET_AUTO_POWER_ON, /* New for FW >= 10 */ + MSGCODE_SET_AUTO_POWER_ON, MSGCODE_FRAME_EOM = 0x80, MSGCODE_FRAME_ACK = 0x40, @@ -143,6 +145,8 @@ static const char * const pulse8_msgnames[] = { "WRITE_EEPROM", "GET_ADAPTER_TYPE", "SET_ACTIVE_SOURCE", + "GET_AUTO_POWER_ON", + "SET_AUTO_POWER_ON", }; static const char *pulse8_msgname(u8 cmd) @@ -579,12 +583,14 @@ static int pulse8_cec_adap_log_addr(struct cec_adapter *adap, u8 log_addr) if (err) goto unlock; - cmd[0] = MSGCODE_SET_HDMI_VERSION; - cmd[1] = adap->log_addrs.cec_version; - err = pulse8_send_and_wait(pulse8, cmd, 2, - MSGCODE_COMMAND_ACCEPTED, 0); - if (err) - goto unlock; + if (pulse8->vers < 10) { + cmd[0] = MSGCODE_SET_HDMI_VERSION; + cmd[1] = adap->log_addrs.cec_version; + err = pulse8_send_and_wait(pulse8, cmd, 2, + MSGCODE_COMMAND_ACCEPTED, 0); + if (err) + goto unlock; + } if (adap->log_addrs.osd_name[0]) { size_t osd_len = strlen(adap->log_addrs.osd_name); @@ -650,7 +656,6 @@ static void pulse8_disconnect(struct serio *serio) struct pulse8 *pulse8 = serio_get_drvdata(serio); cec_unregister_adapter(pulse8->adap); - pulse8->serio = NULL; serio_set_drvdata(serio, NULL); serio_close(serio); } @@ -692,6 +697,14 @@ static int pulse8_setup(struct pulse8 *pulse8, struct serio *serio, dev_dbg(pulse8->dev, "Autonomous mode: %s", data[0] ? "on" : "off"); + if (pulse8->vers >= 10) { + cmd[0] = MSGCODE_GET_AUTO_POWER_ON; + err = pulse8_send_and_wait(pulse8, cmd, 1, cmd[0], 1); + if (!err) + dev_dbg(pulse8->dev, "Auto Power On: %s", + data[0] ? "on" : "off"); + } + cmd[0] = MSGCODE_GET_DEVICE_TYPE; err = pulse8_send_and_wait(pulse8, cmd, 1, cmd[0], 1); if (err) @@ -753,12 +766,15 @@ static int pulse8_setup(struct pulse8 *pulse8, struct serio *serio, dev_dbg(pulse8->dev, "Physical address: %x.%x.%x.%x\n", cec_phys_addr_exp(*pa)); - cmd[0] = MSGCODE_GET_HDMI_VERSION; - err = pulse8_send_and_wait(pulse8, cmd, 1, cmd[0], 1); - if (err) - return err; - log_addrs->cec_version = data[0]; - dev_dbg(pulse8->dev, "CEC version: %d\n", log_addrs->cec_version); + log_addrs->cec_version = CEC_OP_CEC_VERSION_1_4; + if (pulse8->vers < 10) { + cmd[0] = MSGCODE_GET_HDMI_VERSION; + err = pulse8_send_and_wait(pulse8, cmd, 1, cmd[0], 1); + if (err) + return err; + log_addrs->cec_version = data[0]; + dev_dbg(pulse8->dev, "CEC version: %d\n", log_addrs->cec_version); + } cmd[0] = MSGCODE_GET_OSD_NAME; err = pulse8_send_and_wait(pulse8, cmd, 1, cmd[0], 0); @@ -830,8 +846,10 @@ static int pulse8_connect(struct serio *serio, struct serio_driver *drv) pulse8->adap = cec_allocate_adapter(&pulse8_cec_adap_ops, pulse8, dev_name(&serio->dev), caps, 1); err = PTR_ERR_OR_ZERO(pulse8->adap); - if (err < 0) - goto free_device; + if (err < 0) { + kfree(pulse8); + return err; + } pulse8->dev = &serio->dev; serio_set_drvdata(serio, pulse8); @@ -874,8 +892,6 @@ close_serio: serio_close(serio); delete_adap: cec_delete_adapter(pulse8->adap); -free_device: - kfree(pulse8); return err; } diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index 4eab6d81cce1..89e38392509c 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -414,6 +414,17 @@ static int __vb2_queue_alloc(struct vb2_queue *q, enum vb2_memory memory, vb->index = q->num_buffers + buffer; vb->type = q->type; vb->memory = memory; + /* + * We need to set these flags here so that the videobuf2 core + * will call ->prepare()/->finish() cache sync/flush on vb2 + * buffers when appropriate. However, we can avoid explicit + * ->prepare() and ->finish() cache sync for DMABUF buffers, + * because DMA exporter takes care of it. + */ + if (q->memory != VB2_MEMORY_DMABUF) { + vb->need_cache_sync_on_prepare = 1; + vb->need_cache_sync_on_finish = 1; + } for (plane = 0; plane < num_planes; ++plane) { vb->planes[plane].length = plane_sizes[plane]; vb->planes[plane].min_length = plane_sizes[plane]; diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig index a3cb104956d5..7e152bbb4fa6 100644 --- a/drivers/media/platform/Kconfig +++ b/drivers/media/platform/Kconfig @@ -253,17 +253,31 @@ config VIDEO_MEDIATEK_VCODEC depends on MTK_IOMMU || COMPILE_TEST depends on VIDEO_DEV && VIDEO_V4L2 depends on ARCH_MEDIATEK || COMPILE_TEST + depends on VIDEO_MEDIATEK_VPU || MTK_SCP + # The two following lines ensure we have the same state ("m" or "y") as + # our dependencies, to avoid missing symbols during link. + depends on VIDEO_MEDIATEK_VPU || !VIDEO_MEDIATEK_VPU + depends on MTK_SCP || !MTK_SCP select VIDEOBUF2_DMA_CONTIG select V4L2_MEM2MEM_DEV - select VIDEO_MEDIATEK_VPU - select MTK_SCP + select VIDEO_MEDIATEK_VCODEC_VPU if VIDEO_MEDIATEK_VPU + select VIDEO_MEDIATEK_VCODEC_SCP if MTK_SCP help - Mediatek video codec driver provides HW capability to - encode and decode in a range of video formats - This driver rely on VPU driver to communicate with VPU. + Mediatek video codec driver provides HW capability to + encode and decode in a range of video formats on MT8173 + and MT8183. + + Note that support for MT8173 requires VIDEO_MEDIATEK_VPU to + also be selected. Support for MT8183 depends on MTK_SCP. + + To compile this driver as modules, choose M here: the + modules will be called mtk-vcodec-dec and mtk-vcodec-enc. + +config VIDEO_MEDIATEK_VCODEC_VPU + bool - To compile this driver as modules, choose M here: the - modules will be called mtk-vcodec-dec and mtk-vcodec-enc. +config VIDEO_MEDIATEK_VCODEC_SCP + bool config VIDEO_MEM2MEM_DEINTERLACE tristate "Deinterlace support" diff --git a/drivers/media/platform/marvell-ccic/mmp-driver.c b/drivers/media/platform/marvell-ccic/mmp-driver.c index cd902b180669..63fce1b85d26 100644 --- a/drivers/media/platform/marvell-ccic/mmp-driver.c +++ b/drivers/media/platform/marvell-ccic/mmp-driver.c @@ -307,6 +307,7 @@ static int mmpcam_platform_remove(struct platform_device *pdev) * Suspend/resume support. */ +#ifdef CONFIG_PM static int mmpcam_runtime_resume(struct device *dev) { struct mmp_camera *cam = dev_get_drvdata(dev); @@ -352,6 +353,7 @@ static int __maybe_unused mmpcam_resume(struct device *dev) return mccic_resume(&cam->mcam); return 0; } +#endif static const struct dev_pm_ops mmpcam_pm_ops = { SET_RUNTIME_PM_OPS(mmpcam_runtime_suspend, mmpcam_runtime_resume, NULL) diff --git a/drivers/media/platform/mtk-vcodec/Makefile b/drivers/media/platform/mtk-vcodec/Makefile index f679c6e1a3e9..4618d43dbbc8 100644 --- a/drivers/media/platform/mtk-vcodec/Makefile +++ b/drivers/media/platform/mtk-vcodec/Makefile @@ -24,4 +24,12 @@ mtk-vcodec-enc-y := venc/venc_vp8_if.o \ mtk-vcodec-common-y := mtk_vcodec_intr.o \ mtk_vcodec_util.o \ - mtk_vcodec_fw.o + mtk_vcodec_fw.o \ + +ifneq ($(CONFIG_VIDEO_MEDIATEK_VCODEC_VPU),) +mtk-vcodec-common-y += mtk_vcodec_fw_vpu.o +endif + +ifneq ($(CONFIG_VIDEO_MEDIATEK_VCODEC_SCP),) +mtk-vcodec-common-y += mtk_vcodec_fw_scp.o +endif diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c index d14bc208ea5e..145686d2c219 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c @@ -241,7 +241,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev) } dma_set_max_seg_size(&pdev->dev, DMA_BIT_MASK(32)); - dev->fw_handler = mtk_vcodec_fw_select(dev, fw_type, VPU_RST_DEC); + dev->fw_handler = mtk_vcodec_fw_select(dev, fw_type, DECODER); if (IS_ERR(dev->fw_handler)) return PTR_ERR(dev->fw_handler); diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_drv.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_drv.c index dcfa2c2d4def..3be8a04c4c67 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_drv.c +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc_drv.c @@ -293,7 +293,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev) } dma_set_max_seg_size(&pdev->dev, DMA_BIT_MASK(32)); - dev->fw_handler = mtk_vcodec_fw_select(dev, fw_type, VPU_RST_ENC); + dev->fw_handler = mtk_vcodec_fw_select(dev, fw_type, ENCODER); if (IS_ERR(dev->fw_handler)) return PTR_ERR(dev->fw_handler); diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.c index 6c2a2568d844..94b39ae5c2e1 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.c +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.c @@ -1,193 +1,29 @@ // SPDX-License-Identifier: GPL-2.0 #include "mtk_vcodec_fw.h" +#include "mtk_vcodec_fw_priv.h" #include "mtk_vcodec_util.h" #include "mtk_vcodec_drv.h" -struct mtk_vcodec_fw_ops { - int (*load_firmware)(struct mtk_vcodec_fw *fw); - unsigned int (*get_vdec_capa)(struct mtk_vcodec_fw *fw); - unsigned int (*get_venc_capa)(struct mtk_vcodec_fw *fw); - void * (*map_dm_addr)(struct mtk_vcodec_fw *fw, u32 dtcm_dmem_addr); - int (*ipi_register)(struct mtk_vcodec_fw *fw, int id, - mtk_vcodec_ipi_handler handler, const char *name, void *priv); - int (*ipi_send)(struct mtk_vcodec_fw *fw, int id, void *buf, - unsigned int len, unsigned int wait); -}; - -struct mtk_vcodec_fw { - enum mtk_vcodec_fw_type type; - const struct mtk_vcodec_fw_ops *ops; - struct platform_device *pdev; - struct mtk_scp *scp; -}; - -static int mtk_vcodec_vpu_load_firmware(struct mtk_vcodec_fw *fw) -{ - return vpu_load_firmware(fw->pdev); -} - -static unsigned int mtk_vcodec_vpu_get_vdec_capa(struct mtk_vcodec_fw *fw) -{ - return vpu_get_vdec_hw_capa(fw->pdev); -} - -static unsigned int mtk_vcodec_vpu_get_venc_capa(struct mtk_vcodec_fw *fw) -{ - return vpu_get_venc_hw_capa(fw->pdev); -} - -static void *mtk_vcodec_vpu_map_dm_addr(struct mtk_vcodec_fw *fw, - u32 dtcm_dmem_addr) -{ - return vpu_mapping_dm_addr(fw->pdev, dtcm_dmem_addr); -} - -static int mtk_vcodec_vpu_set_ipi_register(struct mtk_vcodec_fw *fw, int id, - mtk_vcodec_ipi_handler handler, - const char *name, void *priv) -{ - /* - * The handler we receive takes a void * as its first argument. We - * cannot change this because it needs to be passed down to the rproc - * subsystem when SCP is used. VPU takes a const argument, which is - * more constrained, so the conversion below is safe. - */ - ipi_handler_t handler_const = (ipi_handler_t)handler; - - return vpu_ipi_register(fw->pdev, id, handler_const, name, priv); -} - -static int mtk_vcodec_vpu_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf, - unsigned int len, unsigned int wait) -{ - return vpu_ipi_send(fw->pdev, id, buf, len); -} - -static const struct mtk_vcodec_fw_ops mtk_vcodec_vpu_msg = { - .load_firmware = mtk_vcodec_vpu_load_firmware, - .get_vdec_capa = mtk_vcodec_vpu_get_vdec_capa, - .get_venc_capa = mtk_vcodec_vpu_get_venc_capa, - .map_dm_addr = mtk_vcodec_vpu_map_dm_addr, - .ipi_register = mtk_vcodec_vpu_set_ipi_register, - .ipi_send = mtk_vcodec_vpu_ipi_send, -}; - -static int mtk_vcodec_scp_load_firmware(struct mtk_vcodec_fw *fw) -{ - return rproc_boot(scp_get_rproc(fw->scp)); -} - -static unsigned int mtk_vcodec_scp_get_vdec_capa(struct mtk_vcodec_fw *fw) -{ - return scp_get_vdec_hw_capa(fw->scp); -} - -static unsigned int mtk_vcodec_scp_get_venc_capa(struct mtk_vcodec_fw *fw) -{ - return scp_get_venc_hw_capa(fw->scp); -} - -static void *mtk_vcodec_vpu_scp_dm_addr(struct mtk_vcodec_fw *fw, - u32 dtcm_dmem_addr) -{ - return scp_mapping_dm_addr(fw->scp, dtcm_dmem_addr); -} - -static int mtk_vcodec_scp_set_ipi_register(struct mtk_vcodec_fw *fw, int id, - mtk_vcodec_ipi_handler handler, - const char *name, void *priv) -{ - return scp_ipi_register(fw->scp, id, handler, priv); -} - -static int mtk_vcodec_scp_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf, - unsigned int len, unsigned int wait) -{ - return scp_ipi_send(fw->scp, id, buf, len, wait); -} - -static const struct mtk_vcodec_fw_ops mtk_vcodec_rproc_msg = { - .load_firmware = mtk_vcodec_scp_load_firmware, - .get_vdec_capa = mtk_vcodec_scp_get_vdec_capa, - .get_venc_capa = mtk_vcodec_scp_get_venc_capa, - .map_dm_addr = mtk_vcodec_vpu_scp_dm_addr, - .ipi_register = mtk_vcodec_scp_set_ipi_register, - .ipi_send = mtk_vcodec_scp_ipi_send, -}; - -static void mtk_vcodec_reset_handler(void *priv) -{ - struct mtk_vcodec_dev *dev = priv; - struct mtk_vcodec_ctx *ctx; - - mtk_v4l2_err("Watchdog timeout!!"); - - mutex_lock(&dev->dev_mutex); - list_for_each_entry(ctx, &dev->ctx_list, list) { - ctx->state = MTK_STATE_ABORT; - mtk_v4l2_debug(0, "[%d] Change to state MTK_STATE_ABORT", - ctx->id); - } - mutex_unlock(&dev->dev_mutex); -} - struct mtk_vcodec_fw *mtk_vcodec_fw_select(struct mtk_vcodec_dev *dev, enum mtk_vcodec_fw_type type, - enum rst_id rst_id) + enum mtk_vcodec_fw_use fw_use) { - const struct mtk_vcodec_fw_ops *ops; - struct mtk_vcodec_fw *fw; - struct platform_device *fw_pdev = NULL; - struct mtk_scp *scp = NULL; - switch (type) { case VPU: - ops = &mtk_vcodec_vpu_msg; - fw_pdev = vpu_get_plat_device(dev->plat_dev); - if (!fw_pdev) { - mtk_v4l2_err("firmware device is not ready"); - return ERR_PTR(-EINVAL); - } - vpu_wdt_reg_handler(fw_pdev, mtk_vcodec_reset_handler, - dev, rst_id); - break; + return mtk_vcodec_fw_vpu_init(dev, fw_use); case SCP: - ops = &mtk_vcodec_rproc_msg; - scp = scp_get(dev->plat_dev); - if (!scp) { - mtk_v4l2_err("could not get vdec scp handle"); - return ERR_PTR(-EPROBE_DEFER); - } - break; + return mtk_vcodec_fw_scp_init(dev); default: mtk_v4l2_err("invalid vcodec fw type"); return ERR_PTR(-EINVAL); } - - fw = devm_kzalloc(&dev->plat_dev->dev, sizeof(*fw), GFP_KERNEL); - if (!fw) - return ERR_PTR(-EINVAL); - - fw->type = type; - fw->ops = ops; - fw->pdev = fw_pdev; - fw->scp = scp; - - return fw; } EXPORT_SYMBOL_GPL(mtk_vcodec_fw_select); void mtk_vcodec_fw_release(struct mtk_vcodec_fw *fw) { - switch (fw->type) { - case VPU: - put_device(&fw->pdev->dev); - break; - case SCP: - scp_put(fw->scp); - break; - } + fw->ops->release(fw); } EXPORT_SYMBOL_GPL(mtk_vcodec_fw_release); diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.h index fadbbe6ba6cd..539bb626772c 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.h +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw.h @@ -15,6 +15,11 @@ enum mtk_vcodec_fw_type { SCP, }; +enum mtk_vcodec_fw_use { + DECODER, + ENCODER, +}; + struct mtk_vcodec_fw; typedef void (*mtk_vcodec_ipi_handler) (void *data, @@ -22,7 +27,7 @@ typedef void (*mtk_vcodec_ipi_handler) (void *data, struct mtk_vcodec_fw *mtk_vcodec_fw_select(struct mtk_vcodec_dev *dev, enum mtk_vcodec_fw_type type, - enum rst_id rst_id); + enum mtk_vcodec_fw_use fw_use); void mtk_vcodec_fw_release(struct mtk_vcodec_fw *fw); int mtk_vcodec_fw_load_firmware(struct mtk_vcodec_fw *fw); diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_priv.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_priv.h new file mode 100644 index 000000000000..b41e66185cec --- /dev/null +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_priv.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _MTK_VCODEC_FW_PRIV_H_ +#define _MTK_VCODEC_FW_PRIV_H_ + +#include "mtk_vcodec_fw.h" + +struct mtk_vcodec_dev; + +struct mtk_vcodec_fw { + enum mtk_vcodec_fw_type type; + const struct mtk_vcodec_fw_ops *ops; + struct platform_device *pdev; + struct mtk_scp *scp; +}; + +struct mtk_vcodec_fw_ops { + int (*load_firmware)(struct mtk_vcodec_fw *fw); + unsigned int (*get_vdec_capa)(struct mtk_vcodec_fw *fw); + unsigned int (*get_venc_capa)(struct mtk_vcodec_fw *fw); + void *(*map_dm_addr)(struct mtk_vcodec_fw *fw, u32 dtcm_dmem_addr); + int (*ipi_register)(struct mtk_vcodec_fw *fw, int id, + mtk_vcodec_ipi_handler handler, const char *name, + void *priv); + int (*ipi_send)(struct mtk_vcodec_fw *fw, int id, void *buf, + unsigned int len, unsigned int wait); + void (*release)(struct mtk_vcodec_fw *fw); +}; + +#if IS_ENABLED(CONFIG_VIDEO_MEDIATEK_VCODEC_VPU) +struct mtk_vcodec_fw *mtk_vcodec_fw_vpu_init(struct mtk_vcodec_dev *dev, + enum mtk_vcodec_fw_use fw_use); +#else +static inline struct mtk_vcodec_fw * +mtk_vcodec_fw_vpu_init(struct mtk_vcodec_dev *dev, + enum mtk_vcodec_fw_use fw_use) +{ + return ERR_PTR(-ENODEV); +} +#endif /* CONFIG_VIDEO_MEDIATEK_VCODEC_VPU */ + +#if IS_ENABLED(CONFIG_VIDEO_MEDIATEK_VCODEC_SCP) +struct mtk_vcodec_fw *mtk_vcodec_fw_scp_init(struct mtk_vcodec_dev *dev); +#else +static inline struct mtk_vcodec_fw * +mtk_vcodec_fw_scp_init(struct mtk_vcodec_dev *dev) +{ + return ERR_PTR(-ENODEV); +} +#endif /* CONFIG_VIDEO_MEDIATEK_VCODEC_SCP */ + +#endif /* _MTK_VCODEC_FW_PRIV_H_ */ diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_scp.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_scp.c new file mode 100644 index 000000000000..d8e66b645bd8 --- /dev/null +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_scp.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "mtk_vcodec_fw_priv.h" +#include "mtk_vcodec_util.h" +#include "mtk_vcodec_drv.h" + +static int mtk_vcodec_scp_load_firmware(struct mtk_vcodec_fw *fw) +{ + return rproc_boot(scp_get_rproc(fw->scp)); +} + +static unsigned int mtk_vcodec_scp_get_vdec_capa(struct mtk_vcodec_fw *fw) +{ + return scp_get_vdec_hw_capa(fw->scp); +} + +static unsigned int mtk_vcodec_scp_get_venc_capa(struct mtk_vcodec_fw *fw) +{ + return scp_get_venc_hw_capa(fw->scp); +} + +static void *mtk_vcodec_vpu_scp_dm_addr(struct mtk_vcodec_fw *fw, + u32 dtcm_dmem_addr) +{ + return scp_mapping_dm_addr(fw->scp, dtcm_dmem_addr); +} + +static int mtk_vcodec_scp_set_ipi_register(struct mtk_vcodec_fw *fw, int id, + mtk_vcodec_ipi_handler handler, + const char *name, void *priv) +{ + return scp_ipi_register(fw->scp, id, handler, priv); +} + +static int mtk_vcodec_scp_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf, + unsigned int len, unsigned int wait) +{ + return scp_ipi_send(fw->scp, id, buf, len, wait); +} + +static void mtk_vcodec_scp_release(struct mtk_vcodec_fw *fw) +{ + scp_put(fw->scp); +} + +static const struct mtk_vcodec_fw_ops mtk_vcodec_rproc_msg = { + .load_firmware = mtk_vcodec_scp_load_firmware, + .get_vdec_capa = mtk_vcodec_scp_get_vdec_capa, + .get_venc_capa = mtk_vcodec_scp_get_venc_capa, + .map_dm_addr = mtk_vcodec_vpu_scp_dm_addr, + .ipi_register = mtk_vcodec_scp_set_ipi_register, + .ipi_send = mtk_vcodec_scp_ipi_send, + .release = mtk_vcodec_scp_release, +}; + +struct mtk_vcodec_fw *mtk_vcodec_fw_scp_init(struct mtk_vcodec_dev *dev) +{ + struct mtk_vcodec_fw *fw; + struct mtk_scp *scp; + + scp = scp_get(dev->plat_dev); + if (!scp) { + mtk_v4l2_err("could not get vdec scp handle"); + return ERR_PTR(-EPROBE_DEFER); + } + + fw = devm_kzalloc(&dev->plat_dev->dev, sizeof(*fw), GFP_KERNEL); + fw->type = SCP; + fw->ops = &mtk_vcodec_rproc_msg; + fw->scp = scp; + + return fw; +} diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_vpu.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_vpu.c new file mode 100644 index 000000000000..cd27f637dbe7 --- /dev/null +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_vpu.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "mtk_vcodec_fw_priv.h" +#include "mtk_vcodec_util.h" +#include "mtk_vcodec_drv.h" + +static int mtk_vcodec_vpu_load_firmware(struct mtk_vcodec_fw *fw) +{ + return vpu_load_firmware(fw->pdev); +} + +static unsigned int mtk_vcodec_vpu_get_vdec_capa(struct mtk_vcodec_fw *fw) +{ + return vpu_get_vdec_hw_capa(fw->pdev); +} + +static unsigned int mtk_vcodec_vpu_get_venc_capa(struct mtk_vcodec_fw *fw) +{ + return vpu_get_venc_hw_capa(fw->pdev); +} + +static void *mtk_vcodec_vpu_map_dm_addr(struct mtk_vcodec_fw *fw, + u32 dtcm_dmem_addr) +{ + return vpu_mapping_dm_addr(fw->pdev, dtcm_dmem_addr); +} + +static int mtk_vcodec_vpu_set_ipi_register(struct mtk_vcodec_fw *fw, int id, + mtk_vcodec_ipi_handler handler, + const char *name, void *priv) +{ + /* + * The handler we receive takes a void * as its first argument. We + * cannot change this because it needs to be passed down to the rproc + * subsystem when SCP is used. VPU takes a const argument, which is + * more constrained, so the conversion below is safe. + */ + ipi_handler_t handler_const = (ipi_handler_t)handler; + + return vpu_ipi_register(fw->pdev, id, handler_const, name, priv); +} + +static int mtk_vcodec_vpu_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf, + unsigned int len, unsigned int wait) +{ + return vpu_ipi_send(fw->pdev, id, buf, len); +} + +static void mtk_vcodec_vpu_release(struct mtk_vcodec_fw *fw) +{ + put_device(&fw->pdev->dev); +} + +static void mtk_vcodec_vpu_reset_handler(void *priv) +{ + struct mtk_vcodec_dev *dev = priv; + struct mtk_vcodec_ctx *ctx; + + mtk_v4l2_err("Watchdog timeout!!"); + + mutex_lock(&dev->dev_mutex); + list_for_each_entry(ctx, &dev->ctx_list, list) { + ctx->state = MTK_STATE_ABORT; + mtk_v4l2_debug(0, "[%d] Change to state MTK_STATE_ABORT", + ctx->id); + } + mutex_unlock(&dev->dev_mutex); +} + +static const struct mtk_vcodec_fw_ops mtk_vcodec_vpu_msg = { + .load_firmware = mtk_vcodec_vpu_load_firmware, + .get_vdec_capa = mtk_vcodec_vpu_get_vdec_capa, + .get_venc_capa = mtk_vcodec_vpu_get_venc_capa, + .map_dm_addr = mtk_vcodec_vpu_map_dm_addr, + .ipi_register = mtk_vcodec_vpu_set_ipi_register, + .ipi_send = mtk_vcodec_vpu_ipi_send, + .release = mtk_vcodec_vpu_release, +}; + +struct mtk_vcodec_fw *mtk_vcodec_fw_vpu_init(struct mtk_vcodec_dev *dev, + enum mtk_vcodec_fw_use fw_use) +{ + struct platform_device *fw_pdev; + struct mtk_vcodec_fw *fw; + enum rst_id rst_id; + + switch (fw_use) { + case ENCODER: + rst_id = VPU_RST_ENC; + break; + case DECODER: + default: + rst_id = VPU_RST_DEC; + break; + } + + fw_pdev = vpu_get_plat_device(dev->plat_dev); + if (!fw_pdev) { + mtk_v4l2_err("firmware device is not ready"); + return ERR_PTR(-EINVAL); + } + vpu_wdt_reg_handler(fw_pdev, mtk_vcodec_vpu_reset_handler, dev, rst_id); + + fw = devm_kzalloc(&dev->plat_dev->dev, sizeof(*fw), GFP_KERNEL); + fw->type = VPU; + fw->ops = &mtk_vcodec_vpu_msg; + fw->pdev = fw_pdev; + + return fw; +} diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h index 7b79a33dc9d6..05c9fbd51f0c 100644 --- a/drivers/media/platform/qcom/venus/core.h +++ b/drivers/media/platform/qcom/venus/core.h @@ -243,8 +243,19 @@ struct venc_controls { u32 header_mode; - u32 profile; - u32 level; + struct { + u32 h264; + u32 mpeg4; + u32 hevc; + u32 vp8; + u32 vp9; + } profile; + struct { + u32 h264; + u32 mpeg4; + u32 hevc; + u32 vp9; + } level; }; struct venus_buffer { diff --git a/drivers/media/platform/qcom/venus/pm_helpers.c b/drivers/media/platform/qcom/venus/pm_helpers.c index 57877eacecf0..a9538c2cc3c9 100644 --- a/drivers/media/platform/qcom/venus/pm_helpers.c +++ b/drivers/media/platform/qcom/venus/pm_helpers.c @@ -794,7 +794,7 @@ skip_pmdomains: return 0; opp_dl_add_err: - dev_pm_domain_detach(core->opp_pmdomain, true); + dev_pm_opp_detach_genpd(core->opp_table); opp_attach_err: if (core->pd_dl_venus) { device_link_del(core->pd_dl_venus); @@ -832,7 +832,7 @@ skip_pmdomains: if (core->opp_dl_venus) device_link_del(core->opp_dl_venus); - dev_pm_domain_detach(core->opp_pmdomain, true); + dev_pm_opp_detach_genpd(core->opp_table); } static int core_get_v4(struct device *dev) diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c index f8b1484e7dcd..47246528ac7e 100644 --- a/drivers/media/platform/qcom/venus/venc.c +++ b/drivers/media/platform/qcom/venus/venc.c @@ -537,6 +537,7 @@ static int venc_set_properties(struct venus_inst *inst) struct hfi_quantization quant; struct hfi_quantization_range quant_range; u32 ptype, rate_control, bitrate; + u32 profile, level; int ret; ret = venus_helper_set_work_mode(inst, VIDC_WORK_MODE_2); @@ -684,7 +685,35 @@ static int venc_set_properties(struct venus_inst *inst) if (ret) return ret; - ret = venus_helper_set_profile_level(inst, ctr->profile, ctr->level); + switch (inst->hfi_codec) { + case HFI_VIDEO_CODEC_H264: + profile = ctr->profile.h264; + level = ctr->level.h264; + break; + case HFI_VIDEO_CODEC_MPEG4: + profile = ctr->profile.mpeg4; + level = ctr->level.mpeg4; + break; + case HFI_VIDEO_CODEC_VP8: + profile = ctr->profile.vp8; + level = 0; + break; + case HFI_VIDEO_CODEC_VP9: + profile = ctr->profile.vp9; + level = ctr->level.vp9; + break; + case HFI_VIDEO_CODEC_HEVC: + profile = ctr->profile.hevc; + level = ctr->level.hevc; + break; + case HFI_VIDEO_CODEC_MPEG2: + default: + profile = 0; + level = 0; + break; + } + + ret = venus_helper_set_profile_level(inst, profile, level); if (ret) return ret; diff --git a/drivers/media/platform/qcom/venus/venc_ctrls.c b/drivers/media/platform/qcom/venus/venc_ctrls.c index 0708b3b89d0c..cf860e6446c0 100644 --- a/drivers/media/platform/qcom/venus/venc_ctrls.c +++ b/drivers/media/platform/qcom/venus/venc_ctrls.c @@ -103,15 +103,25 @@ static int venc_op_s_ctrl(struct v4l2_ctrl *ctrl) ctr->h264_entropy_mode = ctrl->val; break; case V4L2_CID_MPEG_VIDEO_MPEG4_PROFILE: + ctr->profile.mpeg4 = ctrl->val; + break; case V4L2_CID_MPEG_VIDEO_H264_PROFILE: + ctr->profile.h264 = ctrl->val; + break; case V4L2_CID_MPEG_VIDEO_HEVC_PROFILE: + ctr->profile.hevc = ctrl->val; + break; case V4L2_CID_MPEG_VIDEO_VP8_PROFILE: - ctr->profile = ctrl->val; + ctr->profile.vp8 = ctrl->val; break; case V4L2_CID_MPEG_VIDEO_MPEG4_LEVEL: + ctr->level.mpeg4 = ctrl->val; + break; case V4L2_CID_MPEG_VIDEO_H264_LEVEL: + ctr->level.h264 = ctrl->val; + break; case V4L2_CID_MPEG_VIDEO_HEVC_LEVEL: - ctr->level = ctrl->val; + ctr->level.hevc = ctrl->val; break; case V4L2_CID_MPEG_VIDEO_H264_I_FRAME_QP: ctr->h264_i_qp = ctrl->val; diff --git a/drivers/media/rc/mtk-cir.c b/drivers/media/rc/mtk-cir.c index 5051a5e5244b..65a136c0fac2 100644 --- a/drivers/media/rc/mtk-cir.c +++ b/drivers/media/rc/mtk-cir.c @@ -151,15 +151,12 @@ static inline u32 mtk_chk_period(struct mtk_ir *ir) { u32 val; - /* Period of raw software sampling in ns */ - val = DIV_ROUND_CLOSEST(1000000000ul, - clk_get_rate(ir->bus) / ir->data->div); - /* * Period for software decoder used in the * unit of raw software sampling */ - val = DIV_ROUND_CLOSEST(MTK_IR_SAMPLE, val); + val = DIV_ROUND_CLOSEST(clk_get_rate(ir->bus), + USEC_PER_SEC * ir->data->div / MTK_IR_SAMPLE); dev_dbg(ir->dev, "@pwm clk = \t%lu\n", clk_get_rate(ir->bus) / ir->data->div); @@ -412,7 +409,7 @@ static int mtk_ir_probe(struct platform_device *pdev) mtk_irq_enable(ir, MTK_IRINT_EN); dev_info(dev, "Initialized MT7623 IR driver, sample period = %dus\n", - DIV_ROUND_CLOSEST(MTK_IR_SAMPLE, 1000)); + MTK_IR_SAMPLE); return 0; diff --git a/drivers/media/test-drivers/vidtv/vidtv_bridge.c b/drivers/media/test-drivers/vidtv/vidtv_bridge.c index 74b054947bbe..fc64d0c8492a 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_bridge.c +++ b/drivers/media/test-drivers/vidtv/vidtv_bridge.c @@ -4,36 +4,43 @@ * validate the existing APIs in the media subsystem. It can also aid * developers working on userspace applications. * - * When this module is loaded, it will attempt to modprobe 'dvb_vidtv_tuner' and 'dvb_vidtv_demod'. + * When this module is loaded, it will attempt to modprobe 'dvb_vidtv_tuner' + * and 'dvb_vidtv_demod'. * * Copyright (C) 2020 Daniel W. S. Almeida */ +#include <linux/dev_printk.h> #include <linux/moduleparam.h> #include <linux/mutex.h> #include <linux/platform_device.h> -#include <linux/dev_printk.h> #include <linux/time.h> #include <linux/types.h> #include <linux/workqueue.h> #include "vidtv_bridge.h" +#include "vidtv_common.h" #include "vidtv_demod.h" -#include "vidtv_tuner.h" -#include "vidtv_ts.h" #include "vidtv_mux.h" -#include "vidtv_common.h" +#include "vidtv_ts.h" +#include "vidtv_tuner.h" -//#define MUX_BUF_MAX_SZ -//#define MUX_BUF_MIN_SZ +#define MUX_BUF_MIN_SZ 90164 +#define MUX_BUF_MAX_SZ (MUX_BUF_MIN_SZ * 10) #define TUNER_DEFAULT_ADDR 0x68 #define DEMOD_DEFAULT_ADDR 0x60 +#define VIDTV_DEFAULT_NETWORK_ID 0xff44 +#define VIDTV_DEFAULT_NETWORK_NAME "LinuxTV.org" +#define VIDTV_DEFAULT_TS_ID 0x4081 -/* LNBf fake parameters: ranges used by an Universal (extended) European LNBf */ -#define LNB_CUT_FREQUENCY 11700000 -#define LNB_LOW_FREQ 9750000 -#define LNB_HIGH_FREQ 10600000 - +/* + * The LNBf fake parameters here are the ranges used by an + * Universal (extended) European LNBf, which is likely the most common LNBf + * found on Satellite digital TV system nowadays. + */ +#define LNB_CUT_FREQUENCY 11700000 /* high IF frequency */ +#define LNB_LOW_FREQ 9750000 /* low IF frequency */ +#define LNB_HIGH_FREQ 10600000 /* transition frequency */ static unsigned int drop_tslock_prob_on_low_snr; module_param(drop_tslock_prob_on_low_snr, uint, 0); @@ -92,7 +99,8 @@ MODULE_PARM_DESC(si_period_msec, "How often to send SI packets. Default: 40ms"); static unsigned int pcr_period_msec = 40; module_param(pcr_period_msec, uint, 0); -MODULE_PARM_DESC(pcr_period_msec, "How often to send PCR packets. Default: 40ms"); +MODULE_PARM_DESC(pcr_period_msec, + "How often to send PCR packets. Default: 40ms"); static unsigned int mux_rate_kbytes_sec = 4096; module_param(mux_rate_kbytes_sec, uint, 0); @@ -104,16 +112,14 @@ MODULE_PARM_DESC(pcr_pid, "PCR PID for all channels: defaults to 0x200"); static unsigned int mux_buf_sz_pkts; module_param(mux_buf_sz_pkts, uint, 0); -MODULE_PARM_DESC(mux_buf_sz_pkts, "Size for the internal mux buffer in multiples of 188 bytes"); - -#define MUX_BUF_MIN_SZ 90164 -#define MUX_BUF_MAX_SZ (MUX_BUF_MIN_SZ * 10) +MODULE_PARM_DESC(mux_buf_sz_pkts, + "Size for the internal mux buffer in multiples of 188 bytes"); static u32 vidtv_bridge_mux_buf_sz_for_mux_rate(void) { u32 max_elapsed_time_msecs = VIDTV_MAX_SLEEP_USECS / USEC_PER_MSEC; - u32 nbytes_expected; u32 mux_buf_sz = mux_buf_sz_pkts * TS_PACKET_LEN; + u32 nbytes_expected; nbytes_expected = mux_rate_kbytes_sec; nbytes_expected *= max_elapsed_time_msecs; @@ -143,14 +149,12 @@ static bool vidtv_bridge_check_demod_lock(struct vidtv_dvb *dvb, u32 n) FE_HAS_LOCK); } -static void -vidtv_bridge_on_new_pkts_avail(void *priv, u8 *buf, u32 npkts) +/* + * called on a separate thread by the mux when new packets become available + */ +static void vidtv_bridge_on_new_pkts_avail(void *priv, u8 *buf, u32 npkts) { - /* - * called on a separate thread by the mux when new packets become - * available - */ - struct vidtv_dvb *dvb = (struct vidtv_dvb *)priv; + struct vidtv_dvb *dvb = priv; /* drop packets if we lose the lock */ if (vidtv_bridge_check_demod_lock(dvb, 0)) @@ -159,7 +163,17 @@ vidtv_bridge_on_new_pkts_avail(void *priv, u8 *buf, u32 npkts) static int vidtv_start_streaming(struct vidtv_dvb *dvb) { - struct vidtv_mux_init_args mux_args = {0}; + struct vidtv_mux_init_args mux_args = { + .mux_rate_kbytes_sec = mux_rate_kbytes_sec, + .on_new_packets_available_cb = vidtv_bridge_on_new_pkts_avail, + .pcr_period_usecs = pcr_period_msec * USEC_PER_MSEC, + .si_period_usecs = si_period_msec * USEC_PER_MSEC, + .pcr_pid = pcr_pid, + .transport_stream_id = VIDTV_DEFAULT_TS_ID, + .network_id = VIDTV_DEFAULT_NETWORK_ID, + .network_name = VIDTV_DEFAULT_NETWORK_NAME, + .priv = dvb, + }; struct device *dev = &dvb->pdev->dev; u32 mux_buf_sz; @@ -168,19 +182,17 @@ static int vidtv_start_streaming(struct vidtv_dvb *dvb) return 0; } - mux_buf_sz = (mux_buf_sz_pkts) ? mux_buf_sz_pkts : vidtv_bridge_mux_buf_sz_for_mux_rate(); + if (mux_buf_sz_pkts) + mux_buf_sz = mux_buf_sz_pkts; + else + mux_buf_sz = vidtv_bridge_mux_buf_sz_for_mux_rate(); - mux_args.mux_rate_kbytes_sec = mux_rate_kbytes_sec; - mux_args.on_new_packets_available_cb = vidtv_bridge_on_new_pkts_avail; - mux_args.mux_buf_sz = mux_buf_sz; - mux_args.pcr_period_usecs = pcr_period_msec * 1000; - mux_args.si_period_usecs = si_period_msec * 1000; - mux_args.pcr_pid = pcr_pid; - mux_args.transport_stream_id = VIDTV_DEFAULT_TS_ID; - mux_args.priv = dvb; + mux_args.mux_buf_sz = mux_buf_sz; dvb->streaming = true; - dvb->mux = vidtv_mux_init(dvb->fe[0], dev, mux_args); + dvb->mux = vidtv_mux_init(dvb->fe[0], dev, &mux_args); + if (!dvb->mux) + return -ENOMEM; vidtv_mux_start_thread(dvb->mux); dev_dbg_ratelimited(dev, "Started streaming\n"); @@ -204,8 +216,8 @@ static int vidtv_start_feed(struct dvb_demux_feed *feed) { struct dvb_demux *demux = feed->demux; struct vidtv_dvb *dvb = demux->priv; - int rc; int ret; + int rc; if (!demux->dmx.frontend) return -EINVAL; @@ -243,9 +255,9 @@ static int vidtv_stop_feed(struct dvb_demux_feed *feed) static struct dvb_frontend *vidtv_get_frontend_ptr(struct i2c_client *c) { - /* the demod will set this when its probe function runs */ struct vidtv_demod_state *state = i2c_get_clientdata(c); + /* the demod will set this when its probe function runs */ return &state->frontend; } @@ -253,6 +265,11 @@ static int vidtv_master_xfer(struct i2c_adapter *i2c_adap, struct i2c_msg msgs[], int num) { + /* + * Right now, this virtual driver doesn't really send or receive + * messages from I2C. A real driver will require an implementation + * here. + */ return 0; } @@ -320,11 +337,10 @@ static int vidtv_bridge_dmxdev_init(struct vidtv_dvb *dvb) static int vidtv_bridge_probe_demod(struct vidtv_dvb *dvb, u32 n) { - struct vidtv_demod_config cfg = {}; - - cfg.drop_tslock_prob_on_low_snr = drop_tslock_prob_on_low_snr; - cfg.recover_tslock_prob_on_good_snr = recover_tslock_prob_on_good_snr; - + struct vidtv_demod_config cfg = { + .drop_tslock_prob_on_low_snr = drop_tslock_prob_on_low_snr, + .recover_tslock_prob_on_good_snr = recover_tslock_prob_on_good_snr, + }; dvb->i2c_client_demod[n] = dvb_module_probe("dvb_vidtv_demod", NULL, &dvb->i2c_adapter, @@ -343,14 +359,14 @@ static int vidtv_bridge_probe_demod(struct vidtv_dvb *dvb, u32 n) static int vidtv_bridge_probe_tuner(struct vidtv_dvb *dvb, u32 n) { - struct vidtv_tuner_config cfg = {}; + struct vidtv_tuner_config cfg = { + .fe = dvb->fe[n], + .mock_power_up_delay_msec = mock_power_up_delay_msec, + .mock_tune_delay_msec = mock_tune_delay_msec, + }; u32 freq; int i; - cfg.fe = dvb->fe[n]; - cfg.mock_power_up_delay_msec = mock_power_up_delay_msec; - cfg.mock_tune_delay_msec = mock_tune_delay_msec; - /* TODO: check if the frequencies are at a valid range */ memcpy(cfg.vidtv_valid_dvb_t_freqs, @@ -389,9 +405,7 @@ static int vidtv_bridge_probe_tuner(struct vidtv_dvb *dvb, u32 n) static int vidtv_bridge_dvb_init(struct vidtv_dvb *dvb) { - int ret; - int i; - int j; + int ret, i, j; ret = vidtv_bridge_i2c_register_adap(dvb); if (ret < 0) diff --git a/drivers/media/test-drivers/vidtv/vidtv_bridge.h b/drivers/media/test-drivers/vidtv/vidtv_bridge.h index 78fe8472fa37..2528adaee27d 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_bridge.h +++ b/drivers/media/test-drivers/vidtv/vidtv_bridge.h @@ -20,9 +20,11 @@ #include <linux/i2c.h> #include <linux/platform_device.h> #include <linux/types.h> + #include <media/dmxdev.h> #include <media/dvb_demux.h> #include <media/dvb_frontend.h> + #include "vidtv_mux.h" /** @@ -32,7 +34,7 @@ * @adapter: Represents a DTV adapter. See 'dvb_register_adapter'. * @demux: The demux used by the dvb_dmx_swfilter_packets() call. * @dmx_dev: Represents a demux device. - * @dmx_frontend: The frontends associated with the demux. + * @dmx_fe: The frontends associated with the demux. * @i2c_adapter: The i2c_adapter associated with the bridge driver. * @i2c_client_demod: The i2c_clients associated with the demodulator modules. * @i2c_client_tuner: The i2c_clients associated with the tuner modules. diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index f2b97cf08e87..7838e6272712 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -9,6 +9,7 @@ * When vidtv boots, it will create some hardcoded channels. * Their services will be concatenated to populate the SDT. * Their programs will be concatenated to populate the PAT + * Their events will be concatenated to populate the EIT * For each program in the PAT, a PMT section will be created * The PMT section for a channel will be assigned its streams. * Every stream will have its corresponding encoder polled to produce TS packets @@ -18,22 +19,22 @@ * Copyright (C) 2020 Daniel W. S. Almeida */ -#include <linux/types.h> -#include <linux/slab.h> #include <linux/dev_printk.h> #include <linux/ratelimit.h> +#include <linux/slab.h> +#include <linux/types.h> #include "vidtv_channel.h" -#include "vidtv_psi.h" +#include "vidtv_common.h" #include "vidtv_encoder.h" #include "vidtv_mux.h" -#include "vidtv_common.h" +#include "vidtv_psi.h" #include "vidtv_s302m.h" static void vidtv_channel_encoder_destroy(struct vidtv_encoder *e) { - struct vidtv_encoder *curr = e; struct vidtv_encoder *tmp = NULL; + struct vidtv_encoder *curr = e; while (curr) { /* forward the call to the derived type */ @@ -44,55 +45,88 @@ static void vidtv_channel_encoder_destroy(struct vidtv_encoder *e) } #define ENCODING_ISO8859_15 "\x0b" +#define TS_NIT_PID 0x10 +/* + * init an audio only channel with a s302m encoder + */ struct vidtv_channel *vidtv_channel_s302m_init(struct vidtv_channel *head, u16 transport_stream_id) { - /* - * init an audio only channel with a s302m encoder - */ - const u16 s302m_service_id = 0x880; - const u16 s302m_program_num = 0x880; - const u16 s302m_program_pid = 0x101; /* packet id for PMT*/ - const u16 s302m_es_pid = 0x111; /* packet id for the ES */ const __be32 s302m_fid = cpu_to_be32(VIDTV_S302M_FORMAT_IDENTIFIER); - - char *name = ENCODING_ISO8859_15 "Beethoven"; + char *event_text = ENCODING_ISO8859_15 "Bagatelle No. 25 in A minor for solo piano, also known as F\xfcr Elise, composed by Ludwig van Beethoven"; + char *event_name = ENCODING_ISO8859_15 "Ludwig van Beethoven: F\xfcr Elise"; + struct vidtv_s302m_encoder_init_args encoder_args = {}; + char *iso_language_code = ENCODING_ISO8859_15 "eng"; char *provider = ENCODING_ISO8859_15 "LinuxTV.org"; + char *name = ENCODING_ISO8859_15 "Beethoven"; + const u16 s302m_es_pid = 0x111; /* packet id for the ES */ + const u16 s302m_program_pid = 0x101; /* packet id for PMT*/ + const u16 s302m_service_id = 0x880; + const u16 s302m_program_num = 0x880; + const u16 s302m_beethoven_event_id = 1; + struct vidtv_channel *s302m; - struct vidtv_channel *s302m = kzalloc(sizeof(*s302m), GFP_KERNEL); - struct vidtv_s302m_encoder_init_args encoder_args = {}; + s302m = kzalloc(sizeof(*s302m), GFP_KERNEL); + if (!s302m) + return NULL; s302m->name = kstrdup(name, GFP_KERNEL); + if (!s302m->name) + goto free_s302m; - s302m->service = vidtv_psi_sdt_service_init(NULL, s302m_service_id); + s302m->service = vidtv_psi_sdt_service_init(NULL, s302m_service_id, false, true); + if (!s302m->service) + goto free_name; s302m->service->descriptor = (struct vidtv_psi_desc *) vidtv_psi_service_desc_init(NULL, - DIGITAL_TELEVISION_SERVICE, + DIGITAL_RADIO_SOUND_SERVICE, name, provider); + if (!s302m->service->descriptor) + goto free_service; s302m->transport_stream_id = transport_stream_id; s302m->program = vidtv_psi_pat_program_init(NULL, s302m_service_id, s302m_program_pid); + if (!s302m->program) + goto free_service; s302m->program_num = s302m_program_num; s302m->streams = vidtv_psi_pmt_stream_init(NULL, STREAM_PRIVATE_DATA, s302m_es_pid); + if (!s302m->streams) + goto free_program; s302m->streams->descriptor = (struct vidtv_psi_desc *) vidtv_psi_registration_desc_init(NULL, s302m_fid, NULL, 0); + if (!s302m->streams->descriptor) + goto free_streams; + encoder_args.es_pid = s302m_es_pid; s302m->encoders = vidtv_s302m_encoder_init(encoder_args); + if (!s302m->encoders) + goto free_streams; + + s302m->events = vidtv_psi_eit_event_init(NULL, s302m_beethoven_event_id); + if (!s302m->events) + goto free_encoders; + s302m->events->descriptor = (struct vidtv_psi_desc *) + vidtv_psi_short_event_desc_init(NULL, + iso_language_code, + event_name, + event_text); + if (!s302m->events->descriptor) + goto free_events; if (head) { while (head->next) @@ -102,6 +136,68 @@ struct vidtv_channel } return s302m; + +free_events: + vidtv_psi_eit_event_destroy(s302m->events); +free_encoders: + vidtv_s302m_encoder_destroy(s302m->encoders); +free_streams: + vidtv_psi_pmt_stream_destroy(s302m->streams); +free_program: + vidtv_psi_pat_program_destroy(s302m->program); +free_service: + vidtv_psi_sdt_service_destroy(s302m->service); +free_name: + kfree(s302m->name); +free_s302m: + kfree(s302m); + + return NULL; +} + +static struct vidtv_psi_table_eit_event +*vidtv_channel_eit_event_cat_into_new(struct vidtv_mux *m) +{ + /* Concatenate the events */ + const struct vidtv_channel *cur_chnl = m->channels; + struct vidtv_psi_table_eit_event *curr = NULL; + struct vidtv_psi_table_eit_event *head = NULL; + struct vidtv_psi_table_eit_event *tail = NULL; + struct vidtv_psi_desc *desc = NULL; + u16 event_id; + + if (!cur_chnl) + return NULL; + + while (cur_chnl) { + curr = cur_chnl->events; + + if (!curr) + dev_warn_ratelimited(m->dev, + "No events found for channel %s\n", + cur_chnl->name); + + while (curr) { + event_id = be16_to_cpu(curr->event_id); + tail = vidtv_psi_eit_event_init(tail, event_id); + if (!tail) { + vidtv_psi_eit_event_destroy(head); + return NULL; + } + + desc = vidtv_psi_desc_clone(curr->descriptor); + vidtv_psi_desc_assign(&tail->descriptor, desc); + + if (!head) + head = tail; + + curr = curr->next; + } + + cur_chnl = cur_chnl->next; + } + + return head; } static struct vidtv_psi_table_sdt_service @@ -125,13 +221,21 @@ static struct vidtv_psi_table_sdt_service if (!curr) dev_warn_ratelimited(m->dev, - "No services found for channel %s\n", cur_chnl->name); + "No services found for channel %s\n", + cur_chnl->name); while (curr) { service_id = be16_to_cpu(curr->service_id); - tail = vidtv_psi_sdt_service_init(tail, service_id); + tail = vidtv_psi_sdt_service_init(tail, + service_id, + curr->EIT_schedule, + curr->EIT_present_following); + if (!tail) + goto free; desc = vidtv_psi_desc_clone(curr->descriptor); + if (!desc) + goto free_tail; vidtv_psi_desc_assign(&tail->descriptor, desc); if (!head) @@ -144,6 +248,12 @@ static struct vidtv_psi_table_sdt_service } return head; + +free_tail: + vidtv_psi_sdt_service_destroy(tail); +free: + vidtv_psi_sdt_service_destroy(head); + return NULL; } static struct vidtv_psi_table_pat_program* @@ -174,6 +284,10 @@ vidtv_channel_pat_prog_cat_into_new(struct vidtv_mux *m) tail = vidtv_psi_pat_program_init(tail, serv_id, pid); + if (!tail) { + vidtv_psi_pat_program_destroy(head); + return NULL; + } if (!head) head = tail; @@ -183,30 +297,30 @@ vidtv_channel_pat_prog_cat_into_new(struct vidtv_mux *m) cur_chnl = cur_chnl->next; } + /* Add the NIT table */ + vidtv_psi_pat_program_init(tail, 0, TS_NIT_PID); return head; } +/* + * Match channels to their respective PMT sections, then assign the + * streams + */ static void vidtv_channel_pmt_match_sections(struct vidtv_channel *channels, struct vidtv_psi_table_pmt **sections, u32 nsections) { - /* - * Match channels to their respective PMT sections, then assign the - * streams - */ struct vidtv_psi_table_pmt *curr_section = NULL; - struct vidtv_channel *cur_chnl = channels; - - struct vidtv_psi_table_pmt_stream *s = NULL; struct vidtv_psi_table_pmt_stream *head = NULL; struct vidtv_psi_table_pmt_stream *tail = NULL; - + struct vidtv_psi_table_pmt_stream *s = NULL; + struct vidtv_channel *cur_chnl = channels; struct vidtv_psi_desc *desc = NULL; - u32 j; - u16 curr_id; u16 e_pid; /* elementary stream pid */ + u16 curr_id; + u32 j; while (cur_chnl) { for (j = 0; j < nsections; ++j) { @@ -232,7 +346,8 @@ vidtv_channel_pmt_match_sections(struct vidtv_channel *channels, head = tail; desc = vidtv_psi_desc_clone(s->descriptor); - vidtv_psi_desc_assign(&tail->descriptor, desc); + vidtv_psi_desc_assign(&tail->descriptor, + desc); s = s->next; } @@ -246,17 +361,103 @@ vidtv_channel_pmt_match_sections(struct vidtv_channel *channels, } } -void vidtv_channel_si_init(struct vidtv_mux *m) +static void +vidtv_channel_destroy_service_list(struct vidtv_psi_desc_service_list_entry *e) +{ + struct vidtv_psi_desc_service_list_entry *tmp; + + while (e) { + tmp = e; + e = e->next; + kfree(tmp); + } +} + +static struct vidtv_psi_desc_service_list_entry +*vidtv_channel_build_service_list(struct vidtv_psi_table_sdt_service *s) { + struct vidtv_psi_desc_service_list_entry *curr_e = NULL; + struct vidtv_psi_desc_service_list_entry *head_e = NULL; + struct vidtv_psi_desc_service_list_entry *prev_e = NULL; + struct vidtv_psi_desc *desc = s->descriptor; + struct vidtv_psi_desc_service *s_desc; + + while (s) { + while (desc) { + if (s->descriptor->type != SERVICE_DESCRIPTOR) + goto next_desc; + + s_desc = (struct vidtv_psi_desc_service *)desc; + + curr_e = kzalloc(sizeof(*curr_e), GFP_KERNEL); + if (!curr_e) { + vidtv_channel_destroy_service_list(head_e); + return NULL; + } + + curr_e->service_id = s->service_id; + curr_e->service_type = s_desc->service_type; + + if (!head_e) + head_e = curr_e; + if (prev_e) + prev_e->next = curr_e; + + prev_e = curr_e; + +next_desc: + desc = desc->next; + } + s = s->next; + } + return head_e; +} + +int vidtv_channel_si_init(struct vidtv_mux *m) +{ + struct vidtv_psi_desc_service_list_entry *service_list = NULL; struct vidtv_psi_table_pat_program *programs = NULL; struct vidtv_psi_table_sdt_service *services = NULL; + struct vidtv_psi_table_eit_event *events = NULL; m->si.pat = vidtv_psi_pat_table_init(m->transport_stream_id); + if (!m->si.pat) + return -ENOMEM; - m->si.sdt = vidtv_psi_sdt_table_init(m->transport_stream_id); + m->si.sdt = vidtv_psi_sdt_table_init(m->network_id, + m->transport_stream_id); + if (!m->si.sdt) + goto free_pat; programs = vidtv_channel_pat_prog_cat_into_new(m); + if (!programs) + goto free_sdt; services = vidtv_channel_sdt_serv_cat_into_new(m); + if (!services) + goto free_programs; + + events = vidtv_channel_eit_event_cat_into_new(m); + if (!events) + goto free_services; + + /* look for a service descriptor for every service */ + service_list = vidtv_channel_build_service_list(services); + if (!service_list) + goto free_events; + + /* use these descriptors to build the NIT */ + m->si.nit = vidtv_psi_nit_table_init(m->network_id, + m->transport_stream_id, + m->network_name, + service_list); + if (!m->si.nit) + goto free_service_list; + + m->si.eit = vidtv_psi_eit_table_init(m->network_id, + m->transport_stream_id, + programs->service_id); + if (!m->si.eit) + goto free_nit; /* assemble all programs and assign to PAT */ vidtv_psi_pat_program_assign(m->si.pat, programs); @@ -264,31 +465,65 @@ void vidtv_channel_si_init(struct vidtv_mux *m) /* assemble all services and assign to SDT */ vidtv_psi_sdt_service_assign(m->si.sdt, services); - m->si.pmt_secs = vidtv_psi_pmt_create_sec_for_each_pat_entry(m->si.pat, m->pcr_pid); + /* assemble all events and assign to EIT */ + vidtv_psi_eit_event_assign(m->si.eit, events); + + m->si.pmt_secs = vidtv_psi_pmt_create_sec_for_each_pat_entry(m->si.pat, + m->pcr_pid); + if (!m->si.pmt_secs) + goto free_eit; vidtv_channel_pmt_match_sections(m->channels, m->si.pmt_secs, - m->si.pat->programs); + m->si.pat->num_pmt); + + vidtv_channel_destroy_service_list(service_list); + + return 0; + +free_eit: + vidtv_psi_eit_table_destroy(m->si.eit); +free_nit: + vidtv_psi_nit_table_destroy(m->si.nit); +free_service_list: + vidtv_channel_destroy_service_list(service_list); +free_events: + vidtv_psi_eit_event_destroy(events); +free_services: + vidtv_psi_sdt_service_destroy(services); +free_programs: + vidtv_psi_pat_program_destroy(programs); +free_sdt: + vidtv_psi_sdt_table_destroy(m->si.sdt); +free_pat: + vidtv_psi_pat_table_destroy(m->si.pat); + return 0; } void vidtv_channel_si_destroy(struct vidtv_mux *m) { u32 i; - u16 num_programs = m->si.pat->programs; - vidtv_psi_pat_table_destroy(m->si.pat); - - for (i = 0; i < num_programs; ++i) + for (i = 0; i < m->si.pat->num_pmt; ++i) vidtv_psi_pmt_table_destroy(m->si.pmt_secs[i]); + vidtv_psi_pat_table_destroy(m->si.pat); + kfree(m->si.pmt_secs); vidtv_psi_sdt_table_destroy(m->si.sdt); + vidtv_psi_nit_table_destroy(m->si.nit); + vidtv_psi_eit_table_destroy(m->si.eit); } -void vidtv_channels_init(struct vidtv_mux *m) +int vidtv_channels_init(struct vidtv_mux *m) { /* this is the place to add new 'channels' for vidtv */ m->channels = vidtv_channel_s302m_init(NULL, m->transport_stream_id); + + if (!m->channels) + return -ENOMEM; + + return 0; } void vidtv_channels_destroy(struct vidtv_mux *m) @@ -302,6 +537,7 @@ void vidtv_channels_destroy(struct vidtv_mux *m) vidtv_psi_pat_program_destroy(curr->program); vidtv_psi_pmt_stream_destroy(curr->streams); vidtv_channel_encoder_destroy(curr->encoders); + vidtv_psi_eit_event_destroy(curr->events); tmp = curr; curr = curr->next; diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.h b/drivers/media/test-drivers/vidtv/vidtv_channel.h index 2c3cba4313b0..fff2e501d375 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.h +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.h @@ -9,6 +9,7 @@ * When vidtv boots, it will create some hardcoded channels. * Their services will be concatenated to populate the SDT. * Their programs will be concatenated to populate the PAT + * Their events will be concatenated to populate the EIT * For each program in the PAT, a PMT section will be created * The PMT section for a channel will be assigned its streams. * Every stream will have its corresponding encoder polled to produce TS packets @@ -22,9 +23,10 @@ #define VIDTV_CHANNEL_H #include <linux/types.h> -#include "vidtv_psi.h" + #include "vidtv_encoder.h" #include "vidtv_mux.h" +#include "vidtv_psi.h" /** * struct vidtv_channel - A 'channel' abstraction @@ -37,6 +39,7 @@ * Every stream will have its corresponding encoder polled to produce TS packets * These packets may be interleaved by the mux and then delivered to the bridge * + * @name: name of the channel * @transport_stream_id: a number to identify the TS, chosen at will. * @service: A _single_ service. Will be concatenated into the SDT. * @program_num: The link between PAT, PMT and SDT. @@ -44,6 +47,7 @@ * Will be concatenated into the PAT. * @streams: A stream loop used to populate the PMT section for 'program' * @encoders: A encoder loop. There must be one encoder for each stream. + * @events: Optional event information. This will feed into the EIT. * @next: Optionally chain this channel. */ struct vidtv_channel { @@ -54,6 +58,7 @@ struct vidtv_channel { struct vidtv_psi_table_pat_program *program; struct vidtv_psi_table_pmt_stream *streams; struct vidtv_encoder *encoders; + struct vidtv_psi_table_eit_event *events; struct vidtv_channel *next; }; @@ -61,14 +66,14 @@ struct vidtv_channel { * vidtv_channel_si_init - Init the PSI tables from the channels in the mux * @m: The mux containing the channels. */ -void vidtv_channel_si_init(struct vidtv_mux *m); +int vidtv_channel_si_init(struct vidtv_mux *m); void vidtv_channel_si_destroy(struct vidtv_mux *m); /** * vidtv_channels_init - Init hardcoded, fake 'channels'. * @m: The mux to store the channels into. */ -void vidtv_channels_init(struct vidtv_mux *m); +int vidtv_channels_init(struct vidtv_mux *m); struct vidtv_channel *vidtv_channel_s302m_init(struct vidtv_channel *head, u16 transport_stream_id); void vidtv_channels_destroy(struct vidtv_mux *m); diff --git a/drivers/media/test-drivers/vidtv/vidtv_common.h b/drivers/media/test-drivers/vidtv/vidtv_common.h index 818e7f2b9ec5..42f63fdee681 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_common.h +++ b/drivers/media/test-drivers/vidtv/vidtv_common.h @@ -16,7 +16,6 @@ #define CLOCK_UNIT_27MHZ 27000000 #define VIDTV_SLEEP_USECS 10000 #define VIDTV_MAX_SLEEP_USECS (2 * VIDTV_SLEEP_USECS) -#define VIDTV_DEFAULT_TS_ID 0x744 u32 vidtv_memcpy(void *to, size_t to_offset, diff --git a/drivers/media/test-drivers/vidtv/vidtv_demod.c b/drivers/media/test-drivers/vidtv/vidtv_demod.c index eba7fe1a1b48..b7823d97b30d 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_demod.c +++ b/drivers/media/test-drivers/vidtv/vidtv_demod.c @@ -19,6 +19,7 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/workqueue.h> + #include <media/dvb_frontend.h> #include "vidtv_demod.h" @@ -192,7 +193,6 @@ static void vidtv_demod_update_stats(struct dvb_frontend *fe) c->cnr.stat[0].svalue = state->tuner_cnr; c->cnr.stat[0].svalue -= prandom_u32_max(state->tuner_cnr / 50); - } static int vidtv_demod_read_status(struct dvb_frontend *fe, diff --git a/drivers/media/test-drivers/vidtv/vidtv_demod.h b/drivers/media/test-drivers/vidtv/vidtv_demod.h index 87651b0193e6..2b8404661348 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_demod.h +++ b/drivers/media/test-drivers/vidtv/vidtv_demod.h @@ -12,6 +12,7 @@ #define VIDTV_DEMOD_H #include <linux/dvb/frontend.h> + #include <media/dvb_frontend.h> /** @@ -19,6 +20,9 @@ * modulation and fec_inner * @modulation: see enum fe_modulation * @fec: see enum fe_fec_rate + * @cnr_ok: S/N threshold to consider the signal as OK. Below that, there's + * a chance of losing sync. + * @cnr_good: S/N threshold to consider the signal strong. * * This struct matches values for 'good' and 'ok' CNRs given the combination * of modulation and fec_inner in use. We might simulate some noise if the @@ -52,13 +56,8 @@ struct vidtv_demod_config { * struct vidtv_demod_state - The demodulator state * @frontend: The frontend structure allocated by the demod. * @config: The config used to init the demod. - * @poll_snr: The task responsible for periodically checking the simulated - * signal quality, eventually dropping or reacquiring the TS lock. * @status: the demod status. - * @cold_start: Whether the demod has not been init yet. - * @poll_snr_thread_running: Whether the task responsible for periodically - * checking the simulated signal quality is running. - * @poll_snr_thread_restart: Whether we should restart the poll_snr task. + * @tuner_cnr: current S/N ratio for the signal carrier */ struct vidtv_demod_state { struct dvb_frontend frontend; diff --git a/drivers/media/test-drivers/vidtv/vidtv_encoder.h b/drivers/media/test-drivers/vidtv/vidtv_encoder.h index 65d81daef4c3..50e3cf4eb4eb 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_encoder.h +++ b/drivers/media/test-drivers/vidtv/vidtv_encoder.h @@ -28,7 +28,7 @@ struct vidtv_access_unit { struct vidtv_access_unit *next; }; -/* Some musical notes, used by a tone generator */ +/* Some musical notes, used by a tone generator. Values are in Hz */ enum musical_notes { NOTE_SILENT = 0, @@ -103,14 +103,16 @@ enum musical_notes { * @encoder_buf_sz: The encoder buffer size, in bytes * @encoder_buf_offset: Our byte position in the encoder buffer. * @sample_count: How many samples we have encoded in total. + * @access_units: encoder payload units, used for clock references * @src_buf: The source of raw data to be encoded, encoder might set a * default if null. + * @src_buf_sz: size of @src_buf. * @src_buf_offset: Our position in the source buffer. * @is_video_encoder: Whether this a video encoder (as opposed to audio) * @ctx: Encoder-specific state. * @stream_id: Examples: Audio streams (0xc0-0xdf), Video streams * (0xe0-0xef). - * @es_id: The TS PID to use for the elementary stream in this encoder. + * @es_pid: The TS PID to use for the elementary stream in this encoder. * @encode: Prepare enough AUs for the given amount of time. * @clear: Clear the encoder output. * @sync: Attempt to synchronize with this encoder. @@ -131,9 +133,6 @@ struct vidtv_encoder { u32 encoder_buf_offset; u64 sample_count; - int last_duration; - int note_offset; - enum musical_notes last_tone; struct vidtv_access_unit *access_units; diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.c b/drivers/media/test-drivers/vidtv/vidtv_mux.c index 082740ae9d44..b51e6a3b8cbe 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.c +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.c @@ -12,23 +12,23 @@ * Copyright (C) 2020 Daniel W. S. Almeida */ -#include <linux/types.h> -#include <linux/slab.h> +#include <linux/delay.h> +#include <linux/dev_printk.h> #include <linux/jiffies.h> #include <linux/kernel.h> -#include <linux/dev_printk.h> +#include <linux/math64.h> #include <linux/ratelimit.h> -#include <linux/delay.h> +#include <linux/slab.h> +#include <linux/types.h> #include <linux/vmalloc.h> -#include <linux/math64.h> -#include "vidtv_mux.h" -#include "vidtv_ts.h" -#include "vidtv_pes.h" -#include "vidtv_encoder.h" #include "vidtv_channel.h" #include "vidtv_common.h" +#include "vidtv_encoder.h" +#include "vidtv_mux.h" +#include "vidtv_pes.h" #include "vidtv_psi.h" +#include "vidtv_ts.h" static struct vidtv_mux_pid_ctx *vidtv_mux_get_pid_ctx(struct vidtv_mux *m, u16 pid) @@ -47,33 +47,56 @@ static struct vidtv_mux_pid_ctx struct vidtv_mux_pid_ctx *ctx; ctx = vidtv_mux_get_pid_ctx(m, pid); - if (ctx) - goto end; + return ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return NULL; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); ctx->pid = pid; ctx->cc = 0; hash_add(m->pid_ctx, &ctx->h, pid); -end: return ctx; } -static void vidtv_mux_pid_ctx_init(struct vidtv_mux *m) +static void vidtv_mux_pid_ctx_destroy(struct vidtv_mux *m) +{ + struct vidtv_mux_pid_ctx *ctx; + struct hlist_node *tmp; + int bkt; + + hash_for_each_safe(m->pid_ctx, bkt, tmp, ctx, h) { + hash_del(&ctx->h); + kfree(ctx); + } +} + +static int vidtv_mux_pid_ctx_init(struct vidtv_mux *m) { struct vidtv_psi_table_pat_program *p = m->si.pat->program; u16 pid; hash_init(m->pid_ctx); /* push the pcr pid ctx */ - vidtv_mux_create_pid_ctx_once(m, m->pcr_pid); - /* push the null packet pid ctx */ - vidtv_mux_create_pid_ctx_once(m, TS_NULL_PACKET_PID); + if (!vidtv_mux_create_pid_ctx_once(m, m->pcr_pid)) + return -ENOMEM; + /* push the NULL packet pid ctx */ + if (!vidtv_mux_create_pid_ctx_once(m, TS_NULL_PACKET_PID)) + goto free; /* push the PAT pid ctx */ - vidtv_mux_create_pid_ctx_once(m, VIDTV_PAT_PID); + if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_PAT_PID)) + goto free; /* push the SDT pid ctx */ - vidtv_mux_create_pid_ctx_once(m, VIDTV_SDT_PID); + if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_SDT_PID)) + goto free; + /* push the NIT pid ctx */ + if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_NIT_PID)) + goto free; + /* push the EIT pid ctx */ + if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_EIT_PID)) + goto free; /* add a ctx for all PMT sections */ while (p) { @@ -81,18 +104,12 @@ static void vidtv_mux_pid_ctx_init(struct vidtv_mux *m) vidtv_mux_create_pid_ctx_once(m, pid); p = p->next; } -} -static void vidtv_mux_pid_ctx_destroy(struct vidtv_mux *m) -{ - int bkt; - struct vidtv_mux_pid_ctx *ctx; - struct hlist_node *tmp; + return 0; - hash_for_each_safe(m->pid_ctx, bkt, tmp, ctx, h) { - hash_del(&ctx->h); - kfree(ctx); - } +free: + vidtv_mux_pid_ctx_destroy(m); + return -ENOMEM; } static void vidtv_mux_update_clk(struct vidtv_mux *m) @@ -112,32 +129,53 @@ static void vidtv_mux_update_clk(struct vidtv_mux *m) static u32 vidtv_mux_push_si(struct vidtv_mux *m) { + struct vidtv_psi_pat_write_args pat_args = { + .buf = m->mux_buf, + .buf_sz = m->mux_buf_sz, + .pat = m->si.pat, + }; + struct vidtv_psi_pmt_write_args pmt_args = { + .buf = m->mux_buf, + .buf_sz = m->mux_buf_sz, + .pcr_pid = m->pcr_pid, + }; + struct vidtv_psi_sdt_write_args sdt_args = { + .buf = m->mux_buf, + .buf_sz = m->mux_buf_sz, + .sdt = m->si.sdt, + }; + struct vidtv_psi_nit_write_args nit_args = { + .buf = m->mux_buf, + .buf_sz = m->mux_buf_sz, + .nit = m->si.nit, + + }; + struct vidtv_psi_eit_write_args eit_args = { + .buf = m->mux_buf, + .buf_sz = m->mux_buf_sz, + .eit = m->si.eit, + }; u32 initial_offset = m->mux_buf_offset; - struct vidtv_mux_pid_ctx *pat_ctx; struct vidtv_mux_pid_ctx *pmt_ctx; struct vidtv_mux_pid_ctx *sdt_ctx; - - struct vidtv_psi_pat_write_args pat_args = {}; - struct vidtv_psi_pmt_write_args pmt_args = {}; - struct vidtv_psi_sdt_write_args sdt_args = {}; - - u32 nbytes; /* the number of bytes written by this function */ + struct vidtv_mux_pid_ctx *nit_ctx; + struct vidtv_mux_pid_ctx *eit_ctx; + u32 nbytes; u16 pmt_pid; u32 i; pat_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_PAT_PID); sdt_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_SDT_PID); + nit_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_NIT_PID); + eit_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_EIT_PID); - pat_args.buf = m->mux_buf; pat_args.offset = m->mux_buf_offset; - pat_args.pat = m->si.pat; - pat_args.buf_sz = m->mux_buf_sz; pat_args.continuity_counter = &pat_ctx->cc; - m->mux_buf_offset += vidtv_psi_pat_write_into(pat_args); + m->mux_buf_offset += vidtv_psi_pat_write_into(&pat_args); - for (i = 0; i < m->si.pat->programs; ++i) { + for (i = 0; i < m->si.pat->num_pmt; ++i) { pmt_pid = vidtv_psi_pmt_get_pid(m->si.pmt_secs[i], m->si.pat); @@ -149,25 +187,29 @@ static u32 vidtv_mux_push_si(struct vidtv_mux *m) pmt_ctx = vidtv_mux_get_pid_ctx(m, pmt_pid); - pmt_args.buf = m->mux_buf; pmt_args.offset = m->mux_buf_offset; pmt_args.pmt = m->si.pmt_secs[i]; pmt_args.pid = pmt_pid; - pmt_args.buf_sz = m->mux_buf_sz; pmt_args.continuity_counter = &pmt_ctx->cc; - pmt_args.pcr_pid = m->pcr_pid; /* write each section into buffer */ - m->mux_buf_offset += vidtv_psi_pmt_write_into(pmt_args); + m->mux_buf_offset += vidtv_psi_pmt_write_into(&pmt_args); } - sdt_args.buf = m->mux_buf; sdt_args.offset = m->mux_buf_offset; - sdt_args.sdt = m->si.sdt; - sdt_args.buf_sz = m->mux_buf_sz; sdt_args.continuity_counter = &sdt_ctx->cc; - m->mux_buf_offset += vidtv_psi_sdt_write_into(sdt_args); + m->mux_buf_offset += vidtv_psi_sdt_write_into(&sdt_args); + + nit_args.offset = m->mux_buf_offset; + nit_args.continuity_counter = &nit_ctx->cc; + + m->mux_buf_offset += vidtv_psi_nit_write_into(&nit_args); + + eit_args.offset = m->mux_buf_offset; + eit_args.continuity_counter = &eit_ctx->cc; + + m->mux_buf_offset += vidtv_psi_eit_write_into(&eit_args); nbytes = m->mux_buf_offset - initial_offset; @@ -230,23 +272,29 @@ static bool vidtv_mux_should_push_si(struct vidtv_mux *m) static u32 vidtv_mux_packetize_access_units(struct vidtv_mux *m, struct vidtv_encoder *e) { - u32 nbytes = 0; - - struct pes_write_args args = {}; - u32 initial_offset = m->mux_buf_offset; + struct pes_write_args args = { + .dest_buf = m->mux_buf, + .dest_buf_sz = m->mux_buf_sz, + .pid = be16_to_cpu(e->es_pid), + .encoder_id = e->id, + .stream_id = be16_to_cpu(e->stream_id), + .send_pts = true, /* forbidden value '01'... */ + .send_dts = false, /* ...for PTS_DTS flags */ + }; struct vidtv_access_unit *au = e->access_units; - + u32 initial_offset = m->mux_buf_offset; + struct vidtv_mux_pid_ctx *pid_ctx; + u32 nbytes = 0; u8 *buf = NULL; - struct vidtv_mux_pid_ctx *pid_ctx = vidtv_mux_create_pid_ctx_once(m, - be16_to_cpu(e->es_pid)); - args.dest_buf = m->mux_buf; - args.dest_buf_sz = m->mux_buf_sz; - args.pid = be16_to_cpu(e->es_pid); - args.encoder_id = e->id; + /* see SMPTE 302M clause 6.4 */ + if (args.encoder_id == S302M) { + args.send_dts = false; + args.send_pts = true; + } + + pid_ctx = vidtv_mux_create_pid_ctx_once(m, be16_to_cpu(e->es_pid)); args.continuity_counter = &pid_ctx->cc; - args.stream_id = be16_to_cpu(e->stream_id); - args.send_pts = true; while (au) { buf = e->encoder_buf + au->offset; @@ -256,7 +304,7 @@ static u32 vidtv_mux_packetize_access_units(struct vidtv_mux *m, args.pts = au->pts; args.pcr = m->timing.clk; - m->mux_buf_offset += vidtv_pes_write_into(args); + m->mux_buf_offset += vidtv_pes_write_into(&args); au = au->next; } @@ -273,10 +321,10 @@ static u32 vidtv_mux_packetize_access_units(struct vidtv_mux *m, static u32 vidtv_mux_poll_encoders(struct vidtv_mux *m) { - u32 nbytes = 0; - u32 au_nbytes; struct vidtv_channel *cur_chnl = m->channels; struct vidtv_encoder *e = NULL; + u32 nbytes = 0; + u32 au_nbytes; while (cur_chnl) { e = cur_chnl->encoders; @@ -300,18 +348,19 @@ static u32 vidtv_mux_poll_encoders(struct vidtv_mux *m) static u32 vidtv_mux_pad_with_nulls(struct vidtv_mux *m, u32 npkts) { - struct null_packet_write_args args = {}; + struct null_packet_write_args args = { + .dest_buf = m->mux_buf, + .buf_sz = m->mux_buf_sz, + .dest_offset = m->mux_buf_offset, + }; u32 initial_offset = m->mux_buf_offset; - u32 nbytes; /* the number of bytes written by this function */ - u32 i; struct vidtv_mux_pid_ctx *ctx; + u32 nbytes; + u32 i; ctx = vidtv_mux_get_pid_ctx(m, TS_NULL_PACKET_PID); - args.dest_buf = m->mux_buf; - args.buf_sz = m->mux_buf_sz; args.continuity_counter = &ctx->cc; - args.dest_offset = m->mux_buf_offset; for (i = 0; i < npkts; ++i) { m->mux_buf_offset += vidtv_ts_null_write_into(args); @@ -343,9 +392,9 @@ static void vidtv_mux_tick(struct work_struct *work) struct vidtv_mux, mpeg_thread); struct dtv_frontend_properties *c = &m->fe->dtv_property_cache; + u32 tot_bits = 0; u32 nbytes; u32 npkts; - u32 tot_bits = 0; while (m->streaming) { nbytes = 0; @@ -427,40 +476,62 @@ void vidtv_mux_stop_thread(struct vidtv_mux *m) struct vidtv_mux *vidtv_mux_init(struct dvb_frontend *fe, struct device *dev, - struct vidtv_mux_init_args args) + struct vidtv_mux_init_args *args) { - struct vidtv_mux *m = kzalloc(sizeof(*m), GFP_KERNEL); + struct vidtv_mux *m; + + m = kzalloc(sizeof(*m), GFP_KERNEL); + if (!m) + return NULL; m->dev = dev; m->fe = fe; - m->timing.pcr_period_usecs = args.pcr_period_usecs; - m->timing.si_period_usecs = args.si_period_usecs; + m->timing.pcr_period_usecs = args->pcr_period_usecs; + m->timing.si_period_usecs = args->si_period_usecs; + + m->mux_rate_kbytes_sec = args->mux_rate_kbytes_sec; - m->mux_rate_kbytes_sec = args.mux_rate_kbytes_sec; + m->on_new_packets_available_cb = args->on_new_packets_available_cb; - m->on_new_packets_available_cb = args.on_new_packets_available_cb; + m->mux_buf = vzalloc(args->mux_buf_sz); + if (!m->mux_buf) + goto free_mux; - m->mux_buf = vzalloc(args.mux_buf_sz); - m->mux_buf_sz = args.mux_buf_sz; + m->mux_buf_sz = args->mux_buf_sz; - m->pcr_pid = args.pcr_pid; - m->transport_stream_id = args.transport_stream_id; - m->priv = args.priv; + m->pcr_pid = args->pcr_pid; + m->transport_stream_id = args->transport_stream_id; + m->priv = args->priv; + m->network_id = args->network_id; + m->network_name = kstrdup(args->network_name, GFP_KERNEL); m->timing.current_jiffies = get_jiffies_64(); - if (args.channels) - m->channels = args.channels; + if (args->channels) + m->channels = args->channels; else - vidtv_channels_init(m); + if (vidtv_channels_init(m) < 0) + goto free_mux_buf; /* will alloc data for pmt_sections after initializing pat */ - vidtv_channel_si_init(m); + if (vidtv_channel_si_init(m) < 0) + goto free_channels; INIT_WORK(&m->mpeg_thread, vidtv_mux_tick); - vidtv_mux_pid_ctx_init(m); + if (vidtv_mux_pid_ctx_init(m) < 0) + goto free_channel_si; return m; + +free_channel_si: + vidtv_channel_si_destroy(m); +free_channels: + vidtv_channels_destroy(m); +free_mux_buf: + vfree(m->mux_buf); +free_mux: + kfree(m); + return NULL; } void vidtv_mux_destroy(struct vidtv_mux *m) @@ -469,6 +540,7 @@ void vidtv_mux_destroy(struct vidtv_mux *m) vidtv_mux_pid_ctx_destroy(m); vidtv_channel_si_destroy(m); vidtv_channels_destroy(m); + kfree(m->network_name); vfree(m->mux_buf); kfree(m); } diff --git a/drivers/media/test-drivers/vidtv/vidtv_mux.h b/drivers/media/test-drivers/vidtv/vidtv_mux.h index 2caa60623e97..ad82eb72b841 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_mux.h +++ b/drivers/media/test-drivers/vidtv/vidtv_mux.h @@ -15,9 +15,10 @@ #ifndef VIDTV_MUX_H #define VIDTV_MUX_H -#include <linux/types.h> #include <linux/hashtable.h> +#include <linux/types.h> #include <linux/workqueue.h> + #include <media/dvb_frontend.h> #include "vidtv_psi.h" @@ -58,12 +59,16 @@ struct vidtv_mux_timing { * @pat: The PAT in use by the muxer. * @pmt_secs: The PMT sections in use by the muxer. One for each program in the PAT. * @sdt: The SDT in use by the muxer. + * @nit: The NIT in use by the muxer. + * @eit: the EIT in use by the muxer. */ struct vidtv_mux_si { /* the SI tables */ struct vidtv_psi_table_pat *pat; struct vidtv_psi_table_pmt **pmt_secs; /* the PMT sections */ struct vidtv_psi_table_sdt *sdt; + struct vidtv_psi_table_nit *nit; + struct vidtv_psi_table_eit *eit; }; /** @@ -82,8 +87,10 @@ struct vidtv_mux_pid_ctx { /** * struct vidtv_mux - A muxer abstraction loosely based in libavcodec/mpegtsenc.c - * @mux_rate_kbytes_sec: The bit rate for the TS, in kbytes. + * @fe: The frontend structure allocated by the muxer. + * @dev: pointer to struct device. * @timing: Keeps track of timing related information. + * @mux_rate_kbytes_sec: The bit rate for the TS, in kbytes. * @pid_ctx: A hash table to keep track of per-PID metadata. * @on_new_packets_available_cb: A callback to inform of new TS packets ready. * @mux_buf: A pointer to a buffer for this muxer. TS packets are stored there @@ -99,6 +106,8 @@ struct vidtv_mux_pid_ctx { * @pcr_pid: The TS PID used for the PSI packets. All channels will share the * same PCR. * @transport_stream_id: The transport stream ID + * @network_id: The network ID + * @network_name: The network name * @priv: Private data. */ struct vidtv_mux { @@ -128,6 +137,8 @@ struct vidtv_mux { u16 pcr_pid; u16 transport_stream_id; + u16 network_id; + char *network_name; void *priv; }; @@ -142,6 +153,8 @@ struct vidtv_mux { * same PCR. * @transport_stream_id: The transport stream ID * @channels: an optional list of channels to use + * @network_id: The network ID + * @network_name: The network name * @priv: Private data. */ struct vidtv_mux_init_args { @@ -153,12 +166,14 @@ struct vidtv_mux_init_args { u16 pcr_pid; u16 transport_stream_id; struct vidtv_channel *channels; + u16 network_id; + char *network_name; void *priv; }; struct vidtv_mux *vidtv_mux_init(struct dvb_frontend *fe, struct device *dev, - struct vidtv_mux_init_args args); + struct vidtv_mux_init_args *args); void vidtv_mux_destroy(struct vidtv_mux *m); void vidtv_mux_start_thread(struct vidtv_mux *m); diff --git a/drivers/media/test-drivers/vidtv/vidtv_pes.c b/drivers/media/test-drivers/vidtv/vidtv_pes.c index 1c75f88070e9..782e5e7fbb02 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_pes.c +++ b/drivers/media/test-drivers/vidtv/vidtv_pes.c @@ -16,7 +16,6 @@ #include <linux/types.h> #include <linux/printk.h> #include <linux/ratelimit.h> -#include <asm/byteorder.h> #include "vidtv_pes.h" #include "vidtv_common.h" @@ -57,7 +56,7 @@ static u32 vidtv_pes_h_get_len(bool send_pts, bool send_dts) return len; } -static u32 vidtv_pes_write_header_stuffing(struct pes_header_write_args args) +static u32 vidtv_pes_write_header_stuffing(struct pes_header_write_args *args) { /* * This is a fixed 8-bit value equal to '0xFF' that can be inserted @@ -65,20 +64,20 @@ static u32 vidtv_pes_write_header_stuffing(struct pes_header_write_args args) * It is discarded by the decoder. No more than 32 stuffing bytes shall * be present in one PES packet header. */ - if (args.n_pes_h_s_bytes > PES_HEADER_MAX_STUFFING_BYTES) { + if (args->n_pes_h_s_bytes > PES_HEADER_MAX_STUFFING_BYTES) { pr_warn_ratelimited("More than %d stuffing bytes in PES packet header\n", PES_HEADER_MAX_STUFFING_BYTES); - args.n_pes_h_s_bytes = PES_HEADER_MAX_STUFFING_BYTES; + args->n_pes_h_s_bytes = PES_HEADER_MAX_STUFFING_BYTES; } - return vidtv_memset(args.dest_buf, - args.dest_offset, - args.dest_buf_sz, + return vidtv_memset(args->dest_buf, + args->dest_offset, + args->dest_buf_sz, TS_FILL_BYTE, - args.n_pes_h_s_bytes); + args->n_pes_h_s_bytes); } -static u32 vidtv_pes_write_pts_dts(struct pes_header_write_args args) +static u32 vidtv_pes_write_pts_dts(struct pes_header_write_args *args) { u32 nbytes = 0; /* the number of bytes written by this function */ @@ -90,7 +89,7 @@ static u32 vidtv_pes_write_pts_dts(struct pes_header_write_args args) u64 mask2; u64 mask3; - if (!args.send_pts && args.send_dts) + if (!args->send_pts && args->send_dts) return 0; mask1 = GENMASK_ULL(32, 30); @@ -98,80 +97,81 @@ static u32 vidtv_pes_write_pts_dts(struct pes_header_write_args args) mask3 = GENMASK_ULL(14, 0); /* see ISO/IEC 13818-1 : 2000 p. 32 */ - if (args.send_pts && args.send_dts) { - pts_dts.pts1 = (0x3 << 4) | ((args.pts & mask1) >> 29) | 0x1; - pts_dts.pts2 = cpu_to_be16(((args.pts & mask2) >> 14) | 0x1); - pts_dts.pts3 = cpu_to_be16(((args.pts & mask3) << 1) | 0x1); + if (args->send_pts && args->send_dts) { + pts_dts.pts1 = (0x3 << 4) | ((args->pts & mask1) >> 29) | 0x1; + pts_dts.pts2 = cpu_to_be16(((args->pts & mask2) >> 14) | 0x1); + pts_dts.pts3 = cpu_to_be16(((args->pts & mask3) << 1) | 0x1); - pts_dts.dts1 = (0x1 << 4) | ((args.dts & mask1) >> 29) | 0x1; - pts_dts.dts2 = cpu_to_be16(((args.dts & mask2) >> 14) | 0x1); - pts_dts.dts3 = cpu_to_be16(((args.dts & mask3) << 1) | 0x1); + pts_dts.dts1 = (0x1 << 4) | ((args->dts & mask1) >> 29) | 0x1; + pts_dts.dts2 = cpu_to_be16(((args->dts & mask2) >> 14) | 0x1); + pts_dts.dts3 = cpu_to_be16(((args->dts & mask3) << 1) | 0x1); op = &pts_dts; op_sz = sizeof(pts_dts); - } else if (args.send_pts) { - pts.pts1 = (0x1 << 5) | ((args.pts & mask1) >> 29) | 0x1; - pts.pts2 = cpu_to_be16(((args.pts & mask2) >> 14) | 0x1); - pts.pts3 = cpu_to_be16(((args.pts & mask3) << 1) | 0x1); + } else if (args->send_pts) { + pts.pts1 = (0x1 << 5) | ((args->pts & mask1) >> 29) | 0x1; + pts.pts2 = cpu_to_be16(((args->pts & mask2) >> 14) | 0x1); + pts.pts3 = cpu_to_be16(((args->pts & mask3) << 1) | 0x1); op = &pts; op_sz = sizeof(pts); } /* copy PTS/DTS optional */ - nbytes += vidtv_memcpy(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + nbytes += vidtv_memcpy(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, op, op_sz); return nbytes; } -static u32 vidtv_pes_write_h(struct pes_header_write_args args) +static u32 vidtv_pes_write_h(struct pes_header_write_args *args) { u32 nbytes = 0; /* the number of bytes written by this function */ struct vidtv_mpeg_pes pes_header = {}; struct vidtv_pes_optional pes_optional = {}; - struct pes_header_write_args pts_dts_args = args; - u32 stream_id = (args.encoder_id == S302M) ? PRIVATE_STREAM_1_ID : args.stream_id; + struct pes_header_write_args pts_dts_args; + u32 stream_id = (args->encoder_id == S302M) ? PRIVATE_STREAM_1_ID : args->stream_id; u16 pes_opt_bitfield = 0x01 << 15; pes_header.bitfield = cpu_to_be32((PES_START_CODE_PREFIX << 8) | stream_id); - pes_header.length = cpu_to_be16(vidtv_pes_op_get_len(args.send_pts, - args.send_dts) + - args.access_unit_len); + pes_header.length = cpu_to_be16(vidtv_pes_op_get_len(args->send_pts, + args->send_dts) + + args->access_unit_len); - if (args.send_pts && args.send_dts) + if (args->send_pts && args->send_dts) pes_opt_bitfield |= (0x3 << 6); - else if (args.send_pts) + else if (args->send_pts) pes_opt_bitfield |= (0x1 << 7); pes_optional.bitfield = cpu_to_be16(pes_opt_bitfield); - pes_optional.length = vidtv_pes_op_get_len(args.send_pts, args.send_dts) + - args.n_pes_h_s_bytes - + pes_optional.length = vidtv_pes_op_get_len(args->send_pts, args->send_dts) + + args->n_pes_h_s_bytes - sizeof(struct vidtv_pes_optional); /* copy header */ - nbytes += vidtv_memcpy(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + nbytes += vidtv_memcpy(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, &pes_header, sizeof(pes_header)); /* copy optional header bits */ - nbytes += vidtv_memcpy(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + nbytes += vidtv_memcpy(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, &pes_optional, sizeof(pes_optional)); /* copy the timing information */ - pts_dts_args.dest_offset = args.dest_offset + nbytes; - nbytes += vidtv_pes_write_pts_dts(pts_dts_args); + pts_dts_args = *args; + pts_dts_args.dest_offset = args->dest_offset + nbytes; + nbytes += vidtv_pes_write_pts_dts(&pts_dts_args); /* write any PES header stuffing */ nbytes += vidtv_pes_write_header_stuffing(args); @@ -300,14 +300,31 @@ static u32 vidtv_pes_write_ts_h(struct pes_ts_header_write_args args, return nbytes; } -u32 vidtv_pes_write_into(struct pes_write_args args) +u32 vidtv_pes_write_into(struct pes_write_args *args) { - u32 unaligned_bytes = (args.dest_offset % TS_PACKET_LEN); - struct pes_ts_header_write_args ts_header_args = {}; - struct pes_header_write_args pes_header_args = {}; - u32 remaining_len = args.access_unit_len; + u32 unaligned_bytes = (args->dest_offset % TS_PACKET_LEN); + struct pes_ts_header_write_args ts_header_args = { + .dest_buf = args->dest_buf, + .dest_buf_sz = args->dest_buf_sz, + .pid = args->pid, + .pcr = args->pcr, + .continuity_counter = args->continuity_counter, + }; + struct pes_header_write_args pes_header_args = { + .dest_buf = args->dest_buf, + .dest_buf_sz = args->dest_buf_sz, + .encoder_id = args->encoder_id, + .send_pts = args->send_pts, + .pts = args->pts, + .send_dts = args->send_dts, + .dts = args->dts, + .stream_id = args->stream_id, + .n_pes_h_s_bytes = args->n_pes_h_s_bytes, + .access_unit_len = args->access_unit_len, + }; + u32 remaining_len = args->access_unit_len; bool wrote_pes_header = false; - u64 last_pcr = args.pcr; + u64 last_pcr = args->pcr; bool need_pcr = true; u32 available_space; u32 payload_size; @@ -318,25 +335,13 @@ u32 vidtv_pes_write_into(struct pes_write_args args) pr_warn_ratelimited("buffer is misaligned, while starting PES\n"); /* forcibly align and hope for the best */ - nbytes += vidtv_memset(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + nbytes += vidtv_memset(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, TS_FILL_BYTE, TS_PACKET_LEN - unaligned_bytes); } - if (args.send_dts && !args.send_pts) { - pr_warn_ratelimited("forbidden value '01' for PTS_DTS flags\n"); - args.send_pts = true; - args.pts = args.dts; - } - - /* see SMPTE 302M clause 6.4 */ - if (args.encoder_id == S302M) { - args.send_dts = false; - args.send_pts = true; - } - while (remaining_len) { available_space = TS_PAYLOAD_LEN; /* @@ -345,14 +350,14 @@ u32 vidtv_pes_write_into(struct pes_write_args args) * the space needed for the TS header _and_ for the PES header */ if (!wrote_pes_header) - available_space -= vidtv_pes_h_get_len(args.send_pts, - args.send_dts); + available_space -= vidtv_pes_h_get_len(args->send_pts, + args->send_dts); /* * if the encoder has inserted stuffing bytes in the PES * header, account for them. */ - available_space -= args.n_pes_h_s_bytes; + available_space -= args->n_pes_h_s_bytes; /* Take the extra adaptation into account if need to send PCR */ if (need_pcr) { @@ -387,14 +392,9 @@ u32 vidtv_pes_write_into(struct pes_write_args args) } /* write ts header */ - ts_header_args.dest_buf = args.dest_buf; - ts_header_args.dest_offset = args.dest_offset + nbytes; - ts_header_args.dest_buf_sz = args.dest_buf_sz; - ts_header_args.pid = args.pid; - ts_header_args.pcr = args.pcr; - ts_header_args.continuity_counter = args.continuity_counter; - ts_header_args.wrote_pes_header = wrote_pes_header; - ts_header_args.n_stuffing_bytes = stuff_bytes; + ts_header_args.dest_offset = args->dest_offset + nbytes; + ts_header_args.wrote_pes_header = wrote_pes_header; + ts_header_args.n_stuffing_bytes = stuff_bytes; nbytes += vidtv_pes_write_ts_h(ts_header_args, need_pcr, &last_pcr); @@ -403,33 +403,20 @@ u32 vidtv_pes_write_into(struct pes_write_args args) if (!wrote_pes_header) { /* write the PES header only once */ - pes_header_args.dest_buf = args.dest_buf; - - pes_header_args.dest_offset = args.dest_offset + - nbytes; - - pes_header_args.dest_buf_sz = args.dest_buf_sz; - pes_header_args.encoder_id = args.encoder_id; - pes_header_args.send_pts = args.send_pts; - pes_header_args.pts = args.pts; - pes_header_args.send_dts = args.send_dts; - pes_header_args.dts = args.dts; - pes_header_args.stream_id = args.stream_id; - pes_header_args.n_pes_h_s_bytes = args.n_pes_h_s_bytes; - pes_header_args.access_unit_len = args.access_unit_len; - - nbytes += vidtv_pes_write_h(pes_header_args); - wrote_pes_header = true; + pes_header_args.dest_offset = args->dest_offset + + nbytes; + nbytes += vidtv_pes_write_h(&pes_header_args); + wrote_pes_header = true; } /* write as much of the payload as we possibly can */ - nbytes += vidtv_memcpy(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, - args.from, + nbytes += vidtv_memcpy(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, + args->from, payload_size); - args.from += payload_size; + args->from += payload_size; remaining_len -= payload_size; } diff --git a/drivers/media/test-drivers/vidtv/vidtv_pes.h b/drivers/media/test-drivers/vidtv/vidtv_pes.h index 0ea9e863024d..963c59155e72 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_pes.h +++ b/drivers/media/test-drivers/vidtv/vidtv_pes.h @@ -14,7 +14,6 @@ #ifndef VIDTV_PES_H #define VIDTV_PES_H -#include <asm/byteorder.h> #include <linux/types.h> #include "vidtv_common.h" @@ -114,8 +113,10 @@ struct pes_header_write_args { * @dest_buf_sz: The size of the dest_buffer * @pid: The PID to use for the TS packets. * @continuity_counter: Incremented on every new TS packet. - * @n_pes_h_s_bytes: Padding bytes. Might be used by an encoder if needed, gets + * @wrote_pes_header: Flag to indicate that the PES header was written + * @n_stuffing_bytes: Padding bytes. Might be used by an encoder if needed, gets * discarded by the decoder. + * @pcr: counter driven by a 27Mhz clock. */ struct pes_ts_header_write_args { void *dest_buf; @@ -146,6 +147,7 @@ struct pes_ts_header_write_args { * @dts: DTS value to send. * @n_pes_h_s_bytes: Padding bytes. Might be used by an encoder if needed, gets * discarded by the decoder. + * @pcr: counter driven by a 27Mhz clock. */ struct pes_write_args { void *dest_buf; @@ -186,6 +188,6 @@ struct pes_write_args { * equal to the size of the access unit, since we need space for PES headers, TS headers * and padding bytes, if any. */ -u32 vidtv_pes_write_into(struct pes_write_args args); +u32 vidtv_pes_write_into(struct pes_write_args *args); #endif // VIDTV_PES_H diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.c b/drivers/media/test-drivers/vidtv/vidtv_psi.c index 82cf67dd27c0..4511a2a98405 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.c +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.c @@ -6,31 +6,31 @@ * technically be broken into one or more sections, we do not do this here, * hence 'table' and 'section' are interchangeable for vidtv. * - * This code currently supports three tables: PAT, PMT and SDT. These are the - * bare minimum to get userspace to recognize our MPEG transport stream. It can - * be extended to support more PSI tables in the future. - * * Copyright (C) 2020 Daniel W. S. Almeida */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s, %d: " fmt, __func__, __LINE__ -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/slab.h> +#include <linux/bcd.h> #include <linux/crc32.h> -#include <linux/string.h> +#include <linux/kernel.h> +#include <linux/ktime.h> #include <linux/printk.h> #include <linux/ratelimit.h> +#include <linux/slab.h> #include <linux/string.h> -#include <asm/byteorder.h> +#include <linux/string.h> +#include <linux/time.h> +#include <linux/types.h> -#include "vidtv_psi.h" #include "vidtv_common.h" +#include "vidtv_psi.h" #include "vidtv_ts.h" #define CRC_SIZE_IN_BYTES 4 #define MAX_VERSION_NUM 32 +#define INITIAL_CRC 0xffffffff +#define ISO_LANGUAGE_CODE_LEN 3 static const u32 CRC_LUT[256] = { /* from libdvbv5 */ @@ -79,7 +79,7 @@ static const u32 CRC_LUT[256] = { 0xbcb4666d, 0xb8757bda, 0xb5365d03, 0xb1f740b4 }; -static inline u32 dvb_crc32(u32 crc, u8 *data, u32 len) +static u32 dvb_crc32(u32 crc, u8 *data, u32 len) { /* from libdvbv5 */ while (len--) @@ -92,40 +92,7 @@ static void vidtv_psi_update_version_num(struct vidtv_psi_table_header *h) h->version++; } -static inline u16 vidtv_psi_sdt_serv_get_desc_loop_len(struct vidtv_psi_table_sdt_service *s) -{ - u16 mask; - u16 ret; - - mask = GENMASK(11, 0); - - ret = be16_to_cpu(s->bitfield) & mask; - return ret; -} - -static inline u16 vidtv_psi_pmt_stream_get_desc_loop_len(struct vidtv_psi_table_pmt_stream *s) -{ - u16 mask; - u16 ret; - - mask = GENMASK(9, 0); - - ret = be16_to_cpu(s->bitfield2) & mask; - return ret; -} - -static inline u16 vidtv_psi_pmt_get_desc_loop_len(struct vidtv_psi_table_pmt *p) -{ - u16 mask; - u16 ret; - - mask = GENMASK(9, 0); - - ret = be16_to_cpu(p->bitfield2) & mask; - return ret; -} - -static inline u16 vidtv_psi_get_sec_len(struct vidtv_psi_table_header *h) +static u16 vidtv_psi_get_sec_len(struct vidtv_psi_table_header *h) { u16 mask; u16 ret; @@ -136,7 +103,7 @@ static inline u16 vidtv_psi_get_sec_len(struct vidtv_psi_table_header *h) return ret; } -inline u16 vidtv_psi_get_pat_program_pid(struct vidtv_psi_table_pat_program *p) +u16 vidtv_psi_get_pat_program_pid(struct vidtv_psi_table_pat_program *p) { u16 mask; u16 ret; @@ -147,7 +114,7 @@ inline u16 vidtv_psi_get_pat_program_pid(struct vidtv_psi_table_pat_program *p) return ret; } -inline u16 vidtv_psi_pmt_stream_get_elem_pid(struct vidtv_psi_table_pmt_stream *s) +u16 vidtv_psi_pmt_stream_get_elem_pid(struct vidtv_psi_table_pmt_stream *s) { u16 mask; u16 ret; @@ -158,10 +125,11 @@ inline u16 vidtv_psi_pmt_stream_get_elem_pid(struct vidtv_psi_table_pmt_stream * return ret; } -static inline void vidtv_psi_set_desc_loop_len(__be16 *bitfield, u16 new_len, u8 desc_len_nbits) +static void vidtv_psi_set_desc_loop_len(__be16 *bitfield, u16 new_len, + u8 desc_len_nbits) { - u16 mask; __be16 new; + u16 mask; mask = GENMASK(15, desc_len_nbits); @@ -188,90 +156,81 @@ static void vidtv_psi_set_sec_len(struct vidtv_psi_table_header *h, u16 new_len) h->bitfield = new; } -static u32 vidtv_psi_ts_psi_write_into(struct psi_write_args args) +/* + * Packetize PSI sections into TS packets: + * push a TS header (4bytes) every 184 bytes + * manage the continuity_counter + * add stuffing (i.e. padding bytes) after the CRC + */ +static u32 vidtv_psi_ts_psi_write_into(struct psi_write_args *args) { - /* - * Packetize PSI sections into TS packets: - * push a TS header (4bytes) every 184 bytes - * manage the continuity_counter - * add stuffing (i.e. padding bytes) after the CRC - */ - - u32 nbytes_past_boundary = (args.dest_offset % TS_PACKET_LEN); + struct vidtv_mpeg_ts ts_header = { + .sync_byte = TS_SYNC_BYTE, + .bitfield = cpu_to_be16((args->new_psi_section << 14) | args->pid), + .scrambling = 0, + .payload = 1, + .adaptation_field = 0, /* no adaptation field */ + }; + u32 nbytes_past_boundary = (args->dest_offset % TS_PACKET_LEN); bool aligned = (nbytes_past_boundary == 0); - struct vidtv_mpeg_ts ts_header = {}; - - /* number of bytes written by this function */ - u32 nbytes = 0; - /* how much there is left to write */ - u32 remaining_len = args.len; - /* how much we can be written in this packet */ + u32 remaining_len = args->len; u32 payload_write_len = 0; - /* where we are in the source */ u32 payload_offset = 0; + u32 nbytes = 0; - const u16 PAYLOAD_START = args.new_psi_section; - - if (!args.crc && !args.is_crc) + if (!args->crc && !args->is_crc) pr_warn_ratelimited("Missing CRC for chunk\n"); - if (args.crc) - *args.crc = dvb_crc32(*args.crc, args.from, args.len); + if (args->crc) + *args->crc = dvb_crc32(*args->crc, args->from, args->len); - if (args.new_psi_section && !aligned) { + if (args->new_psi_section && !aligned) { pr_warn_ratelimited("Cannot write a new PSI section in a misaligned buffer\n"); /* forcibly align and hope for the best */ - nbytes += vidtv_memset(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + nbytes += vidtv_memset(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, TS_FILL_BYTE, TS_PACKET_LEN - nbytes_past_boundary); } while (remaining_len) { - nbytes_past_boundary = (args.dest_offset + nbytes) % TS_PACKET_LEN; + nbytes_past_boundary = (args->dest_offset + nbytes) % TS_PACKET_LEN; aligned = (nbytes_past_boundary == 0); if (aligned) { /* if at a packet boundary, write a new TS header */ - ts_header.sync_byte = TS_SYNC_BYTE; - ts_header.bitfield = cpu_to_be16((PAYLOAD_START << 14) | args.pid); - ts_header.scrambling = 0; - ts_header.continuity_counter = *args.continuity_counter; - ts_header.payload = 1; - /* no adaptation field */ - ts_header.adaptation_field = 0; - - /* copy the header */ - nbytes += vidtv_memcpy(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + ts_header.continuity_counter = *args->continuity_counter; + + nbytes += vidtv_memcpy(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, &ts_header, sizeof(ts_header)); /* * This will trigger a discontinuity if the buffer is full, * effectively dropping the packet. */ - vidtv_ts_inc_cc(args.continuity_counter); + vidtv_ts_inc_cc(args->continuity_counter); } /* write the pointer_field in the first byte of the payload */ - if (args.new_psi_section) - nbytes += vidtv_memset(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + if (args->new_psi_section) + nbytes += vidtv_memset(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, 0x0, 1); /* write as much of the payload as possible */ - nbytes_past_boundary = (args.dest_offset + nbytes) % TS_PACKET_LEN; + nbytes_past_boundary = (args->dest_offset + nbytes) % TS_PACKET_LEN; payload_write_len = min(TS_PACKET_LEN - nbytes_past_boundary, remaining_len); - nbytes += vidtv_memcpy(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, - args.from + payload_offset, + nbytes += vidtv_memcpy(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, + args->from + payload_offset, payload_write_len); /* 'payload_write_len' written from a total of 'len' requested*/ @@ -283,37 +242,45 @@ static u32 vidtv_psi_ts_psi_write_into(struct psi_write_args args) * fill the rest of the packet if there is any remaining space unused */ - nbytes_past_boundary = (args.dest_offset + nbytes) % TS_PACKET_LEN; + nbytes_past_boundary = (args->dest_offset + nbytes) % TS_PACKET_LEN; - if (args.is_crc) - nbytes += vidtv_memset(args.dest_buf, - args.dest_offset + nbytes, - args.dest_buf_sz, + if (args->is_crc) + nbytes += vidtv_memset(args->dest_buf, + args->dest_offset + nbytes, + args->dest_buf_sz, TS_FILL_BYTE, TS_PACKET_LEN - nbytes_past_boundary); return nbytes; } -static u32 table_section_crc32_write_into(struct crc32_write_args args) +static u32 table_section_crc32_write_into(struct crc32_write_args *args) { + struct psi_write_args psi_args = { + .dest_buf = args->dest_buf, + .from = &args->crc, + .len = CRC_SIZE_IN_BYTES, + .dest_offset = args->dest_offset, + .pid = args->pid, + .new_psi_section = false, + .continuity_counter = args->continuity_counter, + .is_crc = true, + .dest_buf_sz = args->dest_buf_sz, + }; + /* the CRC is the last entry in the section */ - u32 nbytes = 0; - struct psi_write_args psi_args = {}; - psi_args.dest_buf = args.dest_buf; - psi_args.from = &args.crc; - psi_args.len = CRC_SIZE_IN_BYTES; - psi_args.dest_offset = args.dest_offset; - psi_args.pid = args.pid; - psi_args.new_psi_section = false; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = true; - psi_args.dest_buf_sz = args.dest_buf_sz; + return vidtv_psi_ts_psi_write_into(&psi_args); +} - nbytes += vidtv_psi_ts_psi_write_into(psi_args); +static void vidtv_psi_desc_chain(struct vidtv_psi_desc *head, struct vidtv_psi_desc *desc) +{ + if (head) { + while (head->next) + head = head->next; - return nbytes; + head->next = desc; + } } struct vidtv_psi_desc_service *vidtv_psi_service_desc_init(struct vidtv_psi_desc *head, @@ -326,6 +293,8 @@ struct vidtv_psi_desc_service *vidtv_psi_service_desc_init(struct vidtv_psi_desc u32 provider_name_len = provider_name ? strlen(provider_name) : 0; desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + return NULL; desc->type = SERVICE_DESCRIPTOR; @@ -347,12 +316,7 @@ struct vidtv_psi_desc_service *vidtv_psi_service_desc_init(struct vidtv_psi_desc if (provider_name && provider_name_len) desc->provider_name = kstrdup(provider_name, GFP_KERNEL); - if (head) { - while (head->next) - head = head->next; - - head->next = (struct vidtv_psi_desc *)desc; - } + vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc); return desc; } @@ -365,6 +329,8 @@ struct vidtv_psi_desc_registration struct vidtv_psi_desc_registration *desc; desc = kzalloc(sizeof(*desc) + sizeof(format_id) + additional_info_len, GFP_KERNEL); + if (!desc) + return NULL; desc->type = REGISTRATION_DESCRIPTOR; @@ -378,44 +344,178 @@ struct vidtv_psi_desc_registration additional_ident_info, additional_info_len); - if (head) { - while (head->next) - head = head->next; + vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc); + return desc; +} - head->next = (struct vidtv_psi_desc *)desc; +struct vidtv_psi_desc_network_name +*vidtv_psi_network_name_desc_init(struct vidtv_psi_desc *head, char *network_name) +{ + u32 network_name_len = network_name ? strlen(network_name) : 0; + struct vidtv_psi_desc_network_name *desc; + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + return NULL; + + desc->type = NETWORK_NAME_DESCRIPTOR; + + desc->length = network_name_len; + + if (network_name && network_name_len) + desc->network_name = kstrdup(network_name, GFP_KERNEL); + + vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc); + return desc; +} + +struct vidtv_psi_desc_service_list +*vidtv_psi_service_list_desc_init(struct vidtv_psi_desc *head, + struct vidtv_psi_desc_service_list_entry *entry) +{ + struct vidtv_psi_desc_service_list_entry *curr_e = NULL; + struct vidtv_psi_desc_service_list_entry *head_e = NULL; + struct vidtv_psi_desc_service_list_entry *prev_e = NULL; + struct vidtv_psi_desc_service_list *desc; + u16 length = 0; + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + return NULL; + + desc->type = SERVICE_LIST_DESCRIPTOR; + + while (entry) { + curr_e = kzalloc(sizeof(*curr_e), GFP_KERNEL); + if (!curr_e) { + while (head_e) { + curr_e = head_e; + head_e = head_e->next; + kfree(curr_e); + } + kfree(desc); + return NULL; + } + + curr_e->service_id = entry->service_id; + curr_e->service_type = entry->service_type; + + length += sizeof(struct vidtv_psi_desc_service_list_entry) - + sizeof(struct vidtv_psi_desc_service_list_entry *); + + if (!head_e) + head_e = curr_e; + if (prev_e) + prev_e->next = curr_e; + + prev_e = curr_e; + entry = entry->next; } + desc->length = length; + desc->service_list = head_e; + + vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc); + return desc; +} + +struct vidtv_psi_desc_short_event +*vidtv_psi_short_event_desc_init(struct vidtv_psi_desc *head, + char *iso_language_code, + char *event_name, + char *text) +{ + u32 iso_len = iso_language_code ? strlen(iso_language_code) : 0; + u32 event_name_len = event_name ? strlen(event_name) : 0; + struct vidtv_psi_desc_short_event *desc; + u32 text_len = text ? strlen(text) : 0; + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + return NULL; + + desc->type = SHORT_EVENT_DESCRIPTOR; + + desc->length = ISO_LANGUAGE_CODE_LEN + + sizeof_field(struct vidtv_psi_desc_short_event, event_name_len) + + event_name_len + + sizeof_field(struct vidtv_psi_desc_short_event, text_len) + + text_len; + + desc->event_name_len = event_name_len; + desc->text_len = text_len; + + if (iso_len != ISO_LANGUAGE_CODE_LEN) + iso_language_code = "eng"; + + desc->iso_language_code = kstrdup(iso_language_code, GFP_KERNEL); + + if (event_name && event_name_len) + desc->event_name = kstrdup(event_name, GFP_KERNEL); + + if (text && text_len) + desc->text = kstrdup(text, GFP_KERNEL); + + vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc); return desc; } struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc) { + struct vidtv_psi_desc_network_name *desc_network_name; + struct vidtv_psi_desc_service_list *desc_service_list; + struct vidtv_psi_desc_short_event *desc_short_event; + struct vidtv_psi_desc_service *service; struct vidtv_psi_desc *head = NULL; struct vidtv_psi_desc *prev = NULL; struct vidtv_psi_desc *curr = NULL; - struct vidtv_psi_desc_service *service; - while (desc) { switch (desc->type) { case SERVICE_DESCRIPTOR: service = (struct vidtv_psi_desc_service *)desc; curr = (struct vidtv_psi_desc *) - vidtv_psi_service_desc_init(head, - service->service_type, - service->service_name, - service->provider_name); + vidtv_psi_service_desc_init(head, + service->service_type, + service->service_name, + service->provider_name); + break; + + case NETWORK_NAME_DESCRIPTOR: + desc_network_name = (struct vidtv_psi_desc_network_name *)desc; + curr = (struct vidtv_psi_desc *) + vidtv_psi_network_name_desc_init(head, + desc_network_name->network_name); + break; + + case SERVICE_LIST_DESCRIPTOR: + desc_service_list = (struct vidtv_psi_desc_service_list *)desc; + curr = (struct vidtv_psi_desc *) + vidtv_psi_service_list_desc_init(head, + desc_service_list->service_list); + break; + + case SHORT_EVENT_DESCRIPTOR: + desc_short_event = (struct vidtv_psi_desc_short_event *)desc; + curr = (struct vidtv_psi_desc *) + vidtv_psi_short_event_desc_init(head, + desc_short_event->iso_language_code, + desc_short_event->event_name, + desc_short_event->text); break; case REGISTRATION_DESCRIPTOR: default: curr = kzalloc(sizeof(*desc) + desc->length, GFP_KERNEL); + if (!curr) + return NULL; memcpy(curr, desc, sizeof(*desc) + desc->length); - break; - } + } - if (curr) - curr->next = NULL; + if (!curr) + return NULL; + + curr->next = NULL; if (!head) head = curr; if (prev) @@ -430,6 +530,8 @@ struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc) void vidtv_psi_desc_destroy(struct vidtv_psi_desc *desc) { + struct vidtv_psi_desc_service_list_entry *sl_entry_tmp = NULL; + struct vidtv_psi_desc_service_list_entry *sl_entry = NULL; struct vidtv_psi_desc *curr = desc; struct vidtv_psi_desc *tmp = NULL; @@ -447,6 +549,25 @@ void vidtv_psi_desc_destroy(struct vidtv_psi_desc *desc) /* nothing to do */ break; + case NETWORK_NAME_DESCRIPTOR: + kfree(((struct vidtv_psi_desc_network_name *)tmp)->network_name); + break; + + case SERVICE_LIST_DESCRIPTOR: + sl_entry = ((struct vidtv_psi_desc_service_list *)tmp)->service_list; + while (sl_entry) { + sl_entry_tmp = sl_entry; + sl_entry = sl_entry->next; + kfree(sl_entry_tmp); + } + break; + + case SHORT_EVENT_DESCRIPTOR: + kfree(((struct vidtv_psi_desc_short_event *)tmp)->iso_language_code); + kfree(((struct vidtv_psi_desc_short_event *)tmp)->event_name); + kfree(((struct vidtv_psi_desc_short_event *)tmp)->text); + break; + default: pr_warn_ratelimited("Possible leak: not handling descriptor type %d\n", tmp->type); @@ -513,63 +634,119 @@ void vidtv_sdt_desc_assign(struct vidtv_psi_table_sdt *sdt, vidtv_psi_update_version_num(&sdt->header); } -static u32 vidtv_psi_desc_write_into(struct desc_write_args args) +static u32 vidtv_psi_desc_write_into(struct desc_write_args *args) { - /* the number of bytes written by this function */ + struct psi_write_args psi_args = { + .dest_buf = args->dest_buf, + .from = &args->desc->type, + .pid = args->pid, + .new_psi_section = false, + .continuity_counter = args->continuity_counter, + .is_crc = false, + .dest_buf_sz = args->dest_buf_sz, + .crc = args->crc, + .len = sizeof_field(struct vidtv_psi_desc, type) + + sizeof_field(struct vidtv_psi_desc, length), + }; + struct vidtv_psi_desc_service_list_entry *serv_list_entry = NULL; u32 nbytes = 0; - struct psi_write_args psi_args = {}; - - psi_args.dest_buf = args.dest_buf; - psi_args.from = &args.desc->type; - psi_args.len = sizeof_field(struct vidtv_psi_desc, type) + - sizeof_field(struct vidtv_psi_desc, length); + psi_args.dest_offset = args->dest_offset + nbytes; - psi_args.dest_offset = args.dest_offset + nbytes; - psi_args.pid = args.pid; - psi_args.new_psi_section = false; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = false; - psi_args.dest_buf_sz = args.dest_buf_sz; - psi_args.crc = args.crc; + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - nbytes += vidtv_psi_ts_psi_write_into(psi_args); - - switch (args.desc->type) { + switch (args->desc->type) { case SERVICE_DESCRIPTOR: - psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.dest_offset = args->dest_offset + nbytes; psi_args.len = sizeof_field(struct vidtv_psi_desc_service, service_type) + sizeof_field(struct vidtv_psi_desc_service, provider_name_len); - psi_args.from = &((struct vidtv_psi_desc_service *)args.desc)->service_type; + psi_args.from = &((struct vidtv_psi_desc_service *)args->desc)->service_type; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - psi_args.dest_offset = args.dest_offset + nbytes; - psi_args.len = ((struct vidtv_psi_desc_service *)args.desc)->provider_name_len; - psi_args.from = ((struct vidtv_psi_desc_service *)args.desc)->provider_name; + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = ((struct vidtv_psi_desc_service *)args->desc)->provider_name_len; + psi_args.from = ((struct vidtv_psi_desc_service *)args->desc)->provider_name; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - psi_args.dest_offset = args.dest_offset + nbytes; + psi_args.dest_offset = args->dest_offset + nbytes; psi_args.len = sizeof_field(struct vidtv_psi_desc_service, service_name_len); - psi_args.from = &((struct vidtv_psi_desc_service *)args.desc)->service_name_len; + psi_args.from = &((struct vidtv_psi_desc_service *)args->desc)->service_name_len; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - psi_args.dest_offset = args.dest_offset + nbytes; - psi_args.len = ((struct vidtv_psi_desc_service *)args.desc)->service_name_len; - psi_args.from = ((struct vidtv_psi_desc_service *)args.desc)->service_name; + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = ((struct vidtv_psi_desc_service *)args->desc)->service_name_len; + psi_args.from = ((struct vidtv_psi_desc_service *)args->desc)->service_name; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + break; + + case NETWORK_NAME_DESCRIPTOR: + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = args->desc->length; + psi_args.from = ((struct vidtv_psi_desc_network_name *)args->desc)->network_name; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + break; + + case SERVICE_LIST_DESCRIPTOR: + serv_list_entry = ((struct vidtv_psi_desc_service_list *)args->desc)->service_list; + while (serv_list_entry) { + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = sizeof(struct vidtv_psi_desc_service_list_entry) - + sizeof(struct vidtv_psi_desc_service_list_entry *); + psi_args.from = serv_list_entry; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + + serv_list_entry = serv_list_entry->next; + } + break; + + case SHORT_EVENT_DESCRIPTOR: + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = ISO_LANGUAGE_CODE_LEN; + psi_args.from = ((struct vidtv_psi_desc_short_event *) + args->desc)->iso_language_code; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = sizeof_field(struct vidtv_psi_desc_short_event, event_name_len); + psi_args.from = &((struct vidtv_psi_desc_short_event *) + args->desc)->event_name_len; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = ((struct vidtv_psi_desc_short_event *)args->desc)->event_name_len; + psi_args.from = ((struct vidtv_psi_desc_short_event *)args->desc)->event_name; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = sizeof_field(struct vidtv_psi_desc_short_event, text_len); + psi_args.from = &((struct vidtv_psi_desc_short_event *)args->desc)->text_len; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = ((struct vidtv_psi_desc_short_event *)args->desc)->text_len; + psi_args.from = ((struct vidtv_psi_desc_short_event *)args->desc)->text; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - nbytes += vidtv_psi_ts_psi_write_into(psi_args); break; case REGISTRATION_DESCRIPTOR: default: - psi_args.dest_offset = args.dest_offset + nbytes; - psi_args.len = args.desc->length; - psi_args.from = &args.desc->data; + psi_args.dest_offset = args->dest_offset + nbytes; + psi_args.len = args->desc->length; + psi_args.from = &args->desc->data; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); break; } @@ -577,40 +754,37 @@ static u32 vidtv_psi_desc_write_into(struct desc_write_args args) } static u32 -vidtv_psi_table_header_write_into(struct header_write_args args) +vidtv_psi_table_header_write_into(struct header_write_args *args) { - /* the number of bytes written by this function */ - u32 nbytes = 0; - struct psi_write_args psi_args = {}; - - psi_args.dest_buf = args.dest_buf; - psi_args.from = args.h; - psi_args.len = sizeof(struct vidtv_psi_table_header); - psi_args.dest_offset = args.dest_offset; - psi_args.pid = args.pid; - psi_args.new_psi_section = true; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = false; - psi_args.dest_buf_sz = args.dest_buf_sz; - psi_args.crc = args.crc; - - nbytes += vidtv_psi_ts_psi_write_into(psi_args); - - return nbytes; + struct psi_write_args psi_args = { + .dest_buf = args->dest_buf, + .from = args->h, + .len = sizeof(struct vidtv_psi_table_header), + .dest_offset = args->dest_offset, + .pid = args->pid, + .new_psi_section = true, + .continuity_counter = args->continuity_counter, + .is_crc = false, + .dest_buf_sz = args->dest_buf_sz, + .crc = args->crc, + }; + + return vidtv_psi_ts_psi_write_into(&psi_args); } void vidtv_psi_pat_table_update_sec_len(struct vidtv_psi_table_pat *pat) { - /* see ISO/IEC 13818-1 : 2000 p.43 */ u16 length = 0; u32 i; + /* see ISO/IEC 13818-1 : 2000 p.43 */ + /* from immediately after 'section_length' until 'last_section_number'*/ length += PAT_LEN_UNTIL_LAST_SECTION_NUMBER; /* do not count the pointer */ - for (i = 0; i < pat->programs; ++i) + for (i = 0; i < pat->num_pat; ++i) length += sizeof(struct vidtv_psi_table_pat_program) - sizeof(struct vidtv_psi_table_pat_program *); @@ -621,10 +795,11 @@ vidtv_psi_pat_table_update_sec_len(struct vidtv_psi_table_pat *pat) void vidtv_psi_pmt_table_update_sec_len(struct vidtv_psi_table_pmt *pmt) { - /* see ISO/IEC 13818-1 : 2000 p.46 */ - u16 length = 0; struct vidtv_psi_table_pmt_stream *s = pmt->stream; u16 desc_loop_len; + u16 length = 0; + + /* see ISO/IEC 13818-1 : 2000 p.46 */ /* from immediately after 'section_length' until 'program_info_length'*/ length += PMT_LEN_UNTIL_PROGRAM_INFO_LENGTH; @@ -655,10 +830,11 @@ void vidtv_psi_pmt_table_update_sec_len(struct vidtv_psi_table_pmt *pmt) void vidtv_psi_sdt_table_update_sec_len(struct vidtv_psi_table_sdt *sdt) { - /* see ETSI EN 300 468 V 1.10.1 p.24 */ - u16 length = 0; struct vidtv_psi_table_sdt_service *s = sdt->service; u16 desc_loop_len; + u16 length = 0; + + /* see ETSI EN 300 468 V 1.10.1 p.24 */ /* * from immediately after 'section_length' until @@ -681,7 +857,6 @@ void vidtv_psi_sdt_table_update_sec_len(struct vidtv_psi_table_sdt *sdt) } length += CRC_SIZE_IN_BYTES; - vidtv_psi_set_sec_len(&sdt->header, length); } @@ -694,6 +869,8 @@ vidtv_psi_pat_program_init(struct vidtv_psi_table_pat_program *head, const u16 RESERVED = 0x07; program = kzalloc(sizeof(*program), GFP_KERNEL); + if (!program) + return NULL; program->service_id = cpu_to_be16(service_id); @@ -714,8 +891,8 @@ vidtv_psi_pat_program_init(struct vidtv_psi_table_pat_program *head, void vidtv_psi_pat_program_destroy(struct vidtv_psi_table_pat_program *p) { - struct vidtv_psi_table_pat_program *curr = p; struct vidtv_psi_table_pat_program *tmp = NULL; + struct vidtv_psi_table_pat_program *curr = p; while (curr) { tmp = curr; @@ -724,42 +901,49 @@ vidtv_psi_pat_program_destroy(struct vidtv_psi_table_pat_program *p) } } +/* This function transfers ownership of p to the table */ void vidtv_psi_pat_program_assign(struct vidtv_psi_table_pat *pat, struct vidtv_psi_table_pat_program *p) { - /* This function transfers ownership of p to the table */ + struct vidtv_psi_table_pat_program *program; + u16 program_count; - u16 program_count = 0; - struct vidtv_psi_table_pat_program *program = p; + do { + program_count = 0; + program = p; - if (p == pat->program) - return; + if (p == pat->program) + return; - while (program) { - ++program_count; - program = program->next; - } + while (program) { + ++program_count; + program = program->next; + } - pat->programs = program_count; - pat->program = p; + pat->num_pat = program_count; + pat->program = p; - /* Recompute section length */ - vidtv_psi_pat_table_update_sec_len(pat); + /* Recompute section length */ + vidtv_psi_pat_table_update_sec_len(pat); - if (vidtv_psi_get_sec_len(&pat->header) > MAX_SECTION_LEN) - vidtv_psi_pat_program_assign(pat, NULL); + p = NULL; + } while (vidtv_psi_get_sec_len(&pat->header) > MAX_SECTION_LEN); vidtv_psi_update_version_num(&pat->header); } struct vidtv_psi_table_pat *vidtv_psi_pat_table_init(u16 transport_stream_id) { - struct vidtv_psi_table_pat *pat = kzalloc(sizeof(*pat), GFP_KERNEL); + struct vidtv_psi_table_pat *pat; const u16 SYNTAX = 0x1; const u16 ZERO = 0x0; const u16 ONES = 0x03; + pat = kzalloc(sizeof(*pat), GFP_KERNEL); + if (!pat) + return NULL; + pat->header.table_id = 0x0; pat->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ZERO << 14) | (ONES << 12)); @@ -772,70 +956,68 @@ struct vidtv_psi_table_pat *vidtv_psi_pat_table_init(u16 transport_stream_id) pat->header.section_id = 0x0; pat->header.last_section = 0x0; - pat->programs = 0; - vidtv_psi_pat_table_update_sec_len(pat); return pat; } -u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args args) +u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args *args) { - /* the number of bytes written by this function */ + struct vidtv_psi_table_pat_program *p = args->pat->program; + struct header_write_args h_args = { + .dest_buf = args->buf, + .dest_offset = args->offset, + .pid = VIDTV_PAT_PID, + .h = &args->pat->header, + .continuity_counter = args->continuity_counter, + .dest_buf_sz = args->buf_sz, + }; + struct psi_write_args psi_args = { + .dest_buf = args->buf, + .pid = VIDTV_PAT_PID, + .new_psi_section = false, + .continuity_counter = args->continuity_counter, + .is_crc = false, + .dest_buf_sz = args->buf_sz, + }; + struct crc32_write_args c_args = { + .dest_buf = args->buf, + .pid = VIDTV_PAT_PID, + .dest_buf_sz = args->buf_sz, + }; + u32 crc = INITIAL_CRC; u32 nbytes = 0; - const u16 pat_pid = VIDTV_PAT_PID; - u32 crc = 0xffffffff; - - struct vidtv_psi_table_pat_program *p = args.pat->program; - struct header_write_args h_args = {}; - struct psi_write_args psi_args = {}; - struct crc32_write_args c_args = {}; + vidtv_psi_pat_table_update_sec_len(args->pat); - vidtv_psi_pat_table_update_sec_len(args.pat); - - h_args.dest_buf = args.buf; - h_args.dest_offset = args.offset; - h_args.h = &args.pat->header; - h_args.pid = pat_pid; - h_args.continuity_counter = args.continuity_counter; - h_args.dest_buf_sz = args.buf_sz; h_args.crc = &crc; - nbytes += vidtv_psi_table_header_write_into(h_args); + nbytes += vidtv_psi_table_header_write_into(&h_args); /* note that the field 'u16 programs' is not really part of the PAT */ - psi_args.dest_buf = args.buf; - psi_args.pid = pat_pid; - psi_args.new_psi_section = false; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = false; - psi_args.dest_buf_sz = args.buf_sz; - psi_args.crc = &crc; + psi_args.crc = &crc; while (p) { /* copy the PAT programs */ psi_args.from = p; /* skip the pointer */ psi_args.len = sizeof(*p) - - sizeof(struct vidtv_psi_table_pat_program *); - psi_args.dest_offset = args.offset + nbytes; + sizeof(struct vidtv_psi_table_pat_program *); + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); p = p->next; } - c_args.dest_buf = args.buf; - c_args.dest_offset = args.offset + nbytes; + c_args.dest_offset = args->offset + nbytes; + c_args.continuity_counter = args->continuity_counter; c_args.crc = cpu_to_be32(crc); - c_args.pid = pat_pid; - c_args.continuity_counter = args.continuity_counter; - c_args.dest_buf_sz = args.buf_sz; /* Write the CRC32 at the end */ - nbytes += table_section_crc32_write_into(c_args); + nbytes += table_section_crc32_write_into(&c_args); return nbytes; } @@ -859,6 +1041,8 @@ vidtv_psi_pmt_stream_init(struct vidtv_psi_table_pmt_stream *head, u16 desc_loop_len; stream = kzalloc(sizeof(*stream), GFP_KERNEL); + if (!stream) + return NULL; stream->type = stream_type; @@ -883,8 +1067,8 @@ vidtv_psi_pmt_stream_init(struct vidtv_psi_table_pmt_stream *head, void vidtv_psi_pmt_stream_destroy(struct vidtv_psi_table_pmt_stream *s) { - struct vidtv_psi_table_pmt_stream *curr_stream = s; struct vidtv_psi_table_pmt_stream *tmp_stream = NULL; + struct vidtv_psi_table_pmt_stream *curr_stream = s; while (curr_stream) { tmp_stream = curr_stream; @@ -897,15 +1081,16 @@ void vidtv_psi_pmt_stream_destroy(struct vidtv_psi_table_pmt_stream *s) void vidtv_psi_pmt_stream_assign(struct vidtv_psi_table_pmt *pmt, struct vidtv_psi_table_pmt_stream *s) { - /* This function transfers ownership of s to the table */ - if (s == pmt->stream) - return; + do { + /* This function transfers ownership of s to the table */ + if (s == pmt->stream) + return; - pmt->stream = s; - vidtv_psi_pmt_table_update_sec_len(pmt); + pmt->stream = s; + vidtv_psi_pmt_table_update_sec_len(pmt); - if (vidtv_psi_get_sec_len(&pmt->header) > MAX_SECTION_LEN) - vidtv_psi_pmt_stream_assign(pmt, NULL); + s = NULL; + } while (vidtv_psi_get_sec_len(&pmt->header) > MAX_SECTION_LEN); vidtv_psi_update_version_num(&pmt->header); } @@ -933,14 +1118,18 @@ u16 vidtv_psi_pmt_get_pid(struct vidtv_psi_table_pmt *section, struct vidtv_psi_table_pmt *vidtv_psi_pmt_table_init(u16 program_number, u16 pcr_pid) { - struct vidtv_psi_table_pmt *pmt = kzalloc(sizeof(*pmt), GFP_KERNEL); - const u16 SYNTAX = 0x1; - const u16 ZERO = 0x0; - const u16 ONES = 0x03; + struct vidtv_psi_table_pmt *pmt; const u16 RESERVED1 = 0x07; const u16 RESERVED2 = 0x0f; + const u16 SYNTAX = 0x1; + const u16 ONES = 0x03; + const u16 ZERO = 0x0; u16 desc_loop_len; + pmt = kzalloc(sizeof(*pmt), GFP_KERNEL); + if (!pmt) + return NULL; + if (!pcr_pid) pcr_pid = 0x1fff; @@ -970,87 +1159,84 @@ struct vidtv_psi_table_pmt *vidtv_psi_pmt_table_init(u16 program_number, return pmt; } -u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) +u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args *args) { - /* the number of bytes written by this function */ + struct vidtv_psi_desc *table_descriptor = args->pmt->descriptor; + struct vidtv_psi_table_pmt_stream *stream = args->pmt->stream; + struct vidtv_psi_desc *stream_descriptor; + struct header_write_args h_args = { + .dest_buf = args->buf, + .dest_offset = args->offset, + .h = &args->pmt->header, + .pid = args->pid, + .continuity_counter = args->continuity_counter, + .dest_buf_sz = args->buf_sz, + }; + struct psi_write_args psi_args = { + .dest_buf = args->buf, + .from = &args->pmt->bitfield, + .len = sizeof_field(struct vidtv_psi_table_pmt, bitfield) + + sizeof_field(struct vidtv_psi_table_pmt, bitfield2), + .pid = args->pid, + .new_psi_section = false, + .is_crc = false, + .dest_buf_sz = args->buf_sz, + }; + struct desc_write_args d_args = { + .dest_buf = args->buf, + .desc = table_descriptor, + .pid = args->pid, + .dest_buf_sz = args->buf_sz, + }; + struct crc32_write_args c_args = { + .dest_buf = args->buf, + .pid = args->pid, + .dest_buf_sz = args->buf_sz, + }; + u32 crc = INITIAL_CRC; u32 nbytes = 0; - u32 crc = 0xffffffff; - - struct vidtv_psi_desc *table_descriptor = args.pmt->descriptor; - struct vidtv_psi_table_pmt_stream *stream = args.pmt->stream; - struct vidtv_psi_desc *stream_descriptor = (stream) ? - args.pmt->stream->descriptor : - NULL; - - struct header_write_args h_args = {}; - struct psi_write_args psi_args = {}; - struct desc_write_args d_args = {}; - struct crc32_write_args c_args = {}; - - vidtv_psi_pmt_table_update_sec_len(args.pmt); - - h_args.dest_buf = args.buf; - h_args.dest_offset = args.offset; - h_args.h = &args.pmt->header; - h_args.pid = args.pid; - h_args.continuity_counter = args.continuity_counter; - h_args.dest_buf_sz = args.buf_sz; + + vidtv_psi_pmt_table_update_sec_len(args->pmt); + h_args.crc = &crc; - nbytes += vidtv_psi_table_header_write_into(h_args); + nbytes += vidtv_psi_table_header_write_into(&h_args); /* write the two bitfields */ - psi_args.dest_buf = args.buf; - psi_args.from = &args.pmt->bitfield; - psi_args.len = sizeof_field(struct vidtv_psi_table_pmt, bitfield) + - sizeof_field(struct vidtv_psi_table_pmt, bitfield2); - - psi_args.dest_offset = args.offset + nbytes; - psi_args.pid = args.pid; - psi_args.new_psi_section = false; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = false; - psi_args.dest_buf_sz = args.buf_sz; - psi_args.crc = &crc; - - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); while (table_descriptor) { /* write the descriptors, if any */ - d_args.dest_buf = args.buf; - d_args.dest_offset = args.offset + nbytes; - d_args.desc = table_descriptor; - d_args.pid = args.pid; - d_args.continuity_counter = args.continuity_counter; - d_args.dest_buf_sz = args.buf_sz; + d_args.dest_offset = args->offset + nbytes; + d_args.continuity_counter = args->continuity_counter; d_args.crc = &crc; - nbytes += vidtv_psi_desc_write_into(d_args); + nbytes += vidtv_psi_desc_write_into(&d_args); table_descriptor = table_descriptor->next; } + psi_args.len += sizeof_field(struct vidtv_psi_table_pmt_stream, type); while (stream) { /* write the streams, if any */ psi_args.from = stream; - psi_args.len = sizeof_field(struct vidtv_psi_table_pmt_stream, type) + - sizeof_field(struct vidtv_psi_table_pmt_stream, bitfield) + - sizeof_field(struct vidtv_psi_table_pmt_stream, bitfield2); - psi_args.dest_offset = args.offset + nbytes; + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + stream_descriptor = stream->descriptor; while (stream_descriptor) { /* write the stream descriptors, if any */ - d_args.dest_buf = args.buf; - d_args.dest_offset = args.offset + nbytes; + d_args.dest_offset = args->offset + nbytes; d_args.desc = stream_descriptor; - d_args.pid = args.pid; - d_args.continuity_counter = args.continuity_counter; - d_args.dest_buf_sz = args.buf_sz; + d_args.continuity_counter = args->continuity_counter; d_args.crc = &crc; - nbytes += vidtv_psi_desc_write_into(d_args); + nbytes += vidtv_psi_desc_write_into(&d_args); stream_descriptor = stream_descriptor->next; } @@ -1058,15 +1244,12 @@ u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args) stream = stream->next; } - c_args.dest_buf = args.buf; - c_args.dest_offset = args.offset + nbytes; + c_args.dest_offset = args->offset + nbytes; c_args.crc = cpu_to_be32(crc); - c_args.pid = args.pid; - c_args.continuity_counter = args.continuity_counter; - c_args.dest_buf_sz = args.buf_sz; + c_args.continuity_counter = args->continuity_counter; /* Write the CRC32 at the end */ - nbytes += table_section_crc32_write_into(c_args); + nbytes += table_section_crc32_write_into(&c_args); return nbytes; } @@ -1078,16 +1261,20 @@ void vidtv_psi_pmt_table_destroy(struct vidtv_psi_table_pmt *pmt) kfree(pmt); } -struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 transport_stream_id) +struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 network_id, + u16 transport_stream_id) { - struct vidtv_psi_table_sdt *sdt = kzalloc(sizeof(*sdt), GFP_KERNEL); + struct vidtv_psi_table_sdt *sdt; + const u16 RESERVED = 0xff; const u16 SYNTAX = 0x1; - const u16 ONE = 0x1; const u16 ONES = 0x03; - const u16 RESERVED = 0xff; + const u16 ONE = 0x1; - sdt->header.table_id = 0x42; + sdt = kzalloc(sizeof(*sdt), GFP_KERNEL); + if (!sdt) + return NULL; + sdt->header.table_id = 0x42; sdt->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ONE << 14) | (ONES << 12)); /* @@ -1111,7 +1298,7 @@ struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 transport_stream_id) * This can be changed to something more useful, when support for * NIT gets added */ - sdt->network_id = cpu_to_be16(0xff01); + sdt->network_id = cpu_to_be16(network_id); sdt->reserved = RESERVED; vidtv_psi_sdt_table_update_sec_len(sdt); @@ -1119,74 +1306,79 @@ struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 transport_stream_id) return sdt; } -u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) +u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args *args) { + struct header_write_args h_args = { + .dest_buf = args->buf, + .dest_offset = args->offset, + .h = &args->sdt->header, + .pid = VIDTV_SDT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct psi_write_args psi_args = { + .dest_buf = args->buf, + .len = sizeof_field(struct vidtv_psi_table_sdt, network_id) + + sizeof_field(struct vidtv_psi_table_sdt, reserved), + .pid = VIDTV_SDT_PID, + .new_psi_section = false, + .is_crc = false, + .dest_buf_sz = args->buf_sz, + }; + struct desc_write_args d_args = { + .dest_buf = args->buf, + .pid = VIDTV_SDT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct crc32_write_args c_args = { + .dest_buf = args->buf, + .pid = VIDTV_SDT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct vidtv_psi_table_sdt_service *service = args->sdt->service; + struct vidtv_psi_desc *service_desc; u32 nbytes = 0; - u16 sdt_pid = VIDTV_SDT_PID; /* see ETSI EN 300 468 v1.15.1 p. 11 */ + u32 crc = INITIAL_CRC; - u32 crc = 0xffffffff; + /* see ETSI EN 300 468 v1.15.1 p. 11 */ - struct vidtv_psi_table_sdt_service *service = args.sdt->service; - struct vidtv_psi_desc *service_desc = (args.sdt->service) ? - args.sdt->service->descriptor : - NULL; + vidtv_psi_sdt_table_update_sec_len(args->sdt); - struct header_write_args h_args = {}; - struct psi_write_args psi_args = {}; - struct desc_write_args d_args = {}; - struct crc32_write_args c_args = {}; - - vidtv_psi_sdt_table_update_sec_len(args.sdt); - - h_args.dest_buf = args.buf; - h_args.dest_offset = args.offset; - h_args.h = &args.sdt->header; - h_args.pid = sdt_pid; - h_args.continuity_counter = args.continuity_counter; - h_args.dest_buf_sz = args.buf_sz; + h_args.continuity_counter = args->continuity_counter; h_args.crc = &crc; - nbytes += vidtv_psi_table_header_write_into(h_args); - - psi_args.dest_buf = args.buf; - psi_args.from = &args.sdt->network_id; + nbytes += vidtv_psi_table_header_write_into(&h_args); - psi_args.len = sizeof_field(struct vidtv_psi_table_sdt, network_id) + - sizeof_field(struct vidtv_psi_table_sdt, reserved); - - psi_args.dest_offset = args.offset + nbytes; - psi_args.pid = sdt_pid; - psi_args.new_psi_section = false; - psi_args.continuity_counter = args.continuity_counter; - psi_args.is_crc = false; - psi_args.dest_buf_sz = args.buf_sz; + psi_args.from = &args->sdt->network_id; + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; psi_args.crc = &crc; /* copy u16 network_id + u8 reserved)*/ - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + + /* skip both pointers at the end */ + psi_args.len = sizeof(struct vidtv_psi_table_sdt_service) - + sizeof(struct vidtv_psi_desc *) - + sizeof(struct vidtv_psi_table_sdt_service *); while (service) { /* copy the services, if any */ psi_args.from = service; - /* skip both pointers at the end */ - psi_args.len = sizeof(struct vidtv_psi_table_sdt_service) - - sizeof(struct vidtv_psi_desc *) - - sizeof(struct vidtv_psi_table_sdt_service *); - psi_args.dest_offset = args.offset + nbytes; + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); - nbytes += vidtv_psi_ts_psi_write_into(psi_args); + service_desc = service->descriptor; while (service_desc) { /* copy the service descriptors, if any */ - d_args.dest_buf = args.buf; - d_args.dest_offset = args.offset + nbytes; + d_args.dest_offset = args->offset + nbytes; d_args.desc = service_desc; - d_args.pid = sdt_pid; - d_args.continuity_counter = args.continuity_counter; - d_args.dest_buf_sz = args.buf_sz; + d_args.continuity_counter = args->continuity_counter; d_args.crc = &crc; - nbytes += vidtv_psi_desc_write_into(d_args); + nbytes += vidtv_psi_desc_write_into(&d_args); service_desc = service_desc->next; } @@ -1194,15 +1386,12 @@ u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args) service = service->next; } - c_args.dest_buf = args.buf; - c_args.dest_offset = args.offset + nbytes; + c_args.dest_offset = args->offset + nbytes; c_args.crc = cpu_to_be32(crc); - c_args.pid = sdt_pid; - c_args.continuity_counter = args.continuity_counter; - c_args.dest_buf_sz = args.buf_sz; + c_args.continuity_counter = args->continuity_counter; /* Write the CRC at the end */ - nbytes += table_section_crc32_write_into(c_args); + nbytes += table_section_crc32_write_into(&c_args); return nbytes; } @@ -1215,11 +1404,15 @@ void vidtv_psi_sdt_table_destroy(struct vidtv_psi_table_sdt *sdt) struct vidtv_psi_table_sdt_service *vidtv_psi_sdt_service_init(struct vidtv_psi_table_sdt_service *head, - u16 service_id) + u16 service_id, + bool eit_schedule, + bool eit_present_following) { struct vidtv_psi_table_sdt_service *service; service = kzalloc(sizeof(*service), GFP_KERNEL); + if (!service) + return NULL; /* * ETSI 300 468: this is a 16bit field which serves as a label to @@ -1228,8 +1421,8 @@ struct vidtv_psi_table_sdt_service * corresponding program_map_section */ service->service_id = cpu_to_be16(service_id); - service->EIT_schedule = 0x0; - service->EIT_present_following = 0x0; + service->EIT_schedule = eit_schedule; + service->EIT_present_following = eit_present_following; service->reserved = 0x3f; service->bitfield = cpu_to_be16(RUNNING << 13); @@ -1262,53 +1455,78 @@ void vidtv_psi_sdt_service_assign(struct vidtv_psi_table_sdt *sdt, struct vidtv_psi_table_sdt_service *service) { - if (service == sdt->service) - return; + do { + if (service == sdt->service) + return; - sdt->service = service; + sdt->service = service; - /* recompute section length */ - vidtv_psi_sdt_table_update_sec_len(sdt); + /* recompute section length */ + vidtv_psi_sdt_table_update_sec_len(sdt); - if (vidtv_psi_get_sec_len(&sdt->header) > MAX_SECTION_LEN) - vidtv_psi_sdt_service_assign(sdt, NULL); + service = NULL; + } while (vidtv_psi_get_sec_len(&sdt->header) > MAX_SECTION_LEN); vidtv_psi_update_version_num(&sdt->header); } +/* + * PMTs contain information about programs. For each program, + * there is one PMT section. This function will create a section + * for each program found in the PAT + */ struct vidtv_psi_table_pmt** -vidtv_psi_pmt_create_sec_for_each_pat_entry(struct vidtv_psi_table_pat *pat, u16 pcr_pid) +vidtv_psi_pmt_create_sec_for_each_pat_entry(struct vidtv_psi_table_pat *pat, + u16 pcr_pid) { + struct vidtv_psi_table_pat_program *program; + struct vidtv_psi_table_pmt **pmt_secs; + u32 i = 0, num_pmt = 0; + /* - * PMTs contain information about programs. For each program, - * there is one PMT section. This function will create a section - * for each program found in the PAT + * The number of PMT entries is the number of PAT entries + * that contain service_id. That exclude special tables, like NIT */ - struct vidtv_psi_table_pat_program *program = pat->program; - struct vidtv_psi_table_pmt **pmt_secs; - u32 i = 0; + program = pat->program; + while (program) { + if (program->service_id) + num_pmt++; + program = program->next; + } - /* a section for each program_id */ - pmt_secs = kcalloc(pat->programs, + pmt_secs = kcalloc(num_pmt, sizeof(struct vidtv_psi_table_pmt *), GFP_KERNEL); - - while (program) { - pmt_secs[i] = vidtv_psi_pmt_table_init(be16_to_cpu(program->service_id), pcr_pid); - ++i; - program = program->next; + if (!pmt_secs) + return NULL; + + for (program = pat->program; program; program = program->next) { + if (!program->service_id) + continue; + pmt_secs[i] = vidtv_psi_pmt_table_init(be16_to_cpu(program->service_id), + pcr_pid); + + if (!pmt_secs[i]) { + while (i > 0) { + i--; + vidtv_psi_pmt_table_destroy(pmt_secs[i]); + } + return NULL; + } + i++; } + pat->num_pmt = num_pmt; return pmt_secs; } +/* find the PMT section associated with 'program_num' */ struct vidtv_psi_table_pmt *vidtv_psi_find_pmt_sec(struct vidtv_psi_table_pmt **pmt_sections, u16 nsections, u16 program_num) { - /* find the PMT section associated with 'program_num' */ struct vidtv_psi_table_pmt *sec = NULL; u32 i; @@ -1320,3 +1538,488 @@ struct vidtv_psi_table_pmt return NULL; /* not found */ } + +static void vidtv_psi_nit_table_update_sec_len(struct vidtv_psi_table_nit *nit) +{ + u16 length = 0; + struct vidtv_psi_table_transport *t = nit->transport; + u16 desc_loop_len; + u16 transport_loop_len = 0; + + /* + * from immediately after 'section_length' until + * 'network_descriptor_length' + */ + length += NIT_LEN_UNTIL_NETWORK_DESCRIPTOR_LEN; + + desc_loop_len = vidtv_psi_desc_comp_loop_len(nit->descriptor); + vidtv_psi_set_desc_loop_len(&nit->bitfield, desc_loop_len, 12); + + length += desc_loop_len; + + length += sizeof_field(struct vidtv_psi_table_nit, bitfield2); + + while (t) { + /* skip both pointers at the end */ + transport_loop_len += sizeof(struct vidtv_psi_table_transport) - + sizeof(struct vidtv_psi_desc *) - + sizeof(struct vidtv_psi_table_transport *); + + length += transport_loop_len; + + desc_loop_len = vidtv_psi_desc_comp_loop_len(t->descriptor); + vidtv_psi_set_desc_loop_len(&t->bitfield, desc_loop_len, 12); + + length += desc_loop_len; + + t = t->next; + } + + // Actually sets the transport stream loop len, maybe rename this function later + vidtv_psi_set_desc_loop_len(&nit->bitfield2, transport_loop_len, 12); + length += CRC_SIZE_IN_BYTES; + + vidtv_psi_set_sec_len(&nit->header, length); +} + +struct vidtv_psi_table_nit +*vidtv_psi_nit_table_init(u16 network_id, + u16 transport_stream_id, + char *network_name, + struct vidtv_psi_desc_service_list_entry *service_list) +{ + struct vidtv_psi_table_transport *transport; + struct vidtv_psi_table_nit *nit; + const u16 SYNTAX = 0x1; + const u16 ONES = 0x03; + const u16 ONE = 0x1; + + nit = kzalloc(sizeof(*nit), GFP_KERNEL); + if (!nit) + return NULL; + + transport = kzalloc(sizeof(*transport), GFP_KERNEL); + if (!transport) + goto free_nit; + + nit->header.table_id = 0x40; // ACTUAL_NETWORK + + nit->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ONE << 14) | (ONES << 12)); + + nit->header.id = cpu_to_be16(network_id); + nit->header.current_next = ONE; + + nit->header.version = 0x1f; + + nit->header.one2 = ONES; + nit->header.section_id = 0; + nit->header.last_section = 0; + + nit->bitfield = cpu_to_be16(0xf); + nit->bitfield2 = cpu_to_be16(0xf); + + nit->descriptor = (struct vidtv_psi_desc *) + vidtv_psi_network_name_desc_init(NULL, network_name); + if (!nit->descriptor) + goto free_transport; + + transport->transport_id = cpu_to_be16(transport_stream_id); + transport->network_id = cpu_to_be16(network_id); + transport->bitfield = cpu_to_be16(0xf); + transport->descriptor = (struct vidtv_psi_desc *) + vidtv_psi_service_list_desc_init(NULL, service_list); + if (!transport->descriptor) + goto free_nit_desc; + + nit->transport = transport; + + vidtv_psi_nit_table_update_sec_len(nit); + + return nit; + +free_nit_desc: + vidtv_psi_desc_destroy((struct vidtv_psi_desc *)nit->descriptor); + +free_transport: + kfree(transport); +free_nit: + kfree(nit); + return NULL; +} + +u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args *args) +{ + struct header_write_args h_args = { + .dest_buf = args->buf, + .dest_offset = args->offset, + .h = &args->nit->header, + .pid = VIDTV_NIT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct psi_write_args psi_args = { + .dest_buf = args->buf, + .from = &args->nit->bitfield, + .len = sizeof_field(struct vidtv_psi_table_nit, bitfield), + .pid = VIDTV_NIT_PID, + .new_psi_section = false, + .is_crc = false, + .dest_buf_sz = args->buf_sz, + }; + struct desc_write_args d_args = { + .dest_buf = args->buf, + .pid = VIDTV_NIT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct crc32_write_args c_args = { + .dest_buf = args->buf, + .pid = VIDTV_NIT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct vidtv_psi_desc *table_descriptor = args->nit->descriptor; + struct vidtv_psi_table_transport *transport = args->nit->transport; + struct vidtv_psi_desc *transport_descriptor; + u32 crc = INITIAL_CRC; + u32 nbytes = 0; + + vidtv_psi_nit_table_update_sec_len(args->nit); + + h_args.continuity_counter = args->continuity_counter; + h_args.crc = &crc; + + nbytes += vidtv_psi_table_header_write_into(&h_args); + + /* write the bitfield */ + + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; + psi_args.crc = &crc; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + + while (table_descriptor) { + /* write the descriptors, if any */ + d_args.dest_offset = args->offset + nbytes; + d_args.desc = table_descriptor; + d_args.continuity_counter = args->continuity_counter; + d_args.crc = &crc; + + nbytes += vidtv_psi_desc_write_into(&d_args); + + table_descriptor = table_descriptor->next; + } + + /* write the second bitfield */ + psi_args.from = &args->nit->bitfield2; + psi_args.len = sizeof_field(struct vidtv_psi_table_nit, bitfield2); + psi_args.dest_offset = args->offset + nbytes; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + + psi_args.len = sizeof_field(struct vidtv_psi_table_transport, transport_id) + + sizeof_field(struct vidtv_psi_table_transport, network_id) + + sizeof_field(struct vidtv_psi_table_transport, bitfield); + while (transport) { + /* write the transport sections, if any */ + psi_args.from = transport; + psi_args.dest_offset = args->offset + nbytes; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + + transport_descriptor = transport->descriptor; + + while (transport_descriptor) { + /* write the transport descriptors, if any */ + d_args.dest_offset = args->offset + nbytes; + d_args.desc = transport_descriptor; + d_args.continuity_counter = args->continuity_counter; + d_args.crc = &crc; + + nbytes += vidtv_psi_desc_write_into(&d_args); + + transport_descriptor = transport_descriptor->next; + } + + transport = transport->next; + } + + c_args.dest_offset = args->offset + nbytes; + c_args.crc = cpu_to_be32(crc); + c_args.continuity_counter = args->continuity_counter; + + /* Write the CRC32 at the end */ + nbytes += table_section_crc32_write_into(&c_args); + + return nbytes; +} + +static void vidtv_psi_transport_destroy(struct vidtv_psi_table_transport *t) +{ + struct vidtv_psi_table_transport *tmp_t = NULL; + struct vidtv_psi_table_transport *curr_t = t; + + while (curr_t) { + tmp_t = curr_t; + curr_t = curr_t->next; + vidtv_psi_desc_destroy(tmp_t->descriptor); + kfree(tmp_t); + } +} + +void vidtv_psi_nit_table_destroy(struct vidtv_psi_table_nit *nit) +{ + vidtv_psi_desc_destroy(nit->descriptor); + vidtv_psi_transport_destroy(nit->transport); + kfree(nit); +} + +void vidtv_psi_eit_table_update_sec_len(struct vidtv_psi_table_eit *eit) +{ + struct vidtv_psi_table_eit_event *e = eit->event; + u16 desc_loop_len; + u16 length = 0; + + /* + * from immediately after 'section_length' until + * 'last_table_id' + */ + length += EIT_LEN_UNTIL_LAST_TABLE_ID; + + while (e) { + /* skip both pointers at the end */ + length += sizeof(struct vidtv_psi_table_eit_event) - + sizeof(struct vidtv_psi_desc *) - + sizeof(struct vidtv_psi_table_eit_event *); + + desc_loop_len = vidtv_psi_desc_comp_loop_len(e->descriptor); + vidtv_psi_set_desc_loop_len(&e->bitfield, desc_loop_len, 12); + + length += desc_loop_len; + + e = e->next; + } + + length += CRC_SIZE_IN_BYTES; + + vidtv_psi_set_sec_len(&eit->header, length); +} + +void vidtv_psi_eit_event_assign(struct vidtv_psi_table_eit *eit, + struct vidtv_psi_table_eit_event *e) +{ + do { + if (e == eit->event) + return; + + eit->event = e; + vidtv_psi_eit_table_update_sec_len(eit); + + e = NULL; + } while (vidtv_psi_get_sec_len(&eit->header) > EIT_MAX_SECTION_LEN); + + vidtv_psi_update_version_num(&eit->header); +} + +struct vidtv_psi_table_eit +*vidtv_psi_eit_table_init(u16 network_id, + u16 transport_stream_id, + __be16 service_id) +{ + struct vidtv_psi_table_eit *eit; + const u16 SYNTAX = 0x1; + const u16 ONE = 0x1; + const u16 ONES = 0x03; + + eit = kzalloc(sizeof(*eit), GFP_KERNEL); + if (!eit) + return NULL; + + eit->header.table_id = 0x4e; //actual_transport_stream: present/following + + eit->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ONE << 14) | (ONES << 12)); + + eit->header.id = service_id; + eit->header.current_next = ONE; + + eit->header.version = 0x1f; + + eit->header.one2 = ONES; + eit->header.section_id = 0; + eit->header.last_section = 0; + + eit->transport_id = cpu_to_be16(transport_stream_id); + eit->network_id = cpu_to_be16(network_id); + + eit->last_segment = eit->header.last_section; /* not implemented */ + eit->last_table_id = eit->header.table_id; /* not implemented */ + + vidtv_psi_eit_table_update_sec_len(eit); + + return eit; +} + +u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args *args) +{ + struct header_write_args h_args = { + .dest_buf = args->buf, + .dest_offset = args->offset, + .h = &args->eit->header, + .pid = VIDTV_EIT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct psi_write_args psi_args = { + .dest_buf = args->buf, + .len = sizeof_field(struct vidtv_psi_table_eit, transport_id) + + sizeof_field(struct vidtv_psi_table_eit, network_id) + + sizeof_field(struct vidtv_psi_table_eit, last_segment) + + sizeof_field(struct vidtv_psi_table_eit, last_table_id), + .pid = VIDTV_EIT_PID, + .new_psi_section = false, + .is_crc = false, + .dest_buf_sz = args->buf_sz, + }; + struct desc_write_args d_args = { + .dest_buf = args->buf, + .pid = VIDTV_EIT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct crc32_write_args c_args = { + .dest_buf = args->buf, + .pid = VIDTV_EIT_PID, + .dest_buf_sz = args->buf_sz, + }; + struct vidtv_psi_table_eit_event *event = args->eit->event; + struct vidtv_psi_desc *event_descriptor; + u32 crc = INITIAL_CRC; + u32 nbytes = 0; + + vidtv_psi_eit_table_update_sec_len(args->eit); + + h_args.continuity_counter = args->continuity_counter; + h_args.crc = &crc; + + nbytes += vidtv_psi_table_header_write_into(&h_args); + + psi_args.from = &args->eit->transport_id; + psi_args.dest_offset = args->offset + nbytes; + psi_args.continuity_counter = args->continuity_counter; + psi_args.crc = &crc; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + + /* skip both pointers at the end */ + psi_args.len = sizeof(struct vidtv_psi_table_eit_event) - + sizeof(struct vidtv_psi_desc *) - + sizeof(struct vidtv_psi_table_eit_event *); + while (event) { + /* copy the events, if any */ + psi_args.from = event; + psi_args.dest_offset = args->offset + nbytes; + + nbytes += vidtv_psi_ts_psi_write_into(&psi_args); + + event_descriptor = event->descriptor; + + while (event_descriptor) { + /* copy the event descriptors, if any */ + d_args.dest_offset = args->offset + nbytes; + d_args.desc = event_descriptor; + d_args.continuity_counter = args->continuity_counter; + d_args.crc = &crc; + + nbytes += vidtv_psi_desc_write_into(&d_args); + + event_descriptor = event_descriptor->next; + } + + event = event->next; + } + + c_args.dest_offset = args->offset + nbytes; + c_args.crc = cpu_to_be32(crc); + c_args.continuity_counter = args->continuity_counter; + + /* Write the CRC at the end */ + nbytes += table_section_crc32_write_into(&c_args); + + return nbytes; +} + +struct vidtv_psi_table_eit_event +*vidtv_psi_eit_event_init(struct vidtv_psi_table_eit_event *head, u16 event_id) +{ + const u8 DURATION[] = {0x23, 0x59, 0x59}; /* BCD encoded */ + struct vidtv_psi_table_eit_event *e; + struct timespec64 ts; + struct tm time; + int mjd, l; + __be16 mjd_be; + + e = kzalloc(sizeof(*e), GFP_KERNEL); + if (!e) + return NULL; + + e->event_id = cpu_to_be16(event_id); + + ts = ktime_to_timespec64(ktime_get_real()); + time64_to_tm(ts.tv_sec, 0, &time); + + /* Convert date to Modified Julian Date - per EN 300 468 Annex C */ + if (time.tm_mon < 2) + l = 1; + else + l = 0; + + mjd = 14956 + time.tm_mday; + mjd += (time.tm_year - l) * 36525 / 100; + mjd += (time.tm_mon + 2 + l * 12) * 306001 / 10000; + mjd_be = cpu_to_be16(mjd); + + /* + * Store MJD and hour/min/sec to the event. + * + * Let's make the event to start on a full hour + */ + memcpy(e->start_time, &mjd_be, sizeof(mjd_be)); + e->start_time[2] = bin2bcd(time.tm_hour); + e->start_time[3] = 0; + e->start_time[4] = 0; + + /* + * TODO: for now, the event will last for a day. Should be + * enough for testing purposes, but if one runs the driver + * for more than that, the current event will become invalid. + * So, we need a better code here in order to change the start + * time once the event expires. + */ + memcpy(e->duration, DURATION, sizeof(e->duration)); + + e->bitfield = cpu_to_be16(RUNNING << 13); + + if (head) { + while (head->next) + head = head->next; + + head->next = e; + } + + return e; +} + +void vidtv_psi_eit_event_destroy(struct vidtv_psi_table_eit_event *e) +{ + struct vidtv_psi_table_eit_event *tmp_e = NULL; + struct vidtv_psi_table_eit_event *curr_e = e; + + while (curr_e) { + tmp_e = curr_e; + curr_e = curr_e->next; + vidtv_psi_desc_destroy(tmp_e->descriptor); + kfree(tmp_e); + } +} + +void vidtv_psi_eit_table_destroy(struct vidtv_psi_table_eit *eit) +{ + vidtv_psi_eit_event_destroy(eit->event); + kfree(eit); +} diff --git a/drivers/media/test-drivers/vidtv/vidtv_psi.h b/drivers/media/test-drivers/vidtv/vidtv_psi.h index 3f962cc78278..fdc825e54138 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_psi.h +++ b/drivers/media/test-drivers/vidtv/vidtv_psi.h @@ -6,10 +6,6 @@ * technically be broken into one or more sections, we do not do this here, * hence 'table' and 'section' are interchangeable for vidtv. * - * This code currently supports three tables: PAT, PMT and SDT. These are the - * bare minimum to get userspace to recognize our MPEG transport stream. It can - * be extended to support more PSI tables in the future. - * * Copyright (C) 2020 Daniel W. S. Almeida */ @@ -17,7 +13,6 @@ #define VIDTV_PSI_H #include <linux/types.h> -#include <asm/byteorder.h> /* * all section lengths start immediately after the 'section_length' field @@ -27,20 +22,28 @@ #define PAT_LEN_UNTIL_LAST_SECTION_NUMBER 5 #define PMT_LEN_UNTIL_PROGRAM_INFO_LENGTH 9 #define SDT_LEN_UNTIL_RESERVED_FOR_FUTURE_USE 8 +#define NIT_LEN_UNTIL_NETWORK_DESCRIPTOR_LEN 7 +#define EIT_LEN_UNTIL_LAST_TABLE_ID 11 #define MAX_SECTION_LEN 1021 +#define EIT_MAX_SECTION_LEN 4093 /* see ETSI 300 468 v.1.10.1 p. 26 */ #define VIDTV_PAT_PID 0 /* mandated by the specs */ #define VIDTV_SDT_PID 0x0011 /* mandated by the specs */ +#define VIDTV_NIT_PID 0x0010 /* mandated by the specs */ +#define VIDTV_EIT_PID 0x0012 /*mandated by the specs */ enum vidtv_psi_descriptors { REGISTRATION_DESCRIPTOR = 0x05, /* See ISO/IEC 13818-1 section 2.6.8 */ + NETWORK_NAME_DESCRIPTOR = 0x40, /* See ETSI EN 300 468 section 6.2.27 */ + SERVICE_LIST_DESCRIPTOR = 0x41, /* See ETSI EN 300 468 section 6.2.35 */ SERVICE_DESCRIPTOR = 0x48, /* See ETSI EN 300 468 section 6.2.33 */ + SHORT_EVENT_DESCRIPTOR = 0x4d, /* See ETSI EN 300 468 section 6.2.37 */ }; enum vidtv_psi_stream_types { STREAM_PRIVATE_DATA = 0x06, /* see ISO/IEC 13818-1 2000 p. 48 */ }; -/** +/* * struct vidtv_psi_desc - A generic PSI descriptor type. * The descriptor length is an 8-bit field specifying the total number of bytes of the data portion * of the descriptor following the byte defining the value of this field. @@ -52,7 +55,7 @@ struct vidtv_psi_desc { u8 data[]; } __packed; -/** +/* * struct vidtv_psi_desc_service - Service descriptor. * See ETSI EN 300 468 section 6.2.33. */ @@ -68,7 +71,7 @@ struct vidtv_psi_desc_service { char *service_name; } __packed; -/** +/* * struct vidtv_psi_desc_registration - A registration descriptor. * See ISO/IEC 13818-1 section 2.6.8 */ @@ -90,7 +93,56 @@ struct vidtv_psi_desc_registration { u8 additional_identification_info[]; } __packed; -/** +/* + * struct vidtv_psi_desc_network_name - A network name descriptor + * see ETSI EN 300 468 v1.15.1 section 6.2.27 + */ +struct vidtv_psi_desc_network_name { + struct vidtv_psi_desc *next; + u8 type; + u8 length; + char *network_name; +} __packed; + +struct vidtv_psi_desc_service_list_entry { + __be16 service_id; + u8 service_type; + struct vidtv_psi_desc_service_list_entry *next; +} __packed; + +/* + * struct vidtv_psi_desc_service_list - A service list descriptor + * see ETSI EN 300 468 v1.15.1 section 6.2.35 + */ +struct vidtv_psi_desc_service_list { + struct vidtv_psi_desc *next; + u8 type; + u8 length; + struct vidtv_psi_desc_service_list_entry *service_list; +} __packed; + +/* + * struct vidtv_psi_desc_short_event - A short event descriptor + * see ETSI EN 300 468 v1.15.1 section 6.2.37 + */ +struct vidtv_psi_desc_short_event { + struct vidtv_psi_desc *next; + u8 type; + u8 length; + char *iso_language_code; + u8 event_name_len; + char *event_name; + u8 text_len; + char *text; +} __packed; + +struct vidtv_psi_desc_short_event +*vidtv_psi_short_event_desc_init(struct vidtv_psi_desc *head, + char *iso_language_code, + char *event_name, + char *text); + +/* * struct vidtv_psi_table_header - A header that is present for all PSI tables. */ struct vidtv_psi_table_header { @@ -106,7 +158,7 @@ struct vidtv_psi_table_header { u8 last_section; /* last_section_number */ } __packed; -/** +/* * struct vidtv_psi_table_pat_program - A single program in the PAT * See ISO/IEC 13818-1 : 2000 p.43 */ @@ -116,17 +168,18 @@ struct vidtv_psi_table_pat_program { struct vidtv_psi_table_pat_program *next; } __packed; -/** +/* * struct vidtv_psi_table_pat - The Program Allocation Table (PAT) * See ISO/IEC 13818-1 : 2000 p.43 */ struct vidtv_psi_table_pat { struct vidtv_psi_table_header header; - u16 programs; /* Included by libdvbv5, not part of the table and not actually serialized */ + u16 num_pat; + u16 num_pmt; struct vidtv_psi_table_pat_program *program; } __packed; -/** +/* * struct vidtv_psi_table_sdt_service - Represents a service in the SDT. * see ETSI EN 300 468 v1.15.1 section 5.2.3. */ @@ -140,7 +193,7 @@ struct vidtv_psi_table_sdt_service { struct vidtv_psi_table_sdt_service *next; } __packed; -/** +/* * struct vidtv_psi_table_sdt - Represents the Service Description Table * see ETSI EN 300 468 v1.15.1 section 5.2.3. */ @@ -152,7 +205,7 @@ struct vidtv_psi_table_sdt { struct vidtv_psi_table_sdt_service *service; } __packed; -/** +/* * enum service_running_status - Status of a SDT service. * see ETSI EN 300 468 v1.15.1 section 5.2.3 table 6. */ @@ -160,16 +213,17 @@ enum service_running_status { RUNNING = 0x4, }; -/** +/* * enum service_type - The type of a SDT service. * see ETSI EN 300 468 v1.15.1 section 6.2.33, table 81. */ enum service_type { /* see ETSI EN 300 468 v1.15.1 p. 77 */ DIGITAL_TELEVISION_SERVICE = 0x1, + DIGITAL_RADIO_SOUND_SERVICE = 0X2, }; -/** +/* * struct vidtv_psi_table_pmt_stream - A single stream in the PMT. * See ISO/IEC 13818-1 : 2000 p.46. */ @@ -181,7 +235,7 @@ struct vidtv_psi_table_pmt_stream { struct vidtv_psi_table_pmt_stream *next; } __packed; -/** +/* * struct vidtv_psi_table_pmt - The Program Map Table (PMT). * See ISO/IEC 13818-1 : 2000 p.46. */ @@ -290,6 +344,13 @@ struct vidtv_psi_desc_registration u8 *additional_ident_info, u32 additional_info_len); +struct vidtv_psi_desc_network_name +*vidtv_psi_network_name_desc_init(struct vidtv_psi_desc *head, char *network_name); + +struct vidtv_psi_desc_service_list +*vidtv_psi_service_list_desc_init(struct vidtv_psi_desc *head, + struct vidtv_psi_desc_service_list_entry *entry); + struct vidtv_psi_table_pat_program *vidtv_psi_pat_program_init(struct vidtv_psi_table_pat_program *head, u16 service_id, @@ -305,11 +366,14 @@ struct vidtv_psi_table_pat *vidtv_psi_pat_table_init(u16 transport_stream_id); struct vidtv_psi_table_pmt *vidtv_psi_pmt_table_init(u16 program_number, u16 pcr_pid); -struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 transport_stream_id); +struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 network_id, + u16 transport_stream_id); struct vidtv_psi_table_sdt_service* vidtv_psi_sdt_service_init(struct vidtv_psi_table_sdt_service *head, - u16 service_id); + u16 service_id, + bool eit_schedule, + bool eit_present_following); void vidtv_psi_desc_destroy(struct vidtv_psi_desc *desc); @@ -356,7 +420,7 @@ void vidtv_psi_desc_assign(struct vidtv_psi_desc **to, struct vidtv_psi_desc *desc); /** - * vidtv_psi_pmt_desc_assign - Assigns a descriptor loop at some point in a PMT section. + * vidtv_pmt_desc_assign - Assigns a descriptor loop at some point in a PMT section. * @pmt: The PMT section that will contain the descriptor loop * @to: Where in the PMT to assign this descriptor loop to * @desc: The descriptor loop that will be assigned. @@ -370,7 +434,7 @@ void vidtv_pmt_desc_assign(struct vidtv_psi_table_pmt *pmt, struct vidtv_psi_desc *desc); /** - * vidtv_psi_sdt_desc_assign - Assigns a descriptor loop at some point in a SDT. + * vidtv_sdt_desc_assign - Assigns a descriptor loop at some point in a SDT. * @sdt: The SDT that will contain the descriptor loop * @to: Where in the PMT to assign this descriptor loop to * @desc: The descriptor loop that will be assigned. @@ -410,10 +474,9 @@ void vidtv_psi_pmt_stream_assign(struct vidtv_psi_table_pmt *pmt, struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc); /** - * vidtv_psi_create_sec_for_each_pat_entry - Create a PMT section for each + * vidtv_psi_pmt_create_sec_for_each_pat_entry - Create a PMT section for each * program found in the PAT * @pat: The PAT to look for programs. - * @s: The stream loop (one or more streams) * @pcr_pid: packet ID for the PCR to be used for the program described in this * PMT section */ @@ -492,7 +555,7 @@ struct vidtv_psi_pat_write_args { * equal to the size of the PAT, since more space is needed for TS headers during TS * encapsulation. */ -u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args args); +u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args *args); /** * struct vidtv_psi_sdt_write_args - Arguments for writing a SDT table @@ -524,16 +587,18 @@ struct vidtv_psi_sdt_write_args { * equal to the size of the SDT, since more space is needed for TS headers during TS * encapsulation. */ -u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args); +u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args *args); /** * struct vidtv_psi_pmt_write_args - Arguments for writing a PMT section * @buf: The destination buffer. * @offset: The offset into the destination buffer. * @pmt: A pointer to the PMT. + * @pid: Program ID * @buf_sz: The size of the destination buffer. * @continuity_counter: A pointer to the CC. Incremented on every new packet. - * + * @pcr_pid: The TS PID used for the PSI packets. All channels will share the + * same PCR. */ struct vidtv_psi_pmt_write_args { char *buf; @@ -557,7 +622,7 @@ struct vidtv_psi_pmt_write_args { * equal to the size of the PMT section, since more space is needed for TS headers * during TS encapsulation. */ -u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args); +u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args *args); /** * vidtv_psi_find_pmt_sec - Finds the PMT section for 'program_num' @@ -574,4 +639,171 @@ struct vidtv_psi_table_pmt *vidtv_psi_find_pmt_sec(struct vidtv_psi_table_pmt ** u16 vidtv_psi_get_pat_program_pid(struct vidtv_psi_table_pat_program *p); u16 vidtv_psi_pmt_stream_get_elem_pid(struct vidtv_psi_table_pmt_stream *s); +/** + * struct vidtv_psi_table_transport - A entry in the TS loop for the NIT and/or other tables. + * See ETSI 300 468 section 5.2.1 + * @transport_id: The TS ID being described + * @network_id: The network_id that contains the TS ID + * @bitfield: Contains the descriptor loop length + * @descriptor: A descriptor loop + * @next: Pointer to the next entry + * + */ +struct vidtv_psi_table_transport { + __be16 transport_id; + __be16 network_id; + __be16 bitfield; /* desc_len: 12, reserved: 4 */ + struct vidtv_psi_desc *descriptor; + struct vidtv_psi_table_transport *next; +} __packed; + +/** + * struct vidtv_psi_table_nit - A Network Information Table (NIT). See ETSI 300 + * 468 section 5.2.1 + * @header: A PSI table header + * @bitfield: Contains the network descriptor length + * @descriptor: A descriptor loop describing the network + * @bitfield2: Contains the transport stream loop length + * @transport: The transport stream loop + * + */ +struct vidtv_psi_table_nit { + struct vidtv_psi_table_header header; + __be16 bitfield; /* network_desc_len: 12, reserved:4 */ + struct vidtv_psi_desc *descriptor; + __be16 bitfield2; /* ts_loop_len: 12, reserved: 4 */ + struct vidtv_psi_table_transport *transport; +} __packed; + +struct vidtv_psi_table_nit +*vidtv_psi_nit_table_init(u16 network_id, + u16 transport_stream_id, + char *network_name, + struct vidtv_psi_desc_service_list_entry *service_list); + +/** + * struct vidtv_psi_nit_write_args - Arguments for writing a NIT section + * @buf: The destination buffer. + * @offset: The offset into the destination buffer. + * @nit: A pointer to the NIT + * @buf_sz: The size of the destination buffer. + * @continuity_counter: A pointer to the CC. Incremented on every new packet. + * + */ +struct vidtv_psi_nit_write_args { + char *buf; + u32 offset; + struct vidtv_psi_table_nit *nit; + u32 buf_sz; + u8 *continuity_counter; +}; + +/** + * vidtv_psi_nit_write_into - Write NIT as MPEG-TS packets into a buffer. + * @args: an instance of struct vidtv_psi_nit_write_args + * + * This function writes the MPEG TS packets for a NIT table into a buffer. + * Calling code will usually generate the NIT via a call to its init function + * and thus is responsible for freeing it. + * + * Return: The number of bytes written into the buffer. This is NOT + * equal to the size of the NIT, since more space is needed for TS headers during TS + * encapsulation. + */ +u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args *args); + +void vidtv_psi_nit_table_destroy(struct vidtv_psi_table_nit *nit); + +/* + * struct vidtv_psi_desc_short_event - A short event descriptor + * see ETSI EN 300 468 v1.15.1 section 6.2.37 + */ +struct vidtv_psi_table_eit_event { + __be16 event_id; + u8 start_time[5]; + u8 duration[3]; + __be16 bitfield; /* desc_length: 12, free_CA_mode: 1, running_status: 1 */ + struct vidtv_psi_desc *descriptor; + struct vidtv_psi_table_eit_event *next; +} __packed; + +/* + * struct vidtv_psi_table_eit - A Event Information Table (EIT) + * See ETSI 300 468 section 5.2.4 + */ +struct vidtv_psi_table_eit { + struct vidtv_psi_table_header header; + __be16 transport_id; + __be16 network_id; + u8 last_segment; + u8 last_table_id; + struct vidtv_psi_table_eit_event *event; +} __packed; + +struct vidtv_psi_table_eit +*vidtv_psi_eit_table_init(u16 network_id, + u16 transport_stream_id, + __be16 service_id); + +/** + * struct vidtv_psi_eit_write_args - Arguments for writing an EIT section + * @buf: The destination buffer. + * @offset: The offset into the destination buffer. + * @eit: A pointer to the EIT + * @buf_sz: The size of the destination buffer. + * @continuity_counter: A pointer to the CC. Incremented on every new packet. + * + */ +struct vidtv_psi_eit_write_args { + char *buf; + u32 offset; + struct vidtv_psi_table_eit *eit; + u32 buf_sz; + u8 *continuity_counter; +}; + +/** + * vidtv_psi_eit_write_into - Write EIT as MPEG-TS packets into a buffer. + * @args: an instance of struct vidtv_psi_nit_write_args + * + * This function writes the MPEG TS packets for a EIT table into a buffer. + * Calling code will usually generate the EIT via a call to its init function + * and thus is responsible for freeing it. + * + * Return: The number of bytes written into the buffer. This is NOT + * equal to the size of the EIT, since more space is needed for TS headers during TS + * encapsulation. + */ +u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args *args); + +void vidtv_psi_eit_table_destroy(struct vidtv_psi_table_eit *eit); + +/** + * vidtv_psi_eit_table_update_sec_len - Recompute and update the EIT section length. + * @eit: The EIT whose length is to be updated. + * + * This will traverse the table and accumulate the length of its components, + * which is then used to replace the 'section_length' field. + * + * If section_length > EIT_MAX_SECTION_LEN, the operation fails. + */ +void vidtv_psi_eit_table_update_sec_len(struct vidtv_psi_table_eit *eit); + +/** + * vidtv_psi_eit_event_assign - Assigns the event loop to the EIT. + * @eit: The EIT to assign to. + * @e: The event loop + * + * This will free the previous event loop in the table. + * This will assign ownership of the stream loop to the table, i.e. the table + * will free this stream loop when a call to its destroy function is made. + */ +void vidtv_psi_eit_event_assign(struct vidtv_psi_table_eit *eit, + struct vidtv_psi_table_eit_event *e); + +struct vidtv_psi_table_eit_event +*vidtv_psi_eit_event_init(struct vidtv_psi_table_eit_event *head, u16 event_id); + +void vidtv_psi_eit_event_destroy(struct vidtv_psi_table_eit_event *e); + #endif // VIDTV_PSI_H diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.c b/drivers/media/test-drivers/vidtv/vidtv_s302m.c index a447ccbd68d5..d79b65854627 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.c +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.c @@ -17,23 +17,22 @@ #define pr_fmt(fmt) KBUILD_MODNAME ":%s, %d: " fmt, __func__, __LINE__ -#include <linux/types.h> -#include <linux/slab.h> +#include <linux/bug.h> #include <linux/crc32.h> -#include <linux/vmalloc.h> -#include <linux/string.h> -#include <linux/kernel.h> +#include <linux/fixp-arith.h> #include <linux/jiffies.h> +#include <linux/kernel.h> +#include <linux/math64.h> #include <linux/printk.h> #include <linux/ratelimit.h> -#include <linux/fixp-arith.h> - -#include <linux/math64.h> -#include <asm/byteorder.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/vmalloc.h> -#include "vidtv_s302m.h" -#include "vidtv_encoder.h" #include "vidtv_common.h" +#include "vidtv_encoder.h" +#include "vidtv_s302m.h" #define S302M_SAMPLING_RATE_HZ 48000 #define PES_PRIVATE_STREAM_1 0xbd /* PES: private_stream_1 */ @@ -79,8 +78,9 @@ struct tone_duration { int duration; }; -#define COMPASS 120 /* beats per minute (Allegro) */ -static const struct tone_duration beethoven_5th_symphony[] = { +#define COMPASS 100 /* beats per minute */ +static const struct tone_duration beethoven_fur_elise[] = { + { NOTE_SILENT, 512}, { NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_B_5, 128}, { NOTE_D_6, 128}, { NOTE_C_6, 128}, { NOTE_A_3, 128}, @@ -121,31 +121,36 @@ static const struct tone_duration beethoven_5th_symphony[] = { { NOTE_E_5, 128}, { NOTE_D_5, 128}, { NOTE_A_3, 128}, { NOTE_E_4, 128}, { NOTE_A_4, 128}, { NOTE_E_4, 128}, { NOTE_D_5, 128}, { NOTE_C_5, 128}, { NOTE_E_3, 128}, - { NOTE_E_4, 128}, { NOTE_E_5, 255}, { NOTE_E_6, 128}, - { NOTE_E_5, 128}, { NOTE_E_6, 128}, { NOTE_E_5, 255}, + { NOTE_E_4, 128}, { NOTE_E_5, 128}, { NOTE_E_5, 128}, + { NOTE_E_6, 128}, { NOTE_E_5, 128}, { NOTE_E_6, 128}, + { NOTE_E_5, 128}, { NOTE_E_5, 128}, { NOTE_DS_5, 128}, + { NOTE_E_5, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_DS_5, 128}, { NOTE_E_5, 128}, { NOTE_DS_6, 128}, - { NOTE_E_6, 128}, { NOTE_DS_5, 128}, { NOTE_E_5, 128}, - { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, - { NOTE_B_5, 128}, { NOTE_D_6, 128}, { NOTE_C_6, 128}, - { NOTE_A_3, 128}, { NOTE_E_4, 128}, { NOTE_A_4, 128}, - { NOTE_C_5, 128}, { NOTE_E_5, 128}, { NOTE_A_5, 128}, - { NOTE_E_3, 128}, { NOTE_E_4, 128}, { NOTE_GS_4, 128}, - { NOTE_E_5, 128}, { NOTE_GS_5, 128}, { NOTE_B_5, 128}, - { NOTE_A_3, 128}, { NOTE_E_4, 128}, { NOTE_A_4, 128}, - { NOTE_E_5, 128}, { NOTE_E_6, 128}, { NOTE_DS_6, 128}, + { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_B_5, 128}, + { NOTE_D_6, 128}, { NOTE_C_6, 128}, { NOTE_A_3, 128}, + { NOTE_E_4, 128}, { NOTE_A_4, 128}, { NOTE_C_5, 128}, + { NOTE_E_5, 128}, { NOTE_A_5, 128}, { NOTE_E_3, 128}, + { NOTE_E_4, 128}, { NOTE_GS_4, 128}, { NOTE_E_5, 128}, + { NOTE_GS_5, 128}, { NOTE_B_5, 128}, { NOTE_A_3, 128}, + { NOTE_E_4, 128}, { NOTE_A_4, 128}, { NOTE_E_5, 128}, { NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128}, - { NOTE_B_5, 128}, { NOTE_D_6, 128}, { NOTE_C_6, 128}, - { NOTE_A_3, 128}, { NOTE_E_4, 128}, { NOTE_A_4, 128}, - { NOTE_C_5, 128}, { NOTE_E_5, 128}, { NOTE_A_5, 128}, - { NOTE_E_3, 128}, { NOTE_E_4, 128}, { NOTE_GS_4, 128}, - { NOTE_E_5, 128}, { NOTE_C_6, 128}, { NOTE_B_5, 128}, - { NOTE_C_5, 255}, { NOTE_C_5, 255}, { NOTE_SILENT, 512}, + { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_B_5, 128}, + { NOTE_D_6, 128}, { NOTE_C_6, 128}, { NOTE_A_3, 128}, + { NOTE_E_4, 128}, { NOTE_A_4, 128}, { NOTE_C_5, 128}, + { NOTE_E_5, 128}, { NOTE_A_5, 128}, { NOTE_E_3, 128}, + { NOTE_E_4, 128}, { NOTE_GS_4, 128}, { NOTE_E_5, 128}, + { NOTE_C_6, 128}, { NOTE_B_5, 128}, { NOTE_A_5, 512}, + { NOTE_SILENT, 256}, }; static struct vidtv_access_unit *vidtv_s302m_access_unit_init(struct vidtv_access_unit *head) { - struct vidtv_access_unit *au = kzalloc(sizeof(*au), GFP_KERNEL); + struct vidtv_access_unit *au; + + au = kzalloc(sizeof(*au), GFP_KERNEL); + if (!au) + return NULL; if (head) { while (head->next) @@ -196,10 +201,10 @@ static void vidtv_s302m_alloc_au(struct vidtv_encoder *e) static void vidtv_s302m_compute_sample_count_from_video(struct vidtv_encoder *e) { - struct vidtv_access_unit *au = e->access_units; struct vidtv_access_unit *sync_au = e->sync->access_units; - u32 vau_duration_usecs; + struct vidtv_access_unit *au = e->access_units; u32 sample_duration_usecs; + u32 vau_duration_usecs; u32 s; vau_duration_usecs = USEC_PER_SEC / e->sync->sampling_rate_hz; @@ -230,36 +235,32 @@ static u16 vidtv_s302m_get_sample(struct vidtv_encoder *e) { u16 sample; int pos; + struct vidtv_s302m_ctx *ctx = e->ctx; if (!e->src_buf) { /* * Simple tone generator: play the tones at the - * beethoven_5th_symphony array. + * beethoven_fur_elise array. */ - if (e->last_duration <= 0) { - if (e->src_buf_offset >= ARRAY_SIZE(beethoven_5th_symphony)) + if (ctx->last_duration <= 0) { + if (e->src_buf_offset >= ARRAY_SIZE(beethoven_fur_elise)) e->src_buf_offset = 0; - e->last_tone = beethoven_5th_symphony[e->src_buf_offset].note; - e->last_duration = beethoven_5th_symphony[e->src_buf_offset].duration * S302M_SAMPLING_RATE_HZ / COMPASS / 5; + ctx->last_tone = beethoven_fur_elise[e->src_buf_offset].note; + ctx->last_duration = beethoven_fur_elise[e->src_buf_offset].duration * + S302M_SAMPLING_RATE_HZ / COMPASS / 5; e->src_buf_offset++; - e->note_offset = 0; + ctx->note_offset = 0; } else { - e->last_duration--; + ctx->last_duration--; } - /* Handle silent */ - if (!e->last_tone) { - e->src_buf_offset = 0; + /* Handle pause notes */ + if (!ctx->last_tone) return 0x8000; - } - - pos = (2 * PI * e->note_offset * e->last_tone / S302M_SAMPLING_RATE_HZ); - if (pos == 360) - e->note_offset = 0; - else - e->note_offset++; + pos = (2 * PI * ctx->note_offset * ctx->last_tone) / S302M_SAMPLING_RATE_HZ; + ctx->note_offset++; return (fixp_sin32(pos % (2 * PI)) >> 16) + 0x8000; } @@ -289,9 +290,9 @@ static u16 vidtv_s302m_get_sample(struct vidtv_encoder *e) static u32 vidtv_s302m_write_frame(struct vidtv_encoder *e, u16 sample) { - u32 nbytes = 0; - struct vidtv_s302m_frame_16 f = {}; struct vidtv_s302m_ctx *ctx = e->ctx; + struct vidtv_s302m_frame_16 f = {}; + u32 nbytes = 0; /* from ffmpeg: see s302enc.c */ @@ -388,6 +389,8 @@ static void vidtv_s302m_write_frames(struct vidtv_encoder *e) static void *vidtv_s302m_encode(struct vidtv_encoder *e) { + struct vidtv_s302m_ctx *ctx = e->ctx; + /* * According to SMPTE 302M, an audio access unit is specified as those * AES3 words that are associated with a corresponding video frame. @@ -401,8 +404,6 @@ static void *vidtv_s302m_encode(struct vidtv_encoder *e) * ffmpeg */ - struct vidtv_s302m_ctx *ctx = e->ctx; - vidtv_s302m_access_unit_destroy(e); vidtv_s302m_alloc_au(e); @@ -440,8 +441,13 @@ static u32 vidtv_s302m_clear(struct vidtv_encoder *e) struct vidtv_encoder *vidtv_s302m_encoder_init(struct vidtv_s302m_encoder_init_args args) { - struct vidtv_encoder *e = kzalloc(sizeof(*e), GFP_KERNEL); u32 priv_sz = sizeof(struct vidtv_s302m_ctx); + struct vidtv_s302m_ctx *ctx; + struct vidtv_encoder *e; + + e = kzalloc(sizeof(*e), GFP_KERNEL); + if (!e) + return NULL; e->id = S302M; @@ -453,14 +459,21 @@ struct vidtv_encoder e->encoder_buf_offset = 0; e->sample_count = 0; - e->last_duration = 0; e->src_buf = (args.src_buf) ? args.src_buf : NULL; e->src_buf_sz = (args.src_buf) ? args.src_buf_sz : 0; e->src_buf_offset = 0; e->is_video_encoder = false; - e->ctx = kzalloc(priv_sz, GFP_KERNEL); + + ctx = kzalloc(priv_sz, GFP_KERNEL); + if (!ctx) { + kfree(e); + return NULL; + } + + e->ctx = ctx; + ctx->last_duration = 0; e->encode = vidtv_s302m_encode; e->clear = vidtv_s302m_clear; diff --git a/drivers/media/test-drivers/vidtv/vidtv_s302m.h b/drivers/media/test-drivers/vidtv/vidtv_s302m.h index eca5e3150ede..9cc94e4a8924 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_s302m.h +++ b/drivers/media/test-drivers/vidtv/vidtv_s302m.h @@ -19,7 +19,6 @@ #define VIDTV_S302M_H #include <linux/types.h> -#include <asm/byteorder.h> #include "vidtv_encoder.h" @@ -34,14 +33,20 @@ * @enc: A pointer to the containing encoder structure. * @frame_index: The current frame in a block * @au_count: The total number of access units encoded up to now + * @last_duration: Duration of the tone currently being played + * @note_offset: Position at the music tone array + * @last_tone: Tone currently being played */ struct vidtv_s302m_ctx { struct vidtv_encoder *enc; u32 frame_index; u32 au_count; + int last_duration; + unsigned int note_offset; + enum musical_notes last_tone; }; -/** +/* * struct vidtv_smpte_s302m_es - s302m MPEG Elementary Stream header. * * See SMPTE 302M 2007 table 1. diff --git a/drivers/media/test-drivers/vidtv/vidtv_ts.c b/drivers/media/test-drivers/vidtv/vidtv_ts.c index 190b9e4438dc..ca4bb9c40b78 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_ts.c +++ b/drivers/media/test-drivers/vidtv/vidtv_ts.c @@ -9,14 +9,13 @@ #define pr_fmt(fmt) KBUILD_MODNAME ":%s, %d: " fmt, __func__, __LINE__ +#include <linux/math64.h> #include <linux/printk.h> #include <linux/ratelimit.h> #include <linux/types.h> -#include <linux/math64.h> -#include <asm/byteorder.h> -#include "vidtv_ts.h" #include "vidtv_common.h" +#include "vidtv_ts.h" static u32 vidtv_ts_write_pcr_bits(u8 *to, u32 to_offset, u64 pcr) { diff --git a/drivers/media/test-drivers/vidtv/vidtv_ts.h b/drivers/media/test-drivers/vidtv/vidtv_ts.h index 83dcc9183b45..f5e8e1f37f05 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_ts.h +++ b/drivers/media/test-drivers/vidtv/vidtv_ts.h @@ -11,7 +11,6 @@ #define VIDTV_TS_H #include <linux/types.h> -#include <asm/byteorder.h> #define TS_SYNC_BYTE 0x47 #define TS_PACKET_LEN 188 @@ -45,7 +44,7 @@ struct vidtv_mpeg_ts { u8 adaptation_field:1; u8 scrambling:2; } __packed; - struct vidtv_mpeg_ts_adaption adaption[]; + struct vidtv_mpeg_ts_adaption *adaption; } __packed; /** @@ -54,7 +53,7 @@ struct vidtv_mpeg_ts { * @dest_offset: The byte offset into the buffer. * @pid: The TS PID for the PCR packets. * @buf_sz: The size of the buffer in bytes. - * @countinuity_counter: The TS continuity_counter. + * @continuity_counter: The TS continuity_counter. * @pcr: A sample from the system clock. */ struct pcr_write_args { @@ -71,7 +70,7 @@ struct pcr_write_args { * @dest_buf: The buffer to write into. * @dest_offset: The byte offset into the buffer. * @buf_sz: The size of the buffer in bytes. - * @countinuity_counter: The TS continuity_counter. + * @continuity_counter: The TS continuity_counter. */ struct null_packet_write_args { void *dest_buf; diff --git a/drivers/media/test-drivers/vidtv/vidtv_tuner.c b/drivers/media/test-drivers/vidtv/vidtv_tuner.c index 9bc49e099f65..14b6bc902ee1 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_tuner.c +++ b/drivers/media/test-drivers/vidtv/vidtv_tuner.c @@ -13,11 +13,12 @@ #include <linux/errno.h> #include <linux/i2c.h> #include <linux/module.h> +#include <linux/printk.h> +#include <linux/ratelimit.h> #include <linux/slab.h> #include <linux/types.h> + #include <media/dvb_frontend.h> -#include <linux/printk.h> -#include <linux/ratelimit.h> #include "vidtv_tuner.h" diff --git a/drivers/media/test-drivers/vidtv/vidtv_tuner.h b/drivers/media/test-drivers/vidtv/vidtv_tuner.h index 8455b2d564b3..fd55346a5c87 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_tuner.h +++ b/drivers/media/test-drivers/vidtv/vidtv_tuner.h @@ -11,6 +11,7 @@ #define VIDTV_TUNER_H #include <linux/types.h> + #include <media/dvb_frontend.h> #define NUM_VALID_TUNER_FREQS 8 diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 1c0a41803bb6..926408b41270 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -736,7 +736,6 @@ static int at24_probe(struct i2c_client *client) nvmem_config.type = NVMEM_TYPE_EEPROM; nvmem_config.dev = dev; - nvmem_config.id = NVMEM_DEVID_AUTO; nvmem_config.read_only = !writable; nvmem_config.root_only = !(flags & AT24_FLAG_IRUGO); nvmem_config.owner = THIS_MODULE; diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c index 901e213daf40..ada570f35a41 100644 --- a/drivers/misc/habanalabs/common/command_buffer.c +++ b/drivers/misc/habanalabs/common/command_buffer.c @@ -142,11 +142,10 @@ static void cb_fini(struct hl_device *hdev, struct hl_cb *cb) { if (cb->is_internal) gen_pool_free(hdev->internal_cb_pool, - cb->kernel_address, cb->size); + (uintptr_t)cb->kernel_address, cb->size); else hdev->asic_funcs->asic_dma_free_coherent(hdev, cb->size, - (void *) (uintptr_t) cb->kernel_address, - cb->bus_address); + cb->kernel_address, cb->bus_address); kfree(cb); } @@ -230,7 +229,7 @@ static struct hl_cb *hl_cb_alloc(struct hl_device *hdev, u32 cb_size, return NULL; } - cb->kernel_address = (u64) (uintptr_t) p; + cb->kernel_address = p; cb->size = cb_size; return cb; @@ -509,7 +508,7 @@ int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma) vma->vm_private_data = cb; - rc = hdev->asic_funcs->cb_mmap(hdev, vma, (void *) cb->kernel_address, + rc = hdev->asic_funcs->cb_mmap(hdev, vma, cb->kernel_address, cb->bus_address, cb->size); if (rc) { spin_lock(&cb->lock); diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index 20572224099a..783bbdcb1e61 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -231,16 +231,16 @@ delete_cdev_device: static void device_cdev_sysfs_del(struct hl_device *hdev) { - /* device_release() won't be called so must free devices explicitly */ - if (!hdev->cdev_sysfs_created) { - kfree(hdev->dev_ctrl); - kfree(hdev->dev); - return; - } + if (!hdev->cdev_sysfs_created) + goto put_devices; hl_sysfs_fini(hdev); cdev_device_del(&hdev->cdev_ctrl, hdev->dev_ctrl); cdev_device_del(&hdev->cdev, hdev->dev); + +put_devices: + put_device(hdev->dev); + put_device(hdev->dev_ctrl); } /* @@ -1371,9 +1371,9 @@ sw_fini: early_fini: device_early_fini(hdev); free_dev_ctrl: - kfree(hdev->dev_ctrl); + put_device(hdev->dev_ctrl); free_dev: - kfree(hdev->dev); + put_device(hdev->dev); out_disabled: hdev->disabled = true; if (add_cdev_sysfs_on_err) diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 80d4d7385ffe..6ed974d2def0 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -452,7 +452,7 @@ struct hl_cb { struct list_head pool_list; struct list_head va_block_list; u64 id; - u64 kernel_address; + void *kernel_address; dma_addr_t bus_address; u32 mmap_size; u32 size; @@ -515,7 +515,7 @@ struct hl_hw_queue { struct hl_hw_sob hw_sob[HL_RSVD_SOBS]; struct hl_cs_job **shadow_queue; enum hl_queue_type queue_type; - u64 kernel_address; + void *kernel_address; dma_addr_t bus_address; u32 pi; atomic_t ci; @@ -544,7 +544,7 @@ struct hl_hw_queue { */ struct hl_cq { struct hl_device *hdev; - u64 kernel_address; + void *kernel_address; dma_addr_t bus_address; u32 cq_idx; u32 hw_queue_id; @@ -562,7 +562,7 @@ struct hl_cq { */ struct hl_eq { struct hl_device *hdev; - u64 kernel_address; + void *kernel_address; dma_addr_t bus_address; u32 ci; }; @@ -757,7 +757,7 @@ struct hl_asic_funcs { u32 (*get_dma_desc_list_size)(struct hl_device *hdev, struct sg_table *sgt); void (*add_end_of_cb_packets)(struct hl_device *hdev, - u64 kernel_address, u32 len, + void *kernel_address, u32 len, u64 cq_addr, u32 cq_val, u32 msix_num, bool eb); void (*update_eq_ci)(struct hl_device *hdev, u32 val); @@ -1382,13 +1382,13 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val); for (;;) { \ /* Verify we read updates done by other cores or by device */ \ mb(); \ - (val) = *((u32 *) (uintptr_t) (addr)); \ + (val) = *((u32 *)(addr)); \ if (mem_written_by_device) \ (val) = le32_to_cpu(*(__le32 *) &(val)); \ if (cond) \ break; \ if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) { \ - (val) = *((u32 *) (uintptr_t) (addr)); \ + (val) = *((u32 *)(addr)); \ if (mem_written_by_device) \ (val) = le32_to_cpu(*(__le32 *) &(val)); \ break; \ diff --git a/drivers/misc/habanalabs/common/hw_queue.c b/drivers/misc/habanalabs/common/hw_queue.c index 5e66c98fb0d3..250cf9cefc06 100644 --- a/drivers/misc/habanalabs/common/hw_queue.c +++ b/drivers/misc/habanalabs/common/hw_queue.c @@ -75,7 +75,7 @@ static void ext_and_hw_queue_submit_bd(struct hl_device *hdev, { struct hl_bd *bd; - bd = (struct hl_bd *) (uintptr_t) q->kernel_address; + bd = q->kernel_address; bd += hl_pi_2_offset(q->pi); bd->ctl = cpu_to_le32(ctl); bd->len = cpu_to_le32(len); @@ -335,8 +335,7 @@ static void int_queue_schedule_job(struct hl_cs_job *job) bd.len = cpu_to_le32(job->job_cb_size); bd.ptr = cpu_to_le64((u64) (uintptr_t) job->user_cb); - pi = (__le64 *) (uintptr_t) (q->kernel_address + - ((q->pi & (q->int_queue_len - 1)) * sizeof(bd))); + pi = q->kernel_address + (q->pi & (q->int_queue_len - 1)) * sizeof(bd); q->pi++; q->pi &= ((q->int_queue_len << 1) - 1); @@ -630,7 +629,7 @@ static int ext_and_cpu_queue_init(struct hl_device *hdev, struct hl_hw_queue *q, if (!p) return -ENOMEM; - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; q->shadow_queue = kmalloc_array(HL_QUEUE_LENGTH, sizeof(*q->shadow_queue), @@ -653,11 +652,11 @@ free_queue: if (is_cpu_queue) hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address); + q->kernel_address); else hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address, + q->kernel_address, q->bus_address); return rc; @@ -676,7 +675,7 @@ static int int_queue_init(struct hl_device *hdev, struct hl_hw_queue *q) return -EFAULT; } - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; q->pi = 0; atomic_set(&q->ci, 0); @@ -704,7 +703,7 @@ static int hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q) if (!p) return -ENOMEM; - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; /* Make sure read/write pointers are initialized to start of queue */ atomic_set(&q->ci, 0); @@ -839,11 +838,11 @@ static void queue_fini(struct hl_device *hdev, struct hl_hw_queue *q) if (q->queue_type == QUEUE_TYPE_CPU) hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address); + q->kernel_address); else hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address, + q->kernel_address, q->bus_address); } diff --git a/drivers/misc/habanalabs/common/irq.c b/drivers/misc/habanalabs/common/irq.c index d20e40a53d70..de53fb5f978a 100644 --- a/drivers/misc/habanalabs/common/irq.c +++ b/drivers/misc/habanalabs/common/irq.c @@ -90,7 +90,7 @@ irqreturn_t hl_irq_handler_cq(int irq, void *arg) return IRQ_HANDLED; } - cq_base = (struct hl_cq_entry *) (uintptr_t) cq->kernel_address; + cq_base = cq->kernel_address; while (1) { bool entry_ready = ((le32_to_cpu(cq_base[cq->ci].data) & @@ -152,7 +152,7 @@ irqreturn_t hl_irq_handler_eq(int irq, void *arg) struct hl_eq_entry *eq_base; struct hl_eqe_work *handle_eqe_work; - eq_base = (struct hl_eq_entry *) (uintptr_t) eq->kernel_address; + eq_base = eq->kernel_address; while (1) { bool entry_ready = @@ -221,7 +221,7 @@ int hl_cq_init(struct hl_device *hdev, struct hl_cq *q, u32 hw_queue_id) return -ENOMEM; q->hdev = hdev; - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; q->hw_queue_id = hw_queue_id; q->ci = 0; q->pi = 0; @@ -242,7 +242,8 @@ int hl_cq_init(struct hl_device *hdev, struct hl_cq *q, u32 hw_queue_id) void hl_cq_fini(struct hl_device *hdev, struct hl_cq *q) { hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_CQ_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address, q->bus_address); + q->kernel_address, + q->bus_address); } void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q) @@ -259,7 +260,7 @@ void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q) * when the device is operational again */ - memset((void *) (uintptr_t) q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES); + memset(q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES); } /** @@ -282,7 +283,7 @@ int hl_eq_init(struct hl_device *hdev, struct hl_eq *q) return -ENOMEM; q->hdev = hdev; - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; q->ci = 0; return 0; @@ -302,7 +303,7 @@ void hl_eq_fini(struct hl_device *hdev, struct hl_eq *q) hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, HL_EQ_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address); + q->kernel_address); } void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q) @@ -316,5 +317,5 @@ void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q) * when the device is operational again */ - memset((void *) (uintptr_t) q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES); + memset(q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES); } diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c index 84227819e4d1..bfe223abf142 100644 --- a/drivers/misc/habanalabs/common/memory.c +++ b/drivers/misc/habanalabs/common/memory.c @@ -1626,6 +1626,7 @@ static int vm_ctx_init_with_ranges(struct hl_ctx *ctx, goto host_hpage_range_err; } } else { + kfree(ctx->host_huge_va_range); ctx->host_huge_va_range = ctx->host_va_range; } diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 5f65a1691551..7ea6b4368a91 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -680,8 +680,7 @@ static int _gaudi_init_tpc_mem(struct hl_device *hdev, if (!cb) return -EFAULT; - init_tpc_mem_pkt = (struct packet_lin_dma *) (uintptr_t) - cb->kernel_address; + init_tpc_mem_pkt = cb->kernel_address; cb_size = sizeof(*init_tpc_mem_pkt); memset(init_tpc_mem_pkt, 0, cb_size); @@ -3811,8 +3810,7 @@ static int gaudi_validate_cb(struct hl_device *hdev, u16 pkt_size; struct gaudi_packet *user_pkt; - user_pkt = (struct gaudi_packet *) (uintptr_t) - (parser->user_cb->kernel_address + cb_parsed_length); + user_pkt = parser->user_cb->kernel_address + cb_parsed_length; pkt_id = (enum packet_id) ( (le64_to_cpu(user_pkt->header) & @@ -4035,11 +4033,9 @@ static int gaudi_patch_cb(struct hl_device *hdev, u32 new_pkt_size = 0; struct gaudi_packet *user_pkt, *kernel_pkt; - user_pkt = (struct gaudi_packet *) (uintptr_t) - (parser->user_cb->kernel_address + cb_parsed_length); - kernel_pkt = (struct gaudi_packet *) (uintptr_t) - (parser->patched_cb->kernel_address + - cb_patched_cur_length); + user_pkt = parser->user_cb->kernel_address + cb_parsed_length; + kernel_pkt = parser->patched_cb->kernel_address + + cb_patched_cur_length; pkt_id = (enum packet_id) ( (le64_to_cpu(user_pkt->header) & @@ -4155,8 +4151,8 @@ static int gaudi_parse_cb_mmu(struct hl_device *hdev, * The check that parser->user_cb_size <= parser->user_cb->size was done * in validate_queue_index(). */ - memcpy((void *) (uintptr_t) parser->patched_cb->kernel_address, - (void *) (uintptr_t) parser->user_cb->kernel_address, + memcpy(parser->patched_cb->kernel_address, + parser->user_cb->kernel_address, parser->user_cb_size); patched_cb_size = parser->patched_cb_size; @@ -4290,7 +4286,7 @@ static int gaudi_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser) } static void gaudi_add_end_of_cb_packets(struct hl_device *hdev, - u64 kernel_address, u32 len, + void *kernel_address, u32 len, u64 cq_addr, u32 cq_val, u32 msi_vec, bool eb) { @@ -4298,8 +4294,7 @@ static void gaudi_add_end_of_cb_packets(struct hl_device *hdev, struct packet_msg_prot *cq_pkt; u32 tmp; - cq_pkt = (struct packet_msg_prot *) (uintptr_t) - (kernel_address + len - (sizeof(struct packet_msg_prot) * 2)); + cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2); tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT); tmp |= FIELD_PREP(GAUDI_PKT_CTL_MB_MASK, 1); @@ -4342,7 +4337,7 @@ static int gaudi_memset_device_memory(struct hl_device *hdev, u64 addr, if (!cb) return -EFAULT; - lin_dma_pkt = (struct packet_lin_dma *) (uintptr_t) cb->kernel_address; + lin_dma_pkt = cb->kernel_address; memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt)); cb_size = sizeof(*lin_dma_pkt); @@ -4747,7 +4742,7 @@ static void gaudi_write_pte(struct hl_device *hdev, u64 addr, u64 val) (addr - gaudi->hbm_bar_cur_addr)); } -static void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid) +void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid) { /* mask to zero the MMBP and ASID bits */ WREG32_AND(reg, ~0x7FF); @@ -4915,9 +4910,6 @@ static void gaudi_mmu_prepare(struct hl_device *hdev, u32 asid) gaudi_mmu_prepare_reg(hdev, mmMME2_ACC_WBC, asid); gaudi_mmu_prepare_reg(hdev, mmMME3_ACC_WBC, asid); - gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, asid); - gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, asid); - hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); @@ -4954,8 +4946,8 @@ static int gaudi_send_job_on_qman0(struct hl_device *hdev, cb = job->patched_cb; - fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address + - job->job_cb_size - sizeof(struct packet_msg_prot)); + fence_pkt = cb->kernel_address + + job->job_cb_size - sizeof(struct packet_msg_prot); tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT); tmp |= FIELD_PREP(GAUDI_PKT_CTL_EB_MASK, 1); @@ -5444,6 +5436,8 @@ static void gaudi_handle_ecc_event(struct hl_device *hdev, u16 event_type, params.num_memories = 33; params.derr = true; params.disable_clock_gating = true; + extract_info_from_fw = false; + break; default: return; } @@ -6386,7 +6380,7 @@ static void gaudi_gen_signal_cb(struct hl_device *hdev, void *data, u16 sob_id) struct packet_msg_short *pkt; u32 value, ctl; - pkt = (struct packet_msg_short *) (uintptr_t) cb->kernel_address; + pkt = cb->kernel_address; memset(pkt, 0, sizeof(*pkt)); /* Inc by 1, Mode ADD */ @@ -6478,7 +6472,7 @@ static void gaudi_gen_wait_cb(struct hl_device *hdev, void *data, u16 sob_id, u16 sob_val, u16 mon_id, u32 q_idx) { struct hl_cb *cb = (struct hl_cb *) data; - void *buf = (void *) (uintptr_t) cb->kernel_address; + void *buf = cb->kernel_address; u64 monitor_base, fence_addr = 0; u32 size = 0; u16 msg_addr_offset; diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h index 83ad2b0a3a61..8eb598db81b2 100644 --- a/drivers/misc/habanalabs/gaudi/gaudiP.h +++ b/drivers/misc/habanalabs/gaudi/gaudiP.h @@ -271,5 +271,6 @@ void gaudi_set_pll_profile(struct hl_device *hdev, enum hl_pll_frequency freq); int gaudi_debug_coresight(struct hl_device *hdev, void *data); void gaudi_halt_coresight(struct hl_device *hdev); int gaudi_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk); +void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid); #endif /* GAUDIP_H_ */ diff --git a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c index 881531d4d9da..3d2b0f0f4650 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c +++ b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c @@ -623,6 +623,11 @@ static int gaudi_config_etr(struct hl_device *hdev, return -EINVAL; } + gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, + hdev->compute_ctx->asid); + gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, + hdev->compute_ctx->asid); + msb = upper_32_bits(input->buffer_address) >> 8; msb &= PSOC_GLOBAL_CONF_TRACE_ADDR_MSB_MASK; WREG32(mmPSOC_GLOBAL_CONF_TRACE_ADDR, msb); diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 5db52064ed9e..235d47b2420f 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2882,8 +2882,8 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) cb = job->patched_cb; - fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address + - job->job_cb_size - sizeof(struct packet_msg_prot)); + fence_pkt = cb->kernel_address + + job->job_cb_size - sizeof(struct packet_msg_prot); tmp = (PACKET_MSG_PROT << GOYA_PKT_CTL_OPCODE_SHIFT) | (1 << GOYA_PKT_CTL_EB_SHIFT) | @@ -3475,8 +3475,7 @@ static int goya_validate_cb(struct hl_device *hdev, u16 pkt_size; struct goya_packet *user_pkt; - user_pkt = (struct goya_packet *) (uintptr_t) - (parser->user_cb->kernel_address + cb_parsed_length); + user_pkt = parser->user_cb->kernel_address + cb_parsed_length; pkt_id = (enum packet_id) ( (le64_to_cpu(user_pkt->header) & @@ -3713,11 +3712,9 @@ static int goya_patch_cb(struct hl_device *hdev, u32 new_pkt_size = 0; struct goya_packet *user_pkt, *kernel_pkt; - user_pkt = (struct goya_packet *) (uintptr_t) - (parser->user_cb->kernel_address + cb_parsed_length); - kernel_pkt = (struct goya_packet *) (uintptr_t) - (parser->patched_cb->kernel_address + - cb_patched_cur_length); + user_pkt = parser->user_cb->kernel_address + cb_parsed_length; + kernel_pkt = parser->patched_cb->kernel_address + + cb_patched_cur_length; pkt_id = (enum packet_id) ( (le64_to_cpu(user_pkt->header) & @@ -3841,8 +3838,8 @@ static int goya_parse_cb_mmu(struct hl_device *hdev, * The check that parser->user_cb_size <= parser->user_cb->size was done * in validate_queue_index(). */ - memcpy((void *) (uintptr_t) parser->patched_cb->kernel_address, - (void *) (uintptr_t) parser->user_cb->kernel_address, + memcpy(parser->patched_cb->kernel_address, + parser->user_cb->kernel_address, parser->user_cb_size); patched_cb_size = parser->patched_cb_size; @@ -3974,15 +3971,14 @@ int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser) return goya_parse_cb_no_mmu(hdev, parser); } -void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address, +void goya_add_end_of_cb_packets(struct hl_device *hdev, void *kernel_address, u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec, bool eb) { struct packet_msg_prot *cq_pkt; u32 tmp; - cq_pkt = (struct packet_msg_prot *) (uintptr_t) - (kernel_address + len - (sizeof(struct packet_msg_prot) * 2)); + cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2); tmp = (PACKET_MSG_PROT << GOYA_PKT_CTL_OPCODE_SHIFT) | (1 << GOYA_PKT_CTL_EB_SHIFT) | @@ -4746,7 +4742,7 @@ static int goya_memset_device_memory(struct hl_device *hdev, u64 addr, u64 size, if (!cb) return -ENOMEM; - lin_dma_pkt = (struct packet_lin_dma *) (uintptr_t) cb->kernel_address; + lin_dma_pkt = cb->kernel_address; do { memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt)); diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h index 09b4006d4dc3..def86c75e035 100644 --- a/drivers/misc/habanalabs/goya/goyaP.h +++ b/drivers/misc/habanalabs/goya/goyaP.h @@ -217,7 +217,7 @@ int goya_resume(struct hl_device *hdev); void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry); void *goya_get_events_stat(struct hl_device *hdev, bool aggregate, u32 *size); -void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address, +void goya_add_end_of_cb_packets(struct hl_device *hdev, void *kernel_address, u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec, bool eb); int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser); diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h index f395721060bd..46aed13f16b1 100644 --- a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h +++ b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h @@ -421,7 +421,6 @@ enum axi_id { #define QM_ARB_ERR_MSG_EN_MASK (\ QM_ARB_ERR_MSG_EN_CHOISE_OVF_MASK |\ - QM_ARB_ERR_MSG_EN_CHOISE_WDT_MASK |\ QM_ARB_ERR_MSG_EN_AXI_LBW_ERR_MASK) #define PCIE_AUX_FLR_CTRL_HW_CTRL_MASK 0x1 diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig index c06581ffa7bd..f5fd5b786607 100644 --- a/drivers/misc/mei/Kconfig +++ b/drivers/misc/mei/Kconfig @@ -46,14 +46,4 @@ config INTEL_MEI_TXE Supported SoCs: Intel Bay Trail -config INTEL_MEI_VIRTIO - tristate "Intel MEI interface emulation with virtio framework" - select INTEL_MEI - depends on X86 && PCI && VIRTIO_PCI - help - This module implements mei hw emulation over virtio transport. - The module will be called mei_virtio. - Enable this if your virtual machine supports virtual mei - device over virtio. - source "drivers/misc/mei/hdcp/Kconfig" diff --git a/drivers/misc/mei/Makefile b/drivers/misc/mei/Makefile index 52aefaab5c1b..f1c76f7ee804 100644 --- a/drivers/misc/mei/Makefile +++ b/drivers/misc/mei/Makefile @@ -22,9 +22,6 @@ obj-$(CONFIG_INTEL_MEI_TXE) += mei-txe.o mei-txe-objs := pci-txe.o mei-txe-objs += hw-txe.o -obj-$(CONFIG_INTEL_MEI_VIRTIO) += mei-virtio.o -mei-virtio-objs := hw-virtio.o - mei-$(CONFIG_EVENT_TRACING) += mei-trace.o CFLAGS_mei-trace.o = -I$(src) diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h index 64143d4ec758..9e08a9843bba 100644 --- a/drivers/misc/mei/client.h +++ b/drivers/misc/mei/client.h @@ -182,11 +182,11 @@ static inline u8 mei_cl_me_id(const struct mei_cl *cl) * * @cl: host client * - * Return: mtu + * Return: mtu or 0 if client is not connected */ static inline size_t mei_cl_mtu(const struct mei_cl *cl) { - return cl->me_cl->props.max_msg_length; + return cl->me_cl ? cl->me_cl->props.max_msg_length : 0; } /** diff --git a/drivers/misc/mei/hw-virtio.c b/drivers/misc/mei/hw-virtio.c deleted file mode 100644 index 899dc1c5e7ca..000000000000 --- a/drivers/misc/mei/hw-virtio.c +++ /dev/null @@ -1,874 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2018-2020, Intel Corporation. - */ -#include <linux/err.h> -#include <linux/module.h> -#include <linux/pm_runtime.h> -#include <linux/scatterlist.h> -#include <linux/spinlock.h> -#include <linux/slab.h> -#include <linux/virtio.h> -#include <linux/virtio_config.h> -#include <linux/virtio_ids.h> -#include <linux/atomic.h> - -#include "mei_dev.h" -#include "hbm.h" -#include "client.h" - -#define MEI_VIRTIO_RPM_TIMEOUT 500 -/* ACRN virtio device types */ -#ifndef VIRTIO_ID_MEI -#define VIRTIO_ID_MEI 0xFFFE /* virtio mei */ -#endif - -/** - * struct mei_virtio_cfg - settings passed from the virtio backend - * @buf_depth: read buffer depth in slots (4bytes) - * @hw_ready: hw is ready for operation - * @host_reset: synchronize reset with virtio backend - * @reserved: reserved for alignment - * @fw_status: FW status - */ -struct mei_virtio_cfg { - u32 buf_depth; - u8 hw_ready; - u8 host_reset; - u8 reserved[2]; - u32 fw_status[MEI_FW_STATUS_MAX]; -} __packed; - -struct mei_virtio_hw { - struct mei_device mdev; - char name[32]; - - struct virtqueue *in; - struct virtqueue *out; - - bool host_ready; - struct work_struct intr_handler; - - u32 *recv_buf; - u8 recv_rdy; - size_t recv_sz; - u32 recv_idx; - u32 recv_len; - - /* send buffer */ - atomic_t hbuf_ready; - const void *send_hdr; - const void *send_buf; - - struct mei_virtio_cfg cfg; -}; - -#define to_virtio_hw(_dev) container_of(_dev, struct mei_virtio_hw, mdev) - -/** - * mei_virtio_fw_status() - read status register of mei - * @dev: mei device - * @fw_status: fw status register values - * - * Return: always 0 - */ -static int mei_virtio_fw_status(struct mei_device *dev, - struct mei_fw_status *fw_status) -{ - struct virtio_device *vdev = dev_to_virtio(dev->dev); - - fw_status->count = MEI_FW_STATUS_MAX; - virtio_cread_bytes(vdev, offsetof(struct mei_virtio_cfg, fw_status), - fw_status->status, sizeof(fw_status->status)); - return 0; -} - -/** - * mei_virtio_pg_state() - translate internal pg state - * to the mei power gating state - * There is no power management in ACRN mode always return OFF - * @dev: mei device - * - * Return: - * * MEI_PG_OFF - if aliveness is on (always) - * * MEI_PG_ON - (never) - */ -static inline enum mei_pg_state mei_virtio_pg_state(struct mei_device *dev) -{ - return MEI_PG_OFF; -} - -/** - * mei_virtio_hw_config() - configure hw dependent settings - * - * @dev: mei device - * - * Return: always 0 - */ -static int mei_virtio_hw_config(struct mei_device *dev) -{ - return 0; -} - -/** - * mei_virtio_hbuf_empty_slots() - counts write empty slots. - * @dev: the device structure - * - * Return: always return frontend buf size if buffer is ready, 0 otherwise - */ -static int mei_virtio_hbuf_empty_slots(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - return (atomic_read(&hw->hbuf_ready) == 1) ? hw->cfg.buf_depth : 0; -} - -/** - * mei_virtio_hbuf_is_ready() - checks if write buffer is ready - * @dev: the device structure - * - * Return: true if hbuf is ready - */ -static bool mei_virtio_hbuf_is_ready(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - return atomic_read(&hw->hbuf_ready) == 1; -} - -/** - * mei_virtio_hbuf_max_depth() - returns depth of FE write buffer. - * @dev: the device structure - * - * Return: size of frontend write buffer in bytes - */ -static u32 mei_virtio_hbuf_depth(const struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - return hw->cfg.buf_depth; -} - -/** - * mei_virtio_intr_clear() - clear and stop interrupts - * @dev: the device structure - */ -static void mei_virtio_intr_clear(struct mei_device *dev) -{ - /* - * In our virtio solution, there are two types of interrupts, - * vq interrupt and config change interrupt. - * 1) start/reset rely on virtio config changed interrupt; - * 2) send/recv rely on virtio virtqueue interrupts. - * They are all virtual interrupts. So, we don't have corresponding - * operation to do here. - */ -} - -/** - * mei_virtio_intr_enable() - enables mei BE virtqueues callbacks - * @dev: the device structure - */ -static void mei_virtio_intr_enable(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - struct virtio_device *vdev = dev_to_virtio(dev->dev); - - virtio_config_enable(vdev); - - virtqueue_enable_cb(hw->in); - virtqueue_enable_cb(hw->out); -} - -/** - * mei_virtio_intr_disable() - disables mei BE virtqueues callbacks - * - * @dev: the device structure - */ -static void mei_virtio_intr_disable(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - struct virtio_device *vdev = dev_to_virtio(dev->dev); - - virtio_config_disable(vdev); - - virtqueue_disable_cb(hw->in); - virtqueue_disable_cb(hw->out); -} - -/** - * mei_virtio_synchronize_irq() - wait for pending IRQ handlers for all - * virtqueue - * @dev: the device structure - */ -static void mei_virtio_synchronize_irq(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - /* - * Now, all IRQ handlers are converted to workqueue. - * Change synchronize irq to flush this work. - */ - flush_work(&hw->intr_handler); -} - -static void mei_virtio_free_outbufs(struct mei_virtio_hw *hw) -{ - kfree(hw->send_hdr); - kfree(hw->send_buf); - hw->send_hdr = NULL; - hw->send_buf = NULL; -} - -/** - * mei_virtio_write_message() - writes a message to mei virtio back-end service. - * @dev: the device structure - * @hdr: mei header of message - * @hdr_len: header length - * @data: message payload will be written - * @data_len: message payload length - * - * Return: - * * 0: on success - * * -EIO: if write has failed - * * -ENOMEM: on memory allocation failure - */ -static int mei_virtio_write_message(struct mei_device *dev, - const void *hdr, size_t hdr_len, - const void *data, size_t data_len) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - struct scatterlist sg[2]; - const void *hbuf, *dbuf; - int ret; - - if (WARN_ON(!atomic_add_unless(&hw->hbuf_ready, -1, 0))) - return -EIO; - - hbuf = kmemdup(hdr, hdr_len, GFP_KERNEL); - hw->send_hdr = hbuf; - - dbuf = kmemdup(data, data_len, GFP_KERNEL); - hw->send_buf = dbuf; - - if (!hbuf || !dbuf) { - ret = -ENOMEM; - goto fail; - } - - sg_init_table(sg, 2); - sg_set_buf(&sg[0], hbuf, hdr_len); - sg_set_buf(&sg[1], dbuf, data_len); - - ret = virtqueue_add_outbuf(hw->out, sg, 2, hw, GFP_KERNEL); - if (ret) { - dev_err(dev->dev, "failed to add outbuf\n"); - goto fail; - } - - virtqueue_kick(hw->out); - return 0; -fail: - - mei_virtio_free_outbufs(hw); - - return ret; -} - -/** - * mei_virtio_count_full_read_slots() - counts read full slots. - * @dev: the device structure - * - * Return: -EOVERFLOW if overflow, otherwise filled slots count - */ -static int mei_virtio_count_full_read_slots(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - if (hw->recv_idx > hw->recv_len) - return -EOVERFLOW; - - return hw->recv_len - hw->recv_idx; -} - -/** - * mei_virtio_read_hdr() - Reads 32bit dword from mei virtio receive buffer - * - * @dev: the device structure - * - * Return: 32bit dword of receive buffer (u32) - */ -static inline u32 mei_virtio_read_hdr(const struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - WARN_ON(hw->cfg.buf_depth < hw->recv_idx + 1); - - return hw->recv_buf[hw->recv_idx++]; -} - -static int mei_virtio_read(struct mei_device *dev, unsigned char *buffer, - unsigned long len) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - u32 slots = mei_data2slots(len); - - if (WARN_ON(hw->cfg.buf_depth < hw->recv_idx + slots)) - return -EOVERFLOW; - - /* - * Assumption: There is only one MEI message in recv_buf each time. - * Backend service need follow this rule too. - */ - memcpy(buffer, hw->recv_buf + hw->recv_idx, len); - hw->recv_idx += slots; - - return 0; -} - -static bool mei_virtio_pg_is_enabled(struct mei_device *dev) -{ - return false; -} - -static bool mei_virtio_pg_in_transition(struct mei_device *dev) -{ - return false; -} - -static void mei_virtio_add_recv_buf(struct mei_virtio_hw *hw) -{ - struct scatterlist sg; - - if (hw->recv_rdy) /* not needed */ - return; - - /* refill the recv_buf to IN virtqueue to get next message */ - sg_init_one(&sg, hw->recv_buf, mei_slots2data(hw->cfg.buf_depth)); - hw->recv_len = 0; - hw->recv_idx = 0; - hw->recv_rdy = 1; - virtqueue_add_inbuf(hw->in, &sg, 1, hw->recv_buf, GFP_KERNEL); - virtqueue_kick(hw->in); -} - -/** - * mei_virtio_hw_is_ready() - check whether the BE(hw) has turned ready - * @dev: mei device - * Return: bool - */ -static bool mei_virtio_hw_is_ready(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - struct virtio_device *vdev = dev_to_virtio(dev->dev); - - virtio_cread(vdev, struct mei_virtio_cfg, - hw_ready, &hw->cfg.hw_ready); - - dev_dbg(dev->dev, "hw ready %d\n", hw->cfg.hw_ready); - - return hw->cfg.hw_ready; -} - -/** - * mei_virtio_hw_reset - resets virtio hw. - * - * @dev: the device structure - * @intr_enable: virtio use data/config callbacks - * - * Return: 0 on success an error code otherwise - */ -static int mei_virtio_hw_reset(struct mei_device *dev, bool intr_enable) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - struct virtio_device *vdev = dev_to_virtio(dev->dev); - - dev_dbg(dev->dev, "hw reset\n"); - - dev->recvd_hw_ready = false; - hw->host_ready = false; - atomic_set(&hw->hbuf_ready, 0); - hw->recv_len = 0; - hw->recv_idx = 0; - - hw->cfg.host_reset = 1; - virtio_cwrite(vdev, struct mei_virtio_cfg, - host_reset, &hw->cfg.host_reset); - - mei_virtio_hw_is_ready(dev); - - if (intr_enable) - mei_virtio_intr_enable(dev); - - return 0; -} - -/** - * mei_virtio_hw_reset_release() - release device from the reset - * @dev: the device structure - */ -static void mei_virtio_hw_reset_release(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - struct virtio_device *vdev = dev_to_virtio(dev->dev); - - dev_dbg(dev->dev, "hw reset release\n"); - hw->cfg.host_reset = 0; - virtio_cwrite(vdev, struct mei_virtio_cfg, - host_reset, &hw->cfg.host_reset); -} - -/** - * mei_virtio_hw_ready_wait() - wait until the virtio(hw) has turned ready - * or timeout is reached - * @dev: mei device - * - * Return: 0 on success, error otherwise - */ -static int mei_virtio_hw_ready_wait(struct mei_device *dev) -{ - mutex_unlock(&dev->device_lock); - wait_event_timeout(dev->wait_hw_ready, - dev->recvd_hw_ready, - mei_secs_to_jiffies(MEI_HW_READY_TIMEOUT)); - mutex_lock(&dev->device_lock); - if (!dev->recvd_hw_ready) { - dev_err(dev->dev, "wait hw ready failed\n"); - return -ETIMEDOUT; - } - - dev->recvd_hw_ready = false; - return 0; -} - -/** - * mei_virtio_hw_start() - hw start routine - * @dev: mei device - * - * Return: 0 on success, error otherwise - */ -static int mei_virtio_hw_start(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - int ret; - - dev_dbg(dev->dev, "hw start\n"); - mei_virtio_hw_reset_release(dev); - - ret = mei_virtio_hw_ready_wait(dev); - if (ret) - return ret; - - mei_virtio_add_recv_buf(hw); - atomic_set(&hw->hbuf_ready, 1); - dev_dbg(dev->dev, "hw is ready\n"); - hw->host_ready = true; - - return 0; -} - -/** - * mei_virtio_host_is_ready() - check whether the FE has turned ready - * @dev: mei device - * - * Return: bool - */ -static bool mei_virtio_host_is_ready(struct mei_device *dev) -{ - struct mei_virtio_hw *hw = to_virtio_hw(dev); - - dev_dbg(dev->dev, "host ready %d\n", hw->host_ready); - - return hw->host_ready; -} - -/** - * mei_virtio_data_in() - The callback of recv virtqueue of virtio mei - * @vq: receiving virtqueue - */ -static void mei_virtio_data_in(struct virtqueue *vq) -{ - struct mei_virtio_hw *hw = vq->vdev->priv; - - /* disable interrupts (enabled again from in the interrupt worker) */ - virtqueue_disable_cb(hw->in); - - schedule_work(&hw->intr_handler); -} - -/** - * mei_virtio_data_out() - The callback of send virtqueue of virtio mei - * @vq: transmitting virtqueue - */ -static void mei_virtio_data_out(struct virtqueue *vq) -{ - struct mei_virtio_hw *hw = vq->vdev->priv; - - schedule_work(&hw->intr_handler); -} - -static void mei_virtio_intr_handler(struct work_struct *work) -{ - struct mei_virtio_hw *hw = - container_of(work, struct mei_virtio_hw, intr_handler); - struct mei_device *dev = &hw->mdev; - LIST_HEAD(complete_list); - s32 slots; - int rets = 0; - void *data; - unsigned int len; - - mutex_lock(&dev->device_lock); - - if (dev->dev_state == MEI_DEV_DISABLED) { - dev_warn(dev->dev, "Interrupt in disabled state.\n"); - mei_virtio_intr_disable(dev); - goto end; - } - - /* check if ME wants a reset */ - if (!mei_hw_is_ready(dev) && dev->dev_state != MEI_DEV_RESETTING) { - dev_warn(dev->dev, "BE service not ready: resetting.\n"); - schedule_work(&dev->reset_work); - goto end; - } - - /* check if we need to start the dev */ - if (!mei_host_is_ready(dev)) { - if (mei_hw_is_ready(dev)) { - dev_dbg(dev->dev, "we need to start the dev.\n"); - dev->recvd_hw_ready = true; - wake_up(&dev->wait_hw_ready); - } else { - dev_warn(dev->dev, "Spurious Interrupt\n"); - } - goto end; - } - - /* read */ - if (hw->recv_rdy) { - data = virtqueue_get_buf(hw->in, &len); - if (!data || !len) { - dev_dbg(dev->dev, "No data %d", len); - } else { - dev_dbg(dev->dev, "data_in %d\n", len); - WARN_ON(data != hw->recv_buf); - hw->recv_len = mei_data2slots(len); - hw->recv_rdy = 0; - } - } - - /* write */ - if (!atomic_read(&hw->hbuf_ready)) { - if (!virtqueue_get_buf(hw->out, &len)) { - dev_warn(dev->dev, "Failed to getbuf\n"); - } else { - mei_virtio_free_outbufs(hw); - atomic_inc(&hw->hbuf_ready); - } - } - - /* check slots available for reading */ - slots = mei_count_full_read_slots(dev); - while (slots > 0) { - dev_dbg(dev->dev, "slots to read = %08x\n", slots); - rets = mei_irq_read_handler(dev, &complete_list, &slots); - - if (rets && - (dev->dev_state != MEI_DEV_RESETTING && - dev->dev_state != MEI_DEV_POWER_DOWN)) { - dev_err(dev->dev, "mei_irq_read_handler ret = %d.\n", - rets); - schedule_work(&dev->reset_work); - goto end; - } - } - - dev->hbuf_is_ready = mei_hbuf_is_ready(dev); - - mei_irq_write_handler(dev, &complete_list); - - dev->hbuf_is_ready = mei_hbuf_is_ready(dev); - - mei_irq_compl_handler(dev, &complete_list); - - mei_virtio_add_recv_buf(hw); - -end: - if (dev->dev_state != MEI_DEV_DISABLED) { - if (!virtqueue_enable_cb(hw->in)) - schedule_work(&hw->intr_handler); - } - - mutex_unlock(&dev->device_lock); -} - -static void mei_virtio_config_changed(struct virtio_device *vdev) -{ - struct mei_virtio_hw *hw = vdev->priv; - struct mei_device *dev = &hw->mdev; - - virtio_cread(vdev, struct mei_virtio_cfg, - hw_ready, &hw->cfg.hw_ready); - - if (dev->dev_state == MEI_DEV_DISABLED) { - dev_dbg(dev->dev, "disabled state don't start\n"); - return; - } - - /* Run intr handler once to handle reset notify */ - schedule_work(&hw->intr_handler); -} - -static void mei_virtio_remove_vqs(struct virtio_device *vdev) -{ - struct mei_virtio_hw *hw = vdev->priv; - - virtqueue_detach_unused_buf(hw->in); - hw->recv_len = 0; - hw->recv_idx = 0; - hw->recv_rdy = 0; - - virtqueue_detach_unused_buf(hw->out); - - mei_virtio_free_outbufs(hw); - - vdev->config->del_vqs(vdev); -} - -/* - * There are two virtqueues, one is for send and another is for recv. - */ -static int mei_virtio_init_vqs(struct mei_virtio_hw *hw, - struct virtio_device *vdev) -{ - struct virtqueue *vqs[2]; - - vq_callback_t *cbs[] = { - mei_virtio_data_in, - mei_virtio_data_out, - }; - static const char * const names[] = { - "in", - "out", - }; - int ret; - - ret = virtio_find_vqs(vdev, 2, vqs, cbs, names, NULL); - if (ret) - return ret; - - hw->in = vqs[0]; - hw->out = vqs[1]; - - return 0; -} - -static const struct mei_hw_ops mei_virtio_ops = { - .fw_status = mei_virtio_fw_status, - .pg_state = mei_virtio_pg_state, - - .host_is_ready = mei_virtio_host_is_ready, - - .hw_is_ready = mei_virtio_hw_is_ready, - .hw_reset = mei_virtio_hw_reset, - .hw_config = mei_virtio_hw_config, - .hw_start = mei_virtio_hw_start, - - .pg_in_transition = mei_virtio_pg_in_transition, - .pg_is_enabled = mei_virtio_pg_is_enabled, - - .intr_clear = mei_virtio_intr_clear, - .intr_enable = mei_virtio_intr_enable, - .intr_disable = mei_virtio_intr_disable, - .synchronize_irq = mei_virtio_synchronize_irq, - - .hbuf_free_slots = mei_virtio_hbuf_empty_slots, - .hbuf_is_ready = mei_virtio_hbuf_is_ready, - .hbuf_depth = mei_virtio_hbuf_depth, - - .write = mei_virtio_write_message, - - .rdbuf_full_slots = mei_virtio_count_full_read_slots, - .read_hdr = mei_virtio_read_hdr, - .read = mei_virtio_read, -}; - -static int mei_virtio_probe(struct virtio_device *vdev) -{ - struct mei_virtio_hw *hw; - int ret; - - hw = devm_kzalloc(&vdev->dev, sizeof(*hw), GFP_KERNEL); - if (!hw) - return -ENOMEM; - - vdev->priv = hw; - - INIT_WORK(&hw->intr_handler, mei_virtio_intr_handler); - - ret = mei_virtio_init_vqs(hw, vdev); - if (ret) - goto vqs_failed; - - virtio_cread(vdev, struct mei_virtio_cfg, - buf_depth, &hw->cfg.buf_depth); - - hw->recv_buf = kzalloc(mei_slots2data(hw->cfg.buf_depth), GFP_KERNEL); - if (!hw->recv_buf) { - ret = -ENOMEM; - goto hbuf_failed; - } - atomic_set(&hw->hbuf_ready, 0); - - virtio_device_ready(vdev); - - mei_device_init(&hw->mdev, &vdev->dev, &mei_virtio_ops); - - pm_runtime_get_noresume(&vdev->dev); - pm_runtime_set_active(&vdev->dev); - pm_runtime_enable(&vdev->dev); - - ret = mei_start(&hw->mdev); - if (ret) - goto mei_start_failed; - - pm_runtime_set_autosuspend_delay(&vdev->dev, MEI_VIRTIO_RPM_TIMEOUT); - pm_runtime_use_autosuspend(&vdev->dev); - - ret = mei_register(&hw->mdev, &vdev->dev); - if (ret) - goto mei_failed; - - pm_runtime_put(&vdev->dev); - - return 0; - -mei_failed: - mei_stop(&hw->mdev); -mei_start_failed: - mei_cancel_work(&hw->mdev); - mei_disable_interrupts(&hw->mdev); - kfree(hw->recv_buf); -hbuf_failed: - vdev->config->del_vqs(vdev); -vqs_failed: - return ret; -} - -static int __maybe_unused mei_virtio_pm_runtime_idle(struct device *device) -{ - struct virtio_device *vdev = dev_to_virtio(device); - struct mei_virtio_hw *hw = vdev->priv; - - dev_dbg(&vdev->dev, "rpm: mei_virtio : runtime_idle\n"); - - if (!hw) - return -ENODEV; - - if (mei_write_is_idle(&hw->mdev)) - pm_runtime_autosuspend(device); - - return -EBUSY; -} - -static int __maybe_unused mei_virtio_pm_runtime_suspend(struct device *device) -{ - return 0; -} - -static int __maybe_unused mei_virtio_pm_runtime_resume(struct device *device) -{ - return 0; -} - -static int __maybe_unused mei_virtio_freeze(struct virtio_device *vdev) -{ - struct mei_virtio_hw *hw = vdev->priv; - - dev_dbg(&vdev->dev, "freeze\n"); - - if (!hw) - return -ENODEV; - - mei_stop(&hw->mdev); - mei_disable_interrupts(&hw->mdev); - cancel_work_sync(&hw->intr_handler); - vdev->config->reset(vdev); - mei_virtio_remove_vqs(vdev); - - return 0; -} - -static int __maybe_unused mei_virtio_restore(struct virtio_device *vdev) -{ - struct mei_virtio_hw *hw = vdev->priv; - int ret; - - dev_dbg(&vdev->dev, "restore\n"); - - if (!hw) - return -ENODEV; - - ret = mei_virtio_init_vqs(hw, vdev); - if (ret) - return ret; - - virtio_device_ready(vdev); - - ret = mei_restart(&hw->mdev); - if (ret) - return ret; - - /* Start timer if stopped in suspend */ - schedule_delayed_work(&hw->mdev.timer_work, HZ); - - return 0; -} - -static const struct dev_pm_ops mei_virtio_pm_ops = { - SET_RUNTIME_PM_OPS(mei_virtio_pm_runtime_suspend, - mei_virtio_pm_runtime_resume, - mei_virtio_pm_runtime_idle) -}; - -static void mei_virtio_remove(struct virtio_device *vdev) -{ - struct mei_virtio_hw *hw = vdev->priv; - - mei_stop(&hw->mdev); - mei_disable_interrupts(&hw->mdev); - cancel_work_sync(&hw->intr_handler); - mei_deregister(&hw->mdev); - vdev->config->reset(vdev); - mei_virtio_remove_vqs(vdev); - kfree(hw->recv_buf); - pm_runtime_disable(&vdev->dev); -} - -static struct virtio_device_id id_table[] = { - { VIRTIO_ID_MEI, VIRTIO_DEV_ANY_ID }, - { } -}; - -static struct virtio_driver mei_virtio_driver = { - .id_table = id_table, - .probe = mei_virtio_probe, - .remove = mei_virtio_remove, - .config_changed = mei_virtio_config_changed, - .driver = { - .name = KBUILD_MODNAME, - .owner = THIS_MODULE, - .pm = &mei_virtio_pm_ops, - }, -#ifdef CONFIG_PM_SLEEP - .freeze = mei_virtio_freeze, - .restore = mei_virtio_restore, -#endif -}; - -module_virtio_driver(mei_virtio_driver); -MODULE_DEVICE_TABLE(virtio, id_table); -MODULE_DESCRIPTION("Virtio MEI frontend driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 8d3df0be0355..42e27a298218 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -580,7 +580,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, memcpy(&(idata->ic.response), cmd.resp, sizeof(cmd.resp)); - if (idata->rpmb || (cmd.flags & MMC_RSP_R1B)) { + if (idata->rpmb || (cmd.flags & MMC_RSP_R1B) == MMC_RSP_R1B) { /* * Ensure RPMB/R1B command has completed by polling CMD13 * "Send Status". diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index a704745e5882..004fbfc23672 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -446,7 +446,7 @@ struct msdc_host { static const struct mtk_mmc_compatible mt8135_compat = { .clk_div_bits = 8, - .recheck_sdio_irq = false, + .recheck_sdio_irq = true, .hs400_tune = false, .pad_tune_reg = MSDC_PAD_TUNE, .async_fifo = false, @@ -485,7 +485,7 @@ static const struct mtk_mmc_compatible mt8183_compat = { static const struct mtk_mmc_compatible mt2701_compat = { .clk_div_bits = 12, - .recheck_sdio_irq = false, + .recheck_sdio_irq = true, .hs400_tune = false, .pad_tune_reg = MSDC_PAD_TUNE0, .async_fifo = true, @@ -511,7 +511,7 @@ static const struct mtk_mmc_compatible mt2712_compat = { static const struct mtk_mmc_compatible mt7622_compat = { .clk_div_bits = 12, - .recheck_sdio_irq = false, + .recheck_sdio_irq = true, .hs400_tune = false, .pad_tune_reg = MSDC_PAD_TUNE0, .async_fifo = true, @@ -524,7 +524,7 @@ static const struct mtk_mmc_compatible mt7622_compat = { static const struct mtk_mmc_compatible mt8516_compat = { .clk_div_bits = 12, - .recheck_sdio_irq = false, + .recheck_sdio_irq = true, .hs400_tune = false, .pad_tune_reg = MSDC_PAD_TUNE0, .async_fifo = true, @@ -535,7 +535,7 @@ static const struct mtk_mmc_compatible mt8516_compat = { static const struct mtk_mmc_compatible mt7620_compat = { .clk_div_bits = 8, - .recheck_sdio_irq = false, + .recheck_sdio_irq = true, .hs400_tune = false, .pad_tune_reg = MSDC_PAD_TUNE, .async_fifo = false, @@ -548,6 +548,7 @@ static const struct mtk_mmc_compatible mt7620_compat = { static const struct mtk_mmc_compatible mt6779_compat = { .clk_div_bits = 12, + .recheck_sdio_irq = false, .hs400_tune = false, .pad_tune_reg = MSDC_PAD_TUNE0, .async_fifo = true, @@ -2603,7 +2604,6 @@ static int msdc_drv_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM static void msdc_save_reg(struct msdc_host *host) { u32 tune_reg = host->dev_comp->pad_tune_reg; @@ -2662,7 +2662,7 @@ static void msdc_restore_reg(struct msdc_host *host) __msdc_enable_sdio_irq(host, 1); } -static int msdc_runtime_suspend(struct device *dev) +static int __maybe_unused msdc_runtime_suspend(struct device *dev) { struct mmc_host *mmc = dev_get_drvdata(dev); struct msdc_host *host = mmc_priv(mmc); @@ -2672,7 +2672,7 @@ static int msdc_runtime_suspend(struct device *dev) return 0; } -static int msdc_runtime_resume(struct device *dev) +static int __maybe_unused msdc_runtime_resume(struct device *dev) { struct mmc_host *mmc = dev_get_drvdata(dev); struct msdc_host *host = mmc_priv(mmc); @@ -2681,11 +2681,28 @@ static int msdc_runtime_resume(struct device *dev) msdc_restore_reg(host); return 0; } -#endif + +static int __maybe_unused msdc_suspend(struct device *dev) +{ + struct mmc_host *mmc = dev_get_drvdata(dev); + int ret; + + if (mmc->caps2 & MMC_CAP2_CQE) { + ret = cqhci_suspend(mmc); + if (ret) + return ret; + } + + return pm_runtime_force_suspend(dev); +} + +static int __maybe_unused msdc_resume(struct device *dev) +{ + return pm_runtime_force_resume(dev); +} static const struct dev_pm_ops msdc_dev_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, - pm_runtime_force_resume) + SET_SYSTEM_SLEEP_PM_OPS(msdc_suspend, msdc_resume) SET_RUNTIME_PM_OPS(msdc_runtime_suspend, msdc_runtime_resume, NULL) }; diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index 414314151d0a..acb9c81a4e45 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -572,17 +572,6 @@ static void renesas_sdhi_reset(struct tmio_mmc_host *host) TMIO_MASK_INIT_RCAR2); } -/* - * This is a temporary workaround! This driver used 'hw_reset' wrongly and the - * fix for that showed a regression. So, we mimic the old behaviour until the - * proper solution is found. - */ -static void renesas_sdhi_hw_reset(struct mmc_host *mmc) -{ - struct tmio_mmc_host *host = mmc_priv(mmc); - renesas_sdhi_reset(host); -} - #define SH_MOBILE_SDHI_MIN_TAP_ROW 3 static int renesas_sdhi_select_tuning(struct tmio_mmc_host *host) @@ -1020,8 +1009,6 @@ int renesas_sdhi_probe(struct platform_device *pdev, if (of_data && of_data->scc_offset) { priv->scc_ctl = host->ctl + of_data->scc_offset; host->reset = renesas_sdhi_reset; - host->ops.hw_reset = renesas_sdhi_hw_reset; - host->mmc->caps |= MMC_CAP_HW_RESET; } } @@ -1160,6 +1147,7 @@ int renesas_sdhi_remove(struct platform_device *pdev) tmio_mmc_host_remove(host); renesas_sdhi_clk_disable(host); + tmio_mmc_host_free(host); return 0; } diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c index 829ccef87426..3b8d456e857d 100644 --- a/drivers/mmc/host/sdhci-of-arasan.c +++ b/drivers/mmc/host/sdhci-of-arasan.c @@ -30,7 +30,10 @@ #define SDHCI_ARASAN_VENDOR_REGISTER 0x78 #define SDHCI_ARASAN_ITAPDLY_REGISTER 0xF0F8 +#define SDHCI_ARASAN_ITAPDLY_SEL_MASK 0xFF + #define SDHCI_ARASAN_OTAPDLY_REGISTER 0xF0FC +#define SDHCI_ARASAN_OTAPDLY_SEL_MASK 0x3F #define SDHCI_ARASAN_CQE_BASE_ADDR 0x200 #define VENDOR_ENHANCED_STROBE BIT(0) @@ -600,14 +603,8 @@ static int sdhci_zynqmp_sdcardclk_set_phase(struct clk_hw *hw, int degrees) u8 tap_delay, tap_max = 0; int ret; - /* - * This is applicable for SDHCI_SPEC_300 and above - * ZynqMP does not set phase for <=25MHz clock. - * If degrees is zero, no need to do anything. - */ - if (host->version < SDHCI_SPEC_300 || - host->timing == MMC_TIMING_LEGACY || - host->timing == MMC_TIMING_UHS_SDR12 || !degrees) + /* This is applicable for SDHCI_SPEC_300 and above */ + if (host->version < SDHCI_SPEC_300) return 0; switch (host->timing) { @@ -638,6 +635,9 @@ static int sdhci_zynqmp_sdcardclk_set_phase(struct clk_hw *hw, int degrees) if (ret) pr_err("Error setting Output Tap Delay\n"); + /* Release DLL Reset */ + zynqmp_pm_sd_dll_reset(node_id, PM_DLL_RESET_RELEASE); + return ret; } @@ -668,16 +668,13 @@ static int sdhci_zynqmp_sampleclk_set_phase(struct clk_hw *hw, int degrees) u8 tap_delay, tap_max = 0; int ret; - /* - * This is applicable for SDHCI_SPEC_300 and above - * ZynqMP does not set phase for <=25MHz clock. - * If degrees is zero, no need to do anything. - */ - if (host->version < SDHCI_SPEC_300 || - host->timing == MMC_TIMING_LEGACY || - host->timing == MMC_TIMING_UHS_SDR12 || !degrees) + /* This is applicable for SDHCI_SPEC_300 and above */ + if (host->version < SDHCI_SPEC_300) return 0; + /* Assert DLL Reset */ + zynqmp_pm_sd_dll_reset(node_id, PM_DLL_RESET_ASSERT); + switch (host->timing) { case MMC_TIMING_MMC_HS: case MMC_TIMING_SD_HS: @@ -733,14 +730,8 @@ static int sdhci_versal_sdcardclk_set_phase(struct clk_hw *hw, int degrees) struct sdhci_host *host = sdhci_arasan->host; u8 tap_delay, tap_max = 0; - /* - * This is applicable for SDHCI_SPEC_300 and above - * Versal does not set phase for <=25MHz clock. - * If degrees is zero, no need to do anything. - */ - if (host->version < SDHCI_SPEC_300 || - host->timing == MMC_TIMING_LEGACY || - host->timing == MMC_TIMING_UHS_SDR12 || !degrees) + /* This is applicable for SDHCI_SPEC_300 and above */ + if (host->version < SDHCI_SPEC_300) return 0; switch (host->timing) { @@ -773,6 +764,7 @@ static int sdhci_versal_sdcardclk_set_phase(struct clk_hw *hw, int degrees) regval = sdhci_readl(host, SDHCI_ARASAN_OTAPDLY_REGISTER); regval |= SDHCI_OTAPDLY_ENABLE; sdhci_writel(host, regval, SDHCI_ARASAN_OTAPDLY_REGISTER); + regval &= ~SDHCI_ARASAN_OTAPDLY_SEL_MASK; regval |= tap_delay; sdhci_writel(host, regval, SDHCI_ARASAN_OTAPDLY_REGISTER); } @@ -804,14 +796,8 @@ static int sdhci_versal_sampleclk_set_phase(struct clk_hw *hw, int degrees) struct sdhci_host *host = sdhci_arasan->host; u8 tap_delay, tap_max = 0; - /* - * This is applicable for SDHCI_SPEC_300 and above - * Versal does not set phase for <=25MHz clock. - * If degrees is zero, no need to do anything. - */ - if (host->version < SDHCI_SPEC_300 || - host->timing == MMC_TIMING_LEGACY || - host->timing == MMC_TIMING_UHS_SDR12 || !degrees) + /* This is applicable for SDHCI_SPEC_300 and above */ + if (host->version < SDHCI_SPEC_300) return 0; switch (host->timing) { @@ -846,6 +832,7 @@ static int sdhci_versal_sampleclk_set_phase(struct clk_hw *hw, int degrees) sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER); regval |= SDHCI_ITAPDLY_ENABLE; sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER); + regval &= ~SDHCI_ARASAN_ITAPDLY_SEL_MASK; regval |= tap_delay; sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER); regval &= ~SDHCI_ITAPDLY_CHGWIN; @@ -1199,16 +1186,19 @@ static struct sdhci_arasan_of_data sdhci_arasan_versal_data = { static struct sdhci_arasan_of_data intel_keembay_emmc_data = { .soc_ctl_map = &intel_keembay_soc_ctl_map, .pdata = &sdhci_keembay_emmc_pdata, + .clk_ops = &arasan_clk_ops, }; static struct sdhci_arasan_of_data intel_keembay_sd_data = { .soc_ctl_map = &intel_keembay_soc_ctl_map, .pdata = &sdhci_keembay_sd_pdata, + .clk_ops = &arasan_clk_ops, }; static struct sdhci_arasan_of_data intel_keembay_sdio_data = { .soc_ctl_map = &intel_keembay_soc_ctl_map, .pdata = &sdhci_keembay_sdio_pdata, + .clk_ops = &arasan_clk_ops, }; static const struct of_device_id sdhci_arasan_of_match[] = { diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c index bb094459196a..ab5ab969f711 100644 --- a/drivers/mmc/host/sdhci-of-esdhc.c +++ b/drivers/mmc/host/sdhci-of-esdhc.c @@ -1324,6 +1324,8 @@ static struct soc_device_attribute soc_fixup_sdhc_clkdivs[] = { static struct soc_device_attribute soc_unreliable_pulse_detection[] = { { .family = "QorIQ LX2160A", .revision = "1.0", }, + { .family = "QorIQ LX2160A", .revision = "2.0", }, + { .family = "QorIQ LS1028A", .revision = "1.0", }, { }, }; diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index 23da7f7fe093..9552708846ca 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -665,6 +665,15 @@ static void sdhci_intel_set_power(struct sdhci_host *host, unsigned char mode, } } +static void sdhci_intel_set_uhs_signaling(struct sdhci_host *host, + unsigned int timing) +{ + /* Set UHS timing to SDR25 for High Speed mode */ + if (timing == MMC_TIMING_MMC_HS || timing == MMC_TIMING_SD_HS) + timing = MMC_TIMING_UHS_SDR25; + sdhci_set_uhs_signaling(host, timing); +} + #define INTEL_HS400_ES_REG 0x78 #define INTEL_HS400_ES_BIT BIT(0) @@ -721,7 +730,7 @@ static const struct sdhci_ops sdhci_intel_byt_ops = { .enable_dma = sdhci_pci_enable_dma, .set_bus_width = sdhci_set_bus_width, .reset = sdhci_reset, - .set_uhs_signaling = sdhci_set_uhs_signaling, + .set_uhs_signaling = sdhci_intel_set_uhs_signaling, .hw_reset = sdhci_pci_hw_reset, }; @@ -731,7 +740,7 @@ static const struct sdhci_ops sdhci_intel_glk_ops = { .enable_dma = sdhci_pci_enable_dma, .set_bus_width = sdhci_set_bus_width, .reset = sdhci_cqhci_reset, - .set_uhs_signaling = sdhci_set_uhs_signaling, + .set_uhs_signaling = sdhci_intel_set_uhs_signaling, .hw_reset = sdhci_pci_hw_reset, .irq = sdhci_cqhci_irq, }; diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 2fce0518632d..ac4e7874a3f1 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -175,6 +175,8 @@ static void tmio_mmc_reset(struct tmio_mmc_host *host) if (host->reset) host->reset(host); + tmio_mmc_abort_dma(host); + if (host->pdata->flags & TMIO_MMC_SDIO_IRQ) { sd_ctrl_write16(host, CTL_SDIO_IRQ_MASK, host->sdio_irq_mask); sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0001); @@ -223,8 +225,6 @@ static void tmio_mmc_reset_work(struct work_struct *work) /* Ready for new calls */ host->mrq = NULL; - - tmio_mmc_abort_dma(host); mmc_request_done(host->mmc, mrq); } @@ -927,6 +927,9 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) switch (ios->power_mode) { case MMC_POWER_OFF: tmio_mmc_power_off(host); + /* For R-Car Gen2+, we need to reset SDHI specific SCC */ + if (host->pdata->flags & TMIO_MMC_MIN_RCAR2) + host->reset(host); host->set_clock(host, 0); break; case MMC_POWER_UP: diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index d3c5cc513c8f..ff1697f899ba 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -215,8 +215,19 @@ static int gpio_nand_setup_interface(struct nand_chip *this, int csline, return 0; } +static int gpio_nand_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + static const struct nand_controller_ops gpio_nand_ops = { .exec_op = gpio_nand_exec_op, + .attach_chip = gpio_nand_attach_chip, .setup_interface = gpio_nand_setup_interface, }; @@ -260,9 +271,6 @@ static int gpio_nand_probe(struct platform_device *pdev) return err; } - this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - this->ecc.algo = NAND_ECC_ALGO_HAMMING; - platform_set_drvdata(pdev, priv); /* Set chip enabled but write protected */ diff --git a/drivers/mtd/nand/raw/au1550nd.c b/drivers/mtd/nand/raw/au1550nd.c index 79b057400fe9..7b6b354f2d39 100644 --- a/drivers/mtd/nand/raw/au1550nd.c +++ b/drivers/mtd/nand/raw/au1550nd.c @@ -236,8 +236,19 @@ static int au1550nd_exec_op(struct nand_chip *this, return ret; } +static int au1550nd_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + static const struct nand_controller_ops au1550nd_ops = { .exec_op = au1550nd_exec_op, + .attach_chip = au1550nd_attach_chip, }; static int au1550nd_probe(struct platform_device *pdev) @@ -294,8 +305,6 @@ static int au1550nd_probe(struct platform_device *pdev) nand_controller_init(&ctx->controller); ctx->controller.ops = &au1550nd_ops; this->controller = &ctx->controller; - this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - this->ecc.algo = NAND_ECC_ALGO_HAMMING; if (pd->devwidth) this->options |= NAND_BUSWIDTH_16; diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c index b7f3f6347761..282203debd0c 100644 --- a/drivers/mtd/nand/raw/cs553x_nand.c +++ b/drivers/mtd/nand/raw/cs553x_nand.c @@ -243,8 +243,24 @@ static int cs_calculate_ecc(struct nand_chip *this, const u_char *dat, static struct cs553x_nand_controller *controllers[4]; +static int cs553x_attach_chip(struct nand_chip *chip) +{ + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + + chip->ecc.size = 256; + chip->ecc.bytes = 3; + chip->ecc.hwctl = cs_enable_hwecc; + chip->ecc.calculate = cs_calculate_ecc; + chip->ecc.correct = nand_correct_data; + chip->ecc.strength = 1; + + return 0; +} + static const struct nand_controller_ops cs553x_nand_controller_ops = { .exec_op = cs553x_exec_op, + .attach_chip = cs553x_attach_chip, }; static int __init cs553x_init_one(int cs, int mmio, unsigned long adr) @@ -286,14 +302,6 @@ static int __init cs553x_init_one(int cs, int mmio, unsigned long adr) goto out_mtd; } - this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - this->ecc.size = 256; - this->ecc.bytes = 3; - this->ecc.hwctl = cs_enable_hwecc; - this->ecc.calculate = cs_calculate_ecc; - this->ecc.correct = nand_correct_data; - this->ecc.strength = 1; - /* Enable the following for a flash based bad block table */ this->bbt_options = NAND_BBT_USE_FLASH; diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c index 427f320fb79b..f8c36d19ab47 100644 --- a/drivers/mtd/nand/raw/davinci_nand.c +++ b/drivers/mtd/nand/raw/davinci_nand.c @@ -585,6 +585,10 @@ static int davinci_nand_attach_chip(struct nand_chip *chip) if (IS_ERR(pdata)) return PTR_ERR(pdata); + /* Use board-specific ECC config */ + info->chip.ecc.engine_type = pdata->engine_type; + info->chip.ecc.placement = pdata->ecc_placement; + switch (info->chip.ecc.engine_type) { case NAND_ECC_ENGINE_TYPE_NONE: pdata->ecc_bits = 0; @@ -850,10 +854,6 @@ static int nand_davinci_probe(struct platform_device *pdev) info->mask_ale = pdata->mask_ale ? : MASK_ALE; info->mask_cle = pdata->mask_cle ? : MASK_CLE; - /* Use board-specific ECC config */ - info->chip.ecc.engine_type = pdata->engine_type; - info->chip.ecc.placement = pdata->ecc_placement; - spin_lock_irq(&davinci_nand_lock); /* put CSxNAND into NAND mode */ diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c index 94432a453e5e..26b265e4384a 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -1269,12 +1269,31 @@ static inline int __init doc2001plus_init(struct mtd_info *mtd) return 1; } +static int doc200x_attach_chip(struct nand_chip *chip) +{ + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + + chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED; + chip->ecc.size = 512; + chip->ecc.bytes = 6; + chip->ecc.strength = 2; + chip->ecc.options = NAND_ECC_GENERIC_ERASED_CHECK; + chip->ecc.hwctl = doc200x_enable_hwecc; + chip->ecc.calculate = doc200x_calculate_ecc; + chip->ecc.correct = doc200x_correct_data; + + return 0; +} + static const struct nand_controller_ops doc200x_ops = { .exec_op = doc200x_exec_op, + .attach_chip = doc200x_attach_chip, }; static const struct nand_controller_ops doc2001plus_ops = { .exec_op = doc2001plus_exec_op, + .attach_chip = doc200x_attach_chip, }; static int __init doc_probe(unsigned long physadr) @@ -1452,16 +1471,6 @@ static int __init doc_probe(unsigned long physadr) nand->controller = &doc->base; nand_set_controller_data(nand, doc); - nand->ecc.hwctl = doc200x_enable_hwecc; - nand->ecc.calculate = doc200x_calculate_ecc; - nand->ecc.correct = doc200x_correct_data; - - nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - nand->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED; - nand->ecc.size = 512; - nand->ecc.bytes = 6; - nand->ecc.strength = 2; - nand->ecc.options = NAND_ECC_GENERIC_ERASED_CHECK; nand->bbt_options = NAND_BBT_USE_FLASH; /* Skip the automatic BBT scan so we can run it manually */ nand->options |= NAND_SKIP_BBTSCAN | NAND_NO_BBM_QUIRK; diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index 4191831df182..c88421a1c078 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -880,6 +880,20 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand) struct mtd_info *mtd = nand_to_mtd(nand); struct fsmc_nand_data *host = nand_to_fsmc(nand); + if (nand->ecc.engine_type == NAND_ECC_ENGINE_TYPE_INVALID) + nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; + + if (!nand->ecc.size) + nand->ecc.size = 512; + + if (AMBA_REV_BITS(host->pid) >= 8) { + nand->ecc.read_page = fsmc_read_page_hwecc; + nand->ecc.calculate = fsmc_read_hwecc_ecc4; + nand->ecc.correct = fsmc_bch8_correct_data; + nand->ecc.bytes = 13; + nand->ecc.strength = 8; + } + if (AMBA_REV_BITS(host->pid) >= 8) { switch (mtd->oobsize) { case 16: @@ -905,6 +919,7 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand) dev_info(host->dev, "Using 1-bit HW ECC scheme\n"); nand->ecc.calculate = fsmc_read_hwecc_ecc1; nand->ecc.correct = nand_correct_data; + nand->ecc.hwctl = fsmc_enable_hwecc; nand->ecc.bytes = 3; nand->ecc.strength = 1; nand->ecc.options |= NAND_ECC_SOFT_HAMMING_SM_ORDER; @@ -1055,13 +1070,6 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) mtd->dev.parent = &pdev->dev; - /* - * Setup default ECC mode. nand_dt_init() called from nand_scan_ident() - * can overwrite this value if the DT provides a different value. - */ - nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - nand->ecc.hwctl = fsmc_enable_hwecc; - nand->ecc.size = 512; nand->badblockbits = 7; if (host->mode == USE_DMA_ACCESS) { @@ -1084,14 +1092,6 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) nand->options |= NAND_KEEP_TIMINGS; } - if (AMBA_REV_BITS(host->pid) >= 8) { - nand->ecc.read_page = fsmc_read_page_hwecc; - nand->ecc.calculate = fsmc_read_hwecc_ecc4; - nand->ecc.correct = fsmc_bch8_correct_data; - nand->ecc.bytes = 13; - nand->ecc.strength = 8; - } - nand_controller_init(&host->base); host->base.ops = &fsmc_nand_controller_ops; nand->controller = &host->base; diff --git a/drivers/mtd/nand/raw/gpio.c b/drivers/mtd/nand/raw/gpio.c index 4ec0a1e10867..fb7a086de35e 100644 --- a/drivers/mtd/nand/raw/gpio.c +++ b/drivers/mtd/nand/raw/gpio.c @@ -161,8 +161,19 @@ static int gpio_nand_exec_op(struct nand_chip *chip, return ret; } +static int gpio_nand_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + static const struct nand_controller_ops gpio_nand_ops = { .exec_op = gpio_nand_exec_op, + .attach_chip = gpio_nand_attach_chip, }; #ifdef CONFIG_OF @@ -342,8 +353,6 @@ static int gpio_nand_probe(struct platform_device *pdev) gpiomtd->base.ops = &gpio_nand_ops; nand_set_flash_node(chip, pdev->dev.of_node); - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; chip->options = gpiomtd->plat.options; chip->controller = &gpiomtd->base; diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c index 4940bb2e3c07..9e728c731795 100644 --- a/drivers/mtd/nand/raw/lpc32xx_mlc.c +++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c @@ -648,6 +648,9 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip) struct lpc32xx_nand_host *host = nand_get_controller_data(chip); struct device *dev = &host->pdev->dev; + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + host->dma_buf = devm_kzalloc(dev, mtd->writesize, GFP_KERNEL); if (!host->dma_buf) return -ENOMEM; @@ -656,8 +659,17 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip) if (!host->dummy_buf) return -ENOMEM; - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; chip->ecc.size = 512; + chip->ecc.hwctl = lpc32xx_ecc_enable; + chip->ecc.read_page_raw = lpc32xx_read_page; + chip->ecc.read_page = lpc32xx_read_page; + chip->ecc.write_page_raw = lpc32xx_write_page_lowlevel; + chip->ecc.write_page = lpc32xx_write_page_lowlevel; + chip->ecc.write_oob = lpc32xx_write_oob; + chip->ecc.read_oob = lpc32xx_read_oob; + chip->ecc.strength = 4; + chip->ecc.bytes = 10; + mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops); host->mlcsubpages = mtd->writesize / 512; @@ -741,15 +753,6 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) platform_set_drvdata(pdev, host); /* Initialize function pointers */ - nand_chip->ecc.hwctl = lpc32xx_ecc_enable; - nand_chip->ecc.read_page_raw = lpc32xx_read_page; - nand_chip->ecc.read_page = lpc32xx_read_page; - nand_chip->ecc.write_page_raw = lpc32xx_write_page_lowlevel; - nand_chip->ecc.write_page = lpc32xx_write_page_lowlevel; - nand_chip->ecc.write_oob = lpc32xx_write_oob; - nand_chip->ecc.read_oob = lpc32xx_read_oob; - nand_chip->ecc.strength = 4; - nand_chip->ecc.bytes = 10; nand_chip->legacy.waitfunc = lpc32xx_waitfunc; nand_chip->options = NAND_NO_SUBPAGE_WRITE; diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c index 6db9d2ed6881..dc7785e30d2f 100644 --- a/drivers/mtd/nand/raw/lpc32xx_slc.c +++ b/drivers/mtd/nand/raw/lpc32xx_slc.c @@ -775,6 +775,9 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip) struct mtd_info *mtd = nand_to_mtd(chip); struct lpc32xx_nand_host *host = nand_get_controller_data(chip); + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + /* OOB and ECC CPU and DMA work areas */ host->ecc_buf = (uint32_t *)(host->data_buf + LPC32XX_DMA_DATA_SIZE); @@ -786,11 +789,22 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip) if (mtd->writesize <= 512) mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops); + chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED; /* These sizes remain the same regardless of page size */ chip->ecc.size = 256; + chip->ecc.strength = 1; chip->ecc.bytes = LPC32XX_SLC_DEV_ECC_BYTES; chip->ecc.prepad = 0; chip->ecc.postpad = 0; + chip->ecc.read_page_raw = lpc32xx_nand_read_page_raw_syndrome; + chip->ecc.read_page = lpc32xx_nand_read_page_syndrome; + chip->ecc.write_page_raw = lpc32xx_nand_write_page_raw_syndrome; + chip->ecc.write_page = lpc32xx_nand_write_page_syndrome; + chip->ecc.write_oob = lpc32xx_nand_write_oob_syndrome; + chip->ecc.read_oob = lpc32xx_nand_read_oob_syndrome; + chip->ecc.calculate = lpc32xx_nand_ecc_calculate; + chip->ecc.correct = nand_correct_data; + chip->ecc.hwctl = lpc32xx_nand_ecc_enable; /* * Use a custom BBT marker setup for small page FLASH that @@ -881,21 +895,9 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) platform_set_drvdata(pdev, host); /* NAND callbacks for LPC32xx SLC hardware */ - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED; chip->legacy.read_byte = lpc32xx_nand_read_byte; chip->legacy.read_buf = lpc32xx_nand_read_buf; chip->legacy.write_buf = lpc32xx_nand_write_buf; - chip->ecc.read_page_raw = lpc32xx_nand_read_page_raw_syndrome; - chip->ecc.read_page = lpc32xx_nand_read_page_syndrome; - chip->ecc.write_page_raw = lpc32xx_nand_write_page_raw_syndrome; - chip->ecc.write_page = lpc32xx_nand_write_page_syndrome; - chip->ecc.write_oob = lpc32xx_nand_write_oob_syndrome; - chip->ecc.read_oob = lpc32xx_nand_read_oob_syndrome; - chip->ecc.calculate = lpc32xx_nand_ecc_calculate; - chip->ecc.correct = nand_correct_data; - chip->ecc.strength = 1; - chip->ecc.hwctl = lpc32xx_nand_ecc_enable; /* * Allocate a large enough buffer for a single huge page plus diff --git a/drivers/mtd/nand/raw/mpc5121_nfc.c b/drivers/mtd/nand/raw/mpc5121_nfc.c index dfd0d3ed5ed0..bcd4a556c959 100644 --- a/drivers/mtd/nand/raw/mpc5121_nfc.c +++ b/drivers/mtd/nand/raw/mpc5121_nfc.c @@ -104,6 +104,7 @@ #define NFC_TIMEOUT (HZ / 10) /* 1/10 s */ struct mpc5121_nfc_prv { + struct nand_controller controller; struct nand_chip chip; int irq; void __iomem *regs; @@ -602,6 +603,20 @@ static void mpc5121_nfc_free(struct device *dev, struct mtd_info *mtd) iounmap(prv->csreg); } +static int mpc5121_nfc_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + +static const struct nand_controller_ops mpc5121_nfc_ops = { + .attach_chip = mpc5121_nfc_attach_chip, +}; + static int mpc5121_nfc_probe(struct platform_device *op) { struct device_node *dn = op->dev.of_node; @@ -634,6 +649,10 @@ static int mpc5121_nfc_probe(struct platform_device *op) chip = &prv->chip; mtd = nand_to_mtd(chip); + nand_controller_init(&prv->controller); + prv->controller.ops = &mpc5121_nfc_ops; + chip->controller = &prv->controller; + mtd->dev.parent = dev; nand_set_controller_data(chip, prv); nand_set_flash_node(chip, dn); @@ -688,8 +707,6 @@ static int mpc5121_nfc_probe(struct platform_device *op) chip->legacy.set_features = nand_get_set_features_notsupp; chip->legacy.get_features = nand_get_set_features_notsupp; chip->bbt_options = NAND_BBT_USE_FLASH; - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; /* Support external chip-select logic on ADS5121 board */ if (of_machine_is_compatible("fsl,mpc5121ads")) { diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c index df9c0f8e4b4e..66211c9311d2 100644 --- a/drivers/mtd/nand/raw/orion_nand.c +++ b/drivers/mtd/nand/raw/orion_nand.c @@ -22,6 +22,7 @@ #include <linux/platform_data/mtd-orion_nand.h> struct orion_nand_info { + struct nand_controller controller; struct nand_chip chip; struct clk *clk; }; @@ -82,6 +83,20 @@ static void orion_nand_read_buf(struct nand_chip *chip, uint8_t *buf, int len) buf[i++] = readb(io_base); } +static int orion_nand_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + +static const struct nand_controller_ops orion_nand_ops = { + .attach_chip = orion_nand_attach_chip, +}; + static int __init orion_nand_probe(struct platform_device *pdev) { struct orion_nand_info *info; @@ -101,6 +116,10 @@ static int __init orion_nand_probe(struct platform_device *pdev) nc = &info->chip; mtd = nand_to_mtd(nc); + nand_controller_init(&info->controller); + info->controller.ops = &orion_nand_ops; + nc->controller = &info->controller; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); io_base = devm_ioremap_resource(&pdev->dev, res); @@ -139,8 +158,6 @@ static int __init orion_nand_probe(struct platform_device *pdev) nc->legacy.IO_ADDR_R = nc->legacy.IO_ADDR_W = io_base; nc->legacy.cmd_ctrl = orion_nand_cmd_ctrl; nc->legacy.read_buf = orion_nand_read_buf; - nc->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - nc->ecc.algo = NAND_ECC_ALGO_HAMMING; if (board->chip_delay) nc->legacy.chip_delay = board->chip_delay; diff --git a/drivers/mtd/nand/raw/pasemi_nand.c b/drivers/mtd/nand/raw/pasemi_nand.c index 2b8f155cc0c5..68c08772d7c2 100644 --- a/drivers/mtd/nand/raw/pasemi_nand.c +++ b/drivers/mtd/nand/raw/pasemi_nand.c @@ -29,6 +29,7 @@ static unsigned int lpcctl; static struct mtd_info *pasemi_nand_mtd; +static struct nand_controller controller; static const char driver_name[] = "pasemi-nand"; static void pasemi_read_buf(struct nand_chip *chip, u_char *buf, int len) @@ -73,6 +74,20 @@ static int pasemi_device_ready(struct nand_chip *chip) return !!(inl(lpcctl) & LBICTRL_LPCCTL_NR); } +static int pasemi_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + +static const struct nand_controller_ops pasemi_ops = { + .attach_chip = pasemi_attach_chip, +}; + static int pasemi_nand_probe(struct platform_device *ofdev) { struct device *dev = &ofdev->dev; @@ -100,6 +115,10 @@ static int pasemi_nand_probe(struct platform_device *ofdev) goto out; } + controller.ops = &pasemi_ops; + nand_controller_init(&controller); + chip->controller = &controller; + pasemi_nand_mtd = nand_to_mtd(chip); /* Link the private data with the MTD structure */ @@ -132,8 +151,6 @@ static int pasemi_nand_probe(struct platform_device *ofdev) chip->legacy.read_buf = pasemi_read_buf; chip->legacy.write_buf = pasemi_write_buf; chip->legacy.chip_delay = 0; - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; /* Enable the following for a flash based bad block table */ chip->bbt_options = NAND_BBT_USE_FLASH; diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c index b98c0d5c413f..7711e1020c21 100644 --- a/drivers/mtd/nand/raw/plat_nand.c +++ b/drivers/mtd/nand/raw/plat_nand.c @@ -14,10 +14,25 @@ #include <linux/mtd/platnand.h> struct plat_nand_data { + struct nand_controller controller; struct nand_chip chip; void __iomem *io_base; }; +static int plat_nand_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + +static const struct nand_controller_ops plat_nand_ops = { + .attach_chip = plat_nand_attach_chip, +}; + /* * Probe for the NAND device. */ @@ -46,6 +61,10 @@ static int plat_nand_probe(struct platform_device *pdev) if (!data) return -ENOMEM; + data->controller.ops = &plat_nand_ops; + nand_controller_init(&data->controller); + data->chip.controller = &data->controller; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); data->io_base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(data->io_base)) @@ -66,9 +85,6 @@ static int plat_nand_probe(struct platform_device *pdev) data->chip.options |= pdata->chip.options; data->chip.bbt_options |= pdata->chip.bbt_options; - data->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - data->chip.ecc.algo = NAND_ECC_ALGO_HAMMING; - platform_set_drvdata(pdev, data); /* Handle any platform specific setup */ diff --git a/drivers/mtd/nand/raw/r852.c b/drivers/mtd/nand/raw/r852.c index 6b7addd2c420..c742354c1b0b 100644 --- a/drivers/mtd/nand/raw/r852.c +++ b/drivers/mtd/nand/raw/r852.c @@ -817,6 +817,29 @@ out: return ret; } +static int r852_attach_chip(struct nand_chip *chip) +{ + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + + chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED; + chip->ecc.size = R852_DMA_LEN; + chip->ecc.bytes = SM_OOB_SIZE; + chip->ecc.strength = 2; + chip->ecc.hwctl = r852_ecc_hwctl; + chip->ecc.calculate = r852_ecc_calculate; + chip->ecc.correct = r852_ecc_correct; + + /* TODO: hack */ + chip->ecc.read_oob = r852_read_oob; + + return 0; +} + +static const struct nand_controller_ops r852_ops = { + .attach_chip = r852_attach_chip, +}; + static int r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) { int error; @@ -858,19 +881,6 @@ static int r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) chip->legacy.read_buf = r852_read_buf; chip->legacy.write_buf = r852_write_buf; - /* ecc */ - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED; - chip->ecc.size = R852_DMA_LEN; - chip->ecc.bytes = SM_OOB_SIZE; - chip->ecc.strength = 2; - chip->ecc.hwctl = r852_ecc_hwctl; - chip->ecc.calculate = r852_ecc_calculate; - chip->ecc.correct = r852_ecc_correct; - - /* TODO: hack */ - chip->ecc.read_oob = r852_read_oob; - /* init our device structure */ dev = kzalloc(sizeof(struct r852_device), GFP_KERNEL); @@ -882,6 +892,10 @@ static int r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) dev->pci_dev = pci_dev; pci_set_drvdata(pci_dev, dev); + nand_controller_init(&dev->controller); + dev->controller.ops = &r852_ops; + chip->controller = &dev->controller; + dev->bounce_buffer = dma_alloc_coherent(&pci_dev->dev, R852_DMA_LEN, &dev->phys_bounce_buffer, GFP_KERNEL); diff --git a/drivers/mtd/nand/raw/r852.h b/drivers/mtd/nand/raw/r852.h index e9ce299c499d..96fe301d15da 100644 --- a/drivers/mtd/nand/raw/r852.h +++ b/drivers/mtd/nand/raw/r852.h @@ -104,6 +104,7 @@ #define DMA_MEMORY 1 struct r852_device { + struct nand_controller controller; void __iomem *mmio; /* mmio */ struct nand_chip *chip; /* nand chip backpointer */ struct pci_dev *pci_dev; /* pci backpointer */ diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c index 1327bfb3d5d3..af98bcc9d689 100644 --- a/drivers/mtd/nand/raw/sharpsl.c +++ b/drivers/mtd/nand/raw/sharpsl.c @@ -20,6 +20,7 @@ #include <linux/io.h> struct sharpsl_nand { + struct nand_controller controller; struct nand_chip chip; void __iomem *io; @@ -96,6 +97,25 @@ static int sharpsl_nand_calculate_ecc(struct nand_chip *chip, return readb(sharpsl->io + ECCCNTR) != 0; } +static int sharpsl_attach_chip(struct nand_chip *chip) +{ + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + + chip->ecc.size = 256; + chip->ecc.bytes = 3; + chip->ecc.strength = 1; + chip->ecc.hwctl = sharpsl_nand_enable_hwecc; + chip->ecc.calculate = sharpsl_nand_calculate_ecc; + chip->ecc.correct = nand_correct_data; + + return 0; +} + +static const struct nand_controller_ops sharpsl_ops = { + .attach_chip = sharpsl_attach_chip, +}; + /* * Main initialization routine */ @@ -136,6 +156,10 @@ static int sharpsl_nand_probe(struct platform_device *pdev) /* Get pointer to private data */ this = (struct nand_chip *)(&sharpsl->chip); + nand_controller_init(&sharpsl->controller); + sharpsl->controller.ops = &sharpsl_ops; + this->controller = &sharpsl->controller; + /* Link the private data with the MTD structure */ mtd = nand_to_mtd(this); mtd->dev.parent = &pdev->dev; @@ -156,15 +180,7 @@ static int sharpsl_nand_probe(struct platform_device *pdev) this->legacy.dev_ready = sharpsl_nand_dev_ready; /* 15 us command delay time */ this->legacy.chip_delay = 15; - /* set eccmode using hardware ECC */ - this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - this->ecc.size = 256; - this->ecc.bytes = 3; - this->ecc.strength = 1; this->badblock_pattern = data->badblock_pattern; - this->ecc.hwctl = sharpsl_nand_enable_hwecc; - this->ecc.calculate = sharpsl_nand_calculate_ecc; - this->ecc.correct = nand_correct_data; /* Scan to find existence of the device */ err = nand_scan(this, 1); diff --git a/drivers/mtd/nand/raw/socrates_nand.c b/drivers/mtd/nand/raw/socrates_nand.c index 0f63ff6f7fe7..70f8305c9b6e 100644 --- a/drivers/mtd/nand/raw/socrates_nand.c +++ b/drivers/mtd/nand/raw/socrates_nand.c @@ -22,6 +22,7 @@ #define FPGA_NAND_DATA_SHIFT 16 struct socrates_nand_host { + struct nand_controller controller; struct nand_chip nand_chip; void __iomem *io_base; struct device *dev; @@ -116,6 +117,20 @@ static int socrates_nand_device_ready(struct nand_chip *nand_chip) return 1; } +static int socrates_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + +static const struct nand_controller_ops socrates_ops = { + .attach_chip = socrates_attach_chip, +}; + /* * Probe for the NAND device. */ @@ -141,6 +156,10 @@ static int socrates_nand_probe(struct platform_device *ofdev) mtd = nand_to_mtd(nand_chip); host->dev = &ofdev->dev; + nand_controller_init(&host->controller); + host->controller.ops = &socrates_ops; + nand_chip->controller = &host->controller; + /* link the private data structures */ nand_set_controller_data(nand_chip, host); nand_set_flash_node(nand_chip, ofdev->dev.of_node); @@ -153,10 +172,6 @@ static int socrates_nand_probe(struct platform_device *ofdev) nand_chip->legacy.read_buf = socrates_nand_read_buf; nand_chip->legacy.dev_ready = socrates_nand_device_ready; - /* enable ECC */ - nand_chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - nand_chip->ecc.algo = NAND_ECC_ALGO_HAMMING; - /* TODO: I have no idea what real delay is. */ nand_chip->legacy.chip_delay = 20; /* 20us command delay time */ diff --git a/drivers/mtd/nand/raw/tmio_nand.c b/drivers/mtd/nand/raw/tmio_nand.c index 235a2f7b1bad..aa6c7e7bbf1b 100644 --- a/drivers/mtd/nand/raw/tmio_nand.c +++ b/drivers/mtd/nand/raw/tmio_nand.c @@ -103,6 +103,7 @@ /*--------------------------------------------------------------------------*/ struct tmio_nand { + struct nand_controller controller; struct nand_chip chip; struct completion comp; @@ -355,6 +356,25 @@ static void tmio_hw_stop(struct platform_device *dev, struct tmio_nand *tmio) cell->disable(dev); } +static int tmio_attach_chip(struct nand_chip *chip) +{ + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + + chip->ecc.size = 512; + chip->ecc.bytes = 6; + chip->ecc.strength = 2; + chip->ecc.hwctl = tmio_nand_enable_hwecc; + chip->ecc.calculate = tmio_nand_calculate_ecc; + chip->ecc.correct = tmio_nand_correct_data; + + return 0; +} + +static const struct nand_controller_ops tmio_ops = { + .attach_chip = tmio_attach_chip, +}; + static int tmio_probe(struct platform_device *dev) { struct tmio_nand_data *data = dev_get_platdata(&dev->dev); @@ -385,6 +405,10 @@ static int tmio_probe(struct platform_device *dev) mtd->name = "tmio-nand"; mtd->dev.parent = &dev->dev; + nand_controller_init(&tmio->controller); + tmio->controller.ops = &tmio_ops; + nand_chip->controller = &tmio->controller; + tmio->ccr = devm_ioremap(&dev->dev, ccr->start, resource_size(ccr)); if (!tmio->ccr) return -EIO; @@ -409,15 +433,6 @@ static int tmio_probe(struct platform_device *dev) nand_chip->legacy.write_buf = tmio_nand_write_buf; nand_chip->legacy.read_buf = tmio_nand_read_buf; - /* set eccmode using hardware ECC */ - nand_chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - nand_chip->ecc.size = 512; - nand_chip->ecc.bytes = 6; - nand_chip->ecc.strength = 2; - nand_chip->ecc.hwctl = tmio_nand_enable_hwecc; - nand_chip->ecc.calculate = tmio_nand_calculate_ecc; - nand_chip->ecc.correct = tmio_nand_correct_data; - if (data) nand_chip->badblock_pattern = data->badblock_pattern; diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c index ef81dce6b5c4..fe8ed2441588 100644 --- a/drivers/mtd/nand/raw/txx9ndfmc.c +++ b/drivers/mtd/nand/raw/txx9ndfmc.c @@ -253,6 +253,11 @@ static int txx9ndfmc_attach_chip(struct nand_chip *chip) { struct mtd_info *mtd = nand_to_mtd(chip); + if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) + return 0; + + chip->ecc.strength = 1; + if (mtd->writesize >= 512) { chip->ecc.size = 512; chip->ecc.bytes = 6; @@ -261,6 +266,10 @@ static int txx9ndfmc_attach_chip(struct nand_chip *chip) chip->ecc.bytes = 3; } + chip->ecc.calculate = txx9ndfmc_calculate_ecc; + chip->ecc.correct = txx9ndfmc_correct_data; + chip->ecc.hwctl = txx9ndfmc_enable_hwecc; + return 0; } @@ -326,11 +335,6 @@ static int __init txx9ndfmc_probe(struct platform_device *dev) chip->legacy.write_buf = txx9ndfmc_write_buf; chip->legacy.cmd_ctrl = txx9ndfmc_cmd_ctrl; chip->legacy.dev_ready = txx9ndfmc_dev_ready; - chip->ecc.calculate = txx9ndfmc_calculate_ecc; - chip->ecc.correct = txx9ndfmc_correct_data; - chip->ecc.hwctl = txx9ndfmc_enable_hwecc; - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; - chip->ecc.strength = 1; chip->legacy.chip_delay = 100; chip->controller = &drvdata->controller; diff --git a/drivers/mtd/nand/raw/xway_nand.c b/drivers/mtd/nand/raw/xway_nand.c index f2dbd63a5c1f..26751976e502 100644 --- a/drivers/mtd/nand/raw/xway_nand.c +++ b/drivers/mtd/nand/raw/xway_nand.c @@ -62,6 +62,7 @@ #define NAND_CON_NANDM 1 struct xway_nand_data { + struct nand_controller controller; struct nand_chip chip; unsigned long csflags; void __iomem *nandaddr; @@ -145,6 +146,20 @@ static void xway_write_buf(struct nand_chip *chip, const u_char *buf, int len) xway_writeb(nand_to_mtd(chip), NAND_WRITE_DATA, buf[i]); } +static int xway_attach_chip(struct nand_chip *chip) +{ + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + + if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) + chip->ecc.algo = NAND_ECC_ALGO_HAMMING; + + return 0; +} + +static const struct nand_controller_ops xway_nand_ops = { + .attach_chip = xway_attach_chip, +}; + /* * Probe for the NAND device. */ @@ -180,8 +195,9 @@ static int xway_nand_probe(struct platform_device *pdev) data->chip.legacy.read_byte = xway_read_byte; data->chip.legacy.chip_delay = 30; - data->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - data->chip.ecc.algo = NAND_ECC_ALGO_HAMMING; + nand_controller_init(&data->controller); + data->controller.ops = &xway_nand_ops; + data->chip.controller = &data->controller; platform_set_drvdata(pdev, data); nand_set_controller_data(&data->chip, data); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 84ecbc6fa0ff..47afc5938c26 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1460,7 +1460,39 @@ static void bond_upper_dev_unlink(struct bonding *bond, struct slave *slave) slave->dev->flags &= ~IFF_SLAVE; } -static struct slave *bond_alloc_slave(struct bonding *bond) +static void slave_kobj_release(struct kobject *kobj) +{ + struct slave *slave = to_slave(kobj); + struct bonding *bond = bond_get_bond_by_slave(slave); + + cancel_delayed_work_sync(&slave->notify_work); + if (BOND_MODE(bond) == BOND_MODE_8023AD) + kfree(SLAVE_AD_INFO(slave)); + + kfree(slave); +} + +static struct kobj_type slave_ktype = { + .release = slave_kobj_release, +#ifdef CONFIG_SYSFS + .sysfs_ops = &slave_sysfs_ops, +#endif +}; + +static int bond_kobj_init(struct slave *slave) +{ + int err; + + err = kobject_init_and_add(&slave->kobj, &slave_ktype, + &(slave->dev->dev.kobj), "bonding_slave"); + if (err) + kobject_put(&slave->kobj); + + return err; +} + +static struct slave *bond_alloc_slave(struct bonding *bond, + struct net_device *slave_dev) { struct slave *slave = NULL; @@ -1468,11 +1500,17 @@ static struct slave *bond_alloc_slave(struct bonding *bond) if (!slave) return NULL; + slave->bond = bond; + slave->dev = slave_dev; + + if (bond_kobj_init(slave)) + return NULL; + if (BOND_MODE(bond) == BOND_MODE_8023AD) { SLAVE_AD_INFO(slave) = kzalloc(sizeof(struct ad_slave_info), GFP_KERNEL); if (!SLAVE_AD_INFO(slave)) { - kfree(slave); + kobject_put(&slave->kobj); return NULL; } } @@ -1481,17 +1519,6 @@ static struct slave *bond_alloc_slave(struct bonding *bond) return slave; } -static void bond_free_slave(struct slave *slave) -{ - struct bonding *bond = bond_get_bond_by_slave(slave); - - cancel_delayed_work_sync(&slave->notify_work); - if (BOND_MODE(bond) == BOND_MODE_8023AD) - kfree(SLAVE_AD_INFO(slave)); - - kfree(slave); -} - static void bond_fill_ifbond(struct bonding *bond, struct ifbond *info) { info->bond_mode = BOND_MODE(bond); @@ -1678,14 +1705,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, goto err_undo_flags; } - new_slave = bond_alloc_slave(bond); + new_slave = bond_alloc_slave(bond, slave_dev); if (!new_slave) { res = -ENOMEM; goto err_undo_flags; } - new_slave->bond = bond; - new_slave->dev = slave_dev; /* Set the new_slave's queue_id to be zero. Queue ID mapping * is set via sysfs or module option if desired. */ @@ -2007,7 +2032,7 @@ err_restore_mtu: dev_set_mtu(slave_dev, new_slave->original_mtu); err_free: - bond_free_slave(new_slave); + kobject_put(&new_slave->kobj); err_undo_flags: /* Enslave of first slave has failed and we need to fix master's mac */ @@ -2187,7 +2212,7 @@ static int __bond_release_one(struct net_device *bond_dev, if (!netif_is_bond_master(slave_dev)) slave_dev->priv_flags &= ~IFF_BONDING; - bond_free_slave(slave); + kobject_put(&slave->kobj); return 0; } diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 9abfaae1c6f7..a4e4e15f574d 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -745,6 +745,19 @@ const struct bond_option *bond_opt_get(unsigned int option) return &bond_opts[option]; } +static void bond_set_xfrm_features(struct net_device *bond_dev, u64 mode) +{ + if (!IS_ENABLED(CONFIG_XFRM_OFFLOAD)) + return; + + if (mode == BOND_MODE_ACTIVEBACKUP) + bond_dev->wanted_features |= BOND_XFRM_FEATURES; + else + bond_dev->wanted_features &= ~BOND_XFRM_FEATURES; + + netdev_update_features(bond_dev); +} + static int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newval) { @@ -767,13 +780,8 @@ static int bond_option_mode_set(struct bonding *bond, if (newval->value == BOND_MODE_ALB) bond->params.tlb_dynamic_lb = 1; -#ifdef CONFIG_XFRM_OFFLOAD - if (newval->value == BOND_MODE_ACTIVEBACKUP) - bond->dev->wanted_features |= BOND_XFRM_FEATURES; - else - bond->dev->wanted_features &= ~BOND_XFRM_FEATURES; - netdev_change_features(bond->dev); -#endif /* CONFIG_XFRM_OFFLOAD */ + if (bond->dev->reg_state == NETREG_REGISTERED) + bond_set_xfrm_features(bond->dev, newval->value); /* don't cache arp_validate between modes */ bond->params.arp_validate = BOND_ARP_VALIDATE_NONE; diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c index 9b8346638f69..fd07561da034 100644 --- a/drivers/net/bonding/bond_sysfs_slave.c +++ b/drivers/net/bonding/bond_sysfs_slave.c @@ -121,7 +121,6 @@ static const struct slave_attribute *slave_attrs[] = { }; #define to_slave_attr(_at) container_of(_at, struct slave_attribute, attr) -#define to_slave(obj) container_of(obj, struct slave, kobj) static ssize_t slave_show(struct kobject *kobj, struct attribute *attr, char *buf) @@ -132,28 +131,15 @@ static ssize_t slave_show(struct kobject *kobj, return slave_attr->show(slave, buf); } -static const struct sysfs_ops slave_sysfs_ops = { +const struct sysfs_ops slave_sysfs_ops = { .show = slave_show, }; -static struct kobj_type slave_ktype = { -#ifdef CONFIG_SYSFS - .sysfs_ops = &slave_sysfs_ops, -#endif -}; - int bond_sysfs_slave_add(struct slave *slave) { const struct slave_attribute **a; int err; - err = kobject_init_and_add(&slave->kobj, &slave_ktype, - &(slave->dev->dev.kobj), "bonding_slave"); - if (err) { - kobject_put(&slave->kobj); - return err; - } - for (a = slave_attrs; *a; ++a) { err = sysfs_create_file(&slave->kobj, &((*a)->attr)); if (err) { @@ -171,6 +157,4 @@ void bond_sysfs_slave_del(struct slave *slave) for (a = slave_attrs; *a; ++a) sysfs_remove_file(&slave->kobj, &((*a)->attr)); - - kobject_put(&slave->kobj); } diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index 1ccdbe89585b..1a9e9b9a4bf6 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -1295,12 +1295,22 @@ int c_can_power_up(struct net_device *dev) time_after(time_out, jiffies)) cpu_relax(); - if (time_after(jiffies, time_out)) - return -ETIMEDOUT; + if (time_after(jiffies, time_out)) { + ret = -ETIMEDOUT; + goto err_out; + } ret = c_can_start(dev); - if (!ret) - c_can_irq_control(priv, true); + if (ret) + goto err_out; + + c_can_irq_control(priv, true); + + return 0; + +err_out: + c_can_reset_ram(priv, false); + c_can_pm_runtime_put_sync(priv); return ret; } diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 6dee4f8f2024..81e39d7507d8 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -592,7 +592,7 @@ static void can_restart(struct net_device *dev) cf->can_id |= CAN_ERR_RESTARTED; - netif_rx(skb); + netif_rx_ni(skb); stats->rx_packets++; stats->rx_bytes += cf->can_dlc; diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 881799bd9c5e..99e5f272205d 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -728,8 +728,10 @@ static int flexcan_get_berr_counter(const struct net_device *dev, int err; err = pm_runtime_get_sync(priv->dev); - if (err < 0) + if (err < 0) { + pm_runtime_put_noidle(priv->dev); return err; + } err = __flexcan_get_berr_counter(dev, bec); @@ -1565,14 +1567,10 @@ static int flexcan_chip_start(struct net_device *dev) priv->write(reg_ctrl2, ®s->ctrl2); } - err = flexcan_transceiver_enable(priv); - if (err) - goto out_chip_disable; - /* synchronize with the can bus */ err = flexcan_chip_unfreeze(priv); if (err) - goto out_transceiver_disable; + goto out_chip_disable; priv->can.state = CAN_STATE_ERROR_ACTIVE; @@ -1590,8 +1588,6 @@ static int flexcan_chip_start(struct net_device *dev) return 0; - out_transceiver_disable: - flexcan_transceiver_disable(priv); out_chip_disable: flexcan_chip_disable(priv); return err; @@ -1621,7 +1617,6 @@ static int __flexcan_chip_stop(struct net_device *dev, bool disable_on_error) priv->write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL, ®s->ctrl); - flexcan_transceiver_disable(priv); priv->can.state = CAN_STATE_STOPPED; return 0; @@ -1654,17 +1649,23 @@ static int flexcan_open(struct net_device *dev) } err = pm_runtime_get_sync(priv->dev); - if (err < 0) + if (err < 0) { + pm_runtime_put_noidle(priv->dev); return err; + } err = open_candev(dev); if (err) goto out_runtime_put; - err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev); + err = flexcan_transceiver_enable(priv); if (err) goto out_close; + err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev); + if (err) + goto out_transceiver_disable; + if (priv->can.ctrlmode & CAN_CTRLMODE_FD) priv->mb_size = sizeof(struct flexcan_mb) + CANFD_MAX_DLEN; else @@ -1716,6 +1717,8 @@ static int flexcan_open(struct net_device *dev) can_rx_offload_del(&priv->offload); out_free_irq: free_irq(dev->irq, dev); + out_transceiver_disable: + flexcan_transceiver_disable(priv); out_close: close_candev(dev); out_runtime_put: @@ -1734,6 +1737,7 @@ static int flexcan_close(struct net_device *dev) can_rx_offload_del(&priv->offload); free_irq(dev->irq, dev); + flexcan_transceiver_disable(priv); close_candev(dev); pm_runtime_put(priv->dev); @@ -1852,7 +1856,7 @@ static int flexcan_setup_stop_mode(struct platform_device *pdev) return -EINVAL; /* stop mode property format is: - * <&gpr req_gpr>. + * <&gpr req_gpr req_bit>. */ ret = of_property_read_u32_array(np, "fsl,stop-mode", out_val, ARRAY_SIZE(out_val)); diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 6f766918211a..43151dd6cb1c 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -287,12 +287,12 @@ struct kvaser_pciefd_tx_packet { static const struct can_bittiming_const kvaser_pciefd_bittiming_const = { .name = KVASER_PCIEFD_DRV_NAME, .tseg1_min = 1, - .tseg1_max = 255, + .tseg1_max = 512, .tseg2_min = 1, .tseg2_max = 32, .sjw_max = 16, .brp_min = 1, - .brp_max = 4096, + .brp_max = 8192, .brp_inc = 1, }; @@ -692,8 +692,10 @@ static int kvaser_pciefd_open(struct net_device *netdev) return err; err = kvaser_pciefd_bus_on(can); - if (err) + if (err) { + close_candev(netdev); return err; + } return 0; } diff --git a/drivers/net/can/m_can/Kconfig b/drivers/net/can/m_can/Kconfig index 48be627c85c2..5f9f8192dd0b 100644 --- a/drivers/net/can/m_can/Kconfig +++ b/drivers/net/can/m_can/Kconfig @@ -16,7 +16,8 @@ config CAN_M_CAN_PLATFORM config CAN_M_CAN_TCAN4X5X depends on CAN_M_CAN - depends on REGMAP_SPI + depends on SPI + select REGMAP_SPI tristate "TCAN4X5X M_CAN device" help Say Y here if you want support for Texas Instruments TCAN4x5x diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 02c5795b7393..61a93b192037 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -665,7 +665,7 @@ static int m_can_handle_state_change(struct net_device *dev, unsigned int ecr; switch (new_state) { - case CAN_STATE_ERROR_ACTIVE: + case CAN_STATE_ERROR_WARNING: /* error warning state */ cdev->can.can_stats.error_warning++; cdev->can.state = CAN_STATE_ERROR_WARNING; @@ -694,7 +694,7 @@ static int m_can_handle_state_change(struct net_device *dev, __m_can_get_berr_counter(dev, &bec); switch (new_state) { - case CAN_STATE_ERROR_ACTIVE: + case CAN_STATE_ERROR_WARNING: /* error warning state */ cf->can_id |= CAN_ERR_CRTL; cf->data[1] = (bec.txerr > bec.rxerr) ? @@ -956,6 +956,8 @@ static irqreturn_t m_can_isr(int irq, void *dev_id) struct net_device_stats *stats = &dev->stats; u32 ir; + if (pm_runtime_suspended(cdev->dev)) + return IRQ_NONE; ir = m_can_read(cdev, M_CAN_IR); if (!ir) return IRQ_NONE; @@ -1031,7 +1033,7 @@ static const struct can_bittiming_const m_can_bittiming_const_31X = { .name = KBUILD_MODNAME, .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ .tseg1_max = 256, - .tseg2_min = 1, /* Time segment 2 = phase_seg2 */ + .tseg2_min = 2, /* Time segment 2 = phase_seg2 */ .tseg2_max = 128, .sjw_max = 128, .brp_min = 1, @@ -1383,6 +1385,8 @@ static int m_can_dev_setup(struct m_can_classdev *m_can_dev) &m_can_data_bittiming_const_31X; break; case 32: + case 33: + /* Support both MCAN version v3.2.x and v3.3.0 */ m_can_dev->can.bittiming_const = m_can_dev->bit_timing ? m_can_dev->bit_timing : &m_can_bittiming_const_31X; @@ -1414,6 +1418,9 @@ static void m_can_stop(struct net_device *dev) /* disable all interrupts */ m_can_disable_all_interrupts(cdev); + /* Set init mode to disengage from the network */ + m_can_config_endisable(cdev, true); + /* set the state as STOPPED */ cdev->can.state = CAN_STATE_STOPPED; } @@ -1648,7 +1655,7 @@ static int m_can_open(struct net_device *dev) INIT_WORK(&cdev->tx_work, m_can_tx_work_queue); err = request_threaded_irq(dev->irq, NULL, m_can_isr, - IRQF_ONESHOT | IRQF_TRIGGER_FALLING, + IRQF_ONESHOT, dev->name, dev); } else { err = request_irq(dev->irq, m_can_isr, IRQF_SHARED, dev->name, @@ -1812,6 +1819,12 @@ out: } EXPORT_SYMBOL_GPL(m_can_class_allocate_dev); +void m_can_class_free_dev(struct net_device *net) +{ + free_candev(net); +} +EXPORT_SYMBOL_GPL(m_can_class_free_dev); + int m_can_class_register(struct m_can_classdev *m_can_dev) { int ret; @@ -1850,7 +1863,6 @@ pm_runtime_fail: if (ret) { if (m_can_dev->pm_clock_support) pm_runtime_disable(m_can_dev->dev); - free_candev(m_can_dev->net); } return ret; @@ -1908,8 +1920,6 @@ void m_can_class_unregister(struct m_can_classdev *m_can_dev) unregister_candev(m_can_dev->net); m_can_clk_stop(m_can_dev); - - free_candev(m_can_dev->net); } EXPORT_SYMBOL_GPL(m_can_class_unregister); diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index 49f42b50627a..b2699a7c9997 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -99,6 +99,7 @@ struct m_can_classdev { }; struct m_can_classdev *m_can_class_allocate_dev(struct device *dev); +void m_can_class_free_dev(struct net_device *net); int m_can_class_register(struct m_can_classdev *cdev); void m_can_class_unregister(struct m_can_classdev *cdev); int m_can_class_get_clocks(struct m_can_classdev *cdev); diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c index e6d0cb9ee02f..161cb9be018c 100644 --- a/drivers/net/can/m_can/m_can_platform.c +++ b/drivers/net/can/m_can/m_can_platform.c @@ -67,32 +67,36 @@ static int m_can_plat_probe(struct platform_device *pdev) return -ENOMEM; priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; + if (!priv) { + ret = -ENOMEM; + goto probe_fail; + } mcan_class->device_data = priv; - m_can_class_get_clocks(mcan_class); + ret = m_can_class_get_clocks(mcan_class); + if (ret) + goto probe_fail; res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "m_can"); addr = devm_ioremap_resource(&pdev->dev, res); irq = platform_get_irq_byname(pdev, "int0"); if (IS_ERR(addr) || irq < 0) { ret = -EINVAL; - goto failed_ret; + goto probe_fail; } /* message ram could be shared */ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "message_ram"); if (!res) { ret = -ENODEV; - goto failed_ret; + goto probe_fail; } mram_addr = devm_ioremap(&pdev->dev, res->start, resource_size(res)); if (!mram_addr) { ret = -ENOMEM; - goto failed_ret; + goto probe_fail; } priv->base = addr; @@ -111,9 +115,10 @@ static int m_can_plat_probe(struct platform_device *pdev) m_can_init_ram(mcan_class); - ret = m_can_class_register(mcan_class); + return m_can_class_register(mcan_class); -failed_ret: +probe_fail: + m_can_class_free_dev(mcan_class->net); return ret; } @@ -134,6 +139,8 @@ static int m_can_plat_remove(struct platform_device *pdev) m_can_class_unregister(mcan_class); + m_can_class_free_dev(mcan_class->net); + platform_set_drvdata(pdev, NULL); return 0; diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c index eacd428e07e9..7347ab39c5b6 100644 --- a/drivers/net/can/m_can/tcan4x5x.c +++ b/drivers/net/can/m_can/tcan4x5x.c @@ -440,14 +440,18 @@ static int tcan4x5x_can_probe(struct spi_device *spi) return -ENOMEM; priv = devm_kzalloc(&spi->dev, sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; + if (!priv) { + ret = -ENOMEM; + goto out_m_can_class_free_dev; + } priv->power = devm_regulator_get_optional(&spi->dev, "vsup"); - if (PTR_ERR(priv->power) == -EPROBE_DEFER) - return -EPROBE_DEFER; - else + if (PTR_ERR(priv->power) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto out_m_can_class_free_dev; + } else { priv->power = NULL; + } mcan_class->device_data = priv; @@ -460,8 +464,10 @@ static int tcan4x5x_can_probe(struct spi_device *spi) } /* Sanity check */ - if (freq < 20000000 || freq > TCAN4X5X_EXT_CLK_DEF) - return -ERANGE; + if (freq < 20000000 || freq > TCAN4X5X_EXT_CLK_DEF) { + ret = -ERANGE; + goto out_m_can_class_free_dev; + } priv->reg_offset = TCAN4X5X_MCAN_OFFSET; priv->mram_start = TCAN4X5X_MRAM_START; @@ -483,14 +489,18 @@ static int tcan4x5x_can_probe(struct spi_device *spi) spi->bits_per_word = 32; ret = spi_setup(spi); if (ret) - goto out_clk; + goto out_m_can_class_free_dev; priv->regmap = devm_regmap_init(&spi->dev, &tcan4x5x_bus, &spi->dev, &tcan4x5x_regmap); + if (IS_ERR(priv->regmap)) { + ret = PTR_ERR(priv->regmap); + goto out_m_can_class_free_dev; + } ret = tcan4x5x_power_enable(priv->power, 1); if (ret) - goto out_clk; + goto out_m_can_class_free_dev; ret = tcan4x5x_parse_config(mcan_class); if (ret) @@ -509,13 +519,10 @@ static int tcan4x5x_can_probe(struct spi_device *spi) out_power: tcan4x5x_power_enable(priv->power, 0); -out_clk: - if (!IS_ERR(mcan_class->cclk)) { - clk_disable_unprepare(mcan_class->cclk); - clk_disable_unprepare(mcan_class->hclk); - } - + out_m_can_class_free_dev: + m_can_class_free_dev(mcan_class->net); dev_err(&spi->dev, "Probe failed, err=%d\n", ret); + return ret; } @@ -523,9 +530,11 @@ static int tcan4x5x_can_remove(struct spi_device *spi) { struct tcan4x5x_priv *priv = spi_get_drvdata(spi); + m_can_class_unregister(priv->mcan_dev); + tcan4x5x_power_enable(priv->power, 0); - m_can_class_unregister(priv->mcan_dev); + m_can_class_free_dev(priv->mcan_dev->net); return 0; } diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c index 9f107798f904..25a4d7d0b349 100644 --- a/drivers/net/can/sja1000/sja1000.c +++ b/drivers/net/can/sja1000/sja1000.c @@ -474,7 +474,6 @@ static int sja1000_err(struct net_device *dev, uint8_t isrc, uint8_t status) netdev_dbg(dev, "arbitration lost interrupt\n"); alc = priv->read_reg(priv, SJA1000_ALC); priv->can.can_stats.arbitration_lost++; - stats->tx_errors++; cf->can_id |= CAN_ERR_LOSTARB; cf->data[0] = alc & 0x1f; } diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c index 9d2faaa39ce4..c9ca8b9fceb9 100644 --- a/drivers/net/can/softing/softing_main.c +++ b/drivers/net/can/softing/softing_main.c @@ -382,8 +382,13 @@ static int softing_netdev_open(struct net_device *ndev) /* check or determine and set bittime */ ret = open_candev(ndev); - if (!ret) - ret = softing_startstop(ndev, 1); + if (ret) + return ret; + + ret = softing_startstop(ndev, 1); + if (ret < 0) + close_candev(ndev); + return ret; } diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 9c215f7c5f81..8a39be076e14 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -2738,6 +2738,10 @@ static int mcp251xfd_probe(struct spi_device *spi) u32 freq; int err; + if (!spi->irq) + return dev_err_probe(&spi->dev, -ENXIO, + "No IRQ specified (maybe node \"interrupts-extended\" in DT missing)!\n"); + rx_int = devm_gpiod_get_optional(&spi->dev, "microchip,rx-int", GPIOD_IN); if (PTR_ERR(rx_int) == -EPROBE_DEFER) diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index e2c6cf4b2228..b3f2f4fe5ee0 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -604,7 +604,6 @@ static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status) netdev_dbg(dev, "arbitration lost interrupt\n"); alc = readl(priv->base + SUN4I_REG_STA_ADDR); priv->can.can_stats.arbitration_lost++; - stats->tx_errors++; if (likely(skb)) { cf->can_id |= CAN_ERR_LOSTARB; cf->data[0] = (alc >> 8) & 0x1f; diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index 9913f5458279..2c22f40e12bd 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -881,7 +881,8 @@ static int ti_hecc_probe(struct platform_device *pdev) priv->base = devm_platform_ioremap_resource_byname(pdev, "hecc"); if (IS_ERR(priv->base)) { dev_err(&pdev->dev, "hecc ioremap failed\n"); - return PTR_ERR(priv->base); + err = PTR_ERR(priv->base); + goto probe_exit_candev; } /* handle hecc-ram memory */ @@ -889,20 +890,22 @@ static int ti_hecc_probe(struct platform_device *pdev) "hecc-ram"); if (IS_ERR(priv->hecc_ram)) { dev_err(&pdev->dev, "hecc-ram ioremap failed\n"); - return PTR_ERR(priv->hecc_ram); + err = PTR_ERR(priv->hecc_ram); + goto probe_exit_candev; } /* handle mbx memory */ priv->mbx = devm_platform_ioremap_resource_byname(pdev, "mbx"); if (IS_ERR(priv->mbx)) { dev_err(&pdev->dev, "mbx ioremap failed\n"); - return PTR_ERR(priv->mbx); + err = PTR_ERR(priv->mbx); + goto probe_exit_candev; } irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); if (!irq) { dev_err(&pdev->dev, "No irq resource\n"); - goto probe_exit; + goto probe_exit_candev; } priv->ndev = ndev; @@ -966,7 +969,7 @@ probe_exit_release_clk: clk_put(priv->clk); probe_exit_candev: free_candev(ndev); -probe_exit: + return err; } diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 3005157059ca..018ca3b057a3 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -63,21 +63,27 @@ enum gs_can_identify_mode { }; /* data types passed between host and device */ + +/* The firmware on the original USB2CAN by Geschwister Schneider + * Technologie Entwicklungs- und Vertriebs UG exchanges all data + * between the host and the device in host byte order. This is done + * with the struct gs_host_config::byte_order member, which is sent + * first to indicate the desired byte order. + * + * The widely used open source firmware candleLight doesn't support + * this feature and exchanges the data in little endian byte order. + */ struct gs_host_config { - u32 byte_order; + __le32 byte_order; } __packed; -/* All data exchanged between host and device is exchanged in host byte order, - * thanks to the struct gs_host_config byte_order member, which is sent first - * to indicate the desired byte order. - */ struct gs_device_config { u8 reserved1; u8 reserved2; u8 reserved3; u8 icount; - u32 sw_version; - u32 hw_version; + __le32 sw_version; + __le32 hw_version; } __packed; #define GS_CAN_MODE_NORMAL 0 @@ -87,26 +93,26 @@ struct gs_device_config { #define GS_CAN_MODE_ONE_SHOT BIT(3) struct gs_device_mode { - u32 mode; - u32 flags; + __le32 mode; + __le32 flags; } __packed; struct gs_device_state { - u32 state; - u32 rxerr; - u32 txerr; + __le32 state; + __le32 rxerr; + __le32 txerr; } __packed; struct gs_device_bittiming { - u32 prop_seg; - u32 phase_seg1; - u32 phase_seg2; - u32 sjw; - u32 brp; + __le32 prop_seg; + __le32 phase_seg1; + __le32 phase_seg2; + __le32 sjw; + __le32 brp; } __packed; struct gs_identify_mode { - u32 mode; + __le32 mode; } __packed; #define GS_CAN_FEATURE_LISTEN_ONLY BIT(0) @@ -117,23 +123,23 @@ struct gs_identify_mode { #define GS_CAN_FEATURE_IDENTIFY BIT(5) struct gs_device_bt_const { - u32 feature; - u32 fclk_can; - u32 tseg1_min; - u32 tseg1_max; - u32 tseg2_min; - u32 tseg2_max; - u32 sjw_max; - u32 brp_min; - u32 brp_max; - u32 brp_inc; + __le32 feature; + __le32 fclk_can; + __le32 tseg1_min; + __le32 tseg1_max; + __le32 tseg2_min; + __le32 tseg2_max; + __le32 sjw_max; + __le32 brp_min; + __le32 brp_max; + __le32 brp_inc; } __packed; #define GS_CAN_FLAG_OVERFLOW 1 struct gs_host_frame { u32 echo_id; - u32 can_id; + __le32 can_id; u8 can_dlc; u8 channel; @@ -329,13 +335,13 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) if (!skb) return; - cf->can_id = hf->can_id; + cf->can_id = le32_to_cpu(hf->can_id); cf->can_dlc = get_can_dlc(hf->can_dlc); memcpy(cf->data, hf->data, 8); /* ERROR frames tell us information about the controller */ - if (hf->can_id & CAN_ERR_FLAG) + if (le32_to_cpu(hf->can_id) & CAN_ERR_FLAG) gs_update_state(dev, cf); netdev->stats.rx_packets++; @@ -418,11 +424,11 @@ static int gs_usb_set_bittiming(struct net_device *netdev) if (!dbt) return -ENOMEM; - dbt->prop_seg = bt->prop_seg; - dbt->phase_seg1 = bt->phase_seg1; - dbt->phase_seg2 = bt->phase_seg2; - dbt->sjw = bt->sjw; - dbt->brp = bt->brp; + dbt->prop_seg = cpu_to_le32(bt->prop_seg); + dbt->phase_seg1 = cpu_to_le32(bt->phase_seg1); + dbt->phase_seg2 = cpu_to_le32(bt->phase_seg2); + dbt->sjw = cpu_to_le32(bt->sjw); + dbt->brp = cpu_to_le32(bt->brp); /* request bit timings */ rc = usb_control_msg(interface_to_usbdev(intf), @@ -503,7 +509,7 @@ static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, cf = (struct can_frame *)skb->data; - hf->can_id = cf->can_id; + hf->can_id = cpu_to_le32(cf->can_id); hf->can_dlc = cf->can_dlc; memcpy(hf->data, cf->data, cf->can_dlc); @@ -573,6 +579,7 @@ static int gs_can_open(struct net_device *netdev) int rc, i; struct gs_device_mode *dm; u32 ctrlmode; + u32 flags = 0; rc = open_candev(netdev); if (rc) @@ -640,24 +647,24 @@ static int gs_can_open(struct net_device *netdev) /* flags */ ctrlmode = dev->can.ctrlmode; - dm->flags = 0; if (ctrlmode & CAN_CTRLMODE_LOOPBACK) - dm->flags |= GS_CAN_MODE_LOOP_BACK; + flags |= GS_CAN_MODE_LOOP_BACK; else if (ctrlmode & CAN_CTRLMODE_LISTENONLY) - dm->flags |= GS_CAN_MODE_LISTEN_ONLY; + flags |= GS_CAN_MODE_LISTEN_ONLY; /* Controller is not allowed to retry TX * this mode is unavailable on atmels uc3c hardware */ if (ctrlmode & CAN_CTRLMODE_ONE_SHOT) - dm->flags |= GS_CAN_MODE_ONE_SHOT; + flags |= GS_CAN_MODE_ONE_SHOT; if (ctrlmode & CAN_CTRLMODE_3_SAMPLES) - dm->flags |= GS_CAN_MODE_TRIPLE_SAMPLE; + flags |= GS_CAN_MODE_TRIPLE_SAMPLE; /* finally start device */ - dm->mode = GS_CAN_MODE_START; + dm->mode = cpu_to_le32(GS_CAN_MODE_START); + dm->flags = cpu_to_le32(flags); rc = usb_control_msg(interface_to_usbdev(dev->iface), usb_sndctrlpipe(interface_to_usbdev(dev->iface), 0), GS_USB_BREQ_MODE, @@ -737,9 +744,9 @@ static int gs_usb_set_identify(struct net_device *netdev, bool do_identify) return -ENOMEM; if (do_identify) - imode->mode = GS_CAN_IDENTIFY_ON; + imode->mode = cpu_to_le32(GS_CAN_IDENTIFY_ON); else - imode->mode = GS_CAN_IDENTIFY_OFF; + imode->mode = cpu_to_le32(GS_CAN_IDENTIFY_OFF); rc = usb_control_msg(interface_to_usbdev(dev->iface), usb_sndctrlpipe(interface_to_usbdev(dev->iface), @@ -790,6 +797,7 @@ static struct gs_can *gs_make_candev(unsigned int channel, struct net_device *netdev; int rc; struct gs_device_bt_const *bt_const; + u32 feature; bt_const = kmalloc(sizeof(*bt_const), GFP_KERNEL); if (!bt_const) @@ -830,14 +838,14 @@ static struct gs_can *gs_make_candev(unsigned int channel, /* dev setup */ strcpy(dev->bt_const.name, "gs_usb"); - dev->bt_const.tseg1_min = bt_const->tseg1_min; - dev->bt_const.tseg1_max = bt_const->tseg1_max; - dev->bt_const.tseg2_min = bt_const->tseg2_min; - dev->bt_const.tseg2_max = bt_const->tseg2_max; - dev->bt_const.sjw_max = bt_const->sjw_max; - dev->bt_const.brp_min = bt_const->brp_min; - dev->bt_const.brp_max = bt_const->brp_max; - dev->bt_const.brp_inc = bt_const->brp_inc; + dev->bt_const.tseg1_min = le32_to_cpu(bt_const->tseg1_min); + dev->bt_const.tseg1_max = le32_to_cpu(bt_const->tseg1_max); + dev->bt_const.tseg2_min = le32_to_cpu(bt_const->tseg2_min); + dev->bt_const.tseg2_max = le32_to_cpu(bt_const->tseg2_max); + dev->bt_const.sjw_max = le32_to_cpu(bt_const->sjw_max); + dev->bt_const.brp_min = le32_to_cpu(bt_const->brp_min); + dev->bt_const.brp_max = le32_to_cpu(bt_const->brp_max); + dev->bt_const.brp_inc = le32_to_cpu(bt_const->brp_inc); dev->udev = interface_to_usbdev(intf); dev->iface = intf; @@ -854,28 +862,29 @@ static struct gs_can *gs_make_candev(unsigned int channel, /* can setup */ dev->can.state = CAN_STATE_STOPPED; - dev->can.clock.freq = bt_const->fclk_can; + dev->can.clock.freq = le32_to_cpu(bt_const->fclk_can); dev->can.bittiming_const = &dev->bt_const; dev->can.do_set_bittiming = gs_usb_set_bittiming; dev->can.ctrlmode_supported = 0; - if (bt_const->feature & GS_CAN_FEATURE_LISTEN_ONLY) + feature = le32_to_cpu(bt_const->feature); + if (feature & GS_CAN_FEATURE_LISTEN_ONLY) dev->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY; - if (bt_const->feature & GS_CAN_FEATURE_LOOP_BACK) + if (feature & GS_CAN_FEATURE_LOOP_BACK) dev->can.ctrlmode_supported |= CAN_CTRLMODE_LOOPBACK; - if (bt_const->feature & GS_CAN_FEATURE_TRIPLE_SAMPLE) + if (feature & GS_CAN_FEATURE_TRIPLE_SAMPLE) dev->can.ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES; - if (bt_const->feature & GS_CAN_FEATURE_ONE_SHOT) + if (feature & GS_CAN_FEATURE_ONE_SHOT) dev->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT; SET_NETDEV_DEV(netdev, &intf->dev); - if (dconf->sw_version > 1) - if (bt_const->feature & GS_CAN_FEATURE_IDENTIFY) + if (le32_to_cpu(dconf->sw_version) > 1) + if (feature & GS_CAN_FEATURE_IDENTIFY) netdev->ethtool_ops = &gs_usb_ethtool_ops; kfree(bt_const); @@ -910,7 +919,7 @@ static int gs_usb_probe(struct usb_interface *intf, if (!hconf) return -ENOMEM; - hconf->byte_order = 0x0000beef; + hconf->byte_order = cpu_to_le32(0x0000beef); /* send host config */ rc = usb_control_msg(interface_to_usbdev(intf), diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 7ab87a758754..218fadc91155 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -367,7 +367,7 @@ static const struct can_bittiming_const kvaser_usb_hydra_kcan_bittiming_c = { .tseg2_max = 32, .sjw_max = 16, .brp_min = 1, - .brp_max = 4096, + .brp_max = 8192, .brp_inc = 1, }; diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 5857b37dcd96..e97f2e0da6b0 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -326,8 +326,6 @@ static netdev_tx_t mcba_usb_start_xmit(struct sk_buff *skb, if (!ctx) return NETDEV_TX_BUSY; - can_put_echo_skb(skb, priv->netdev, ctx->ndx); - if (cf->can_id & CAN_EFF_FLAG) { /* SIDH | SIDL | EIDH | EIDL * 28 - 21 | 20 19 18 x x x 17 16 | 15 - 8 | 7 - 0 @@ -357,6 +355,8 @@ static netdev_tx_t mcba_usb_start_xmit(struct sk_buff *skb, if (cf->can_id & CAN_RTR_FLAG) usb_msg.dlc |= MCBA_DLC_RTR_MASK; + can_put_echo_skb(skb, priv->netdev, ctx->ndx); + err = mcba_usb_xmit(priv, (struct mcba_usb_msg *)&usb_msg, ctx); if (err) goto xmit_failed; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index c2764799f9ef..204ccb27d6d9 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -156,7 +156,7 @@ void peak_usb_get_ts_time(struct peak_time_ref *time_ref, u32 ts, ktime_t *time) if (time_ref->ts_dev_1 < time_ref->ts_dev_2) { /* case when event time (tsw) wraps */ if (ts < time_ref->ts_dev_1) - delta_ts = 1 << time_ref->adapter->ts_used_bits; + delta_ts = BIT_ULL(time_ref->adapter->ts_used_bits); /* Otherwise, sync time counter (ts_dev_2) has wrapped: * handle case when event time (tsn) hasn't. @@ -168,7 +168,7 @@ void peak_usb_get_ts_time(struct peak_time_ref *time_ref, u32 ts, ktime_t *time) * tsn ts */ } else if (time_ref->ts_dev_1 < ts) { - delta_ts = -(1 << time_ref->adapter->ts_used_bits); + delta_ts = -BIT_ULL(time_ref->adapter->ts_used_bits); } /* add delay between last sync and event timestamps */ diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 74db81dafee3..09701c17f3f6 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -26,6 +26,7 @@ */ #include <linux/clk.h> +#include <linux/delay.h> #include <linux/etherdevice.h> #include <linux/firmware.h> #include <linux/if_bridge.h> @@ -1837,6 +1838,16 @@ static int gswip_gphy_fw_list(struct gswip_priv *priv, i++; } + /* The standalone PHY11G requires 300ms to be fully + * initialized and ready for any MDIO communication after being + * taken out of reset. For the SoC-internal GPHY variant there + * is no (known) documentation for the minimum time after a + * reset. Use the same value as for the standalone variant as + * some users have reported internal PHYs not being detected + * without any delay. + */ + msleep(300); + return 0; remove_gphy: diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index bd297ae7cf9e..34cca0a4b31c 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2297,6 +2297,8 @@ static void mv88e6xxx_hardware_reset(struct mv88e6xxx_chip *chip) usleep_range(10000, 20000); gpiod_set_value_cansleep(gpiod, 0); usleep_range(10000, 20000); + + mv88e6xxx_g1_wait_eeprom_done(chip); } } diff --git a/drivers/net/dsa/mv88e6xxx/devlink.c b/drivers/net/dsa/mv88e6xxx/devlink.c index 10cd1bfd81a0..ade04c036fd9 100644 --- a/drivers/net/dsa/mv88e6xxx/devlink.c +++ b/drivers/net/dsa/mv88e6xxx/devlink.c @@ -393,8 +393,10 @@ static int mv88e6xxx_region_atu_snapshot(struct devlink *dl, mv88e6xxx_reg_lock(chip); err = mv88e6xxx_fid_map(chip, fid_bitmap); - if (err) + if (err) { + kfree(table); goto out; + } while (1) { fid = find_next_bit(fid_bitmap, MV88E6XXX_N_FID, fid + 1); diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index f62aa83ca08d..33d443a37efc 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -75,6 +75,37 @@ static int mv88e6xxx_g1_wait_init_ready(struct mv88e6xxx_chip *chip) return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STS, bit, 1); } +void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip) +{ + const unsigned long timeout = jiffies + 1 * HZ; + u16 val; + int err; + + /* Wait up to 1 second for the switch to finish reading the + * EEPROM. + */ + while (time_before(jiffies, timeout)) { + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &val); + if (err) { + dev_err(chip->dev, "Error reading status"); + return; + } + + /* If the switch is still resetting, it may not + * respond on the bus, and so MDIO read returns + * 0xffff. Differentiate between that, and waiting for + * the EEPROM to be done by bit 0 being set. + */ + if (val != 0xffff && + val & BIT(MV88E6XXX_G1_STS_IRQ_EEPROM_DONE)) + return; + + usleep_range(1000, 2000); + } + + dev_err(chip->dev, "Timeout waiting for EEPROM done"); +} + /* Offset 0x01: Switch MAC Address Register Bytes 0 & 1 * Offset 0x02: Switch MAC Address Register Bytes 2 & 3 * Offset 0x03: Switch MAC Address Register Bytes 4 & 5 diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 1e3546f8b072..e05abe61fa11 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -278,6 +278,7 @@ int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr); int mv88e6185_g1_reset(struct mv88e6xxx_chip *chip); int mv88e6352_g1_reset(struct mv88e6xxx_chip *chip); int mv88e6250_g1_reset(struct mv88e6xxx_chip *chip); +void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip); int mv88e6185_g1_ppu_enable(struct mv88e6xxx_chip *chip); int mv88e6185_g1_ppu_disable(struct mv88e6xxx_chip *chip); diff --git a/drivers/net/dsa/mv88e6xxx/global1_vtu.c b/drivers/net/dsa/mv88e6xxx/global1_vtu.c index 48390b7b18ad..1048509a849b 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_vtu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_vtu.c @@ -125,11 +125,9 @@ static int mv88e6xxx_g1_vtu_vid_write(struct mv88e6xxx_chip *chip, * Offset 0x08: VTU/STU Data Register 2 * Offset 0x09: VTU/STU Data Register 3 */ - -static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip, - struct mv88e6xxx_vtu_entry *entry) +static int mv88e6185_g1_vtu_stu_data_read(struct mv88e6xxx_chip *chip, + u16 *regs) { - u16 regs[3]; int i; /* Read all 3 VTU/STU Data registers */ @@ -142,12 +140,45 @@ static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip, return err; } - /* Extract MemberTag and PortState data */ + return 0; +} + +static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_vtu_entry *entry) +{ + u16 regs[3]; + int err; + int i; + + err = mv88e6185_g1_vtu_stu_data_read(chip, regs); + if (err) + return err; + + /* Extract MemberTag data */ for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) { unsigned int member_offset = (i % 4) * 4; - unsigned int state_offset = member_offset + 2; entry->member[i] = (regs[i / 4] >> member_offset) & 0x3; + } + + return 0; +} + +static int mv88e6185_g1_stu_data_read(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_vtu_entry *entry) +{ + u16 regs[3]; + int err; + int i; + + err = mv88e6185_g1_vtu_stu_data_read(chip, regs); + if (err) + return err; + + /* Extract PortState data */ + for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) { + unsigned int state_offset = (i % 4) * 4 + 2; + entry->state[i] = (regs[i / 4] >> state_offset) & 0x3; } @@ -349,6 +380,10 @@ int mv88e6185_g1_vtu_getnext(struct mv88e6xxx_chip *chip, if (err) return err; + err = mv88e6185_g1_stu_data_read(chip, entry); + if (err) + return err; + /* VTU DBNum[3:0] are located in VTU Operation 3:0 * VTU DBNum[7:4] are located in VTU Operation 11:8 */ @@ -374,16 +409,20 @@ int mv88e6352_g1_vtu_getnext(struct mv88e6xxx_chip *chip, return err; if (entry->valid) { - /* Fetch (and mask) VLAN PortState data from the STU */ - err = mv88e6xxx_g1_vtu_stu_get(chip, entry); + err = mv88e6185_g1_vtu_data_read(chip, entry); if (err) return err; - err = mv88e6185_g1_vtu_data_read(chip, entry); + err = mv88e6xxx_g1_vtu_fid_read(chip, entry); if (err) return err; - err = mv88e6xxx_g1_vtu_fid_read(chip, entry); + /* Fetch VLAN PortState data from the STU */ + err = mv88e6xxx_g1_vtu_stu_get(chip, entry); + if (err) + return err; + + err = mv88e6185_g1_stu_data_read(chip, entry); if (err) return err; } diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index f791860d495f..c444ef3da3e2 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -569,7 +569,6 @@ static int felix_setup(struct dsa_switch *ds) struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); int port, err; - int tc; err = felix_init_structs(felix, ds->num_ports); if (err) @@ -608,12 +607,6 @@ static int felix_setup(struct dsa_switch *ds) ocelot_write_rix(ocelot, ANA_PGID_PGID_PGID(GENMASK(ocelot->num_phys_ports, 0)), ANA_PGID_PGID, PGID_UC); - /* Setup the per-traffic class flooding PGIDs */ - for (tc = 0; tc < FELIX_NUM_TC; tc++) - ocelot_write_rix(ocelot, ANA_FLOODING_FLD_MULTICAST(PGID_MC) | - ANA_FLOODING_FLD_BROADCAST(PGID_MC) | - ANA_FLOODING_FLD_UNICAST(PGID_UC), - ANA_FLOODING, tc); ds->mtu_enforcement_ingress = true; ds->configure_vlan_while_not_filtering = true; diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 3e925b8d5306..2e5bbdca5ea4 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1429,6 +1429,7 @@ static int felix_pci_probe(struct pci_dev *pdev, pci_set_drvdata(pdev, felix); ocelot = &felix->ocelot; ocelot->dev = &pdev->dev; + ocelot->num_flooding_pgids = FELIX_NUM_TC; felix->info = &felix_info_vsc9959; felix->switch_base = pci_resource_start(pdev, felix->info->switch_pci_bar); diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 1d420c4a2f0f..ebbaf6817ec8 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -1210,6 +1210,7 @@ static int seville_probe(struct platform_device *pdev) ocelot = &felix->ocelot; ocelot->dev = &pdev->dev; + ocelot->num_flooding_pgids = 1; felix->info = &seville_info_vsc9953; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); diff --git a/drivers/net/ethernet/agere/Kconfig b/drivers/net/ethernet/agere/Kconfig index d92516ae59cc..9cd750184947 100644 --- a/drivers/net/ethernet/agere/Kconfig +++ b/drivers/net/ethernet/agere/Kconfig @@ -21,6 +21,7 @@ config ET131X tristate "Agere ET-1310 Gigabit Ethernet support" depends on PCI select PHYLIB + select CRC32 help This driver supports Agere ET-1310 ethernet adapters. diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c index ad30cacc1622..032ab9f20438 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c @@ -516,6 +516,7 @@ int ena_com_rx_pkt(struct ena_com_io_cq *io_cq, { struct ena_com_rx_buf_info *ena_buf = &ena_rx_ctx->ena_bufs[0]; struct ena_eth_io_rx_cdesc_base *cdesc = NULL; + u16 q_depth = io_cq->q_depth; u16 cdesc_idx = 0; u16 nb_hw_desc; u16 i = 0; @@ -543,6 +544,8 @@ int ena_com_rx_pkt(struct ena_com_io_cq *io_cq, do { ena_buf[i].len = cdesc->length; ena_buf[i].req_id = cdesc->req_id; + if (unlikely(ena_buf[i].req_id >= q_depth)) + return -EIO; if (++i >= nb_hw_desc) break; diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index e8131dadc22c..df1884d57d1a 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -789,24 +789,6 @@ static void ena_free_all_io_tx_resources(struct ena_adapter *adapter) adapter->num_io_queues); } -static int validate_rx_req_id(struct ena_ring *rx_ring, u16 req_id) -{ - if (likely(req_id < rx_ring->ring_size)) - return 0; - - netif_err(rx_ring->adapter, rx_err, rx_ring->netdev, - "Invalid rx req_id: %hu\n", req_id); - - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.bad_req_id++; - u64_stats_update_end(&rx_ring->syncp); - - /* Trigger device reset */ - rx_ring->adapter->reset_reason = ENA_REGS_RESET_INV_RX_REQ_ID; - set_bit(ENA_FLAG_TRIGGER_RESET, &rx_ring->adapter->flags); - return -EFAULT; -} - /* ena_setup_rx_resources - allocate I/O Rx resources (Descriptors) * @adapter: network interface device structure * @qid: queue index @@ -926,10 +908,14 @@ static void ena_free_all_io_rx_resources(struct ena_adapter *adapter) static int ena_alloc_rx_page(struct ena_ring *rx_ring, struct ena_rx_buffer *rx_info, gfp_t gfp) { + int headroom = rx_ring->rx_headroom; struct ena_com_buf *ena_buf; struct page *page; dma_addr_t dma; + /* restore page offset value in case it has been changed by device */ + rx_info->page_offset = headroom; + /* if previous allocated page is not used */ if (unlikely(rx_info->page)) return 0; @@ -959,10 +945,9 @@ static int ena_alloc_rx_page(struct ena_ring *rx_ring, "Allocate page %p, rx_info %p\n", page, rx_info); rx_info->page = page; - rx_info->page_offset = 0; ena_buf = &rx_info->ena_buf; - ena_buf->paddr = dma + rx_ring->rx_headroom; - ena_buf->len = ENA_PAGE_SIZE - rx_ring->rx_headroom; + ena_buf->paddr = dma + headroom; + ena_buf->len = ENA_PAGE_SIZE - headroom; return 0; } @@ -1356,15 +1341,10 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, struct ena_rx_buffer *rx_info; u16 len, req_id, buf = 0; void *va; - int rc; len = ena_bufs[buf].len; req_id = ena_bufs[buf].req_id; - rc = validate_rx_req_id(rx_ring, req_id); - if (unlikely(rc < 0)) - return NULL; - rx_info = &rx_ring->rx_buffer_info[req_id]; if (unlikely(!rx_info->page)) { @@ -1379,7 +1359,8 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, /* save virt address of first buffer */ va = page_address(rx_info->page) + rx_info->page_offset; - prefetch(va + NET_IP_ALIGN); + + prefetch(va); if (len <= rx_ring->rx_copybreak) { skb = ena_alloc_skb(rx_ring, false); @@ -1420,8 +1401,6 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page, rx_info->page_offset, len, ENA_PAGE_SIZE); - /* The offset is non zero only for the first buffer */ - rx_info->page_offset = 0; netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "RX skb updated. len %d. data_len %d\n", @@ -1440,10 +1419,6 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, len = ena_bufs[buf].len; req_id = ena_bufs[buf].req_id; - rc = validate_rx_req_id(rx_ring, req_id); - if (unlikely(rc < 0)) - return NULL; - rx_info = &rx_ring->rx_buffer_info[req_id]; } while (1); @@ -1544,8 +1519,7 @@ static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp) int ret; rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]; - xdp->data = page_address(rx_info->page) + - rx_info->page_offset + rx_ring->rx_headroom; + xdp->data = page_address(rx_info->page) + rx_info->page_offset; xdp_set_data_meta_invalid(xdp); xdp->data_hard_start = page_address(rx_info->page); xdp->data_end = xdp->data + rx_ring->ena_bufs[0].len; @@ -1612,8 +1586,9 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, if (unlikely(ena_rx_ctx.descs == 0)) break; + /* First descriptor might have an offset set by the device */ rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]; - rx_info->page_offset = ena_rx_ctx.pkt_offset; + rx_info->page_offset += ena_rx_ctx.pkt_offset; netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "rx_poll: q %d got packet from ena. descs #: %d l3 proto %d l4 proto %d hash: %x\n", @@ -1697,12 +1672,18 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, error: adapter = netdev_priv(rx_ring->netdev); - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->rx_stats.bad_desc_num++; - u64_stats_update_end(&rx_ring->syncp); + if (rc == -ENOSPC) { + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->rx_stats.bad_desc_num++; + u64_stats_update_end(&rx_ring->syncp); + adapter->reset_reason = ENA_REGS_RESET_TOO_MANY_RX_DESCS; + } else { + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->rx_stats.bad_req_id++; + u64_stats_update_end(&rx_ring->syncp); + adapter->reset_reason = ENA_REGS_RESET_INV_RX_REQ_ID; + } - /* Too many desc from the device. Trigger reset */ - adapter->reset_reason = ENA_REGS_RESET_TOO_MANY_RX_DESCS; set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); return 0; @@ -3388,16 +3369,9 @@ static int ena_device_init(struct ena_com_dev *ena_dev, struct pci_dev *pdev, goto err_mmio_read_less; } - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(dma_width)); + rc = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(dma_width)); if (rc) { - dev_err(dev, "pci_set_dma_mask failed 0x%x\n", rc); - goto err_mmio_read_less; - } - - rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(dma_width)); - if (rc) { - dev_err(dev, "err_pci_set_consistent_dma_mask failed 0x%x\n", - rc); + dev_err(dev, "dma_set_mask_and_coherent failed %d\n", rc); goto err_mmio_read_less; } @@ -4167,6 +4141,12 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return rc; } + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(ENA_MAX_PHYS_ADDR_SIZE_BITS)); + if (rc) { + dev_err(&pdev->dev, "dma_set_mask_and_coherent failed %d\n", rc); + goto err_disable_device; + } + pci_set_master(pdev); ena_dev = vzalloc(sizeof(*ena_dev)); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 4f913658eea4..24122ccda614 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -413,85 +413,63 @@ int aq_ring_rx_clean(struct aq_ring_s *self, buff->rxdata.pg_off, buff->len, DMA_FROM_DEVICE); - /* for single fragment packets use build_skb() */ - if (buff->is_eop && - buff->len <= AQ_CFG_RX_FRAME_MAX - AQ_SKB_ALIGN) { - skb = build_skb(aq_buf_vaddr(&buff->rxdata), + skb = napi_alloc_skb(napi, AQ_CFG_RX_HDR_SIZE); + if (unlikely(!skb)) { + u64_stats_update_begin(&self->stats.rx.syncp); + self->stats.rx.skb_alloc_fails++; + u64_stats_update_end(&self->stats.rx.syncp); + err = -ENOMEM; + goto err_exit; + } + if (is_ptp_ring) + buff->len -= + aq_ptp_extract_ts(self->aq_nic, skb, + aq_buf_vaddr(&buff->rxdata), + buff->len); + + hdr_len = buff->len; + if (hdr_len > AQ_CFG_RX_HDR_SIZE) + hdr_len = eth_get_headlen(skb->dev, + aq_buf_vaddr(&buff->rxdata), + AQ_CFG_RX_HDR_SIZE); + + memcpy(__skb_put(skb, hdr_len), aq_buf_vaddr(&buff->rxdata), + ALIGN(hdr_len, sizeof(long))); + + if (buff->len - hdr_len > 0) { + skb_add_rx_frag(skb, 0, buff->rxdata.page, + buff->rxdata.pg_off + hdr_len, + buff->len - hdr_len, AQ_CFG_RX_FRAME_MAX); - if (unlikely(!skb)) { - u64_stats_update_begin(&self->stats.rx.syncp); - self->stats.rx.skb_alloc_fails++; - u64_stats_update_end(&self->stats.rx.syncp); - err = -ENOMEM; - goto err_exit; - } - if (is_ptp_ring) - buff->len -= - aq_ptp_extract_ts(self->aq_nic, skb, - aq_buf_vaddr(&buff->rxdata), - buff->len); - skb_put(skb, buff->len); page_ref_inc(buff->rxdata.page); - } else { - skb = napi_alloc_skb(napi, AQ_CFG_RX_HDR_SIZE); - if (unlikely(!skb)) { - u64_stats_update_begin(&self->stats.rx.syncp); - self->stats.rx.skb_alloc_fails++; - u64_stats_update_end(&self->stats.rx.syncp); - err = -ENOMEM; - goto err_exit; - } - if (is_ptp_ring) - buff->len -= - aq_ptp_extract_ts(self->aq_nic, skb, - aq_buf_vaddr(&buff->rxdata), - buff->len); - - hdr_len = buff->len; - if (hdr_len > AQ_CFG_RX_HDR_SIZE) - hdr_len = eth_get_headlen(skb->dev, - aq_buf_vaddr(&buff->rxdata), - AQ_CFG_RX_HDR_SIZE); - - memcpy(__skb_put(skb, hdr_len), aq_buf_vaddr(&buff->rxdata), - ALIGN(hdr_len, sizeof(long))); - - if (buff->len - hdr_len > 0) { - skb_add_rx_frag(skb, 0, buff->rxdata.page, - buff->rxdata.pg_off + hdr_len, - buff->len - hdr_len, - AQ_CFG_RX_FRAME_MAX); - page_ref_inc(buff->rxdata.page); - } + } - if (!buff->is_eop) { - buff_ = buff; - i = 1U; - do { - next_ = buff_->next, - buff_ = &self->buff_ring[next_]; + if (!buff->is_eop) { + buff_ = buff; + i = 1U; + do { + next_ = buff_->next; + buff_ = &self->buff_ring[next_]; - dma_sync_single_range_for_cpu( - aq_nic_get_dev(self->aq_nic), - buff_->rxdata.daddr, - buff_->rxdata.pg_off, - buff_->len, - DMA_FROM_DEVICE); - skb_add_rx_frag(skb, i++, - buff_->rxdata.page, - buff_->rxdata.pg_off, - buff_->len, - AQ_CFG_RX_FRAME_MAX); - page_ref_inc(buff_->rxdata.page); - buff_->is_cleaned = 1; - - buff->is_ip_cso &= buff_->is_ip_cso; - buff->is_udp_cso &= buff_->is_udp_cso; - buff->is_tcp_cso &= buff_->is_tcp_cso; - buff->is_cso_err |= buff_->is_cso_err; + dma_sync_single_range_for_cpu(aq_nic_get_dev(self->aq_nic), + buff_->rxdata.daddr, + buff_->rxdata.pg_off, + buff_->len, + DMA_FROM_DEVICE); + skb_add_rx_frag(skb, i++, + buff_->rxdata.page, + buff_->rxdata.pg_off, + buff_->len, + AQ_CFG_RX_FRAME_MAX); + page_ref_inc(buff_->rxdata.page); + buff_->is_cleaned = 1; - } while (!buff_->is_eop); - } + buff->is_ip_cso &= buff_->is_ip_cso; + buff->is_udp_cso &= buff_->is_udp_cso; + buff->is_tcp_cso &= buff_->is_tcp_cso; + buff->is_cso_err |= buff_->is_cso_err; + + } while (!buff_->is_eop); } if (buff->is_vlan) diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 0c12cf7bda50..3f65f2b370c5 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -2543,8 +2543,8 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * various kernel subsystems to support the mechanics required by a * fixed-high-32-bit system. */ - if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) || - (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { dev_err(&pdev->dev, "No usable DMA configuration,aborting\n"); goto err_dma; } diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 098b0328e3cb..ff9f96de74b8 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -2312,8 +2312,8 @@ static int atl1e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * various kernel subsystems to support the mechanics required by a * fixed-high-32-bit system. */ - if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) || - (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { dev_err(&pdev->dev, "No usable DMA configuration,aborting\n"); goto err_dma; } diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 7fb42f388d59..7b79528d6eed 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -88,6 +88,7 @@ config BNX2 config CNIC tristate "QLogic CNIC support" depends on PCI && (IPV6 || IPV6=n) + depends on MMU select BNX2 select UIO help diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 74c1778d841e..b455b60a5434 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -2383,7 +2383,8 @@ static int b44_init_one(struct ssb_device *sdev, goto err_out_free_dev; } - if (dma_set_mask_and_coherent(sdev->dma_dev, DMA_BIT_MASK(30))) { + err = dma_set_mask_and_coherent(sdev->dma_dev, DMA_BIT_MASK(30)); + if (err) { dev_err(sdev->dev, "Required 30BIT DMA mask unsupported by the system\n"); goto err_out_powerdown; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 7975f59735d6..0af0af2b70fe 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4099,7 +4099,8 @@ static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init) bnxt_free_ntp_fltrs(bp, irq_re_init); if (irq_re_init) { bnxt_free_ring_stats(bp); - if (!(bp->fw_cap & BNXT_FW_CAP_PORT_STATS_NO_RESET)) + if (!(bp->fw_cap & BNXT_FW_CAP_PORT_STATS_NO_RESET) || + test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) bnxt_free_port_stats(bp); bnxt_free_ring_grps(bp); bnxt_free_vnics(bp); @@ -7757,6 +7758,7 @@ static void bnxt_add_one_ctr(u64 hw, u64 *sw, u64 mask) { u64 sw_tmp; + hw &= mask; sw_tmp = (*sw & ~mask) | hw; if (hw < (*sw & mask)) sw_tmp += mask + 1; @@ -11588,7 +11590,8 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev) if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) != 0 && dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)) != 0) { dev_err(&pdev->dev, "System does not support DMA, aborting\n"); - goto init_err_disable; + rc = -EIO; + goto init_err_release; } pci_set_master(pdev); @@ -12672,6 +12675,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) create_singlethread_workqueue("bnxt_pf_wq"); if (!bnxt_pf_wq) { dev_err(&pdev->dev, "Unable to create workqueue.\n"); + rc = -ENOMEM; goto init_err_pci_clean; } } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 53687bc7fcf5..1471c9a36238 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -2079,6 +2079,9 @@ int bnxt_hwrm_nvm_get_dev_info(struct bnxt *bp, struct hwrm_nvm_get_dev_info_input req = {0}; int rc; + if (BNXT_VF(bp)) + return -EOPNOTSUPP; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_DEV_INFO, -1, -1); mutex_lock(&bp->hwrm_cmd_lock); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -2997,7 +3000,7 @@ static int bnxt_get_module_eeprom(struct net_device *dev, /* Read A2 portion of the EEPROM */ if (length) { start -= ETH_MODULE_SFF_8436_LEN; - rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 1, + rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 0, start, length, data); } return rc; diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig index 85858163bac5..e432a68ac520 100644 --- a/drivers/net/ethernet/cadence/Kconfig +++ b/drivers/net/ethernet/cadence/Kconfig @@ -23,6 +23,7 @@ config MACB tristate "Cadence MACB/GEM support" depends on HAS_DMA && COMMON_CLK select PHYLINK + select CRC32 help The Cadence MACB ethernet interface is found on many Atmel AT32 and AT91 parts. This driver also supports the Cadence GEM (Gigabit diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig index 87cc0ef68b31..8ba0e08e5e64 100644 --- a/drivers/net/ethernet/chelsio/Kconfig +++ b/drivers/net/ethernet/chelsio/Kconfig @@ -68,7 +68,7 @@ config CHELSIO_T3 config CHELSIO_T4 tristate "Chelsio Communications T4/T5/T6 Ethernet support" - depends on PCI && (IPV6 || IPV6=n) + depends on PCI && (IPV6 || IPV6=n) && (TLS || TLS=n) select FW_LOADER select MDIO select ZLIB_DEFLATE diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c index e18e9ce27f94..1cc3c51eff71 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c @@ -3175,6 +3175,7 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports, GFP_KERNEL | __GFP_COMP); if (!avail) { CH_ALERT(adapter, "free list queue 0 initialization failed\n"); + ret = -ENOMEM; goto err; } if (avail < q->fl[0].size) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 3352dad6ca99..27308600da15 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -2124,6 +2124,9 @@ void cxgb4_inline_tx_skb(const struct sk_buff *skb, const struct sge_txq *q, void cxgb4_write_sgl(const struct sk_buff *skb, struct sge_txq *q, struct ulptx_sgl *sgl, u64 *end, unsigned int start, const dma_addr_t *addr); +void cxgb4_write_partial_sgl(const struct sk_buff *skb, struct sge_txq *q, + struct ulptx_sgl *sgl, u64 *end, + const dma_addr_t *addr, u32 start, u32 send_len); void cxgb4_ring_tx_db(struct adapter *adap, struct sge_txq *q, int n); int t4_set_vlan_acl(struct adapter *adap, unsigned int mbox, unsigned int vf, u16 vlan); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 0273f40b85f7..17410fe86626 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -3573,6 +3573,8 @@ static int chcr_stats_show(struct seq_file *seq, void *v) atomic64_read(&adap->ch_ktls_stats.ktls_tx_complete_pkts)); seq_printf(seq, "TX trim pkts : %20llu\n", atomic64_read(&adap->ch_ktls_stats.ktls_tx_trimmed_pkts)); + seq_printf(seq, "TX sw fallback : %20llu\n", + atomic64_read(&adap->ch_ktls_stats.ktls_tx_fallback)); while (i < MAX_NPORTS) { ktls_port = &adap->ch_ktls_stats.ktls_port[i]; seq_printf(seq, "Port %d\n", i); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 4e55f7081644..83b46440408b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -880,7 +880,8 @@ int set_filter_wr(struct adapter *adapter, int fidx) FW_FILTER_WR_OVLAN_VLD_V(f->fs.val.ovlan_vld) | FW_FILTER_WR_IVLAN_VLDM_V(f->fs.mask.ivlan_vld) | FW_FILTER_WR_OVLAN_VLDM_V(f->fs.mask.ovlan_vld)); - fwr->smac_sel = f->smt->idx; + if (f->fs.newsmac) + fwr->smac_sel = f->smt->idx; fwr->rx_chan_rx_rpl_iq = htons(FW_FILTER_WR_RX_CHAN_V(0) | FW_FILTER_WR_RX_RPL_IQ_V(adapter->sge.fw_evtq.abs_id)); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index a952fe198eb9..7fd264a6d085 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -1176,6 +1176,7 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb, txq = netdev_pick_tx(dev, skb, sb_dev); if (xfrm_offload(skb) || is_ptp_enabled(skb, dev) || skb->encapsulation || + cxgb4_is_ktls_skb(skb) || (proto != IPPROTO_TCP && proto != IPPROTO_UDP)) txq = txq % pi->nqsets; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h index b169776ab484..1b49f2fa9b18 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h @@ -388,6 +388,7 @@ struct ch_ktls_stats_debug { atomic64_t ktls_tx_retransmit_pkts; atomic64_t ktls_tx_complete_pkts; atomic64_t ktls_tx_trimmed_pkts; + atomic64_t ktls_tx_fallback; }; #endif @@ -493,6 +494,11 @@ struct cxgb4_uld_info { #endif }; +static inline bool cxgb4_is_ktls_skb(struct sk_buff *skb) +{ + return skb->sk && tls_is_sk_tx_device_offloaded(skb->sk); +} + void cxgb4_uld_enable(struct adapter *adap); void cxgb4_register_uld(enum cxgb4_uld type, const struct cxgb4_uld_info *p); int cxgb4_unregister_uld(enum cxgb4_uld type); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index a9e9c7ae565d..196652a114c5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -890,6 +890,114 @@ void cxgb4_write_sgl(const struct sk_buff *skb, struct sge_txq *q, } EXPORT_SYMBOL(cxgb4_write_sgl); +/* cxgb4_write_partial_sgl - populate SGL for partial packet + * @skb: the packet + * @q: the Tx queue we are writing into + * @sgl: starting location for writing the SGL + * @end: points right after the end of the SGL + * @addr: the list of bus addresses for the SGL elements + * @start: start offset in the SKB where partial data starts + * @len: length of data from @start to send out + * + * This API will handle sending out partial data of a skb if required. + * Unlike cxgb4_write_sgl, @start can be any offset into the skb data, + * and @len will decide how much data after @start offset to send out. + */ +void cxgb4_write_partial_sgl(const struct sk_buff *skb, struct sge_txq *q, + struct ulptx_sgl *sgl, u64 *end, + const dma_addr_t *addr, u32 start, u32 len) +{ + struct ulptx_sge_pair buf[MAX_SKB_FRAGS / 2 + 1] = {0}, *to; + u32 frag_size, skb_linear_data_len = skb_headlen(skb); + struct skb_shared_info *si = skb_shinfo(skb); + u8 i = 0, frag_idx = 0, nfrags = 0; + skb_frag_t *frag; + + /* Fill the first SGL either from linear data or from partial + * frag based on @start. + */ + if (unlikely(start < skb_linear_data_len)) { + frag_size = min(len, skb_linear_data_len - start); + sgl->len0 = htonl(frag_size); + sgl->addr0 = cpu_to_be64(addr[0] + start); + len -= frag_size; + nfrags++; + } else { + start -= skb_linear_data_len; + frag = &si->frags[frag_idx]; + frag_size = skb_frag_size(frag); + /* find the first frag */ + while (start >= frag_size) { + start -= frag_size; + frag_idx++; + frag = &si->frags[frag_idx]; + frag_size = skb_frag_size(frag); + } + + frag_size = min(len, skb_frag_size(frag) - start); + sgl->len0 = cpu_to_be32(frag_size); + sgl->addr0 = cpu_to_be64(addr[frag_idx + 1] + start); + len -= frag_size; + nfrags++; + frag_idx++; + } + + /* If the entire partial data fit in one SGL, then send it out + * now. + */ + if (!len) + goto done; + + /* Most of the complexity below deals with the possibility we hit the + * end of the queue in the middle of writing the SGL. For this case + * only we create the SGL in a temporary buffer and then copy it. + */ + to = (u8 *)end > (u8 *)q->stat ? buf : sgl->sge; + + /* If the skb couldn't fit in first SGL completely, fill the + * rest of the frags in subsequent SGLs. Note that each SGL + * pair can store 2 frags. + */ + while (len) { + frag_size = min(len, skb_frag_size(&si->frags[frag_idx])); + to->len[i & 1] = cpu_to_be32(frag_size); + to->addr[i & 1] = cpu_to_be64(addr[frag_idx + 1]); + if (i && (i & 1)) + to++; + nfrags++; + frag_idx++; + i++; + len -= frag_size; + } + + /* If we ended in an odd boundary, then set the second SGL's + * length in the pair to 0. + */ + if (i & 1) + to->len[1] = cpu_to_be32(0); + + /* Copy from temporary buffer to Tx ring, in case we hit the + * end of the queue in the middle of writing the SGL. + */ + if (unlikely((u8 *)end > (u8 *)q->stat)) { + u32 part0 = (u8 *)q->stat - (u8 *)sgl->sge, part1; + + if (likely(part0)) + memcpy(sgl->sge, buf, part0); + part1 = (u8 *)end - (u8 *)q->stat; + memcpy(q->desc, (u8 *)buf + part0, part1); + end = (void *)q->desc + part1; + } + + /* 0-pad to multiple of 16 */ + if ((uintptr_t)end & 8) + *end = 0; +done: + sgl->cmd_nsge = htonl(ULPTX_CMD_V(ULP_TX_SC_DSGL) | + ULPTX_NSGE_V(nfrags)); +} +EXPORT_SYMBOL(cxgb4_write_partial_sgl); + /* This function copies 64 byte coalesced work request to * memory mapped BAR2 space. For coalesced WR SGE fetches * data from the FIFO instead of from Host. @@ -1422,7 +1530,8 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) #endif /* CHELSIO_IPSEC_INLINE */ #if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE) - if (skb->decrypted) + if (cxgb4_is_ktls_skb(skb) && + (skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb)))) return adap->uld[CXGB4_ULD_KTLS].tx_handler(skb, dev); #endif /* CHELSIO_TLS_DEVICE */ diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c index 5195f692f14d..1b7e8c91b541 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c @@ -14,6 +14,50 @@ static LIST_HEAD(uld_ctx_list); static DEFINE_MUTEX(dev_mutex); +/* chcr_get_nfrags_to_send: get the remaining nfrags after start offset + * @skb: skb + * @start: start offset. + * @len: how much data to send after @start + */ +static int chcr_get_nfrags_to_send(struct sk_buff *skb, u32 start, u32 len) +{ + struct skb_shared_info *si = skb_shinfo(skb); + u32 frag_size, skb_linear_data_len = skb_headlen(skb); + u8 nfrags = 0, frag_idx = 0; + skb_frag_t *frag; + + /* if its a linear skb then return 1 */ + if (!skb_is_nonlinear(skb)) + return 1; + + if (unlikely(start < skb_linear_data_len)) { + frag_size = min(len, skb_linear_data_len - start); + start = 0; + } else { + start -= skb_linear_data_len; + + frag = &si->frags[frag_idx]; + frag_size = skb_frag_size(frag); + while (start >= frag_size) { + start -= frag_size; + frag_idx++; + frag = &si->frags[frag_idx]; + frag_size = skb_frag_size(frag); + } + frag_size = min(len, skb_frag_size(frag) - start); + } + len -= frag_size; + nfrags++; + + while (len) { + frag_size = min(len, skb_frag_size(&si->frags[frag_idx])); + len -= frag_size; + nfrags++; + frag_idx++; + } + return nfrags; +} + static int chcr_init_tcb_fields(struct chcr_ktls_info *tx_info); /* * chcr_ktls_save_keys: calculate and save crypto keys. @@ -500,7 +544,9 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk, /* need to wait for hw response, can't free tx_info yet. */ if (tx_info->open_state == CH_KTLS_OPEN_PENDING) tx_info->pending_close = true; - /* free the lock after the cleanup */ + else + spin_unlock_bh(&tx_info->lock); + /* if in pending close, free the lock after the cleanup */ goto put_module; } spin_unlock_bh(&tx_info->lock); @@ -689,7 +735,8 @@ static int chcr_ktls_cpl_set_tcb_rpl(struct adapter *adap, unsigned char *input) } static void *__chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, - u32 tid, void *pos, u16 word, u64 mask, + u32 tid, void *pos, u16 word, + struct sge_eth_txq *q, u64 mask, u64 val, u32 reply) { struct cpl_set_tcb_field_core *cpl; @@ -698,7 +745,10 @@ static void *__chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, /* ULP_TXPKT */ txpkt = pos; - txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | ULP_TXPKT_DEST_V(0)); + txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | + ULP_TXPKT_CHANNELID_V(tx_info->port_id) | + ULP_TXPKT_FID_V(q->q.cntxt_id) | + ULP_TXPKT_RO_F); txpkt->len = htonl(DIV_ROUND_UP(CHCR_SET_TCB_FIELD_LEN, 16)); /* ULPTX_IDATA sub-command */ @@ -753,7 +803,7 @@ static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, } else { u8 buf[48] = {0}; - __chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word, + __chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word, q, mask, val, reply); return chcr_copy_to_txd(buf, &q->q, pos, @@ -761,7 +811,7 @@ static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, } } - pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word, + pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word, q, mask, val, reply); /* check again if we are at the end of the queue */ @@ -783,11 +833,11 @@ static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, */ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, struct sge_eth_txq *q, u64 tcp_seq, - u64 tcp_ack, u64 tcp_win) + u64 tcp_ack, u64 tcp_win, bool offset) { bool first_wr = ((tx_info->prev_ack == 0) && (tx_info->prev_win == 0)); struct ch_ktls_port_stats_debug *port_stats; - u32 len, cpl = 0, ndesc, wr_len; + u32 len, cpl = 0, ndesc, wr_len, wr_mid = 0; struct fw_ulptx_wr *wr; int credits; void *pos; @@ -803,6 +853,11 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, return NETDEV_TX_BUSY; } + if (unlikely(credits < ETHTXQ_STOP_THRES)) { + chcr_eth_txq_stop(q); + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + } + pos = &q->q.desc[q->q.pidx]; /* make space for WR, we'll fill it later when we know all the cpls * being sent out and have complete length. @@ -818,7 +873,7 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, cpl++; } /* reset snd una if it's a re-transmit pkt */ - if (tcp_seq != tx_info->prev_seq) { + if (tcp_seq != tx_info->prev_seq || offset) { /* reset snd_una */ port_stats = &tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id]; @@ -827,7 +882,8 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, TCB_SND_UNA_RAW_V (TCB_SND_UNA_RAW_M), TCB_SND_UNA_RAW_V(0), 0); - atomic64_inc(&port_stats->ktls_tx_ooo); + if (tcp_seq != tx_info->prev_seq) + atomic64_inc(&port_stats->ktls_tx_ooo); cpl++; } /* update ack */ @@ -856,7 +912,8 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, wr->op_to_compl = htonl(FW_WR_OP_V(FW_ULPTX_WR)); wr->cookie = 0; /* fill len in wr field */ - wr->flowid_len16 = htonl(FW_WR_LEN16_V(DIV_ROUND_UP(len, 16))); + wr->flowid_len16 = htonl(wr_mid | + FW_WR_LEN16_V(DIV_ROUND_UP(len, 16))); ndesc = DIV_ROUND_UP(len, 64); chcr_txq_advance(&q->q, ndesc); @@ -866,34 +923,14 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, } /* - * chcr_ktls_skb_copy - * @nskb - new skb where the frags to be added. - * @skb - old skb from which frags will be copied. - */ -static void chcr_ktls_skb_copy(struct sk_buff *skb, struct sk_buff *nskb) -{ - int i; - - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - skb_shinfo(nskb)->frags[i] = skb_shinfo(skb)->frags[i]; - __skb_frag_ref(&skb_shinfo(nskb)->frags[i]); - } - - skb_shinfo(nskb)->nr_frags = skb_shinfo(skb)->nr_frags; - nskb->len += skb->data_len; - nskb->data_len = skb->data_len; - nskb->truesize += skb->data_len; -} - -/* * chcr_ktls_get_tx_flits * returns number of flits to be sent out, it includes key context length, WR * size and skb fragments. */ static unsigned int -chcr_ktls_get_tx_flits(const struct sk_buff *skb, unsigned int key_ctx_len) +chcr_ktls_get_tx_flits(u32 nr_frags, unsigned int key_ctx_len) { - return chcr_sgl_len(skb_shinfo(skb)->nr_frags) + + return chcr_sgl_len(nr_frags) + DIV_ROUND_UP(key_ctx_len + CHCR_KTLS_WR_SIZE, 8); } @@ -950,15 +987,15 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, struct fw_eth_tx_pkt_wr *wr; struct cpl_tx_pkt_core *cpl; u32 ctrl, iplen, maclen; -#if IS_ENABLED(CONFIG_IPV6) struct ipv6hdr *ip6; -#endif unsigned int ndesc; struct tcphdr *tcp; int len16, pktlen; struct iphdr *ip; + u32 wr_mid = 0; int credits; u8 buf[150]; + u64 cntrl1; void *pos; iplen = skb_network_header_len(skb); @@ -967,7 +1004,7 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, /* packet length = eth hdr len + ip hdr len + tcp hdr len * (including options). */ - pktlen = skb->len - skb->data_len; + pktlen = skb_transport_offset(skb) + tcp_hdrlen(skb); ctrl = sizeof(*cpl) + pktlen; len16 = DIV_ROUND_UP(sizeof(*wr) + ctrl, 16); @@ -980,6 +1017,11 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, return NETDEV_TX_BUSY; } + if (unlikely(credits < ETHTXQ_STOP_THRES)) { + chcr_eth_txq_stop(q); + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + } + pos = &q->q.desc[q->q.pidx]; wr = pos; @@ -987,7 +1029,7 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, wr->op_immdlen = htonl(FW_WR_OP_V(FW_ETH_TX_PKT_WR) | FW_WR_IMMDLEN_V(ctrl)); - wr->equiq_to_len16 = htonl(FW_WR_LEN16_V(len16)); + wr->equiq_to_len16 = htonl(wr_mid | FW_WR_LEN16_V(len16)); wr->r3 = 0; cpl = (void *)(wr + 1); @@ -997,22 +1039,26 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, TXPKT_PF_V(tx_info->adap->pf)); cpl->pack = 0; cpl->len = htons(pktlen); - /* checksum offload */ - cpl->ctrl1 = 0; - - pos = cpl + 1; memcpy(buf, skb->data, pktlen); - if (tx_info->ip_family == AF_INET) { + if (!IS_ENABLED(CONFIG_IPV6) || tx_info->ip_family == AF_INET) { /* we need to correct ip header len */ ip = (struct iphdr *)(buf + maclen); ip->tot_len = htons(pktlen - maclen); -#if IS_ENABLED(CONFIG_IPV6) + cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP); } else { ip6 = (struct ipv6hdr *)(buf + maclen); ip6->payload_len = htons(pktlen - maclen - iplen); -#endif + cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP6); } + + cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) | + TXPKT_IPHDR_LEN_V(iplen); + /* checksum offload */ + cpl->ctrl1 = cpu_to_be64(cntrl1); + + pos = cpl + 1; + /* now take care of the tcp header, if fin is not set then clear push * bit as well, and if fin is set, it will be sent at the last so we * need to update the tcp sequence number as per the last packet. @@ -1031,71 +1077,6 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, return 0; } -/* chcr_ktls_skb_shift - Shifts request length paged data from skb to another. - * @tgt- buffer into which tail data gets added - * @skb- buffer from which the paged data comes from - * @shiftlen- shift up to this many bytes - */ -static int chcr_ktls_skb_shift(struct sk_buff *tgt, struct sk_buff *skb, - int shiftlen) -{ - skb_frag_t *fragfrom, *fragto; - int from, to, todo; - - WARN_ON(shiftlen > skb->data_len); - - todo = shiftlen; - from = 0; - to = 0; - fragfrom = &skb_shinfo(skb)->frags[from]; - - while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) { - fragfrom = &skb_shinfo(skb)->frags[from]; - fragto = &skb_shinfo(tgt)->frags[to]; - - if (todo >= skb_frag_size(fragfrom)) { - *fragto = *fragfrom; - todo -= skb_frag_size(fragfrom); - from++; - to++; - - } else { - __skb_frag_ref(fragfrom); - skb_frag_page_copy(fragto, fragfrom); - skb_frag_off_copy(fragto, fragfrom); - skb_frag_size_set(fragto, todo); - - skb_frag_off_add(fragfrom, todo); - skb_frag_size_sub(fragfrom, todo); - todo = 0; - - to++; - break; - } - } - - /* Ready to "commit" this state change to tgt */ - skb_shinfo(tgt)->nr_frags = to; - - /* Reposition in the original skb */ - to = 0; - while (from < skb_shinfo(skb)->nr_frags) - skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++]; - - skb_shinfo(skb)->nr_frags = to; - - WARN_ON(todo > 0 && !skb_shinfo(skb)->nr_frags); - - skb->len -= shiftlen; - skb->data_len -= shiftlen; - skb->truesize -= shiftlen; - tgt->len += shiftlen; - tgt->data_len += shiftlen; - tgt->truesize += shiftlen; - - return shiftlen; -} - /* * chcr_ktls_xmit_wr_complete: This sends out the complete record. If an skb * received has partial end part of the record, send out the complete record, so @@ -1111,6 +1092,8 @@ static int chcr_ktls_skb_shift(struct sk_buff *tgt, struct sk_buff *skb, static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, struct chcr_ktls_info *tx_info, struct sge_eth_txq *q, u32 tcp_seq, + bool is_last_wr, u32 data_len, + u32 skb_offset, u32 nfrags, bool tcp_push, u32 mss) { u32 len16, wr_mid = 0, flits = 0, ndesc, cipher_start; @@ -1126,7 +1109,7 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, u64 *end; /* get the number of flits required */ - flits = chcr_ktls_get_tx_flits(skb, tx_info->key_ctx_len); + flits = chcr_ktls_get_tx_flits(nfrags, tx_info->key_ctx_len); /* number of descriptors */ ndesc = chcr_flits_to_desc(flits); /* check if enough credits available */ @@ -1155,6 +1138,9 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, return NETDEV_TX_BUSY; } + if (!is_last_wr) + skb_get(skb); + pos = &q->q.desc[q->q.pidx]; end = (u64 *)pos + flits; /* FW_ULPTX_WR */ @@ -1187,7 +1173,7 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, CPL_TX_SEC_PDU_CPLLEN_V(CHCR_CPL_TX_SEC_PDU_LEN_64BIT) | CPL_TX_SEC_PDU_PLACEHOLDER_V(1) | CPL_TX_SEC_PDU_IVINSRTOFST_V(TLS_HEADER_SIZE + 1)); - cpl->pldlen = htonl(skb->data_len); + cpl->pldlen = htonl(data_len); /* encryption should start after tls header size + iv size */ cipher_start = TLS_HEADER_SIZE + tx_info->iv_size + 1; @@ -1229,7 +1215,7 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, /* CPL_TX_DATA */ tx_data = (void *)pos; OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid)); - tx_data->len = htonl(TX_DATA_MSS_V(mss) | TX_LENGTH_V(skb->data_len)); + tx_data->len = htonl(TX_DATA_MSS_V(mss) | TX_LENGTH_V(data_len)); tx_data->rsvd = htonl(tcp_seq); @@ -1249,8 +1235,8 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, } /* send the complete packet except the header */ - cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len, - sgl_sdesc->addr); + cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr, + skb_offset, data_len); sgl_sdesc->skb = skb; chcr_txq_advance(&q->q, ndesc); @@ -1282,10 +1268,11 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, struct sge_eth_txq *q, u32 tcp_seq, bool tcp_push, u32 mss, u32 tls_rec_offset, u8 *prior_data, - u32 prior_data_len) + u32 prior_data_len, u32 data_len, + u32 skb_offset) { + u32 len16, wr_mid = 0, cipher_start, nfrags; struct adapter *adap = tx_info->adap; - u32 len16, wr_mid = 0, cipher_start; unsigned int flits = 0, ndesc; int credits, left, last_desc; struct tx_sw_desc *sgl_sdesc; @@ -1298,10 +1285,11 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, void *pos; u64 *end; + nfrags = chcr_get_nfrags_to_send(skb, skb_offset, data_len); /* get the number of flits required, it's a partial record so 2 flits * (AES_BLOCK_SIZE) will be added. */ - flits = chcr_ktls_get_tx_flits(skb, tx_info->key_ctx_len) + 2; + flits = chcr_ktls_get_tx_flits(nfrags, tx_info->key_ctx_len) + 2; /* get the correct 8 byte IV of this record */ iv_record = cpu_to_be64(tx_info->iv + tx_info->record_no); /* If it's a middle record and not 16 byte aligned to run AES CTR, need @@ -1373,7 +1361,7 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, htonl(CPL_TX_SEC_PDU_OPCODE_V(CPL_TX_SEC_PDU) | CPL_TX_SEC_PDU_CPLLEN_V(CHCR_CPL_TX_SEC_PDU_LEN_64BIT) | CPL_TX_SEC_PDU_IVINSRTOFST_V(1)); - cpl->pldlen = htonl(skb->data_len + AES_BLOCK_LEN + prior_data_len); + cpl->pldlen = htonl(data_len + AES_BLOCK_LEN + prior_data_len); cpl->aadstart_cipherstop_hi = htonl(CPL_TX_SEC_PDU_CIPHERSTART_V(cipher_start)); cpl->cipherstop_lo_authinsert = 0; @@ -1404,7 +1392,7 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, tx_data = (void *)pos; OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid)); tx_data->len = htonl(TX_DATA_MSS_V(mss) | - TX_LENGTH_V(skb->data_len + prior_data_len)); + TX_LENGTH_V(data_len + prior_data_len)); tx_data->rsvd = htonl(tcp_seq); tx_data->flags = htonl(TX_BYPASS_F); if (tcp_push) @@ -1437,8 +1425,8 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, if (prior_data_len) pos = chcr_copy_to_txd(prior_data, &q->q, pos, 16); /* send the complete packet except the header */ - cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len, - sgl_sdesc->addr); + cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr, + skb_offset, data_len); sgl_sdesc->skb = skb; chcr_txq_advance(&q->q, ndesc); @@ -1466,6 +1454,7 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, struct sk_buff *skb, u32 tcp_seq, u32 mss, bool tcp_push, struct sge_eth_txq *q, u32 port_id, u8 *prior_data, + u32 data_len, u32 skb_offset, u32 prior_data_len) { int credits, left, len16, last_desc; @@ -1475,14 +1464,16 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, struct ulptx_idata *idata; struct ulp_txpkt *ulptx; struct fw_ulptx_wr *wr; - u32 wr_mid = 0; + u32 wr_mid = 0, nfrags; void *pos; u64 *end; flits = DIV_ROUND_UP(CHCR_PLAIN_TX_DATA_LEN, 8); - flits += chcr_sgl_len(skb_shinfo(skb)->nr_frags); + nfrags = chcr_get_nfrags_to_send(skb, skb_offset, data_len); + flits += chcr_sgl_len(nfrags); if (prior_data_len) flits += 2; + /* WR will need len16 */ len16 = DIV_ROUND_UP(flits, 2); /* check how many descriptors needed */ @@ -1535,7 +1526,7 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, tx_data = (struct cpl_tx_data *)(idata + 1); OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid)); tx_data->len = htonl(TX_DATA_MSS_V(mss) | - TX_LENGTH_V(skb->data_len + prior_data_len)); + TX_LENGTH_V(data_len + prior_data_len)); /* set tcp seq number */ tx_data->rsvd = htonl(tcp_seq); tx_data->flags = htonl(TX_BYPASS_F); @@ -1559,8 +1550,8 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, end = pos + left; } /* send the complete packet including the header */ - cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len, - sgl_sdesc->addr); + cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr, + skb_offset, data_len); sgl_sdesc->skb = skb; chcr_txq_advance(&q->q, ndesc); @@ -1568,12 +1559,96 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, return 0; } +static int chcr_ktls_tunnel_pkt(struct chcr_ktls_info *tx_info, + struct sk_buff *skb, + struct sge_eth_txq *q) +{ + u32 ctrl, iplen, maclen, wr_mid = 0, len16; + struct tx_sw_desc *sgl_sdesc; + struct fw_eth_tx_pkt_wr *wr; + struct cpl_tx_pkt_core *cpl; + unsigned int flits, ndesc; + int credits, last_desc; + u64 cntrl1, *end; + void *pos; + + ctrl = sizeof(*cpl); + flits = DIV_ROUND_UP(sizeof(*wr) + ctrl, 8); + + flits += chcr_sgl_len(skb_shinfo(skb)->nr_frags + 1); + len16 = DIV_ROUND_UP(flits, 2); + /* check how many descriptors needed */ + ndesc = DIV_ROUND_UP(flits, 8); + + credits = chcr_txq_avail(&q->q) - ndesc; + if (unlikely(credits < 0)) { + chcr_eth_txq_stop(q); + return -ENOMEM; + } + + if (unlikely(credits < ETHTXQ_STOP_THRES)) { + chcr_eth_txq_stop(q); + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + } + + last_desc = q->q.pidx + ndesc - 1; + if (last_desc >= q->q.size) + last_desc -= q->q.size; + sgl_sdesc = &q->q.sdesc[last_desc]; + + if (unlikely(cxgb4_map_skb(tx_info->adap->pdev_dev, skb, + sgl_sdesc->addr) < 0)) { + memset(sgl_sdesc->addr, 0, sizeof(sgl_sdesc->addr)); + q->mapping_err++; + return -ENOMEM; + } + + iplen = skb_network_header_len(skb); + maclen = skb_mac_header_len(skb); + + pos = &q->q.desc[q->q.pidx]; + end = (u64 *)pos + flits; + wr = pos; + + /* Firmware work request header */ + wr->op_immdlen = htonl(FW_WR_OP_V(FW_ETH_TX_PKT_WR) | + FW_WR_IMMDLEN_V(ctrl)); + + wr->equiq_to_len16 = htonl(wr_mid | FW_WR_LEN16_V(len16)); + wr->r3 = 0; + + cpl = (void *)(wr + 1); + + /* CPL header */ + cpl->ctrl0 = htonl(TXPKT_OPCODE_V(CPL_TX_PKT) | + TXPKT_INTF_V(tx_info->tx_chan) | + TXPKT_PF_V(tx_info->adap->pf)); + cpl->pack = 0; + cntrl1 = TXPKT_CSUM_TYPE_V(tx_info->ip_family == AF_INET ? + TX_CSUM_TCPIP : TX_CSUM_TCPIP6); + cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) | + TXPKT_IPHDR_LEN_V(iplen); + /* checksum offload */ + cpl->ctrl1 = cpu_to_be64(cntrl1); + cpl->len = htons(skb->len); + + pos = cpl + 1; + + cxgb4_write_sgl(skb, &q->q, pos, end, 0, sgl_sdesc->addr); + sgl_sdesc->skb = skb; + chcr_txq_advance(&q->q, ndesc); + cxgb4_ring_tx_db(tx_info->adap, &q->q, ndesc); + return 0; +} + /* * chcr_ktls_copy_record_in_skb * @nskb - new skb where the frags to be added. + * @skb - old skb, to copy socket and destructor details. * @record - specific record which has complete 16k record in frags. */ static void chcr_ktls_copy_record_in_skb(struct sk_buff *nskb, + struct sk_buff *skb, struct tls_record_info *record) { int i = 0; @@ -1588,6 +1663,9 @@ static void chcr_ktls_copy_record_in_skb(struct sk_buff *nskb, nskb->data_len = record->len; nskb->len += record->len; nskb->truesize += record->len; + nskb->sk = skb->sk; + nskb->destructor = skb->destructor; + refcount_add(nskb->truesize, &nskb->sk->sk_wmem_alloc); } /* @@ -1659,7 +1737,7 @@ static int chcr_end_part_handler(struct chcr_ktls_info *tx_info, struct sk_buff *skb, struct tls_record_info *record, u32 tcp_seq, int mss, bool tcp_push_no_fin, - struct sge_eth_txq *q, + struct sge_eth_txq *q, u32 skb_offset, u32 tls_end_offset, bool last_wr) { struct sk_buff *nskb = NULL; @@ -1668,30 +1746,37 @@ static int chcr_end_part_handler(struct chcr_ktls_info *tx_info, nskb = skb; atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_complete_pkts); } else { - dev_kfree_skb_any(skb); - - nskb = alloc_skb(0, GFP_KERNEL); - if (!nskb) + nskb = alloc_skb(0, GFP_ATOMIC); + if (!nskb) { + dev_kfree_skb_any(skb); return NETDEV_TX_BUSY; + } + /* copy complete record in skb */ - chcr_ktls_copy_record_in_skb(nskb, record); + chcr_ktls_copy_record_in_skb(nskb, skb, record); /* packet is being sent from the beginning, update the tcp_seq * accordingly. */ tcp_seq = tls_record_start_seq(record); - /* reset snd una, so the middle record won't send the already - * sent part. - */ - if (chcr_ktls_update_snd_una(tx_info, q)) - goto out; + /* reset skb offset */ + skb_offset = 0; + + if (last_wr) + dev_kfree_skb_any(skb); + + last_wr = true; + atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_end_pkts); } if (chcr_ktls_xmit_wr_complete(nskb, tx_info, q, tcp_seq, + last_wr, record->len, skb_offset, + record->num_frags, (last_wr && tcp_push_no_fin), mss)) { goto out; } + tx_info->prev_seq = record->end_seq; return 0; out: dev_kfree_skb_any(nskb); @@ -1723,41 +1808,47 @@ static int chcr_short_record_handler(struct chcr_ktls_info *tx_info, struct sk_buff *skb, struct tls_record_info *record, u32 tcp_seq, int mss, bool tcp_push_no_fin, + u32 data_len, u32 skb_offset, struct sge_eth_txq *q, u32 tls_end_offset) { u32 tls_rec_offset = tcp_seq - tls_record_start_seq(record); u8 prior_data[16] = {0}; u32 prior_data_len = 0; - u32 data_len; /* check if the skb is ending in middle of tag/HASH, its a big * trouble, send the packet before the HASH. */ - int remaining_record = tls_end_offset - skb->data_len; + int remaining_record = tls_end_offset - data_len; if (remaining_record > 0 && remaining_record < TLS_CIPHER_AES_GCM_128_TAG_SIZE) { - int trimmed_len = skb->data_len - - (TLS_CIPHER_AES_GCM_128_TAG_SIZE - remaining_record); - struct sk_buff *tmp_skb = NULL; - /* don't process the pkt if it is only a partial tag */ - if (skb->data_len < TLS_CIPHER_AES_GCM_128_TAG_SIZE) - goto out; + int trimmed_len = 0; - WARN_ON(trimmed_len > skb->data_len); + if (tls_end_offset > TLS_CIPHER_AES_GCM_128_TAG_SIZE) + trimmed_len = data_len - + (TLS_CIPHER_AES_GCM_128_TAG_SIZE - + remaining_record); + if (!trimmed_len) + return FALLBACK; - /* shift to those many bytes */ - tmp_skb = alloc_skb(0, GFP_KERNEL); - if (unlikely(!tmp_skb)) - goto out; + WARN_ON(trimmed_len > data_len); - chcr_ktls_skb_shift(tmp_skb, skb, trimmed_len); - /* free the last trimmed portion */ - dev_kfree_skb_any(skb); - skb = tmp_skb; + data_len = trimmed_len; atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_trimmed_pkts); } - data_len = skb->data_len; + + /* check if it is only the header part. */ + if (tls_rec_offset + data_len <= (TLS_HEADER_SIZE + tx_info->iv_size)) { + if (chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss, + tcp_push_no_fin, q, + tx_info->port_id, prior_data, + data_len, skb_offset, prior_data_len)) + goto out; + + tx_info->prev_seq = tcp_seq + data_len; + return 0; + } + /* check if the middle record's start point is 16 byte aligned. CTR * needs 16 byte aligned start point to start encryption. */ @@ -1818,9 +1909,6 @@ static int chcr_short_record_handler(struct chcr_ktls_info *tx_info, } /* reset tcp_seq as per the prior_data_required len */ tcp_seq -= prior_data_len; - /* include prio_data_len for further calculation. - */ - data_len += prior_data_len; } /* reset snd una, so the middle record won't send the already * sent part. @@ -1829,37 +1917,54 @@ static int chcr_short_record_handler(struct chcr_ktls_info *tx_info, goto out; atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_middle_pkts); } else { - /* Else means, its a partial first part of the record. Check if - * its only the header, don't need to send for encryption then. - */ - if (data_len <= TLS_HEADER_SIZE + tx_info->iv_size) { - if (chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss, - tcp_push_no_fin, q, - tx_info->port_id, - prior_data, - prior_data_len)) { - goto out; - } - return 0; - } atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_start_pkts); } if (chcr_ktls_xmit_wr_short(skb, tx_info, q, tcp_seq, tcp_push_no_fin, mss, tls_rec_offset, prior_data, - prior_data_len)) { + prior_data_len, data_len, skb_offset)) { goto out; } + tx_info->prev_seq = tcp_seq + data_len + prior_data_len; return 0; out: dev_kfree_skb_any(skb); return NETDEV_TX_BUSY; } +static int chcr_ktls_sw_fallback(struct sk_buff *skb, + struct chcr_ktls_info *tx_info, + struct sge_eth_txq *q) +{ + u32 data_len, skb_offset; + struct sk_buff *nskb; + struct tcphdr *th; + + nskb = tls_encrypt_skb(skb); + + if (!nskb) + return 0; + + th = tcp_hdr(nskb); + skb_offset = skb_transport_offset(nskb) + tcp_hdrlen(nskb); + data_len = nskb->len - skb_offset; + skb_tx_timestamp(nskb); + + if (chcr_ktls_tunnel_pkt(tx_info, nskb, q)) + goto out; + + tx_info->prev_seq = ntohl(th->seq) + data_len; + atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_fallback); + return 0; +out: + dev_kfree_skb_any(nskb); + return 0; +} /* nic tls TX handler */ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) { + u32 tls_end_offset, tcp_seq, skb_data_len, skb_offset; struct ch_ktls_port_stats_debug *port_stats; struct chcr_ktls_ofld_ctx_tx *tx_ctx; struct ch_ktls_stats_debug *stats; @@ -1867,20 +1972,17 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) int data_len, qidx, ret = 0, mss; struct tls_record_info *record; struct chcr_ktls_info *tx_info; - u32 tls_end_offset, tcp_seq; struct tls_context *tls_ctx; - struct sk_buff *local_skb; struct sge_eth_txq *q; struct adapter *adap; unsigned long flags; tcp_seq = ntohl(th->seq); + skb_offset = skb_transport_offset(skb) + tcp_hdrlen(skb); + skb_data_len = skb->len - skb_offset; + data_len = skb_data_len; - mss = skb_is_gso(skb) ? skb_shinfo(skb)->gso_size : skb->data_len; - - /* check if we haven't set it for ktls offload */ - if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk)) - goto out; + mss = skb_is_gso(skb) ? skb_shinfo(skb)->gso_size : data_len; tls_ctx = tls_get_ctx(skb->sk); if (unlikely(tls_ctx->netdev != dev)) @@ -1892,14 +1994,6 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(!tx_info)) goto out; - /* don't touch the original skb, make a new skb to extract each records - * and send them separately. - */ - local_skb = alloc_skb(0, GFP_KERNEL); - - if (unlikely(!local_skb)) - return NETDEV_TX_BUSY; - adap = tx_info->adap; stats = &adap->ch_ktls_stats; port_stats = &stats->ktls_port[tx_info->port_id]; @@ -1914,20 +2008,7 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) if (ret) return NETDEV_TX_BUSY; } - /* update tcb */ - ret = chcr_ktls_xmit_tcb_cpls(tx_info, q, ntohl(th->seq), - ntohl(th->ack_seq), - ntohs(th->window)); - if (ret) { - dev_kfree_skb_any(local_skb); - return NETDEV_TX_BUSY; - } - - /* copy skb contents into local skb */ - chcr_ktls_skb_copy(skb, local_skb); - /* go through the skb and send only one record at a time. */ - data_len = skb->data_len; /* TCP segments can be in received either complete or partial. * chcr_end_part_handler will handle cases if complete record or end * part of the record is received. Incase of partial end part of record, @@ -1952,10 +2033,64 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) goto out; } + tls_end_offset = record->end_seq - tcp_seq; + + pr_debug("seq 0x%x, end_seq 0x%x prev_seq 0x%x, datalen 0x%x\n", + tcp_seq, record->end_seq, tx_info->prev_seq, data_len); + /* update tcb for the skb */ + if (skb_data_len == data_len) { + u32 tx_max = tcp_seq; + + if (!tls_record_is_start_marker(record) && + tls_end_offset < TLS_CIPHER_AES_GCM_128_TAG_SIZE) + tx_max = record->end_seq - + TLS_CIPHER_AES_GCM_128_TAG_SIZE; + + ret = chcr_ktls_xmit_tcb_cpls(tx_info, q, tx_max, + ntohl(th->ack_seq), + ntohs(th->window), + tls_end_offset != + record->len); + if (ret) { + spin_unlock_irqrestore(&tx_ctx->base.lock, + flags); + goto out; + } + + if (th->fin) + skb_get(skb); + } + if (unlikely(tls_record_is_start_marker(record))) { - spin_unlock_irqrestore(&tx_ctx->base.lock, flags); atomic64_inc(&port_stats->ktls_tx_skip_no_sync_data); - goto out; + /* If tls_end_offset < data_len, means there is some + * data after start marker, which needs encryption, send + * plaintext first and take skb refcount. else send out + * complete pkt as plaintext. + */ + if (tls_end_offset < data_len) + skb_get(skb); + else + tls_end_offset = data_len; + + ret = chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss, + (!th->fin && th->psh), q, + tx_info->port_id, NULL, + tls_end_offset, skb_offset, + 0); + + spin_unlock_irqrestore(&tx_ctx->base.lock, flags); + if (ret) { + /* free the refcount taken earlier */ + if (tls_end_offset < data_len) + dev_kfree_skb_any(skb); + goto out; + } + + data_len -= tls_end_offset; + tcp_seq = record->end_seq; + skb_offset += tls_end_offset; + continue; } /* increase page reference count of the record, so that there @@ -1967,73 +2102,64 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) /* lock cleared */ spin_unlock_irqrestore(&tx_ctx->base.lock, flags); - tls_end_offset = record->end_seq - tcp_seq; - pr_debug("seq 0x%x, end_seq 0x%x prev_seq 0x%x, datalen 0x%x\n", - tcp_seq, record->end_seq, tx_info->prev_seq, data_len); /* if a tls record is finishing in this SKB */ if (tls_end_offset <= data_len) { - struct sk_buff *nskb = NULL; - - if (tls_end_offset < data_len) { - nskb = alloc_skb(0, GFP_KERNEL); - if (unlikely(!nskb)) { - ret = -ENOMEM; - goto clear_ref; - } - - chcr_ktls_skb_shift(nskb, local_skb, - tls_end_offset); - } else { - /* its the only record in this skb, directly - * point it. - */ - nskb = local_skb; - } - ret = chcr_end_part_handler(tx_info, nskb, record, + ret = chcr_end_part_handler(tx_info, skb, record, tcp_seq, mss, (!th->fin && th->psh), q, + skb_offset, tls_end_offset, - (nskb == local_skb)); - - if (ret && nskb != local_skb) - dev_kfree_skb_any(local_skb); + skb_offset + + tls_end_offset == skb->len); data_len -= tls_end_offset; /* tcp_seq increment is required to handle next record. */ tcp_seq += tls_end_offset; + skb_offset += tls_end_offset; } else { - ret = chcr_short_record_handler(tx_info, local_skb, + ret = chcr_short_record_handler(tx_info, skb, record, tcp_seq, mss, (!th->fin && th->psh), + data_len, skb_offset, q, tls_end_offset); data_len = 0; } -clear_ref: + /* clear the frag ref count which increased locally before */ for (i = 0; i < record->num_frags; i++) { /* clear the frag ref count */ __skb_frag_unref(&record->frags[i]); } /* if any failure, come out from the loop. */ - if (ret) - goto out; + if (ret) { + if (th->fin) + dev_kfree_skb_any(skb); + + if (ret == FALLBACK) + return chcr_ktls_sw_fallback(skb, tx_info, q); + + return NETDEV_TX_OK; + } + /* length should never be less than 0 */ WARN_ON(data_len < 0); } while (data_len > 0); - tx_info->prev_seq = ntohl(th->seq) + skb->data_len; atomic64_inc(&port_stats->ktls_tx_encrypted_packets); - atomic64_add(skb->data_len, &port_stats->ktls_tx_encrypted_bytes); + atomic64_add(skb_data_len, &port_stats->ktls_tx_encrypted_bytes); /* tcp finish is set, send a separate tcp msg including all the options * as well. */ - if (th->fin) + if (th->fin) { chcr_ktls_write_tcp_options(tx_info, skb, q, tx_info->tx_chan); + dev_kfree_skb_any(skb); + } + return NETDEV_TX_OK; out: dev_kfree_skb_any(skb); return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h index c1651b1431a0..18b3b1f02415 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h @@ -26,6 +26,7 @@ #define CHCR_KTLS_WR_SIZE (CHCR_PLAIN_TX_DATA_LEN +\ sizeof(struct cpl_tx_sec_pdu)) +#define FALLBACK 35 enum ch_ktls_open_state { CH_KTLS_OPEN_SUCCESS = 0, diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index 96d561653496..50e3a70e5a29 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -1206,6 +1206,7 @@ static struct sock *chtls_recv_sock(struct sock *lsk, sk_setup_caps(newsk, dst); ctx = tls_get_ctx(lsk); newsk->sk_destruct = ctx->sk_destruct; + newsk->sk_prot_creator = lsk->sk_prot_creator; csk->sk = newsk; csk->passive_reap_next = oreq; csk->tx_chan = cxgb4_port_chan(ndev); diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c index 62c829023da5..a4fb463af22a 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c @@ -391,6 +391,7 @@ int chtls_setkey(struct chtls_sock *csk, u32 keylen, csk->wr_unacked += DIV_ROUND_UP(len, 16); enqueue_wr(csk, skb); cxgb4_ofld_send(csk->egress_dev, skb); + skb = NULL; chtls_set_scmd(csk); /* Clear quiesce for Rx key */ diff --git a/drivers/net/ethernet/faraday/Kconfig b/drivers/net/ethernet/faraday/Kconfig index c2677ec0564d..3d1e9a302148 100644 --- a/drivers/net/ethernet/faraday/Kconfig +++ b/drivers/net/ethernet/faraday/Kconfig @@ -33,6 +33,7 @@ config FTGMAC100 depends on !64BIT || BROKEN select PHYLIB select MDIO_ASPEED if MACH_ASPEED_G6 + select CRC32 help This driver supports the FTGMAC100 Gigabit Ethernet controller from Faraday. It is used on Faraday A369, Andes AG102 and some diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 00024dd41147..80fb1f537bb3 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1907,6 +1907,8 @@ err_register_netdev: clk_disable_unprepare(priv->rclk); clk_disable_unprepare(priv->clk); err_ncsi_dev: + if (priv->ndev) + ncsi_unregister_dev(priv->ndev); ftgmac100_destroy_mdio(netdev); err_setup_mdio: iounmap(priv->base); @@ -1926,6 +1928,8 @@ static int ftgmac100_remove(struct platform_device *pdev) netdev = platform_get_drvdata(pdev); priv = netdev_priv(netdev); + if (priv->ndev) + ncsi_unregister_dev(priv->ndev); unregister_netdev(netdev); clk_disable_unprepare(priv->rclk); diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index a1d53ddf1593..3f9175bdce77 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -25,6 +25,7 @@ config FEC depends on (M523x || M527x || M5272 || M528x || M520x || M532x || \ ARCH_MXC || SOC_IMX28 || COMPILE_TEST) default ARCH_MXC || SOC_IMX28 if ARM + select CRC32 select PHYLIB imply PTP_1588_CLOCK help diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index d9c285948fc2..cb7c028b1bf5 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2120,6 +2120,15 @@ workaround: skb_copy_header(new_skb, skb); new_skb->dev = skb->dev; + /* Copy relevant timestamp info from the old skb to the new */ + if (priv->tx_tstamp) { + skb_shinfo(new_skb)->tx_flags = skb_shinfo(skb)->tx_flags; + skb_shinfo(new_skb)->hwtstamps = skb_shinfo(skb)->hwtstamps; + skb_shinfo(new_skb)->tskey = skb_shinfo(skb)->tskey; + if (skb->sk) + skb_set_owner_w(new_skb, skb->sk); + } + /* We move the headroom when we align it so we have to reset the * network and transport header offsets relative to the new data * pointer. The checksum offload relies on these offsets. @@ -2127,7 +2136,6 @@ workaround: skb_set_network_header(new_skb, skb_network_offset(skb)); skb_set_transport_header(new_skb, skb_transport_offset(skb)); - /* TODO: does timestamping need the result in the old skb? */ dev_kfree_skb(skb); *s = new_skb; diff --git a/drivers/net/ethernet/freescale/dpaa2/Kconfig b/drivers/net/ethernet/freescale/dpaa2/Kconfig index cfd369cf4c8c..ee7a906e30b3 100644 --- a/drivers/net/ethernet/freescale/dpaa2/Kconfig +++ b/drivers/net/ethernet/freescale/dpaa2/Kconfig @@ -4,6 +4,8 @@ config FSL_DPAA2_ETH depends on FSL_MC_BUS && FSL_MC_DPIO select PHYLINK select PCS_LYNX + select FSL_XGMAC_MDIO + select NET_DEVLINK help This is the DPAA2 Ethernet driver supporting Freescale SoCs with DPAA2 (DataPath Acceleration Architecture v2). diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index 90cd243070d7..828c177df03d 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -269,6 +269,7 @@ static int dpaa2_pcs_create(struct dpaa2_mac *mac, if (!of_device_is_available(node)) { netdev_err(mac->net_dev, "pcs-handle node not available\n"); + of_node_put(node); return -ENODEV; } diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig index 0fa18b00c49b..d99ea0f4e4a6 100644 --- a/drivers/net/ethernet/freescale/enetc/Kconfig +++ b/drivers/net/ethernet/freescale/enetc/Kconfig @@ -16,6 +16,7 @@ config FSL_ENETC config FSL_ENETC_VF tristate "ENETC VF driver" depends on PCI && PCI_MSI + select FSL_ENETC_MDIO select PHYLINK select DIMLIB help diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 52be6e315752..fc2075ea57fe 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -33,7 +33,10 @@ netdev_tx_t enetc_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_BUSY; } + enetc_lock_mdio(); count = enetc_map_tx_buffs(tx_ring, skb, priv->active_offloads); + enetc_unlock_mdio(); + if (unlikely(!count)) goto drop_packet_err; @@ -239,7 +242,7 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb, skb_tx_timestamp(skb); /* let H/W know BD ring has been updated */ - enetc_wr_reg(tx_ring->tpir, i); /* includes wmb() */ + enetc_wr_reg_hot(tx_ring->tpir, i); /* includes wmb() */ return count; @@ -262,12 +265,16 @@ static irqreturn_t enetc_msix(int irq, void *data) struct enetc_int_vector *v = data; int i; + enetc_lock_mdio(); + /* disable interrupts */ - enetc_wr_reg(v->rbier, 0); - enetc_wr_reg(v->ricr1, v->rx_ictt); + enetc_wr_reg_hot(v->rbier, 0); + enetc_wr_reg_hot(v->ricr1, v->rx_ictt); for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS) - enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), 0); + enetc_wr_reg_hot(v->tbier_base + ENETC_BDR_OFF(i), 0); + + enetc_unlock_mdio(); napi_schedule(&v->napi); @@ -334,19 +341,23 @@ static int enetc_poll(struct napi_struct *napi, int budget) v->rx_napi_work = false; + enetc_lock_mdio(); + /* enable interrupts */ - enetc_wr_reg(v->rbier, ENETC_RBIER_RXTIE); + enetc_wr_reg_hot(v->rbier, ENETC_RBIER_RXTIE); for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS) - enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), - ENETC_TBIER_TXTIE); + enetc_wr_reg_hot(v->tbier_base + ENETC_BDR_OFF(i), + ENETC_TBIER_TXTIE); + + enetc_unlock_mdio(); return work_done; } static int enetc_bd_ready_count(struct enetc_bdr *tx_ring, int ci) { - int pi = enetc_rd_reg(tx_ring->tcir) & ENETC_TBCIR_IDX_MASK; + int pi = enetc_rd_reg_hot(tx_ring->tcir) & ENETC_TBCIR_IDX_MASK; return pi >= ci ? pi - ci : tx_ring->bd_count - ci + pi; } @@ -386,7 +397,10 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) i = tx_ring->next_to_clean; tx_swbd = &tx_ring->tx_swbd[i]; + + enetc_lock_mdio(); bds_to_clean = enetc_bd_ready_count(tx_ring, i); + enetc_unlock_mdio(); do_tstamp = false; @@ -429,16 +443,20 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) tx_swbd = tx_ring->tx_swbd; } + enetc_lock_mdio(); + /* BD iteration loop end */ if (is_eof) { tx_frm_cnt++; /* re-arm interrupt source */ - enetc_wr_reg(tx_ring->idr, BIT(tx_ring->index) | - BIT(16 + tx_ring->index)); + enetc_wr_reg_hot(tx_ring->idr, BIT(tx_ring->index) | + BIT(16 + tx_ring->index)); } if (unlikely(!bds_to_clean)) bds_to_clean = enetc_bd_ready_count(tx_ring, i); + + enetc_unlock_mdio(); } tx_ring->next_to_clean = i; @@ -515,8 +533,6 @@ static int enetc_refill_rx_ring(struct enetc_bdr *rx_ring, const int buff_cnt) if (likely(j)) { rx_ring->next_to_alloc = i; /* keep track from page reuse */ rx_ring->next_to_use = i; - /* update ENETC's consumer index */ - enetc_wr_reg(rx_ring->rcir, i); } return j; @@ -534,8 +550,8 @@ static void enetc_get_rx_tstamp(struct net_device *ndev, u64 tstamp; if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_TSTMP) { - lo = enetc_rd(hw, ENETC_SICTR0); - hi = enetc_rd(hw, ENETC_SICTR1); + lo = enetc_rd_reg_hot(hw->reg + ENETC_SICTR0); + hi = enetc_rd_reg_hot(hw->reg + ENETC_SICTR1); rxbd = enetc_rxbd_ext(rxbd); tstamp_lo = le32_to_cpu(rxbd->ext.tstamp); if (lo <= tstamp_lo) @@ -684,23 +700,31 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, u32 bd_status; u16 size; + enetc_lock_mdio(); + if (cleaned_cnt >= ENETC_RXBD_BUNDLE) { int count = enetc_refill_rx_ring(rx_ring, cleaned_cnt); + /* update ENETC's consumer index */ + enetc_wr_reg_hot(rx_ring->rcir, rx_ring->next_to_use); cleaned_cnt -= count; } rxbd = enetc_rxbd(rx_ring, i); bd_status = le32_to_cpu(rxbd->r.lstatus); - if (!bd_status) + if (!bd_status) { + enetc_unlock_mdio(); break; + } - enetc_wr_reg(rx_ring->idr, BIT(rx_ring->index)); + enetc_wr_reg_hot(rx_ring->idr, BIT(rx_ring->index)); dma_rmb(); /* for reading other rxbd fields */ size = le16_to_cpu(rxbd->r.buf_len); skb = enetc_map_rx_buff_to_skb(rx_ring, i, size); - if (!skb) + if (!skb) { + enetc_unlock_mdio(); break; + } enetc_get_offloads(rx_ring, rxbd, skb); @@ -712,6 +736,7 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, if (unlikely(bd_status & ENETC_RXBD_LSTATUS(ENETC_RXBD_ERR_MASK))) { + enetc_unlock_mdio(); dev_kfree_skb(skb); while (!(bd_status & ENETC_RXBD_LSTATUS_F)) { dma_rmb(); @@ -751,6 +776,8 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, enetc_process_skb(rx_ring, skb); + enetc_unlock_mdio(); + napi_gro_receive(napi, skb); rx_frm_cnt++; @@ -1225,6 +1252,7 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) rx_ring->idr = hw->reg + ENETC_SIRXIDR; enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring)); + enetc_wr(hw, ENETC_SIRXIDR, rx_ring->next_to_use); /* enable ring */ enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index 8ed1ebd5a183..89e558135432 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -143,8 +143,8 @@ static const struct { { ENETC_PM0_R255, "MAC rx 128-255 byte packets" }, { ENETC_PM0_R511, "MAC rx 256-511 byte packets" }, { ENETC_PM0_R1023, "MAC rx 512-1023 byte packets" }, - { ENETC_PM0_R1518, "MAC rx 1024-1518 byte packets" }, - { ENETC_PM0_R1519X, "MAC rx 1519 to max-octet packets" }, + { ENETC_PM0_R1522, "MAC rx 1024-1522 byte packets" }, + { ENETC_PM0_R1523X, "MAC rx 1523 to max-octet packets" }, { ENETC_PM0_ROVR, "MAC rx oversized packets" }, { ENETC_PM0_RJBR, "MAC rx jabber packets" }, { ENETC_PM0_RFRG, "MAC rx fragment packets" }, @@ -163,9 +163,13 @@ static const struct { { ENETC_PM0_TBCA, "MAC tx broadcast frames" }, { ENETC_PM0_TPKT, "MAC tx packets" }, { ENETC_PM0_TUND, "MAC tx undersized packets" }, + { ENETC_PM0_T64, "MAC tx 64 byte packets" }, { ENETC_PM0_T127, "MAC tx 65-127 byte packets" }, + { ENETC_PM0_T255, "MAC tx 128-255 byte packets" }, + { ENETC_PM0_T511, "MAC tx 256-511 byte packets" }, { ENETC_PM0_T1023, "MAC tx 512-1023 byte packets" }, - { ENETC_PM0_T1518, "MAC tx 1024-1518 byte packets" }, + { ENETC_PM0_T1522, "MAC tx 1024-1522 byte packets" }, + { ENETC_PM0_T1523X, "MAC tx 1523 to max-octet packets" }, { ENETC_PM0_TCNP, "MAC tx control packets" }, { ENETC_PM0_TDFR, "MAC tx deferred packets" }, { ENETC_PM0_TMCOL, "MAC tx multiple collisions" }, diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 17cf7c94fdb5..4cbf1667d7ff 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -267,8 +267,8 @@ enum enetc_bdr_type {TX, RX}; #define ENETC_PM0_R255 0x8180 #define ENETC_PM0_R511 0x8188 #define ENETC_PM0_R1023 0x8190 -#define ENETC_PM0_R1518 0x8198 -#define ENETC_PM0_R1519X 0x81A0 +#define ENETC_PM0_R1522 0x8198 +#define ENETC_PM0_R1523X 0x81A0 #define ENETC_PM0_ROVR 0x81A8 #define ENETC_PM0_RJBR 0x81B0 #define ENETC_PM0_RFRG 0x81B8 @@ -287,9 +287,13 @@ enum enetc_bdr_type {TX, RX}; #define ENETC_PM0_TBCA 0x8250 #define ENETC_PM0_TPKT 0x8260 #define ENETC_PM0_TUND 0x8268 +#define ENETC_PM0_T64 0x8270 #define ENETC_PM0_T127 0x8278 +#define ENETC_PM0_T255 0x8280 +#define ENETC_PM0_T511 0x8288 #define ENETC_PM0_T1023 0x8290 -#define ENETC_PM0_T1518 0x8298 +#define ENETC_PM0_T1522 0x8298 +#define ENETC_PM0_T1523X 0x82A0 #define ENETC_PM0_TCNP 0x82C0 #define ENETC_PM0_TDFR 0x82D0 #define ENETC_PM0_TMCOL 0x82D8 @@ -324,14 +328,100 @@ struct enetc_hw { void __iomem *global; }; -/* general register accessors */ -#define enetc_rd_reg(reg) ioread32((reg)) -#define enetc_wr_reg(reg, val) iowrite32((val), (reg)) +/* ENETC register accessors */ + +/* MDIO issue workaround (on LS1028A) - + * Due to a hardware issue, an access to MDIO registers + * that is concurrent with other ENETC register accesses + * may lead to the MDIO access being dropped or corrupted. + * To protect the MDIO accesses a readers-writers locking + * scheme is used, where the MDIO register accesses are + * protected by write locks to insure exclusivity, while + * the remaining ENETC registers are accessed under read + * locks since they only compete with MDIO accesses. + */ +extern rwlock_t enetc_mdio_lock; + +/* use this locking primitive only on the fast datapath to + * group together multiple non-MDIO register accesses to + * minimize the overhead of the lock + */ +static inline void enetc_lock_mdio(void) +{ + read_lock(&enetc_mdio_lock); +} + +static inline void enetc_unlock_mdio(void) +{ + read_unlock(&enetc_mdio_lock); +} + +/* use these accessors only on the fast datapath under + * the enetc_lock_mdio() locking primitive to minimize + * the overhead of the lock + */ +static inline u32 enetc_rd_reg_hot(void __iomem *reg) +{ + lockdep_assert_held(&enetc_mdio_lock); + + return ioread32(reg); +} + +static inline void enetc_wr_reg_hot(void __iomem *reg, u32 val) +{ + lockdep_assert_held(&enetc_mdio_lock); + + iowrite32(val, reg); +} + +/* internal helpers for the MDIO w/a */ +static inline u32 _enetc_rd_reg_wa(void __iomem *reg) +{ + u32 val; + + enetc_lock_mdio(); + val = ioread32(reg); + enetc_unlock_mdio(); + + return val; +} + +static inline void _enetc_wr_reg_wa(void __iomem *reg, u32 val) +{ + enetc_lock_mdio(); + iowrite32(val, reg); + enetc_unlock_mdio(); +} + +static inline u32 _enetc_rd_mdio_reg_wa(void __iomem *reg) +{ + unsigned long flags; + u32 val; + + write_lock_irqsave(&enetc_mdio_lock, flags); + val = ioread32(reg); + write_unlock_irqrestore(&enetc_mdio_lock, flags); + + return val; +} + +static inline void _enetc_wr_mdio_reg_wa(void __iomem *reg, u32 val) +{ + unsigned long flags; + + write_lock_irqsave(&enetc_mdio_lock, flags); + iowrite32(val, reg); + write_unlock_irqrestore(&enetc_mdio_lock, flags); +} + #ifdef ioread64 -#define enetc_rd_reg64(reg) ioread64((reg)) +static inline u64 _enetc_rd_reg64(void __iomem *reg) +{ + return ioread64(reg); +} #else /* using this to read out stats on 32b systems */ -static inline u64 enetc_rd_reg64(void __iomem *reg) +static inline u64 _enetc_rd_reg64(void __iomem *reg) { u32 low, high, tmp; @@ -345,12 +435,29 @@ static inline u64 enetc_rd_reg64(void __iomem *reg) } #endif +static inline u64 _enetc_rd_reg64_wa(void __iomem *reg) +{ + u64 val; + + enetc_lock_mdio(); + val = _enetc_rd_reg64(reg); + enetc_unlock_mdio(); + + return val; +} + +/* general register accessors */ +#define enetc_rd_reg(reg) _enetc_rd_reg_wa((reg)) +#define enetc_wr_reg(reg, val) _enetc_wr_reg_wa((reg), (val)) #define enetc_rd(hw, off) enetc_rd_reg((hw)->reg + (off)) #define enetc_wr(hw, off, val) enetc_wr_reg((hw)->reg + (off), val) -#define enetc_rd64(hw, off) enetc_rd_reg64((hw)->reg + (off)) +#define enetc_rd64(hw, off) _enetc_rd_reg64_wa((hw)->reg + (off)) /* port register accessors - PF only */ #define enetc_port_rd(hw, off) enetc_rd_reg((hw)->port + (off)) #define enetc_port_wr(hw, off, val) enetc_wr_reg((hw)->port + (off), val) +#define enetc_port_rd_mdio(hw, off) _enetc_rd_mdio_reg_wa((hw)->port + (off)) +#define enetc_port_wr_mdio(hw, off, val) _enetc_wr_mdio_reg_wa(\ + (hw)->port + (off), val) /* global register accessors - PF only */ #define enetc_global_rd(hw, off) enetc_rd_reg((hw)->global + (off)) #define enetc_global_wr(hw, off, val) enetc_wr_reg((hw)->global + (off), val) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c index 48c32a171afa..ee0116ed4738 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c @@ -16,13 +16,13 @@ static inline u32 _enetc_mdio_rd(struct enetc_mdio_priv *mdio_priv, int off) { - return enetc_port_rd(mdio_priv->hw, mdio_priv->mdio_base + off); + return enetc_port_rd_mdio(mdio_priv->hw, mdio_priv->mdio_base + off); } static inline void _enetc_mdio_wr(struct enetc_mdio_priv *mdio_priv, int off, u32 val) { - enetc_port_wr(mdio_priv->hw, mdio_priv->mdio_base + off, val); + enetc_port_wr_mdio(mdio_priv->hw, mdio_priv->mdio_base + off, val); } #define enetc_mdio_rd(mdio_priv, off) \ @@ -174,3 +174,7 @@ struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs) return hw; } EXPORT_SYMBOL_GPL(enetc_hw_alloc); + +/* Lock for MDIO access errata on LS1028A */ +DEFINE_RWLOCK(enetc_mdio_lock); +EXPORT_SYMBOL_GPL(enetc_mdio_lock); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 827f74e86d34..dbceb99c4441 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -92,18 +92,8 @@ static int enetc_setup_taprio(struct net_device *ndev, gcl_config->atc = 0xff; gcl_config->acl_len = cpu_to_le16(gcl_len); - if (!admin_conf->base_time) { - gcl_data->btl = - cpu_to_le32(enetc_rd(&priv->si->hw, ENETC_SICTR0)); - gcl_data->bth = - cpu_to_le32(enetc_rd(&priv->si->hw, ENETC_SICTR1)); - } else { - gcl_data->btl = - cpu_to_le32(lower_32_bits(admin_conf->base_time)); - gcl_data->bth = - cpu_to_le32(upper_32_bits(admin_conf->base_time)); - } - + gcl_data->btl = cpu_to_le32(lower_32_bits(admin_conf->base_time)); + gcl_data->bth = cpu_to_le32(upper_32_bits(admin_conf->base_time)); gcl_data->ct = cpu_to_le32(admin_conf->cycle_time); gcl_data->cte = cpu_to_le32(admin_conf->cycle_time_extension); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index d7919555250d..04f24c66cf36 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1808,7 +1808,7 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) int ret = 0, frame_start, frame_addr, frame_op; bool is_c45 = !!(regnum & MII_ADDR_C45); - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret; @@ -1867,11 +1867,9 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, int ret, frame_start, frame_addr; bool is_c45 = !!(regnum & MII_ADDR_C45); - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret; - else - ret = 0; if (is_c45) { frame_start = FEC_MMFR_ST_C45; @@ -2275,7 +2273,7 @@ static void fec_enet_get_regs(struct net_device *ndev, u32 i, off; int ret; - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return; @@ -2976,7 +2974,7 @@ fec_enet_open(struct net_device *ndev) int ret; bool reset_again; - ret = pm_runtime_get_sync(&fep->pdev->dev); + ret = pm_runtime_resume_and_get(&fep->pdev->dev); if (ret < 0) return ret; @@ -3770,7 +3768,7 @@ fec_drv_remove(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; int ret; - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) return ret; diff --git a/drivers/net/ethernet/freescale/fman/Kconfig b/drivers/net/ethernet/freescale/fman/Kconfig index 34150182cc35..48bf8088795d 100644 --- a/drivers/net/ethernet/freescale/fman/Kconfig +++ b/drivers/net/ethernet/freescale/fman/Kconfig @@ -4,6 +4,7 @@ config FSL_FMAN depends on FSL_SOC || ARCH_LAYERSCAPE || COMPILE_TEST select GENERIC_ALLOCATOR select PHYLIB + select CRC32 default n help Freescale Data-Path Acceleration Architecture Frame Manager diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h index a9066e6ff697..ca2ab6cf84d9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h @@ -35,8 +35,6 @@ #define HCLGE_DBG_DFX_SSU_2_OFFSET 12 -#pragma pack(1) - struct hclge_qos_pri_map_cmd { u8 pri0_tc : 4, pri1_tc : 4; @@ -85,8 +83,6 @@ struct hclge_dbg_reg_type_info { struct hclge_dbg_reg_common_msg reg_msg; }; -#pragma pack() - static const struct hclge_dbg_dfx_message hclge_dbg_bios_common_reg[] = { {false, "Reserved"}, {true, "BP_CPU_STATE"}, diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index da15913879f8..da9450f18717 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -834,7 +834,7 @@ static void release_napi(struct ibmvnic_adapter *adapter) static int ibmvnic_login(struct net_device *netdev) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - unsigned long timeout = msecs_to_jiffies(30000); + unsigned long timeout = msecs_to_jiffies(20000); int retry_count = 0; int retries = 10; bool retry; @@ -850,10 +850,8 @@ static int ibmvnic_login(struct net_device *netdev) adapter->init_done_rc = 0; reinit_completion(&adapter->init_done); rc = send_login(adapter); - if (rc) { - netdev_warn(netdev, "Unable to login\n"); + if (rc) return rc; - } if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { @@ -940,7 +938,7 @@ static void release_resources(struct ibmvnic_adapter *adapter) static int set_link_state(struct ibmvnic_adapter *adapter, u8 link_state) { struct net_device *netdev = adapter->netdev; - unsigned long timeout = msecs_to_jiffies(30000); + unsigned long timeout = msecs_to_jiffies(20000); union ibmvnic_crq crq; bool resend; int rc; @@ -1857,7 +1855,7 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter, if (reset_state == VNIC_OPEN) { rc = __ibmvnic_close(netdev); if (rc) - return rc; + goto out; } release_resources(adapter); @@ -1875,24 +1873,25 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter, } rc = ibmvnic_reset_init(adapter, true); - if (rc) - return IBMVNIC_INIT_FAILED; + if (rc) { + rc = IBMVNIC_INIT_FAILED; + goto out; + } /* If the adapter was in PROBE state prior to the reset, * exit here. */ if (reset_state == VNIC_PROBED) - return 0; + goto out; rc = ibmvnic_login(netdev); if (rc) { - adapter->state = reset_state; - return rc; + goto out; } rc = init_resources(adapter); if (rc) - return rc; + goto out; ibmvnic_disable_irqs(adapter); @@ -1902,8 +1901,10 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter, return 0; rc = __ibmvnic_open(netdev); - if (rc) - return IBMVNIC_OPEN_FAILED; + if (rc) { + rc = IBMVNIC_OPEN_FAILED; + goto out; + } /* refresh device's multicast list */ ibmvnic_set_multi(netdev); @@ -1912,7 +1913,10 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter, for (i = 0; i < adapter->req_rx_queues; i++) napi_schedule(&adapter->napi[i]); - return 0; +out: + if (rc) + adapter->state = reset_state; + return rc; } /** @@ -2015,7 +2019,6 @@ static int do_reset(struct ibmvnic_adapter *adapter, rc = ibmvnic_login(netdev); if (rc) { - adapter->state = reset_state; goto out; } @@ -2074,12 +2077,18 @@ static int do_reset(struct ibmvnic_adapter *adapter, for (i = 0; i < adapter->req_rx_queues; i++) napi_schedule(&adapter->napi[i]); - if (adapter->reset_reason != VNIC_RESET_FAILOVER) + if (adapter->reset_reason == VNIC_RESET_FAILOVER || + adapter->reset_reason == VNIC_RESET_MOBILITY) { call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev); + call_netdevice_notifiers(NETDEV_RESEND_IGMP, netdev); + } rc = 0; out: + /* restore the adapter state if reset failed */ + if (rc) + adapter->state = reset_state; rtnl_unlock(); return rc; @@ -2112,40 +2121,46 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter, if (rc) { netdev_err(adapter->netdev, "Couldn't initialize crq. rc=%d\n", rc); - return rc; + goto out; } rc = ibmvnic_reset_init(adapter, false); if (rc) - return rc; + goto out; /* If the adapter was in PROBE state prior to the reset, * exit here. */ if (reset_state == VNIC_PROBED) - return 0; + goto out; rc = ibmvnic_login(netdev); - if (rc) { - adapter->state = VNIC_PROBED; - return 0; - } + if (rc) + goto out; rc = init_resources(adapter); if (rc) - return rc; + goto out; ibmvnic_disable_irqs(adapter); adapter->state = VNIC_CLOSED; if (reset_state == VNIC_CLOSED) - return 0; + goto out; rc = __ibmvnic_open(netdev); - if (rc) - return IBMVNIC_OPEN_FAILED; + if (rc) { + rc = IBMVNIC_OPEN_FAILED; + goto out; + } - return 0; + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev); + call_netdevice_notifiers(NETDEV_RESEND_IGMP, netdev); +out: + /* restore adapter state if reset failed */ + if (rc) + adapter->state = reset_state; + return rc; } static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter) @@ -2167,17 +2182,6 @@ static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter) return rwi; } -static void free_all_rwi(struct ibmvnic_adapter *adapter) -{ - struct ibmvnic_rwi *rwi; - - rwi = get_next_rwi(adapter); - while (rwi) { - kfree(rwi); - rwi = get_next_rwi(adapter); - } -} - static void __ibmvnic_reset(struct work_struct *work) { struct ibmvnic_rwi *rwi; @@ -2209,7 +2213,6 @@ static void __ibmvnic_reset(struct work_struct *work) if (!saved_state) { reset_state = adapter->state; - adapter->state = VNIC_RESETTING; saved_state = true; } spin_unlock_irqrestore(&adapter->state_lock, flags); @@ -2236,20 +2239,23 @@ static void __ibmvnic_reset(struct work_struct *work) rc = do_hard_reset(adapter, rwi, reset_state); rtnl_unlock(); } + if (rc) { + /* give backing device time to settle down */ + netdev_dbg(adapter->netdev, + "[S:%d] Hard reset failed, waiting 60 secs\n", + adapter->state); + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(60 * HZ); + } } else if (!(rwi->reset_reason == VNIC_RESET_FATAL && adapter->from_passive_init)) { rc = do_reset(adapter, rwi, reset_state); } kfree(rwi); - if (rc == IBMVNIC_OPEN_FAILED) { - if (list_empty(&adapter->rwi_list)) - adapter->state = VNIC_CLOSED; - else - adapter->state = reset_state; - rc = 0; - } else if (rc && rc != IBMVNIC_INIT_FAILED && - !adapter->force_reset_recovery) - break; + adapter->last_reset_time = jiffies; + + if (rc) + netdev_dbg(adapter->netdev, "Reset failed, rc=%d\n", rc); rwi = get_next_rwi(adapter); @@ -2263,11 +2269,6 @@ static void __ibmvnic_reset(struct work_struct *work) complete(&adapter->reset_done); } - if (rc) { - netdev_dbg(adapter->netdev, "Reset failed\n"); - free_all_rwi(adapter); - } - clear_bit_unlock(0, &adapter->resetting); } @@ -2350,6 +2351,18 @@ static void ibmvnic_tx_timeout(struct net_device *dev, unsigned int txqueue) { struct ibmvnic_adapter *adapter = netdev_priv(dev); + if (test_bit(0, &adapter->resetting)) { + netdev_err(adapter->netdev, + "Adapter is resetting, skip timeout reset\n"); + return; + } + /* No queuing up reset until at least 5 seconds (default watchdog val) + * after last reset + */ + if (time_before(jiffies, (adapter->last_reset_time + dev->watchdog_timeo))) { + netdev_dbg(dev, "Not yet time to tx timeout.\n"); + return; + } ibmvnic_reset(adapter, VNIC_RESET_TIMEOUT); } @@ -2391,6 +2404,12 @@ restart_poll: if (!pending_scrq(adapter, adapter->rx_scrq[scrq_num])) break; + /* The queue entry at the current index is peeked at above + * to determine that there is a valid descriptor awaiting + * processing. We want to be sure that the current slot + * holds a valid descriptor before reading its contents. + */ + dma_rmb(); next = ibmvnic_next_scrq(adapter, adapter->rx_scrq[scrq_num]); rx_buff = (struct ibmvnic_rx_buff *)be64_to_cpu(next-> @@ -2849,15 +2868,26 @@ static int reset_one_sub_crq_queue(struct ibmvnic_adapter *adapter, { int rc; + if (!scrq) { + netdev_dbg(adapter->netdev, + "Invalid scrq reset. irq (%d) or msgs (%p).\n", + scrq->irq, scrq->msgs); + return -EINVAL; + } + if (scrq->irq) { free_irq(scrq->irq, scrq); irq_dispose_mapping(scrq->irq); scrq->irq = 0; } - - memset(scrq->msgs, 0, 4 * PAGE_SIZE); - atomic_set(&scrq->used, 0); - scrq->cur = 0; + if (scrq->msgs) { + memset(scrq->msgs, 0, 4 * PAGE_SIZE); + atomic_set(&scrq->used, 0); + scrq->cur = 0; + } else { + netdev_dbg(adapter->netdev, "Invalid scrq reset\n"); + return -EINVAL; + } rc = h_reg_sub_crq(adapter->vdev->unit_address, scrq->msg_token, 4 * PAGE_SIZE, &scrq->crq_num, &scrq->hw_irq); @@ -2868,6 +2898,9 @@ static int reset_sub_crq_queues(struct ibmvnic_adapter *adapter) { int i, rc; + if (!adapter->tx_scrq || !adapter->rx_scrq) + return -EINVAL; + for (i = 0; i < adapter->req_tx_queues; i++) { netdev_dbg(adapter->netdev, "Re-setting tx_scrq[%d]\n", i); rc = reset_one_sub_crq_queue(adapter, adapter->tx_scrq[i]); @@ -3086,13 +3119,18 @@ restart_loop: unsigned int pool = scrq->pool_index; int num_entries = 0; + /* The queue entry at the current index is peeked at above + * to determine that there is a valid descriptor awaiting + * processing. We want to be sure that the current slot + * holds a valid descriptor before reading its contents. + */ + dma_rmb(); + next = ibmvnic_next_scrq(adapter, scrq); for (i = 0; i < next->tx_comp.num_comps; i++) { - if (next->tx_comp.rcs[i]) { + if (next->tx_comp.rcs[i]) dev_err(dev, "tx error %x\n", next->tx_comp.rcs[i]); - continue; - } index = be32_to_cpu(next->tx_comp.correlators[i]); if (index & IBMVNIC_TSO_POOL_MASK) { tx_pool = &adapter->tso_pool[pool]; @@ -3486,6 +3524,11 @@ static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *adapter, } spin_unlock_irqrestore(&scrq->lock, flags); + /* Ensure that the entire buffer descriptor has been + * loaded before reading its contents + */ + dma_rmb(); + return entry; } @@ -3707,15 +3750,16 @@ static int send_login(struct ibmvnic_adapter *adapter) struct ibmvnic_login_rsp_buffer *login_rsp_buffer; struct ibmvnic_login_buffer *login_buffer; struct device *dev = &adapter->vdev->dev; + struct vnic_login_client_data *vlcd; dma_addr_t rsp_buffer_token; dma_addr_t buffer_token; size_t rsp_buffer_size; union ibmvnic_crq crq; + int client_data_len; size_t buffer_size; __be64 *tx_list_p; __be64 *rx_list_p; - int client_data_len; - struct vnic_login_client_data *vlcd; + int rc; int i; if (!adapter->tx_scrq || !adapter->rx_scrq) { @@ -3819,16 +3863,25 @@ static int send_login(struct ibmvnic_adapter *adapter) crq.login.cmd = LOGIN; crq.login.ioba = cpu_to_be32(buffer_token); crq.login.len = cpu_to_be32(buffer_size); - ibmvnic_send_crq(adapter, &crq); + + adapter->login_pending = true; + rc = ibmvnic_send_crq(adapter, &crq); + if (rc) { + adapter->login_pending = false; + netdev_err(adapter->netdev, "Failed to send login, rc=%d\n", rc); + goto buf_rsp_map_failed; + } return 0; buf_rsp_map_failed: kfree(login_rsp_buffer); + adapter->login_rsp_buf = NULL; buf_rsp_alloc_failed: dma_unmap_single(dev, buffer_token, buffer_size, DMA_TO_DEVICE); buf_map_failed: kfree(login_buffer); + adapter->login_buf = NULL; buf_alloc_failed: return -1; } @@ -4371,6 +4424,15 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, u64 *size_array; int i; + /* CHECK: Test/set of login_pending does not need to be atomic + * because only ibmvnic_tasklet tests/clears this. + */ + if (!adapter->login_pending) { + netdev_warn(netdev, "Ignoring unexpected login response\n"); + return 0; + } + adapter->login_pending = false; + dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz, DMA_TO_DEVICE); dma_unmap_single(dev, adapter->login_rsp_buf_token, @@ -4400,7 +4462,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, adapter->req_rx_add_queues != be32_to_cpu(login_rsp->num_rxadd_subcrqs))) { dev_err(dev, "FATAL: Inconsistent login and login rsp\n"); - ibmvnic_remove(adapter->vdev); + ibmvnic_reset(adapter, VNIC_RESET_FATAL); return -EIO; } size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + @@ -4742,6 +4804,11 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, case IBMVNIC_CRQ_INIT: dev_info(dev, "Partner initialized\n"); adapter->from_passive_init = true; + /* Discard any stale login responses from prev reset. + * CHECK: should we clear even on INIT_COMPLETE? + */ + adapter->login_pending = false; + if (!completion_done(&adapter->init_done)) { complete(&adapter->init_done); adapter->init_done_rc = -EIO; @@ -4958,6 +5025,9 @@ static int ibmvnic_reset_crq(struct ibmvnic_adapter *adapter) } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); /* Clean out the queue */ + if (!crq->msgs) + return -EINVAL; + memset(crq->msgs, 0, PAGE_SIZE); crq->cur = 0; crq->active = false; @@ -5076,7 +5146,7 @@ map_failed: static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset) { struct device *dev = &adapter->vdev->dev; - unsigned long timeout = msecs_to_jiffies(30000); + unsigned long timeout = msecs_to_jiffies(20000); u64 old_num_rx_queues, old_num_tx_queues; int rc; @@ -5171,6 +5241,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) dev_set_drvdata(&dev->dev, netdev); adapter->vdev = dev; adapter->netdev = netdev; + adapter->login_pending = false; ether_addr_copy(adapter->mac_addr, mac_addr_p); ether_addr_copy(netdev->dev_addr, adapter->mac_addr); @@ -5234,7 +5305,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) adapter->state = VNIC_PROBED; adapter->wait_for_reset = false; - + adapter->last_reset_time = jiffies; return 0; ibmvnic_register_fail: @@ -5262,7 +5333,7 @@ static int ibmvnic_remove(struct vio_dev *dev) unsigned long flags; spin_lock_irqsave(&adapter->state_lock, flags); - if (adapter->state == VNIC_RESETTING) { + if (test_bit(0, &adapter->resetting)) { spin_unlock_irqrestore(&adapter->state_lock, flags); return -EBUSY; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 217dcc7ded70..21e7ea858cda 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -942,8 +942,7 @@ enum vnic_state {VNIC_PROBING = 1, VNIC_CLOSING, VNIC_CLOSED, VNIC_REMOVING, - VNIC_REMOVED, - VNIC_RESETTING}; + VNIC_REMOVED}; enum ibmvnic_reset_reason {VNIC_RESET_FAILOVER = 1, VNIC_RESET_MOBILITY, @@ -1087,6 +1086,9 @@ struct ibmvnic_adapter { struct delayed_work ibmvnic_delayed_reset; unsigned long resetting; bool napi_enabled, from_passive_init; + bool login_pending; + /* last device reset time */ + unsigned long last_reset_time; bool failover_pending; bool force_reset_recovery; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index b30f00891c03..128ab6898070 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6475,13 +6475,13 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter) /* Ungate PGCB clock */ mac_data = er32(FEXTNVM9); - mac_data |= BIT(28); + mac_data &= ~BIT(28); ew32(FEXTNVM9, mac_data); /* Enable K1 off to enable mPHY Power Gating */ mac_data = er32(FEXTNVM6); mac_data |= BIT(31); - ew32(FEXTNVM12, mac_data); + ew32(FEXTNVM6, mac_data); /* Enable mPHY power gating for any link and speed */ mac_data = er32(FEXTNVM8); @@ -6525,11 +6525,11 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) /* Disable K1 off */ mac_data = er32(FEXTNVM6); mac_data &= ~BIT(31); - ew32(FEXTNVM12, mac_data); + ew32(FEXTNVM6, mac_data); /* Disable Ungate PGCB clock */ mac_data = er32(FEXTNVM9); - mac_data &= ~BIT(28); + mac_data |= BIT(28); ew32(FEXTNVM9, mac_data); /* Cancel not waking from dynamic diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 537300e762f0..d231a2cdd98f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -140,6 +140,7 @@ enum i40e_state_t { __I40E_CLIENT_RESET, __I40E_VIRTCHNL_OP_PENDING, __I40E_RECOVERY_MODE, + __I40E_VF_RESETS_DISABLED, /* disable resets during i40e_remove */ /* This must be last as it determines the size of the BITMAP */ __I40E_STATE_SIZE__, }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 4f8a2154b93f..1337686bd099 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4010,8 +4010,16 @@ static irqreturn_t i40e_intr(int irq, void *data) } if (icr0 & I40E_PFINT_ICR0_VFLR_MASK) { - ena_mask &= ~I40E_PFINT_ICR0_ENA_VFLR_MASK; - set_bit(__I40E_VFLR_EVENT_PENDING, pf->state); + /* disable any further VFLR event notifications */ + if (test_bit(__I40E_VF_RESETS_DISABLED, pf->state)) { + u32 reg = rd32(hw, I40E_PFINT_ICR0_ENA); + + reg &= ~I40E_PFINT_ICR0_VFLR_MASK; + wr32(hw, I40E_PFINT_ICR0_ENA, reg); + } else { + ena_mask &= ~I40E_PFINT_ICR0_ENA_VFLR_MASK; + set_bit(__I40E_VFLR_EVENT_PENDING, pf->state); + } } if (icr0 & I40E_PFINT_ICR0_GRST_MASK) { @@ -15311,6 +15319,11 @@ static void i40e_remove(struct pci_dev *pdev) while (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) usleep_range(1000, 2000); + if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { + set_bit(__I40E_VF_RESETS_DISABLED, pf->state); + i40e_free_vfs(pf); + pf->flags &= ~I40E_FLAG_SRIOV_ENABLED; + } /* no more scheduling of any task */ set_bit(__I40E_SUSPENDED, pf->state); set_bit(__I40E_DOWN, pf->state); @@ -15337,11 +15350,6 @@ static void i40e_remove(struct pci_dev *pdev) */ i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false); - if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { - i40e_free_vfs(pf); - pf->flags &= ~I40E_FLAG_SRIOV_ENABLED; - } - i40e_fdir_teardown(pf); /* If there is a switch structure or any orphans, remove them. diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index d43ce13a93c9..3f5825fa67c9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1850,6 +1850,7 @@ static inline bool i40e_page_is_reusable(struct page *page) * the adapter for another receive * * @rx_buffer: buffer containing the page + * @rx_buffer_pgcnt: buffer page refcount pre xdp_do_redirect() call * * If page is reusable, rx_buffer->page_offset is adjusted to point to * an unused region in the page. @@ -1872,7 +1873,8 @@ static inline bool i40e_page_is_reusable(struct page *page) * * In either case, if the page is reusable its refcount is increased. **/ -static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) +static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; @@ -1883,7 +1885,7 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_count(page) - pagecnt_bias) > 1)) + if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) return false; #else #define I40E_LAST_OFFSET \ @@ -1942,16 +1944,24 @@ static void i40e_add_rx_frag(struct i40e_ring *rx_ring, * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use * @rx_ring: rx descriptor ring to transact packets on * @size: size of buffer to add to skb + * @rx_buffer_pgcnt: buffer page refcount * * This function will pull an Rx buffer from the ring and synchronize it * for use by the CPU. */ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, - const unsigned int size) + const unsigned int size, + int *rx_buffer_pgcnt) { struct i40e_rx_buffer *rx_buffer; rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); + *rx_buffer_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buffer->page); +#else + 0; +#endif prefetch_page_address(rx_buffer->page); /* we are reusing so sync this buffer for CPU use */ @@ -2102,14 +2112,16 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, * i40e_put_rx_buffer - Clean up used buffer and either recycle or free * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: rx buffer to pull data from + * @rx_buffer_pgcnt: rx buffer page refcount pre xdp_do_redirect() call * * This function will clean up the contents of the rx_buffer. It will * either recycle the buffer or unmap it and free the associated resources. */ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer) + struct i40e_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) { - if (i40e_can_reuse_rx_page(rx_buffer)) { + if (i40e_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) { /* hand second half of page back to the ring */ i40e_reuse_rx_page(rx_ring, rx_buffer); } else { @@ -2336,6 +2348,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) while (likely(total_rx_packets < (unsigned int)budget)) { struct i40e_rx_buffer *rx_buffer; union i40e_rx_desc *rx_desc; + int rx_buffer_pgcnt; unsigned int size; u64 qword; @@ -2378,7 +2391,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) break; i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb); - rx_buffer = i40e_get_rx_buffer(rx_ring, size); + rx_buffer = i40e_get_rx_buffer(rx_ring, size, &rx_buffer_pgcnt); /* retrieve a buffer from the ring */ if (!skb) { @@ -2421,7 +2434,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) break; } - i40e_put_rx_buffer(rx_ring, rx_buffer); + i40e_put_rx_buffer(rx_ring, rx_buffer, rx_buffer_pgcnt); cleaned_count++; if (i40e_is_non_eop(rx_ring, rx_desc, skb)) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index c96e2f2d4cba..1b5390ec3d78 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1403,7 +1403,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf) * @vf: pointer to the VF structure * @flr: VFLR was issued or not * - * Returns true if the VF is reset, false otherwise. + * Returns true if the VF is in reset, resets successfully, or resets + * are disabled and false otherwise. **/ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) { @@ -1413,11 +1414,14 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) u32 reg; int i; + if (test_bit(__I40E_VF_RESETS_DISABLED, pf->state)) + return true; + /* If the VFs have been disabled, this means something else is * resetting the VF, so we shouldn't continue. */ if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) - return false; + return true; i40e_trigger_vf_reset(vf, flr); @@ -1581,6 +1585,15 @@ void i40e_free_vfs(struct i40e_pf *pf) i40e_notify_client_of_vf_enable(pf, 0); + /* Disable IOV before freeing resources. This lets any VF drivers + * running in the host get themselves cleaned up before we yank + * the carpet out from underneath their feet. + */ + if (!pci_vfs_assigned(pf->pdev)) + pci_disable_sriov(pf->pdev); + else + dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n"); + /* Amortize wait time by stopping all VFs at the same time */ for (i = 0; i < pf->num_alloc_vfs; i++) { if (test_bit(I40E_VF_STATE_INIT, &pf->vf[i].vf_states)) @@ -1596,15 +1609,6 @@ void i40e_free_vfs(struct i40e_pf *pf) i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[i].lan_vsi_idx]); } - /* Disable IOV before freeing resources. This lets any VF drivers - * running in the host get themselves cleaned up before we yank - * the carpet out from underneath their feet. - */ - if (!pci_vfs_assigned(pf->pdev)) - pci_disable_sriov(pf->pdev); - else - dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n"); - /* free up VF resources */ tmp = pf->num_alloc_vfs; pf->num_alloc_vfs = 0; @@ -2713,6 +2717,10 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; } + if (is_valid_ether_addr(al->list[i].addr) && + is_zero_ether_addr(vf->default_lan_addr.addr)) + ether_addr_copy(vf->default_lan_addr.addr, + al->list[i].addr); } } spin_unlock_bh(&vsi->mac_filter_hash_lock); @@ -2740,6 +2748,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_ether_addr_list *al = (struct virtchnl_ether_addr_list *)msg; + bool was_unimac_deleted = false; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; i40e_status ret = 0; @@ -2759,6 +2768,8 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) ret = I40E_ERR_INVALID_MAC_ADDR; goto error_param; } + if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr)) + was_unimac_deleted = true; } vsi = pf->vsi[vf->lan_vsi_idx]; @@ -2779,10 +2790,25 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) dev_err(&pf->pdev->dev, "Unable to program VF %d MAC filters, error %d\n", vf->vf_id, ret); + if (vf->trusted && was_unimac_deleted) { + struct i40e_mac_filter *f; + struct hlist_node *h; + u8 *macaddr = NULL; + int bkt; + + /* set last unicast mac address as default */ + spin_lock_bh(&vsi->mac_filter_hash_lock); + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + if (is_valid_ether_addr(f->macaddr)) + macaddr = f->macaddr; + } + if (macaddr) + ether_addr_copy(vf->default_lan_addr.addr, macaddr); + spin_unlock_bh(&vsi->mac_filter_hash_lock); + } error_param: /* send the response to the VF */ - return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR, - ret); + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR, ret); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 6acede0acdca..567fd67e900e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -281,8 +281,8 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_packets = 0; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); unsigned int xdp_res, xdp_xmit = 0; + bool failure = false; struct sk_buff *skb; - bool failure; while (likely(total_rx_packets < (unsigned int)budget)) { union i40e_rx_desc *rx_desc; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index eae75260fe20..23eca2f0a03b 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -762,13 +762,15 @@ ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size) /** * ice_can_reuse_rx_page - Determine if page can be reused for another Rx * @rx_buf: buffer containing the page + * @rx_buf_pgcnt: rx_buf page refcount pre xdp_do_redirect() call * * If page is reusable, we have a green light for calling ice_reuse_rx_page, * which will assign the current buffer to the buffer that next_to_alloc is * pointing to; otherwise, the DMA mapping needs to be destroyed and * page freed */ -static bool ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) +static bool +ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf, int rx_buf_pgcnt) { unsigned int pagecnt_bias = rx_buf->pagecnt_bias; struct page *page = rx_buf->page; @@ -779,7 +781,7 @@ static bool ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_count(page) - pagecnt_bias) > 1)) + if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1)) return false; #else #define ICE_LAST_OFFSET \ @@ -864,17 +866,24 @@ ice_reuse_rx_page(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf) * @rx_ring: Rx descriptor ring to transact packets on * @skb: skb to be used * @size: size of buffer to add to skb + * @rx_buf_pgcnt: rx_buf page refcount * * This function will pull an Rx buffer from the ring and synchronize it * for use by the CPU. */ static struct ice_rx_buf * ice_get_rx_buf(struct ice_ring *rx_ring, struct sk_buff **skb, - const unsigned int size) + const unsigned int size, int *rx_buf_pgcnt) { struct ice_rx_buf *rx_buf; rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean]; + *rx_buf_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buf->page); +#else + 0; +#endif prefetchw(rx_buf->page); *skb = rx_buf->skb; @@ -1006,12 +1015,15 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, * ice_put_rx_buf - Clean up used buffer and either recycle or free * @rx_ring: Rx descriptor ring to transact packets on * @rx_buf: Rx buffer to pull data from + * @rx_buf_pgcnt: Rx buffer page count pre xdp_do_redirect() * * This function will update next_to_clean and then clean up the contents * of the rx_buf. It will either recycle the buffer or unmap it and free * the associated resources. */ -static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) +static void +ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, + int rx_buf_pgcnt) { u16 ntc = rx_ring->next_to_clean + 1; @@ -1022,7 +1034,7 @@ static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) if (!rx_buf) return; - if (ice_can_reuse_rx_page(rx_buf)) { + if (ice_can_reuse_rx_page(rx_buf, rx_buf_pgcnt)) { /* hand second half of page back to the ring */ ice_reuse_rx_page(rx_ring, rx_buf); } else { @@ -1097,6 +1109,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) struct sk_buff *skb; unsigned int size; u16 stat_err_bits; + int rx_buf_pgcnt; u16 vlan_tag = 0; u8 rx_ptype; @@ -1119,7 +1132,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) dma_rmb(); if (rx_desc->wb.rxdid == FDIR_DESC_RXDID || !rx_ring->netdev) { - ice_put_rx_buf(rx_ring, NULL); + ice_put_rx_buf(rx_ring, NULL, 0); cleaned_count++; continue; } @@ -1128,7 +1141,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) ICE_RX_FLX_DESC_PKT_LEN_M; /* retrieve a buffer from the ring */ - rx_buf = ice_get_rx_buf(rx_ring, &skb, size); + rx_buf = ice_get_rx_buf(rx_ring, &skb, size, &rx_buf_pgcnt); if (!size) { xdp.data = NULL; @@ -1168,7 +1181,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) total_rx_pkts++; cleaned_count++; - ice_put_rx_buf(rx_ring, rx_buf); + ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt); continue; construct_skb: if (skb) { @@ -1187,7 +1200,7 @@ construct_skb: break; } - ice_put_rx_buf(rx_ring, rx_buf); + ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt); cleaned_count++; /* skip if it is NOP desc */ diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 0286d2fceee4..aaa954aae574 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -138,6 +138,8 @@ struct vf_mac_filter { /* this is the size past which hardware will drop packets when setting LPE=0 */ #define MAXIMUM_ETHERNET_VLAN_SIZE 1522 +#define IGB_ETH_PKT_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) + /* Supported Rx Buffer Sizes */ #define IGB_RXBUFFER_256 256 #define IGB_RXBUFFER_1536 1536 @@ -247,6 +249,9 @@ enum igb_tx_flags { #define IGB_SFF_ADDRESSING_MODE 0x4 #define IGB_SFF_8472_UNSUP 0x00 +/* TX resources are shared between XDP and netstack + * and we need to tag the buffer type to distinguish them + */ enum igb_tx_buf_type { IGB_TYPE_SKB = 0, IGB_TYPE_XDP, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 5fc2c381da55..0d343d050973 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2824,20 +2824,25 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, } } -static int igb_xdp_setup(struct net_device *dev, struct bpf_prog *prog) +static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf) { - int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + int i, frame_size = dev->mtu + IGB_ETH_PKT_HDR_PAD; struct igb_adapter *adapter = netdev_priv(dev); + struct bpf_prog *prog = bpf->prog, *old_prog; bool running = netif_running(dev); - struct bpf_prog *old_prog; bool need_reset; /* verify igb ring attributes are sufficient for XDP */ for (i = 0; i < adapter->num_rx_queues; i++) { struct igb_ring *ring = adapter->rx_ring[i]; - if (frame_size > igb_rx_bufsz(ring)) + if (frame_size > igb_rx_bufsz(ring)) { + NL_SET_ERR_MSG_MOD(bpf->extack, + "The RX buffer size is too small for the frame size"); + netdev_warn(dev, "XDP RX buffer size %d is too small for the frame size %d\n", + igb_rx_bufsz(ring), frame_size); return -EINVAL; + } } old_prog = xchg(&adapter->xdp_prog, prog); @@ -2869,7 +2874,7 @@ static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: - return igb_xdp_setup(dev, xdp->prog); + return igb_xdp_setup(dev, xdp); default: return -EINVAL; } @@ -2910,10 +2915,12 @@ static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) */ tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; if (unlikely(!tx_ring)) - return -ENXIO; + return IGB_XDP_CONSUMED; nq = txring_txq(tx_ring); __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + nq->trans_start = jiffies; ret = igb_xmit_xdp_ring(adapter, tx_ring, xdpf); __netif_tx_unlock(nq); @@ -2946,6 +2953,9 @@ static int igb_xdp_xmit(struct net_device *dev, int n, nq = txring_txq(tx_ring); __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + nq->trans_start = jiffies; + for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; int err; @@ -3950,8 +3960,7 @@ static int igb_sw_init(struct igb_adapter *adapter) /* set default work limits */ adapter->tx_work_limit = IGB_DEFAULT_TX_WORK; - adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + - VLAN_HLEN; + adapter->max_frame_size = netdev->mtu + IGB_ETH_PKT_HDR_PAD; adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; spin_lock_init(&adapter->nfc_lock); @@ -6491,7 +6500,7 @@ static void igb_get_stats64(struct net_device *netdev, static int igb_change_mtu(struct net_device *netdev, int new_mtu) { struct igb_adapter *adapter = netdev_priv(netdev); - int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + int max_frame = new_mtu + IGB_ETH_PKT_HDR_PAD; if (adapter->xdp_prog) { int i; @@ -6500,7 +6509,9 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu) struct igb_ring *ring = adapter->rx_ring[i]; if (max_frame > igb_rx_bufsz(ring)) { - netdev_warn(adapter->netdev, "Requested MTU size is not supported with XDP\n"); + netdev_warn(adapter->netdev, + "Requested MTU size is not supported with XDP. Max frame size is %d\n", + max_frame); return -EINVAL; } } @@ -8351,6 +8362,7 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, SKB_DATA_ALIGN(xdp->data_end - xdp->data_hard_start); #endif + unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb; /* prefetch first cache line of first page */ @@ -8365,6 +8377,9 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, skb_reserve(skb, xdp->data - xdp->data_hard_start); __skb_put(skb, xdp->data_end - xdp->data); + if (metasize) + skb_metadata_set(skb, metasize); + /* pull timestamp out of packet data */ if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb); @@ -8771,7 +8786,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) rx_ring->skb = skb; if (xdp_xmit & IGB_XDP_REDIR) - xdp_do_flush_map(); + xdp_do_flush(); if (xdp_xmit & IGB_XDP_TX) { struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 9112dff075cf..b673ac1199bb 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3891,21 +3891,23 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu) } /** - * igc_get_stats - Get System Network Statistics + * igc_get_stats64 - Get System Network Statistics * @netdev: network interface device structure + * @stats: rtnl_link_stats64 pointer * * Returns the address of the device statistics structure. * The statistics are updated here and also from the timer callback. */ -static struct net_device_stats *igc_get_stats(struct net_device *netdev) +static void igc_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) { struct igc_adapter *adapter = netdev_priv(netdev); + spin_lock(&adapter->stats64_lock); if (!test_bit(__IGC_RESETTING, &adapter->state)) igc_update_stats(adapter); - - /* only return the current stats */ - return &netdev->stats; + memcpy(stats, &adapter->stats64, sizeof(*stats)); + spin_unlock(&adapter->stats64_lock); } static netdev_features_t igc_fix_features(struct net_device *netdev, @@ -4855,7 +4857,7 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_set_rx_mode = igc_set_rx_mode, .ndo_set_mac_address = igc_set_mac, .ndo_change_mtu = igc_change_mtu, - .ndo_get_stats = igc_get_stats, + .ndo_get_stats64 = igc_get_stats64, .ndo_fix_features = igc_fix_features, .ndo_set_features = igc_set_features, .ndo_features_check = igc_features_check, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 45ae33e15303..f3f449f53920 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1945,7 +1945,8 @@ static inline bool ixgbe_page_is_reserved(struct page *page) return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } -static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer) +static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; @@ -1956,7 +1957,7 @@ static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) + if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) return false; #else /* The last offset is a bit aggressive in that we assume the @@ -2021,11 +2022,18 @@ static void ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, static struct ixgbe_rx_buffer *ixgbe_get_rx_buffer(struct ixgbe_ring *rx_ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff **skb, - const unsigned int size) + const unsigned int size, + int *rx_buffer_pgcnt) { struct ixgbe_rx_buffer *rx_buffer; rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + *rx_buffer_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buffer->page); +#else + 0; +#endif prefetchw(rx_buffer->page); *skb = rx_buffer->skb; @@ -2055,9 +2063,10 @@ skip_sync: static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *rx_buffer, - struct sk_buff *skb) + struct sk_buff *skb, + int rx_buffer_pgcnt) { - if (ixgbe_can_reuse_rx_page(rx_buffer)) { + if (ixgbe_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) { /* hand second half of page back to the ring */ ixgbe_reuse_rx_page(rx_ring, rx_buffer); } else { @@ -2303,6 +2312,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, union ixgbe_adv_rx_desc *rx_desc; struct ixgbe_rx_buffer *rx_buffer; struct sk_buff *skb; + int rx_buffer_pgcnt; unsigned int size; /* return some buffers to hardware, one at a time is too slow */ @@ -2322,7 +2332,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, */ dma_rmb(); - rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size); + rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size, &rx_buffer_pgcnt); /* retrieve a buffer from the ring */ if (!skb) { @@ -2367,7 +2377,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, break; } - ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb); + ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb, rx_buffer_pgcnt); cleaned_count++; /* place incomplete frames back on ring for completion */ diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 54b0bf574c05..4a9041ee1b39 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2287,6 +2287,7 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, dma_sync_single_for_cpu(dev->dev.parent, rx_desc->buf_phys_addr, len, dma_dir); + rx_desc->buf_phys_addr = 0; if (data_len > 0 && sinfo->nr_frags < MAX_SKB_FRAGS) { skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags]; @@ -2295,8 +2296,8 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, skb_frag_size_set(frag, data_len); __skb_frag_set_page(frag, page); sinfo->nr_frags++; - - rx_desc->buf_phys_addr = 0; + } else { + page_pool_put_full_page(rxq->page_pool, page, true); } *size -= len; } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index f6616c8933ca..cea886c5bcb5 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4426,6 +4426,7 @@ static int mvpp2_open(struct net_device *dev) if (!valid) { netdev_err(port->dev, "invalid configuration: no dt or link IRQ"); + err = -ENOENT; goto err_free_irq; } diff --git a/drivers/net/ethernet/marvell/prestera/Kconfig b/drivers/net/ethernet/marvell/prestera/Kconfig index b1fcc44f566a..b6f20e2034c6 100644 --- a/drivers/net/ethernet/marvell/prestera/Kconfig +++ b/drivers/net/ethernet/marvell/prestera/Kconfig @@ -6,6 +6,7 @@ config PRESTERA tristate "Marvell Prestera Switch ASICs support" depends on NET_SWITCHDEV && VLAN_8021Q + depends on BRIDGE || BRIDGE=n select NET_DEVLINK help This driver supports Marvell Prestera Switch ASICs family. diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 0f20e0788cce..da4b286d1337 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -318,8 +318,10 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) goto err_port_init; } - if (port->fp_id >= PRESTERA_MAC_ADDR_NUM_MAX) + if (port->fp_id >= PRESTERA_MAC_ADDR_NUM_MAX) { + err = -EINVAL; goto err_port_init; + } /* firmware requires that port's MAC address consist of the first * 5 bytes of the base MAC address diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index 1b97adae542e..be5677623455 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -676,7 +676,8 @@ static int prestera_pci_probe(struct pci_dev *pdev, if (err) return err; - if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(30))) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(30)); + if (err) { dev_err(&pdev->dev, "fail to set DMA mask\n"); goto err_dma_mask; } @@ -702,8 +703,10 @@ static int prestera_pci_probe(struct pci_dev *pdev, dev_info(fw->dev.dev, "Prestera FW is ready\n"); fw->wq = alloc_workqueue("prestera_fw_wq", WQ_HIGHPRI, 1); - if (!fw->wq) + if (!fw->wq) { + err = -ENOMEM; goto err_wq_alloc; + } INIT_WORK(&fw->evt_work, prestera_fw_evt_work_fn); diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index 13250553263b..a8641a407c06 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -966,6 +966,7 @@ static int mtk_star_enable(struct net_device *ndev) mtk_star_adjust_link, 0, priv->phy_intf); if (!priv->phydev) { netdev_err(ndev, "failed to connect to PHY\n"); + ret = -ENODEV; goto err_free_irq; } @@ -1053,7 +1054,7 @@ static int mtk_star_netdev_start_xmit(struct sk_buff *skb, err_drop_packet: dev_kfree_skb(skb); ndev->stats.tx_dropped++; - return NETDEV_TX_BUSY; + return NETDEV_TX_OK; } /* Returns the number of bytes sent or a negative number on the first diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 106513f772c3..6f290319b617 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1378,8 +1378,10 @@ static void mlx4_en_tx_timeout(struct net_device *dev, unsigned int txqueue) tx_ring->cons, tx_ring->prod); priv->port_stats.tx_timeout++; - en_dbg(DRV, priv, "Scheduling watchdog\n"); - queue_work(mdev->workqueue, &priv->watchdog_task); + if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) { + en_dbg(DRV, priv, "Scheduling port restart\n"); + queue_work(mdev->workqueue, &priv->restart_task); + } } @@ -1733,6 +1735,7 @@ int mlx4_en_start_port(struct net_device *dev) mlx4_en_deactivate_cq(priv, cq); goto tx_err; } + clear_bit(MLX4_EN_TX_RING_STATE_RECOVERING, &tx_ring->state); if (t != TX_XDP) { tx_ring->tx_queue = netdev_get_tx_queue(dev, i); tx_ring->recycle_ring = NULL; @@ -1829,6 +1832,7 @@ int mlx4_en_start_port(struct net_device *dev) local_bh_enable(); } + clear_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state); netif_tx_start_all_queues(dev); netif_device_attach(dev); @@ -1999,7 +2003,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach) static void mlx4_en_restart(struct work_struct *work) { struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, - watchdog_task); + restart_task); struct mlx4_en_dev *mdev = priv->mdev; struct net_device *dev = priv->dev; @@ -2377,7 +2381,7 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) if (netif_running(dev)) { mutex_lock(&mdev->state_lock); if (!mdev->device_up) { - /* NIC is probably restarting - let watchdog task reset + /* NIC is probably restarting - let restart task reset * the port */ en_dbg(DRV, priv, "Change MTU called with card down!?\n"); } else { @@ -2386,7 +2390,9 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) if (err) { en_err(priv, "Failed restarting port:%d\n", priv->port); - queue_work(mdev->workqueue, &priv->watchdog_task); + if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, + &priv->state)) + queue_work(mdev->workqueue, &priv->restart_task); } } mutex_unlock(&mdev->state_lock); @@ -2792,7 +2798,8 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) if (err) { en_err(priv, "Failed starting port %d for XDP change\n", priv->port); - queue_work(mdev->workqueue, &priv->watchdog_task); + if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) + queue_work(mdev->workqueue, &priv->restart_task); } } @@ -3165,7 +3172,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv->counter_index = MLX4_SINK_COUNTER_INDEX(mdev->dev); spin_lock_init(&priv->stats_lock); INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode); - INIT_WORK(&priv->watchdog_task, mlx4_en_restart); + INIT_WORK(&priv->restart_task, mlx4_en_restart); INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate); INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats); INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 3ddb7268e415..59b097cda327 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -392,6 +392,35 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring) return cnt; } +static void mlx4_en_handle_err_cqe(struct mlx4_en_priv *priv, struct mlx4_err_cqe *err_cqe, + u16 cqe_index, struct mlx4_en_tx_ring *ring) +{ + struct mlx4_en_dev *mdev = priv->mdev; + struct mlx4_en_tx_info *tx_info; + struct mlx4_en_tx_desc *tx_desc; + u16 wqe_index; + int desc_size; + + en_err(priv, "CQE error - cqn 0x%x, ci 0x%x, vendor syndrome: 0x%x syndrome: 0x%x\n", + ring->sp_cqn, cqe_index, err_cqe->vendor_err_syndrome, err_cqe->syndrome); + print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, err_cqe, sizeof(*err_cqe), + false); + + wqe_index = be16_to_cpu(err_cqe->wqe_index) & ring->size_mask; + tx_info = &ring->tx_info[wqe_index]; + desc_size = tx_info->nr_txbb << LOG_TXBB_SIZE; + en_err(priv, "Related WQE - qpn 0x%x, wqe index 0x%x, wqe size 0x%x\n", ring->qpn, + wqe_index, desc_size); + tx_desc = ring->buf + (wqe_index << LOG_TXBB_SIZE); + print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, tx_desc, desc_size, false); + + if (test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) + return; + + en_err(priv, "Scheduling port restart\n"); + queue_work(mdev->workqueue, &priv->restart_task); +} + int mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int napi_budget) { @@ -438,13 +467,10 @@ int mlx4_en_process_tx_cq(struct net_device *dev, dma_rmb(); if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == - MLX4_CQE_OPCODE_ERROR)) { - struct mlx4_err_cqe *cqe_err = (struct mlx4_err_cqe *)cqe; - - en_err(priv, "CQE error - vendor syndrome: 0x%x syndrome: 0x%x\n", - cqe_err->vendor_err_syndrome, - cqe_err->syndrome); - } + MLX4_CQE_OPCODE_ERROR)) + if (!test_and_set_bit(MLX4_EN_TX_RING_STATE_RECOVERING, &ring->state)) + mlx4_en_handle_err_cqe(priv, (struct mlx4_err_cqe *)cqe, index, + ring); /* Skip over last polled CQE */ new_index = be16_to_cpu(cqe->wqe_index) & size_mask; diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index f6ff9620a137..f6cfec81ccc3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -1864,8 +1864,8 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) #define INIT_HCA_LOG_RD_OFFSET (INIT_HCA_QPC_OFFSET + 0x77) #define INIT_HCA_MCAST_OFFSET 0x0c0 #define INIT_HCA_MC_BASE_OFFSET (INIT_HCA_MCAST_OFFSET + 0x00) -#define INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x12) -#define INIT_HCA_LOG_MC_HASH_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x16) +#define INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x13) +#define INIT_HCA_LOG_MC_HASH_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x17) #define INIT_HCA_UC_STEERING_OFFSET (INIT_HCA_MCAST_OFFSET + 0x18) #define INIT_HCA_LOG_MC_TABLE_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x1b) #define INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN 0x6 @@ -1873,7 +1873,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) #define INIT_HCA_DRIVER_VERSION_SZ 0x40 #define INIT_HCA_FS_PARAM_OFFSET 0x1d0 #define INIT_HCA_FS_BASE_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x00) -#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x12) +#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x13) #define INIT_HCA_FS_A0_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x18) #define INIT_HCA_FS_LOG_TABLE_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x1b) #define INIT_HCA_FS_ETH_BITS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x21) diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index 650ae08c71de..8f020f26ebf5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -182,8 +182,8 @@ struct mlx4_init_hca_param { u64 cmpt_base; u64 mtt_base; u64 global_caps; - u16 log_mc_entry_sz; - u16 log_mc_hash_sz; + u8 log_mc_entry_sz; + u8 log_mc_hash_sz; u16 hca_core_clock; /* Internal Clock Frequency (in MHz) */ u8 log_num_qps; u8 log_num_srqs; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index a46efe37cfa9..30378e4c90b5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -271,6 +271,10 @@ struct mlx4_en_page_cache { } buf[MLX4_EN_CACHE_SIZE]; }; +enum { + MLX4_EN_TX_RING_STATE_RECOVERING, +}; + struct mlx4_en_priv; struct mlx4_en_tx_ring { @@ -317,6 +321,7 @@ struct mlx4_en_tx_ring { * Only queue_stopped might be used if BQL is not properly working. */ unsigned long queue_stopped; + unsigned long state; struct mlx4_hwq_resources sp_wqres; struct mlx4_qp sp_qp; struct mlx4_qp_context sp_context; @@ -530,6 +535,10 @@ struct mlx4_en_stats_bitmap { struct mutex mutex; /* for mutual access to stats bitmap */ }; +enum { + MLX4_EN_STATE_FLAG_RESTARTING, +}; + struct mlx4_en_priv { struct mlx4_en_dev *mdev; struct mlx4_en_port_profile *prof; @@ -595,7 +604,7 @@ struct mlx4_en_priv { struct mlx4_en_cq *rx_cq[MAX_RX_RINGS]; struct mlx4_qp drop_qp; struct work_struct rx_mode_task; - struct work_struct watchdog_task; + struct work_struct restart_task; struct work_struct linkstate_task; struct delayed_work stats_task; struct delayed_work service_task; @@ -641,6 +650,7 @@ struct mlx4_en_priv { u32 pflags; u8 rss_key[MLX4_EN_RSS_KEY_SIZE]; u8 rss_hash_fn; + unsigned long state; }; enum mlx4_en_wol { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 99f1ec3b2575..3e371d24c462 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -198,6 +198,7 @@ config MLX5_EN_TLS config MLX5_SW_STEERING bool "Mellanox Technologies software-managed steering" depends on MLX5_CORE_EN && MLX5_ESWITCH + select CRC32 default y help Build support for software-managed steering in the NIC. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c index 3e44e4d820c5..95f2b26a3ee3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c @@ -187,7 +187,7 @@ static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev) struct mlx5e_priv *priv; /* A given netdev is not a representor or not a slave of LAG configuration */ - if (!mlx5e_eswitch_rep(netdev) || !bond_slave_get_rtnl(netdev)) + if (!mlx5e_eswitch_rep(netdev) || !netif_is_lag_port(netdev)) return false; priv = netdev_priv(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index e36e505d38ad..d29af7b9c695 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -107,12 +107,16 @@ void mlx5e_rep_update_flows(struct mlx5e_priv *priv, mlx5e_tc_encap_flows_del(priv, e, &flow_list); if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) { + struct net_device *route_dev; + ether_addr_copy(e->h_dest, ha); ether_addr_copy(eth->h_dest, ha); /* Update the encap source mac, in case that we delete * the flows when encap source mac changed. */ - ether_addr_copy(eth->h_source, e->route_dev->dev_addr); + route_dev = __dev_get_by_index(dev_net(priv->netdev), e->route_dev_ifindex); + if (route_dev) + ether_addr_copy(eth->h_source, route_dev->dev_addr); mlx5e_tc_encap_flows_add(priv, e, &flow_list); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 7cce85faa16f..90930e54b6f2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -77,13 +77,13 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv, return 0; } -static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, - struct net_device *mirred_dev, - struct net_device **out_dev, - struct net_device **route_dev, - struct flowi4 *fl4, - struct neighbour **out_n, - u8 *out_ttl) +static int mlx5e_route_lookup_ipv4_get(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct net_device **out_dev, + struct net_device **route_dev, + struct flowi4 *fl4, + struct neighbour **out_n, + u8 *out_ttl) { struct neighbour *n; struct rtable *rt; @@ -117,18 +117,28 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, ip_rt_put(rt); return ret; } + dev_hold(*route_dev); if (!(*out_ttl)) *out_ttl = ip4_dst_hoplimit(&rt->dst); n = dst_neigh_lookup(&rt->dst, &fl4->daddr); ip_rt_put(rt); - if (!n) + if (!n) { + dev_put(*route_dev); return -ENOMEM; + } *out_n = n; return 0; } +static void mlx5e_route_lookup_ipv4_put(struct net_device *route_dev, + struct neighbour *n) +{ + neigh_release(n); + dev_put(route_dev); +} + static const char *mlx5e_netdev_kind(struct net_device *dev) { if (dev->rtnl_link_ops) @@ -193,8 +203,8 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, fl4.saddr = tun_key->u.ipv4.src; ttl = tun_key->ttl; - err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev, &route_dev, - &fl4, &n, &ttl); + err = mlx5e_route_lookup_ipv4_get(priv, mirred_dev, &out_dev, &route_dev, + &fl4, &n, &ttl); if (err) return err; @@ -223,7 +233,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; - e->route_dev = route_dev; + e->route_dev_ifindex = route_dev->ifindex; /* It's important to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the @@ -278,7 +288,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); - neigh_release(n); + mlx5e_route_lookup_ipv4_put(route_dev, n); return err; destroy_neigh_entry: @@ -286,18 +296,18 @@ destroy_neigh_entry: free_encap: kfree(encap_header); release_neigh: - neigh_release(n); + mlx5e_route_lookup_ipv4_put(route_dev, n); return err; } #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) -static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, - struct net_device *mirred_dev, - struct net_device **out_dev, - struct net_device **route_dev, - struct flowi6 *fl6, - struct neighbour **out_n, - u8 *out_ttl) +static int mlx5e_route_lookup_ipv6_get(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct net_device **out_dev, + struct net_device **route_dev, + struct flowi6 *fl6, + struct neighbour **out_n, + u8 *out_ttl) { struct dst_entry *dst; struct neighbour *n; @@ -318,15 +328,25 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, return ret; } + dev_hold(*route_dev); n = dst_neigh_lookup(dst, &fl6->daddr); dst_release(dst); - if (!n) + if (!n) { + dev_put(*route_dev); return -ENOMEM; + } *out_n = n; return 0; } +static void mlx5e_route_lookup_ipv6_put(struct net_device *route_dev, + struct neighbour *n) +{ + neigh_release(n); + dev_put(route_dev); +} + int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, struct net_device *mirred_dev, struct mlx5e_encap_entry *e) @@ -348,8 +368,8 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, fl6.daddr = tun_key->u.ipv6.dst; fl6.saddr = tun_key->u.ipv6.src; - err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev, &route_dev, - &fl6, &n, &ttl); + err = mlx5e_route_lookup_ipv6_get(priv, mirred_dev, &out_dev, &route_dev, + &fl6, &n, &ttl); if (err) return err; @@ -378,7 +398,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; - e->route_dev = route_dev; + e->route_dev_ifindex = route_dev->ifindex; /* It's importent to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the @@ -433,7 +453,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); - neigh_release(n); + mlx5e_route_lookup_ipv6_put(route_dev, n); return err; destroy_neigh_entry: @@ -441,7 +461,7 @@ destroy_neigh_entry: free_encap: kfree(encap_header); release_neigh: - neigh_release(n); + mlx5e_route_lookup_ipv6_put(route_dev, n); return err; } #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index 4e574ac73019..be3465ba38ca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -122,9 +122,9 @@ void mlx5e_activate_xsk(struct mlx5e_channel *c) set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); /* TX queue is created active. */ - spin_lock(&c->async_icosq_lock); + spin_lock_bh(&c->async_icosq_lock); mlx5e_trigger_irq(&c->async_icosq); - spin_unlock(&c->async_icosq_lock); + spin_unlock_bh(&c->async_icosq_lock); } void mlx5e_deactivate_xsk(struct mlx5e_channel *c) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index fb671a457129..8e96260fce1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -36,9 +36,9 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) if (test_and_set_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->async_icosq.state)) return 0; - spin_lock(&c->async_icosq_lock); + spin_lock_bh(&c->async_icosq_lock); mlx5e_trigger_irq(&c->async_icosq); - spin_unlock(&c->async_icosq_lock); + spin_unlock_bh(&c->async_icosq_lock); } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c index 97f1594cee11..e51f60b55daa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c @@ -44,6 +44,7 @@ static void accel_fs_tcp_set_ipv4_flow(struct mlx5_flow_spec *spec, struct sock outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4); } +#if IS_ENABLED(CONFIG_IPV6) static void accel_fs_tcp_set_ipv6_flow(struct mlx5_flow_spec *spec, struct sock *sk) { MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol); @@ -63,6 +64,7 @@ static void accel_fs_tcp_set_ipv6_flow(struct mlx5_flow_spec *spec, struct sock outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), 0xff, 16); } +#endif void mlx5e_accel_fs_del_sk(struct mlx5_flow_handle *rule) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 0e45590662a8..381a9c8c9da9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -64,13 +64,13 @@ static int rx_err_add_rule(struct mlx5e_priv *priv, if (!spec) return -ENOMEM; - /* Action to copy 7 bit ipsec_syndrome to regB[0:6] */ + /* Action to copy 7 bit ipsec_syndrome to regB[24:30] */ MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY); MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME); MLX5_SET(copy_action_in, action, src_offset, 0); MLX5_SET(copy_action_in, action, length, 7); MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); - MLX5_SET(copy_action_in, action, dst_offset, 0); + MLX5_SET(copy_action_in, action, dst_offset, 24); modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL, 1, action); @@ -488,13 +488,13 @@ static int rx_add_rule(struct mlx5e_priv *priv, setup_fte_common(attrs, ipsec_obj_id, spec, &flow_act); - /* Set 1 bit ipsec marker */ - /* Set 24 bit ipsec_obj_id */ + /* Set bit[31] ipsec marker */ + /* Set bit[23-0] ipsec_obj_id */ MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); - MLX5_SET(set_action_in, action, data, (ipsec_obj_id << 1) | 0x1); - MLX5_SET(set_action_in, action, offset, 7); - MLX5_SET(set_action_in, action, length, 25); + MLX5_SET(set_action_in, action, data, (ipsec_obj_id | BIT(31))); + MLX5_SET(set_action_in, action, offset, 0); + MLX5_SET(set_action_in, action, length, 32); modify_hdr = mlx5_modify_header_alloc(priv->mdev, MLX5_FLOW_NAMESPACE_KERNEL, 1, action); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 11e31a3db2be..a9b45606dbdb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -453,7 +453,6 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev, struct mlx5_cqe64 *cqe) { u32 ipsec_meta_data = be32_to_cpu(cqe->ft_metadata); - u8 ipsec_syndrome = ipsec_meta_data & 0xFF; struct mlx5e_priv *priv; struct xfrm_offload *xo; struct xfrm_state *xs; @@ -481,7 +480,7 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev, xo = xfrm_offload(skb); xo->flags = CRYPTO_DONE; - switch (ipsec_syndrome & MLX5_IPSEC_METADATA_SYNDROM_MASK) { + switch (MLX5_IPSEC_METADATA_SYNDROM(ipsec_meta_data)) { case MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED: xo->status = CRYPTO_SUCCESS; if (WARN_ON_ONCE(priv->ipsec->no_trailer)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index 056dacb612b0..9df9b9a8e09b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -39,9 +39,10 @@ #include "en.h" #include "en/txrx.h" -#define MLX5_IPSEC_METADATA_MARKER_MASK (0x80) -#define MLX5_IPSEC_METADATA_SYNDROM_MASK (0x7F) -#define MLX5_IPSEC_METADATA_HANDLE(metadata) (((metadata) >> 8) & 0xFF) +/* Bit31: IPsec marker, Bit30-24: IPsec syndrome, Bit23-0: IPsec obj id */ +#define MLX5_IPSEC_METADATA_MARKER(metadata) (((metadata) >> 31) & 0x1) +#define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(6, 0)) +#define MLX5_IPSEC_METADATA_HANDLE(metadata) ((metadata) & GENMASK(23, 0)) struct mlx5e_accel_tx_ipsec_state { struct xfrm_offload *xo; @@ -78,7 +79,7 @@ static inline unsigned int mlx5e_ipsec_tx_ids_len(struct mlx5e_accel_tx_ipsec_st static inline bool mlx5_ipsec_is_rx_flow(struct mlx5_cqe64 *cqe) { - return !!(MLX5_IPSEC_METADATA_MARKER_MASK & be32_to_cpu(cqe->ft_metadata)); + return MLX5_IPSEC_METADATA_MARKER(be32_to_cpu(cqe->ft_metadata)); } static inline bool mlx5e_ipsec_is_tx_flow(struct mlx5e_accel_tx_ipsec_state *ipsec_st) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index ccaccb9fc2f7..6a1d82503ef8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -188,7 +188,7 @@ static int post_rx_param_wqes(struct mlx5e_channel *c, err = 0; sq = &c->async_icosq; - spin_lock(&c->async_icosq_lock); + spin_lock_bh(&c->async_icosq_lock); cseg = post_static_params(sq, priv_rx); if (IS_ERR(cseg)) @@ -199,7 +199,7 @@ static int post_rx_param_wqes(struct mlx5e_channel *c, mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); unlock: - spin_unlock(&c->async_icosq_lock); + spin_unlock_bh(&c->async_icosq_lock); return err; @@ -265,10 +265,10 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1); - spin_lock(&sq->channel->async_icosq_lock); + spin_lock_bh(&sq->channel->async_icosq_lock); if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) { - spin_unlock(&sq->channel->async_icosq_lock); + spin_unlock_bh(&sq->channel->async_icosq_lock); err = -ENOSPC; goto err_dma_unmap; } @@ -299,7 +299,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, icosq_fill_wi(sq, pi, &wi); sq->pc++; mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); - spin_unlock(&sq->channel->async_icosq_lock); + spin_unlock_bh(&sq->channel->async_icosq_lock); return 0; @@ -360,7 +360,7 @@ static int resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_rx err = 0; sq = &c->async_icosq; - spin_lock(&c->async_icosq_lock); + spin_lock_bh(&c->async_icosq_lock); cseg = post_static_params(sq, priv_rx); if (IS_ERR(cseg)) { @@ -372,7 +372,7 @@ static int resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_rx mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); priv_rx->stats->tls_resync_res_ok++; unlock: - spin_unlock(&c->async_icosq_lock); + spin_unlock_bh(&c->async_icosq_lock); return err; } @@ -476,19 +476,22 @@ static void resync_update_sn(struct mlx5e_rq *rq, struct sk_buff *skb) depth += sizeof(struct tcphdr); - if (unlikely(!sk || sk->sk_state == TCP_TIME_WAIT)) + if (unlikely(!sk)) return; - if (unlikely(!resync_queue_get_psv(sk))) - return; + if (unlikely(sk->sk_state == TCP_TIME_WAIT)) + goto unref; - skb->sk = sk; - skb->destructor = sock_edemux; + if (unlikely(!resync_queue_get_psv(sk))) + goto unref; seq = th->seq; datalen = skb->len - depth; tls_offload_rx_resync_async_request_start(sk, seq, datalen); rq->stats->tls_resync_req_start++; + +unref: + sock_gen_put(sk); } void mlx5e_ktls_rx_resync(struct net_device *netdev, struct sock *sk, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b3f02aac7f26..ebce97921e03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5253,6 +5253,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) mlx5e_disable_async_events(priv); mlx5_lag_remove(mdev); + mlx5_vxlan_reset_to_default(mdev->vxlan); } int mlx5e_update_nic_rx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 9020d1419bcf..8932c387d46a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -186,7 +186,7 @@ struct mlx5e_encap_entry { unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ struct net_device *out_dev; - struct net_device *route_dev; + int route_dev_ifindex; struct mlx5e_tc_tunnel *tunnel; int reformat_type; u8 flags; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 599f5b5ebc97..6628a0197b4e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1584,7 +1584,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq))); out: - if (rq->xdp_prog) + if (rcu_access_pointer(rq->xdp_prog)) mlx5e_xdp_rx_poll_complete(rq); mlx5_cqwq_update_db_record(cqwq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index e3a968e9e2a0..ce710f22b1ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -4658,6 +4658,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, return flow; err_free: + dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts); mlx5e_flow_put(priv, flow); out: return ERR_PTR(err); @@ -4802,6 +4803,7 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv, return 0; err_free: + dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts); mlx5e_flow_put(priv, flow); out: return err; @@ -5227,8 +5229,10 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) tc->ct = mlx5_tc_ct_init(priv, tc->chains, &priv->fs.tc.mod_hdr, MLX5_FLOW_NAMESPACE_KERNEL); - if (IS_ERR(tc->ct)) + if (IS_ERR(tc->ct)) { + err = PTR_ERR(tc->ct); goto err_ct; + } tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event; err = register_netdevice_notifier_dev_net(priv->netdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 3b979008143d..4a2ce241522e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -283,6 +283,9 @@ static inline bool mlx5e_cqe_regb_chain(struct mlx5_cqe64 *cqe) reg_b = be32_to_cpu(cqe->ft_metadata); + if (reg_b >> (MLX5E_TC_TABLE_CHAIN_TAG_BITS + ZONE_RESTORE_BITS)) + return false; + chain = reg_b & MLX5E_TC_TABLE_CHAIN_TAG_MASK; if (chain) return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 82b4419af9d4..d97203cf6a00 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -144,7 +144,9 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs) memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz); } -/* RM 2311217: no L4 inner checksum for IPsec tunnel type packet */ +/* If packet is not IP's CHECKSUM_PARTIAL (e.g. icmd packet), + * need to set L3 checksum flag for IPsec + */ static void ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) @@ -154,19 +156,15 @@ ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM; sq->stats->csum_partial_inner++; } else { - eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial++; } } static inline void -mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) +mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5e_accel_tx_state *accel, + struct mlx5_wqe_eth_seg *eseg) { - if (unlikely(eseg->flow_table_metadata & cpu_to_be32(MLX5_ETH_WQE_FT_META_IPSEC))) { - ipsec_txwqe_build_eseg_csum(sq, skb, eseg); - return; - } - if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; if (skb->encapsulation) { @@ -177,6 +175,14 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial++; } +#ifdef CONFIG_MLX5_EN_TLS + } else if (unlikely(accel && accel->tls.tls_tisn)) { + eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM; + sq->stats->csum_partial++; +#endif + } else if (unlikely(eseg->flow_table_metadata & cpu_to_be32(MLX5_ETH_WQE_FT_META_IPSEC))) { + ipsec_txwqe_build_eseg_csum(sq, skb, eseg); + } else sq->stats->csum_none++; } @@ -608,12 +614,13 @@ void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq) } static bool mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq, - struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) + struct sk_buff *skb, struct mlx5e_accel_tx_state *accel, + struct mlx5_wqe_eth_seg *eseg) { if (unlikely(!mlx5e_accel_tx_eseg(priv, skb, eseg))) return false; - mlx5e_txwqe_build_eseg_csum(sq, skb, eseg); + mlx5e_txwqe_build_eseg_csum(sq, skb, accel, eseg); return true; } @@ -640,7 +647,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) if (mlx5e_tx_skb_supports_mpwqe(skb, &attr)) { struct mlx5_wqe_eth_seg eseg = {}; - if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &eseg))) + if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg))) return NETDEV_TX_OK; mlx5e_sq_xmit_mpwqe(sq, skb, &eseg, netdev_xmit_more()); @@ -657,7 +664,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) /* May update the WQE, but may not post other WQEs. */ mlx5e_accel_tx_finish(sq, wqe, &accel, (struct mlx5_wqe_inline_seg *)(wqe->data + wqe_attr.ds_cnt_inl)); - if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &wqe->eth))) + if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth))) return NETDEV_TX_OK; mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, netdev_xmit_more()); @@ -676,7 +683,7 @@ void mlx5e_sq_xmit_simple(struct mlx5e_txqsq *sq, struct sk_buff *skb, bool xmit mlx5e_sq_calc_wqe_attr(skb, &attr, &wqe_attr); pi = mlx5e_txqsq_get_next_pi(sq, wqe_attr.num_wqebbs); wqe = MLX5E_TX_FETCH_WQE(sq, pi); - mlx5e_txwqe_build_eseg_csum(sq, skb, &wqe->eth); + mlx5e_txwqe_build_eseg_csum(sq, skb, NULL, &wqe->eth); mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, xmit_more); } @@ -945,7 +952,7 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, mlx5i_txwqe_build_datagram(av, dqpn, dqkey, datagram); - mlx5e_txwqe_build_eseg_csum(sq, skb, eseg); + mlx5e_txwqe_build_eseg_csum(sq, skb, NULL, eseg); eseg->mss = attr.mss; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 6e6a9a563992..d4ee0a9c03db 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1142,6 +1142,10 @@ int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, struct mlx5_vport *vport; vport = mlx5_eswitch_get_vport(esw, vport_num); + + if (!vport->qos.enabled) + return -EOPNOTSUPP; + MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps); return mlx5_modify_scheduling_element_cmd(esw->dev, @@ -1408,6 +1412,7 @@ static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw) int i; mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) { + memset(&vport->qos, 0, sizeof(vport->qos)); memset(&vport->info, 0, sizeof(vport->info)); vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; } @@ -1902,8 +1907,6 @@ int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink, ether_addr_copy(hw_addr, vport->info.mac); *hw_addr_len = ETH_ALEN; err = 0; - } else { - NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled"); } mutex_unlock(&esw->state_lock); return err; @@ -2223,12 +2226,15 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw) max_guarantee = evport->info.min_rate; } - return max_t(u32, max_guarantee / fw_max_bw_share, 1); + if (max_guarantee) + return max_t(u32, max_guarantee / fw_max_bw_share, 1); + return 0; } -static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) +static int normalize_vports_min_rate(struct mlx5_eswitch *esw) { u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share); + u32 divider = calculate_vports_min_rate_divider(esw); struct mlx5_vport *evport; u32 vport_max_rate; u32 vport_min_rate; @@ -2241,9 +2247,9 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) continue; vport_min_rate = evport->info.min_rate; vport_max_rate = evport->info.max_rate; - bw_share = MLX5_MIN_BW_SHARE; + bw_share = 0; - if (vport_min_rate) + if (divider) bw_share = MLX5_RATE_TO_BW_SHARE(vport_min_rate, divider, fw_max_bw_share); @@ -2268,7 +2274,6 @@ int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport, struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); u32 fw_max_bw_share; u32 previous_min_rate; - u32 divider; bool min_rate_supported; bool max_rate_supported; int err = 0; @@ -2293,8 +2298,7 @@ int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport, previous_min_rate = evport->info.min_rate; evport->info.min_rate = min_rate; - divider = calculate_vports_min_rate_divider(esw); - err = normalize_vports_min_rate(esw, divider); + err = normalize_vports_min_rate(esw); if (err) { evport->info.min_rate = previous_min_rate; goto unlock; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 16091838bfcf..9fdd99272e31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -534,6 +534,13 @@ static void del_sw_hw_rule(struct fs_node *node) goto out; } + if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_PORT && + --fte->dests_size) { + fte->modify_mask |= BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION); + fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_ALLOW; + goto out; + } + if ((fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) && --fte->dests_size) { fte->modify_mask |= @@ -2010,10 +2017,11 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle) down_write_ref_node(&fte->node, false); for (i = handle->num_rules - 1; i >= 0; i--) tree_remove_node(&handle->rule[i]->node, true); - if (fte->modify_mask && fte->dests_size) { - modify_fte(fte); + if (fte->dests_size) { + if (fte->modify_mask) + modify_fte(fte); up_write_ref_node(&fte->node, false); - } else { + } else if (list_empty(&fte->node.children)) { del_hw_fte(&fte->node); /* Avoid double call to del_hw_fte */ fte->node.del_hw_func = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c index 3315afe2f8dc..38084400ee8f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c @@ -168,6 +168,17 @@ struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev) void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { + if (!mlx5_vxlan_allowed(vxlan)) + return; + + mlx5_vxlan_del_port(vxlan, IANA_VXLAN_UDP_PORT); + WARN_ON(!hash_empty(vxlan->htable)); + + kfree(vxlan); +} + +void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan) +{ struct mlx5_vxlan_port *vxlanp; struct hlist_node *tmp; int bkt; @@ -175,12 +186,12 @@ void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) if (!mlx5_vxlan_allowed(vxlan)) return; - /* Lockless since we are the only hash table consumers*/ hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) { - hash_del(&vxlanp->hlist); - mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port); - kfree(vxlanp); + /* Don't delete default UDP port added by the HW. + * Remove only user configured ports + */ + if (vxlanp->udp_port == IANA_VXLAN_UDP_PORT) + continue; + mlx5_vxlan_del_port(vxlan, vxlanp->udp_port); } - - kfree(vxlan); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h index ec766529f49b..34ef662da35e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h @@ -56,6 +56,7 @@ void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan); int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port); int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port); bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port); +void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan); #else static inline struct mlx5_vxlan* mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-EOPNOTSUPP); } @@ -63,6 +64,7 @@ static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; } static inline int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; } static inline int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; } static inline bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) { return false; } +static inline void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan) { return; } #endif #endif /* __MLX5_VXLAN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 150638814517..4d7f8a357df7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -422,6 +422,24 @@ static void release_all_pages(struct mlx5_core_dev *dev, u32 func_id, npages, ec_function, func_id); } +static u32 fwp_fill_manage_pages_out(struct fw_page *fwp, u32 *out, u32 index, + u32 npages) +{ + u32 pages_set = 0; + unsigned int n; + + for_each_clear_bit(n, &fwp->bitmask, MLX5_NUM_4K_IN_PAGE) { + MLX5_ARRAY_SET64(manage_pages_out, out, pas, index + pages_set, + fwp->addr + (n * MLX5_ADAPTER_PAGE_SIZE)); + pages_set++; + + if (!--npages) + break; + } + + return pages_set; +} + static int reclaim_pages_cmd(struct mlx5_core_dev *dev, u32 *in, int in_size, u32 *out, int out_size) { @@ -448,8 +466,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, fwp = rb_entry(p, struct fw_page, rb_node); p = rb_next(p); - MLX5_ARRAY_SET64(manage_pages_out, out, pas, i, fwp->addr); - i++; + i += fwp_fill_manage_pages_out(fwp, out, i, npages - i); } MLX5_SET(manage_pages_out, out, output_num_entries, i); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 6bd34b293007..51bbd88ff021 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -92,6 +92,7 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, caps->eswitch_manager = MLX5_CAP_GEN(mdev, eswitch_manager); caps->gvmi = MLX5_CAP_GEN(mdev, vhca_id); caps->flex_protocols = MLX5_CAP_GEN(mdev, flex_parser_protocols); + caps->sw_format_ver = MLX5_CAP_GEN(mdev, steering_format_version); if (mlx5dr_matcher_supp_flex_parser_icmp_v4(caps)) { caps->flex_parser_id_icmp_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 890767a2a7cb..aa2c2d6c44e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -223,6 +223,11 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, if (ret) return ret; + if (dmn->info.caps.sw_format_ver != MLX5_STEERING_FORMAT_CONNECTX_5) { + mlx5dr_err(dmn, "SW steering is not supported on this device\n"); + return -EOPNOTSUPP; + } + ret = dr_domain_query_fdb_caps(mdev, dmn); if (ret) return ret; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index f50f3b107aa3..cf62ea4f882e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -625,6 +625,7 @@ struct mlx5dr_cmd_caps { u8 max_ft_level; u16 roce_min_src_udp; u8 num_esw_ports; + u8 sw_format_ver; bool eswitch_manager; bool rx_sw_owner; bool tx_sw_owner; diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index 872e9910bb7c..a619d90559f7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -6,6 +6,7 @@ config MLXSW_CORE tristate "Mellanox Technologies Switch ASICs support" select NET_DEVLINK + select MLXFW help This driver supports Mellanox Technologies Switch ASICs family. @@ -82,7 +83,6 @@ config MLXSW_SPECTRUM select GENERIC_ALLOCATOR select PARMAN select OBJAGG - select MLXFW imply PTP_1588_CLOCK select NET_PTP_CLASSIFY if PTP_1588_CLOCK default m diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 937b8e46f8c7..1a86535c4968 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -571,7 +571,8 @@ static void mlxsw_emad_trans_timeout_schedule(struct mlxsw_reg_trans *trans) if (trans->core->fw_flash_in_progress) timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS); - queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, timeout); + queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, + timeout << trans->retries); } static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core, diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig index 31f9a82dc113..d0f6dfe0dcf3 100644 --- a/drivers/net/ethernet/microchip/Kconfig +++ b/drivers/net/ethernet/microchip/Kconfig @@ -47,6 +47,7 @@ config LAN743X depends on PCI select PHYLIB select CRC16 + select CRC32 help Support for the Microchip LAN743x PCI Express Gigabit Ethernet chip diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index a1938842f828..b319c22c211c 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -148,7 +148,8 @@ static void lan743x_intr_software_isr(void *context) int_sts = lan743x_csr_read(adapter, INT_STS); if (int_sts & INT_BIT_SW_GP_) { - lan743x_csr_write(adapter, INT_STS, INT_BIT_SW_GP_); + /* disable the interrupt to prevent repeated re-triggering */ + lan743x_csr_write(adapter, INT_EN_CLR, INT_BIT_SW_GP_); intr->software_isr_flag = 1; } } @@ -674,14 +675,12 @@ clean_up: static int lan743x_dp_write(struct lan743x_adapter *adapter, u32 select, u32 addr, u32 length, u32 *buf) { - int ret = -EIO; u32 dp_sel; int i; - mutex_lock(&adapter->dp_lock); if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_, 1, 40, 100, 100)) - goto unlock; + return -EIO; dp_sel = lan743x_csr_read(adapter, DP_SEL); dp_sel &= ~DP_SEL_MASK_; dp_sel |= select; @@ -693,13 +692,10 @@ static int lan743x_dp_write(struct lan743x_adapter *adapter, lan743x_csr_write(adapter, DP_CMD, DP_CMD_WRITE_); if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_, 1, 40, 100, 100)) - goto unlock; + return -EIO; } - ret = 0; -unlock: - mutex_unlock(&adapter->dp_lock); - return ret; + return 0; } static u32 lan743x_mac_mii_access(u16 id, u16 index, int read) @@ -1019,16 +1015,16 @@ static void lan743x_phy_close(struct lan743x_adapter *adapter) static int lan743x_phy_open(struct lan743x_adapter *adapter) { struct lan743x_phy *phy = &adapter->phy; + struct phy_device *phydev = NULL; struct device_node *phynode; - struct phy_device *phydev; struct net_device *netdev; int ret = -EIO; netdev = adapter->netdev; phynode = of_node_get(adapter->pdev->dev.of_node); - adapter->phy_mode = PHY_INTERFACE_MODE_GMII; if (phynode) { + /* try devicetree phy, or fixed link */ of_get_phy_mode(phynode, &adapter->phy_mode); if (of_phy_is_fixed_link(phynode)) { @@ -1044,13 +1040,15 @@ static int lan743x_phy_open(struct lan743x_adapter *adapter) lan743x_phy_link_status_change, 0, adapter->phy_mode); of_node_put(phynode); - if (!phydev) - goto return_error; - } else { + } + + if (!phydev) { + /* try internal phy */ phydev = phy_find_first(adapter->mdiobus); if (!phydev) goto return_error; + adapter->phy_mode = PHY_INTERFACE_MODE_GMII; ret = phy_connect_direct(netdev, phydev, lan743x_phy_link_status_change, adapter->phy_mode); @@ -1310,13 +1308,13 @@ clean_up_data_descriptor: goto clear_active; if (!(buffer_info->flags & TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED)) { - dev_kfree_skb(buffer_info->skb); + dev_kfree_skb_any(buffer_info->skb); goto clear_skb; } if (cleanup) { lan743x_ptp_unrequest_tx_timestamp(tx->adapter); - dev_kfree_skb(buffer_info->skb); + dev_kfree_skb_any(buffer_info->skb); } else { ignore_sync = (buffer_info->flags & TX_BUFFER_INFO_FLAG_IGNORE_SYNC) != 0; @@ -1626,7 +1624,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx, if (required_number_of_descriptors > lan743x_tx_get_avail_desc(tx)) { if (required_number_of_descriptors > (tx->ring_size - 1)) { - dev_kfree_skb(skb); + dev_kfree_skb_irq(skb); } else { /* save to overflow buffer */ tx->overflow_skb = skb; @@ -1659,7 +1657,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx, start_frame_length, do_timestamp, skb->ip_summed == CHECKSUM_PARTIAL)) { - dev_kfree_skb(skb); + dev_kfree_skb_irq(skb); goto unlock; } @@ -1678,7 +1676,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx, * frame assembler clean up was performed inside * lan743x_tx_frame_add_fragment */ - dev_kfree_skb(skb); + dev_kfree_skb_irq(skb); goto unlock; } } @@ -2733,7 +2731,6 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, adapter->intr.irq = adapter->pdev->irq; lan743x_csr_write(adapter, INT_EN_CLR, 0xFFFFFFFF); - mutex_init(&adapter->dp_lock); ret = lan743x_gpio_init(adapter); if (ret) diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index c61a40411317..a536f4a4994d 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -712,9 +712,6 @@ struct lan743x_adapter { struct lan743x_csr csr; struct lan743x_intr intr; - /* lock, used to prevent concurrent access to data port */ - struct mutex dp_lock; - struct lan743x_gpio gpio; struct lan743x_ptp ptp; diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 70bf8c67d7ef..a53bd36b11c6 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1489,10 +1489,11 @@ int ocelot_init(struct ocelot *ocelot) SYS_FRM_AGING_MAX_AGE(307692), SYS_FRM_AGING); /* Setup flooding PGIDs */ - ocelot_write_rix(ocelot, ANA_FLOODING_FLD_MULTICAST(PGID_MC) | - ANA_FLOODING_FLD_BROADCAST(PGID_MC) | - ANA_FLOODING_FLD_UNICAST(PGID_UC), - ANA_FLOODING, 0); + for (i = 0; i < ocelot->num_flooding_pgids; i++) + ocelot_write_rix(ocelot, ANA_FLOODING_FLD_MULTICAST(PGID_MC) | + ANA_FLOODING_FLD_BROADCAST(PGID_MC) | + ANA_FLOODING_FLD_UNICAST(PGID_UC), + ANA_FLOODING, i); ocelot_write(ocelot, ANA_FLOODING_IPMC_FLD_MC6_DATA(PGID_MCIPV6) | ANA_FLOODING_IPMC_FLD_MC6_CTRL(PGID_MC) | ANA_FLOODING_IPMC_FLD_MC4_DATA(PGID_MCIPV4) | diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index dc00772950e5..1e7729421a82 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -1254,6 +1254,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev) } ocelot->num_phys_ports = of_get_child_count(ports); + ocelot->num_flooding_pgids = 1; ocelot->vcap = vsc7514_vcap_props; ocelot->inj_prefix = OCELOT_TAG_PREFIX_NONE; diff --git a/drivers/net/ethernet/netronome/Kconfig b/drivers/net/ethernet/netronome/Kconfig index d8b99d6a0356..b82758d5beed 100644 --- a/drivers/net/ethernet/netronome/Kconfig +++ b/drivers/net/ethernet/netronome/Kconfig @@ -22,6 +22,7 @@ config NFP depends on VXLAN || VXLAN=n depends on TLS && TLS_DEVICE || TLS_DEVICE=n select NET_DEVLINK + select CRC32 help This driver supports the Netronome(R) NFP4000/NFP6000 based cards working as a advanced Ethernet NIC. It works with both diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index b150da43adb2..437226866ce8 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3562,9 +3562,6 @@ static int nfp_net_xdp_setup_drv(struct nfp_net *nn, struct netdev_bpf *bpf) struct nfp_net_dp *dp; int err; - if (!xdp_attachment_flags_ok(&nn->xdp, bpf)) - return -EBUSY; - if (!prog == !nn->dp.xdp_prog) { WRITE_ONCE(nn->dp.xdp_prog, prog); xdp_attachment_setup(&nn->xdp, bpf); @@ -3593,9 +3590,6 @@ static int nfp_net_xdp_setup_hw(struct nfp_net *nn, struct netdev_bpf *bpf) { int err; - if (!xdp_attachment_flags_ok(&nn->xdp_hw, bpf)) - return -EBUSY; - err = nfp_app_xdp_offload(nn->app, nn, bpf->prog, bpf->extack); if (err) return err; diff --git a/drivers/net/ethernet/nxp/Kconfig b/drivers/net/ethernet/nxp/Kconfig index ee83a71c2509..c84997db828c 100644 --- a/drivers/net/ethernet/nxp/Kconfig +++ b/drivers/net/ethernet/nxp/Kconfig @@ -3,6 +3,7 @@ config LPC_ENET tristate "NXP ethernet MAC on LPC devices" depends on ARCH_LPC32XX || COMPILE_TEST select PHYLIB + select CRC32 help Say Y or M here if you want to use the NXP ethernet MAC included on some NXP LPC devices. You can safely enable this option for LPC32xx diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c index be6660128b55..040a15a828b4 100644 --- a/drivers/net/ethernet/pasemi/pasemi_mac.c +++ b/drivers/net/ethernet/pasemi/pasemi_mac.c @@ -1078,16 +1078,20 @@ static int pasemi_mac_open(struct net_device *dev) mac->tx = pasemi_mac_setup_tx_resources(dev); - if (!mac->tx) + if (!mac->tx) { + ret = -ENOMEM; goto out_tx_ring; + } /* We might already have allocated rings in case mtu was changed * before interface was brought up. */ if (dev->mtu > 1500 && !mac->num_cs) { pasemi_mac_setup_csrings(mac); - if (!mac->num_cs) + if (!mac->num_cs) { + ret = -ENOMEM; goto out_tx_ring; + } } /* Zero out rmon counters */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 0e4cd8890cff..0a22f8ce9a2c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -1647,9 +1647,9 @@ static void qed_src_init_pf(struct qed_hwfn *p_hwfn) ilog2(rounded_conn_num)); STORE_RT_REG_AGG(p_hwfn, SRC_REG_FIRSTFREE_RT_OFFSET, - p_hwfn->p_cxt_mngr->first_free); + p_hwfn->p_cxt_mngr->src_t2.first_free); STORE_RT_REG_AGG(p_hwfn, SRC_REG_LASTFREE_RT_OFFSET, - p_hwfn->p_cxt_mngr->last_free); + p_hwfn->p_cxt_mngr->src_t2.last_free); } /* Timers PF */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h index 8b64495f8745..056e79620a0e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h @@ -326,9 +326,6 @@ struct qed_cxt_mngr { /* SRC T2 */ struct qed_src_t2 src_t2; - u32 t2_num_pages; - u64 first_free; - u64 last_free; /* total number of SRQ's for this hwfn */ u32 srq_count; diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index 512cbef24097..a99861124630 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -2754,14 +2754,18 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, iwarp_info->partial_fpdus = kcalloc((u16)p_hwfn->p_rdma_info->num_qps, sizeof(*iwarp_info->partial_fpdus), GFP_KERNEL); - if (!iwarp_info->partial_fpdus) + if (!iwarp_info->partial_fpdus) { + rc = -ENOMEM; goto err; + } iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps; iwarp_info->mpa_intermediate_buf = kzalloc(buff_size, GFP_KERNEL); - if (!iwarp_info->mpa_intermediate_buf) + if (!iwarp_info->mpa_intermediate_buf) { + rc = -ENOMEM; goto err; + } /* The mpa_bufs array serves for pending RX packets received on the * mpa ll2 that don't have place on the tx ring and require later @@ -2771,8 +2775,10 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, iwarp_info->mpa_bufs = kcalloc(data.input.rx_num_desc, sizeof(*iwarp_info->mpa_bufs), GFP_KERNEL); - if (!iwarp_info->mpa_bufs) + if (!iwarp_info->mpa_bufs) { + rc = -ENOMEM; goto err; + } INIT_LIST_HEAD(&iwarp_info->mpa_buf_pending_list); INIT_LIST_HEAD(&iwarp_info->mpa_buf_list); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index b8af59fc1aa4..d2c190732d3e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -2231,7 +2231,8 @@ static int qlcnic_83xx_restart_hw(struct qlcnic_adapter *adapter) /* Boot either flash image or firmware image from host file system */ if (qlcnic_load_fw_file == 1) { - if (qlcnic_83xx_load_fw_image_from_host(adapter)) + err = qlcnic_83xx_load_fw_image_from_host(adapter); + if (err) return err; } else { QLC_SHARED_REG_WR32(adapter, QLCNIC_FW_IMG_VALID, diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 29a7bfa2584d..3d7d3ab383f8 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -188,6 +188,11 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) dev = skb->dev; port = rmnet_get_port_rcu(dev); + if (unlikely(!port)) { + atomic_long_inc(&skb->dev->rx_nohandler); + kfree_skb(skb); + goto done; + } switch (port->rmnet_mode) { case RMNET_EPMODE_VND: diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 7766d73823eb..85d9c3e30c69 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4163,7 +4163,8 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp, opts[1] |= transport_offset << TCPHO_SHIFT; } else { if (unlikely(skb->len < ETH_ZLEN && rtl_test_hw_pad_bug(tp))) - return !eth_skb_pad(skb); + /* eth_skb_pad would free the skb on error */ + return !__skb_put_padto(skb, ETH_ZLEN, false); } return true; @@ -4342,18 +4343,9 @@ static netdev_features_t rtl8169_features_check(struct sk_buff *skb, rtl_chip_supports_csum_v2(tp)) features &= ~NETIF_F_ALL_TSO; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { - if (skb->len < ETH_ZLEN) { - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_11: - case RTL_GIGA_MAC_VER_12: - case RTL_GIGA_MAC_VER_17: - case RTL_GIGA_MAC_VER_34: - features &= ~NETIF_F_CSUM_MASK; - break; - default: - break; - } - } + /* work around hw bug on some chip versions */ + if (skb->len < ETH_ZLEN) + features &= ~NETIF_F_CSUM_MASK; if (transport_offset > TCPHO_MAX && rtl_chip_supports_csum_v2(tp)) diff --git a/drivers/net/ethernet/rocker/Kconfig b/drivers/net/ethernet/rocker/Kconfig index 99e1290e0307..2318811ff75a 100644 --- a/drivers/net/ethernet/rocker/Kconfig +++ b/drivers/net/ethernet/rocker/Kconfig @@ -19,6 +19,7 @@ if NET_VENDOR_ROCKER config ROCKER tristate "Rocker switch driver (EXPERIMENTAL)" depends on PCI && NET_SWITCHDEV && BRIDGE + select CRC32 help This driver supports Rocker switch device. diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index efef5476a577..223f69da7e95 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -246,13 +246,7 @@ static int imx_dwmac_probe(struct platform_device *pdev) goto err_parse_dt; } - ret = dma_set_mask_and_coherent(&pdev->dev, - DMA_BIT_MASK(dwmac->ops->addr_width)); - if (ret) { - dev_err(&pdev->dev, "DMA mask set failed\n"); - goto err_dma_mask; - } - + plat_dat->addr64 = dwmac->ops->addr_width; plat_dat->init = imx_dwmac_init; plat_dat->exit = imx_dwmac_exit; plat_dat->fix_mac_speed = imx_dwmac_fix_speed; @@ -272,7 +266,6 @@ static int imx_dwmac_probe(struct platform_device *pdev) err_dwmac_init: err_drv_probe: imx_dwmac_exit(pdev, plat_dat->bsp_priv); -err_dma_mask: err_parse_dt: err_match_data: stmmac_remove_config_dt(pdev, plat_dat); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c index f61cb997a8f6..82b1c7a5a7a9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c @@ -113,8 +113,10 @@ static int intel_eth_plat_probe(struct platform_device *pdev) /* Enable TX clock */ if (dwmac->data->tx_clk_en) { dwmac->tx_clk = devm_clk_get(&pdev->dev, "tx_clk"); - if (IS_ERR(dwmac->tx_clk)) + if (IS_ERR(dwmac->tx_clk)) { + ret = PTR_ERR(dwmac->tx_clk); goto err_remove_config_dt; + } clk_prepare_enable(dwmac->tx_clk); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 5afcf05bbf9c..6d6bd77bb6af 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -30,7 +30,6 @@ #define PRG_ETH0_EXT_RMII_MODE 4 /* mux to choose between fclk_div2 (bit unset) and mpll2 (bit set) */ -#define PRG_ETH0_CLK_M250_SEL_SHIFT 4 #define PRG_ETH0_CLK_M250_SEL_MASK GENMASK(4, 4) /* TX clock delay in ns = "8ns / 4 * tx_dly_val" (where 8ns are exactly one @@ -155,8 +154,9 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) return -ENOMEM; clk_configs->m250_mux.reg = dwmac->regs + PRG_ETH0; - clk_configs->m250_mux.shift = PRG_ETH0_CLK_M250_SEL_SHIFT; - clk_configs->m250_mux.mask = PRG_ETH0_CLK_M250_SEL_MASK; + clk_configs->m250_mux.shift = __ffs(PRG_ETH0_CLK_M250_SEL_MASK); + clk_configs->m250_mux.mask = PRG_ETH0_CLK_M250_SEL_MASK >> + clk_configs->m250_mux.shift; clk = meson8b_dwmac_register_clk(dwmac, "m250_sel", mux_parents, ARRAY_SIZE(mux_parents), &clk_mux_ops, &clk_configs->m250_mux.hw); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 002791b77356..ced6d76a0d85 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -1171,7 +1171,6 @@ const struct stmmac_ops dwmac4_ops = { .pcs_get_adv_lp = dwmac4_get_adv_lp, .debug = dwmac4_debug, .set_filter = dwmac4_set_filter, - .flex_pps_config = dwmac5_flex_pps_config, .set_mac_loopback = dwmac4_set_mac_loopback, .update_vlan_hash = dwmac4_update_vlan_hash, .sarc_configure = dwmac4_sarc_configure, @@ -1213,6 +1212,7 @@ const struct stmmac_ops dwmac410_ops = { .pcs_get_adv_lp = dwmac4_get_adv_lp, .debug = dwmac4_debug, .set_filter = dwmac4_set_filter, + .flex_pps_config = dwmac5_flex_pps_config, .set_mac_loopback = dwmac4_set_mac_loopback, .update_vlan_hash = dwmac4_update_vlan_hash, .sarc_configure = dwmac4_sarc_configure, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index 6e30d7eb4983..0b4ee2dbb691 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -22,7 +22,7 @@ int dwmac4_dma_reset(void __iomem *ioaddr) return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value, !(value & DMA_BUS_MODE_SFT_RESET), - 10000, 100000); + 10000, 1000000); } void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index cb87d31a99df..57a53a600aa5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -23,7 +23,7 @@ int dwmac_dma_reset(void __iomem *ioaddr) return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value, !(value & DMA_BUS_MODE_SFT_RESET), - 10000, 100000); + 10000, 200000); } /* CSR1 enables the transmit DMA to check for new descriptor */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ab54ce3094ac..b92dfa932737 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1534,6 +1534,19 @@ static void dma_free_tx_skbufs(struct stmmac_priv *priv, u32 queue) } /** + * stmmac_free_tx_skbufs - free TX skb buffers + * @priv: private structure + */ +static void stmmac_free_tx_skbufs(struct stmmac_priv *priv) +{ + u32 tx_queue_cnt = priv->plat->tx_queues_to_use; + u32 queue; + + for (queue = 0; queue < tx_queue_cnt; queue++) + dma_free_tx_skbufs(priv, queue); +} + +/** * free_dma_rx_desc_resources - free RX dma desc resources * @priv: private structure */ @@ -2898,9 +2911,6 @@ static int stmmac_release(struct net_device *dev) struct stmmac_priv *priv = netdev_priv(dev); u32 chan; - if (priv->eee_enabled) - del_timer_sync(&priv->eee_ctrl_timer); - if (device_may_wakeup(priv->device)) phylink_speed_down(priv->phylink, false); /* Stop and disconnect the PHY */ @@ -2919,6 +2929,11 @@ static int stmmac_release(struct net_device *dev) if (priv->lpi_irq > 0) free_irq(priv->lpi_irq, dev); + if (priv->eee_enabled) { + priv->tx_path_in_lpi_mode = false; + del_timer_sync(&priv->eee_ctrl_timer); + } + /* Stop TX/RX DMA and clear the descriptors */ stmmac_stop_all_dma(priv); @@ -4933,6 +4948,14 @@ int stmmac_dvr_probe(struct device *device, dev_info(priv->device, "SPH feature enabled\n"); } + /* The current IP register MAC_HW_Feature1[ADDR64] only define + * 32/40/64 bit width, but some SOC support others like i.MX8MP + * support 34 bits but it map to 40 bits width in MAC_HW_Feature1[ADDR64]. + * So overwrite dma_cap.addr64 according to HW real design. + */ + if (priv->plat->addr64) + priv->dma_cap.addr64 = priv->plat->addr64; + if (priv->dma_cap.addr64) { ret = dma_set_mask_and_coherent(device, DMA_BIT_MASK(priv->dma_cap.addr64)); @@ -5145,6 +5168,11 @@ int stmmac_suspend(struct device *dev) for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++) del_timer_sync(&priv->tx_queue[chan].txtimer); + if (priv->eee_enabled) { + priv->tx_path_in_lpi_mode = false; + del_timer_sync(&priv->eee_ctrl_timer); + } + /* Stop TX/RX DMA */ stmmac_stop_all_dma(priv); @@ -5250,10 +5278,20 @@ int stmmac_resume(struct device *dev) return ret; } + if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { + rtnl_lock(); + phylink_start(priv->phylink); + /* We may have called phylink_speed_down before */ + phylink_speed_up(priv->phylink); + rtnl_unlock(); + } + + rtnl_lock(); mutex_lock(&priv->lock); stmmac_reset_queues_param(priv); + stmmac_free_tx_skbufs(priv); stmmac_clear_descriptors(priv); stmmac_hw_setup(ndev, false); @@ -5265,14 +5303,7 @@ int stmmac_resume(struct device *dev) stmmac_enable_all_queues(priv); mutex_unlock(&priv->lock); - - if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { - rtnl_lock(); - phylink_start(priv->phylink); - /* We may have called phylink_speed_down before */ - phylink_speed_up(priv->phylink); - rtnl_unlock(); - } + rtnl_unlock(); phylink_mac_change(priv->phylink, true); diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index 75056c14b161..5dc60ecabe56 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -1001,8 +1001,7 @@ struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs, if (IS_ERR_OR_NULL(cpts->ptp_clock)) { dev_err(dev, "Failed to register ptp clk %ld\n", PTR_ERR(cpts->ptp_clock)); - if (!cpts->ptp_clock) - ret = -ENODEV; + ret = cpts->ptp_clock ? PTR_ERR(cpts->ptp_clock) : -ENODEV; goto refclk_disable; } cpts->phc_index = ptp_clock_index(cpts->ptp_clock); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 9fd1f77190ad..b0f00b4edd94 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -838,9 +838,12 @@ static int cpsw_ndo_open(struct net_device *ndev) if (ret < 0) goto err_cleanup; - if (cpts_register(cpsw->cpts)) - dev_err(priv->dev, "error registering cpts device\n"); - + if (cpsw->cpts) { + if (cpts_register(cpsw->cpts)) + dev_err(priv->dev, "error registering cpts device\n"); + else + writel(0x10, &cpsw->wr_regs->misc_en); + } } cpsw_restore(priv); @@ -1631,6 +1634,7 @@ static int cpsw_probe(struct platform_device *pdev) CPSW_MAX_QUEUES, CPSW_MAX_QUEUES); if (!ndev) { dev_err(dev, "error allocating net_device\n"); + ret = -ENOMEM; goto clean_cpts; } @@ -1716,7 +1720,6 @@ static int cpsw_probe(struct platform_device *pdev) /* Enable misc CPTS evnt_pend IRQ */ cpts_set_irqpoll(cpsw->cpts, false); - writel(0x10, &cpsw->wr_regs->misc_en); skip_cpts: cpsw_notice(priv, probe, diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index f779d2e1b5c5..2f5e0ad23ad7 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -873,8 +873,12 @@ static int cpsw_ndo_open(struct net_device *ndev) if (ret < 0) goto err_cleanup; - if (cpts_register(cpsw->cpts)) - dev_err(priv->dev, "error registering cpts device\n"); + if (cpsw->cpts) { + if (cpts_register(cpsw->cpts)) + dev_err(priv->dev, "error registering cpts device\n"); + else + writel(0x10, &cpsw->wr_regs->misc_en); + } napi_enable(&cpsw->napi_rx); napi_enable(&cpsw->napi_tx); @@ -2006,7 +2010,6 @@ static int cpsw_probe(struct platform_device *pdev) /* Enable misc CPTS evnt_pend IRQ */ cpts_set_irqpoll(cpsw->cpts, false); - writel(0x10, &cpsw->wr_regs->misc_en); skip_cpts: ret = cpsw_register_notifiers(cpsw); diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index 31c5e36ff706..424e644724e4 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -1265,9 +1265,6 @@ static int cpsw_xdp_prog_setup(struct cpsw_priv *priv, struct netdev_bpf *bpf) if (!priv->xdpi.prog && !prog) return 0; - if (!xdp_attachment_flags_ok(&priv->xdpi, bpf)) - return -EBUSY; - WRITE_ONCE(priv->xdp_prog, prog); xdp_attachment_setup(&priv->xdpi, bpf); diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 60c199fcb91e..030185301014 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1351,7 +1351,6 @@ static int temac_probe(struct platform_device *pdev) struct device_node *temac_np = dev_of_node(&pdev->dev), *dma_np; struct temac_local *lp; struct net_device *ndev; - struct resource *res; const void *addr; __be32 *p; bool little_endian; @@ -1500,13 +1499,11 @@ static int temac_probe(struct platform_device *pdev) of_node_put(dma_np); } else if (pdata) { /* 2nd memory resource specifies DMA registers */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - lp->sdma_regs = devm_ioremap(&pdev->dev, res->start, - resource_size(res)); - if (!lp->sdma_regs) { + lp->sdma_regs = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(lp->sdma_regs)) { dev_err(&pdev->dev, "could not map DMA registers\n"); - return -ENOMEM; + return PTR_ERR(lp->sdma_regs); } if (pdata->dma_little_endian) { lp->dma_in = temac_dma_in32_le; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index d07008a818df..1426bfc009bc 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -224,8 +224,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, if (ip_tunnel_collect_metadata() || gs->collect_md) { __be16 flags; - flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT | - (gnvh->oam ? TUNNEL_OAM : 0) | + flags = TUNNEL_KEY | (gnvh->oam ? TUNNEL_OAM : 0) | (gnvh->critical ? TUNNEL_CRIT_OPT : 0); tun_dst = udp_tun_rx_dst(skb, geneve_get_sk_family(gs), flags, diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index 92642030e735..6c3ed5b17b80 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -156,6 +156,9 @@ int gsi_trans_pool_init_dma(struct device *dev, struct gsi_trans_pool *pool, /* The allocator will give us a power-of-2 number of pages. But we * can't guarantee that, so request it. That way we won't waste any * memory that would be available beyond the required space. + * + * Note that gsi_trans_pool_exit_dma() assumes the total allocated + * size is exactly (count * size). */ total_size = get_order(total_size) << PAGE_SHIFT; @@ -175,7 +178,9 @@ int gsi_trans_pool_init_dma(struct device *dev, struct gsi_trans_pool *pool, void gsi_trans_pool_exit_dma(struct device *dev, struct gsi_trans_pool *pool) { - dma_free_coherent(dev, pool->size, pool->base, pool->addr); + size_t total_size = pool->count * pool->size; + + dma_free_coherent(dev, total_size, pool->base, pool->addr); memset(pool, 0, sizeof(*pool)); } @@ -362,22 +367,31 @@ struct gsi_trans *gsi_channel_trans_alloc(struct gsi *gsi, u32 channel_id, return trans; } -/* Free a previously-allocated transaction (used only in case of error) */ +/* Free a previously-allocated transaction */ void gsi_trans_free(struct gsi_trans *trans) { + refcount_t *refcount = &trans->refcount; struct gsi_trans_info *trans_info; + bool last; - if (!refcount_dec_and_test(&trans->refcount)) + /* We must hold the lock to release the last reference */ + if (refcount_dec_not_one(refcount)) return; trans_info = &trans->gsi->channel[trans->channel_id].trans_info; spin_lock_bh(&trans_info->spinlock); - list_del(&trans->links); + /* Reference might have been added before we got the lock */ + last = refcount_dec_and_test(refcount); + if (last) + list_del(&trans->links); spin_unlock_bh(&trans_info->spinlock); + if (!last) + return; + ipa_gsi_trans_release(trans); /* Releasing the reserved TREs implicitly frees the sgl[] and diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 2e90512f3bbe..90aafb56f140 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -63,15 +63,20 @@ static int nsim_bpf_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn) { struct nsim_bpf_bound_prog *state; + int ret = 0; state = env->prog->aux->offload->dev_priv; if (state->nsim_dev->bpf_bind_verifier_delay && !insn_idx) msleep(state->nsim_dev->bpf_bind_verifier_delay); - if (insn_idx == env->prog->len - 1) + if (insn_idx == env->prog->len - 1) { pr_vlog(env, "Hello from netdevsim!\n"); - return 0; + if (!state->nsim_dev->bpf_bind_verifier_accept) + ret = -EOPNOTSUPP; + } + + return ret; } static int nsim_bpf_finalize(struct bpf_verifier_env *env) @@ -190,9 +195,6 @@ nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf, { int err; - if (!xdp_attachment_flags_ok(xdp, bpf)) - return -EBUSY; - if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) { NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS"); return -EOPNOTSUPP; @@ -598,6 +600,9 @@ int nsim_bpf_dev_init(struct nsim_dev *nsim_dev) &nsim_dev->bpf_bind_accept); debugfs_create_u32("bpf_bind_verifier_delay", 0600, nsim_dev->ddir, &nsim_dev->bpf_bind_verifier_delay); + nsim_dev->bpf_bind_verifier_accept = true; + debugfs_create_bool("bpf_bind_verifier_accept", 0600, nsim_dev->ddir, + &nsim_dev->bpf_bind_verifier_accept); return 0; } diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index d07061417675..e7972e88ffe0 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -96,6 +96,7 @@ static const struct file_operations nsim_dev_take_snapshot_fops = { .open = simple_open, .write = nsim_dev_take_snapshot_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, }; static ssize_t nsim_dev_trap_fa_cookie_read(struct file *file, @@ -188,6 +189,7 @@ static const struct file_operations nsim_dev_trap_fa_cookie_fops = { .read = nsim_dev_trap_fa_cookie_read, .write = nsim_dev_trap_fa_cookie_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, }; static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c index 62958b238d50..21e2974660e7 100644 --- a/drivers/net/netdevsim/health.c +++ b/drivers/net/netdevsim/health.c @@ -261,6 +261,7 @@ static const struct file_operations nsim_dev_health_break_fops = { .open = simple_open, .write = nsim_dev_health_break_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, }; int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink) diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 827fc80f50a0..c4e7ad2a1964 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -189,6 +189,7 @@ struct nsim_dev { struct dentry *take_snapshot; struct bpf_offload_dev *bpf_dev; bool bpf_bind_accept; + bool bpf_bind_verifier_accept; u32 bpf_bind_verifier_delay; struct dentry *ddir_bpf_bound_progs; u32 prog_id_gen; diff --git a/drivers/net/netdevsim/udp_tunnels.c b/drivers/net/netdevsim/udp_tunnels.c index 6ab023acefd6..02dc3123eb6c 100644 --- a/drivers/net/netdevsim/udp_tunnels.c +++ b/drivers/net/netdevsim/udp_tunnels.c @@ -124,6 +124,7 @@ static const struct file_operations nsim_udp_tunnels_info_reset_fops = { .open = simple_open, .write = nsim_udp_tunnels_info_reset_write, .llseek = generic_file_llseek, + .owner = THIS_MODULE, }; int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, diff --git a/drivers/net/phy/mscc/mscc_macsec.c b/drivers/net/phy/mscc/mscc_macsec.c index 6cf9b798b710..10be266e48e8 100644 --- a/drivers/net/phy/mscc/mscc_macsec.c +++ b/drivers/net/phy/mscc/mscc_macsec.c @@ -981,7 +981,6 @@ int vsc8584_macsec_init(struct phy_device *phydev) switch (phydev->phy_id & phydev->drv->phy_id_mask) { case PHY_ID_VSC856X: - case PHY_ID_VSC8575: case PHY_ID_VSC8582: case PHY_ID_VSC8584: INIT_LIST_HEAD(&vsc8531->macsec_flows); diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index fb1db713b7fb..575580d3ffe0 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -551,6 +551,8 @@ static struct phy_driver realtek_drvs[] = { { PHY_ID_MATCH_EXACT(0x00008201), .name = "RTL8201CP Ethernet", + .read_page = rtl821x_read_page, + .write_page = rtl821x_write_page, }, { PHY_ID_MATCH_EXACT(0x001cc816), .name = "RTL8201F Fast Ethernet", diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index ec97669be5c2..0fc39ac5ca88 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -291,8 +291,10 @@ static int smsc_phy_probe(struct phy_device *phydev) return ret; ret = clk_set_rate(priv->refclk, 50 * 1000 * 1000); - if (ret) + if (ret) { + clk_disable_unprepare(priv->refclk); return ret; + } return 0; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index be69d272052f..cd06cae76035 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1961,12 +1961,15 @@ static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t result; + int noblock = 0; if (!tun) return -EBADFD; - result = tun_get_user(tun, tfile, NULL, from, - file->f_flags & O_NONBLOCK, false); + if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) + noblock = 1; + + result = tun_get_user(tun, tfile, NULL, from, noblock, false); tun_put(tun); return result; @@ -2185,10 +2188,15 @@ static ssize_t tun_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t len = iov_iter_count(to), ret; + int noblock = 0; if (!tun) return -EBADFD; - ret = tun_do_read(tun, tfile, to, file->f_flags & O_NONBLOCK, NULL); + + if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) + noblock = 1; + + ret = tun_do_read(tun, tfile, to, noblock, NULL); ret = min_t(ssize_t, ret, len); if (ret > 0) iocb->ki_pos = ret; diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c index ca89d8258dd3..c4568a491dc4 100644 --- a/drivers/net/usb/cx82310_eth.c +++ b/drivers/net/usb/cx82310_eth.c @@ -197,7 +197,8 @@ static int cx82310_bind(struct usbnet *dev, struct usb_interface *intf) } /* enable ethernet mode (?) */ - if (cx82310_enable_ethernet(dev)) + ret = cx82310_enable_ethernet(dev); + if (ret) goto err; /* get the MAC address */ diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index b09b45382faf..207e59e74935 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -59,7 +59,7 @@ #define IPHETH_USBINTF_SUBCLASS 253 #define IPHETH_USBINTF_PROTO 1 -#define IPHETH_BUF_SIZE 1516 +#define IPHETH_BUF_SIZE 1514 #define IPHETH_IP_ALIGN 2 /* padding at front of URB */ #define IPHETH_TX_TIMEOUT (5 * HZ) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 581ed51abb53..fc378ff56775 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1070,7 +1070,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x05c6, 0x9011, 4)}, {QMI_FIXED_INTF(0x05c6, 0x9021, 1)}, {QMI_FIXED_INTF(0x05c6, 0x9022, 2)}, - {QMI_FIXED_INTF(0x05c6, 0x9025, 4)}, /* Alcatel-sbell ASB TL131 TDD LTE (China Mobile) */ + {QMI_QUIRK_SET_DTR(0x05c6, 0x9025, 4)}, /* Alcatel-sbell ASB TL131 TDD LTE (China Mobile) */ {QMI_FIXED_INTF(0x05c6, 0x9026, 3)}, {QMI_FIXED_INTF(0x05c6, 0x902e, 5)}, {QMI_FIXED_INTF(0x05c6, 0x9031, 5)}, diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 60c1aadece89..b9b7e00b72a8 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -608,8 +608,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) return ret; } -static int vrf_finish_direct(struct net *net, struct sock *sk, - struct sk_buff *skb) +static void vrf_finish_direct(struct sk_buff *skb) { struct net_device *vrf_dev = skb->dev; @@ -628,7 +627,8 @@ static int vrf_finish_direct(struct net *net, struct sock *sk, skb_pull(skb, ETH_HLEN); } - return 1; + /* reset skb device */ + nf_reset_ct(skb); } #if IS_ENABLED(CONFIG_IPV6) @@ -707,15 +707,41 @@ static struct sk_buff *vrf_ip6_out_redirect(struct net_device *vrf_dev, return skb; } +static int vrf_output6_direct_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + vrf_finish_direct(skb); + + return vrf_ip6_local_out(net, sk, skb); +} + static int vrf_output6_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { + int err = 1; + skb->protocol = htons(ETH_P_IPV6); - return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, - net, sk, skb, NULL, skb->dev, - vrf_finish_direct, - !(IPCB(skb)->flags & IPSKB_REROUTED)); + if (!(IPCB(skb)->flags & IPSKB_REROUTED)) + err = nf_hook(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, + NULL, skb->dev, vrf_output6_direct_finish); + + if (likely(err == 1)) + vrf_finish_direct(skb); + + return err; +} + +static int vrf_ip6_out_direct_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + int err; + + err = vrf_output6_direct(net, sk, skb); + if (likely(err == 1)) + err = vrf_ip6_local_out(net, sk, skb); + + return err; } static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, @@ -728,18 +754,15 @@ static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, - skb, NULL, vrf_dev, vrf_output6_direct); + skb, NULL, vrf_dev, vrf_ip6_out_direct_finish); if (likely(err == 1)) err = vrf_output6_direct(net, sk, skb); - /* reset skb device */ if (likely(err == 1)) - nf_reset_ct(skb); - else - skb = NULL; + return skb; - return skb; + return NULL; } static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, @@ -919,15 +942,41 @@ static struct sk_buff *vrf_ip_out_redirect(struct net_device *vrf_dev, return skb; } +static int vrf_output_direct_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + vrf_finish_direct(skb); + + return vrf_ip_local_out(net, sk, skb); +} + static int vrf_output_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { + int err = 1; + skb->protocol = htons(ETH_P_IP); - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, - net, sk, skb, NULL, skb->dev, - vrf_finish_direct, - !(IPCB(skb)->flags & IPSKB_REROUTED)); + if (!(IPCB(skb)->flags & IPSKB_REROUTED)) + err = nf_hook(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, + NULL, skb->dev, vrf_output_direct_finish); + + if (likely(err == 1)) + vrf_finish_direct(skb); + + return err; +} + +static int vrf_ip_out_direct_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + int err; + + err = vrf_output_direct(net, sk, skb); + if (likely(err == 1)) + err = vrf_ip_local_out(net, sk, skb); + + return err; } static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, @@ -940,18 +989,15 @@ static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, - skb, NULL, vrf_dev, vrf_output_direct); + skb, NULL, vrf_dev, vrf_ip_out_direct_finish); if (likely(err == 1)) err = vrf_output_direct(net, sk, skb); - /* reset skb device */ if (likely(err == 1)) - nf_reset_ct(skb); - else - skb = NULL; + return skb; - return skb; + return NULL; } static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev, @@ -1269,11 +1315,17 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, int orig_iif = skb->skb_iif; bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); bool is_ndisc = ipv6_ndisc_frame(skb); + bool is_ll_src; /* loopback, multicast & non-ND link-local traffic; do not push through - * packet taps again. Reset pkt_type for upper layers to process skb + * packet taps again. Reset pkt_type for upper layers to process skb. + * for packets with lladdr src, however, skip so that the dst can be + * determine at input using original ifindex in the case that daddr + * needs strict */ - if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) { + is_ll_src = ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL; + if (skb->pkt_type == PACKET_LOOPBACK || + (need_strict && !is_ndisc && !is_ll_src)) { skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IP6CB(skb)->flags |= IP6SKB_L3SLAVE; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 1a557aeba32b..977f77e2c2ce 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3798,6 +3798,9 @@ static void vxlan_config_apply(struct net_device *dev, dev->gso_max_segs = lowerdev->gso_max_segs; needed_headroom = lowerdev->hard_header_len; + needed_headroom += lowerdev->needed_headroom; + + dev->needed_tailroom = lowerdev->needed_tailroom; max_mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); @@ -3877,8 +3880,10 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, if (dst->remote_ifindex) { remote_dev = __dev_get_by_index(net, dst->remote_ifindex); - if (!remote_dev) + if (!remote_dev) { + err = -ENODEV; goto errout; + } err = netdev_upper_dev_link(remote_dev, dev, extack); if (err) diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index f8aed0696d77..2369ca250cd6 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -889,6 +889,7 @@ static ssize_t cosa_write(struct file *file, chan->tx_status = 1; spin_unlock_irqrestore(&cosa->lock, flags); up(&chan->wsem); + kfree(kbuf); return -ERESTARTSYS; } } diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h index d43e0d3f3a12..052413eef059 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h @@ -5,10 +5,9 @@ * * GPL LICENSE SUMMARY * - * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 - 2019 Intel Corporation + * Copyright(c) 2012-2014, 2018 - 2020 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -28,10 +27,9 @@ * * BSD LICENSE * - * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 - 2019 Intel Corporation + * Copyright(c) 2012-2014, 2018 - 2020 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -128,7 +126,9 @@ enum iwl_sta_flags { STA_FLG_MAX_AGG_SIZE_256K = (5 << STA_FLG_MAX_AGG_SIZE_SHIFT), STA_FLG_MAX_AGG_SIZE_512K = (6 << STA_FLG_MAX_AGG_SIZE_SHIFT), STA_FLG_MAX_AGG_SIZE_1024K = (7 << STA_FLG_MAX_AGG_SIZE_SHIFT), - STA_FLG_MAX_AGG_SIZE_MSK = (7 << STA_FLG_MAX_AGG_SIZE_SHIFT), + STA_FLG_MAX_AGG_SIZE_2M = (8 << STA_FLG_MAX_AGG_SIZE_SHIFT), + STA_FLG_MAX_AGG_SIZE_4M = (9 << STA_FLG_MAX_AGG_SIZE_SHIFT), + STA_FLG_MAX_AGG_SIZE_MSK = (0xf << STA_FLG_MAX_AGG_SIZE_SHIFT), STA_FLG_AGG_MPDU_DENS_SHIFT = 23, STA_FLG_AGG_MPDU_DENS_2US = (4 << STA_FLG_AGG_MPDU_DENS_SHIFT), diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h b/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h index a731f28e101a..53b438d709db 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h @@ -8,7 +8,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 - 2019 Intel Corporation + * Copyright(c) 2018 - 2020 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -31,7 +31,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 - 2019 Intel Corporation + * Copyright(c) 2018 - 2020 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -421,12 +421,14 @@ struct iwl_hs20_roc_res { * able to run the GO Negotiation. Will not be fragmented and not * repetitive. Valid only on the P2P Device MAC. Only the duration will * be taken into account. + * @SESSION_PROTECT_CONF_MAX_ID: not used */ enum iwl_mvm_session_prot_conf_id { SESSION_PROTECT_CONF_ASSOC, SESSION_PROTECT_CONF_GO_CLIENT_ASSOC, SESSION_PROTECT_CONF_P2P_DEVICE_DISCOV, SESSION_PROTECT_CONF_P2P_GO_NEGOTIATION, + SESSION_PROTECT_CONF_MAX_ID, }; /* SESSION_PROTECTION_CONF_ID_E_VER_1 */ /** @@ -459,7 +461,7 @@ struct iwl_mvm_session_prot_cmd { * @mac_id: the mac id for which the session protection started / ended * @status: 1 means success, 0 means failure * @start: 1 means the session protection started, 0 means it ended - * @conf_id: the configuration id of the session that started / eneded + * @conf_id: see &enum iwl_mvm_session_prot_conf_id * * Note that any session protection will always get two notifications: start * and end even the firmware could not schedule it. diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index ca4967b81d01..580b07a43856 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -491,8 +491,8 @@ struct iwl_cfg { #define IWL_CFG_RF_ID_HR 0x7 #define IWL_CFG_RF_ID_HR1 0x4 -#define IWL_CFG_NO_160 0x0 -#define IWL_CFG_160 0x1 +#define IWL_CFG_NO_160 0x1 +#define IWL_CFG_160 0x0 #define IWL_CFG_CORES_BT 0x0 #define IWL_CFG_CORES_BT_GNSS 0x5 diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h index cb9e8e189a1a..1d48c7d7fffd 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h @@ -147,6 +147,16 @@ #define CSR_MAC_SHADOW_REG_CTL2 (CSR_BASE + 0x0AC) #define CSR_MAC_SHADOW_REG_CTL2_RX_WAKE 0xFFFF +/* LTR control (since IWL_DEVICE_FAMILY_22000) */ +#define CSR_LTR_LONG_VAL_AD (CSR_BASE + 0x0D4) +#define CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ 0x80000000 +#define CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE 0x1c000000 +#define CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL 0x03ff0000 +#define CSR_LTR_LONG_VAL_AD_SNOOP_REQ 0x00008000 +#define CSR_LTR_LONG_VAL_AD_SNOOP_SCALE 0x00001c00 +#define CSR_LTR_LONG_VAL_AD_SNOOP_VAL 0x000003ff +#define CSR_LTR_LONG_VAL_AD_SCALE_USEC 2 + /* GIO Chicken Bits (PCI Express bus link power management) */ #define CSR_GIO_CHICKEN_BITS (CSR_BASE+0x100) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 688c1125e67b..b627e7da7ac9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -3080,7 +3080,7 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw, /* this would be a mac80211 bug ... but don't crash */ if (WARN_ON_ONCE(!mvmvif->phy_ctxt)) - return -EINVAL; + return test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status) ? 0 : -EINVAL; /* * If we are in a STA removal flow and in DQA mode: @@ -3127,6 +3127,9 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw, goto out_unlock; } + if (vif->type == NL80211_IFTYPE_STATION) + vif->bss_conf.he_support = sta->he_cap.has_he; + if (sta->tdls && (vif->p2p || iwl_mvm_tdls_sta_count(mvm, NULL) == diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 779ab751cf45..9912fbdc3ad6 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -196,6 +196,7 @@ int iwl_mvm_sta_send_to_fw(struct iwl_mvm *mvm, struct ieee80211_sta *sta, mpdu_dens = sta->ht_cap.ampdu_density; } + if (sta->vht_cap.vht_supported) { agg_size = sta->vht_cap.cap & IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; @@ -205,6 +206,23 @@ int iwl_mvm_sta_send_to_fw(struct iwl_mvm *mvm, struct ieee80211_sta *sta, agg_size = sta->ht_cap.ampdu_factor; } + /* D6.0 10.12.2 A-MPDU length limit rules + * A STA indicates the maximum length of the A-MPDU preEOF padding + * that it can receive in an HE PPDU in the Maximum A-MPDU Length + * Exponent field in its HT Capabilities, VHT Capabilities, + * and HE 6 GHz Band Capabilities elements (if present) and the + * Maximum AMPDU Length Exponent Extension field in its HE + * Capabilities element + */ + if (sta->he_cap.has_he) + agg_size += u8_get_bits(sta->he_cap.he_cap_elem.mac_cap_info[3], + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK); + + /* Limit to max A-MPDU supported by FW */ + if (agg_size > (STA_FLG_MAX_AGG_SIZE_4M >> STA_FLG_MAX_AGG_SIZE_SHIFT)) + agg_size = (STA_FLG_MAX_AGG_SIZE_4M >> + STA_FLG_MAX_AGG_SIZE_SHIFT); + add_sta_cmd.station_flags |= cpu_to_le32(agg_size << STA_FLG_MAX_AGG_SIZE_SHIFT); add_sta_cmd.station_flags |= diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 7fce79c1c114..1db6d8d38822 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -641,11 +641,32 @@ void iwl_mvm_protect_session(struct iwl_mvm *mvm, } } +static void iwl_mvm_cancel_session_protection(struct iwl_mvm *mvm, + struct iwl_mvm_vif *mvmvif) +{ + struct iwl_mvm_session_prot_cmd cmd = { + .id_and_color = + cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->id, + mvmvif->color)), + .action = cpu_to_le32(FW_CTXT_ACTION_REMOVE), + .conf_id = cpu_to_le32(mvmvif->time_event_data.id), + }; + int ret; + + ret = iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(SESSION_PROTECTION_CMD, + MAC_CONF_GROUP, 0), + 0, sizeof(cmd), &cmd); + if (ret) + IWL_ERR(mvm, + "Couldn't send the SESSION_PROTECTION_CMD: %d\n", ret); +} + static bool __iwl_mvm_remove_time_event(struct iwl_mvm *mvm, struct iwl_mvm_time_event_data *te_data, u32 *uid) { u32 id; + struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(te_data->vif); /* * It is possible that by the time we got to this point the time @@ -663,14 +684,29 @@ static bool __iwl_mvm_remove_time_event(struct iwl_mvm *mvm, iwl_mvm_te_clear_data(mvm, te_data); spin_unlock_bh(&mvm->time_event_lock); - /* - * It is possible that by the time we try to remove it, the time event - * has already ended and removed. In such a case there is no need to - * send a removal command. + /* When session protection is supported, the te_data->id field + * is reused to save session protection's configuration. */ - if (id == TE_MAX) { - IWL_DEBUG_TE(mvm, "TE 0x%x has already ended\n", *uid); + if (fw_has_capa(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_SESSION_PROT_CMD)) { + if (mvmvif && id < SESSION_PROTECT_CONF_MAX_ID) { + /* Session protection is still ongoing. Cancel it */ + iwl_mvm_cancel_session_protection(mvm, mvmvif); + if (te_data->vif->type == NL80211_IFTYPE_P2P_DEVICE) { + set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status); + iwl_mvm_roc_finished(mvm); + } + } return false; + } else { + /* It is possible that by the time we try to remove it, the + * time event has already ended and removed. In such a case + * there is no need to send a removal command. + */ + if (id == TE_MAX) { + IWL_DEBUG_TE(mvm, "TE 0x%x has already ended\n", *uid); + return false; + } } return true; @@ -771,6 +807,7 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm, struct iwl_rx_packet *pkt = rxb_addr(rxb); struct iwl_mvm_session_prot_notif *notif = (void *)pkt->data; struct ieee80211_vif *vif; + struct iwl_mvm_vif *mvmvif; rcu_read_lock(); vif = iwl_mvm_rcu_dereference_vif_id(mvm, le32_to_cpu(notif->mac_id), @@ -779,9 +816,10 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm, if (!vif) goto out_unlock; + mvmvif = iwl_mvm_vif_from_mac80211(vif); + /* The vif is not a P2P_DEVICE, maintain its time_event_data */ if (vif->type != NL80211_IFTYPE_P2P_DEVICE) { - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_mvm_time_event_data *te_data = &mvmvif->time_event_data; @@ -816,10 +854,14 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm, if (!le32_to_cpu(notif->status) || !le32_to_cpu(notif->start)) { /* End TE, notify mac80211 */ + mvmvif->time_event_data.id = SESSION_PROTECT_CONF_MAX_ID; ieee80211_remain_on_channel_expired(mvm->hw); set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status); iwl_mvm_roc_finished(mvm); } else if (le32_to_cpu(notif->start)) { + if (WARN_ON(mvmvif->time_event_data.id != + le32_to_cpu(notif->conf_id))) + goto out_unlock; set_bit(IWL_MVM_STATUS_ROC_RUNNING, &mvm->status); ieee80211_ready_on_channel(mvm->hw); /* Start TE */ } @@ -845,20 +887,24 @@ iwl_mvm_start_p2p_roc_session_protection(struct iwl_mvm *mvm, lockdep_assert_held(&mvm->mutex); + /* The time_event_data.id field is reused to save session + * protection's configuration. + */ switch (type) { case IEEE80211_ROC_TYPE_NORMAL: - cmd.conf_id = - cpu_to_le32(SESSION_PROTECT_CONF_P2P_DEVICE_DISCOV); + mvmvif->time_event_data.id = + SESSION_PROTECT_CONF_P2P_DEVICE_DISCOV; break; case IEEE80211_ROC_TYPE_MGMT_TX: - cmd.conf_id = - cpu_to_le32(SESSION_PROTECT_CONF_P2P_GO_NEGOTIATION); + mvmvif->time_event_data.id = + SESSION_PROTECT_CONF_P2P_GO_NEGOTIATION; break; default: WARN_ONCE(1, "Got an invalid ROC type\n"); return -EINVAL; } + cmd.conf_id = cpu_to_le32(mvmvif->time_event_data.id); return iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(SESSION_PROTECTION_CMD, MAC_CONF_GROUP, 0), 0, sizeof(cmd), &cmd); @@ -960,25 +1006,6 @@ void iwl_mvm_cleanup_roc_te(struct iwl_mvm *mvm) __iwl_mvm_remove_time_event(mvm, te_data, &uid); } -static void iwl_mvm_cancel_session_protection(struct iwl_mvm *mvm, - struct iwl_mvm_vif *mvmvif) -{ - struct iwl_mvm_session_prot_cmd cmd = { - .id_and_color = - cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->id, - mvmvif->color)), - .action = cpu_to_le32(FW_CTXT_ACTION_REMOVE), - }; - int ret; - - ret = iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(SESSION_PROTECTION_CMD, - MAC_CONF_GROUP, 0), - 0, sizeof(cmd), &cmd); - if (ret) - IWL_ERR(mvm, - "Couldn't send the SESSION_PROTECTION_CMD: %d\n", ret); -} - void iwl_mvm_stop_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif) { struct iwl_mvm_vif *mvmvif; @@ -988,10 +1015,13 @@ void iwl_mvm_stop_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif) IWL_UCODE_TLV_CAPA_SESSION_PROT_CMD)) { mvmvif = iwl_mvm_vif_from_mac80211(vif); - iwl_mvm_cancel_session_protection(mvm, mvmvif); - - if (vif->type == NL80211_IFTYPE_P2P_DEVICE) + if (vif->type == NL80211_IFTYPE_P2P_DEVICE) { + iwl_mvm_cancel_session_protection(mvm, mvmvif); set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status); + } else { + iwl_mvm_remove_aux_roc_te(mvm, mvmvif, + &mvmvif->time_event_data); + } iwl_mvm_roc_finished(mvm); @@ -1126,10 +1156,15 @@ void iwl_mvm_schedule_session_protection(struct iwl_mvm *mvm, cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->id, mvmvif->color)), .action = cpu_to_le32(FW_CTXT_ACTION_ADD), - .conf_id = cpu_to_le32(SESSION_PROTECT_CONF_ASSOC), .duration_tu = cpu_to_le32(MSEC_TO_TU(duration)), }; + /* The time_event_data.id field is reused to save session + * protection's configuration. + */ + mvmvif->time_event_data.id = SESSION_PROTECT_CONF_ASSOC; + cmd.conf_id = cpu_to_le32(mvmvif->time_event_data.id); + lockdep_assert_held(&mvm->mutex); spin_lock_bh(&mvm->time_event_lock); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c index a0352fa873d9..5512e3c630c3 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c @@ -252,6 +252,26 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, iwl_set_bit(trans, CSR_CTXT_INFO_BOOT_CTRL, CSR_AUTO_FUNC_BOOT_ENA); + + if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210) { + /* + * The firmware initializes this again later (to a smaller + * value), but for the boot process initialize the LTR to + * ~250 usec. + */ + u32 val = CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ | + u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, + CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE) | + u32_encode_bits(250, + CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL) | + CSR_LTR_LONG_VAL_AD_SNOOP_REQ | + u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, + CSR_LTR_LONG_VAL_AD_SNOOP_SCALE) | + u32_encode_bits(250, CSR_LTR_LONG_VAL_AD_SNOOP_VAL); + + iwl_write32(trans, CSR_LTR_LONG_VAL_AD, val); + } + if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) iwl_write_umac_prph(trans, UREG_CPU_INIT_RUN, 1); else diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 129021f26791..7b5ece380fbf 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -536,9 +536,15 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2725, 0x0090, iwlax211_2ax_cfg_so_gf_a0)}, {IWL_PCI_DEVICE(0x2725, 0x0020, iwlax210_2ax_cfg_ty_gf_a0)}, + {IWL_PCI_DEVICE(0x2725, 0x0024, iwlax210_2ax_cfg_ty_gf_a0)}, {IWL_PCI_DEVICE(0x2725, 0x0310, iwlax210_2ax_cfg_ty_gf_a0)}, {IWL_PCI_DEVICE(0x2725, 0x0510, iwlax210_2ax_cfg_ty_gf_a0)}, {IWL_PCI_DEVICE(0x2725, 0x0A10, iwlax210_2ax_cfg_ty_gf_a0)}, + {IWL_PCI_DEVICE(0x2725, 0xE020, iwlax210_2ax_cfg_ty_gf_a0)}, + {IWL_PCI_DEVICE(0x2725, 0xE024, iwlax210_2ax_cfg_ty_gf_a0)}, + {IWL_PCI_DEVICE(0x2725, 0x4020, iwlax210_2ax_cfg_ty_gf_a0)}, + {IWL_PCI_DEVICE(0x2725, 0x6020, iwlax210_2ax_cfg_ty_gf_a0)}, + {IWL_PCI_DEVICE(0x2725, 0x6024, iwlax210_2ax_cfg_ty_gf_a0)}, {IWL_PCI_DEVICE(0x2725, 0x00B0, iwlax411_2ax_cfg_sosnj_gf4_a0)}, {IWL_PCI_DEVICE(0x2726, 0x0070, iwlax201_cfg_snj_hr_b0)}, {IWL_PCI_DEVICE(0x2726, 0x0074, iwlax201_cfg_snj_hr_b0)}, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index d2e69ad53b27..2fffbbc8462f 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -2156,18 +2156,36 @@ static int iwl_trans_pcie_read_mem(struct iwl_trans *trans, u32 addr, void *buf, int dwords) { unsigned long flags; - int offs, ret = 0; + int offs = 0; u32 *vals = buf; - if (iwl_trans_grab_nic_access(trans, &flags)) { - iwl_write32(trans, HBUS_TARG_MEM_RADDR, addr); - for (offs = 0; offs < dwords; offs++) - vals[offs] = iwl_read32(trans, HBUS_TARG_MEM_RDAT); - iwl_trans_release_nic_access(trans, &flags); - } else { - ret = -EBUSY; + while (offs < dwords) { + /* limit the time we spin here under lock to 1/2s */ + ktime_t timeout = ktime_add_us(ktime_get(), 500 * USEC_PER_MSEC); + + if (iwl_trans_grab_nic_access(trans, &flags)) { + iwl_write32(trans, HBUS_TARG_MEM_RADDR, + addr + 4 * offs); + + while (offs < dwords) { + vals[offs] = iwl_read32(trans, + HBUS_TARG_MEM_RDAT); + offs++; + + /* calling ktime_get is expensive so + * do it once in 128 reads + */ + if (offs % 128 == 0 && ktime_after(ktime_get(), + timeout)) + break; + } + iwl_trans_release_nic_access(trans, &flags); + } else { + return -EBUSY; + } } - return ret; + + return 0; } static int iwl_trans_pcie_write_mem(struct iwl_trans *trans, u32 addr, diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c index 7d3f0a2e5fa0..f1ae9ff835b2 100644 --- a/drivers/net/wireless/mediatek/mt76/usb.c +++ b/drivers/net/wireless/mediatek/mt76/usb.c @@ -1020,8 +1020,6 @@ void mt76u_stop_tx(struct mt76_dev *dev) { int ret; - mt76_worker_disable(&dev->tx_worker); - ret = wait_event_timeout(dev->tx_wait, !mt76_has_tx_pending(&dev->phy), HZ / 5); if (!ret) { @@ -1040,6 +1038,8 @@ void mt76u_stop_tx(struct mt76_dev *dev) usb_kill_urb(q->entry[j].urb); } + mt76_worker_disable(&dev->tx_worker); + /* On device removal we maight queue skb's, but mt76u_tx_kick() * will fail to submit urb, cleanup those skb's manually. */ @@ -1048,18 +1048,19 @@ void mt76u_stop_tx(struct mt76_dev *dev) if (!q) continue; - entry = q->entry[q->tail]; - q->entry[q->tail].done = false; - - mt76_queue_tx_complete(dev, q, &entry); + while (q->queued > 0) { + entry = q->entry[q->tail]; + q->entry[q->tail].done = false; + mt76_queue_tx_complete(dev, q, &entry); + } } + + mt76_worker_enable(&dev->tx_worker); } cancel_work_sync(&dev->usb.stat_work); clear_bit(MT76_READING_STATS, &dev->phy.state); - mt76_worker_enable(&dev->tx_worker); - mt76_tx_status_check(dev, NULL, true); } EXPORT_SYMBOL_GPL(mt76u_stop_tx); diff --git a/drivers/net/wireless/realtek/rtw88/debug.c b/drivers/net/wireless/realtek/rtw88/debug.c index 3852c4f0ac0b..efbba9caef3b 100644 --- a/drivers/net/wireless/realtek/rtw88/debug.c +++ b/drivers/net/wireless/realtek/rtw88/debug.c @@ -147,6 +147,8 @@ static int rtw_debugfs_copy_from_user(char tmp[], int size, { int tmp_len; + memset(tmp, 0, size); + if (count < num) return -EFAULT; diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c index 042015bc8055..b2fd87834f23 100644 --- a/drivers/net/wireless/realtek/rtw88/fw.c +++ b/drivers/net/wireless/realtek/rtw88/fw.c @@ -1482,7 +1482,7 @@ static bool rtw_fw_dump_check_size(struct rtw_dev *rtwdev, int rtw_fw_dump_fifo(struct rtw_dev *rtwdev, u8 fifo_sel, u32 addr, u32 size, u32 *buffer) { - if (!rtwdev->chip->fw_fifo_addr) { + if (!rtwdev->chip->fw_fifo_addr[0]) { rtw_dbg(rtwdev, RTW_DBG_FW, "chip not support dump fw fifo\n"); return -ENOTSUPP; } diff --git a/drivers/nfc/s3fwrn5/i2c.c b/drivers/nfc/s3fwrn5/i2c.c index dc995286be84..d0a3bd9ff3c3 100644 --- a/drivers/nfc/s3fwrn5/i2c.c +++ b/drivers/nfc/s3fwrn5/i2c.c @@ -26,8 +26,8 @@ struct s3fwrn5_i2c_phy { struct i2c_client *i2c_dev; struct nci_dev *ndev; - unsigned int gpio_en; - unsigned int gpio_fw_wake; + int gpio_en; + int gpio_fw_wake; struct mutex mutex; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 40ca71b29bb9..9a270e49df17 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2060,8 +2060,6 @@ static void nvme_update_disk_info(struct gendisk *disk, if (id->nsattr & NVME_NS_ATTR_RO) set_disk_ro(disk, true); - else - set_disk_ro(disk, false); } static inline bool nvme_first_scan(struct gendisk *disk) @@ -2931,7 +2929,7 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi, static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi, struct nvme_effects_log **log) { - struct nvme_cel *cel = xa_load(&ctrl->cels, csi); + struct nvme_effects_log *cel = xa_load(&ctrl->cels, csi); int ret; if (cel) @@ -2942,16 +2940,15 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi, return -ENOMEM; ret = nvme_get_log(ctrl, 0x00, NVME_LOG_CMD_EFFECTS, 0, csi, - &cel->log, sizeof(cel->log), 0); + cel, sizeof(*cel), 0); if (ret) { kfree(cel); return ret; } - cel->csi = csi; - xa_store(&ctrl->cels, cel->csi, cel, GFP_KERNEL); + xa_store(&ctrl->cels, csi, cel, GFP_KERNEL); out: - *log = &cel->log; + *log = cel; return 0; } @@ -4376,6 +4373,19 @@ void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_uninit_ctrl); +static void nvme_free_cels(struct nvme_ctrl *ctrl) +{ + struct nvme_effects_log *cel; + unsigned long i; + + xa_for_each (&ctrl->cels, i, cel) { + xa_erase(&ctrl->cels, i); + kfree(cel); + } + + xa_destroy(&ctrl->cels); +} + static void nvme_free_ctrl(struct device *dev) { struct nvme_ctrl *ctrl = @@ -4385,8 +4395,7 @@ static void nvme_free_ctrl(struct device *dev) if (!subsys || ctrl->instance != subsys->instance) ida_simple_remove(&nvme_instance_ida, ctrl->instance); - xa_destroy(&ctrl->cels); - + nvme_free_cels(ctrl); nvme_mpath_uninit(ctrl); __free_page(ctrl->discard_page); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index bc330bf0d3bd..567f7ad18a91 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -226,12 +226,6 @@ struct nvme_fault_inject { #endif }; -struct nvme_cel { - struct list_head entry; - struct nvme_effects_log log; - u8 csi; -}; - struct nvme_ctrl { bool comp_seen; enum nvme_ctrl_state state; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 0578ff253c47..3be352403839 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -292,9 +292,21 @@ static void nvme_dbbuf_init(struct nvme_dev *dev, nvmeq->dbbuf_cq_ei = &dev->dbbuf_eis[cq_idx(qid, dev->db_stride)]; } +static void nvme_dbbuf_free(struct nvme_queue *nvmeq) +{ + if (!nvmeq->qid) + return; + + nvmeq->dbbuf_sq_db = NULL; + nvmeq->dbbuf_cq_db = NULL; + nvmeq->dbbuf_sq_ei = NULL; + nvmeq->dbbuf_cq_ei = NULL; +} + static void nvme_dbbuf_set(struct nvme_dev *dev) { struct nvme_command c; + unsigned int i; if (!dev->dbbuf_dbs) return; @@ -308,6 +320,9 @@ static void nvme_dbbuf_set(struct nvme_dev *dev) dev_warn(dev->ctrl.device, "unable to set dbbuf\n"); /* Free memory and continue on */ nvme_dbbuf_dma_free(dev); + + for (i = 1; i <= dev->online_queues; i++) + nvme_dbbuf_free(&dev->queues[i]); } } diff --git a/drivers/of/address.c b/drivers/of/address.c index eb9ab4f1e80b..1c3257a2d4e3 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -1034,11 +1034,13 @@ out: */ bool of_dma_is_coherent(struct device_node *np) { - struct device_node *node = of_node_get(np); + struct device_node *node; if (IS_ENABLED(CONFIG_OF_DMA_DEFAULT_COHERENT)) return true; + node = of_node_get(np); + while (node) { if (of_property_read_bool(node, "dma-coherent")) { of_node_put(node); diff --git a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c index 456dc4a100c2..e63457e145c7 100644 --- a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c +++ b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c @@ -270,11 +270,6 @@ static void usb_init_common_7211b0(struct brcm_usb_init_params *params) reg |= params->mode << USB_PHY_UTMI_CTL_1_PHY_MODE_SHIFT; brcm_usb_writel(reg, usb_phy + USB_PHY_UTMI_CTL_1); - /* Fix the incorrect default */ - reg = brcm_usb_readl(ctrl + USB_CTRL_SETUP); - reg &= ~USB_CTRL_SETUP_tca_drv_sel_MASK; - brcm_usb_writel(reg, ctrl + USB_CTRL_SETUP); - usb_init_common(params); /* diff --git a/drivers/phy/intel/Kconfig b/drivers/phy/intel/Kconfig index 58ec695c92ec..62c24764654b 100644 --- a/drivers/phy/intel/Kconfig +++ b/drivers/phy/intel/Kconfig @@ -4,7 +4,7 @@ # config PHY_INTEL_KEEMBAY_EMMC tristate "Intel Keem Bay EMMC PHY driver" - depends on (OF && ARM64) || COMPILE_TEST + depends on ARCH_KEEMBAY || COMPILE_TEST depends on HAS_IOMEM select GENERIC_PHY select REGMAP_MMIO diff --git a/drivers/phy/mediatek/Kconfig b/drivers/phy/mediatek/Kconfig index 50c5e9306e19..c8126bde9d7c 100644 --- a/drivers/phy/mediatek/Kconfig +++ b/drivers/phy/mediatek/Kconfig @@ -12,7 +12,7 @@ config PHY_MTK_TPHY it supports multiple usb2.0, usb3.0 ports, PCIe and SATA, and meanwhile supports two version T-PHY which have different banks layout, the T-PHY with shared banks between - multi-ports is first version, otherwise is second veriosn, + multi-ports is first version, otherwise is second version, so you can easily distinguish them by banks layout. config PHY_MTK_UFS diff --git a/drivers/phy/motorola/phy-cpcap-usb.c b/drivers/phy/motorola/phy-cpcap-usb.c index 089db0dea703..442522ba487f 100644 --- a/drivers/phy/motorola/phy-cpcap-usb.c +++ b/drivers/phy/motorola/phy-cpcap-usb.c @@ -364,7 +364,8 @@ static int cpcap_usb_init_irq(struct platform_device *pdev, error = devm_request_threaded_irq(ddata->dev, irq, NULL, cpcap_phy_irq_thread, - IRQF_SHARED, + IRQF_SHARED | + IRQF_ONESHOT, name, ddata); if (error) { dev_err(ddata->dev, "could not get irq %s: %i\n", diff --git a/drivers/phy/qualcomm/Kconfig b/drivers/phy/qualcomm/Kconfig index 928db510b86c..7f6fcb8ec5ba 100644 --- a/drivers/phy/qualcomm/Kconfig +++ b/drivers/phy/qualcomm/Kconfig @@ -87,7 +87,7 @@ config PHY_QCOM_USB_HSIC config PHY_QCOM_USB_HS_28NM tristate "Qualcomm 28nm High-Speed PHY" - depends on ARCH_QCOM || COMPILE_TEST + depends on OF && (ARCH_QCOM || COMPILE_TEST) depends on EXTCON || !EXTCON # if EXTCON=m, this cannot be built-in select GENERIC_PHY help @@ -98,7 +98,7 @@ config PHY_QCOM_USB_HS_28NM config PHY_QCOM_USB_SS tristate "Qualcomm USB Super-Speed PHY driver" - depends on ARCH_QCOM || COMPILE_TEST + depends on OF && (ARCH_QCOM || COMPILE_TEST) depends on EXTCON || !EXTCON # if EXTCON=m, this cannot be built-in select GENERIC_PHY help diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.c b/drivers/phy/qualcomm/phy-qcom-qmp.c index d361d0fee378..c651d31375cc 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp.c @@ -3927,7 +3927,7 @@ static int qcom_qmp_phy_probe(struct platform_device *pdev) struct phy_provider *phy_provider; void __iomem *serdes; void __iomem *usb_serdes; - void __iomem *dp_serdes; + void __iomem *dp_serdes = NULL; const struct qmp_phy_combo_cfg *combo_cfg = NULL; const struct qmp_phy_cfg *cfg = NULL; const struct qmp_phy_cfg *usb_cfg = NULL; diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index de4a46fe1763..ad88d74c1884 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -1242,6 +1242,7 @@ power_down: reset: reset_control_assert(padctl->rst); remove: + platform_set_drvdata(pdev, NULL); soc->ops->remove(padctl); return err; } diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c index 6a94eaecf638..9c65d560d48f 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c @@ -286,13 +286,76 @@ int aspeed_pinmux_set_mux(struct pinctrl_dev *pctldev, unsigned int function, static bool aspeed_expr_is_gpio(const struct aspeed_sig_expr *expr) { /* - * The signal type is GPIO if the signal name has "GPIO" as a prefix. - * strncmp (rather than strcmp) is used to implement the prefix - * requirement. + * We need to differentiate between GPIO and non-GPIO signals to + * implement the gpio_request_enable() interface. For better or worse + * the ASPEED pinctrl driver uses the expression names to determine + * whether an expression will mux a pin for GPIO. * - * expr->signal might look like "GPIOT3" in the GPIO case. + * Generally we have the following - A GPIO such as B1 has: + * + * - expr->signal set to "GPIOB1" + * - expr->function set to "GPIOB1" + * + * Using this fact we can determine whether the provided expression is + * a GPIO expression by testing the signal name for the string prefix + * "GPIO". + * + * However, some GPIOs are input-only, and the ASPEED datasheets name + * them differently. An input-only GPIO such as T0 has: + * + * - expr->signal set to "GPIT0" + * - expr->function set to "GPIT0" + * + * It's tempting to generalise the prefix test from "GPIO" to "GPI" to + * account for both GPIOs and GPIs, but in doing so we run aground on + * another feature: + * + * Some pins in the ASPEED BMC SoCs have a "pass-through" GPIO + * function where the input state of one pin is replicated as the + * output state of another (as if they were shorted together - a mux + * configuration that is typically enabled by hardware strapping). + * This feature allows the BMC to pass e.g. power button state through + * to the host while the BMC is yet to boot, but take control of the + * button state once the BMC has booted by muxing each pin as a + * separate, pin-specific GPIO. + * + * Conceptually this pass-through mode is a form of GPIO and is named + * as such in the datasheets, e.g. "GPID0". This naming similarity + * trips us up with the simple GPI-prefixed-signal-name scheme + * discussed above, as the pass-through configuration is not what we + * want when muxing a pin as GPIO for the GPIO subsystem. + * + * On e.g. the AST2400, a pass-through function "GPID0" is grouped on + * balls A18 and D16, where we have: + * + * For ball A18: + * - expr->signal set to "GPID0IN" + * - expr->function set to "GPID0" + * + * For ball D16: + * - expr->signal set to "GPID0OUT" + * - expr->function set to "GPID0" + * + * By contrast, the pin-specific GPIO expressions for the same pins are + * as follows: + * + * For ball A18: + * - expr->signal looks like "GPIOD0" + * - expr->function looks like "GPIOD0" + * + * For ball D16: + * - expr->signal looks like "GPIOD1" + * - expr->function looks like "GPIOD1" + * + * Testing both the signal _and_ function names gives us the means + * differentiate the pass-through GPIO pinmux configuration from the + * pin-specific configuration that the GPIO subsystem is after: An + * expression is a pin-specific (non-pass-through) GPIO configuration + * if the signal prefix is "GPI" and the signal name matches the + * function name. */ - return strncmp(expr->signal, "GPIO", 4) == 0; + return !strncmp(expr->signal, "GPI", 3) && + !strcmp(expr->signal, expr->function); } static bool aspeed_gpio_in_exprs(const struct aspeed_sig_expr **exprs) diff --git a/drivers/pinctrl/aspeed/pinmux-aspeed.h b/drivers/pinctrl/aspeed/pinmux-aspeed.h index f86739e800c3..dba5875ff276 100644 --- a/drivers/pinctrl/aspeed/pinmux-aspeed.h +++ b/drivers/pinctrl/aspeed/pinmux-aspeed.h @@ -452,10 +452,11 @@ struct aspeed_sig_desc { * evaluation of the descriptors. * * @signal: The signal name for the priority level on the pin. If the signal - * type is GPIO, then the signal name must begin with the string - * "GPIO", e.g. GPIOA0, GPIOT4 etc. + * type is GPIO, then the signal name must begin with the + * prefix "GPI", e.g. GPIOA0, GPIT0 etc. * @function: The name of the function the signal participates in for the - * associated expression + * associated expression. For pin-specific GPIO, the function + * name must match the signal name. * @ndescs: The number of signal descriptors in the expression * @descs: Pointer to an array of signal descriptors that comprise the * function expression diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index d49aab3cfbaa..394a421a19d5 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -1049,7 +1049,6 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev, break; case PIN_CONFIG_INPUT_DEBOUNCE: debounce = readl(db_reg); - debounce &= ~BYT_DEBOUNCE_PULSE_MASK; if (arg) conf |= BYT_DEBOUNCE_EN; @@ -1058,24 +1057,31 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev, switch (arg) { case 375: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_375US; break; case 750: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_750US; break; case 1500: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_1500US; break; case 3000: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_3MS; break; case 6000: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_6MS; break; case 12000: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_12MS; break; case 24000: + debounce &= ~BYT_DEBOUNCE_PULSE_MASK; debounce |= BYT_DEBOUNCE_PULSE_24MS; break; default: diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 154ce3f908cd..b6ef1911c1dd 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -62,10 +62,10 @@ #define PADCFG1_TERM_UP BIT(13) #define PADCFG1_TERM_SHIFT 10 #define PADCFG1_TERM_MASK GENMASK(12, 10) -#define PADCFG1_TERM_20K 4 -#define PADCFG1_TERM_2K 3 -#define PADCFG1_TERM_5K 2 -#define PADCFG1_TERM_1K 1 +#define PADCFG1_TERM_20K BIT(2) +#define PADCFG1_TERM_5K BIT(1) +#define PADCFG1_TERM_1K BIT(0) +#define PADCFG1_TERM_833 (BIT(1) | BIT(0)) #define PADCFG2 0x008 #define PADCFG2_DEBEN BIT(0) @@ -442,8 +442,8 @@ static void intel_gpio_set_gpio_mode(void __iomem *padcfg0) value |= PADCFG0_PMODE_GPIO; /* Disable input and output buffers */ - value &= ~PADCFG0_GPIORXDIS; - value &= ~PADCFG0_GPIOTXDIS; + value |= PADCFG0_GPIORXDIS; + value |= PADCFG0_GPIOTXDIS; /* Disable SCI/SMI/NMI generation */ value &= ~(PADCFG0_GPIROUTIOXAPIC | PADCFG0_GPIROUTSCI); @@ -549,12 +549,12 @@ static int intel_config_get_pull(struct intel_pinctrl *pctrl, unsigned int pin, return -EINVAL; switch (term) { + case PADCFG1_TERM_833: + *arg = 833; + break; case PADCFG1_TERM_1K: *arg = 1000; break; - case PADCFG1_TERM_2K: - *arg = 2000; - break; case PADCFG1_TERM_5K: *arg = 5000; break; @@ -570,6 +570,11 @@ static int intel_config_get_pull(struct intel_pinctrl *pctrl, unsigned int pin, return -EINVAL; switch (term) { + case PADCFG1_TERM_833: + if (!(community->features & PINCTRL_FEATURE_1K_PD)) + return -EINVAL; + *arg = 833; + break; case PADCFG1_TERM_1K: if (!(community->features & PINCTRL_FEATURE_1K_PD)) return -EINVAL; @@ -678,6 +683,10 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin, value |= PADCFG1_TERM_UP; + /* Set default strength value in case none is given */ + if (arg == 1) + arg = 5000; + switch (arg) { case 20000: value |= PADCFG1_TERM_20K << PADCFG1_TERM_SHIFT; @@ -685,12 +694,12 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin, case 5000: value |= PADCFG1_TERM_5K << PADCFG1_TERM_SHIFT; break; - case 2000: - value |= PADCFG1_TERM_2K << PADCFG1_TERM_SHIFT; - break; case 1000: value |= PADCFG1_TERM_1K << PADCFG1_TERM_SHIFT; break; + case 833: + value |= PADCFG1_TERM_833 << PADCFG1_TERM_SHIFT; + break; default: ret = -EINVAL; } @@ -700,6 +709,10 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin, case PIN_CONFIG_BIAS_PULL_DOWN: value &= ~(PADCFG1_TERM_UP | PADCFG1_TERM_MASK); + /* Set default strength value in case none is given */ + if (arg == 1) + arg = 5000; + switch (arg) { case 20000: value |= PADCFG1_TERM_20K << PADCFG1_TERM_SHIFT; @@ -714,6 +727,13 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin, } value |= PADCFG1_TERM_1K << PADCFG1_TERM_SHIFT; break; + case 833: + if (!(community->features & PINCTRL_FEATURE_1K_PD)) { + ret = -EINVAL; + break; + } + value |= PADCFG1_TERM_833 << PADCFG1_TERM_SHIFT; + break; default: ret = -EINVAL; } diff --git a/drivers/pinctrl/intel/pinctrl-jasperlake.c b/drivers/pinctrl/intel/pinctrl-jasperlake.c index 9bd0e8e6310c..ec435b7ab392 100644 --- a/drivers/pinctrl/intel/pinctrl-jasperlake.c +++ b/drivers/pinctrl/intel/pinctrl-jasperlake.c @@ -16,7 +16,7 @@ #define JSL_PAD_OWN 0x020 #define JSL_PADCFGLOCK 0x080 -#define JSL_HOSTSW_OWN 0x0b0 +#define JSL_HOSTSW_OWN 0x0c0 #define JSL_GPI_IS 0x100 #define JSL_GPI_IE 0x120 @@ -65,252 +65,263 @@ static const struct pinctrl_pin_desc jsl_pins[] = { PINCTRL_PIN(17, "EMMC_CLK"), PINCTRL_PIN(18, "EMMC_RESETB"), PINCTRL_PIN(19, "A4WP_PRESENT"), + /* SPI */ + PINCTRL_PIN(20, "SPI0_IO_2"), + PINCTRL_PIN(21, "SPI0_IO_3"), + PINCTRL_PIN(22, "SPI0_MOSI_IO_0"), + PINCTRL_PIN(23, "SPI0_MISO_IO_1"), + PINCTRL_PIN(24, "SPI0_TPM_CSB"), + PINCTRL_PIN(25, "SPI0_FLASH_0_CSB"), + PINCTRL_PIN(26, "SPI0_FLASH_1_CSB"), + PINCTRL_PIN(27, "SPI0_CLK"), + PINCTRL_PIN(28, "SPI0_CLK_LOOPBK"), /* GPP_B */ - PINCTRL_PIN(20, "CORE_VID_0"), - PINCTRL_PIN(21, "CORE_VID_1"), - PINCTRL_PIN(22, "VRALERTB"), - PINCTRL_PIN(23, "CPU_GP_2"), - PINCTRL_PIN(24, "CPU_GP_3"), - PINCTRL_PIN(25, "SRCCLKREQB_0"), - PINCTRL_PIN(26, "SRCCLKREQB_1"), - PINCTRL_PIN(27, "SRCCLKREQB_2"), - PINCTRL_PIN(28, "SRCCLKREQB_3"), - PINCTRL_PIN(29, "SRCCLKREQB_4"), - PINCTRL_PIN(30, "SRCCLKREQB_5"), - PINCTRL_PIN(31, "PMCALERTB"), - PINCTRL_PIN(32, "SLP_S0B"), - PINCTRL_PIN(33, "PLTRSTB"), - PINCTRL_PIN(34, "SPKR"), - PINCTRL_PIN(35, "GSPI0_CS0B"), - PINCTRL_PIN(36, "GSPI0_CLK"), - PINCTRL_PIN(37, "GSPI0_MISO"), - PINCTRL_PIN(38, "GSPI0_MOSI"), - PINCTRL_PIN(39, "GSPI1_CS0B"), - PINCTRL_PIN(40, "GSPI1_CLK"), - PINCTRL_PIN(41, "GSPI1_MISO"), - PINCTRL_PIN(42, "GSPI1_MOSI"), - PINCTRL_PIN(43, "DDSP_HPD_A"), - PINCTRL_PIN(44, "GSPI0_CLK_LOOPBK"), - PINCTRL_PIN(45, "GSPI1_CLK_LOOPBK"), + PINCTRL_PIN(29, "CORE_VID_0"), + PINCTRL_PIN(30, "CORE_VID_1"), + PINCTRL_PIN(31, "VRALERTB"), + PINCTRL_PIN(32, "CPU_GP_2"), + PINCTRL_PIN(33, "CPU_GP_3"), + PINCTRL_PIN(34, "SRCCLKREQB_0"), + PINCTRL_PIN(35, "SRCCLKREQB_1"), + PINCTRL_PIN(36, "SRCCLKREQB_2"), + PINCTRL_PIN(37, "SRCCLKREQB_3"), + PINCTRL_PIN(38, "SRCCLKREQB_4"), + PINCTRL_PIN(39, "SRCCLKREQB_5"), + PINCTRL_PIN(40, "PMCALERTB"), + PINCTRL_PIN(41, "SLP_S0B"), + PINCTRL_PIN(42, "PLTRSTB"), + PINCTRL_PIN(43, "SPKR"), + PINCTRL_PIN(44, "GSPI0_CS0B"), + PINCTRL_PIN(45, "GSPI0_CLK"), + PINCTRL_PIN(46, "GSPI0_MISO"), + PINCTRL_PIN(47, "GSPI0_MOSI"), + PINCTRL_PIN(48, "GSPI1_CS0B"), + PINCTRL_PIN(49, "GSPI1_CLK"), + PINCTRL_PIN(50, "GSPI1_MISO"), + PINCTRL_PIN(51, "GSPI1_MOSI"), + PINCTRL_PIN(52, "DDSP_HPD_A"), + PINCTRL_PIN(53, "GSPI0_CLK_LOOPBK"), + PINCTRL_PIN(54, "GSPI1_CLK_LOOPBK"), /* GPP_A */ - PINCTRL_PIN(46, "ESPI_IO_0"), - PINCTRL_PIN(47, "ESPI_IO_1"), - PINCTRL_PIN(48, "ESPI_IO_2"), - PINCTRL_PIN(49, "ESPI_IO_3"), - PINCTRL_PIN(50, "ESPI_CSB"), - PINCTRL_PIN(51, "ESPI_CLK"), - PINCTRL_PIN(52, "ESPI_RESETB"), - PINCTRL_PIN(53, "SMBCLK"), - PINCTRL_PIN(54, "SMBDATA"), - PINCTRL_PIN(55, "SMBALERTB"), - PINCTRL_PIN(56, "CPU_GP_0"), - PINCTRL_PIN(57, "CPU_GP_1"), - PINCTRL_PIN(58, "USB2_OCB_1"), - PINCTRL_PIN(59, "USB2_OCB_2"), - PINCTRL_PIN(60, "USB2_OCB_3"), - PINCTRL_PIN(61, "DDSP_HPD_A_TIME_SYNC_0"), - PINCTRL_PIN(62, "DDSP_HPD_B"), - PINCTRL_PIN(63, "DDSP_HPD_C"), - PINCTRL_PIN(64, "USB2_OCB_0"), - PINCTRL_PIN(65, "PCHHOTB"), - PINCTRL_PIN(66, "ESPI_CLK_LOOPBK"), + PINCTRL_PIN(55, "ESPI_IO_0"), + PINCTRL_PIN(56, "ESPI_IO_1"), + PINCTRL_PIN(57, "ESPI_IO_2"), + PINCTRL_PIN(58, "ESPI_IO_3"), + PINCTRL_PIN(59, "ESPI_CSB"), + PINCTRL_PIN(60, "ESPI_CLK"), + PINCTRL_PIN(61, "ESPI_RESETB"), + PINCTRL_PIN(62, "SMBCLK"), + PINCTRL_PIN(63, "SMBDATA"), + PINCTRL_PIN(64, "SMBALERTB"), + PINCTRL_PIN(65, "CPU_GP_0"), + PINCTRL_PIN(66, "CPU_GP_1"), + PINCTRL_PIN(67, "USB2_OCB_1"), + PINCTRL_PIN(68, "USB2_OCB_2"), + PINCTRL_PIN(69, "USB2_OCB_3"), + PINCTRL_PIN(70, "DDSP_HPD_A_TIME_SYNC_0"), + PINCTRL_PIN(71, "DDSP_HPD_B"), + PINCTRL_PIN(72, "DDSP_HPD_C"), + PINCTRL_PIN(73, "USB2_OCB_0"), + PINCTRL_PIN(74, "PCHHOTB"), + PINCTRL_PIN(75, "ESPI_CLK_LOOPBK"), /* GPP_S */ - PINCTRL_PIN(67, "SNDW1_CLK"), - PINCTRL_PIN(68, "SNDW1_DATA"), - PINCTRL_PIN(69, "SNDW2_CLK"), - PINCTRL_PIN(70, "SNDW2_DATA"), - PINCTRL_PIN(71, "SNDW1_CLK"), - PINCTRL_PIN(72, "SNDW1_DATA"), - PINCTRL_PIN(73, "SNDW4_CLK_DMIC_CLK_0"), - PINCTRL_PIN(74, "SNDW4_DATA_DMIC_DATA_0"), + PINCTRL_PIN(76, "SNDW1_CLK"), + PINCTRL_PIN(77, "SNDW1_DATA"), + PINCTRL_PIN(78, "SNDW2_CLK"), + PINCTRL_PIN(79, "SNDW2_DATA"), + PINCTRL_PIN(80, "SNDW1_CLK"), + PINCTRL_PIN(81, "SNDW1_DATA"), + PINCTRL_PIN(82, "SNDW4_CLK_DMIC_CLK_0"), + PINCTRL_PIN(83, "SNDW4_DATA_DMIC_DATA_0"), /* GPP_R */ - PINCTRL_PIN(75, "HDA_BCLK"), - PINCTRL_PIN(76, "HDA_SYNC"), - PINCTRL_PIN(77, "HDA_SDO"), - PINCTRL_PIN(78, "HDA_SDI_0"), - PINCTRL_PIN(79, "HDA_RSTB"), - PINCTRL_PIN(80, "HDA_SDI_1"), - PINCTRL_PIN(81, "I2S1_SFRM"), - PINCTRL_PIN(82, "I2S1_TXD"), + PINCTRL_PIN(84, "HDA_BCLK"), + PINCTRL_PIN(85, "HDA_SYNC"), + PINCTRL_PIN(86, "HDA_SDO"), + PINCTRL_PIN(87, "HDA_SDI_0"), + PINCTRL_PIN(88, "HDA_RSTB"), + PINCTRL_PIN(89, "HDA_SDI_1"), + PINCTRL_PIN(90, "I2S1_SFRM"), + PINCTRL_PIN(91, "I2S1_TXD"), /* GPP_H */ - PINCTRL_PIN(83, "GPPC_H_0"), - PINCTRL_PIN(84, "SD_PWR_EN_B"), - PINCTRL_PIN(85, "MODEM_CLKREQ"), - PINCTRL_PIN(86, "SX_EXIT_HOLDOFFB"), - PINCTRL_PIN(87, "I2C2_SDA"), - PINCTRL_PIN(88, "I2C2_SCL"), - PINCTRL_PIN(89, "I2C3_SDA"), - PINCTRL_PIN(90, "I2C3_SCL"), - PINCTRL_PIN(91, "I2C4_SDA"), - PINCTRL_PIN(92, "I2C4_SCL"), - PINCTRL_PIN(93, "CPU_VCCIO_PWR_GATEB"), - PINCTRL_PIN(94, "I2S2_SCLK"), - PINCTRL_PIN(95, "I2S2_SFRM"), - PINCTRL_PIN(96, "I2S2_TXD"), - PINCTRL_PIN(97, "I2S2_RXD"), - PINCTRL_PIN(98, "I2S1_SCLK"), - PINCTRL_PIN(99, "GPPC_H_16"), - PINCTRL_PIN(100, "GPPC_H_17"), - PINCTRL_PIN(101, "GPPC_H_18"), - PINCTRL_PIN(102, "GPPC_H_19"), - PINCTRL_PIN(103, "GPPC_H_20"), - PINCTRL_PIN(104, "GPPC_H_21"), - PINCTRL_PIN(105, "GPPC_H_22"), - PINCTRL_PIN(106, "GPPC_H_23"), + PINCTRL_PIN(92, "GPPC_H_0"), + PINCTRL_PIN(93, "SD_PWR_EN_B"), + PINCTRL_PIN(94, "MODEM_CLKREQ"), + PINCTRL_PIN(95, "SX_EXIT_HOLDOFFB"), + PINCTRL_PIN(96, "I2C2_SDA"), + PINCTRL_PIN(97, "I2C2_SCL"), + PINCTRL_PIN(98, "I2C3_SDA"), + PINCTRL_PIN(99, "I2C3_SCL"), + PINCTRL_PIN(100, "I2C4_SDA"), + PINCTRL_PIN(101, "I2C4_SCL"), + PINCTRL_PIN(102, "CPU_VCCIO_PWR_GATEB"), + PINCTRL_PIN(103, "I2S2_SCLK"), + PINCTRL_PIN(104, "I2S2_SFRM"), + PINCTRL_PIN(105, "I2S2_TXD"), + PINCTRL_PIN(106, "I2S2_RXD"), + PINCTRL_PIN(107, "I2S1_SCLK"), + PINCTRL_PIN(108, "GPPC_H_16"), + PINCTRL_PIN(109, "GPPC_H_17"), + PINCTRL_PIN(110, "GPPC_H_18"), + PINCTRL_PIN(111, "GPPC_H_19"), + PINCTRL_PIN(112, "GPPC_H_20"), + PINCTRL_PIN(113, "GPPC_H_21"), + PINCTRL_PIN(114, "GPPC_H_22"), + PINCTRL_PIN(115, "GPPC_H_23"), /* GPP_D */ - PINCTRL_PIN(107, "SPI1_CSB"), - PINCTRL_PIN(108, "SPI1_CLK"), - PINCTRL_PIN(109, "SPI1_MISO_IO_1"), - PINCTRL_PIN(110, "SPI1_MOSI_IO_0"), - PINCTRL_PIN(111, "ISH_I2C0_SDA"), - PINCTRL_PIN(112, "ISH_I2C0_SCL"), - PINCTRL_PIN(113, "ISH_I2C1_SDA"), - PINCTRL_PIN(114, "ISH_I2C1_SCL"), - PINCTRL_PIN(115, "ISH_SPI_CSB"), - PINCTRL_PIN(116, "ISH_SPI_CLK"), - PINCTRL_PIN(117, "ISH_SPI_MISO"), - PINCTRL_PIN(118, "ISH_SPI_MOSI"), - PINCTRL_PIN(119, "ISH_UART0_RXD"), - PINCTRL_PIN(120, "ISH_UART0_TXD"), - PINCTRL_PIN(121, "ISH_UART0_RTSB"), - PINCTRL_PIN(122, "ISH_UART0_CTSB"), - PINCTRL_PIN(123, "SPI1_IO_2"), - PINCTRL_PIN(124, "SPI1_IO_3"), - PINCTRL_PIN(125, "I2S_MCLK"), - PINCTRL_PIN(126, "CNV_MFUART2_RXD"), - PINCTRL_PIN(127, "CNV_MFUART2_TXD"), - PINCTRL_PIN(128, "CNV_PA_BLANKING"), - PINCTRL_PIN(129, "I2C5_SDA"), - PINCTRL_PIN(130, "I2C5_SCL"), - PINCTRL_PIN(131, "GSPI2_CLK_LOOPBK"), - PINCTRL_PIN(132, "SPI1_CLK_LOOPBK"), + PINCTRL_PIN(116, "SPI1_CSB"), + PINCTRL_PIN(117, "SPI1_CLK"), + PINCTRL_PIN(118, "SPI1_MISO_IO_1"), + PINCTRL_PIN(119, "SPI1_MOSI_IO_0"), + PINCTRL_PIN(120, "ISH_I2C0_SDA"), + PINCTRL_PIN(121, "ISH_I2C0_SCL"), + PINCTRL_PIN(122, "ISH_I2C1_SDA"), + PINCTRL_PIN(123, "ISH_I2C1_SCL"), + PINCTRL_PIN(124, "ISH_SPI_CSB"), + PINCTRL_PIN(125, "ISH_SPI_CLK"), + PINCTRL_PIN(126, "ISH_SPI_MISO"), + PINCTRL_PIN(127, "ISH_SPI_MOSI"), + PINCTRL_PIN(128, "ISH_UART0_RXD"), + PINCTRL_PIN(129, "ISH_UART0_TXD"), + PINCTRL_PIN(130, "ISH_UART0_RTSB"), + PINCTRL_PIN(131, "ISH_UART0_CTSB"), + PINCTRL_PIN(132, "SPI1_IO_2"), + PINCTRL_PIN(133, "SPI1_IO_3"), + PINCTRL_PIN(134, "I2S_MCLK"), + PINCTRL_PIN(135, "CNV_MFUART2_RXD"), + PINCTRL_PIN(136, "CNV_MFUART2_TXD"), + PINCTRL_PIN(137, "CNV_PA_BLANKING"), + PINCTRL_PIN(138, "I2C5_SDA"), + PINCTRL_PIN(139, "I2C5_SCL"), + PINCTRL_PIN(140, "GSPI2_CLK_LOOPBK"), + PINCTRL_PIN(141, "SPI1_CLK_LOOPBK"), /* vGPIO */ - PINCTRL_PIN(133, "CNV_BTEN"), - PINCTRL_PIN(134, "CNV_WCEN"), - PINCTRL_PIN(135, "CNV_BT_HOST_WAKEB"), - PINCTRL_PIN(136, "CNV_BT_IF_SELECT"), - PINCTRL_PIN(137, "vCNV_BT_UART_TXD"), - PINCTRL_PIN(138, "vCNV_BT_UART_RXD"), - PINCTRL_PIN(139, "vCNV_BT_UART_CTS_B"), - PINCTRL_PIN(140, "vCNV_BT_UART_RTS_B"), - PINCTRL_PIN(141, "vCNV_MFUART1_TXD"), - PINCTRL_PIN(142, "vCNV_MFUART1_RXD"), - PINCTRL_PIN(143, "vCNV_MFUART1_CTS_B"), - PINCTRL_PIN(144, "vCNV_MFUART1_RTS_B"), - PINCTRL_PIN(145, "vUART0_TXD"), - PINCTRL_PIN(146, "vUART0_RXD"), - PINCTRL_PIN(147, "vUART0_CTS_B"), - PINCTRL_PIN(148, "vUART0_RTS_B"), - PINCTRL_PIN(149, "vISH_UART0_TXD"), - PINCTRL_PIN(150, "vISH_UART0_RXD"), - PINCTRL_PIN(151, "vISH_UART0_CTS_B"), - PINCTRL_PIN(152, "vISH_UART0_RTS_B"), - PINCTRL_PIN(153, "vCNV_BT_I2S_BCLK"), - PINCTRL_PIN(154, "vCNV_BT_I2S_WS_SYNC"), - PINCTRL_PIN(155, "vCNV_BT_I2S_SDO"), - PINCTRL_PIN(156, "vCNV_BT_I2S_SDI"), - PINCTRL_PIN(157, "vI2S2_SCLK"), - PINCTRL_PIN(158, "vI2S2_SFRM"), - PINCTRL_PIN(159, "vI2S2_TXD"), - PINCTRL_PIN(160, "vI2S2_RXD"), - PINCTRL_PIN(161, "vSD3_CD_B"), + PINCTRL_PIN(142, "CNV_BTEN"), + PINCTRL_PIN(143, "CNV_WCEN"), + PINCTRL_PIN(144, "CNV_BT_HOST_WAKEB"), + PINCTRL_PIN(145, "CNV_BT_IF_SELECT"), + PINCTRL_PIN(146, "vCNV_BT_UART_TXD"), + PINCTRL_PIN(147, "vCNV_BT_UART_RXD"), + PINCTRL_PIN(148, "vCNV_BT_UART_CTS_B"), + PINCTRL_PIN(149, "vCNV_BT_UART_RTS_B"), + PINCTRL_PIN(150, "vCNV_MFUART1_TXD"), + PINCTRL_PIN(151, "vCNV_MFUART1_RXD"), + PINCTRL_PIN(152, "vCNV_MFUART1_CTS_B"), + PINCTRL_PIN(153, "vCNV_MFUART1_RTS_B"), + PINCTRL_PIN(154, "vUART0_TXD"), + PINCTRL_PIN(155, "vUART0_RXD"), + PINCTRL_PIN(156, "vUART0_CTS_B"), + PINCTRL_PIN(157, "vUART0_RTS_B"), + PINCTRL_PIN(158, "vISH_UART0_TXD"), + PINCTRL_PIN(159, "vISH_UART0_RXD"), + PINCTRL_PIN(160, "vISH_UART0_CTS_B"), + PINCTRL_PIN(161, "vISH_UART0_RTS_B"), + PINCTRL_PIN(162, "vCNV_BT_I2S_BCLK"), + PINCTRL_PIN(163, "vCNV_BT_I2S_WS_SYNC"), + PINCTRL_PIN(164, "vCNV_BT_I2S_SDO"), + PINCTRL_PIN(165, "vCNV_BT_I2S_SDI"), + PINCTRL_PIN(166, "vI2S2_SCLK"), + PINCTRL_PIN(167, "vI2S2_SFRM"), + PINCTRL_PIN(168, "vI2S2_TXD"), + PINCTRL_PIN(169, "vI2S2_RXD"), + PINCTRL_PIN(170, "vSD3_CD_B"), /* GPP_C */ - PINCTRL_PIN(162, "GPPC_C_0"), - PINCTRL_PIN(163, "GPPC_C_1"), - PINCTRL_PIN(164, "GPPC_C_2"), - PINCTRL_PIN(165, "GPPC_C_3"), - PINCTRL_PIN(166, "GPPC_C_4"), - PINCTRL_PIN(167, "GPPC_C_5"), - PINCTRL_PIN(168, "SUSWARNB_SUSPWRDNACK"), - PINCTRL_PIN(169, "SUSACKB"), - PINCTRL_PIN(170, "UART0_RXD"), - PINCTRL_PIN(171, "UART0_TXD"), - PINCTRL_PIN(172, "UART0_RTSB"), - PINCTRL_PIN(173, "UART0_CTSB"), - PINCTRL_PIN(174, "UART1_RXD"), - PINCTRL_PIN(175, "UART1_TXD"), - PINCTRL_PIN(176, "UART1_RTSB"), - PINCTRL_PIN(177, "UART1_CTSB"), - PINCTRL_PIN(178, "I2C0_SDA"), - PINCTRL_PIN(179, "I2C0_SCL"), - PINCTRL_PIN(180, "I2C1_SDA"), - PINCTRL_PIN(181, "I2C1_SCL"), - PINCTRL_PIN(182, "UART2_RXD"), - PINCTRL_PIN(183, "UART2_TXD"), - PINCTRL_PIN(184, "UART2_RTSB"), - PINCTRL_PIN(185, "UART2_CTSB"), + PINCTRL_PIN(171, "GPPC_C_0"), + PINCTRL_PIN(172, "GPPC_C_1"), + PINCTRL_PIN(173, "GPPC_C_2"), + PINCTRL_PIN(174, "GPPC_C_3"), + PINCTRL_PIN(175, "GPPC_C_4"), + PINCTRL_PIN(176, "GPPC_C_5"), + PINCTRL_PIN(177, "SUSWARNB_SUSPWRDNACK"), + PINCTRL_PIN(178, "SUSACKB"), + PINCTRL_PIN(179, "UART0_RXD"), + PINCTRL_PIN(180, "UART0_TXD"), + PINCTRL_PIN(181, "UART0_RTSB"), + PINCTRL_PIN(182, "UART0_CTSB"), + PINCTRL_PIN(183, "UART1_RXD"), + PINCTRL_PIN(184, "UART1_TXD"), + PINCTRL_PIN(185, "UART1_RTSB"), + PINCTRL_PIN(186, "UART1_CTSB"), + PINCTRL_PIN(187, "I2C0_SDA"), + PINCTRL_PIN(188, "I2C0_SCL"), + PINCTRL_PIN(189, "I2C1_SDA"), + PINCTRL_PIN(190, "I2C1_SCL"), + PINCTRL_PIN(191, "UART2_RXD"), + PINCTRL_PIN(192, "UART2_TXD"), + PINCTRL_PIN(193, "UART2_RTSB"), + PINCTRL_PIN(194, "UART2_CTSB"), /* HVCMOS */ - PINCTRL_PIN(186, "L_BKLTEN"), - PINCTRL_PIN(187, "L_BKLTCTL"), - PINCTRL_PIN(188, "L_VDDEN"), - PINCTRL_PIN(189, "SYS_PWROK"), - PINCTRL_PIN(190, "SYS_RESETB"), - PINCTRL_PIN(191, "MLK_RSTB"), + PINCTRL_PIN(195, "L_BKLTEN"), + PINCTRL_PIN(196, "L_BKLTCTL"), + PINCTRL_PIN(197, "L_VDDEN"), + PINCTRL_PIN(198, "SYS_PWROK"), + PINCTRL_PIN(199, "SYS_RESETB"), + PINCTRL_PIN(200, "MLK_RSTB"), /* GPP_E */ - PINCTRL_PIN(192, "ISH_GP_0"), - PINCTRL_PIN(193, "ISH_GP_1"), - PINCTRL_PIN(194, "IMGCLKOUT_1"), - PINCTRL_PIN(195, "ISH_GP_2"), - PINCTRL_PIN(196, "IMGCLKOUT_2"), - PINCTRL_PIN(197, "SATA_LEDB"), - PINCTRL_PIN(198, "IMGCLKOUT_3"), - PINCTRL_PIN(199, "ISH_GP_3"), - PINCTRL_PIN(200, "ISH_GP_4"), - PINCTRL_PIN(201, "ISH_GP_5"), - PINCTRL_PIN(202, "ISH_GP_6"), - PINCTRL_PIN(203, "ISH_GP_7"), - PINCTRL_PIN(204, "IMGCLKOUT_4"), - PINCTRL_PIN(205, "DDPA_CTRLCLK"), - PINCTRL_PIN(206, "DDPA_CTRLDATA"), - PINCTRL_PIN(207, "DDPB_CTRLCLK"), - PINCTRL_PIN(208, "DDPB_CTRLDATA"), - PINCTRL_PIN(209, "DDPC_CTRLCLK"), - PINCTRL_PIN(210, "DDPC_CTRLDATA"), - PINCTRL_PIN(211, "IMGCLKOUT_5"), - PINCTRL_PIN(212, "CNV_BRI_DT"), - PINCTRL_PIN(213, "CNV_BRI_RSP"), - PINCTRL_PIN(214, "CNV_RGI_DT"), - PINCTRL_PIN(215, "CNV_RGI_RSP"), + PINCTRL_PIN(201, "ISH_GP_0"), + PINCTRL_PIN(202, "ISH_GP_1"), + PINCTRL_PIN(203, "IMGCLKOUT_1"), + PINCTRL_PIN(204, "ISH_GP_2"), + PINCTRL_PIN(205, "IMGCLKOUT_2"), + PINCTRL_PIN(206, "SATA_LEDB"), + PINCTRL_PIN(207, "IMGCLKOUT_3"), + PINCTRL_PIN(208, "ISH_GP_3"), + PINCTRL_PIN(209, "ISH_GP_4"), + PINCTRL_PIN(210, "ISH_GP_5"), + PINCTRL_PIN(211, "ISH_GP_6"), + PINCTRL_PIN(212, "ISH_GP_7"), + PINCTRL_PIN(213, "IMGCLKOUT_4"), + PINCTRL_PIN(214, "DDPA_CTRLCLK"), + PINCTRL_PIN(215, "DDPA_CTRLDATA"), + PINCTRL_PIN(216, "DDPB_CTRLCLK"), + PINCTRL_PIN(217, "DDPB_CTRLDATA"), + PINCTRL_PIN(218, "DDPC_CTRLCLK"), + PINCTRL_PIN(219, "DDPC_CTRLDATA"), + PINCTRL_PIN(220, "IMGCLKOUT_5"), + PINCTRL_PIN(221, "CNV_BRI_DT"), + PINCTRL_PIN(222, "CNV_BRI_RSP"), + PINCTRL_PIN(223, "CNV_RGI_DT"), + PINCTRL_PIN(224, "CNV_RGI_RSP"), /* GPP_G */ - PINCTRL_PIN(216, "SD3_CMD"), - PINCTRL_PIN(217, "SD3_D0"), - PINCTRL_PIN(218, "SD3_D1"), - PINCTRL_PIN(219, "SD3_D2"), - PINCTRL_PIN(220, "SD3_D3"), - PINCTRL_PIN(221, "SD3_CDB"), - PINCTRL_PIN(222, "SD3_CLK"), - PINCTRL_PIN(223, "SD3_WP"), + PINCTRL_PIN(225, "SD3_CMD"), + PINCTRL_PIN(226, "SD3_D0"), + PINCTRL_PIN(227, "SD3_D1"), + PINCTRL_PIN(228, "SD3_D2"), + PINCTRL_PIN(229, "SD3_D3"), + PINCTRL_PIN(230, "SD3_CDB"), + PINCTRL_PIN(231, "SD3_CLK"), + PINCTRL_PIN(232, "SD3_WP"), }; static const struct intel_padgroup jsl_community0_gpps[] = { JSL_GPP(0, 0, 19, 320), /* GPP_F */ - JSL_GPP(1, 20, 45, 32), /* GPP_B */ - JSL_GPP(2, 46, 66, 64), /* GPP_A */ - JSL_GPP(3, 67, 74, 96), /* GPP_S */ - JSL_GPP(4, 75, 82, 128), /* GPP_R */ + JSL_GPP(1, 20, 28, INTEL_GPIO_BASE_NOMAP), /* SPI */ + JSL_GPP(2, 29, 54, 32), /* GPP_B */ + JSL_GPP(3, 55, 75, 64), /* GPP_A */ + JSL_GPP(4, 76, 83, 96), /* GPP_S */ + JSL_GPP(5, 84, 91, 128), /* GPP_R */ }; static const struct intel_padgroup jsl_community1_gpps[] = { - JSL_GPP(0, 83, 106, 160), /* GPP_H */ - JSL_GPP(1, 107, 132, 192), /* GPP_D */ - JSL_GPP(2, 133, 161, 224), /* vGPIO */ - JSL_GPP(3, 162, 185, 256), /* GPP_C */ + JSL_GPP(0, 92, 115, 160), /* GPP_H */ + JSL_GPP(1, 116, 141, 192), /* GPP_D */ + JSL_GPP(2, 142, 170, 224), /* vGPIO */ + JSL_GPP(3, 171, 194, 256), /* GPP_C */ }; static const struct intel_padgroup jsl_community4_gpps[] = { - JSL_GPP(0, 186, 191, INTEL_GPIO_BASE_NOMAP), /* HVCMOS */ - JSL_GPP(1, 192, 215, 288), /* GPP_E */ + JSL_GPP(0, 195, 200, INTEL_GPIO_BASE_NOMAP), /* HVCMOS */ + JSL_GPP(1, 201, 224, 288), /* GPP_E */ }; static const struct intel_padgroup jsl_community5_gpps[] = { - JSL_GPP(0, 216, 223, INTEL_GPIO_BASE_ZERO), /* GPP_G */ + JSL_GPP(0, 225, 232, INTEL_GPIO_BASE_ZERO), /* GPP_G */ }; static const struct intel_community jsl_communities[] = { - JSL_COMMUNITY(0, 0, 82, jsl_community0_gpps), - JSL_COMMUNITY(1, 83, 185, jsl_community1_gpps), - JSL_COMMUNITY(2, 186, 215, jsl_community4_gpps), - JSL_COMMUNITY(3, 216, 223, jsl_community5_gpps), + JSL_COMMUNITY(0, 0, 91, jsl_community0_gpps), + JSL_COMMUNITY(1, 92, 194, jsl_community1_gpps), + JSL_COMMUNITY(2, 195, 224, jsl_community4_gpps), + JSL_COMMUNITY(3, 225, 232, jsl_community5_gpps), }; static const struct intel_pinctrl_soc_data jsl_soc_data = { @@ -336,7 +347,6 @@ static struct platform_driver jsl_pinctrl_driver = { .pm = &jsl_pinctrl_pm_ops, }, }; - module_platform_driver(jsl_pinctrl_driver); MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>"); diff --git a/drivers/pinctrl/intel/pinctrl-merrifield.c b/drivers/pinctrl/intel/pinctrl-merrifield.c index e4ff8da1b894..3ae141e0b421 100644 --- a/drivers/pinctrl/intel/pinctrl-merrifield.c +++ b/drivers/pinctrl/intel/pinctrl-merrifield.c @@ -745,6 +745,10 @@ static int mrfld_config_set_pin(struct mrfld_pinctrl *mp, unsigned int pin, mask |= BUFCFG_Px_EN_MASK | BUFCFG_PUPD_VAL_MASK; bits |= BUFCFG_PU_EN; + /* Set default strength value in case none is given */ + if (arg == 1) + arg = 20000; + switch (arg) { case 50000: bits |= BUFCFG_PUPD_VAL_50K << BUFCFG_PUPD_VAL_SHIFT; @@ -765,6 +769,10 @@ static int mrfld_config_set_pin(struct mrfld_pinctrl *mp, unsigned int pin, mask |= BUFCFG_Px_EN_MASK | BUFCFG_PUPD_VAL_MASK; bits |= BUFCFG_PD_EN; + /* Set default strength value in case none is given */ + if (arg == 1) + arg = 20000; + switch (arg) { case 50000: bits |= BUFCFG_PUPD_VAL_50K << BUFCFG_PUPD_VAL_SHIFT; diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 9a760f5cd7ed..899c16c17b6d 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -156,7 +156,7 @@ static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset, pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF); pin_reg &= ~BIT(DB_TMR_LARGE_OFF); } else if (debounce < 250000) { - time = debounce / 15600; + time = debounce / 15625; pin_reg |= time & DB_TMR_OUT_MASK; pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF); pin_reg |= BIT(DB_TMR_LARGE_OFF); @@ -166,14 +166,14 @@ static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset, pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF); pin_reg |= BIT(DB_TMR_LARGE_OFF); } else { - pin_reg &= ~DB_CNTRl_MASK; + pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF); ret = -EINVAL; } } else { pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF); pin_reg &= ~BIT(DB_TMR_LARGE_OFF); pin_reg &= ~DB_TMR_OUT_MASK; - pin_reg &= ~DB_CNTRl_MASK; + pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF); } writel(pin_reg, gpio_dev->base + offset * 4); raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); @@ -429,7 +429,6 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type) pin_reg &= ~BIT(LEVEL_TRIG_OFF); pin_reg &= ~(ACTIVE_LEVEL_MASK << ACTIVE_LEVEL_OFF); pin_reg |= ACTIVE_HIGH << ACTIVE_LEVEL_OFF; - pin_reg |= DB_TYPE_REMOVE_GLITCH << DB_CNTRL_OFF; irq_set_handler_locked(d, handle_edge_irq); break; @@ -437,7 +436,6 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type) pin_reg &= ~BIT(LEVEL_TRIG_OFF); pin_reg &= ~(ACTIVE_LEVEL_MASK << ACTIVE_LEVEL_OFF); pin_reg |= ACTIVE_LOW << ACTIVE_LEVEL_OFF; - pin_reg |= DB_TYPE_REMOVE_GLITCH << DB_CNTRL_OFF; irq_set_handler_locked(d, handle_edge_irq); break; @@ -445,7 +443,6 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type) pin_reg &= ~BIT(LEVEL_TRIG_OFF); pin_reg &= ~(ACTIVE_LEVEL_MASK << ACTIVE_LEVEL_OFF); pin_reg |= BOTH_EADGE << ACTIVE_LEVEL_OFF; - pin_reg |= DB_TYPE_REMOVE_GLITCH << DB_CNTRL_OFF; irq_set_handler_locked(d, handle_edge_irq); break; @@ -453,8 +450,6 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type) pin_reg |= LEVEL_TRIGGER << LEVEL_TRIG_OFF; pin_reg &= ~(ACTIVE_LEVEL_MASK << ACTIVE_LEVEL_OFF); pin_reg |= ACTIVE_HIGH << ACTIVE_LEVEL_OFF; - pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF); - pin_reg |= DB_TYPE_PRESERVE_LOW_GLITCH << DB_CNTRL_OFF; irq_set_handler_locked(d, handle_level_irq); break; @@ -462,8 +457,6 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type) pin_reg |= LEVEL_TRIGGER << LEVEL_TRIG_OFF; pin_reg &= ~(ACTIVE_LEVEL_MASK << ACTIVE_LEVEL_OFF); pin_reg |= ACTIVE_LOW << ACTIVE_LEVEL_OFF; - pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF); - pin_reg |= DB_TYPE_PRESERVE_HIGH_GLITCH << DB_CNTRL_OFF; irq_set_handler_locked(d, handle_level_irq); break; diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index c8e50a58a5e5..621909b01deb 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -635,44 +635,44 @@ static int jz4770_uart3_data_pins[] = { 0x6c, 0x85, }; static int jz4770_uart3_hwflow_pins[] = { 0x88, 0x89, }; static int jz4770_ssi0_dt_a_pins[] = { 0x15, }; static int jz4770_ssi0_dt_b_pins[] = { 0x35, }; -static int jz4770_ssi0_dt_d_pins[] = { 0x55, }; -static int jz4770_ssi0_dt_e_pins[] = { 0x71, }; +static int jz4770_ssi0_dt_d_pins[] = { 0x75, }; +static int jz4770_ssi0_dt_e_pins[] = { 0x91, }; static int jz4770_ssi0_dr_a_pins[] = { 0x14, }; static int jz4770_ssi0_dr_b_pins[] = { 0x34, }; -static int jz4770_ssi0_dr_d_pins[] = { 0x54, }; -static int jz4770_ssi0_dr_e_pins[] = { 0x6e, }; +static int jz4770_ssi0_dr_d_pins[] = { 0x74, }; +static int jz4770_ssi0_dr_e_pins[] = { 0x8e, }; static int jz4770_ssi0_clk_a_pins[] = { 0x12, }; static int jz4770_ssi0_clk_b_pins[] = { 0x3c, }; -static int jz4770_ssi0_clk_d_pins[] = { 0x58, }; -static int jz4770_ssi0_clk_e_pins[] = { 0x6f, }; +static int jz4770_ssi0_clk_d_pins[] = { 0x78, }; +static int jz4770_ssi0_clk_e_pins[] = { 0x8f, }; static int jz4770_ssi0_gpc_b_pins[] = { 0x3e, }; -static int jz4770_ssi0_gpc_d_pins[] = { 0x56, }; -static int jz4770_ssi0_gpc_e_pins[] = { 0x73, }; +static int jz4770_ssi0_gpc_d_pins[] = { 0x76, }; +static int jz4770_ssi0_gpc_e_pins[] = { 0x93, }; static int jz4770_ssi0_ce0_a_pins[] = { 0x13, }; static int jz4770_ssi0_ce0_b_pins[] = { 0x3d, }; -static int jz4770_ssi0_ce0_d_pins[] = { 0x59, }; -static int jz4770_ssi0_ce0_e_pins[] = { 0x70, }; +static int jz4770_ssi0_ce0_d_pins[] = { 0x79, }; +static int jz4770_ssi0_ce0_e_pins[] = { 0x90, }; static int jz4770_ssi0_ce1_b_pins[] = { 0x3f, }; -static int jz4770_ssi0_ce1_d_pins[] = { 0x57, }; -static int jz4770_ssi0_ce1_e_pins[] = { 0x72, }; +static int jz4770_ssi0_ce1_d_pins[] = { 0x77, }; +static int jz4770_ssi0_ce1_e_pins[] = { 0x92, }; static int jz4770_ssi1_dt_b_pins[] = { 0x35, }; -static int jz4770_ssi1_dt_d_pins[] = { 0x55, }; -static int jz4770_ssi1_dt_e_pins[] = { 0x71, }; +static int jz4770_ssi1_dt_d_pins[] = { 0x75, }; +static int jz4770_ssi1_dt_e_pins[] = { 0x91, }; static int jz4770_ssi1_dr_b_pins[] = { 0x34, }; -static int jz4770_ssi1_dr_d_pins[] = { 0x54, }; -static int jz4770_ssi1_dr_e_pins[] = { 0x6e, }; +static int jz4770_ssi1_dr_d_pins[] = { 0x74, }; +static int jz4770_ssi1_dr_e_pins[] = { 0x8e, }; static int jz4770_ssi1_clk_b_pins[] = { 0x3c, }; -static int jz4770_ssi1_clk_d_pins[] = { 0x58, }; -static int jz4770_ssi1_clk_e_pins[] = { 0x6f, }; +static int jz4770_ssi1_clk_d_pins[] = { 0x78, }; +static int jz4770_ssi1_clk_e_pins[] = { 0x8f, }; static int jz4770_ssi1_gpc_b_pins[] = { 0x3e, }; -static int jz4770_ssi1_gpc_d_pins[] = { 0x56, }; -static int jz4770_ssi1_gpc_e_pins[] = { 0x73, }; +static int jz4770_ssi1_gpc_d_pins[] = { 0x76, }; +static int jz4770_ssi1_gpc_e_pins[] = { 0x93, }; static int jz4770_ssi1_ce0_b_pins[] = { 0x3d, }; -static int jz4770_ssi1_ce0_d_pins[] = { 0x59, }; -static int jz4770_ssi1_ce0_e_pins[] = { 0x70, }; +static int jz4770_ssi1_ce0_d_pins[] = { 0x79, }; +static int jz4770_ssi1_ce0_e_pins[] = { 0x90, }; static int jz4770_ssi1_ce1_b_pins[] = { 0x3f, }; -static int jz4770_ssi1_ce1_d_pins[] = { 0x57, }; -static int jz4770_ssi1_ce1_e_pins[] = { 0x72, }; +static int jz4770_ssi1_ce1_d_pins[] = { 0x77, }; +static int jz4770_ssi1_ce1_e_pins[] = { 0x92, }; static int jz4770_mmc0_1bit_a_pins[] = { 0x12, 0x13, 0x14, }; static int jz4770_mmc0_4bit_a_pins[] = { 0x15, 0x16, 0x17, }; static int jz4770_mmc0_1bit_e_pins[] = { 0x9c, 0x9d, 0x94, }; @@ -1050,35 +1050,35 @@ static int jz4780_ssi0_dt_a_19_pins[] = { 0x13, }; static int jz4780_ssi0_dt_a_21_pins[] = { 0x15, }; static int jz4780_ssi0_dt_a_28_pins[] = { 0x1c, }; static int jz4780_ssi0_dt_b_pins[] = { 0x3d, }; -static int jz4780_ssi0_dt_d_pins[] = { 0x59, }; +static int jz4780_ssi0_dt_d_pins[] = { 0x79, }; static int jz4780_ssi0_dr_a_20_pins[] = { 0x14, }; static int jz4780_ssi0_dr_a_27_pins[] = { 0x1b, }; static int jz4780_ssi0_dr_b_pins[] = { 0x34, }; -static int jz4780_ssi0_dr_d_pins[] = { 0x54, }; +static int jz4780_ssi0_dr_d_pins[] = { 0x74, }; static int jz4780_ssi0_clk_a_pins[] = { 0x12, }; static int jz4780_ssi0_clk_b_5_pins[] = { 0x25, }; static int jz4780_ssi0_clk_b_28_pins[] = { 0x3c, }; -static int jz4780_ssi0_clk_d_pins[] = { 0x58, }; +static int jz4780_ssi0_clk_d_pins[] = { 0x78, }; static int jz4780_ssi0_gpc_b_pins[] = { 0x3e, }; -static int jz4780_ssi0_gpc_d_pins[] = { 0x56, }; +static int jz4780_ssi0_gpc_d_pins[] = { 0x76, }; static int jz4780_ssi0_ce0_a_23_pins[] = { 0x17, }; static int jz4780_ssi0_ce0_a_25_pins[] = { 0x19, }; static int jz4780_ssi0_ce0_b_pins[] = { 0x3f, }; -static int jz4780_ssi0_ce0_d_pins[] = { 0x57, }; +static int jz4780_ssi0_ce0_d_pins[] = { 0x77, }; static int jz4780_ssi0_ce1_b_pins[] = { 0x35, }; -static int jz4780_ssi0_ce1_d_pins[] = { 0x55, }; +static int jz4780_ssi0_ce1_d_pins[] = { 0x75, }; static int jz4780_ssi1_dt_b_pins[] = { 0x3d, }; -static int jz4780_ssi1_dt_d_pins[] = { 0x59, }; +static int jz4780_ssi1_dt_d_pins[] = { 0x79, }; static int jz4780_ssi1_dr_b_pins[] = { 0x34, }; -static int jz4780_ssi1_dr_d_pins[] = { 0x54, }; +static int jz4780_ssi1_dr_d_pins[] = { 0x74, }; static int jz4780_ssi1_clk_b_pins[] = { 0x3c, }; -static int jz4780_ssi1_clk_d_pins[] = { 0x58, }; +static int jz4780_ssi1_clk_d_pins[] = { 0x78, }; static int jz4780_ssi1_gpc_b_pins[] = { 0x3e, }; -static int jz4780_ssi1_gpc_d_pins[] = { 0x56, }; +static int jz4780_ssi1_gpc_d_pins[] = { 0x76, }; static int jz4780_ssi1_ce0_b_pins[] = { 0x3f, }; -static int jz4780_ssi1_ce0_d_pins[] = { 0x57, }; +static int jz4780_ssi1_ce0_d_pins[] = { 0x77, }; static int jz4780_ssi1_ce1_b_pins[] = { 0x35, }; -static int jz4780_ssi1_ce1_d_pins[] = { 0x55, }; +static int jz4780_ssi1_ce1_d_pins[] = { 0x75, }; static int jz4780_mmc0_8bit_a_pins[] = { 0x04, 0x05, 0x06, 0x07, 0x18, }; static int jz4780_i2c3_pins[] = { 0x6a, 0x6b, }; static int jz4780_i2c4_e_pins[] = { 0x8c, 0x8d, }; diff --git a/drivers/pinctrl/pinctrl-mcp23s08_spi.c b/drivers/pinctrl/pinctrl-mcp23s08_spi.c index 1f47a661b0a7..9ae10318f6f3 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08_spi.c +++ b/drivers/pinctrl/pinctrl-mcp23s08_spi.c @@ -119,13 +119,15 @@ static int mcp23s08_spi_regmap_init(struct mcp23s08 *mcp, struct device *dev, return -EINVAL; } - copy = devm_kmemdup(dev, &config, sizeof(config), GFP_KERNEL); + copy = devm_kmemdup(dev, config, sizeof(*config), GFP_KERNEL); if (!copy) return -ENOMEM; copy->name = name; mcp->regmap = devm_regmap_init(dev, &mcp23sxx_spi_regmap, mcp, copy); + if (IS_ERR(mcp->regmap)) + dev_err(dev, "regmap init failed for %s\n", mcp->chip.label); return PTR_ERR_OR_ZERO(mcp->regmap); } diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index 0401c1da79dd..aa1a1c850d05 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -3155,7 +3155,9 @@ static int rockchip_gpio_to_irq(struct gpio_chip *gc, unsigned offset) if (!bank->domain) return -ENXIO; + clk_enable(bank->clk); virq = irq_create_mapping(bank->domain, offset); + clk_disable(bank->clk); return (virq) ? : -ENXIO; } @@ -3194,7 +3196,7 @@ static void rockchip_irq_demux(struct irq_desc *desc) irq = __ffs(pend); pend &= ~BIT(irq); - virq = irq_linear_revmap(bank->domain, irq); + virq = irq_find_mapping(bank->domain, irq); if (!virq) { dev_err(bank->drvdata->dev, "unmapped irq %d\n", irq); @@ -3373,7 +3375,7 @@ static int rockchip_interrupts_register(struct platform_device *pdev, unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN; struct irq_chip_generic *gc; int ret; - int i, j; + int i; for (i = 0; i < ctrl->nr_banks; ++i, ++bank) { if (!bank->valid) { @@ -3400,7 +3402,7 @@ static int rockchip_interrupts_register(struct platform_device *pdev, ret = irq_alloc_domain_generic_chips(bank->domain, 32, 1, "rockchip_gpio_irq", handle_level_irq, - clr, 0, IRQ_GC_INIT_MASK_CACHE); + clr, 0, 0); if (ret) { dev_err(&pdev->dev, "could not alloc generic chips for bank %s\n", bank->name); @@ -3409,14 +3411,6 @@ static int rockchip_interrupts_register(struct platform_device *pdev, continue; } - /* - * Linux assumes that all interrupts start out disabled/masked. - * Our driver only uses the concept of masked and always keeps - * things enabled, so for us that's all masked and all enabled. - */ - writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTMASK); - writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTEN); - gc = irq_get_domain_generic_chip(bank->domain, 0); gc->reg_base = bank->reg_base; gc->private = bank; @@ -3433,13 +3427,17 @@ static int rockchip_interrupts_register(struct platform_device *pdev, gc->chip_types[0].chip.irq_set_type = rockchip_irq_set_type; gc->wake_enabled = IRQ_MSK(bank->nr_pins); + /* + * Linux assumes that all interrupts start out disabled/masked. + * Our driver only uses the concept of masked and always keeps + * things enabled, so for us that's all masked and all enabled. + */ + writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTMASK); + writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTEN); + gc->mask_cache = 0xffffffff; + irq_set_chained_handler_and_data(bank->irq, rockchip_irq_demux, bank); - - /* map the gpio irqs here, when the clock is still running */ - for (j = 0 ; j < 32 ; j++) - irq_create_mapping(bank->domain, j); - clk_disable(bank->clk); } diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index c4bcda90aac4..77a25bdf0da7 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -815,21 +815,14 @@ static void msm_gpio_irq_clear_unmask(struct irq_data *d, bool status_clear) static void msm_gpio_irq_enable(struct irq_data *d) { - /* - * Clear the interrupt that may be pending before we enable - * the line. - * This is especially a problem with the GPIOs routed to the - * PDC. These GPIOs are direct-connect interrupts to the GIC. - * Disabling the interrupt line at the PDC does not prevent - * the interrupt from being latched at the GIC. The state at - * GIC needs to be cleared before enabling. - */ - if (d->parent_data) { - irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + + if (d->parent_data) irq_chip_enable_parent(d); - } - msm_gpio_irq_clear_unmask(d, true); + if (!test_bit(d->hwirq, pctrl->skip_wake_irqs)) + msm_gpio_irq_clear_unmask(d, true); } static void msm_gpio_irq_disable(struct irq_data *d) @@ -1104,6 +1097,19 @@ static int msm_gpio_irq_reqres(struct irq_data *d) ret = -EINVAL; goto out; } + + /* + * Clear the interrupt that may be pending before we enable + * the line. + * This is especially a problem with the GPIOs routed to the + * PDC. These GPIOs are direct-connect interrupts to the GIC. + * Disabling the interrupt line at the PDC does not prevent + * the interrupt from being latched at the GIC. The state at + * GIC needs to be cleared before enabling. + */ + if (d->parent_data && test_bit(d->hwirq, pctrl->skip_wake_irqs)) + irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0); + return 0; out: module_put(gc->owner); diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250.c b/drivers/pinctrl/qcom/pinctrl-sm8250.c index 826df0d637ea..af144e724bd9 100644 --- a/drivers/pinctrl/qcom/pinctrl-sm8250.c +++ b/drivers/pinctrl/qcom/pinctrl-sm8250.c @@ -1313,6 +1313,22 @@ static const struct msm_pingroup sm8250_groups[] = { [183] = SDC_PINGROUP(sdc2_data, 0xb7000, 9, 0), }; +static const struct msm_gpio_wakeirq_map sm8250_pdc_map[] = { + { 0, 79 }, { 1, 84 }, { 2, 80 }, { 3, 82 }, { 4, 107 }, { 7, 43 }, + { 11, 42 }, { 14, 44 }, { 15, 52 }, { 19, 67 }, { 23, 68 }, { 24, 105 }, + { 27, 92 }, { 28, 106 }, { 31, 69 }, { 35, 70 }, { 39, 37 }, + { 40, 108 }, { 43, 71 }, { 45, 72 }, { 47, 83 }, { 51, 74 }, { 55, 77 }, + { 59, 78 }, { 63, 75 }, { 64, 81 }, { 65, 87 }, { 66, 88 }, { 67, 89 }, + { 68, 54 }, { 70, 85 }, { 77, 46 }, { 80, 90 }, { 81, 91 }, { 83, 97 }, + { 84, 98 }, { 86, 99 }, { 87, 100 }, { 88, 101 }, { 89, 102 }, + { 92, 103 }, { 93, 104 }, { 100, 53 }, { 103, 47 }, { 104, 48 }, + { 108, 49 }, { 109, 94 }, { 110, 95 }, { 111, 96 }, { 112, 55 }, + { 113, 56 }, { 118, 50 }, { 121, 51 }, { 122, 57 }, { 123, 58 }, + { 124, 45 }, { 126, 59 }, { 128, 76 }, { 129, 86 }, { 132, 93 }, + { 133, 65 }, { 134, 66 }, { 136, 62 }, { 137, 63 }, { 138, 64 }, + { 142, 60 }, { 143, 61 } +}; + static const struct msm_pinctrl_soc_data sm8250_pinctrl = { .pins = sm8250_pins, .npins = ARRAY_SIZE(sm8250_pins), @@ -1323,6 +1339,8 @@ static const struct msm_pinctrl_soc_data sm8250_pinctrl = { .ngpios = 181, .tiles = sm8250_tiles, .ntiles = ARRAY_SIZE(sm8250_tiles), + .wakeirq_map = sm8250_pdc_map, + .nwakeirq_map = ARRAY_SIZE(sm8250_pdc_map), }; static int sm8250_pinctrl_probe(struct platform_device *pdev) diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index 49f4b73be513..5592a929b593 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -111,6 +111,7 @@ static const struct key_entry acer_wmi_keymap[] __initconst = { {KE_KEY, 0x64, {KEY_SWITCHVIDEOMODE} }, /* Display Switch */ {KE_IGNORE, 0x81, {KEY_SLEEP} }, {KE_KEY, 0x82, {KEY_TOUCHPAD_TOGGLE} }, /* Touch Pad Toggle */ + {KE_IGNORE, 0x84, {KEY_KBDILLUMTOGGLE} }, /* Automatic Keyboard background light toggle */ {KE_KEY, KEY_TOUCHPAD_ON, {KEY_TOUCHPAD_ON} }, {KE_KEY, KEY_TOUCHPAD_OFF, {KEY_TOUCHPAD_OFF} }, {KE_IGNORE, 0x83, {KEY_TOUCHPAD_TOGGLE} }, diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index f5901b0b07cd..0419c8001fe3 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -206,6 +206,12 @@ static const struct dmi_system_id dmi_switches_allow_list[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Stream x360 Convertible PC 11"), }, }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion 13 x360 PC"), + }, + }, {} /* Array terminator */ }; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index e3810675090a..c404706379d9 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -3218,7 +3218,14 @@ static int hotkey_init_tablet_mode(void) in_tablet_mode = hotkey_gmms_get_tablet_mode(res, &has_tablet_mode); - if (has_tablet_mode) + /* + * The Yoga 11e series has 2 accelerometers described by a + * BOSC0200 ACPI node. This setup relies on a Windows service + * which calls special ACPI methods on this node to report + * the laptop/tent/tablet mode to the EC. The bmc150 iio driver + * does not support this, so skip the hotkey on these models. + */ + if (has_tablet_mode && !acpi_dev_present("BOSC0200", "1", -1)) tp_features.hotkey_tablet = TP_HOTKEY_TABLET_USES_GMMS; type = "GMMS"; } else if (acpi_evalf(hkey_handle, &res, "MHKG", "qd")) { @@ -4228,6 +4235,7 @@ static void hotkey_resume(void) pr_err("error while attempting to reset the event firmware interface\n"); tpacpi_send_radiosw_update(); + tpacpi_input_send_tabletsw(); hotkey_tablet_mode_notify_change(); hotkey_wakeup_reason_notify_change(); hotkey_wakeup_hotunplug_complete_notify_change(); @@ -8776,6 +8784,8 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('N', '2', 'C', TPACPI_FAN_2CTL), /* P52 / P72 */ TPACPI_Q_LNV3('N', '2', 'E', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (1st gen) */ TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (2nd gen) */ + TPACPI_Q_LNV3('N', '2', 'V', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (3nd gen) */ + TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL), /* P15 (1st gen) / P15v (1st gen) */ }; static int __init fan_init(struct ibm_init_struct *iibm) @@ -9703,6 +9713,7 @@ static const struct tpacpi_quirk battery_quirk_table[] __initconst = { TPACPI_Q_LNV3('R', '0', 'B', true), /* Thinkpad 11e gen 3 */ TPACPI_Q_LNV3('R', '0', 'C', true), /* Thinkpad 13 */ TPACPI_Q_LNV3('R', '0', 'J', true), /* Thinkpad 13 gen 2 */ + TPACPI_Q_LNV3('R', '0', 'K', true), /* Thinkpad 11e gen 4 celeron BIOS */ }; static int __init tpacpi_battery_init(struct ibm_init_struct *ibm) diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index e557d757c647..fa7232ad8c39 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -1478,7 +1478,7 @@ static ssize_t video_proc_write(struct file *file, const char __user *buf, struct toshiba_acpi_dev *dev = PDE_DATA(file_inode(file)); char *buffer; char *cmd; - int lcd_out, crt_out, tv_out; + int lcd_out = -1, crt_out = -1, tv_out = -1; int remain = count; int value; int ret; @@ -1510,7 +1510,6 @@ static ssize_t video_proc_write(struct file *file, const char __user *buf, kfree(cmd); - lcd_out = crt_out = tv_out = -1; ret = get_video_status(dev, &video_out); if (!ret) { unsigned int new_video_out = video_out; diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index dda60f89c951..5783139d0a11 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -295,6 +295,21 @@ static const struct ts_dmi_data irbis_tw90_data = { .properties = irbis_tw90_props, }; +static const struct property_entry irbis_tw118_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 20), + PROPERTY_ENTRY_U32("touchscreen-min-y", 30), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1960), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1510), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-irbis-tw118.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct ts_dmi_data irbis_tw118_data = { + .acpi_name = "MSSL1680:00", + .properties = irbis_tw118_props, +}; + static const struct property_entry itworks_tw891_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-x", 1), PROPERTY_ENTRY_U32("touchscreen-min-y", 5), @@ -623,6 +638,23 @@ static const struct ts_dmi_data pov_mobii_wintab_p1006w_v10_data = { .properties = pov_mobii_wintab_p1006w_v10_props, }; +static const struct property_entry predia_basic_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 3), + PROPERTY_ENTRY_U32("touchscreen-min-y", 10), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1728), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1144), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl3680-predia-basic.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data predia_basic_data = { + .acpi_name = "MSSL1680:00", + .properties = predia_basic_props, +}; + static const struct property_entry schneider_sct101ctm_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1715), PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), @@ -937,6 +969,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* Irbis TW118 */ + .driver_data = (void *)&irbis_tw118_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "IRBIS"), + DMI_MATCH(DMI_PRODUCT_NAME, "TW118"), + }, + }, + { /* I.T.Works TW891 */ .driver_data = (void *)&itworks_tw891_data, .matches = { @@ -1110,6 +1150,16 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* Predia Basic tablet) */ + .driver_data = (void *)&predia_basic_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "CherryTrail"), + /* Above matches are too generic, add bios-version match */ + DMI_MATCH(DMI_BIOS_VERSION, "Mx.WT107.KUBNGEA"), + }, + }, + { /* Point of View mobii wintab p800w (v2.1) */ .driver_data = (void *)&pov_mobii_wintab_p800w_v21_data, .matches = { diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c index f808c5fa9838..3f0b8e2ef3d4 100644 --- a/drivers/powercap/powercap_sys.c +++ b/drivers/powercap/powercap_sys.c @@ -367,9 +367,9 @@ static void create_power_zone_common_attributes( &dev_attr_max_energy_range_uj.attr; if (power_zone->ops->get_energy_uj) { if (power_zone->ops->reset_energy_uj) - dev_attr_energy_uj.attr.mode = S_IWUSR | S_IRUGO; + dev_attr_energy_uj.attr.mode = S_IWUSR | S_IRUSR; else - dev_attr_energy_uj.attr.mode = S_IRUGO; + dev_attr_energy_uj.attr.mode = S_IRUSR; power_zone->zone_dev_attrs[count++] = &dev_attr_energy_uj.attr; } diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c index e020faff7da5..663255774c0b 100644 --- a/drivers/ptp/ptp_clockmatrix.c +++ b/drivers/ptp/ptp_clockmatrix.c @@ -103,43 +103,26 @@ static int timespec_to_char_array(struct timespec64 const *ts, return 0; } -static int idtcm_strverscmp(const char *ver1, const char *ver2) +static int idtcm_strverscmp(const char *version1, const char *version2) { - u8 num1; - u8 num2; - int result = 0; - - /* loop through each level of the version string */ - while (result == 0) { - /* extract leading version numbers */ - if (kstrtou8(ver1, 10, &num1) < 0) - return -1; + u8 ver1[3], ver2[3]; + int i; - if (kstrtou8(ver2, 10, &num2) < 0) - return -1; + if (sscanf(version1, "%hhu.%hhu.%hhu", + &ver1[0], &ver1[1], &ver1[2]) != 3) + return -1; + if (sscanf(version2, "%hhu.%hhu.%hhu", + &ver2[0], &ver2[1], &ver2[2]) != 3) + return -1; - /* if numbers differ, then set the result */ - if (num1 < num2) - result = -1; - else if (num1 > num2) - result = 1; - else { - /* if numbers are the same, go to next level */ - ver1 = strchr(ver1, '.'); - ver2 = strchr(ver2, '.'); - if (!ver1 && !ver2) - break; - else if (!ver1) - result = -1; - else if (!ver2) - result = 1; - else { - ver1++; - ver2++; - } - } + for (i = 0; i < 3; i++) { + if (ver1[i] > ver2[i]) + return 1; + if (ver1[i] < ver2[i]) + return -1; } - return result; + + return 0; } static int idtcm_xfer_read(struct idtcm *idtcm, diff --git a/drivers/pwm/pwm-sl28cpld.c b/drivers/pwm/pwm-sl28cpld.c index 5046b6b7fd35..b4c651fc749c 100644 --- a/drivers/pwm/pwm-sl28cpld.c +++ b/drivers/pwm/pwm-sl28cpld.c @@ -84,12 +84,14 @@ struct sl28cpld_pwm { struct regmap *regmap; u32 offset; }; +#define sl28cpld_pwm_from_chip(_chip) \ + container_of(_chip, struct sl28cpld_pwm, pwm_chip) static void sl28cpld_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, struct pwm_state *state) { - struct sl28cpld_pwm *priv = dev_get_drvdata(chip->dev); + struct sl28cpld_pwm *priv = sl28cpld_pwm_from_chip(chip); unsigned int reg; int prescaler; @@ -118,7 +120,7 @@ static void sl28cpld_pwm_get_state(struct pwm_chip *chip, static int sl28cpld_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, const struct pwm_state *state) { - struct sl28cpld_pwm *priv = dev_get_drvdata(chip->dev); + struct sl28cpld_pwm *priv = sl28cpld_pwm_from_chip(chip); unsigned int cycle, prescaler; bool write_duty_cycle_first; int ret; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index a5ad553da8cd..42bbd99a36ac 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1315,7 +1315,6 @@ static int _regulator_do_enable(struct regulator_dev *rdev); /** * set_machine_constraints - sets regulator constraints * @rdev: regulator source - * @constraints: constraints to apply * * Allows platform initialisation code to define and constrain * regulator circuits e.g. valid voltage/current ranges, etc. NOTE: @@ -1323,21 +1322,11 @@ static int _regulator_do_enable(struct regulator_dev *rdev); * regulator operations to proceed i.e. set_voltage, set_current_limit, * set_mode. */ -static int set_machine_constraints(struct regulator_dev *rdev, - const struct regulation_constraints *constraints) +static int set_machine_constraints(struct regulator_dev *rdev) { int ret = 0; const struct regulator_ops *ops = rdev->desc->ops; - if (constraints) - rdev->constraints = kmemdup(constraints, sizeof(*constraints), - GFP_KERNEL); - else - rdev->constraints = kzalloc(sizeof(*constraints), - GFP_KERNEL); - if (!rdev->constraints) - return -ENOMEM; - ret = machine_constraints_voltage(rdev, rdev->constraints); if (ret != 0) return ret; @@ -1852,6 +1841,15 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) } } + if (r == rdev) { + dev_err(dev, "Supply for %s (%s) resolved to itself\n", + rdev->desc->name, rdev->supply_name); + if (!have_full_constraints()) + return -EINVAL; + r = dummy_regulator_rdev; + get_device(&r->dev); + } + /* * If the supply's parent device is not the same as the * regulator's parent device, then ensure the parent device @@ -5146,7 +5144,6 @@ struct regulator_dev * regulator_register(const struct regulator_desc *regulator_desc, const struct regulator_config *cfg) { - const struct regulation_constraints *constraints = NULL; const struct regulator_init_data *init_data; struct regulator_config *config = NULL; static atomic_t regulator_no = ATOMIC_INIT(-1); @@ -5285,14 +5282,23 @@ regulator_register(const struct regulator_desc *regulator_desc, /* set regulator constraints */ if (init_data) - constraints = &init_data->constraints; + rdev->constraints = kmemdup(&init_data->constraints, + sizeof(*rdev->constraints), + GFP_KERNEL); + else + rdev->constraints = kzalloc(sizeof(*rdev->constraints), + GFP_KERNEL); + if (!rdev->constraints) { + ret = -ENOMEM; + goto wash; + } if (init_data && init_data->supply_regulator) rdev->supply_name = init_data->supply_regulator; else if (regulator_desc->supply_name) rdev->supply_name = regulator_desc->supply_name; - ret = set_machine_constraints(rdev, constraints); + ret = set_machine_constraints(rdev); if (ret == -EPROBE_DEFER) { /* Regulator might be in bypass mode and so needs its supply * to set the constraints */ @@ -5301,7 +5307,7 @@ regulator_register(const struct regulator_desc *regulator_desc, * that is just being created */ ret = regulator_resolve_supply(rdev); if (!ret) - ret = set_machine_constraints(rdev, constraints); + ret = set_machine_constraints(rdev); else rdev_dbg(rdev, "unable to resolve supply early: %pe\n", ERR_PTR(ret)); @@ -5843,13 +5849,14 @@ static int regulator_late_cleanup(struct device *dev, void *data) if (rdev->use_count) goto unlock; - /* If we can't read the status assume it's on. */ + /* If we can't read the status assume it's always on. */ if (ops->is_enabled) enabled = ops->is_enabled(rdev); else enabled = 1; - if (!enabled) + /* But if reading the status failed, assume that it's off. */ + if (enabled <= 0) goto unlock; if (have_full_constraints()) { diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c index 7e8ba9246167..01a12cfcea7c 100644 --- a/drivers/regulator/pfuze100-regulator.c +++ b/drivers/regulator/pfuze100-regulator.c @@ -836,11 +836,14 @@ static int pfuze100_regulator_probe(struct i2c_client *client, * the switched regulator till yet. */ if (pfuze_chip->flags & PFUZE_FLAG_DISABLE_SW) { - if (pfuze_chip->regulator_descs[i].sw_reg) { - desc->ops = &pfuze100_sw_disable_regulator_ops; - desc->enable_val = 0x8; - desc->disable_val = 0x0; - desc->enable_time = 500; + if (pfuze_chip->chip_id == PFUZE100 || + pfuze_chip->chip_id == PFUZE200) { + if (pfuze_chip->regulator_descs[i].sw_reg) { + desc->ops = &pfuze100_sw_disable_regulator_ops; + desc->enable_val = 0x8; + desc->disable_val = 0x0; + desc->enable_time = 500; + } } } diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c index 3e60bff76194..9f0a4d50cead 100644 --- a/drivers/regulator/ti-abb-regulator.c +++ b/drivers/regulator/ti-abb-regulator.c @@ -342,8 +342,17 @@ static int ti_abb_set_voltage_sel(struct regulator_dev *rdev, unsigned sel) return ret; } - /* If data is exactly the same, then just update index, no change */ info = &abb->info[sel]; + /* + * When Linux kernel is starting up, we are'nt sure of the + * Bias configuration that bootloader has configured. + * So, we get to know the actual setting the first time + * we are asked to transition. + */ + if (abb->current_info_idx == -EINVAL) + goto just_set_abb; + + /* If data is exactly the same, then just update index, no change */ oinfo = &abb->info[abb->current_info_idx]; if (!memcmp(info, oinfo, sizeof(*info))) { dev_dbg(dev, "%s: Same data new idx=%d, old idx=%d\n", __func__, @@ -351,6 +360,7 @@ static int ti_abb_set_voltage_sel(struct regulator_dev *rdev, unsigned sel) goto out; } +just_set_abb: ret = ti_abb_set_opp(rdev, abb, info); out: diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index eb17fea8075c..217a7b84abdf 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2980,6 +2980,12 @@ static int _dasd_requeue_request(struct dasd_ccw_req *cqr) if (!block) return -EINVAL; + /* + * If the request is an ERP request there is nothing to requeue. + * This will be done with the remaining original request. + */ + if (cqr->refers) + return 0; spin_lock_irq(&cqr->dq->lock); req = (struct request *) cqr->callback_data; blk_mq_requeue_request(req, false); diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index f73b4756ed5e..b235393e091c 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -417,10 +417,13 @@ enum qeth_qdio_out_buffer_state { QETH_QDIO_BUF_EMPTY, /* Filled by driver; owned by hardware in order to be sent. */ QETH_QDIO_BUF_PRIMED, - /* Identified to be pending in TPQ. */ + /* Discovered by the TX completion code: */ QETH_QDIO_BUF_PENDING, - /* Found in completion queue. */ - QETH_QDIO_BUF_IN_CQ, + /* Finished by the TX completion code: */ + QETH_QDIO_BUF_NEED_QAOB, + /* Received QAOB notification on CQ: */ + QETH_QDIO_BUF_QAOB_OK, + QETH_QDIO_BUF_QAOB_ERROR, /* Handled via transfer pending / completion queue. */ QETH_QDIO_BUF_HANDLED_DELAYED, }; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 5ed443725e8a..6ca05e5363d1 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -33,6 +33,7 @@ #include <net/iucv/af_iucv.h> #include <net/dsfield.h> +#include <net/sock.h> #include <asm/ebcdic.h> #include <asm/chpid.h> @@ -499,17 +500,12 @@ static void qeth_cleanup_handled_pending(struct qeth_qdio_out_q *q, int bidx, } } - if (forced_cleanup && (atomic_read(&(q->bufs[bidx]->state)) == - QETH_QDIO_BUF_HANDLED_DELAYED)) { - /* for recovery situations */ - qeth_init_qdio_out_buf(q, bidx); - QETH_CARD_TEXT(q->card, 2, "clprecov"); - } } static void qeth_qdio_handle_aob(struct qeth_card *card, unsigned long phys_aob_addr) { + enum qeth_qdio_out_buffer_state new_state = QETH_QDIO_BUF_QAOB_OK; struct qaob *aob; struct qeth_qdio_out_buffer *buffer; enum iucv_tx_notify notification; @@ -521,22 +517,6 @@ static void qeth_qdio_handle_aob(struct qeth_card *card, buffer = (struct qeth_qdio_out_buffer *) aob->user1; QETH_CARD_TEXT_(card, 5, "%lx", aob->user1); - if (atomic_cmpxchg(&buffer->state, QETH_QDIO_BUF_PRIMED, - QETH_QDIO_BUF_IN_CQ) == QETH_QDIO_BUF_PRIMED) { - notification = TX_NOTIFY_OK; - } else { - WARN_ON_ONCE(atomic_read(&buffer->state) != - QETH_QDIO_BUF_PENDING); - atomic_set(&buffer->state, QETH_QDIO_BUF_IN_CQ); - notification = TX_NOTIFY_DELAYED_OK; - } - - if (aob->aorc != 0) { - QETH_CARD_TEXT_(card, 2, "aorc%02X", aob->aorc); - notification = qeth_compute_cq_notification(aob->aorc, 1); - } - qeth_notify_skbs(buffer->q, buffer, notification); - /* Free dangling allocations. The attached skbs are handled by * qeth_cleanup_handled_pending(). */ @@ -548,7 +528,33 @@ static void qeth_qdio_handle_aob(struct qeth_card *card, if (data && buffer->is_header[i]) kmem_cache_free(qeth_core_header_cache, data); } - atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED); + + if (aob->aorc) { + QETH_CARD_TEXT_(card, 2, "aorc%02X", aob->aorc); + new_state = QETH_QDIO_BUF_QAOB_ERROR; + } + + switch (atomic_xchg(&buffer->state, new_state)) { + case QETH_QDIO_BUF_PRIMED: + /* Faster than TX completion code. */ + notification = qeth_compute_cq_notification(aob->aorc, 0); + qeth_notify_skbs(buffer->q, buffer, notification); + atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED); + break; + case QETH_QDIO_BUF_PENDING: + /* TX completion code is active and will handle the async + * completion for us. + */ + break; + case QETH_QDIO_BUF_NEED_QAOB: + /* TX completion code is already finished. */ + notification = qeth_compute_cq_notification(aob->aorc, 1); + qeth_notify_skbs(buffer->q, buffer, notification); + atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED); + break; + default: + WARN_ON_ONCE(1); + } qdio_release_aob(aob); } @@ -1406,7 +1412,7 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *q, skb_queue_walk(&buf->skb_list, skb) { QETH_CARD_TEXT_(q->card, 5, "skbn%d", notification); QETH_CARD_TEXT_(q->card, 5, "%lx", (long) skb); - if (skb->protocol == htons(ETH_P_AF_IUCV) && skb->sk) + if (skb->sk && skb->sk->sk_family == PF_IUCV) iucv_sk(skb->sk)->sk_txnotify(skb, notification); } } @@ -1417,9 +1423,6 @@ static void qeth_tx_complete_buf(struct qeth_qdio_out_buffer *buf, bool error, struct qeth_qdio_out_q *queue = buf->q; struct sk_buff *skb; - /* release may never happen from within CQ tasklet scope */ - WARN_ON_ONCE(atomic_read(&buf->state) == QETH_QDIO_BUF_IN_CQ); - if (atomic_read(&buf->state) == QETH_QDIO_BUF_PENDING) qeth_notify_skbs(queue, buf, TX_NOTIFY_GENERALERROR); @@ -5870,9 +5873,32 @@ static void qeth_iqd_tx_complete(struct qeth_qdio_out_q *queue, if (atomic_cmpxchg(&buffer->state, QETH_QDIO_BUF_PRIMED, QETH_QDIO_BUF_PENDING) == - QETH_QDIO_BUF_PRIMED) + QETH_QDIO_BUF_PRIMED) { qeth_notify_skbs(queue, buffer, TX_NOTIFY_PENDING); + /* Handle race with qeth_qdio_handle_aob(): */ + switch (atomic_xchg(&buffer->state, + QETH_QDIO_BUF_NEED_QAOB)) { + case QETH_QDIO_BUF_PENDING: + /* No concurrent QAOB notification. */ + break; + case QETH_QDIO_BUF_QAOB_OK: + qeth_notify_skbs(queue, buffer, + TX_NOTIFY_DELAYED_OK); + atomic_set(&buffer->state, + QETH_QDIO_BUF_HANDLED_DELAYED); + break; + case QETH_QDIO_BUF_QAOB_ERROR: + qeth_notify_skbs(queue, buffer, + TX_NOTIFY_DELAYED_GENERALERROR); + atomic_set(&buffer->state, + QETH_QDIO_BUF_HANDLED_DELAYED); + break; + default: + WARN_ON_ONCE(1); + } + } + QETH_CARD_TEXT_(card, 5, "pel%u", bidx); /* prepare the queue slot for re-use: */ diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 28f6dda95736..79939ba5d523 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -985,32 +985,19 @@ static void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) * change notification' and thus can support the learning_sync bridgeport * attribute * @card: qeth_card structure pointer - * - * This is a destructive test and must be called before dev2br or - * bridgeport address notification is enabled! */ static void qeth_l2_detect_dev2br_support(struct qeth_card *card) { struct qeth_priv *priv = netdev_priv(card->dev); bool dev2br_supported; - int rc; QETH_CARD_TEXT(card, 2, "d2brsup"); if (!IS_IQD(card)) return; /* dev2br requires valid cssid,iid,chid */ - if (!card->info.ids_valid) { - dev2br_supported = false; - } else if (css_general_characteristics.enarf) { - dev2br_supported = true; - } else { - /* Old machines don't have the feature bit: - * Probe by testing whether a disable succeeds - */ - rc = qeth_l2_pnso(card, PNSO_OC_NET_ADDR_INFO, 0, NULL, NULL); - dev2br_supported = !rc; - } + dev2br_supported = card->info.ids_valid && + css_general_characteristics.enarf; QETH_CARD_TEXT_(card, 2, "D2Bsup%02x", dev2br_supported); if (dev2br_supported) @@ -2233,7 +2220,6 @@ static int qeth_l2_set_online(struct qeth_card *card, bool carrier_ok) struct net_device *dev = card->dev; int rc = 0; - /* query before bridgeport_notification may be enabled */ qeth_l2_detect_dev2br_support(card); mutex_lock(&card->sbp_lock); diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c index 202ba925c494..5c3513a4b450 100644 --- a/drivers/scsi/be2iscsi/be_main.c +++ b/drivers/scsi/be2iscsi/be_main.c @@ -3020,7 +3020,6 @@ static int beiscsi_create_eqs(struct beiscsi_hba *phba, goto create_eq_error; } - mem->dma = paddr; mem->va = eq_vaddress; ret = be_fill_queue(eq, phba->params.num_eq_entries, sizeof(struct be_eq_entry), eq_vaddress); @@ -3030,6 +3029,7 @@ static int beiscsi_create_eqs(struct beiscsi_hba *phba, goto create_eq_error; } + mem->dma = paddr; ret = beiscsi_cmd_eq_create(&phba->ctrl, eq, BEISCSI_EQ_DELAY_DEF); if (ret) { @@ -3086,7 +3086,6 @@ static int beiscsi_create_cqs(struct beiscsi_hba *phba, goto create_cq_error; } - mem->dma = paddr; ret = be_fill_queue(cq, phba->params.num_cq_entries, sizeof(struct sol_cqe), cq_vaddress); if (ret) { @@ -3096,6 +3095,7 @@ static int beiscsi_create_cqs(struct beiscsi_hba *phba, goto create_cq_error; } + mem->dma = paddr; ret = beiscsi_cmd_cq_create(&phba->ctrl, cq, eq, false, false, 0); if (ret) { diff --git a/drivers/scsi/bnx2i/Kconfig b/drivers/scsi/bnx2i/Kconfig index 75ace2302fed..0cc06c2ce0b8 100644 --- a/drivers/scsi/bnx2i/Kconfig +++ b/drivers/scsi/bnx2i/Kconfig @@ -4,6 +4,7 @@ config SCSI_BNX2_ISCSI depends on NET depends on PCI depends on (IPV6 || IPV6=n) + depends on MMU select SCSI_ISCSI_ATTRS select NETDEVICES select ETHERNET diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index c8dd8588f800..274ccf18ce2d 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -452,6 +452,12 @@ static int hisi_sas_task_prep(struct sas_task *task, blk_tag = blk_mq_unique_tag(scmd->request); dq_index = blk_mq_unique_tag_to_hwq(blk_tag); *dq_pointer = dq = &hisi_hba->dq[dq_index]; + } else if (hisi_hba->shost->nr_hw_queues) { + struct Scsi_Host *shost = hisi_hba->shost; + struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; + int queue = qmap->mq_map[raw_smp_processor_id()]; + + *dq_pointer = dq = &hisi_hba->dq[queue]; } else { *dq_pointer = dq = sas_dev->dq; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 7133ca859b5e..960de375ce69 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2452,6 +2452,11 @@ static int interrupt_init_v3_hw(struct hisi_hba *hisi_hba) rc = -ENOENT; goto free_irq_vectors; } + cq->irq_mask = pci_irq_get_affinity(pdev, i + BASE_VECTORS_V3_HW); + if (!cq->irq_mask) { + dev_err(dev, "could not get cq%d irq affinity!\n", i); + return -ENOENT; + } } return 0; diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 1e9c3171fa9f..f9314f1393fb 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -533,8 +533,8 @@ static void iscsi_complete_task(struct iscsi_task *task, int state) if (conn->task == task) conn->task = NULL; - if (conn->ping_task == task) - conn->ping_task = NULL; + if (READ_ONCE(conn->ping_task) == task) + WRITE_ONCE(conn->ping_task, NULL); /* release get from queueing */ __iscsi_put_task(task); @@ -738,6 +738,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, task->conn->session->age); } + if (unlikely(READ_ONCE(conn->ping_task) == INVALID_SCSI_TASK)) + WRITE_ONCE(conn->ping_task, task); + if (!ihost->workq) { if (iscsi_prep_mgmt_task(conn, task)) goto free_task; @@ -941,8 +944,11 @@ static int iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr) struct iscsi_nopout hdr; struct iscsi_task *task; - if (!rhdr && conn->ping_task) - return -EINVAL; + if (!rhdr) { + if (READ_ONCE(conn->ping_task)) + return -EINVAL; + WRITE_ONCE(conn->ping_task, INVALID_SCSI_TASK); + } memset(&hdr, 0, sizeof(struct iscsi_nopout)); hdr.opcode = ISCSI_OP_NOOP_OUT | ISCSI_OP_IMMEDIATE; @@ -957,11 +963,12 @@ static int iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr) task = __iscsi_conn_send_pdu(conn, (struct iscsi_hdr *)&hdr, NULL, 0); if (!task) { + if (!rhdr) + WRITE_ONCE(conn->ping_task, NULL); iscsi_conn_printk(KERN_ERR, conn, "Could not send nopout\n"); return -EIO; } else if (!rhdr) { /* only track our nops */ - conn->ping_task = task; conn->last_ping = jiffies; } @@ -984,7 +991,7 @@ static int iscsi_nop_out_rsp(struct iscsi_task *task, struct iscsi_conn *conn = task->conn; int rc = 0; - if (conn->ping_task != task) { + if (READ_ONCE(conn->ping_task) != task) { /* * If this is not in response to one of our * nops then it must be from userspace. @@ -1923,7 +1930,7 @@ static void iscsi_start_tx(struct iscsi_conn *conn) */ static int iscsi_has_ping_timed_out(struct iscsi_conn *conn) { - if (conn->ping_task && + if (READ_ONCE(conn->ping_task) && time_before_eq(conn->last_recv + (conn->recv_timeout * HZ) + (conn->ping_timeout * HZ), jiffies)) return 1; @@ -2058,7 +2065,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc) * Checking the transport already or nop from a cmd timeout still * running */ - if (conn->ping_task) { + if (READ_ONCE(conn->ping_task)) { task->have_checked_conn = true; rc = BLK_EH_RESET_TIMER; goto done; diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 41cd66fc7d81..e158d3d62056 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -37,7 +37,6 @@ #include <linux/poll.h> #include <linux/vmalloc.h> #include <linux/irq_poll.h> -#include <linux/blk-mq-pci.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> @@ -114,10 +113,6 @@ unsigned int enable_sdev_max_qd; module_param(enable_sdev_max_qd, int, 0444); MODULE_PARM_DESC(enable_sdev_max_qd, "Enable sdev max qd as can_queue. Default: 0"); -int host_tagset_enable = 1; -module_param(host_tagset_enable, int, 0444); -MODULE_PARM_DESC(host_tagset_enable, "Shared host tagset enable/disable Default: enable(1)"); - MODULE_LICENSE("GPL"); MODULE_VERSION(MEGASAS_VERSION); MODULE_AUTHOR("megaraidlinux.pdl@broadcom.com"); @@ -3124,19 +3119,6 @@ megasas_bios_param(struct scsi_device *sdev, struct block_device *bdev, return 0; } -static int megasas_map_queues(struct Scsi_Host *shost) -{ - struct megasas_instance *instance; - - instance = (struct megasas_instance *)shost->hostdata; - - if (shost->nr_hw_queues == 1) - return 0; - - return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], - instance->pdev, instance->low_latency_index_start); -} - static void megasas_aen_polling(struct work_struct *work); /** @@ -3445,7 +3427,6 @@ static struct scsi_host_template megasas_template = { .eh_timed_out = megasas_reset_timer, .shost_attrs = megaraid_host_attrs, .bios_param = megasas_bios_param, - .map_queues = megasas_map_queues, .change_queue_depth = scsi_change_queue_depth, .max_segment_size = 0xffffffff, }; @@ -6827,26 +6808,6 @@ static int megasas_io_attach(struct megasas_instance *instance) host->max_lun = MEGASAS_MAX_LUN; host->max_cmd_len = 16; - /* Use shared host tagset only for fusion adaptors - * if there are managed interrupts (smp affinity enabled case). - * Single msix_vectors in kdump, so shared host tag is also disabled. - */ - - host->host_tagset = 0; - host->nr_hw_queues = 1; - - if ((instance->adapter_type != MFI_SERIES) && - (instance->msix_vectors > instance->low_latency_index_start) && - host_tagset_enable && - instance->smp_affinity_enable) { - host->host_tagset = 1; - host->nr_hw_queues = instance->msix_vectors - - instance->low_latency_index_start; - } - - dev_info(&instance->pdev->dev, - "Max firmware commands: %d shared with nr_hw_queues = %d\n", - instance->max_fw_cmds, host->nr_hw_queues); /* * Notify the mid-layer about the new controller */ diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index fd607287608e..b0c01cf0428f 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -359,29 +359,24 @@ megasas_get_msix_index(struct megasas_instance *instance, { int sdev_busy; - /* TBD - if sml remove device_busy in future, driver - * should track counter in internal structure. - */ - sdev_busy = atomic_read(&scmd->device->device_busy); + /* nr_hw_queue = 1 for MegaRAID */ + struct blk_mq_hw_ctx *hctx = + scmd->device->request_queue->queue_hw_ctx[0]; + + sdev_busy = atomic_read(&hctx->nr_active); if (instance->perf_mode == MR_BALANCED_PERF_MODE && - sdev_busy > (data_arms * MR_DEVICE_HIGH_IOPS_DEPTH)) { + sdev_busy > (data_arms * MR_DEVICE_HIGH_IOPS_DEPTH)) cmd->request_desc->SCSIIO.MSIxIndex = mega_mod64((atomic64_add_return(1, &instance->high_iops_outstanding) / MR_HIGH_IOPS_BATCH_COUNT), instance->low_latency_index_start); - } else if (instance->msix_load_balance) { + else if (instance->msix_load_balance) cmd->request_desc->SCSIIO.MSIxIndex = (mega_mod64(atomic64_add_return(1, &instance->total_io_count), instance->msix_vectors)); - } else if (instance->host->nr_hw_queues > 1) { - u32 tag = blk_mq_unique_tag(scmd->request); - - cmd->request_desc->SCSIIO.MSIxIndex = blk_mq_unique_tag_to_hwq(tag) + - instance->low_latency_index_start; - } else { + else cmd->request_desc->SCSIIO.MSIxIndex = instance->reply_map[raw_smp_processor_id()]; - } } /** @@ -961,6 +956,9 @@ megasas_alloc_cmds_fusion(struct megasas_instance *instance) if (megasas_alloc_cmdlist_fusion(instance)) goto fail_exit; + dev_info(&instance->pdev->dev, "Configured max firmware commands: %d\n", + instance->max_fw_cmds); + /* The first 256 bytes (SMID 0) is not used. Don't add to the cmd list */ io_req_base = fusion->io_request_frames + MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE; io_req_base_phys = fusion->io_request_frames_phys + MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE; @@ -1104,9 +1102,8 @@ megasas_ioc_init_fusion(struct megasas_instance *instance) MR_HIGH_IOPS_QUEUE_COUNT) && cur_intr_coalescing) instance->perf_mode = MR_BALANCED_PERF_MODE; - dev_info(&instance->pdev->dev, "Performance mode :%s (latency index = %d)\n", - MEGASAS_PERF_MODE_2STR(instance->perf_mode), - instance->low_latency_index_start); + dev_info(&instance->pdev->dev, "Performance mode :%s\n", + MEGASAS_PERF_MODE_2STR(instance->perf_mode)); instance->fw_sync_cache_support = (scratch_pad_1 & MR_CAN_HANDLE_SYNC_CACHE_OFFSET) ? 1 : 0; diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index e4cc92bc4d94..bb940cbcbb5d 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -6459,7 +6459,7 @@ _base_send_ioc_init(struct MPT3SAS_ADAPTER *ioc) r = _base_handshake_req_reply_wait(ioc, sizeof(Mpi2IOCInitRequest_t), (u32 *)&mpi_request, - sizeof(Mpi2IOCInitReply_t), (u16 *)&mpi_reply, 10); + sizeof(Mpi2IOCInitReply_t), (u16 *)&mpi_reply, 30); if (r != 0) { ioc_err(ioc, "%s: handshake failed (r=%d)\n", __func__, r); diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index 0f2b681449e6..edd26a2570fa 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -664,7 +664,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg, Mpi26NVMeEncapsulatedRequest_t *nvme_encap_request = NULL; struct _pcie_device *pcie_device = NULL; u16 smid; - u8 timeout; + unsigned long timeout; u8 issue_reset; u32 sz, sz_arg; void *psge; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 60c7a7d74852..03c6d0620bfd 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1703,8 +1703,7 @@ out_put_budget: break; case BLK_STS_RESOURCE: case BLK_STS_ZONE_RESOURCE: - if (atomic_read(&sdev->device_busy) || - scsi_device_blocked(sdev)) + if (scsi_device_blocked(sdev)) ret = BLK_STS_DEV_RESOURCE; break; default: diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 0c65fbd41035..ded00a89bfc4 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1994,8 +1994,10 @@ static int storvsc_probe(struct hv_device *device, alloc_ordered_workqueue("storvsc_error_wq_%d", WQ_MEM_RECLAIM, host->host_no); - if (!host_dev->handle_error_wq) + if (!host_dev->handle_error_wq) { + ret = -ENOMEM; goto err_out2; + } INIT_WORK(&host_dev->host_scan_work, storvsc_host_scan); /* Register the HBA and start the scsi bus scan */ ret = scsi_add_host(host, &device->device); diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index b8f573a02713..0c148fcd24de 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -1294,8 +1294,15 @@ static int ufshcd_devfreq_target(struct device *dev, } spin_unlock_irqrestore(hba->host->host_lock, irq_flags); + pm_runtime_get_noresume(hba->dev); + if (!pm_runtime_active(hba->dev)) { + pm_runtime_put_noidle(hba->dev); + ret = -EAGAIN; + goto out; + } start = ktime_get(); ret = ufshcd_devfreq_scale(hba, scale_up); + pm_runtime_put(hba->dev); trace_ufshcd_profile_clk_scaling(dev_name(hba->dev), (scale_up ? "up" : "down"), @@ -1627,12 +1634,12 @@ start: */ fallthrough; case CLKS_OFF: - ufshcd_scsi_block_requests(hba); hba->clk_gating.state = REQ_CLKS_ON; trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state); - queue_work(hba->clk_gating.clk_gating_workq, - &hba->clk_gating.ungate_work); + if (queue_work(hba->clk_gating.clk_gating_workq, + &hba->clk_gating.ungate_work)) + ufshcd_scsi_block_requests(hba); /* * fall through to check if we should wait for this * work to be done or not. @@ -2115,10 +2122,20 @@ ufshcd_wait_for_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd) unsigned long flags; if (wait_for_completion_timeout(&uic_cmd->done, - msecs_to_jiffies(UIC_CMD_TIMEOUT))) + msecs_to_jiffies(UIC_CMD_TIMEOUT))) { ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT; - else + } else { ret = -ETIMEDOUT; + dev_err(hba->dev, + "uic cmd 0x%x with arg3 0x%x completion timeout\n", + uic_cmd->command, uic_cmd->argument3); + + if (!uic_cmd->cmd_active) { + dev_err(hba->dev, "%s: UIC cmd has been completed, return the result\n", + __func__); + ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT; + } + } spin_lock_irqsave(hba->host->host_lock, flags); hba->active_uic_cmd = NULL; @@ -2150,6 +2167,7 @@ __ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd, if (completion) init_completion(&uic_cmd->done); + uic_cmd->cmd_active = 1; ufshcd_dispatch_uic_cmd(hba, uic_cmd); return 0; @@ -3181,13 +3199,19 @@ int ufshcd_read_desc_param(struct ufs_hba *hba, /* Get the length of descriptor */ ufshcd_map_desc_id_to_length(hba, desc_id, &buff_len); if (!buff_len) { - dev_err(hba->dev, "%s: Failed to get desc length", __func__); + dev_err(hba->dev, "%s: Failed to get desc length\n", __func__); + return -EINVAL; + } + + if (param_offset >= buff_len) { + dev_err(hba->dev, "%s: Invalid offset 0x%x in descriptor IDN 0x%x, length 0x%x\n", + __func__, param_offset, desc_id, buff_len); return -EINVAL; } /* Check whether we need temp memory */ if (param_offset != 0 || param_size < buff_len) { - desc_buf = kmalloc(buff_len, GFP_KERNEL); + desc_buf = kzalloc(buff_len, GFP_KERNEL); if (!desc_buf) return -ENOMEM; } else { @@ -3201,14 +3225,14 @@ int ufshcd_read_desc_param(struct ufs_hba *hba, desc_buf, &buff_len); if (ret) { - dev_err(hba->dev, "%s: Failed reading descriptor. desc_id %d, desc_index %d, param_offset %d, ret %d", + dev_err(hba->dev, "%s: Failed reading descriptor. desc_id %d, desc_index %d, param_offset %d, ret %d\n", __func__, desc_id, desc_index, param_offset, ret); goto out; } /* Sanity check */ if (desc_buf[QUERY_DESC_DESC_TYPE_OFFSET] != desc_id) { - dev_err(hba->dev, "%s: invalid desc_id %d in descriptor header", + dev_err(hba->dev, "%s: invalid desc_id %d in descriptor header\n", __func__, desc_buf[QUERY_DESC_DESC_TYPE_OFFSET]); ret = -EINVAL; goto out; @@ -3218,12 +3242,12 @@ int ufshcd_read_desc_param(struct ufs_hba *hba, buff_len = desc_buf[QUERY_DESC_LENGTH_OFFSET]; ufshcd_update_desc_length(hba, desc_id, desc_index, buff_len); - /* Check wherher we will not copy more data, than available */ - if (is_kmalloc && (param_offset + param_size) > buff_len) - param_size = buff_len - param_offset; - - if (is_kmalloc) + if (is_kmalloc) { + /* Make sure we don't copy more data than available */ + if (param_offset + param_size > buff_len) + param_size = buff_len - param_offset; memcpy(param_read_buf, &desc_buf[param_offset], param_size); + } out: if (is_kmalloc) kfree(desc_buf); @@ -3807,10 +3831,18 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd) dev_err(hba->dev, "pwr ctrl cmd 0x%x with mode 0x%x completion timeout\n", cmd->command, cmd->argument3); + + if (!cmd->cmd_active) { + dev_err(hba->dev, "%s: Power Mode Change operation has been completed, go check UPMCRS\n", + __func__); + goto check_upmcrs; + } + ret = -ETIMEDOUT; goto out; } +check_upmcrs: status = ufshcd_get_upmcrs(hba); if (status != PWR_LOCAL) { dev_err(hba->dev, @@ -4902,11 +4934,14 @@ static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status) ufshcd_get_uic_cmd_result(hba); hba->active_uic_cmd->argument3 = ufshcd_get_dme_attr_val(hba); + if (!hba->uic_async_done) + hba->active_uic_cmd->cmd_active = 0; complete(&hba->active_uic_cmd->done); retval = IRQ_HANDLED; } if ((intr_status & UFSHCD_UIC_PWR_MASK) && hba->uic_async_done) { + hba->active_uic_cmd->cmd_active = 0; complete(hba->uic_async_done); retval = IRQ_HANDLED; } @@ -8878,11 +8913,7 @@ int ufshcd_shutdown(struct ufs_hba *hba) if (ufshcd_is_ufs_dev_poweroff(hba) && ufshcd_is_link_off(hba)) goto out; - if (pm_runtime_suspended(hba->dev)) { - ret = ufshcd_runtime_resume(hba); - if (ret) - goto out; - } + pm_runtime_get_sync(hba->dev); ret = ufshcd_suspend(hba, UFS_SHUTDOWN_PM); out: @@ -8906,6 +8937,7 @@ void ufshcd_remove(struct ufs_hba *hba) blk_mq_free_tag_set(&hba->tmf_tag_set); blk_cleanup_queue(hba->cmd_queue); scsi_remove_host(hba->host); + destroy_workqueue(hba->eh_wq); /* disable interrupts */ ufshcd_disable_intr(hba, hba->intr_mask); ufshcd_hba_stop(hba); @@ -9206,6 +9238,7 @@ out_remove_scsi_host: exit_gating: ufshcd_exit_clk_scaling(hba); ufshcd_exit_clk_gating(hba); + destroy_workqueue(hba->eh_wq); out_disable: hba->is_irq_enabled = false; ufshcd_hba_exit(hba); diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index 47eb1430274c..e0f00a42371c 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -64,6 +64,7 @@ enum dev_cmd_type { * @argument1: UIC command argument 1 * @argument2: UIC command argument 2 * @argument3: UIC command argument 3 + * @cmd_active: Indicate if UIC command is outstanding * @done: UIC command completion */ struct uic_command { @@ -71,6 +72,7 @@ struct uic_command { u32 argument1; u32 argument2; u32 argument3; + int cmd_active; struct completion done; }; diff --git a/drivers/soc/fsl/dpio/dpio-driver.c b/drivers/soc/fsl/dpio/dpio-driver.c index 7b642c330977..7f397b4ad878 100644 --- a/drivers/soc/fsl/dpio/dpio-driver.c +++ b/drivers/soc/fsl/dpio/dpio-driver.c @@ -95,7 +95,6 @@ static int register_dpio_irq_handlers(struct fsl_mc_device *dpio_dev, int cpu) { int error; struct fsl_mc_device_irq *irq; - cpumask_t mask; irq = dpio_dev->irqs[0]; error = devm_request_irq(&dpio_dev->dev, @@ -112,9 +111,7 @@ static int register_dpio_irq_handlers(struct fsl_mc_device *dpio_dev, int cpu) } /* set the affinity hint */ - cpumask_clear(&mask); - cpumask_set_cpu(cpu, &mask); - if (irq_set_affinity_hint(irq->msi_desc->irq, &mask)) + if (irq_set_affinity_hint(irq->msi_desc->irq, cpumask_of(cpu))) dev_err(&dpio_dev->dev, "irq_set_affinity failed irq %d cpu %d\n", irq->msi_desc->irq, cpu); diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 14c9d0133bce..c028446c7460 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -1327,7 +1327,7 @@ int bcm_qspi_probe(struct platform_device *pdev, data = of_id->data; - master = spi_alloc_master(dev, sizeof(struct bcm_qspi)); + master = devm_spi_alloc_master(dev, sizeof(struct bcm_qspi)); if (!master) { dev_err(dev, "error allocating spi_master\n"); return -ENOMEM; @@ -1367,21 +1367,17 @@ int bcm_qspi_probe(struct platform_device *pdev, if (res) { qspi->base[MSPI] = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->base[MSPI])) { - ret = PTR_ERR(qspi->base[MSPI]); - goto qspi_resource_err; - } + if (IS_ERR(qspi->base[MSPI])) + return PTR_ERR(qspi->base[MSPI]); } else { - goto qspi_resource_err; + return 0; } res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "bspi"); if (res) { qspi->base[BSPI] = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->base[BSPI])) { - ret = PTR_ERR(qspi->base[BSPI]); - goto qspi_resource_err; - } + if (IS_ERR(qspi->base[BSPI])) + return PTR_ERR(qspi->base[BSPI]); qspi->bspi_mode = true; } else { qspi->bspi_mode = false; @@ -1392,18 +1388,14 @@ int bcm_qspi_probe(struct platform_device *pdev, res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cs_reg"); if (res) { qspi->base[CHIP_SELECT] = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->base[CHIP_SELECT])) { - ret = PTR_ERR(qspi->base[CHIP_SELECT]); - goto qspi_resource_err; - } + if (IS_ERR(qspi->base[CHIP_SELECT])) + return PTR_ERR(qspi->base[CHIP_SELECT]); } qspi->dev_ids = kcalloc(num_irqs, sizeof(struct bcm_qspi_dev_id), GFP_KERNEL); - if (!qspi->dev_ids) { - ret = -ENOMEM; - goto qspi_resource_err; - } + if (!qspi->dev_ids) + return -ENOMEM; for (val = 0; val < num_irqs; val++) { irq = -1; @@ -1484,7 +1476,7 @@ int bcm_qspi_probe(struct platform_device *pdev, qspi->xfer_mode.addrlen = -1; qspi->xfer_mode.hp = -1; - ret = devm_spi_register_master(&pdev->dev, master); + ret = spi_register_master(master); if (ret < 0) { dev_err(dev, "can't register master\n"); goto qspi_reg_err; @@ -1497,8 +1489,6 @@ qspi_reg_err: clk_disable_unprepare(qspi->clk); qspi_probe_err: kfree(qspi->dev_ids); -qspi_resource_err: - spi_master_put(master); return ret; } /* probe function to be called by SoC specific platform driver probe */ @@ -1508,10 +1498,10 @@ int bcm_qspi_remove(struct platform_device *pdev) { struct bcm_qspi *qspi = platform_get_drvdata(pdev); + spi_unregister_master(qspi->master); bcm_qspi_hw_uninit(qspi); clk_disable_unprepare(qspi->clk); kfree(qspi->dev_ids); - spi_unregister_master(qspi->master); return 0; } diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index 7104cf17b848..197485f2c2b2 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -1278,7 +1278,7 @@ static int bcm2835_spi_probe(struct platform_device *pdev) struct bcm2835_spi *bs; int err; - ctlr = spi_alloc_master(&pdev->dev, ALIGN(sizeof(*bs), + ctlr = devm_spi_alloc_master(&pdev->dev, ALIGN(sizeof(*bs), dma_get_cache_alignment())); if (!ctlr) return -ENOMEM; @@ -1299,23 +1299,17 @@ static int bcm2835_spi_probe(struct platform_device *pdev) bs->ctlr = ctlr; bs->regs = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(bs->regs)) { - err = PTR_ERR(bs->regs); - goto out_controller_put; - } + if (IS_ERR(bs->regs)) + return PTR_ERR(bs->regs); bs->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(bs->clk)) { - err = dev_err_probe(&pdev->dev, PTR_ERR(bs->clk), - "could not get clk\n"); - goto out_controller_put; - } + if (IS_ERR(bs->clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(bs->clk), + "could not get clk\n"); bs->irq = platform_get_irq(pdev, 0); - if (bs->irq <= 0) { - err = bs->irq ? bs->irq : -ENODEV; - goto out_controller_put; - } + if (bs->irq <= 0) + return bs->irq ? bs->irq : -ENODEV; clk_prepare_enable(bs->clk); @@ -1349,8 +1343,6 @@ out_dma_release: bcm2835_dma_release(ctlr, bs); out_clk_disable: clk_disable_unprepare(bs->clk); -out_controller_put: - spi_controller_put(ctlr); return err; } diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c index 03b034c15d2b..1a26865c42f8 100644 --- a/drivers/spi/spi-bcm2835aux.c +++ b/drivers/spi/spi-bcm2835aux.c @@ -494,7 +494,7 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev) unsigned long clk_hz; int err; - master = spi_alloc_master(&pdev->dev, sizeof(*bs)); + master = devm_spi_alloc_master(&pdev->dev, sizeof(*bs)); if (!master) return -ENOMEM; @@ -524,29 +524,25 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev) /* the main area */ bs->regs = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(bs->regs)) { - err = PTR_ERR(bs->regs); - goto out_master_put; - } + if (IS_ERR(bs->regs)) + return PTR_ERR(bs->regs); bs->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(bs->clk)) { err = PTR_ERR(bs->clk); dev_err(&pdev->dev, "could not get clk: %d\n", err); - goto out_master_put; + return err; } bs->irq = platform_get_irq(pdev, 0); - if (bs->irq <= 0) { - err = bs->irq ? bs->irq : -ENODEV; - goto out_master_put; - } + if (bs->irq <= 0) + return bs->irq ? bs->irq : -ENODEV; /* this also enables the HW block */ err = clk_prepare_enable(bs->clk); if (err) { dev_err(&pdev->dev, "could not prepare clock: %d\n", err); - goto out_master_put; + return err; } /* just checking if the clock returns a sane value */ @@ -581,8 +577,6 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev) out_clk_disable: clk_disable_unprepare(bs->clk); -out_master_put: - spi_master_put(master); return err; } diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 40938cf3806d..ba7d40c2922f 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1260,12 +1260,14 @@ static int cqspi_probe(struct platform_device *pdev) /* Obtain QSPI reset control */ rstc = devm_reset_control_get_optional_exclusive(dev, "qspi"); if (IS_ERR(rstc)) { + ret = PTR_ERR(rstc); dev_err(dev, "Cannot get QSPI reset.\n"); goto probe_reset_failed; } rstc_ocp = devm_reset_control_get_optional_exclusive(dev, "qspi-ocp"); if (IS_ERR(rstc_ocp)) { + ret = PTR_ERR(rstc_ocp); dev_err(dev, "Cannot get QSPI OCP reset.\n"); goto probe_reset_failed; } diff --git a/drivers/spi/spi-dw-core.c b/drivers/spi/spi-dw-core.c index 2e50cc0a9291..c33866f747db 100644 --- a/drivers/spi/spi-dw-core.c +++ b/drivers/spi/spi-dw-core.c @@ -357,11 +357,11 @@ static void dw_spi_irq_setup(struct dw_spi *dws) dw_writel(dws, DW_SPI_TXFTLR, level); dw_writel(dws, DW_SPI_RXFTLR, level - 1); + dws->transfer_handler = dw_spi_transfer_handler; + imask = SPI_INT_TXEI | SPI_INT_TXOI | SPI_INT_RXUI | SPI_INT_RXOI | SPI_INT_RXFI; spi_umask_intr(dws, imask); - - dws->transfer_handler = dw_spi_transfer_handler; } /* @@ -875,7 +875,8 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws) master->set_cs = dw_spi_set_cs; master->transfer_one = dw_spi_transfer_one; master->handle_err = dw_spi_handle_err; - master->mem_ops = &dws->mem_ops; + if (dws->mem_ops.exec_op) + master->mem_ops = &dws->mem_ops; master->max_speed_hz = dws->max_freq; master->dev.of_node = dev->of_node; master->dev.fwnode = dev->fwnode; diff --git a/drivers/spi/spi-fsi.c b/drivers/spi/spi-fsi.c index 8a440c7078ef..3920cd3286d8 100644 --- a/drivers/spi/spi-fsi.c +++ b/drivers/spi/spi-fsi.c @@ -477,7 +477,7 @@ static int fsi_spi_transfer_one_message(struct spi_controller *ctlr, rc = fsi_spi_check_mux(ctx->fsi, ctx->dev); if (rc) - return rc; + goto error; list_for_each_entry(transfer, &mesg->transfers, transfer_list) { struct fsi_spi_sequence seq; diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index 986b9793fd3c..a2886ee44e4c 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -938,9 +938,6 @@ static int fsl_lpspi_remove(struct platform_device *pdev) spi_controller_get_devdata(controller); pm_runtime_disable(fsl_lpspi->dev); - - spi_master_put(controller); - return 0; } diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 4b80e27ecdbf..0b597905ee72 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -1686,6 +1686,7 @@ static int spi_imx_probe(struct platform_device *pdev) pm_runtime_set_autosuspend_delay(spi_imx->dev, MXC_RPM_TIMEOUT); pm_runtime_use_autosuspend(spi_imx->dev); + pm_runtime_get_noresume(spi_imx->dev); pm_runtime_set_active(spi_imx->dev); pm_runtime_enable(spi_imx->dev); diff --git a/drivers/spi/spi-npcm-fiu.c b/drivers/spi/spi-npcm-fiu.c index 341f7cffeaac..1cb9329de945 100644 --- a/drivers/spi/spi-npcm-fiu.c +++ b/drivers/spi/spi-npcm-fiu.c @@ -679,7 +679,7 @@ static int npcm_fiu_probe(struct platform_device *pdev) struct resource *res; int id; - ctrl = spi_alloc_master(dev, sizeof(*fiu)); + ctrl = devm_spi_alloc_master(dev, sizeof(*fiu)); if (!ctrl) return -ENOMEM; diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c index 0d41406c036d..ab9035662717 100644 --- a/drivers/spi/spi-nxp-fspi.c +++ b/drivers/spi/spi-nxp-fspi.c @@ -1001,6 +1001,7 @@ static int nxp_fspi_probe(struct platform_device *pdev) struct resource *res; struct nxp_fspi *f; int ret; + u32 reg; ctlr = spi_alloc_master(&pdev->dev, sizeof(*f)); if (!ctlr) @@ -1032,6 +1033,12 @@ static int nxp_fspi_probe(struct platform_device *pdev) goto err_put_ctrl; } + /* Clear potential interrupts */ + reg = fspi_readl(f, f->iobase + FSPI_INTR); + if (reg) + fspi_writel(f, reg, f->iobase + FSPI_INTR); + + /* find the resources - controller memory mapped space */ if (is_acpi_node(f->dev->fwnode)) res = platform_get_resource(pdev, IORESOURCE_MEM, 1); diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 0cab239d8e7f..fc9a59788d2e 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -812,18 +812,16 @@ static void spi_set_cs(struct spi_device *spi, bool enable) enable = !enable; if (spi->cs_gpiod || gpio_is_valid(spi->cs_gpio)) { - /* - * Honour the SPI_NO_CS flag and invert the enable line, as - * active low is default for SPI. Execution paths that handle - * polarity inversion in gpiolib (such as device tree) will - * enforce active high using the SPI_CS_HIGH resulting in a - * double inversion through the code above. - */ if (!(spi->mode & SPI_NO_CS)) { if (spi->cs_gpiod) + /* polarity handled by gpiolib */ gpiod_set_value_cansleep(spi->cs_gpiod, - !enable); + enable1); else + /* + * invert the enable line, as active low is + * default for SPI. + */ gpio_set_value_cansleep(spi->cs_gpio, !enable); } /* Some SPI masters need both GPIO CS & slave_select */ @@ -1992,15 +1990,6 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, } spi->chip_select = value; - /* - * For descriptors associated with the device, polarity inversion is - * handled in the gpiolib, so all gpio chip selects are "active high" - * in the logical sense, the gpiolib will invert the line if need be. - */ - if ((ctlr->use_gpio_descriptors) && ctlr->cs_gpiods && - ctlr->cs_gpiods[spi->chip_select]) - spi->mode |= SPI_CS_HIGH; - /* Device speed */ if (!of_property_read_u32(nc, "spi-max-frequency", &value)) spi->max_speed_hz = value; @@ -2453,6 +2442,49 @@ struct spi_controller *__spi_alloc_controller(struct device *dev, } EXPORT_SYMBOL_GPL(__spi_alloc_controller); +static void devm_spi_release_controller(struct device *dev, void *ctlr) +{ + spi_controller_put(*(struct spi_controller **)ctlr); +} + +/** + * __devm_spi_alloc_controller - resource-managed __spi_alloc_controller() + * @dev: physical device of SPI controller + * @size: how much zeroed driver-private data to allocate + * @slave: whether to allocate an SPI master (false) or SPI slave (true) + * Context: can sleep + * + * Allocate an SPI controller and automatically release a reference on it + * when @dev is unbound from its driver. Drivers are thus relieved from + * having to call spi_controller_put(). + * + * The arguments to this function are identical to __spi_alloc_controller(). + * + * Return: the SPI controller structure on success, else NULL. + */ +struct spi_controller *__devm_spi_alloc_controller(struct device *dev, + unsigned int size, + bool slave) +{ + struct spi_controller **ptr, *ctlr; + + ptr = devres_alloc(devm_spi_release_controller, sizeof(*ptr), + GFP_KERNEL); + if (!ptr) + return NULL; + + ctlr = __spi_alloc_controller(dev, size, slave); + if (ctlr) { + *ptr = ctlr; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return ctlr; +} +EXPORT_SYMBOL_GPL(__devm_spi_alloc_controller); + #ifdef CONFIG_OF static int of_spi_get_gpio_numbers(struct spi_controller *ctlr) { @@ -2789,6 +2821,11 @@ int devm_spi_register_controller(struct device *dev, } EXPORT_SYMBOL_GPL(devm_spi_register_controller); +static int devm_spi_match_controller(struct device *dev, void *res, void *ctlr) +{ + return *(struct spi_controller **)res == ctlr; +} + static int __unregister(struct device *dev, void *null) { spi_unregister_device(to_spi_device(dev)); @@ -2830,7 +2867,15 @@ void spi_unregister_controller(struct spi_controller *ctlr) list_del(&ctlr->list); mutex_unlock(&board_lock); - device_unregister(&ctlr->dev); + device_del(&ctlr->dev); + + /* Release the last reference on the controller if its driver + * has not yet been converted to devm_spi_alloc_master/slave(). + */ + if (!devres_find(ctlr->dev.parent, devm_spi_release_controller, + devm_spi_match_controller, ctlr)) + put_device(&ctlr->dev); + /* free bus id */ mutex_lock(&board_lock); if (found == ctlr) @@ -3327,12 +3372,15 @@ int spi_setup(struct spi_device *spi) if (!spi->max_speed_hz) spi->max_speed_hz = spi->controller->max_speed_hz; + mutex_lock(&spi->controller->io_mutex); + if (spi->controller->setup) status = spi->controller->setup(spi); if (spi->controller->auto_runtime_pm && spi->controller->set_cs) { status = pm_runtime_get_sync(spi->controller->dev.parent); if (status < 0) { + mutex_unlock(&spi->controller->io_mutex); pm_runtime_put_noidle(spi->controller->dev.parent); dev_err(&spi->controller->dev, "Failed to power device: %d\n", status); @@ -3354,6 +3402,8 @@ int spi_setup(struct spi_device *spi) spi_set_cs(spi, false); } + mutex_unlock(&spi->controller->io_mutex); + if (spi->rt && !spi->controller->rt) { spi->controller->rt = true; spi_set_thread_rt(spi->controller); diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c index 28319351e909..781c84a9b1b7 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c @@ -446,7 +446,7 @@ static void cedrus_set_params(struct cedrus_ctx *ctx, reg |= (pps->second_chroma_qp_index_offset & 0x3f) << 16; reg |= (pps->chroma_qp_index_offset & 0x3f) << 8; reg |= (pps->pic_init_qp_minus26 + 26 + slice->slice_qp_delta) & 0x3f; - if (pps->flags & V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT) + if (!(pps->flags & V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT)) reg |= VE_H264_SHS_QP_SCALING_MATRIX_DEFAULT; cedrus_write(dev, VE_H264_SHS_QP, reg); diff --git a/drivers/staging/mt7621-pci/pci-mt7621.c b/drivers/staging/mt7621-pci/pci-mt7621.c index f961b353c22e..8831db383fad 100644 --- a/drivers/staging/mt7621-pci/pci-mt7621.c +++ b/drivers/staging/mt7621-pci/pci-mt7621.c @@ -653,16 +653,11 @@ static int mt7621_pcie_init_virtual_bridges(struct mt7621_pcie *pcie) return 0; } -static int mt7621_pcie_request_resources(struct mt7621_pcie *pcie, - struct list_head *res) +static void mt7621_pcie_add_resources(struct mt7621_pcie *pcie, + struct list_head *res) { - struct device *dev = pcie->dev; - pci_add_resource_offset(res, &pcie->io, pcie->offset.io); pci_add_resource_offset(res, &pcie->mem, pcie->offset.mem); - pci_add_resource(res, &pcie->busn); - - return devm_request_pci_bus_resources(dev, res); } static int mt7621_pcie_register_host(struct pci_host_bridge *host, @@ -738,11 +733,7 @@ static int mt7621_pci_probe(struct platform_device *pdev) setup_cm_memory_region(pcie); - err = mt7621_pcie_request_resources(pcie, &res); - if (err) { - dev_err(dev, "Error requesting resources\n"); - return err; - } + mt7621_pcie_add_resources(pcie, &res); err = mt7621_pcie_register_host(bridge, &res); if (err) { diff --git a/drivers/staging/ralink-gdma/Kconfig b/drivers/staging/ralink-gdma/Kconfig index 54e8029e6b1a..0017376234e2 100644 --- a/drivers/staging/ralink-gdma/Kconfig +++ b/drivers/staging/ralink-gdma/Kconfig @@ -2,6 +2,7 @@ config DMA_RALINK tristate "RALINK DMA support" depends on RALINK && !SOC_RT288X + depends on DMADEVICES select DMA_ENGINE select DMA_VIRTUAL_CHANNELS diff --git a/drivers/staging/rtl8723bs/os_dep/sdio_intf.c b/drivers/staging/rtl8723bs/os_dep/sdio_intf.c index 79b55ec827a4..b2208e5f190a 100644 --- a/drivers/staging/rtl8723bs/os_dep/sdio_intf.c +++ b/drivers/staging/rtl8723bs/os_dep/sdio_intf.c @@ -20,6 +20,7 @@ static const struct sdio_device_id sdio_ids[] = { { SDIO_DEVICE(0x024c, 0x0525), }, { SDIO_DEVICE(0x024c, 0x0623), }, { SDIO_DEVICE(0x024c, 0x0626), }, + { SDIO_DEVICE(0x024c, 0x0627), }, { SDIO_DEVICE(0x024c, 0xb723), }, { /* end: all zeroes */ }, }; diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index f77e5eee6b80..518fac4864cf 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -483,8 +483,7 @@ EXPORT_SYMBOL(iscsit_queue_rsp); void iscsit_aborted_task(struct iscsi_conn *conn, struct iscsi_cmd *cmd) { spin_lock_bh(&conn->cmd_lock); - if (!list_empty(&cmd->i_conn_node) && - !(cmd->se_cmd.transport_state & CMD_T_FABRIC_STOP)) + if (!list_empty(&cmd->i_conn_node)) list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); @@ -4083,12 +4082,22 @@ static void iscsit_release_commands_from_conn(struct iscsi_conn *conn) spin_lock_bh(&conn->cmd_lock); list_splice_init(&conn->conn_cmd_list, &tmp_list); - list_for_each_entry(cmd, &tmp_list, i_conn_node) { + list_for_each_entry_safe(cmd, cmd_tmp, &tmp_list, i_conn_node) { struct se_cmd *se_cmd = &cmd->se_cmd; if (se_cmd->se_tfo != NULL) { spin_lock_irq(&se_cmd->t_state_lock); - se_cmd->transport_state |= CMD_T_FABRIC_STOP; + if (se_cmd->transport_state & CMD_T_ABORTED) { + /* + * LIO's abort path owns the cleanup for this, + * so put it back on the list and let + * aborted_task handle it. + */ + list_move_tail(&cmd->i_conn_node, + &conn->conn_cmd_list); + } else { + se_cmd->transport_state |= CMD_T_FABRIC_STOP; + } spin_unlock_irq(&se_cmd->t_state_lock); } } diff --git a/drivers/tee/amdtee/amdtee_private.h b/drivers/tee/amdtee/amdtee_private.h index d7f798c3394b..337c8d82f74e 100644 --- a/drivers/tee/amdtee/amdtee_private.h +++ b/drivers/tee/amdtee/amdtee_private.h @@ -64,9 +64,13 @@ struct amdtee_session { /** * struct amdtee_context_data - AMD-TEE driver context data * @sess_list: Keeps track of sessions opened in current TEE context + * @shm_list: Keeps track of buffers allocated and mapped in current TEE + * context */ struct amdtee_context_data { struct list_head sess_list; + struct list_head shm_list; + struct mutex shm_mutex; /* synchronizes access to @shm_list */ }; struct amdtee_driver_data { @@ -89,10 +93,6 @@ struct amdtee_shm_data { u32 buf_id; }; -struct amdtee_shm_context { - struct list_head shmdata_list; -}; - #define LOWER_TWO_BYTE_MASK 0x0000FFFF /** diff --git a/drivers/tee/amdtee/core.c b/drivers/tee/amdtee/core.c index 27b4cd77d0db..8a6a8f30bb42 100644 --- a/drivers/tee/amdtee/core.c +++ b/drivers/tee/amdtee/core.c @@ -20,7 +20,6 @@ static struct amdtee_driver_data *drv_data; static DEFINE_MUTEX(session_list_mutex); -static struct amdtee_shm_context shmctx; static void amdtee_get_version(struct tee_device *teedev, struct tee_ioctl_version_data *vers) @@ -42,7 +41,8 @@ static int amdtee_open(struct tee_context *ctx) return -ENOMEM; INIT_LIST_HEAD(&ctxdata->sess_list); - INIT_LIST_HEAD(&shmctx.shmdata_list); + INIT_LIST_HEAD(&ctxdata->shm_list); + mutex_init(&ctxdata->shm_mutex); ctx->data = ctxdata; return 0; @@ -86,6 +86,7 @@ static void amdtee_release(struct tee_context *ctx) list_del(&sess->list_node); release_session(sess); } + mutex_destroy(&ctxdata->shm_mutex); kfree(ctxdata); ctx->data = NULL; @@ -152,14 +153,17 @@ static struct amdtee_session *find_session(struct amdtee_context_data *ctxdata, u32 get_buffer_id(struct tee_shm *shm) { - u32 buf_id = 0; + struct amdtee_context_data *ctxdata = shm->ctx->data; struct amdtee_shm_data *shmdata; + u32 buf_id = 0; - list_for_each_entry(shmdata, &shmctx.shmdata_list, shm_node) + mutex_lock(&ctxdata->shm_mutex); + list_for_each_entry(shmdata, &ctxdata->shm_list, shm_node) if (shmdata->kaddr == shm->kaddr) { buf_id = shmdata->buf_id; break; } + mutex_unlock(&ctxdata->shm_mutex); return buf_id; } @@ -333,8 +337,9 @@ int amdtee_close_session(struct tee_context *ctx, u32 session) int amdtee_map_shmem(struct tee_shm *shm) { - struct shmem_desc shmem; + struct amdtee_context_data *ctxdata; struct amdtee_shm_data *shmnode; + struct shmem_desc shmem; int rc, count; u32 buf_id; @@ -362,7 +367,10 @@ int amdtee_map_shmem(struct tee_shm *shm) shmnode->kaddr = shm->kaddr; shmnode->buf_id = buf_id; - list_add(&shmnode->shm_node, &shmctx.shmdata_list); + ctxdata = shm->ctx->data; + mutex_lock(&ctxdata->shm_mutex); + list_add(&shmnode->shm_node, &ctxdata->shm_list); + mutex_unlock(&ctxdata->shm_mutex); pr_debug("buf_id :[%x] kaddr[%p]\n", shmnode->buf_id, shmnode->kaddr); @@ -371,6 +379,7 @@ int amdtee_map_shmem(struct tee_shm *shm) void amdtee_unmap_shmem(struct tee_shm *shm) { + struct amdtee_context_data *ctxdata; struct amdtee_shm_data *shmnode; u32 buf_id; @@ -381,12 +390,15 @@ void amdtee_unmap_shmem(struct tee_shm *shm) /* Unmap the shared memory from TEE */ handle_unmap_shmem(buf_id); - list_for_each_entry(shmnode, &shmctx.shmdata_list, shm_node) + ctxdata = shm->ctx->data; + mutex_lock(&ctxdata->shm_mutex); + list_for_each_entry(shmnode, &ctxdata->shm_list, shm_node) if (buf_id == shmnode->buf_id) { list_del(&shmnode->shm_node); kfree(shmnode); break; } + mutex_unlock(&ctxdata->shm_mutex); } int amdtee_invoke_func(struct tee_context *ctx, diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c index 20b6fd7383c5..c981757ba0d4 100644 --- a/drivers/tee/optee/call.c +++ b/drivers/tee/optee/call.c @@ -534,7 +534,8 @@ void optee_free_pages_list(void *list, size_t num_entries) static bool is_normal_memory(pgprot_t p) { #if defined(CONFIG_ARM) - return (pgprot_val(p) & L_PTE_MT_MASK) == L_PTE_MT_WRITEALLOC; + return (((pgprot_val(p) & L_PTE_MT_MASK) == L_PTE_MT_WRITEALLOC) || + ((pgprot_val(p) & L_PTE_MT_MASK) == L_PTE_MT_WRITEBACK)); #elif defined(CONFIG_ARM64) return (pgprot_val(p) & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL); #else diff --git a/drivers/thermal/ti-soc-thermal/ti-bandgap.c b/drivers/thermal/ti-soc-thermal/ti-bandgap.c index 5e596168ba73..dcac99f327b0 100644 --- a/drivers/thermal/ti-soc-thermal/ti-bandgap.c +++ b/drivers/thermal/ti-soc-thermal/ti-bandgap.c @@ -20,6 +20,7 @@ #include <linux/err.h> #include <linux/types.h> #include <linux/spinlock.h> +#include <linux/sys_soc.h> #include <linux/reboot.h> #include <linux/of_device.h> #include <linux/of_platform.h> @@ -864,6 +865,17 @@ static struct ti_bandgap *ti_bandgap_build(struct platform_device *pdev) return bgp; } +/* + * List of SoCs on which the CPU PM notifier can cause erros on the DTEMP + * readout. + * Enabled notifier on these machines results in erroneous, random values which + * could trigger unexpected thermal shutdown. + */ +static const struct soc_device_attribute soc_no_cpu_notifier[] = { + { .machine = "OMAP4430" }, + { /* sentinel */ }, +}; + /*** Device driver call backs ***/ static @@ -1020,7 +1032,8 @@ int ti_bandgap_probe(struct platform_device *pdev) #ifdef CONFIG_PM_SLEEP bgp->nb.notifier_call = bandgap_omap_cpu_notifier; - cpu_pm_register_notifier(&bgp->nb); + if (!soc_device_match(soc_no_cpu_notifier)) + cpu_pm_register_notifier(&bgp->nb); #endif return 0; @@ -1056,7 +1069,8 @@ int ti_bandgap_remove(struct platform_device *pdev) struct ti_bandgap *bgp = platform_get_drvdata(pdev); int i; - cpu_pm_unregister_notifier(&bgp->nb); + if (!soc_device_match(soc_no_cpu_notifier)) + cpu_pm_unregister_notifier(&bgp->nb); /* Remove sensor interfaces */ for (i = 0; i < bgp->conf->sensor_count; i++) { diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c index 3680b2784ea1..ed65d2b13964 100644 --- a/drivers/thunderbolt/debugfs.c +++ b/drivers/thunderbolt/debugfs.c @@ -9,6 +9,7 @@ #include <linux/debugfs.h> #include <linux/pm_runtime.h> +#include <linux/uaccess.h> #include "tb.h" diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index b51fc3f62b1f..82c46b200c34 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -1976,7 +1976,9 @@ static int complete_rpm(struct device *dev, void *data) static void remove_unplugged_switch(struct tb_switch *sw) { - pm_runtime_get_sync(sw->dev.parent); + struct device *parent = get_device(sw->dev.parent); + + pm_runtime_get_sync(parent); /* * Signal this and switches below for rpm_complete because @@ -1987,8 +1989,10 @@ static void remove_unplugged_switch(struct tb_switch *sw) bus_for_each_dev(&tb_bus_type, &sw->dev, NULL, complete_rpm); tb_switch_remove(sw); - pm_runtime_mark_last_busy(sw->dev.parent); - pm_runtime_put_autosuspend(sw->dev.parent); + pm_runtime_mark_last_busy(parent); + pm_runtime_put_autosuspend(parent); + + put_device(parent); } static void icm_free_unplugged_children(struct tb_switch *sw) @@ -2284,6 +2288,8 @@ struct tb *icm_probe(struct tb_nhi *nhi) case PCI_DEVICE_ID_INTEL_TGL_NHI0: case PCI_DEVICE_ID_INTEL_TGL_NHI1: + case PCI_DEVICE_ID_INTEL_TGL_H_NHI0: + case PCI_DEVICE_ID_INTEL_TGL_H_NHI1: icm->is_supported = icm_tgl_is_supported; icm->driver_ready = icm_icl_driver_ready; icm->set_uuid = icm_icl_set_uuid; diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 3f79baa54829..db80dc5dfeba 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -406,12 +406,23 @@ static int ring_request_msix(struct tb_ring *ring, bool no_suspend) ring->vector = ret; - ring->irq = pci_irq_vector(ring->nhi->pdev, ring->vector); - if (ring->irq < 0) - return ring->irq; + ret = pci_irq_vector(ring->nhi->pdev, ring->vector); + if (ret < 0) + goto err_ida_remove; + + ring->irq = ret; irqflags = no_suspend ? IRQF_NO_SUSPEND : 0; - return request_irq(ring->irq, ring_msix, irqflags, "thunderbolt", ring); + ret = request_irq(ring->irq, ring_msix, irqflags, "thunderbolt", ring); + if (ret) + goto err_ida_remove; + + return 0; + +err_ida_remove: + ida_simple_remove(&nhi->msix_ida, ring->vector); + + return ret; } static void ring_release_msix(struct tb_ring *ring) @@ -1334,6 +1345,10 @@ static struct pci_device_id nhi_ids[] = { .driver_data = (kernel_ulong_t)&icl_nhi_ops }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_NHI1), .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI0), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI1), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, /* Any USB4 compliant host */ { PCI_DEVICE_CLASS(PCI_CLASS_SERIAL_USB_USB4, ~0) }, diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h index 80162e4b013f..4e0861d75072 100644 --- a/drivers/thunderbolt/nhi.h +++ b/drivers/thunderbolt/nhi.h @@ -75,6 +75,8 @@ extern const struct tb_nhi_ops icl_nhi_ops; #define PCI_DEVICE_ID_INTEL_ICL_NHI0 0x8a17 #define PCI_DEVICE_ID_INTEL_TGL_NHI0 0x9a1b #define PCI_DEVICE_ID_INTEL_TGL_NHI1 0x9a1d +#define PCI_DEVICE_ID_INTEL_TGL_H_NHI0 0x9a1f +#define PCI_DEVICE_ID_INTEL_TGL_H_NHI1 0x9a21 #define PCI_CLASS_SERIAL_USB_USB4 0x0c0340 diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index a9995e21b916..8ea360b0ff77 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -784,6 +784,8 @@ static inline bool tb_switch_is_tiger_lake(const struct tb_switch *sw) switch (sw->config.device_id) { case PCI_DEVICE_ID_INTEL_TGL_NHI0: case PCI_DEVICE_ID_INTEL_TGL_NHI1: + case PCI_DEVICE_ID_INTEL_TGL_H_NHI0: + case PCI_DEVICE_ID_INTEL_TGL_H_NHI1: return true; } } diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 40f13579a3fe..f2583b4053e4 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -421,8 +421,12 @@ int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags) * upstream USB4 port. */ tb_switch_for_each_port(sw, port) { + if (!tb_port_is_null(port)) + continue; if (!route && tb_is_upstream_port(port)) continue; + if (!port->cap_usb4) + continue; ret = tb_port_read(port, &val, TB_CFG_PORT, port->cap_usb4 + PORT_CS_19, 1); diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index 48907853732a..c00ad817042e 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -881,6 +881,7 @@ static void enumerate_services(struct tb_xdomain *xd) id = ida_simple_get(&xd->service_ids, 0, 0, GFP_KERNEL); if (id < 0) { + kfree(svc->key); kfree(svc); break; } diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c index 0c80a79d7442..c2be7cf91399 100644 --- a/drivers/tty/serial/ar933x_uart.c +++ b/drivers/tty/serial/ar933x_uart.c @@ -789,8 +789,10 @@ static int ar933x_uart_probe(struct platform_device *pdev) goto err_disable_clk; up->gpios = mctrl_gpio_init(port, 0); - if (IS_ERR(up->gpios) && PTR_ERR(up->gpios) != -ENOSYS) - return PTR_ERR(up->gpios); + if (IS_ERR(up->gpios) && PTR_ERR(up->gpios) != -ENOSYS) { + ret = PTR_ERR(up->gpios); + goto err_disable_clk; + } up->rts_gpiod = mctrl_gpio_to_gpiod(up->gpios, UART_GPIO_RTS); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 1731d9728865..cacf7266a262 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -942,8 +942,14 @@ static irqreturn_t imx_uart_int(int irq, void *dev_id) struct imx_port *sport = dev_id; unsigned int usr1, usr2, ucr1, ucr2, ucr3, ucr4; irqreturn_t ret = IRQ_NONE; + unsigned long flags = 0; - spin_lock(&sport->port.lock); + /* + * IRQs might not be disabled upon entering this interrupt handler, + * e.g. when interrupt handlers are forced to be threaded. To support + * this scenario as well, disable IRQs when acquiring the spinlock. + */ + spin_lock_irqsave(&sport->port.lock, flags); usr1 = imx_uart_readl(sport, USR1); usr2 = imx_uart_readl(sport, USR2); @@ -1013,7 +1019,7 @@ static irqreturn_t imx_uart_int(int irq, void *dev_id) ret = IRQ_HANDLED; } - spin_unlock(&sport->port.lock); + spin_unlock_irqrestore(&sport->port.lock, flags); return ret; } @@ -2002,16 +2008,6 @@ imx_uart_console_write(struct console *co, const char *s, unsigned int count) unsigned int ucr1; unsigned long flags = 0; int locked = 1; - int retval; - - retval = clk_enable(sport->clk_per); - if (retval) - return; - retval = clk_enable(sport->clk_ipg); - if (retval) { - clk_disable(sport->clk_per); - return; - } if (sport->port.sysrq) locked = 0; @@ -2047,9 +2043,6 @@ imx_uart_console_write(struct console *co, const char *s, unsigned int count) if (locked) spin_unlock_irqrestore(&sport->port.lock, flags); - - clk_disable(sport->clk_ipg); - clk_disable(sport->clk_per); } /* @@ -2150,15 +2143,14 @@ imx_uart_console_setup(struct console *co, char *options) retval = uart_set_options(&sport->port, co, baud, parity, bits, flow); - clk_disable(sport->clk_ipg); if (retval) { - clk_unprepare(sport->clk_ipg); + clk_disable_unprepare(sport->clk_ipg); goto error_console; } - retval = clk_prepare(sport->clk_per); + retval = clk_prepare_enable(sport->clk_per); if (retval) - clk_unprepare(sport->clk_ipg); + clk_disable_unprepare(sport->clk_ipg); error_console: return retval; diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 9f8b9a567b35..56ade99ef99f 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2897,10 +2897,14 @@ void __do_SAK(struct tty_struct *tty) struct task_struct *g, *p; struct pid *session; int i; + unsigned long flags; if (!tty) return; - session = tty->session; + + spin_lock_irqsave(&tty->ctrl_lock, flags); + session = get_pid(tty->session); + spin_unlock_irqrestore(&tty->ctrl_lock, flags); tty_ldisc_flush(tty); @@ -2932,6 +2936,7 @@ void __do_SAK(struct tty_struct *tty) task_unlock(p); } while_each_thread(g, p); read_unlock(&tasklist_lock); + put_pid(session); #endif } diff --git a/drivers/tty/tty_jobctrl.c b/drivers/tty/tty_jobctrl.c index 28a23a0fef21..aa6d0537b379 100644 --- a/drivers/tty/tty_jobctrl.c +++ b/drivers/tty/tty_jobctrl.c @@ -103,8 +103,8 @@ static void __proc_set_tty(struct tty_struct *tty) put_pid(tty->session); put_pid(tty->pgrp); tty->pgrp = get_pid(task_pgrp(current)); - spin_unlock_irqrestore(&tty->ctrl_lock, flags); tty->session = get_pid(task_session(current)); + spin_unlock_irqrestore(&tty->ctrl_lock, flags); if (current->signal->tty) { tty_debug(tty, "current tty %s not NULL!!\n", current->signal->tty->name); @@ -293,20 +293,23 @@ void disassociate_ctty(int on_exit) spin_lock_irq(¤t->sighand->siglock); put_pid(current->signal->tty_old_pgrp); current->signal->tty_old_pgrp = NULL; - tty = tty_kref_get(current->signal->tty); + spin_unlock_irq(¤t->sighand->siglock); + if (tty) { unsigned long flags; + + tty_lock(tty); spin_lock_irqsave(&tty->ctrl_lock, flags); put_pid(tty->session); put_pid(tty->pgrp); tty->session = NULL; tty->pgrp = NULL; spin_unlock_irqrestore(&tty->ctrl_lock, flags); + tty_unlock(tty); tty_kref_put(tty); } - spin_unlock_irq(¤t->sighand->siglock); /* Now clear signal->tty under the lock */ read_lock(&tasklist_lock); session_clear_tty(task_session(current)); @@ -477,14 +480,19 @@ static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t return -ENOTTY; if (retval) return retval; - if (!current->signal->tty || - (current->signal->tty != real_tty) || - (real_tty->session != task_session(current))) - return -ENOTTY; + if (get_user(pgrp_nr, p)) return -EFAULT; if (pgrp_nr < 0) return -EINVAL; + + spin_lock_irq(&real_tty->ctrl_lock); + if (!current->signal->tty || + (current->signal->tty != real_tty) || + (real_tty->session != task_session(current))) { + retval = -ENOTTY; + goto out_unlock_ctrl; + } rcu_read_lock(); pgrp = find_vpid(pgrp_nr); retval = -ESRCH; @@ -494,12 +502,12 @@ static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t if (session_of_pgrp(pgrp) != task_session(current)) goto out_unlock; retval = 0; - spin_lock_irq(&tty->ctrl_lock); put_pid(real_tty->pgrp); real_tty->pgrp = get_pid(pgrp); - spin_unlock_irq(&tty->ctrl_lock); out_unlock: rcu_read_unlock(); +out_unlock_ctrl: + spin_unlock_irq(&real_tty->ctrl_lock); return retval; } @@ -511,20 +519,30 @@ out_unlock: * * Obtain the session id of the tty. If there is no session * return an error. - * - * Locking: none. Reference to current->signal->tty is safe. */ static int tiocgsid(struct tty_struct *tty, struct tty_struct *real_tty, pid_t __user *p) { + unsigned long flags; + pid_t sid; + /* * (tty == real_tty) is a cheap way of * testing if the tty is NOT a master pty. */ if (tty == real_tty && current->signal->tty != real_tty) return -ENOTTY; + + spin_lock_irqsave(&real_tty->ctrl_lock, flags); if (!real_tty->session) - return -ENOTTY; - return put_user(pid_vnr(real_tty->session), p); + goto err; + sid = pid_vnr(real_tty->session); + spin_unlock_irqrestore(&real_tty->ctrl_lock, flags); + + return put_user(sid, p); + +err: + spin_unlock_irqrestore(&real_tty->ctrl_lock, flags); + return -ENOTTY; } /* diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index 6dca744e39e9..be06f1a961c2 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -413,10 +413,10 @@ static int uio_get_minor(struct uio_device *idev) return retval; } -static void uio_free_minor(struct uio_device *idev) +static void uio_free_minor(unsigned long minor) { mutex_lock(&minor_lock); - idr_remove(&uio_idr, idev->minor); + idr_remove(&uio_idr, minor); mutex_unlock(&minor_lock); } @@ -990,7 +990,7 @@ err_request_irq: err_uio_dev_add_attributes: device_del(&idev->dev); err_device_create: - uio_free_minor(idev); + uio_free_minor(idev->minor); put_device(&idev->dev); return ret; } @@ -1042,11 +1042,13 @@ EXPORT_SYMBOL_GPL(__devm_uio_register_device); void uio_unregister_device(struct uio_info *info) { struct uio_device *idev; + unsigned long minor; if (!info || !info->uio_dev) return; idev = info->uio_dev; + minor = idev->minor; mutex_lock(&idev->info_lock); uio_dev_del_attributes(idev); @@ -1062,7 +1064,7 @@ void uio_unregister_device(struct uio_info *info) device_unregister(&idev->dev); - uio_free_minor(idev); + uio_free_minor(minor); return; } diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c index a0f73d4711ae..039ab5d2435e 100644 --- a/drivers/usb/cdns3/core.c +++ b/drivers/usb/cdns3/core.c @@ -427,7 +427,6 @@ static irqreturn_t cdns3_wakeup_irq(int irq, void *data) */ static int cdns3_probe(struct platform_device *pdev) { - struct usb_role_switch_desc sw_desc = { }; struct device *dev = &pdev->dev; struct resource *res; struct cdns3 *cdns; @@ -529,18 +528,21 @@ static int cdns3_probe(struct platform_device *pdev) if (ret) goto err2; - sw_desc.set = cdns3_role_set; - sw_desc.get = cdns3_role_get; - sw_desc.allow_userspace_control = true; - sw_desc.driver_data = cdns; - if (device_property_read_bool(dev, "usb-role-switch")) + if (device_property_read_bool(dev, "usb-role-switch")) { + struct usb_role_switch_desc sw_desc = { }; + + sw_desc.set = cdns3_role_set; + sw_desc.get = cdns3_role_get; + sw_desc.allow_userspace_control = true; + sw_desc.driver_data = cdns; sw_desc.fwnode = dev->fwnode; - cdns->role_sw = usb_role_switch_register(dev, &sw_desc); - if (IS_ERR(cdns->role_sw)) { - ret = PTR_ERR(cdns->role_sw); - dev_warn(dev, "Unable to register Role Switch\n"); - goto err3; + cdns->role_sw = usb_role_switch_register(dev, &sw_desc); + if (IS_ERR(cdns->role_sw)) { + ret = PTR_ERR(cdns->role_sw); + dev_warn(dev, "Unable to register Role Switch\n"); + goto err3; + } } if (cdns->wakeup_irq) { @@ -551,7 +553,7 @@ static int cdns3_probe(struct platform_device *pdev) if (ret) { dev_err(cdns->dev, "couldn't register wakeup irq handler\n"); - goto err3; + goto err4; } } @@ -582,7 +584,8 @@ static int cdns3_probe(struct platform_device *pdev) return 0; err4: cdns3_drd_exit(cdns); - usb_role_switch_unregister(cdns->role_sw); + if (cdns->role_sw) + usb_role_switch_unregister(cdns->role_sw); err3: set_phy_power_off(cdns); err2: diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c index 66c1e6723eb1..0aa85cc07ff1 100644 --- a/drivers/usb/cdns3/gadget.c +++ b/drivers/usb/cdns3/gadget.c @@ -1114,7 +1114,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, struct cdns3_device *priv_dev = priv_ep->cdns3_dev; struct cdns3_request *priv_req; struct cdns3_trb *trb; - struct cdns3_trb *link_trb; + struct cdns3_trb *link_trb = NULL; dma_addr_t trb_dma; u32 togle_pcs = 1; int sg_iter = 0; @@ -1193,10 +1193,20 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, /* set incorrect Cycle Bit for first trb*/ control = priv_ep->pcs ? 0 : TRB_CYCLE; + trb->length = 0; + if (priv_dev->dev_ver >= DEV_VER_V2) { + u16 td_size; + + td_size = DIV_ROUND_UP(request->length, + priv_ep->endpoint.maxpacket); + if (priv_dev->gadget.speed == USB_SPEED_SUPER) + trb->length = TRB_TDL_SS_SIZE(td_size); + else + control |= TRB_TDL_HS_SIZE(td_size); + } do { u32 length; - u16 td_size = 0; /* fill TRB */ control |= TRB_TYPE(TRB_NORMAL); @@ -1208,20 +1218,12 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, length = request->length; } - if (likely(priv_dev->dev_ver >= DEV_VER_V2)) - td_size = DIV_ROUND_UP(length, - priv_ep->endpoint.maxpacket); - else if (priv_ep->flags & EP_TDLCHK_EN) + if (priv_ep->flags & EP_TDLCHK_EN) total_tdl += DIV_ROUND_UP(length, priv_ep->endpoint.maxpacket); - trb->length = cpu_to_le32(TRB_BURST_LEN(priv_ep->trb_burst_size) | + trb->length |= cpu_to_le32(TRB_BURST_LEN(priv_ep->trb_burst_size) | TRB_LEN(length)); - if (priv_dev->gadget.speed == USB_SPEED_SUPER) - trb->length |= cpu_to_le32(TRB_TDL_SS_SIZE(td_size)); - else - control |= TRB_TDL_HS_SIZE(td_size); - pcs = priv_ep->pcs ? TRB_CYCLE : 0; /* @@ -1258,6 +1260,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, priv_req->end_trb = priv_ep->enqueue; cdns3_ep_inc_enq(priv_ep); trb = priv_ep->trb_pool + priv_ep->enqueue; + trb->length = 0; } while (sg_iter < num_trb); trb = priv_req->trb; diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 1e7568867910..f52f1bc0559f 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1693,6 +1693,15 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x0870, 0x0001), /* Metricom GS Modem */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, + { USB_DEVICE(0x045b, 0x023c), /* Renesas USB Download mode */ + .driver_info = DISABLE_ECHO, /* Don't echo banner */ + }, + { USB_DEVICE(0x045b, 0x0248), /* Renesas USB Download mode */ + .driver_info = DISABLE_ECHO, /* Don't echo banner */ + }, + { USB_DEVICE(0x045b, 0x024D), /* Renesas USB Download mode */ + .driver_info = DISABLE_ECHO, /* Don't echo banner */ + }, { USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov@gmail.com */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index e96a858a1218..533236366a03 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -482,11 +482,11 @@ static void snoop_urb(struct usb_device *udev, if (userurb) { /* Async */ if (when == SUBMIT) - dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, " + dev_info(&udev->dev, "userurb %px, ep%d %s-%s, " "length %u\n", userurb, ep, t, d, length); else - dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, " + dev_info(&udev->dev, "userurb %px, ep%d %s-%s, " "actual_length %u status %d\n", userurb, ep, t, d, length, timeout_or_status); @@ -1997,7 +1997,7 @@ static int proc_reapurb(struct usb_dev_state *ps, void __user *arg) if (as) { int retval; - snoop(&ps->dev->dev, "reap %pK\n", as->userurb); + snoop(&ps->dev->dev, "reap %px\n", as->userurb); retval = processcompl(as, (void __user * __user *)arg); free_async(as); return retval; @@ -2014,7 +2014,7 @@ static int proc_reapurbnonblock(struct usb_dev_state *ps, void __user *arg) as = async_getcompleted(ps); if (as) { - snoop(&ps->dev->dev, "reap %pK\n", as->userurb); + snoop(&ps->dev->dev, "reap %px\n", as->userurb); retval = processcompl(as, (void __user * __user *)arg); free_async(as); } else { @@ -2142,7 +2142,7 @@ static int proc_reapurb_compat(struct usb_dev_state *ps, void __user *arg) if (as) { int retval; - snoop(&ps->dev->dev, "reap %pK\n", as->userurb); + snoop(&ps->dev->dev, "reap %px\n", as->userurb); retval = processcompl_compat(as, (void __user * __user *)arg); free_async(as); return retval; @@ -2159,7 +2159,7 @@ static int proc_reapurbnonblock_compat(struct usb_dev_state *ps, void __user *ar as = async_getcompleted(ps); if (as) { - snoop(&ps->dev->dev, "reap %pK\n", as->userurb); + snoop(&ps->dev->dev, "reap %px\n", as->userurb); retval = processcompl_compat(as, (void __user * __user *)arg); free_async(as); } else { @@ -2624,7 +2624,7 @@ static long usbdev_do_ioctl(struct file *file, unsigned int cmd, #endif case USBDEVFS_DISCARDURB: - snoop(&dev->dev, "%s: DISCARDURB %pK\n", __func__, p); + snoop(&dev->dev, "%s: DISCARDURB %px\n", __func__, p); ret = proc_unlinkurb(ps, p); break; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index a1e3a037a289..fad31ccd1fa8 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -348,6 +348,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* Guillemot Webcam Hercules Dualpix Exchange*/ { USB_DEVICE(0x06f8, 0x3005), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Guillemot Hercules DJ Console audio card (BZ 208357) */ + { USB_DEVICE(0x06f8, 0xb000), .driver_info = + USB_QUIRK_ENDPOINT_IGNORE }, + /* Midiman M-Audio Keystation 88es */ { USB_DEVICE(0x0763, 0x0192), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -421,6 +425,10 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x1532, 0x0116), .driver_info = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL }, + /* Lenovo ThinkCenter A630Z TI024Gen3 usb-audio */ + { USB_DEVICE(0x17ef, 0xa012), .driver_info = + USB_QUIRK_DISCONNECT_SUSPEND }, + /* BUILDWIN Photo Frame */ { USB_DEVICE(0x1908, 0x1315), .driver_info = USB_QUIRK_HONOR_BNUMINTERFACES }, @@ -521,6 +529,8 @@ static const struct usb_device_id usb_amd_resume_quirk_list[] = { * Matched for devices with USB_QUIRK_ENDPOINT_IGNORE. */ static const struct usb_device_id usb_endpoint_ignore[] = { + { USB_DEVICE_INTERFACE_NUMBER(0x06f8, 0xb000, 5), .driver_info = 0x01 }, + { USB_DEVICE_INTERFACE_NUMBER(0x06f8, 0xb000, 5), .driver_info = 0x81 }, { USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0202, 1), .driver_info = 0x85 }, { USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0208, 1), .driver_info = 0x85 }, { } diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 046f770a76da..c727cb5de871 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1324,7 +1324,7 @@ static long ffs_epfile_ioctl(struct file *file, unsigned code, case FUNCTIONFS_ENDPOINT_DESC: { int desc_idx; - struct usb_endpoint_descriptor *desc; + struct usb_endpoint_descriptor desc1, *desc; switch (epfile->ffs->gadget->speed) { case USB_SPEED_SUPER: @@ -1336,10 +1336,12 @@ static long ffs_epfile_ioctl(struct file *file, unsigned code, default: desc_idx = 0; } + desc = epfile->ep->descs[desc_idx]; + memcpy(&desc1, desc, desc->bLength); spin_unlock_irq(&epfile->ffs->eps_lock); - ret = copy_to_user((void __user *)value, desc, desc->bLength); + ret = copy_to_user((void __user *)value, &desc1, desc1.bLength); if (ret) ret = -EFAULT; return ret; diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c index 85cb15734aa8..19d97940eeb9 100644 --- a/drivers/usb/gadget/function/f_midi.c +++ b/drivers/usb/gadget/function/f_midi.c @@ -1315,7 +1315,7 @@ static struct usb_function *f_midi_alloc(struct usb_function_instance *fi) midi->id = kstrdup(opts->id, GFP_KERNEL); if (opts->id && !midi->id) { status = -ENOMEM; - goto setup_fail; + goto midi_free; } midi->in_ports = opts->in_ports; midi->out_ports = opts->out_ports; @@ -1327,7 +1327,7 @@ static struct usb_function *f_midi_alloc(struct usb_function_instance *fi) status = kfifo_alloc(&midi->in_req_fifo, midi->qlen, GFP_KERNEL); if (status) - goto setup_fail; + goto midi_free; spin_lock_init(&midi->transmit_lock); @@ -1343,9 +1343,13 @@ static struct usb_function *f_midi_alloc(struct usb_function_instance *fi) return &midi->func; +midi_free: + if (midi) + kfree(midi->id); + kfree(midi); setup_fail: mutex_unlock(&opts->lock); - kfree(midi); + return ERR_PTR(status); } diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 1b430b36d0a6..71e7d10dd76b 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -2039,6 +2039,9 @@ gadgetfs_fill_super (struct super_block *sb, struct fs_context *fc) return 0; Enomem: + kfree(CHIP); + CHIP = NULL; + return -ENOMEM; } diff --git a/drivers/usb/host/ohci-omap.c b/drivers/usb/host/ohci-omap.c index 9ccdf2c216b5..6374501ba139 100644 --- a/drivers/usb/host/ohci-omap.c +++ b/drivers/usb/host/ohci-omap.c @@ -91,14 +91,14 @@ static int omap_ohci_transceiver_power(struct ohci_omap_priv *priv, int on) | ((1 << 5/*usb1*/) | (1 << 3/*usb2*/)), INNOVATOR_FPGA_CAM_USB_CONTROL); else if (priv->power) - gpiod_set_value(priv->power, 0); + gpiod_set_value_cansleep(priv->power, 0); } else { if (machine_is_omap_innovator() && cpu_is_omap1510()) __raw_writeb(__raw_readb(INNOVATOR_FPGA_CAM_USB_CONTROL) & ~((1 << 5/*usb1*/) | (1 << 3/*usb2*/)), INNOVATOR_FPGA_CAM_USB_CONTROL); else if (priv->power) - gpiod_set_value(priv->power, 1); + gpiod_set_value_cansleep(priv->power, 1); } return 0; diff --git a/drivers/usb/host/xhci-histb.c b/drivers/usb/host/xhci-histb.c index 5546e7e013a8..08369857686e 100644 --- a/drivers/usb/host/xhci-histb.c +++ b/drivers/usb/host/xhci-histb.c @@ -240,7 +240,7 @@ static int xhci_histb_probe(struct platform_device *pdev) /* Initialize dma_mask and coherent_dma_mask to 32-bits */ ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); if (ret) - return ret; + goto disable_pm; hcd = usb_create_hcd(driver, dev, dev_name(dev)); if (!hcd) { diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c index 30085b2be7b9..5892f3ce0cdc 100644 --- a/drivers/usb/musb/musb_dsps.c +++ b/drivers/usb/musb/musb_dsps.c @@ -429,10 +429,12 @@ static int dsps_musb_init(struct musb *musb) struct platform_device *parent = to_platform_device(dev->parent); const struct dsps_musb_wrapper *wrp = glue->wrp; void __iomem *reg_base; + struct resource *r; u32 rev, val; int ret; - reg_base = devm_platform_ioremap_resource_byname(parent, "control"); + r = platform_get_resource_byname(parent, IORESOURCE_MEM, "control"); + reg_base = devm_ioremap_resource(dev, r); if (IS_ERR(reg_base)) return PTR_ERR(reg_base); musb->ctrl_base = reg_base; diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c index a2e2f56c88cd..28deaaec581f 100644 --- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -81,10 +81,11 @@ #define CH341_QUIRK_SIMULATE_BREAK BIT(1) static const struct usb_device_id id_table[] = { - { USB_DEVICE(0x4348, 0x5523) }, + { USB_DEVICE(0x1a86, 0x5512) }, + { USB_DEVICE(0x1a86, 0x5523) }, { USB_DEVICE(0x1a86, 0x7522) }, { USB_DEVICE(0x1a86, 0x7523) }, - { USB_DEVICE(0x1a86, 0x5523) }, + { USB_DEVICE(0x4348, 0x5523) }, { }, }; MODULE_DEVICE_TABLE(usb, id_table); diff --git a/drivers/usb/serial/kl5kusb105.c b/drivers/usb/serial/kl5kusb105.c index 5ee48b0650c4..5f6b82ebccc5 100644 --- a/drivers/usb/serial/kl5kusb105.c +++ b/drivers/usb/serial/kl5kusb105.c @@ -276,12 +276,12 @@ static int klsi_105_open(struct tty_struct *tty, struct usb_serial_port *port) priv->cfg.unknown2 = cfg->unknown2; spin_unlock_irqrestore(&priv->lock, flags); + kfree(cfg); + /* READ_ON and urb submission */ rc = usb_serial_generic_open(tty, port); - if (rc) { - retval = rc; - goto err_free_cfg; - } + if (rc) + return rc; rc = usb_control_msg(port->serial->dev, usb_sndctrlpipe(port->serial->dev, 0), @@ -324,8 +324,6 @@ err_disable_read: KLSI_TIMEOUT); err_generic_close: usb_serial_generic_close(port); -err_free_cfg: - kfree(cfg); return retval; } diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 54ca85cc920d..56d6f6d83bd7 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -419,6 +419,7 @@ static void option_instat_callback(struct urb *urb); #define CINTERION_PRODUCT_PH8 0x0053 #define CINTERION_PRODUCT_AHXX 0x0055 #define CINTERION_PRODUCT_PLXX 0x0060 +#define CINTERION_PRODUCT_EXS82 0x006c #define CINTERION_PRODUCT_PH8_2RMNET 0x0082 #define CINTERION_PRODUCT_PH8_AUDIO 0x0083 #define CINTERION_PRODUCT_AHXX_2RMNET 0x0084 @@ -1105,9 +1106,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0xff, 0xff), .driver_info = NUMEP2 }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0, 0) }, - { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96, 0xff, 0xff, 0xff), - .driver_info = NUMEP2 }, - { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96, 0xff, 0, 0) }, + { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96), + .driver_info = RSVD(4) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff), .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) }, @@ -1902,6 +1902,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX_AUDIO, 0xff) }, { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_CLS8, 0xff), .driver_info = RSVD(0) | RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EXS82, 0xff) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) }, { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDM) }, @@ -2046,12 +2047,13 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE(0x0489, 0xe0b5), /* Foxconn T77W968 ESIM */ .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, - { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 */ + { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 (IOT version) */ .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, { USB_DEVICE(0x2cb7, 0x0104), /* Fibocom NL678 series */ .driver_info = RSVD(4) | RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0105, 0xff), /* Fibocom NL678 series */ .driver_info = RSVD(6) }, + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) }, /* GosunCn GM500 ECM/NCM */ diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 560efd1479ba..e5a971b83e3f 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -92,7 +92,7 @@ static int slave_alloc (struct scsi_device *sdev) static int slave_configure(struct scsi_device *sdev) { struct us_data *us = host_to_us(sdev->host); - struct device *dev = sdev->host->dma_dev; + struct device *dev = us->pusb_dev->bus->sysdev; /* * Many devices have trouble transferring more than 32KB at a time, diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index c8a577309e8f..652d6d6f1f36 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -837,24 +837,17 @@ static int uas_slave_alloc(struct scsi_device *sdev) */ blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1)); + if (devinfo->flags & US_FL_MAX_SECTORS_64) + blk_queue_max_hw_sectors(sdev->request_queue, 64); + else if (devinfo->flags & US_FL_MAX_SECTORS_240) + blk_queue_max_hw_sectors(sdev->request_queue, 240); + return 0; } static int uas_slave_configure(struct scsi_device *sdev) { struct uas_dev_info *devinfo = sdev->hostdata; - struct device *dev = sdev->host->dma_dev; - - if (devinfo->flags & US_FL_MAX_SECTORS_64) - blk_queue_max_hw_sectors(sdev->request_queue, 64); - else if (devinfo->flags & US_FL_MAX_SECTORS_240) - blk_queue_max_hw_sectors(sdev->request_queue, 240); - else if (devinfo->udev->speed >= USB_SPEED_SUPER) - blk_queue_max_hw_sectors(sdev->request_queue, 2048); - - blk_queue_max_hw_sectors(sdev->request_queue, - min_t(size_t, queue_max_hw_sectors(sdev->request_queue), - dma_max_mapping_size(dev) >> SECTOR_SHIFT)); if (devinfo->flags & US_FL_NO_REPORT_OPCODES) sdev->no_report_opcodes = 1; @@ -1040,7 +1033,7 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) shost->can_queue = devinfo->qdepth - 2; usb_set_intfdata(intf, shost); - result = scsi_add_host_with_dma(shost, &intf->dev, udev->bus->sysdev); + result = scsi_add_host(shost, &intf->dev); if (result) goto free_streams; diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c index c2ef367cf257..94a64729dc27 100644 --- a/drivers/usb/storage/usb.c +++ b/drivers/usb/storage/usb.c @@ -1049,9 +1049,8 @@ int usb_stor_probe2(struct us_data *us) goto BadDevice; usb_autopm_get_interface_no_resume(us->pusb_intf); snprintf(us->scsi_name, sizeof(us->scsi_name), "usb-storage %s", - dev_name(dev)); - result = scsi_add_host_with_dma(us_to_host(us), dev, - us->pusb_dev->bus->sysdev); + dev_name(&us->pusb_intf->dev)); + result = scsi_add_host(us_to_host(us), dev); if (result) { dev_warn(dev, "Unable to add the scsi host\n"); diff --git a/drivers/usb/typec/Kconfig b/drivers/usb/typec/Kconfig index 6c5908a37ee8..e7f120874c48 100644 --- a/drivers/usb/typec/Kconfig +++ b/drivers/usb/typec/Kconfig @@ -88,6 +88,7 @@ config TYPEC_STUSB160X config TYPEC_QCOM_PMIC tristate "Qualcomm PMIC USB Type-C driver" depends on ARCH_QCOM || COMPILE_TEST + depends on USB_ROLE_SWITCH || !USB_ROLE_SWITCH help Driver for supporting role switch over the Qualcomm PMIC. This will handle the USB Type-C role and orientation detection reported by the diff --git a/drivers/usb/typec/stusb160x.c b/drivers/usb/typec/stusb160x.c index 2a618f02f4f1..d21750bbbb44 100644 --- a/drivers/usb/typec/stusb160x.c +++ b/drivers/usb/typec/stusb160x.c @@ -562,7 +562,7 @@ static int stusb160x_get_fw_caps(struct stusb160x *chip, * Supported power operation mode can be configured through device tree * else it is read from chip registers in stusb160x_get_caps. */ - ret = fwnode_property_read_string(fwnode, "power-opmode", &cap_str); + ret = fwnode_property_read_string(fwnode, "typec-power-opmode", &cap_str); if (!ret) { ret = typec_find_pwr_opmode(cap_str); /* Power delivery not yet supported */ diff --git a/drivers/usb/typec/ucsi/psy.c b/drivers/usb/typec/ucsi/psy.c index 26ed0b520749..571a51e16234 100644 --- a/drivers/usb/typec/ucsi/psy.c +++ b/drivers/usb/typec/ucsi/psy.c @@ -238,4 +238,13 @@ void ucsi_unregister_port_psy(struct ucsi_connector *con) return; power_supply_unregister(con->psy); + con->psy = NULL; +} + +void ucsi_port_psy_changed(struct ucsi_connector *con) +{ + if (IS_ERR_OR_NULL(con->psy)) + return; + + power_supply_changed(con->psy); } diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 758b988ac518..51a570d40a42 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -643,8 +643,10 @@ static void ucsi_handle_connector_change(struct work_struct *work) role = !!(con->status.flags & UCSI_CONSTAT_PWR_DIR); if (con->status.change & UCSI_CONSTAT_POWER_OPMODE_CHANGE || - con->status.change & UCSI_CONSTAT_POWER_LEVEL_CHANGE) + con->status.change & UCSI_CONSTAT_POWER_LEVEL_CHANGE) { ucsi_pwr_opmode_change(con); + ucsi_port_psy_changed(con); + } if (con->status.change & UCSI_CONSTAT_POWER_DIR_CHANGE) { typec_set_pwr_role(con->port, role); @@ -674,6 +676,8 @@ static void ucsi_handle_connector_change(struct work_struct *work) ucsi_register_partner(con); else ucsi_unregister_partner(con); + + ucsi_port_psy_changed(con); } if (con->status.change & UCSI_CONSTAT_CAM_CHANGE) { @@ -994,6 +998,7 @@ static int ucsi_register_port(struct ucsi *ucsi, int index) !!(con->status.flags & UCSI_CONSTAT_PWR_DIR)); ucsi_pwr_opmode_change(con); ucsi_register_partner(con); + ucsi_port_psy_changed(con); } if (con->partner) { diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index cba6f77bea61..b7a92f246050 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -340,9 +340,11 @@ int ucsi_resume(struct ucsi *ucsi); #if IS_ENABLED(CONFIG_POWER_SUPPLY) int ucsi_register_port_psy(struct ucsi_connector *con); void ucsi_unregister_port_psy(struct ucsi_connector *con); +void ucsi_port_psy_changed(struct ucsi_connector *con); #else static inline int ucsi_register_port_psy(struct ucsi_connector *con) { return 0; } static inline void ucsi_unregister_port_psy(struct ucsi_connector *con) { } +static inline void ucsi_port_psy_changed(struct ucsi_connector *con) { } #endif /* CONFIG_POWER_SUPPLY */ #if IS_ENABLED(CONFIG_TYPEC_DP_ALTMODE) diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index d7d32b656102..6caf539091e5 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -13,6 +13,7 @@ config VDPA_SIM depends on RUNTIME_TESTING_MENU && HAS_DMA select DMA_OPS select VHOST_RING + select GENERIC_NET_UTILS default n help vDPA networking device simulator which loop TX traffic back @@ -31,6 +32,7 @@ config IFCVF config MLX5_VDPA bool + select VHOST_IOTLB help Support library for Mellanox VDPA drivers. Provides code that is common for all types of VDPA drivers. The following drivers are planned: diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index b22adf03f584..6ff8a5096691 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -52,7 +52,6 @@ #define VHOST_SCSI_VERSION "v0.1" #define VHOST_SCSI_NAMELEN 256 #define VHOST_SCSI_MAX_CDB_SIZE 32 -#define VHOST_SCSI_DEFAULT_TAGS 256 #define VHOST_SCSI_PREALLOC_SGLS 2048 #define VHOST_SCSI_PREALLOC_UPAGES 2048 #define VHOST_SCSI_PREALLOC_PROT_SGLS 2048 @@ -140,6 +139,7 @@ struct vhost_scsi_tpg { struct se_portal_group se_tpg; /* Pointer back to vhost_scsi, protected by tv_tpg_mutex */ struct vhost_scsi *vhost_scsi; + struct list_head tmf_queue; }; struct vhost_scsi_tport { @@ -189,6 +189,9 @@ struct vhost_scsi_virtqueue { * Writers must also take dev mutex and flush under it. */ int inflight_idx; + struct vhost_scsi_cmd *scsi_cmds; + struct sbitmap scsi_tags; + int max_cmds; }; struct vhost_scsi { @@ -209,6 +212,21 @@ struct vhost_scsi { int vs_events_nr; /* num of pending events, protected by vq->mutex */ }; +struct vhost_scsi_tmf { + struct vhost_work vwork; + struct vhost_scsi_tpg *tpg; + struct vhost_scsi *vhost; + struct vhost_scsi_virtqueue *svq; + struct list_head queue_entry; + + struct se_cmd se_cmd; + u8 scsi_resp; + struct vhost_scsi_inflight *inflight; + struct iovec resp_iov; + int in_iovs; + int vq_desc; +}; + /* * Context for processing request and control queue operations. */ @@ -320,11 +338,13 @@ static u32 vhost_scsi_tpg_get_inst_index(struct se_portal_group *se_tpg) return 1; } -static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) +static void vhost_scsi_release_cmd_res(struct se_cmd *se_cmd) { struct vhost_scsi_cmd *tv_cmd = container_of(se_cmd, struct vhost_scsi_cmd, tvc_se_cmd); - struct se_session *se_sess = tv_cmd->tvc_nexus->tvn_se_sess; + struct vhost_scsi_virtqueue *svq = container_of(tv_cmd->tvc_vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_inflight *inflight = tv_cmd->inflight; int i; if (tv_cmd->tvc_sgl_count) { @@ -336,8 +356,36 @@ static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) put_page(sg_page(&tv_cmd->tvc_prot_sgl[i])); } - vhost_scsi_put_inflight(tv_cmd->inflight); - target_free_tag(se_sess, se_cmd); + sbitmap_clear_bit(&svq->scsi_tags, se_cmd->map_tag); + vhost_scsi_put_inflight(inflight); +} + +static void vhost_scsi_release_tmf_res(struct vhost_scsi_tmf *tmf) +{ + struct vhost_scsi_tpg *tpg = tmf->tpg; + struct vhost_scsi_inflight *inflight = tmf->inflight; + + mutex_lock(&tpg->tv_tpg_mutex); + list_add_tail(&tpg->tmf_queue, &tmf->queue_entry); + mutex_unlock(&tpg->tv_tpg_mutex); + vhost_scsi_put_inflight(inflight); +} + +static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) +{ + if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) { + struct vhost_scsi_tmf *tmf = container_of(se_cmd, + struct vhost_scsi_tmf, se_cmd); + + vhost_work_queue(&tmf->vhost->dev, &tmf->vwork); + } else { + struct vhost_scsi_cmd *cmd = container_of(se_cmd, + struct vhost_scsi_cmd, tvc_se_cmd); + struct vhost_scsi *vs = cmd->tvc_vhost; + + llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list); + vhost_work_queue(&vs->dev, &vs->vs_completion_work); + } } static u32 vhost_scsi_sess_get_index(struct se_session *se_sess) @@ -362,34 +410,25 @@ static int vhost_scsi_get_cmd_state(struct se_cmd *se_cmd) return 0; } -static void vhost_scsi_complete_cmd(struct vhost_scsi_cmd *cmd) -{ - struct vhost_scsi *vs = cmd->tvc_vhost; - - llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list); - - vhost_work_queue(&vs->dev, &vs->vs_completion_work); -} - static int vhost_scsi_queue_data_in(struct se_cmd *se_cmd) { - struct vhost_scsi_cmd *cmd = container_of(se_cmd, - struct vhost_scsi_cmd, tvc_se_cmd); - vhost_scsi_complete_cmd(cmd); + transport_generic_free_cmd(se_cmd, 0); return 0; } static int vhost_scsi_queue_status(struct se_cmd *se_cmd) { - struct vhost_scsi_cmd *cmd = container_of(se_cmd, - struct vhost_scsi_cmd, tvc_se_cmd); - vhost_scsi_complete_cmd(cmd); + transport_generic_free_cmd(se_cmd, 0); return 0; } static void vhost_scsi_queue_tm_rsp(struct se_cmd *se_cmd) { - return; + struct vhost_scsi_tmf *tmf = container_of(se_cmd, struct vhost_scsi_tmf, + se_cmd); + + tmf->scsi_resp = se_cmd->se_tmr_req->response; + transport_generic_free_cmd(&tmf->se_cmd, 0); } static void vhost_scsi_aborted_task(struct se_cmd *se_cmd) @@ -429,15 +468,6 @@ vhost_scsi_allocate_evt(struct vhost_scsi *vs, return evt; } -static void vhost_scsi_free_cmd(struct vhost_scsi_cmd *cmd) -{ - struct se_cmd *se_cmd = &cmd->tvc_se_cmd; - - /* TODO locking against target/backend threads? */ - transport_generic_free_cmd(se_cmd, 0); - -} - static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd) { return target_put_sess_cmd(se_cmd); @@ -556,7 +586,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) } else pr_err("Faulted on virtio_scsi_cmd_resp\n"); - vhost_scsi_free_cmd(cmd); + vhost_scsi_release_cmd_res(se_cmd); } vq = -1; @@ -566,31 +596,31 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) } static struct vhost_scsi_cmd * -vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, +vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, unsigned char *cdb, u64 scsi_tag, u16 lun, u8 task_attr, u32 exp_data_len, int data_direction) { + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); struct vhost_scsi_cmd *cmd; struct vhost_scsi_nexus *tv_nexus; - struct se_session *se_sess; struct scatterlist *sg, *prot_sg; struct page **pages; - int tag, cpu; + int tag; tv_nexus = tpg->tpg_nexus; if (!tv_nexus) { pr_err("Unable to locate active struct vhost_scsi_nexus\n"); return ERR_PTR(-EIO); } - se_sess = tv_nexus->tvn_se_sess; - tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu); + tag = sbitmap_get(&svq->scsi_tags, 0, false); if (tag < 0) { pr_err("Unable to obtain tag for vhost_scsi_cmd\n"); return ERR_PTR(-ENOMEM); } - cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[tag]; + cmd = &svq->scsi_cmds[tag]; sg = cmd->tvc_sgl; prot_sg = cmd->tvc_prot_sgl; pages = cmd->tvc_upages; @@ -599,7 +629,6 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, cmd->tvc_prot_sgl = prot_sg; cmd->tvc_upages = pages; cmd->tvc_se_cmd.map_tag = tag; - cmd->tvc_se_cmd.map_cpu = cpu; cmd->tvc_tag = scsi_tag; cmd->tvc_lun = lun; cmd->tvc_task_attr = task_attr; @@ -907,6 +936,11 @@ vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc, return ret; } +static u16 vhost_buf_to_lun(u8 *lun_buf) +{ + return ((lun_buf[2] << 8) | lun_buf[3]) & 0x3FFF; +} + static void vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) { @@ -1045,12 +1079,12 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) tag = vhost64_to_cpu(vq, v_req_pi.tag); task_attr = v_req_pi.task_attr; cdb = &v_req_pi.cdb[0]; - lun = ((v_req_pi.lun[2] << 8) | v_req_pi.lun[3]) & 0x3FFF; + lun = vhost_buf_to_lun(v_req_pi.lun); } else { tag = vhost64_to_cpu(vq, v_req.tag); task_attr = v_req.task_attr; cdb = &v_req.cdb[0]; - lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF; + lun = vhost_buf_to_lun(v_req.lun); } /* * Check that the received CDB size does not exceeded our @@ -1065,11 +1099,11 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) scsi_command_size(cdb), VHOST_SCSI_MAX_CDB_SIZE); goto err; } - cmd = vhost_scsi_get_tag(vq, tpg, cdb, tag, lun, task_attr, + cmd = vhost_scsi_get_cmd(vq, tpg, cdb, tag, lun, task_attr, exp_data_len + prot_bytes, data_direction); if (IS_ERR(cmd)) { - vq_err(vq, "vhost_scsi_get_tag failed %ld\n", + vq_err(vq, "vhost_scsi_get_cmd failed %ld\n", PTR_ERR(cmd)); goto err; } @@ -1088,7 +1122,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) &prot_iter, exp_data_len, &data_iter))) { vq_err(vq, "Failed to map iov to sgl\n"); - vhost_scsi_release_cmd(&cmd->tvc_se_cmd); + vhost_scsi_release_cmd_res(&cmd->tvc_se_cmd); goto err; } } @@ -1124,9 +1158,9 @@ out: } static void -vhost_scsi_send_tmf_reject(struct vhost_scsi *vs, - struct vhost_virtqueue *vq, - struct vhost_scsi_ctx *vc) +vhost_scsi_send_tmf_resp(struct vhost_scsi *vs, struct vhost_virtqueue *vq, + int in_iovs, int vq_desc, struct iovec *resp_iov, + int tmf_resp_code) { struct virtio_scsi_ctrl_tmf_resp rsp; struct iov_iter iov_iter; @@ -1134,17 +1168,87 @@ vhost_scsi_send_tmf_reject(struct vhost_scsi *vs, pr_debug("%s\n", __func__); memset(&rsp, 0, sizeof(rsp)); - rsp.response = VIRTIO_SCSI_S_FUNCTION_REJECTED; + rsp.response = tmf_resp_code; - iov_iter_init(&iov_iter, READ, &vq->iov[vc->out], vc->in, sizeof(rsp)); + iov_iter_init(&iov_iter, READ, resp_iov, in_iovs, sizeof(rsp)); ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter); if (likely(ret == sizeof(rsp))) - vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0); + vhost_add_used_and_signal(&vs->dev, vq, vq_desc, 0); else pr_err("Faulted on virtio_scsi_ctrl_tmf_resp\n"); } +static void vhost_scsi_tmf_resp_work(struct vhost_work *work) +{ + struct vhost_scsi_tmf *tmf = container_of(work, struct vhost_scsi_tmf, + vwork); + int resp_code; + + if (tmf->scsi_resp == TMR_FUNCTION_COMPLETE) + resp_code = VIRTIO_SCSI_S_FUNCTION_SUCCEEDED; + else + resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED; + + vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs, + tmf->vq_desc, &tmf->resp_iov, resp_code); + vhost_scsi_release_tmf_res(tmf); +} + +static void +vhost_scsi_handle_tmf(struct vhost_scsi *vs, struct vhost_scsi_tpg *tpg, + struct vhost_virtqueue *vq, + struct virtio_scsi_ctrl_tmf_req *vtmf, + struct vhost_scsi_ctx *vc) +{ + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_tmf *tmf; + + if (vhost32_to_cpu(vq, vtmf->subtype) != + VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET) + goto send_reject; + + if (!tpg->tpg_nexus || !tpg->tpg_nexus->tvn_se_sess) { + pr_err("Unable to locate active struct vhost_scsi_nexus for LUN RESET.\n"); + goto send_reject; + } + + mutex_lock(&tpg->tv_tpg_mutex); + if (list_empty(&tpg->tmf_queue)) { + pr_err("Missing reserve TMF. Could not handle LUN RESET.\n"); + mutex_unlock(&tpg->tv_tpg_mutex); + goto send_reject; + } + + tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf, + queue_entry); + list_del_init(&tmf->queue_entry); + mutex_unlock(&tpg->tv_tpg_mutex); + + tmf->tpg = tpg; + tmf->vhost = vs; + tmf->svq = svq; + tmf->resp_iov = vq->iov[vc->out]; + tmf->vq_desc = vc->head; + tmf->in_iovs = vc->in; + tmf->inflight = vhost_scsi_get_inflight(vq); + + if (target_submit_tmr(&tmf->se_cmd, tpg->tpg_nexus->tvn_se_sess, NULL, + vhost_buf_to_lun(vtmf->lun), NULL, + TMR_LUN_RESET, GFP_KERNEL, 0, + TARGET_SCF_ACK_KREF) < 0) { + vhost_scsi_release_tmf_res(tmf); + goto send_reject; + } + + return; + +send_reject: + vhost_scsi_send_tmf_resp(vs, vq, vc->in, vc->head, &vq->iov[vc->out], + VIRTIO_SCSI_S_FUNCTION_REJECTED); +} + static void vhost_scsi_send_an_resp(struct vhost_scsi *vs, struct vhost_virtqueue *vq, @@ -1170,6 +1274,7 @@ vhost_scsi_send_an_resp(struct vhost_scsi *vs, static void vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) { + struct vhost_scsi_tpg *tpg; union { __virtio32 type; struct virtio_scsi_ctrl_an_req an; @@ -1251,12 +1356,12 @@ vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) vc.req += typ_size; vc.req_size -= typ_size; - ret = vhost_scsi_get_req(vq, &vc, NULL); + ret = vhost_scsi_get_req(vq, &vc, &tpg); if (ret) goto err; if (v_req.type == VIRTIO_SCSI_T_TMF) - vhost_scsi_send_tmf_reject(vs, vq, &vc); + vhost_scsi_handle_tmf(vs, tpg, vq, &v_req.tmf, &vc); else vhost_scsi_send_an_resp(vs, vq, &vc); err: @@ -1373,6 +1478,83 @@ static void vhost_scsi_flush(struct vhost_scsi *vs) wait_for_completion(&old_inflight[i]->comp); } +static void vhost_scsi_destroy_vq_cmds(struct vhost_virtqueue *vq) +{ + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_cmd *tv_cmd; + unsigned int i; + + if (!svq->scsi_cmds) + return; + + for (i = 0; i < svq->max_cmds; i++) { + tv_cmd = &svq->scsi_cmds[i]; + + kfree(tv_cmd->tvc_sgl); + kfree(tv_cmd->tvc_prot_sgl); + kfree(tv_cmd->tvc_upages); + } + + sbitmap_free(&svq->scsi_tags); + kfree(svq->scsi_cmds); + svq->scsi_cmds = NULL; +} + +static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds) +{ + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_cmd *tv_cmd; + unsigned int i; + + if (svq->scsi_cmds) + return 0; + + if (sbitmap_init_node(&svq->scsi_tags, max_cmds, -1, GFP_KERNEL, + NUMA_NO_NODE)) + return -ENOMEM; + svq->max_cmds = max_cmds; + + svq->scsi_cmds = kcalloc(max_cmds, sizeof(*tv_cmd), GFP_KERNEL); + if (!svq->scsi_cmds) { + sbitmap_free(&svq->scsi_tags); + return -ENOMEM; + } + + for (i = 0; i < max_cmds; i++) { + tv_cmd = &svq->scsi_cmds[i]; + + tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS, + sizeof(struct scatterlist), + GFP_KERNEL); + if (!tv_cmd->tvc_sgl) { + pr_err("Unable to allocate tv_cmd->tvc_sgl\n"); + goto out; + } + + tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES, + sizeof(struct page *), + GFP_KERNEL); + if (!tv_cmd->tvc_upages) { + pr_err("Unable to allocate tv_cmd->tvc_upages\n"); + goto out; + } + + tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS, + sizeof(struct scatterlist), + GFP_KERNEL); + if (!tv_cmd->tvc_prot_sgl) { + pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n"); + goto out; + } + } + return 0; +out: + vhost_scsi_destroy_vq_cmds(vq); + return -ENOMEM; +} + /* * Called from vhost_scsi_ioctl() context to walk the list of available * vhost_scsi_tpg with an active struct vhost_scsi_nexus @@ -1427,10 +1609,9 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) { if (vs->vs_tpg && vs->vs_tpg[tpg->tport_tpgt]) { - kfree(vs_tpg); mutex_unlock(&tpg->tv_tpg_mutex); ret = -EEXIST; - goto out; + goto undepend; } /* * In order to ensure individual vhost-scsi configfs @@ -1442,9 +1623,8 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, ret = target_depend_item(&se_tpg->tpg_group.cg_item); if (ret) { pr_warn("target_depend_item() failed: %d\n", ret); - kfree(vs_tpg); mutex_unlock(&tpg->tv_tpg_mutex); - goto out; + goto undepend; } tpg->tv_tpg_vhost_count++; tpg->vhost_scsi = vs; @@ -1457,6 +1637,16 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (match) { memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn, sizeof(vs->vs_vhost_wwpn)); + + for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) { + vq = &vs->vqs[i].vq; + if (!vhost_vq_is_setup(vq)) + continue; + + if (vhost_scsi_setup_vq_cmds(vq, vq->num)) + goto destroy_vq_cmds; + } + for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) { vq = &vs->vqs[i].vq; mutex_lock(&vq->mutex); @@ -1476,7 +1666,22 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, vhost_scsi_flush(vs); kfree(vs->vs_tpg); vs->vs_tpg = vs_tpg; + goto out; +destroy_vq_cmds: + for (i--; i >= VHOST_SCSI_VQ_IO; i--) { + if (!vhost_vq_get_backend(&vs->vqs[i].vq)) + vhost_scsi_destroy_vq_cmds(&vs->vqs[i].vq); + } +undepend: + for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) { + tpg = vs_tpg[i]; + if (tpg) { + tpg->tv_tpg_vhost_count--; + target_undepend_item(&tpg->se_tpg.tpg_group.cg_item); + } + } + kfree(vs_tpg); out: mutex_unlock(&vs->dev.mutex); mutex_unlock(&vhost_scsi_mutex); @@ -1549,6 +1754,12 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, mutex_lock(&vq->mutex); vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); + /* + * Make sure cmds are not running before tearing them + * down. + */ + vhost_scsi_flush(vs); + vhost_scsi_destroy_vq_cmds(vq); } } /* @@ -1811,11 +2022,19 @@ static int vhost_scsi_port_link(struct se_portal_group *se_tpg, { struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); + struct vhost_scsi_tmf *tmf; + + tmf = kzalloc(sizeof(*tmf), GFP_KERNEL); + if (!tmf) + return -ENOMEM; + INIT_LIST_HEAD(&tmf->queue_entry); + vhost_work_init(&tmf->vwork, vhost_scsi_tmf_resp_work); mutex_lock(&vhost_scsi_mutex); mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count++; + list_add_tail(&tmf->queue_entry, &tpg->tmf_queue); mutex_unlock(&tpg->tv_tpg_mutex); vhost_scsi_hotplug(tpg, lun); @@ -1830,11 +2049,16 @@ static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg, { struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); + struct vhost_scsi_tmf *tmf; mutex_lock(&vhost_scsi_mutex); mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count--; + tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf, + queue_entry); + list_del(&tmf->queue_entry); + kfree(tmf); mutex_unlock(&tpg->tv_tpg_mutex); vhost_scsi_hotunplug(tpg, lun); @@ -1842,23 +2066,6 @@ static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg, mutex_unlock(&vhost_scsi_mutex); } -static void vhost_scsi_free_cmd_map_res(struct se_session *se_sess) -{ - struct vhost_scsi_cmd *tv_cmd; - unsigned int i; - - if (!se_sess->sess_cmd_map) - return; - - for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) { - tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i]; - - kfree(tv_cmd->tvc_sgl); - kfree(tv_cmd->tvc_prot_sgl); - kfree(tv_cmd->tvc_upages); - } -} - static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_store( struct config_item *item, const char *page, size_t count) { @@ -1898,45 +2105,6 @@ static struct configfs_attribute *vhost_scsi_tpg_attrib_attrs[] = { NULL, }; -static int vhost_scsi_nexus_cb(struct se_portal_group *se_tpg, - struct se_session *se_sess, void *p) -{ - struct vhost_scsi_cmd *tv_cmd; - unsigned int i; - - for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) { - tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i]; - - tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS, - sizeof(struct scatterlist), - GFP_KERNEL); - if (!tv_cmd->tvc_sgl) { - pr_err("Unable to allocate tv_cmd->tvc_sgl\n"); - goto out; - } - - tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES, - sizeof(struct page *), - GFP_KERNEL); - if (!tv_cmd->tvc_upages) { - pr_err("Unable to allocate tv_cmd->tvc_upages\n"); - goto out; - } - - tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS, - sizeof(struct scatterlist), - GFP_KERNEL); - if (!tv_cmd->tvc_prot_sgl) { - pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n"); - goto out; - } - } - return 0; -out: - vhost_scsi_free_cmd_map_res(se_sess); - return -ENOMEM; -} - static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg, const char *name) { @@ -1960,12 +2128,9 @@ static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg, * struct se_node_acl for the vhost_scsi struct se_portal_group with * the SCSI Initiator port name of the passed configfs group 'name'. */ - tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, - VHOST_SCSI_DEFAULT_TAGS, - sizeof(struct vhost_scsi_cmd), + tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, 0, 0, TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS, - (unsigned char *)name, tv_nexus, - vhost_scsi_nexus_cb); + (unsigned char *)name, tv_nexus, NULL); if (IS_ERR(tv_nexus->tvn_se_sess)) { mutex_unlock(&tpg->tv_tpg_mutex); kfree(tv_nexus); @@ -2015,7 +2180,6 @@ static int vhost_scsi_drop_nexus(struct vhost_scsi_tpg *tpg) " %s Initiator Port: %s\n", vhost_scsi_dump_proto_id(tpg->tport), tv_nexus->tvn_se_sess->se_node_acl->initiatorname); - vhost_scsi_free_cmd_map_res(se_sess); /* * Release the SCSI I_T Nexus to the emulated vhost Target Port */ @@ -2155,6 +2319,7 @@ vhost_scsi_make_tpg(struct se_wwn *wwn, const char *name) } mutex_init(&tpg->tv_tpg_mutex); INIT_LIST_HEAD(&tpg->tv_tpg_list); + INIT_LIST_HEAD(&tpg->tmf_queue); tpg->tport = tport; tpg->tport_tpgt = tpgt; diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 2754f3069738..29ed4173f04e 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -348,7 +348,9 @@ static long vhost_vdpa_get_iova_range(struct vhost_vdpa *v, u32 __user *argp) .last = v->range.last, }; - return copy_to_user(argp, &range, sizeof(range)); + if (copy_to_user(argp, &range, sizeof(range))) + return -EFAULT; + return 0; } static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, @@ -577,6 +579,8 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, if (r) vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1); + else + atomic64_add(size >> PAGE_SHIFT, &dev->mm->pinned_vm); return r; } @@ -608,8 +612,9 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, unsigned long list_size = PAGE_SIZE / sizeof(struct page *); unsigned int gup_flags = FOLL_LONGTERM; unsigned long npages, cur_base, map_pfn, last_pfn = 0; - unsigned long locked, lock_limit, pinned, i; + unsigned long lock_limit, sz2pin, nchunks, i; u64 iova = msg->iova; + long pinned; int ret = 0; if (msg->iova < v->range.first || @@ -620,6 +625,7 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, msg->iova + msg->size - 1)) return -EEXIST; + /* Limit the use of memory for bookkeeping */ page_list = (struct page **) __get_free_page(GFP_KERNEL); if (!page_list) return -ENOMEM; @@ -628,52 +634,75 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, gup_flags |= FOLL_WRITE; npages = PAGE_ALIGN(msg->size + (iova & ~PAGE_MASK)) >> PAGE_SHIFT; - if (!npages) - return -EINVAL; + if (!npages) { + ret = -EINVAL; + goto free; + } mmap_read_lock(dev->mm); - locked = atomic64_add_return(npages, &dev->mm->pinned_vm); lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - - if (locked > lock_limit) { + if (npages + atomic64_read(&dev->mm->pinned_vm) > lock_limit) { ret = -ENOMEM; - goto out; + goto unlock; } cur_base = msg->uaddr & PAGE_MASK; iova &= PAGE_MASK; + nchunks = 0; while (npages) { - pinned = min_t(unsigned long, npages, list_size); - ret = pin_user_pages(cur_base, pinned, - gup_flags, page_list, NULL); - if (ret != pinned) + sz2pin = min_t(unsigned long, npages, list_size); + pinned = pin_user_pages(cur_base, sz2pin, + gup_flags, page_list, NULL); + if (sz2pin != pinned) { + if (pinned < 0) { + ret = pinned; + } else { + unpin_user_pages(page_list, pinned); + ret = -ENOMEM; + } goto out; + } + nchunks++; if (!last_pfn) map_pfn = page_to_pfn(page_list[0]); - for (i = 0; i < ret; i++) { + for (i = 0; i < pinned; i++) { unsigned long this_pfn = page_to_pfn(page_list[i]); u64 csize; if (last_pfn && (this_pfn != last_pfn + 1)) { /* Pin a contiguous chunk of memory */ csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT; - if (vhost_vdpa_map(v, iova, csize, - map_pfn << PAGE_SHIFT, - msg->perm)) + ret = vhost_vdpa_map(v, iova, csize, + map_pfn << PAGE_SHIFT, + msg->perm); + if (ret) { + /* + * Unpin the pages that are left unmapped + * from this point on in the current + * page_list. The remaining outstanding + * ones which may stride across several + * chunks will be covered in the common + * error path subsequently. + */ + unpin_user_pages(&page_list[i], + pinned - i); goto out; + } + map_pfn = this_pfn; iova += csize; + nchunks = 0; } last_pfn = this_pfn; } - cur_base += ret << PAGE_SHIFT; - npages -= ret; + cur_base += pinned << PAGE_SHIFT; + npages -= pinned; } /* Pin the rest chunk */ @@ -681,10 +710,27 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, map_pfn << PAGE_SHIFT, msg->perm); out: if (ret) { + if (nchunks) { + unsigned long pfn; + + /* + * Unpin the outstanding pages which are yet to be + * mapped but haven't due to vdpa_map() or + * pin_user_pages() failure. + * + * Mapped pages are accounted in vdpa_map(), hence + * the corresponding unpinning will be handled by + * vdpa_unmap(). + */ + WARN_ON(!last_pfn); + for (pfn = map_pfn; pfn <= last_pfn; pfn++) + unpin_user_page(pfn_to_page(pfn)); + } vhost_vdpa_unmap(v, msg->iova, msg->size); - atomic64_sub(npages, &dev->mm->pinned_vm); } +unlock: mmap_read_unlock(dev->mm); +free: free_page((unsigned long)page_list); return ret; } diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 5c835a292783..a262e12c6dc2 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -304,6 +304,12 @@ static void vhost_vring_call_reset(struct vhost_vring_call *call_ctx) memset(&call_ctx->producer, 0x0, sizeof(struct irq_bypass_producer)); } +bool vhost_vq_is_setup(struct vhost_virtqueue *vq) +{ + return vq->avail && vq->desc && vq->used && vhost_vq_access_ok(vq); +} +EXPORT_SYMBOL_GPL(vhost_vq_is_setup); + static void vhost_vq_reset(struct vhost_dev *dev, struct vhost_virtqueue *vq) { diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index e016cd3fa02f..b063324c7669 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -190,6 +190,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *, struct vhost_log *log, unsigned int *log_num); void vhost_discard_vq_desc(struct vhost_virtqueue *, int n); +bool vhost_vq_is_setup(struct vhost_virtqueue *vq); int vhost_vq_init_access(struct vhost_virtqueue *); int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len); int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads, diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 8bd8b403f087..b7403ba8e7f7 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -730,7 +730,7 @@ EXPORT_SYMBOL(vringh_iov_pull_user); /** * vringh_iov_push_user - copy bytes into vring_iov. * @wiov: the wiov as passed to vringh_getdesc_user() (updated as we consume) - * @dst: the place to copy. + * @src: the place to copy from. * @len: the maximum length to copy. * * Returns the bytes copied <= len or a negative errno. @@ -976,7 +976,7 @@ EXPORT_SYMBOL(vringh_iov_pull_kern); /** * vringh_iov_push_kern - copy bytes into vring_iov. * @wiov: the wiov as passed to vringh_getdesc_kern() (updated as we consume) - * @dst: the place to copy. + * @src: the place to copy from. * @len: the maximum length to copy. * * Returns the bytes copied <= len or a negative errno. @@ -1333,7 +1333,7 @@ EXPORT_SYMBOL(vringh_iov_pull_iotlb); * vringh_iov_push_iotlb - copy bytes into vring_iov. * @vrh: the vring. * @wiov: the wiov as passed to vringh_getdesc_iotlb() (updated as we consume) - * @dst: the place to copy. + * @src: the place to copy from. * @len: the maximum length to copy. * * Returns the bytes copied <= len or a negative errno. diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index e36fb1a0ecdb..c8b0ae676809 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -47,6 +47,7 @@ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/vmalloc.h> #include <linux/init.h> #include <linux/completion.h> #include <linux/fb.h> @@ -1092,7 +1093,12 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) goto err1; } - fb_virt = ioremap(par->mem->start, screen_fb_size); + /* + * Map the VRAM cacheable for performance. This is also required for + * VM Connect to display properly for ARM64 Linux VM, as the host also + * maps the VRAM cacheable. + */ + fb_virt = ioremap_cache(par->mem->start, screen_fb_size); if (!fb_virt) goto err2; diff --git a/drivers/virt/nitro_enclaves/ne_misc_dev.c b/drivers/virt/nitro_enclaves/ne_misc_dev.c index f06622b48d69..f1964ea4b826 100644 --- a/drivers/virt/nitro_enclaves/ne_misc_dev.c +++ b/drivers/virt/nitro_enclaves/ne_misc_dev.c @@ -1505,10 +1505,8 @@ static __poll_t ne_enclave_poll(struct file *file, poll_table *wait) poll_wait(file, &ne_enclave->eventq, wait); - if (!ne_enclave->has_event) - return mask; - - mask = POLLHUP; + if (ne_enclave->has_event) + mask |= EPOLLHUP; return mask; } diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 523dcdf39cc9..3729bea0c989 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -813,6 +813,129 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages) } EXPORT_SYMBOL_GPL(gnttab_alloc_pages); +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC +static inline void cache_init(struct gnttab_page_cache *cache) +{ + cache->pages = NULL; +} + +static inline bool cache_empty(struct gnttab_page_cache *cache) +{ + return !cache->pages; +} + +static inline struct page *cache_deq(struct gnttab_page_cache *cache) +{ + struct page *page; + + page = cache->pages; + cache->pages = page->zone_device_data; + + return page; +} + +static inline void cache_enq(struct gnttab_page_cache *cache, struct page *page) +{ + page->zone_device_data = cache->pages; + cache->pages = page; +} +#else +static inline void cache_init(struct gnttab_page_cache *cache) +{ + INIT_LIST_HEAD(&cache->pages); +} + +static inline bool cache_empty(struct gnttab_page_cache *cache) +{ + return list_empty(&cache->pages); +} + +static inline struct page *cache_deq(struct gnttab_page_cache *cache) +{ + struct page *page; + + page = list_first_entry(&cache->pages, struct page, lru); + list_del(&page->lru); + + return page; +} + +static inline void cache_enq(struct gnttab_page_cache *cache, struct page *page) +{ + list_add(&page->lru, &cache->pages); +} +#endif + +void gnttab_page_cache_init(struct gnttab_page_cache *cache) +{ + spin_lock_init(&cache->lock); + cache_init(cache); + cache->num_pages = 0; +} +EXPORT_SYMBOL_GPL(gnttab_page_cache_init); + +int gnttab_page_cache_get(struct gnttab_page_cache *cache, struct page **page) +{ + unsigned long flags; + + spin_lock_irqsave(&cache->lock, flags); + + if (cache_empty(cache)) { + spin_unlock_irqrestore(&cache->lock, flags); + return gnttab_alloc_pages(1, page); + } + + page[0] = cache_deq(cache); + cache->num_pages--; + + spin_unlock_irqrestore(&cache->lock, flags); + + return 0; +} +EXPORT_SYMBOL_GPL(gnttab_page_cache_get); + +void gnttab_page_cache_put(struct gnttab_page_cache *cache, struct page **page, + unsigned int num) +{ + unsigned long flags; + unsigned int i; + + spin_lock_irqsave(&cache->lock, flags); + + for (i = 0; i < num; i++) + cache_enq(cache, page[i]); + cache->num_pages += num; + + spin_unlock_irqrestore(&cache->lock, flags); +} +EXPORT_SYMBOL_GPL(gnttab_page_cache_put); + +void gnttab_page_cache_shrink(struct gnttab_page_cache *cache, unsigned int num) +{ + struct page *page[10]; + unsigned int i = 0; + unsigned long flags; + + spin_lock_irqsave(&cache->lock, flags); + + while (cache->num_pages > num) { + page[i] = cache_deq(cache); + cache->num_pages--; + if (++i == ARRAY_SIZE(page)) { + spin_unlock_irqrestore(&cache->lock, flags); + gnttab_free_pages(i, page); + i = 0; + spin_lock_irqsave(&cache->lock, flags); + } + } + + spin_unlock_irqrestore(&cache->lock, flags); + + if (i != 0) + gnttab_free_pages(i, page); +} +EXPORT_SYMBOL_GPL(gnttab_page_cache_shrink); + void gnttab_pages_clear_private(int nr_pages, struct page **pages) { int i; diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 71ce1b7a23d1..2b385c1b4a99 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -395,8 +395,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, */ trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); - map = swiotlb_tbl_map_single(dev, virt_to_phys(xen_io_tlb_start), - phys, size, size, dir, attrs); + map = swiotlb_tbl_map_single(dev, phys, size, size, dir, attrs); if (map == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c index 8c512ea550bb..7762c1bb23cb 100644 --- a/drivers/xen/unpopulated-alloc.c +++ b/drivers/xen/unpopulated-alloc.c @@ -12,7 +12,7 @@ #include <xen/xen.h> static DEFINE_MUTEX(list_lock); -static LIST_HEAD(page_list); +static struct page *page_list; static unsigned int list_count; static int fill_list(unsigned int nr_pages) @@ -84,7 +84,8 @@ static int fill_list(unsigned int nr_pages) struct page *pg = virt_to_page(vaddr + PAGE_SIZE * i); BUG_ON(!virt_addr_valid(vaddr + PAGE_SIZE * i)); - list_add(&pg->lru, &page_list); + pg->zone_device_data = page_list; + page_list = pg; list_count++; } @@ -118,12 +119,10 @@ int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages) } for (i = 0; i < nr_pages; i++) { - struct page *pg = list_first_entry_or_null(&page_list, - struct page, - lru); + struct page *pg = page_list; BUG_ON(!pg); - list_del(&pg->lru); + page_list = pg->zone_device_data; list_count--; pages[i] = pg; @@ -134,7 +133,8 @@ int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages) unsigned int j; for (j = 0; j <= i; j++) { - list_add(&pages[j]->lru, &page_list); + pages[j]->zone_device_data = page_list; + page_list = pages[j]; list_count++; } goto out; @@ -160,7 +160,8 @@ void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages) mutex_lock(&list_lock); for (i = 0; i < nr_pages; i++) { - list_add(&pages[i]->lru, &page_list); + pages[i]->zone_device_data = page_list; + page_list = pages[i]; list_count++; } mutex_unlock(&list_lock); @@ -189,7 +190,8 @@ static int __init init(void) struct page *pg = pfn_to_page(xen_extra_mem[i].start_pfn + j); - list_add(&pg->lru, &page_list); + pg->zone_device_data = page_list; + page_list = pg; list_count++; } } diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 4acc4e899600..862162dca33c 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -99,6 +99,8 @@ struct vscsibk_info { struct list_head v2p_entry_lists; wait_queue_head_t waiting_to_free; + + struct gnttab_page_cache free_pages; }; /* theoretical maximum of grants for one request */ @@ -188,10 +190,6 @@ module_param_named(max_buffer_pages, scsiback_max_buffer_pages, int, 0644); MODULE_PARM_DESC(max_buffer_pages, "Maximum number of free pages to keep in backend buffer"); -static DEFINE_SPINLOCK(free_pages_lock); -static int free_pages_num; -static LIST_HEAD(scsiback_free_pages); - /* Global spinlock to protect scsiback TPG list */ static DEFINE_MUTEX(scsiback_mutex); static LIST_HEAD(scsiback_list); @@ -207,41 +205,6 @@ static void scsiback_put(struct vscsibk_info *info) wake_up(&info->waiting_to_free); } -static void put_free_pages(struct page **page, int num) -{ - unsigned long flags; - int i = free_pages_num + num, n = num; - - if (num == 0) - return; - if (i > scsiback_max_buffer_pages) { - n = min(num, i - scsiback_max_buffer_pages); - gnttab_free_pages(n, page + num - n); - n = num - n; - } - spin_lock_irqsave(&free_pages_lock, flags); - for (i = 0; i < n; i++) - list_add(&page[i]->lru, &scsiback_free_pages); - free_pages_num += n; - spin_unlock_irqrestore(&free_pages_lock, flags); -} - -static int get_free_page(struct page **page) -{ - unsigned long flags; - - spin_lock_irqsave(&free_pages_lock, flags); - if (list_empty(&scsiback_free_pages)) { - spin_unlock_irqrestore(&free_pages_lock, flags); - return gnttab_alloc_pages(1, page); - } - page[0] = list_first_entry(&scsiback_free_pages, struct page, lru); - list_del(&page[0]->lru); - free_pages_num--; - spin_unlock_irqrestore(&free_pages_lock, flags); - return 0; -} - static unsigned long vaddr_page(struct page *page) { unsigned long pfn = page_to_pfn(page); @@ -302,7 +265,8 @@ static void scsiback_fast_flush_area(struct vscsibk_pend *req) BUG_ON(err); } - put_free_pages(req->pages, req->n_grants); + gnttab_page_cache_put(&req->info->free_pages, req->pages, + req->n_grants); req->n_grants = 0; } @@ -445,8 +409,8 @@ static int scsiback_gnttab_data_map_list(struct vscsibk_pend *pending_req, struct vscsibk_info *info = pending_req->info; for (i = 0; i < cnt; i++) { - if (get_free_page(pg + mapcount)) { - put_free_pages(pg, mapcount); + if (gnttab_page_cache_get(&info->free_pages, pg + mapcount)) { + gnttab_page_cache_put(&info->free_pages, pg, mapcount); pr_err("no grant page\n"); return -ENOMEM; } @@ -796,6 +760,8 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info, cond_resched(); } + gnttab_page_cache_shrink(&info->free_pages, scsiback_max_buffer_pages); + RING_FINAL_CHECK_FOR_REQUESTS(&info->ring, more_to_do); return more_to_do; } @@ -1233,6 +1199,8 @@ static int scsiback_remove(struct xenbus_device *dev) scsiback_release_translation_entry(info); + gnttab_page_cache_shrink(&info->free_pages, 0); + dev_set_drvdata(&dev->dev, NULL); return 0; @@ -1263,6 +1231,7 @@ static int scsiback_probe(struct xenbus_device *dev, info->irq = 0; INIT_LIST_HEAD(&info->v2p_entry_lists); spin_lock_init(&info->v2p_lock); + gnttab_page_cache_init(&info->free_pages); err = xenbus_printf(XBT_NIL, dev->nodename, "feature-sg-grant", "%u", SG_ALL); @@ -1879,13 +1848,6 @@ out: static void __exit scsiback_exit(void) { - struct page *page; - - while (free_pages_num) { - if (get_free_page(&page)) - BUG(); - gnttab_free_pages(1, &page); - } target_unregister_template(&scsiback_ops); xenbus_unregister_driver(&scsiback_driver); } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index b177fd3b1eb3..be5768949cb1 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -655,6 +655,8 @@ const struct file_operations v9fs_cached_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = v9fs_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, }; @@ -667,6 +669,8 @@ const struct file_operations v9fs_cached_file_operations_dotl = { .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, .mmap = v9fs_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, }; @@ -678,6 +682,8 @@ const struct file_operations v9fs_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = generic_file_readonly_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, }; @@ -690,6 +696,8 @@ const struct file_operations v9fs_file_operations_dotl = { .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, .mmap = generic_file_readonly_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, }; @@ -701,6 +709,8 @@ const struct file_operations v9fs_mmap_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = v9fs_mmap_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, }; @@ -713,5 +723,7 @@ const struct file_operations v9fs_mmap_file_operations_dotl = { .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, .mmap = v9fs_mmap_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, }; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 1bb5b9d7f0a2..9068d5578a26 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -823,6 +823,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, vp->cb_break_before = afs_calc_vnode_cb_break(vnode); vp->vnode = vnode; vp->put_vnode = true; + vp->speculative = true; /* vnode not locked */ } } } diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 0fe8844b4bee..b0d7b892090d 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -294,6 +294,13 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v op->flags &= ~AFS_OPERATION_DIR_CONFLICT; } } else if (vp->scb.have_status) { + if (vp->dv_before + vp->dv_delta != vp->scb.status.data_version && + vp->speculative) + /* Ignore the result of a speculative bulk status fetch + * if it splits around a modification op, thereby + * appearing to regress the data version. + */ + goto out; afs_apply_status(op, vp); if (vp->scb.have_cb) afs_apply_callback(op, vp); @@ -305,6 +312,7 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v } } +out: write_sequnlock(&vnode->cb_lock); if (vp->scb.have_status) diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 14d5d75f4b6e..0d150a29e39e 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -755,6 +755,7 @@ struct afs_vnode_param { bool update_ctime:1; /* Need to update the ctime */ bool set_size:1; /* Must update i_size */ bool op_unlinked:1; /* True if file was unlinked by op */ + bool speculative:1; /* T if speculative status fetch (no vnode lock) */ }; /* diff --git a/fs/afs/super.c b/fs/afs/super.c index 6c5900df6aa5..e38bb1e7a4d2 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -230,6 +230,9 @@ static int afs_parse_source(struct fs_context *fc, struct fs_parameter *param) _enter(",%s", name); + if (fc->source) + return invalf(fc, "kAFS: Multiple sources not supported"); + if (!name) { printk(KERN_ERR "kAFS: no volume name specified\n"); return -EINVAL; diff --git a/fs/afs/write.c b/fs/afs/write.c index 50371207f327..c9195fc67fd8 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -169,11 +169,14 @@ int afs_write_end(struct file *file, struct address_space *mapping, unsigned int f, from = pos & (PAGE_SIZE - 1); unsigned int t, to = from + copied; loff_t i_size, maybe_i_size; - int ret; + int ret = 0; _enter("{%llx:%llu},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index); + if (copied == 0) + goto out; + maybe_i_size = pos + copied; i_size = i_size_read(&vnode->vfs_inode); @@ -1572,7 +1572,7 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb, * we return to userspace. */ if (S_ISREG(file_inode(file)->i_mode)) { - __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); + sb_start_write(file_inode(file)->i_sb); __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE); } req->ki_flags |= IOCB_WRITE; diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index 7e1549a84fcc..bc920afe23bf 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -511,7 +511,8 @@ again: /*DEFAULT_RATELIMIT_BURST*/ 1); if (__ratelimit(&_rs)) WARN(1, KERN_DEBUG - "BTRFS: block rsv returned %d\n", ret); + "BTRFS: block rsv %d returned %d\n", + block_rsv->type, ret); } try_reserve: ret = btrfs_reserve_metadata_bytes(root, block_rsv, blocksize, diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0378933d163c..0b29bdb25105 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -878,7 +878,10 @@ struct btrfs_fs_info { */ struct ulist *qgroup_ulist; - /* protect user change for quota operations */ + /* + * Protect user change for quota operations. If a transaction is needed, + * it must be started before locking this lock. + */ struct mutex qgroup_ioctl_lock; /* list of dirty qgroups to be written at next commit */ diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 5b9e3f3ace22..10638537b9ef 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -91,6 +91,17 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info) ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0); if (ret) { no_valid_dev_replace_entry_found: + /* + * We don't have a replace item or it's corrupted. If there is + * a replace target, fail the mount. + */ + if (btrfs_find_device(fs_info->fs_devices, + BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) { + btrfs_err(fs_info, + "found replace target device without a valid replace item"); + ret = -EUCLEAN; + goto out; + } ret = 0; dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED; @@ -143,8 +154,19 @@ no_valid_dev_replace_entry_found: case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: - dev_replace->srcdev = NULL; - dev_replace->tgtdev = NULL; + /* + * We don't have an active replace item but if there is a + * replace target, fail the mount. + */ + if (btrfs_find_device(fs_info->fs_devices, + BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) { + btrfs_err(fs_info, + "replace devid present without an active replace item"); + ret = -EUCLEAN; + } else { + dev_replace->srcdev = NULL; + dev_replace->tgtdev = NULL; + } break; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 87355a38a654..4373da7bcc0d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -452,46 +452,6 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) } } -static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, - const u64 start, - const u64 len, - struct extent_state **cached_state) -{ - u64 search_start = start; - const u64 end = start + len - 1; - - while (search_start < end) { - const u64 search_len = end - search_start + 1; - struct extent_map *em; - u64 em_len; - int ret = 0; - - em = btrfs_get_extent(inode, NULL, 0, search_start, search_len); - if (IS_ERR(em)) - return PTR_ERR(em); - - if (em->block_start != EXTENT_MAP_HOLE) - goto next; - - em_len = em->len; - if (em->start < search_start) - em_len -= search_start - em->start; - if (em_len > search_len) - em_len = search_len; - - ret = set_extent_bit(&inode->io_tree, search_start, - search_start + em_len - 1, - EXTENT_DELALLOC_NEW, - NULL, cached_state, GFP_NOFS); -next: - search_start = extent_map_end(em); - free_extent_map(em); - if (ret) - return ret; - } - return 0; -} - /* * after copy_from_user, pages need to be dirtied and we need to make * sure holes are created between the current EOF and the start of @@ -528,23 +488,6 @@ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, cached); - if (!btrfs_is_free_space_inode(inode)) { - if (start_pos >= isize && - !(inode->flags & BTRFS_INODE_PREALLOC)) { - /* - * There can't be any extents following eof in this case - * so just set the delalloc new bit for the range - * directly. - */ - extra_bits |= EXTENT_DELALLOC_NEW; - } else { - err = btrfs_find_new_delalloc_bytes(inode, start_pos, - num_bytes, cached); - if (err) - return err; - } - } - err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block, extra_bits, cached); if (err) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index da58c58ef9aa..7e8d8169779d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2253,11 +2253,69 @@ static int add_pending_csums(struct btrfs_trans_handle *trans, return 0; } +static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, + const u64 start, + const u64 len, + struct extent_state **cached_state) +{ + u64 search_start = start; + const u64 end = start + len - 1; + + while (search_start < end) { + const u64 search_len = end - search_start + 1; + struct extent_map *em; + u64 em_len; + int ret = 0; + + em = btrfs_get_extent(inode, NULL, 0, search_start, search_len); + if (IS_ERR(em)) + return PTR_ERR(em); + + if (em->block_start != EXTENT_MAP_HOLE) + goto next; + + em_len = em->len; + if (em->start < search_start) + em_len -= search_start - em->start; + if (em_len > search_len) + em_len = search_len; + + ret = set_extent_bit(&inode->io_tree, search_start, + search_start + em_len - 1, + EXTENT_DELALLOC_NEW, + NULL, cached_state, GFP_NOFS); +next: + search_start = extent_map_end(em); + free_extent_map(em); + if (ret) + return ret; + } + return 0; +} + int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state) { WARN_ON(PAGE_ALIGNED(end)); + + if (start >= i_size_read(&inode->vfs_inode) && + !(inode->flags & BTRFS_INODE_PREALLOC)) { + /* + * There can't be any extents following eof in this case so just + * set the delalloc new bit for the range directly. + */ + extra_bits |= EXTENT_DELALLOC_NEW; + } else { + int ret; + + ret = btrfs_find_new_delalloc_bytes(inode, start, + end + 1 - start, + cached_state); + if (ret) + return ret; + } + return set_extent_delalloc(&inode->io_tree, start, end, extra_bits, cached_state); } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ab408a23ba32..69a384145dc6 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1274,6 +1274,7 @@ static int cluster_pages_for_defrag(struct inode *inode, u64 page_start; u64 page_end; u64 page_cnt; + u64 start = (u64)start_index << PAGE_SHIFT; int ret; int i; int i_done; @@ -1290,8 +1291,7 @@ static int cluster_pages_for_defrag(struct inode *inode, page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1); ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved, - start_index << PAGE_SHIFT, - page_cnt << PAGE_SHIFT); + start, page_cnt << PAGE_SHIFT); if (ret) return ret; i_done = 0; @@ -1380,8 +1380,7 @@ again: btrfs_mod_outstanding_extents(BTRFS_I(inode), 1); spin_unlock(&BTRFS_I(inode)->lock); btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, - start_index << PAGE_SHIFT, - (page_cnt - i_done) << PAGE_SHIFT, true); + start, (page_cnt - i_done) << PAGE_SHIFT, true); } @@ -1408,8 +1407,7 @@ out: put_page(pages[i]); } btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, - start_index << PAGE_SHIFT, - page_cnt << PAGE_SHIFT, true); + start, page_cnt << PAGE_SHIFT, true); btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); extent_changeset_free(data_reserved); return ret; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index c54ea6586632..87bd37b70738 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -11,6 +11,7 @@ #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/btrfs.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "transaction.h" @@ -497,13 +498,13 @@ next2: break; } out: + btrfs_free_path(path); fs_info->qgroup_flags |= flags; if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); else if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN && ret >= 0) ret = qgroup_rescan_init(fs_info, rescan_progress, 0); - btrfs_free_path(path); if (ret < 0) { ulist_free(fs_info->qgroup_ulist); @@ -936,6 +937,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) struct btrfs_key found_key; struct btrfs_qgroup *qgroup = NULL; struct btrfs_trans_handle *trans = NULL; + struct ulist *ulist = NULL; int ret = 0; int slot; @@ -943,8 +945,8 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) if (fs_info->quota_root) goto out; - fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL); - if (!fs_info->qgroup_ulist) { + ulist = ulist_alloc(GFP_KERNEL); + if (!ulist) { ret = -ENOMEM; goto out; } @@ -952,6 +954,22 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) ret = btrfs_sysfs_add_qgroups(fs_info); if (ret < 0) goto out; + + /* + * Unlock qgroup_ioctl_lock before starting the transaction. This is to + * avoid lock acquisition inversion problems (reported by lockdep) between + * qgroup_ioctl_lock and the vfs freeze semaphores, acquired when we + * start a transaction. + * After we started the transaction lock qgroup_ioctl_lock again and + * check if someone else created the quota root in the meanwhile. If so, + * just return success and release the transaction handle. + * + * Also we don't need to worry about someone else calling + * btrfs_sysfs_add_qgroups() after we unlock and getting an error because + * that function returns 0 (success) when the sysfs entries already exist. + */ + mutex_unlock(&fs_info->qgroup_ioctl_lock); + /* * 1 for quota root item * 1 for BTRFS_QGROUP_STATUS item @@ -961,12 +979,20 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) * would be a lot of overkill. */ trans = btrfs_start_transaction(tree_root, 2); + + mutex_lock(&fs_info->qgroup_ioctl_lock); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; goto out; } + if (fs_info->quota_root) + goto out; + + fs_info->qgroup_ulist = ulist; + ulist = NULL; + /* * initially create the quota tree */ @@ -1124,11 +1150,14 @@ out: if (ret) { ulist_free(fs_info->qgroup_ulist); fs_info->qgroup_ulist = NULL; - if (trans) - btrfs_end_transaction(trans); btrfs_sysfs_del_qgroups(fs_info); } mutex_unlock(&fs_info->qgroup_ioctl_lock); + if (ret && trans) + btrfs_end_transaction(trans); + else if (trans) + ret = btrfs_end_transaction(trans); + ulist_free(ulist); return ret; } @@ -1141,19 +1170,29 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) goto out; + mutex_unlock(&fs_info->qgroup_ioctl_lock); /* * 1 For the root item * * We should also reserve enough items for the quota tree deletion in * btrfs_clean_quota_tree but this is not done. + * + * Also, we must always start a transaction without holding the mutex + * qgroup_ioctl_lock, see btrfs_quota_enable(). */ trans = btrfs_start_transaction(fs_info->tree_root, 1); + + mutex_lock(&fs_info->qgroup_ioctl_lock); if (IS_ERR(trans)) { ret = PTR_ERR(trans); + trans = NULL; goto out; } + if (!fs_info->quota_root) + goto out; + clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); @@ -1167,13 +1206,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) ret = btrfs_clean_quota_tree(trans, quota_root); if (ret) { btrfs_abort_transaction(trans, ret); - goto end_trans; + goto out; } ret = btrfs_del_root(trans, "a_root->root_key); if (ret) { btrfs_abort_transaction(trans, ret); - goto end_trans; + goto out; } list_del("a_root->dirty_list); @@ -1185,10 +1224,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) btrfs_put_root(quota_root); -end_trans: - ret = btrfs_end_transaction(trans); out: mutex_unlock(&fs_info->qgroup_ioctl_lock); + if (ret && trans) + btrfs_end_transaction(trans); + else if (trans) + ret = btrfs_end_transaction(trans); + return ret; } @@ -1324,13 +1366,17 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, struct btrfs_qgroup *member; struct btrfs_qgroup_list *list; struct ulist *tmp; + unsigned int nofs_flag; int ret = 0; /* Check the level of src and dst first */ if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) return -EINVAL; + /* We hold a transaction handle open, must do a NOFS allocation. */ + nofs_flag = memalloc_nofs_save(); tmp = ulist_alloc(GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!tmp) return -ENOMEM; @@ -1387,10 +1433,14 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, struct btrfs_qgroup_list *list; struct ulist *tmp; bool found = false; + unsigned int nofs_flag; int ret = 0; int ret2; + /* We hold a transaction handle open, must do a NOFS allocation. */ + nofs_flag = memalloc_nofs_save(); tmp = ulist_alloc(GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!tmp) return -ENOMEM; @@ -3435,24 +3485,20 @@ static int qgroup_unreserve_range(struct btrfs_inode *inode, { struct rb_node *node; struct rb_node *next; - struct ulist_node *entry = NULL; + struct ulist_node *entry; int ret = 0; node = reserved->range_changed.root.rb_node; + if (!node) + return 0; while (node) { entry = rb_entry(node, struct ulist_node, rb_node); if (entry->val < start) node = node->rb_right; - else if (entry) - node = node->rb_left; else - break; + node = node->rb_left; } - /* Empty changeset */ - if (!entry) - return 0; - if (entry->val > start && rb_prev(&entry->rb_node)) entry = rb_entry(rb_prev(&entry->rb_node), struct ulist_node, rb_node); @@ -3516,6 +3562,7 @@ static int try_flush_qgroup(struct btrfs_root *root) { struct btrfs_trans_handle *trans; int ret; + bool can_commit = true; /* * We don't want to run flush again and again, so if there is a running @@ -3527,6 +3574,20 @@ static int try_flush_qgroup(struct btrfs_root *root) return 0; } + /* + * If current process holds a transaction, we shouldn't flush, as we + * assume all space reservation happens before a transaction handle is + * held. + * + * But there are cases like btrfs_delayed_item_reserve_metadata() where + * we try to reserve space with one transction handle already held. + * In that case we can't commit transaction, but at least try to end it + * and hope the started data writes can free some space. + */ + if (current->journal_info && + current->journal_info != BTRFS_SEND_TRANS_STUB) + can_commit = false; + ret = btrfs_start_delalloc_snapshot(root); if (ret < 0) goto out; @@ -3538,7 +3599,10 @@ static int try_flush_qgroup(struct btrfs_root *root) goto out; } - ret = btrfs_commit_transaction(trans); + if (can_commit) + ret = btrfs_commit_transaction(trans); + else + ret = btrfs_end_transaction(trans); out: clear_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state); wake_up(&root->qgroup_flush_wait); diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 7f03dbe5b609..78693d3dd15b 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -860,6 +860,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, "dropping a ref for a root that doesn't have a ref on the block"); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); + kfree(ref); kfree(ra); goto out_unlock; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 3602806d71bd..9ba92d86da0b 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1648,6 +1648,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, struct btrfs_root_item *root_item; struct btrfs_path *path; struct extent_buffer *leaf; + int reserve_level; int level; int max_level; int replaced = 0; @@ -1696,7 +1697,8 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, * Thus the needed metadata size is at most root_level * nodesize, * and * 2 since we have two trees to COW. */ - min_reserved = fs_info->nodesize * btrfs_root_level(root_item) * 2; + reserve_level = max_t(int, 1, btrfs_root_level(root_item)); + min_reserved = fs_info->nodesize * reserve_level * 2; memset(&next_key, 0, sizeof(next_key)); while (1) { diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index cf63f1e27a27..e71e7586e9eb 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3866,8 +3866,9 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, if (!is_dev_replace && !readonly && !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); - btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable", - rcu_str_deref(dev->name)); + btrfs_err_in_rcu(fs_info, + "scrub on devid %llu: filesystem on %s is not writable", + devid, rcu_str_deref(dev->name)); ret = -EROFS; goto out; } diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index e6719f7db386..04022069761d 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -983,7 +983,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, BTRFS_MAX_EXTENT_SIZE >> 1, (BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1050,7 +1051,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, BTRFS_MAX_EXTENT_SIZE + sectorsize, BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1082,7 +1084,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) /* Empty */ ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1097,7 +1100,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) out: if (ret) clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); iput(inode); btrfs_free_dummy_root(root); btrfs_free_dummy_fs_info(fs_info); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 8784b74f5232..ea2bb4cb5890 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1068,6 +1068,7 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key, "invalid root item size, have %u expect %zu or %u", btrfs_item_size_nr(leaf, slot), sizeof(ri), btrfs_legacy_root_item_size()); + return -EUCLEAN; } /* @@ -1423,6 +1424,7 @@ static int check_extent_data_ref(struct extent_buffer *leaf, "invalid item size, have %u expect aligned to %zu for key type %u", btrfs_item_size_nr(leaf, slot), sizeof(*dref), key->type); + return -EUCLEAN; } if (!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize)) { generic_err(leaf, slot, @@ -1451,6 +1453,7 @@ static int check_extent_data_ref(struct extent_buffer *leaf, extent_err(leaf, slot, "invalid extent data backref offset, have %llu expect aligned to %u", offset, leaf->fs_info->sectorsize); + return -EUCLEAN; } } return 0; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b1e48078c318..78637665166e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -940,7 +940,13 @@ static noinline struct btrfs_device *device_list_add(const char *path, if (device->bdev != path_bdev) { bdput(path_bdev); mutex_unlock(&fs_devices->device_list_mutex); - btrfs_warn_in_rcu(device->fs_info, + /* + * device->fs_info may not be reliable here, so + * pass in a NULL instead. This avoids a + * possible use-after-free when the fs_info and + * fs_info->sb are already torn down. + */ + btrfs_warn_in_rcu(NULL, "duplicate device %s devid %llu generation %llu scanned by %s (%d)", path, devid, found_transid, current->comm, @@ -1056,22 +1062,13 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, continue; } - if (device->devid == BTRFS_DEV_REPLACE_DEVID) { - /* - * In the first step, keep the device which has - * the correct fsid and the devid that is used - * for the dev_replace procedure. - * In the second step, the dev_replace state is - * read from the device tree and it is known - * whether the procedure is really active or - * not, which means whether this device is - * used or whether it should be removed. - */ - if (step == 0 || test_bit(BTRFS_DEV_STATE_REPLACE_TGT, - &device->dev_state)) { - continue; - } - } + /* + * We have already validated the presence of BTRFS_DEV_REPLACE_DEVID, + * in btrfs_init_dev_replace() so just continue. + */ + if (device->devid == BTRFS_DEV_REPLACE_DEVID) + continue; + if (device->bdev) { blkdev_put(device->bdev, device->mode); device->bdev = NULL; @@ -1080,9 +1077,6 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { list_del_init(&device->dev_alloc_list); clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); - if (!test_bit(BTRFS_DEV_STATE_REPLACE_TGT, - &device->dev_state)) - fs_devices->rw_devices--; } list_del_init(&device->dev_list); fs_devices->num_devices--; diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 23b21e943652..ef4784e72b1d 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1266,6 +1266,7 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc); } else if (mode_from_special_sid) { rc = parse_sec_desc(cifs_sb, pntsd, acllen, fattr, true); + kfree(pntsd); } else { /* get approximated mode from ACL */ rc = parse_sec_desc(cifs_sb, pntsd, acllen, fattr, false); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index c7214aefde8b..82986b66b10c 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -876,6 +876,8 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) list_del_init(&server->tcp_ses_list); spin_unlock(&cifs_tcp_ses_lock); + cancel_delayed_work_sync(&server->echo); + spin_lock(&GlobalMid_Lock); server->tcpStatus = CifsExiting; spin_unlock(&GlobalMid_Lock); @@ -4544,7 +4546,8 @@ static void set_root_ses(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, if (ses) { spin_lock(&cifs_tcp_ses_lock); ses->ses_count++; - ses->tcon_ipc->remap = cifs_remap(cifs_sb); + if (ses->tcon_ipc) + ses->tcon_ipc->remap = cifs_remap(cifs_sb); spin_unlock(&cifs_tcp_ses_lock); } *root_ses = ses; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 504766cb6c19..3d914d7d0d11 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -264,7 +264,7 @@ smb2_revert_current_mid(struct TCP_Server_Info *server, const unsigned int val) } static struct mid_q_entry * -smb2_find_mid(struct TCP_Server_Info *server, char *buf) +__smb2_find_mid(struct TCP_Server_Info *server, char *buf, bool dequeue) { struct mid_q_entry *mid; struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf; @@ -281,6 +281,10 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf) (mid->mid_state == MID_REQUEST_SUBMITTED) && (mid->command == shdr->Command)) { kref_get(&mid->refcount); + if (dequeue) { + list_del_init(&mid->qhead); + mid->mid_flags |= MID_DELETED; + } spin_unlock(&GlobalMid_Lock); return mid; } @@ -289,6 +293,18 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf) return NULL; } +static struct mid_q_entry * +smb2_find_mid(struct TCP_Server_Info *server, char *buf) +{ + return __smb2_find_mid(server, buf, false); +} + +static struct mid_q_entry * +smb2_find_dequeue_mid(struct TCP_Server_Info *server, char *buf) +{ + return __smb2_find_mid(server, buf, true); +} + static void smb2_dump_detail(void *buf, struct TCP_Server_Info *server) { @@ -3098,8 +3114,8 @@ smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon, rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE; rc = SMB2_ioctl_init(tcon, server, - &rqst[1], fid.persistent_fid, - fid.volatile_fid, FSCTL_GET_REPARSE_POINT, + &rqst[1], COMPOUND_FID, + COMPOUND_FID, FSCTL_GET_REPARSE_POINT, true /* is_fctl */, NULL, 0, CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - @@ -4356,7 +4372,8 @@ init_read_bvec(struct page **pages, unsigned int npages, unsigned int data_size, static int handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, char *buf, unsigned int buf_len, struct page **pages, - unsigned int npages, unsigned int page_data_size) + unsigned int npages, unsigned int page_data_size, + bool is_offloaded) { unsigned int data_offset; unsigned int data_len; @@ -4378,7 +4395,8 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, if (server->ops->is_session_expired && server->ops->is_session_expired(buf)) { - cifs_reconnect(server); + if (!is_offloaded) + cifs_reconnect(server); return -1; } @@ -4402,7 +4420,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, cifs_dbg(FYI, "%s: server returned error %d\n", __func__, rdata->result); /* normal error on read response */ - dequeue_mid(mid, false); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_RECEIVED; + else + dequeue_mid(mid, false); return 0; } @@ -4426,7 +4447,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, cifs_dbg(FYI, "%s: data offset (%u) beyond end of smallbuf\n", __func__, data_offset); rdata->result = -EIO; - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } @@ -4442,21 +4466,30 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, cifs_dbg(FYI, "%s: data offset (%u) beyond 1st page of response\n", __func__, data_offset); rdata->result = -EIO; - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } if (data_len > page_data_size - pad_len) { /* data_len is corrupt -- discard frame */ rdata->result = -EIO; - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } rdata->result = init_read_bvec(pages, npages, page_data_size, cur_off, &bvec); if (rdata->result != 0) { - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } @@ -4471,7 +4504,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, /* read response payload cannot be in both buf and pages */ WARN_ONCE(1, "buf can not contain only a part of read data"); rdata->result = -EIO; - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } @@ -4482,7 +4518,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, if (length < 0) return length; - dequeue_mid(mid, false); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_RECEIVED; + else + dequeue_mid(mid, false); return length; } @@ -4511,15 +4550,34 @@ static void smb2_decrypt_offload(struct work_struct *work) } dw->server->lstrp = jiffies; - mid = smb2_find_mid(dw->server, dw->buf); + mid = smb2_find_dequeue_mid(dw->server, dw->buf); if (mid == NULL) cifs_dbg(FYI, "mid not found\n"); else { mid->decrypted = true; rc = handle_read_data(dw->server, mid, dw->buf, dw->server->vals->read_rsp_size, - dw->ppages, dw->npages, dw->len); - mid->callback(mid); + dw->ppages, dw->npages, dw->len, + true); + if (rc >= 0) { +#ifdef CONFIG_CIFS_STATS2 + mid->when_received = jiffies; +#endif + mid->callback(mid); + } else { + spin_lock(&GlobalMid_Lock); + if (dw->server->tcpStatus == CifsNeedReconnect) { + mid->mid_state = MID_RETRY_NEEDED; + spin_unlock(&GlobalMid_Lock); + mid->callback(mid); + } else { + mid->mid_state = MID_REQUEST_SUBMITTED; + mid->mid_flags &= ~(MID_DELETED); + list_add_tail(&mid->qhead, + &dw->server->pending_mid_q); + spin_unlock(&GlobalMid_Lock); + } + } cifs_mid_q_entry_release(mid); } @@ -4622,7 +4680,7 @@ non_offloaded_decrypt: (*mid)->decrypted = true; rc = handle_read_data(server, *mid, buf, server->vals->read_rsp_size, - pages, npages, len); + pages, npages, len, false); } free_pages: @@ -4765,7 +4823,7 @@ smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid) char *buf = server->large_buf ? server->bigbuf : server->smallbuf; return handle_read_data(server, mid, buf, server->pdu_size, - NULL, 0, 0); + NULL, 0, 0, false); } static int diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 445e80862865..acb72705062d 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2272,17 +2272,15 @@ static struct crt_sd_ctxt * create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) { struct crt_sd_ctxt *buf; - struct cifs_ace *pace; - unsigned int sdlen, acelen; + __u8 *ptr, *aclptr; + unsigned int acelen, acl_size, ace_count; unsigned int owner_offset = 0; unsigned int group_offset = 0; + struct smb3_acl acl; - *len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 2), 8); + *len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8); if (set_owner) { - /* offset fields are from beginning of security descriptor not of create context */ - owner_offset = sizeof(struct smb3_acl) + (sizeof(struct cifs_ace) * 2); - /* sizeof(struct owner_group_sids) is already multiple of 8 so no need to round */ *len += sizeof(struct owner_group_sids); } @@ -2291,26 +2289,22 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) if (buf == NULL) return buf; + ptr = (__u8 *)&buf[1]; if (set_owner) { + /* offset fields are from beginning of security descriptor not of create context */ + owner_offset = ptr - (__u8 *)&buf->sd; buf->sd.OffsetOwner = cpu_to_le32(owner_offset); - group_offset = owner_offset + sizeof(struct owner_sid); + group_offset = owner_offset + offsetof(struct owner_group_sids, group); buf->sd.OffsetGroup = cpu_to_le32(group_offset); + + setup_owner_group_sids(ptr); + ptr += sizeof(struct owner_group_sids); } else { buf->sd.OffsetOwner = 0; buf->sd.OffsetGroup = 0; } - sdlen = sizeof(struct smb3_sd) + sizeof(struct smb3_acl) + - 2 * sizeof(struct cifs_ace); - if (set_owner) { - sdlen += sizeof(struct owner_group_sids); - setup_owner_group_sids(owner_offset + sizeof(struct create_context) + 8 /* name */ - + (char *)buf); - } - - buf->ccontext.DataOffset = cpu_to_le16(offsetof - (struct crt_sd_ctxt, sd)); - buf->ccontext.DataLength = cpu_to_le32(sdlen); + buf->ccontext.DataOffset = cpu_to_le16(offsetof(struct crt_sd_ctxt, sd)); buf->ccontext.NameOffset = cpu_to_le16(offsetof(struct crt_sd_ctxt, Name)); buf->ccontext.NameLength = cpu_to_le16(4); /* SMB2_CREATE_SD_BUFFER_TOKEN is "SecD" */ @@ -2319,6 +2313,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) buf->Name[2] = 'c'; buf->Name[3] = 'D'; buf->sd.Revision = 1; /* Must be one see MS-DTYP 2.4.6 */ + /* * ACL is "self relative" ie ACL is stored in contiguous block of memory * and "DP" ie the DACL is present @@ -2326,28 +2321,38 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) buf->sd.Control = cpu_to_le16(ACL_CONTROL_SR | ACL_CONTROL_DP); /* offset owner, group and Sbz1 and SACL are all zero */ - buf->sd.OffsetDacl = cpu_to_le32(sizeof(struct smb3_sd)); - buf->acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */ + buf->sd.OffsetDacl = cpu_to_le32(ptr - (__u8 *)&buf->sd); + /* Ship the ACL for now. we will copy it into buf later. */ + aclptr = ptr; + ptr += sizeof(struct cifs_acl); /* create one ACE to hold the mode embedded in reserved special SID */ - pace = (struct cifs_ace *)(sizeof(struct crt_sd_ctxt) + (char *)buf); - acelen = setup_special_mode_ACE(pace, (__u64)mode); + acelen = setup_special_mode_ACE((struct cifs_ace *)ptr, (__u64)mode); + ptr += acelen; + acl_size = acelen + sizeof(struct smb3_acl); + ace_count = 1; if (set_owner) { /* we do not need to reallocate buffer to add the two more ACEs. plenty of space */ - pace = (struct cifs_ace *)(acelen + (sizeof(struct crt_sd_ctxt) + (char *)buf)); - acelen += setup_special_user_owner_ACE(pace); - /* it does not appear necessary to add an ACE for the NFS group SID */ - buf->acl.AceCount = cpu_to_le16(3); - } else - buf->acl.AceCount = cpu_to_le16(2); + acelen = setup_special_user_owner_ACE((struct cifs_ace *)ptr); + ptr += acelen; + acl_size += acelen; + ace_count += 1; + } /* and one more ACE to allow access for authenticated users */ - pace = (struct cifs_ace *)(acelen + (sizeof(struct crt_sd_ctxt) + - (char *)buf)); - acelen += setup_authusers_ACE(pace); - - buf->acl.AclSize = cpu_to_le16(sizeof(struct cifs_acl) + acelen); + acelen = setup_authusers_ACE((struct cifs_ace *)ptr); + ptr += acelen; + acl_size += acelen; + ace_count += 1; + + acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */ + acl.AclSize = cpu_to_le16(acl_size); + acl.AceCount = cpu_to_le16(ace_count); + memcpy(aclptr, &acl, sizeof(struct cifs_acl)); + + buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd); + *len = ptr - (__u8 *)buf; return buf; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index f05f9b12f689..fa57b03ca98c 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -963,8 +963,6 @@ struct crt_sd_ctxt { struct create_context ccontext; __u8 Name[8]; struct smb3_sd sd; - struct smb3_acl acl; - /* Followed by at least 4 ACEs */ } __packed; diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index e27e255d40dd..36b2ece43403 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -339,8 +339,8 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, return -EAGAIN; if (signal_pending(current)) { - cifs_dbg(FYI, "signal is pending before sending any data\n"); - return -EINTR; + cifs_dbg(FYI, "signal pending before send request\n"); + return -ERESTARTSYS; } /* cork the socket */ diff --git a/fs/coredump.c b/fs/coredump.c index 0cd9056d79cc..c6acfc694f65 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -229,7 +229,8 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm, */ if (ispipe) { if (isspace(*pat_ptr)) { - was_space = true; + if (cn->used != 0) + was_space = true; pat_ptr++; continue; } else if (was_space) { diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index 89bffa82ed74..c57bebfa48fe 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -74,7 +74,7 @@ int fscrypt_select_encryption_impl(struct fscrypt_info *ci) int i; /* The file must need contents encryption, not filenames encryption */ - if (!fscrypt_needs_contents_encryption(inode)) + if (!S_ISREG(inode->i_mode)) return 0; /* The crypto mode must have a blk-crypto counterpart */ diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index d3c3e5d9b41f..d595abb8ef90 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -269,9 +269,7 @@ unlock: * New inodes may not have an inode number assigned yet. * Hashing their inode number is delayed until later. */ - if (ci->ci_inode->i_ino == 0) - WARN_ON(!(ci->ci_inode->i_state & I_CREATING)); - else + if (ci->ci_inode->i_ino) fscrypt_hash_inode_number(ci, mk); return 0; } diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 96c0c86f3fff..0297ad95eb5c 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -7,6 +7,7 @@ #include <linux/efi.h> #include <linux/fs.h> #include <linux/ctype.h> +#include <linux/kmemleak.h> #include <linux/slab.h> #include <linux/uuid.h> @@ -103,6 +104,7 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, var->var.VariableName[i] = '\0'; inode->i_private = var; + kmemleak_ignore(var); err = efivar_entry_add(var, &efivarfs_list); if (err) diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index 139d0bed42f8..3e21c0e8adae 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -107,11 +107,9 @@ static struct page *erofs_read_inode(struct inode *inode, i_gid_write(inode, le32_to_cpu(die->i_gid)); set_nlink(inode, le32_to_cpu(die->i_nlink)); - /* ns timestamp */ - inode->i_mtime.tv_sec = inode->i_ctime.tv_sec = - le64_to_cpu(die->i_ctime); - inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = - le32_to_cpu(die->i_ctime_nsec); + /* extended inode has its own timestamp */ + inode->i_ctime.tv_sec = le64_to_cpu(die->i_ctime); + inode->i_ctime.tv_nsec = le32_to_cpu(die->i_ctime_nsec); inode->i_size = le64_to_cpu(die->i_size); @@ -149,11 +147,9 @@ static struct page *erofs_read_inode(struct inode *inode, i_gid_write(inode, le16_to_cpu(dic->i_gid)); set_nlink(inode, le16_to_cpu(dic->i_nlink)); - /* use build time to derive all file time */ - inode->i_mtime.tv_sec = inode->i_ctime.tv_sec = - sbi->build_time; - inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = - sbi->build_time_nsec; + /* use build time for compact inodes */ + inode->i_ctime.tv_sec = sbi->build_time; + inode->i_ctime.tv_nsec = sbi->build_time_nsec; inode->i_size = le32_to_cpu(dic->i_size); if (erofs_inode_is_data_compressed(vi->datalayout)) @@ -167,6 +163,11 @@ static struct page *erofs_read_inode(struct inode *inode, goto err_out; } + inode->i_mtime.tv_sec = inode->i_ctime.tv_sec; + inode->i_atime.tv_sec = inode->i_ctime.tv_sec; + inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec; + inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec; + if (!nblks) /* measure inode.i_blocks as generic filesystems */ inode->i_blocks = roundup(inode->i_size, EROFS_BLKSIZ) >> 9; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 50912a5420b4..86fd3bf62af6 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1078,8 +1078,11 @@ out_allocpage: cond_resched(); goto repeat; } - set_page_private(page, (unsigned long)pcl); - SetPagePrivate(page); + + if (tocache) { + set_page_private(page, (unsigned long)pcl); + SetPagePrivate(page); + } out: /* the only exit (for tracing and debugging) */ return page; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 45fcdbf538d1..65ecaf96d0a4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1028,9 +1028,6 @@ struct ext4_inode_info { * protected by sbi->s_fc_lock. */ - /* Fast commit subtid when this inode was committed */ - unsigned int i_fc_committed_subtid; - /* Start of lblk range that needs to be committed in this fast commit */ ext4_lblk_t i_fc_lblk_start; @@ -1234,13 +1231,13 @@ struct ext4_inode_info { blocks */ #define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated file systems */ -#define EXT4_MOUNT2_DAX_NEVER 0x00000008 /* Do not allow Direct Access */ -#define EXT4_MOUNT2_DAX_INODE 0x00000010 /* For printing options only */ - #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM 0x00000008 /* User explicitly specified journal checksum */ #define EXT4_MOUNT2_JOURNAL_FAST_COMMIT 0x00000010 /* Journal fast commit */ +#define EXT4_MOUNT2_DAX_NEVER 0x00000020 /* Do not allow Direct Access */ +#define EXT4_MOUNT2_DAX_INODE 0x00000040 /* For printing options only */ + #define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \ ~EXT4_MOUNT_##opt @@ -1422,16 +1419,6 @@ struct ext4_super_block { #ifdef __KERNEL__ -/* - * run-time mount flags - */ -#define EXT4_MF_MNTDIR_SAMPLED 0x0001 -#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */ -#define EXT4_MF_FC_INELIGIBLE 0x0004 /* Fast commit ineligible */ -#define EXT4_MF_FC_COMMITTING 0x0008 /* File system underoing a fast - * commit. - */ - #ifdef CONFIG_FS_ENCRYPTION #define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL) #else @@ -1466,7 +1453,7 @@ struct ext4_sb_info { struct buffer_head * __rcu *s_group_desc; unsigned int s_mount_opt; unsigned int s_mount_opt2; - unsigned int s_mount_flags; + unsigned long s_mount_flags; unsigned int s_def_mount_opt; ext4_fsblk_t s_sb_block; atomic64_t s_resv_clusters; @@ -1695,6 +1682,34 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) }) /* + * run-time mount flags + */ +enum { + EXT4_MF_MNTDIR_SAMPLED, + EXT4_MF_FS_ABORTED, /* Fatal error detected */ + EXT4_MF_FC_INELIGIBLE, /* Fast commit ineligible */ + EXT4_MF_FC_COMMITTING /* File system underoing a fast + * commit. + */ +}; + +static inline void ext4_set_mount_flag(struct super_block *sb, int bit) +{ + set_bit(bit, &EXT4_SB(sb)->s_mount_flags); +} + +static inline void ext4_clear_mount_flag(struct super_block *sb, int bit) +{ + clear_bit(bit, &EXT4_SB(sb)->s_mount_flags); +} + +static inline int ext4_test_mount_flag(struct super_block *sb, int bit) +{ + return test_bit(bit, &EXT4_SB(sb)->s_mount_flags); +} + + +/* * Simulate_fail codes */ #define EXT4_SIM_BBITMAP_EIO 1 @@ -1863,6 +1878,13 @@ static inline bool ext4_verity_in_progress(struct inode *inode) #define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010 #define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200 +/* + * The reason why "FAST_COMMIT" is a compat feature is that, FS becomes + * incompatible only if fast commit blocks are present in the FS. Since we + * clear the journal (and thus the fast commit blocks), we don't mark FS as + * incompatible. We also have a JBD2 incompat feature, which gets set when + * there are fast commit blocks present in the journal. + */ #define EXT4_FEATURE_COMPAT_FAST_COMMIT 0x0400 #define EXT4_FEATURE_COMPAT_STABLE_INODES 0x0800 @@ -2673,7 +2695,8 @@ void ext4_insert_dentry(struct inode *inode, struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { - if (!ext4_has_feature_dir_index(inode->i_sb)) { + if (!ext4_has_feature_dir_index(inode->i_sb) && + ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { /* ext4_iget() should have caught this... */ WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb)); ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); @@ -2731,12 +2754,16 @@ extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate); int ext4_fc_info_show(struct seq_file *seq, void *v); void ext4_fc_init(struct super_block *sb, journal_t *journal); void ext4_fc_init_inode(struct inode *inode); -void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start, +void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end); -void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry); -void ext4_fc_track_link(struct inode *inode, struct dentry *dentry); -void ext4_fc_track_create(struct inode *inode, struct dentry *dentry); -void ext4_fc_track_inode(struct inode *inode); +void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode, + struct dentry *dentry); +void __ext4_fc_track_link(handle_t *handle, struct inode *inode, + struct dentry *dentry); +void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry); +void ext4_fc_track_link(handle_t *handle, struct dentry *dentry); +void ext4_fc_track_create(handle_t *handle, struct dentry *dentry); +void ext4_fc_track_inode(handle_t *handle, struct inode *inode); void ext4_fc_mark_ineligible(struct super_block *sb, int reason); void ext4_fc_start_ineligible(struct super_block *sb, int reason); void ext4_fc_stop_ineligible(struct super_block *sb); @@ -3452,7 +3479,7 @@ extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode, extern int ext4_ci_compare(const struct inode *parent, const struct qstr *fname, const struct qstr *entry, bool quick); -extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name, +extern int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name, struct inode *inode); extern int __ext4_link(struct inode *dir, struct inode *inode, struct dentry *dentry); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 57cfa28919a9..17d7096b3212 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3724,7 +3724,6 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, err = ext4_ext_dirty(handle, inode, path + path->p_depth); out: ext4_ext_show_leaf(inode, path); - ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1); return err; } @@ -3796,7 +3795,6 @@ convert_initialized_extent(handle_t *handle, struct inode *inode, if (*allocated > map->m_len) *allocated = map->m_len; map->m_len = *allocated; - ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1); return 0; } @@ -4329,7 +4327,6 @@ got_allocated_blocks: map->m_len = ar.len; allocated = map->m_len; ext4_ext_show_leaf(inode, path); - ext4_fc_track_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1); out: ext4_ext_drop_refs(path); kfree(path); @@ -4602,7 +4599,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) goto out_handle; - ext4_fc_track_range(inode, offset >> inode->i_sb->s_blocksize_bits, + ext4_fc_track_range(handle, inode, offset >> inode->i_sb->s_blocksize_bits, (offset + len - 1) >> inode->i_sb->s_blocksize_bits); /* Zero out partial block at the edges of the range */ ret = ext4_zero_partial_blocks(handle, inode, offset, len); @@ -4651,8 +4648,6 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE)) return -EOPNOTSUPP; - ext4_fc_track_range(inode, offset >> blkbits, - (offset + len - 1) >> blkbits); ext4_fc_start_update(inode); diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 8d43058386c3..f2033e13a273 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -83,7 +83,7 @@ * * Atomicity of commits * -------------------- - * In order to gaurantee atomicity during the commit operation, fast commit + * In order to guarantee atomicity during the commit operation, fast commit * uses "EXT4_FC_TAG_TAIL" tag that marks a fast commit as complete. Tail * tag contains CRC of the contents and TID of the transaction after which * this fast commit should be applied. Recovery code replays fast commit @@ -152,7 +152,31 @@ void ext4_fc_init_inode(struct inode *inode) INIT_LIST_HEAD(&ei->i_fc_list); init_waitqueue_head(&ei->i_fc_wait); atomic_set(&ei->i_fc_updates, 0); - ei->i_fc_committed_subtid = 0; +} + +/* This function must be called with sbi->s_fc_lock held. */ +static void ext4_fc_wait_committing_inode(struct inode *inode) +__releases(&EXT4_SB(inode->i_sb)->s_fc_lock) +{ + wait_queue_head_t *wq; + struct ext4_inode_info *ei = EXT4_I(inode); + +#if (BITS_PER_LONG < 64) + DEFINE_WAIT_BIT(wait, &ei->i_state_flags, + EXT4_STATE_FC_COMMITTING); + wq = bit_waitqueue(&ei->i_state_flags, + EXT4_STATE_FC_COMMITTING); +#else + DEFINE_WAIT_BIT(wait, &ei->i_flags, + EXT4_STATE_FC_COMMITTING); + wq = bit_waitqueue(&ei->i_flags, + EXT4_STATE_FC_COMMITTING); +#endif + lockdep_assert_held(&EXT4_SB(inode->i_sb)->s_fc_lock); + prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); + spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); + schedule(); + finish_wait(wq, &wait.wq_entry); } /* @@ -176,22 +200,7 @@ restart: goto out; if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) { - wait_queue_head_t *wq; -#if (BITS_PER_LONG < 64) - DEFINE_WAIT_BIT(wait, &ei->i_state_flags, - EXT4_STATE_FC_COMMITTING); - wq = bit_waitqueue(&ei->i_state_flags, - EXT4_STATE_FC_COMMITTING); -#else - DEFINE_WAIT_BIT(wait, &ei->i_flags, - EXT4_STATE_FC_COMMITTING); - wq = bit_waitqueue(&ei->i_flags, - EXT4_STATE_FC_COMMITTING); -#endif - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); - spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); - schedule(); - finish_wait(wq, &wait.wq_entry); + ext4_fc_wait_committing_inode(inode); goto restart; } out: @@ -234,26 +243,10 @@ restart: } if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) { - wait_queue_head_t *wq; -#if (BITS_PER_LONG < 64) - DEFINE_WAIT_BIT(wait, &ei->i_state_flags, - EXT4_STATE_FC_COMMITTING); - wq = bit_waitqueue(&ei->i_state_flags, - EXT4_STATE_FC_COMMITTING); -#else - DEFINE_WAIT_BIT(wait, &ei->i_flags, - EXT4_STATE_FC_COMMITTING); - wq = bit_waitqueue(&ei->i_flags, - EXT4_STATE_FC_COMMITTING); -#endif - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); - spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); - schedule(); - finish_wait(wq, &wait.wq_entry); + ext4_fc_wait_committing_inode(inode); goto restart; } - if (!list_empty(&ei->i_fc_list)) - list_del_init(&ei->i_fc_list); + list_del_init(&ei->i_fc_list); spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); } @@ -269,7 +262,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason) (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) return; - sbi->s_mount_flags |= EXT4_MF_FC_INELIGIBLE; + ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); WARN_ON(reason >= EXT4_FC_REASON_MAX); sbi->s_fc_stats.fc_ineligible_reason_count[reason]++; } @@ -302,14 +295,14 @@ void ext4_fc_stop_ineligible(struct super_block *sb) (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) return; - EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FC_INELIGIBLE; + ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); atomic_dec(&EXT4_SB(sb)->s_fc_ineligible_updates); } static inline int ext4_fc_is_ineligible(struct super_block *sb) { - return (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FC_INELIGIBLE) || - atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates); + return (ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE) || + atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates)); } /* @@ -323,13 +316,14 @@ static inline int ext4_fc_is_ineligible(struct super_block *sb) * If enqueue is set, this function enqueues the inode in fast commit list. */ static int ext4_fc_track_template( - struct inode *inode, int (*__fc_track_fn)(struct inode *, void *, bool), + handle_t *handle, struct inode *inode, + int (*__fc_track_fn)(struct inode *, void *, bool), void *args, int enqueue) { - tid_t running_txn_tid; bool update = false; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + tid_t tid = 0; int ret; if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || @@ -339,15 +333,13 @@ static int ext4_fc_track_template( if (ext4_fc_is_ineligible(inode->i_sb)) return -EINVAL; - running_txn_tid = sbi->s_journal ? - sbi->s_journal->j_commit_sequence + 1 : 0; - + tid = handle->h_transaction->t_tid; mutex_lock(&ei->i_fc_lock); - if (running_txn_tid == ei->i_sync_tid) { + if (tid == ei->i_sync_tid) { update = true; } else { ext4_fc_reset_inode(inode); - ei->i_sync_tid = running_txn_tid; + ei->i_sync_tid = tid; } ret = __fc_track_fn(inode, args, update); mutex_unlock(&ei->i_fc_lock); @@ -358,7 +350,7 @@ static int ext4_fc_track_template( spin_lock(&sbi->s_fc_lock); if (list_empty(&EXT4_I(inode)->i_fc_list)) list_add_tail(&EXT4_I(inode)->i_fc_list, - (sbi->s_mount_flags & EXT4_MF_FC_COMMITTING) ? + (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) ? &sbi->s_fc_q[FC_Q_STAGING] : &sbi->s_fc_q[FC_Q_MAIN]); spin_unlock(&sbi->s_fc_lock); @@ -384,7 +376,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) mutex_unlock(&ei->i_fc_lock); node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS); if (!node) { - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_MEM); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -397,7 +389,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) if (!node->fcd_name.name) { kmem_cache_free(ext4_fc_dentry_cachep, node); ext4_fc_mark_ineligible(inode->i_sb, - EXT4_FC_REASON_MEM); + EXT4_FC_REASON_NOMEM); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -411,7 +403,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) node->fcd_name.len = dentry->d_name.len; spin_lock(&sbi->s_fc_lock); - if (sbi->s_mount_flags & EXT4_MF_FC_COMMITTING) + if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_STAGING]); else @@ -422,7 +414,8 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) return 0; } -void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry) +void __ext4_fc_track_unlink(handle_t *handle, + struct inode *inode, struct dentry *dentry) { struct __track_dentry_update_args args; int ret; @@ -430,12 +423,18 @@ void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry) args.dentry = dentry; args.op = EXT4_FC_TAG_UNLINK; - ret = ext4_fc_track_template(inode, __track_dentry_update, + ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_unlink(inode, dentry, ret); } -void ext4_fc_track_link(struct inode *inode, struct dentry *dentry) +void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry) +{ + __ext4_fc_track_unlink(handle, d_inode(dentry), dentry); +} + +void __ext4_fc_track_link(handle_t *handle, + struct inode *inode, struct dentry *dentry) { struct __track_dentry_update_args args; int ret; @@ -443,20 +442,26 @@ void ext4_fc_track_link(struct inode *inode, struct dentry *dentry) args.dentry = dentry; args.op = EXT4_FC_TAG_LINK; - ret = ext4_fc_track_template(inode, __track_dentry_update, + ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_link(inode, dentry, ret); } -void ext4_fc_track_create(struct inode *inode, struct dentry *dentry) +void ext4_fc_track_link(handle_t *handle, struct dentry *dentry) +{ + __ext4_fc_track_link(handle, d_inode(dentry), dentry); +} + +void ext4_fc_track_create(handle_t *handle, struct dentry *dentry) { struct __track_dentry_update_args args; + struct inode *inode = d_inode(dentry); int ret; args.dentry = dentry; args.op = EXT4_FC_TAG_CREAT; - ret = ext4_fc_track_template(inode, __track_dentry_update, + ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_create(inode, dentry, ret); } @@ -472,14 +477,20 @@ static int __track_inode(struct inode *inode, void *arg, bool update) return 0; } -void ext4_fc_track_inode(struct inode *inode) +void ext4_fc_track_inode(handle_t *handle, struct inode *inode) { int ret; if (S_ISDIR(inode->i_mode)) return; - ret = ext4_fc_track_template(inode, __track_inode, NULL, 1); + if (ext4_should_journal_data(inode)) { + ext4_fc_mark_ineligible(inode->i_sb, + EXT4_FC_REASON_INODE_JOURNAL_DATA); + return; + } + + ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1); trace_ext4_fc_track_inode(inode, ret); } @@ -515,7 +526,7 @@ static int __track_range(struct inode *inode, void *arg, bool update) return 0; } -void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start, +void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { struct __track_range_args args; @@ -527,7 +538,7 @@ void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start, args.start = start; args.end = end; - ret = ext4_fc_track_template(inode, __track_range, &args, 1); + ret = ext4_fc_track_template(handle, inode, __track_range, &args, 1); trace_ext4_fc_track_range(inode, start, end, ret); } @@ -537,10 +548,11 @@ static void ext4_fc_submit_bh(struct super_block *sb) int write_flags = REQ_SYNC; struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh; + /* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */ if (test_opt(sb, BARRIER)) write_flags |= REQ_FUA | REQ_PREFLUSH; lock_buffer(bh); - clear_buffer_dirty(bh); + set_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = ext4_end_buffer_io_sync; submit_bh(REQ_OP_WRITE, write_flags, bh); @@ -846,7 +858,7 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal) int ret = 0; spin_lock(&sbi->s_fc_lock); - sbi->s_mount_flags |= EXT4_MF_FC_COMMITTING; + ext4_set_mount_flag(sb, EXT4_MF_FC_COMMITTING); list_for_each(pos, &sbi->s_fc_q[FC_Q_MAIN]) { ei = list_entry(pos, struct ext4_inode_info, i_fc_list); ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING); @@ -900,6 +912,8 @@ static int ext4_fc_wait_inode_data_all(journal_t *journal) /* Commit all the directory entry updates */ static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc) +__acquires(&sbi->s_fc_lock) +__releases(&sbi->s_fc_lock) { struct super_block *sb = (struct super_block *)(journal->j_private); struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -996,6 +1010,13 @@ static int ext4_fc_perform_commit(journal_t *journal) if (ret) return ret; + /* + * If file system device is different from journal device, issue a cache + * flush before we start writing fast commit blocks. + */ + if (journal->j_fs_dev != journal->j_dev) + blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS); + blk_start_plug(&plug); if (sbi->s_fc_bytes == 0) { /* @@ -1031,8 +1052,6 @@ static int ext4_fc_perform_commit(journal_t *journal) if (ret) goto out; spin_lock(&sbi->s_fc_lock); - EXT4_I(inode)->i_fc_committed_subtid = - atomic_read(&sbi->s_fc_subtid); } spin_unlock(&sbi->s_fc_lock); @@ -1131,7 +1150,7 @@ out: "Fast commit ended with blks = %d, reason = %d, subtid - %d", nblks, reason, subtid); if (reason == EXT4_FC_REASON_FC_FAILED) - return jbd2_fc_end_commit_fallback(journal, commit_tid); + return jbd2_fc_end_commit_fallback(journal); if (reason == EXT4_FC_REASON_FC_START_FAILED || reason == EXT4_FC_REASON_INELIGIBLE) return jbd2_complete_transaction(journal, commit_tid); @@ -1190,8 +1209,8 @@ static void ext4_fc_cleanup(journal_t *journal, int full) list_splice_init(&sbi->s_fc_q[FC_Q_STAGING], &sbi->s_fc_q[FC_Q_STAGING]); - sbi->s_mount_flags &= ~EXT4_MF_FC_COMMITTING; - sbi->s_mount_flags &= ~EXT4_MF_FC_INELIGIBLE; + ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); + ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); if (full) sbi->s_fc_bytes = 0; @@ -1263,7 +1282,7 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl) return 0; } - ret = __ext4_unlink(old_parent, &entry, inode); + ret = __ext4_unlink(NULL, old_parent, &entry, inode); /* -ENOENT ok coz it might not exist anymore. */ if (ret == -ENOENT) ret = 0; @@ -2079,8 +2098,6 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh, void ext4_fc_init(struct super_block *sb, journal_t *journal) { - int num_fc_blocks; - /* * We set replay callback even if fast commit disabled because we may * could still have fast commit blocks that need to be replayed even if @@ -2090,21 +2107,9 @@ void ext4_fc_init(struct super_block *sb, journal_t *journal) if (!test_opt2(sb, JOURNAL_FAST_COMMIT)) return; journal->j_fc_cleanup_callback = ext4_fc_cleanup; - if (!buffer_uptodate(journal->j_sb_buffer) - && ext4_read_bh_lock(journal->j_sb_buffer, REQ_META | REQ_PRIO, - true)) { - ext4_msg(sb, KERN_ERR, "I/O error on journal"); - return; - } - num_fc_blocks = be32_to_cpu(journal->j_superblock->s_num_fc_blks); - if (jbd2_fc_init(journal, num_fc_blocks ? num_fc_blocks : - EXT4_NUM_FC_BLKS)) { - pr_warn("Error while enabling fast commits, turning off."); - ext4_clear_feature_fast_commit(sb); - } } -const char *fc_ineligible_reasons[] = { +static const char *fc_ineligible_reasons[] = { "Extended attributes changed", "Cross rename", "Journal flag changed", @@ -2113,6 +2118,7 @@ const char *fc_ineligible_reasons[] = { "Resize", "Dir renamed", "Falloc range op", + "Data journalling", "FC Commit Failed" }; diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h index 06907d485989..3a6e5a1fa1b8 100644 --- a/fs/ext4/fast_commit.h +++ b/fs/ext4/fast_commit.h @@ -3,9 +3,6 @@ #ifndef __FAST_COMMIT_H__ #define __FAST_COMMIT_H__ -/* Number of blocks in journal area to allocate for fast commits */ -#define EXT4_NUM_FC_BLKS 256 - /* Fast commit tags */ #define EXT4_FC_TAG_ADD_RANGE 0x0001 #define EXT4_FC_TAG_DEL_RANGE 0x0002 @@ -100,11 +97,12 @@ enum { EXT4_FC_REASON_XATTR = 0, EXT4_FC_REASON_CROSS_RENAME, EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, - EXT4_FC_REASON_MEM, + EXT4_FC_REASON_NOMEM, EXT4_FC_REASON_SWAP_BOOT, EXT4_FC_REASON_RESIZE, EXT4_FC_REASON_RENAME_DIR, EXT4_FC_REASON_FALLOC_RANGE, + EXT4_FC_REASON_INODE_JOURNAL_DATA, EXT4_FC_COMMIT_FAILED, EXT4_FC_REASON_MAX }; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index d85412d12e3a..3ed8c048fb12 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -761,7 +761,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) if (!daxdev_mapping_supported(vma, dax_dev)) return -EOPNOTSUPP; - ext4_fc_start_update(inode); file_accessed(file); if (IS_DAX(file_inode(file))) { vma->vm_ops = &ext4_dax_vm_ops; @@ -769,7 +768,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) } else { vma->vm_ops = &ext4_file_vm_ops; } - ext4_fc_stop_update(inode); return 0; } @@ -782,13 +780,13 @@ static int ext4_sample_last_mounted(struct super_block *sb, handle_t *handle; int err; - if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED)) + if (likely(ext4_test_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED))) return 0; if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb)) return 0; - sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED; + ext4_set_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED); /* * Sample where the filesystem has been mounted and * store it in the superblock for sysadmin convenience diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index b232c2767534..4c2a9fe30067 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -280,7 +280,7 @@ static int ext4_getfsmap_logdev(struct super_block *sb, struct ext4_fsmap *keys, /* Fabricate an rmap entry for the external log device. */ irec.fmr_physical = journal->j_blk_offset; - irec.fmr_length = journal->j_maxlen; + irec.fmr_length = journal->j_total_len; irec.fmr_owner = EXT4_FMR_OWN_LOG; irec.fmr_flags = 0; diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 81a545fd14a3..a42ca95840f2 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -143,7 +143,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (sb_rdonly(inode->i_sb)) { /* Make sure that we read updated s_mount_flags value */ smp_rmb(); - if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) + if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED)) ret = -EROFS; goto out; } diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index caa51473207d..b41512d1badc 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1880,6 +1880,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) ext4_write_lock_xattr(inode, &no_expand); if (!ext4_has_inline_data(inode)) { + ext4_write_unlock_xattr(inode, &no_expand); *has_inline = 0; ext4_journal_stop(handle); return 0; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b96a18679a27..0d8385aea898 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -327,6 +327,8 @@ stop_handle: ext4_xattr_inode_array_free(ea_inode_array); return; no_delete: + if (!list_empty(&EXT4_I(inode)->i_fc_list)) + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ } @@ -730,7 +732,7 @@ out_sem: if (ret) return ret; } - ext4_fc_track_range(inode, map->m_lblk, + ext4_fc_track_range(handle, inode, map->m_lblk, map->m_lblk + map->m_len - 1); } @@ -2440,7 +2442,7 @@ static int mpage_map_and_submit_extent(handle_t *handle, struct super_block *sb = inode->i_sb; if (ext4_forced_shutdown(EXT4_SB(sb)) || - EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) + ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) goto invalidate_dirty_pages; /* * Let the uper layers retry transient errors. @@ -2674,7 +2676,7 @@ static int ext4_writepages(struct address_space *mapping, * the stack trace. */ if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) || - sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) { + ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))) { ret = -EROFS; goto out_writepages; } @@ -3310,8 +3312,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode) EXT4_I(inode)->i_datasync_tid)) return false; if (test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT)) - return atomic_read(&EXT4_SB(inode->i_sb)->s_fc_subtid) < - EXT4_I(inode)->i_fc_committed_subtid; + return !list_empty(&EXT4_I(inode)->i_fc_list); return true; } @@ -4109,7 +4110,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) up_write(&EXT4_I(inode)->i_data_sem); } - ext4_fc_track_range(inode, first_block, stop_block); + ext4_fc_track_range(handle, inode, first_block, stop_block); if (IS_SYNC(inode)) ext4_handle_sync(handle); @@ -5442,14 +5443,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } if (shrink) - ext4_fc_track_range(inode, + ext4_fc_track_range(handle, inode, (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >> inode->i_sb->s_blocksize_bits, (oldsize > 0 ? oldsize - 1 : 0) >> inode->i_sb->s_blocksize_bits); else ext4_fc_track_range( - inode, + handle, inode, (oldsize > 0 ? oldsize - 1 : oldsize) >> inode->i_sb->s_blocksize_bits, (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >> @@ -5699,7 +5700,7 @@ int ext4_mark_iloc_dirty(handle_t *handle, put_bh(iloc->bh); return -EIO; } - ext4_fc_track_inode(inode); + ext4_fc_track_inode(handle, inode); if (IS_I_VERSION(inode)) inode_inc_iversion(inode); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 85abbfb98cbe..24af9ed5c3e5 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4477,7 +4477,7 @@ static inline void ext4_mb_show_pa(struct super_block *sb) { ext4_group_t i, ngroups; - if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) + if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) return; ngroups = ext4_get_groups_count(sb); @@ -4508,7 +4508,7 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; - if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) + if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) return; mb_debug(sb, "Can't allocate:" @@ -5167,7 +5167,7 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle, struct super_block *sb = ar->inode->i_sb; ext4_group_t group; ext4_grpblk_t blkoff; - int i; + int i = sb->s_blocksize; ext4_fsblk_t goal, block; struct ext4_super_block *es = EXT4_SB(sb)->s_es; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index f458d1d81d96..33509266f5a0 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2606,7 +2606,7 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { handle_t *handle; - struct inode *inode, *inode_save; + struct inode *inode; int err, credits, retries = 0; err = dquot_initialize(dir); @@ -2624,11 +2624,9 @@ retry: inode->i_op = &ext4_file_inode_operations; inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); - inode_save = inode; - ihold(inode_save); err = ext4_add_nondir(handle, dentry, &inode); - ext4_fc_track_create(inode_save, dentry); - iput(inode_save); + if (!err) + ext4_fc_track_create(handle, dentry); } if (handle) ext4_journal_stop(handle); @@ -2643,7 +2641,7 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { handle_t *handle; - struct inode *inode, *inode_save; + struct inode *inode; int err, credits, retries = 0; err = dquot_initialize(dir); @@ -2660,12 +2658,9 @@ retry: if (!IS_ERR(inode)) { init_special_inode(inode, inode->i_mode, rdev); inode->i_op = &ext4_special_inode_operations; - inode_save = inode; - ihold(inode_save); err = ext4_add_nondir(handle, dentry, &inode); if (!err) - ext4_fc_track_create(inode_save, dentry); - iput(inode_save); + ext4_fc_track_create(handle, dentry); } if (handle) ext4_journal_stop(handle); @@ -2829,7 +2824,6 @@ out_clear_inode: iput(inode); goto out_retry; } - ext4_fc_track_create(inode, dentry); ext4_inc_count(dir); ext4_update_dx_flag(dir); @@ -2837,6 +2831,7 @@ out_clear_inode: if (err) goto out_clear_inode; d_instantiate_new(dentry, inode); + ext4_fc_track_create(handle, dentry); if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); @@ -3171,7 +3166,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) goto end_rmdir; ext4_dec_count(dir); ext4_update_dx_flag(dir); - ext4_fc_track_unlink(inode, dentry); + ext4_fc_track_unlink(handle, dentry); retval = ext4_mark_inode_dirty(handle, dir); #ifdef CONFIG_UNICODE @@ -3192,13 +3187,12 @@ end_rmdir: return retval; } -int __ext4_unlink(struct inode *dir, const struct qstr *d_name, +int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name, struct inode *inode) { int retval = -ENOENT; struct buffer_head *bh; struct ext4_dir_entry_2 *de; - handle_t *handle = NULL; int skip_remove_dentry = 0; bh = ext4_find_entry(dir, d_name, &de, NULL); @@ -3217,14 +3211,7 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name, if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) skip_remove_dentry = 1; else - goto out_bh; - } - - handle = ext4_journal_start(dir, EXT4_HT_DIR, - EXT4_DATA_TRANS_BLOCKS(dir->i_sb)); - if (IS_ERR(handle)) { - retval = PTR_ERR(handle); - goto out_bh; + goto out; } if (IS_DIRSYNC(dir)) @@ -3233,12 +3220,12 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name, if (!skip_remove_dentry) { retval = ext4_delete_entry(handle, dir, de, bh); if (retval) - goto out_handle; + goto out; dir->i_ctime = dir->i_mtime = current_time(dir); ext4_update_dx_flag(dir); retval = ext4_mark_inode_dirty(handle, dir); if (retval) - goto out_handle; + goto out; } else { retval = 0; } @@ -3252,15 +3239,14 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name, inode->i_ctime = current_time(inode); retval = ext4_mark_inode_dirty(handle, inode); -out_handle: - ext4_journal_stop(handle); -out_bh: +out: brelse(bh); return retval; } static int ext4_unlink(struct inode *dir, struct dentry *dentry) { + handle_t *handle; int retval; if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) @@ -3278,9 +3264,16 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) if (retval) goto out_trace; - retval = __ext4_unlink(dir, &dentry->d_name, d_inode(dentry)); + handle = ext4_journal_start(dir, EXT4_HT_DIR, + EXT4_DATA_TRANS_BLOCKS(dir->i_sb)); + if (IS_ERR(handle)) { + retval = PTR_ERR(handle); + goto out_trace; + } + + retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry)); if (!retval) - ext4_fc_track_unlink(d_inode(dentry), dentry); + ext4_fc_track_unlink(handle, dentry); #ifdef CONFIG_UNICODE /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid @@ -3291,6 +3284,8 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) if (IS_CASEFOLDED(dir)) d_invalidate(dentry); #endif + if (handle) + ext4_journal_stop(handle); out_trace: trace_ext4_unlink_exit(dentry, retval); @@ -3447,7 +3442,6 @@ retry: err = ext4_add_entry(handle, dentry, inode); if (!err) { - ext4_fc_track_link(inode, dentry); err = ext4_mark_inode_dirty(handle, inode); /* this can happen only for tmpfile being * linked the first time @@ -3455,6 +3449,7 @@ retry: if (inode->i_nlink == 1) ext4_orphan_del(handle, inode); d_instantiate(dentry, inode); + ext4_fc_track_link(handle, dentry); } else { drop_nlink(inode); iput(inode); @@ -3915,9 +3910,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, EXT4_FC_REASON_RENAME_DIR); } else { if (new.inode) - ext4_fc_track_unlink(new.inode, new.dentry); - ext4_fc_track_link(old.inode, new.dentry); - ext4_fc_track_unlink(old.inode, old.dentry); + ext4_fc_track_unlink(handle, new.dentry); + __ext4_fc_track_link(handle, old.inode, new.dentry); + __ext4_fc_track_unlink(handle, old.inode, old.dentry); } if (new.inode) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ef4734b40e2a..94472044f4c1 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -289,18 +289,7 @@ void ext4_superblock_csum_set(struct super_block *sb) if (!ext4_has_metadata_csum(sb)) return; - /* - * Locking the superblock prevents the scenario - * where: - * 1) a first thread pauses during checksum calculation. - * 2) a second thread updates the superblock, recalculates - * the checksum, and updates s_checksum - * 3) the first thread resumes and finishes its checksum calculation - * and updates s_checksum with a potentially stale or torn value. - */ - lock_buffer(EXT4_SB(sb)->s_sbh); es->s_checksum = ext4_superblock_csum(sb, es); - unlock_buffer(EXT4_SB(sb)->s_sbh); } ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, @@ -686,7 +675,7 @@ static void ext4_handle_error(struct super_block *sb) if (!test_opt(sb, ERRORS_CONT)) { journal_t *journal = EXT4_SB(sb)->s_journal; - EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; + ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); if (journal) jbd2_journal_abort(journal, -EIO); } @@ -904,7 +893,7 @@ void __ext4_abort(struct super_block *sb, const char *function, va_end(args); if (sb_rdonly(sb) == 0) { - EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; + ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); if (EXT4_SB(sb)->s_journal) jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); @@ -1716,11 +1705,10 @@ enum { Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, - Opt_prefetch_block_bitmaps, Opt_no_fc, + Opt_prefetch_block_bitmaps, #ifdef CONFIG_EXT4_DEBUG - Opt_fc_debug_max_replay, + Opt_fc_debug_max_replay, Opt_fc_debug_force #endif - Opt_fc_debug_force }; static const match_table_t tokens = { @@ -1807,9 +1795,8 @@ static const match_table_t tokens = { {Opt_init_itable, "init_itable=%u"}, {Opt_init_itable, "init_itable"}, {Opt_noinit_itable, "noinit_itable"}, - {Opt_no_fc, "no_fc"}, - {Opt_fc_debug_force, "fc_debug_force"}, #ifdef CONFIG_EXT4_DEBUG + {Opt_fc_debug_force, "fc_debug_force"}, {Opt_fc_debug_max_replay, "fc_debug_max_replay=%u"}, #endif {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, @@ -2027,8 +2014,8 @@ static const struct mount_opts { {Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA), MOPT_CLEAR | MOPT_Q}, - {Opt_usrjquota, 0, MOPT_Q}, - {Opt_grpjquota, 0, MOPT_Q}, + {Opt_usrjquota, 0, MOPT_Q | MOPT_STRING}, + {Opt_grpjquota, 0, MOPT_Q | MOPT_STRING}, {Opt_offusrjquota, 0, MOPT_Q}, {Opt_offgrpjquota, 0, MOPT_Q}, {Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT}, @@ -2039,11 +2026,9 @@ static const struct mount_opts { {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS, MOPT_SET}, - {Opt_no_fc, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, - MOPT_CLEAR | MOPT_2 | MOPT_EXT4_ONLY}, +#ifdef CONFIG_EXT4_DEBUG {Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY}, -#ifdef CONFIG_EXT4_DEBUG {Opt_fc_debug_max_replay, 0, MOPT_GTE0}, #endif {Opt_err, 0, 0} @@ -2153,7 +2138,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt); return 1; case Opt_abort: - sbi->s_mount_flags |= EXT4_MF_FS_ABORTED; + ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); return 1; case Opt_i_version: sb->s_flags |= SB_I_VERSION; @@ -2653,10 +2638,6 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, } else if (test_opt2(sb, DAX_INODE)) { SEQ_OPTS_PUTS("dax=inode"); } - - if (test_opt2(sb, JOURNAL_FAST_COMMIT)) - SEQ_OPTS_PUTS("fast_commit"); - ext4_show_quota_options(seq, sb); return 0; } @@ -3976,7 +3957,7 @@ int ext4_calculate_overhead(struct super_block *sb) * loaded or not */ if (sbi->s_journal && !sbi->s_journal_bdev) - overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen); + overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len); else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ j_inode = ext4_get_journal_inode(sb, j_inum); @@ -4340,9 +4321,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #endif if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { - printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n"); + printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, O_DIRECT and fast_commit support!\n"); /* can't mount with both data=journal and dioread_nolock. */ clear_opt(sb, DIOREAD_NOLOCK); + clear_opt2(sb, JOURNAL_FAST_COMMIT); if (test_opt2(sb, EXPLICIT_DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and delalloc"); @@ -4777,8 +4759,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]); INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]); sbi->s_fc_bytes = 0; - sbi->s_mount_flags &= ~EXT4_MF_FC_INELIGIBLE; - sbi->s_mount_flags &= ~EXT4_MF_FC_COMMITTING; + ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); + ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); spin_lock_init(&sbi->s_fc_lock); memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats)); sbi->s_fc_replay_state.fc_regions = NULL; @@ -4857,6 +4839,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount_wq; } + if (test_opt2(sb, JOURNAL_FAST_COMMIT) && + !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, + JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) { + ext4_msg(sb, KERN_ERR, + "Failed to set fast commit journal feature"); + goto failed_mount_wq; + } + /* We have now updated the journal if required, so we can * validate the data journaling mode. */ switch (test_opt(sb, DATA_FLAGS)) { @@ -5872,7 +5862,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } - if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) + if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user"); sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | @@ -5886,7 +5876,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) { - if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) { + if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) { err = -EROFS; goto restore_opts; } @@ -6560,10 +6550,6 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, brelse(bh); out: if (inode->i_size < off + len) { - ext4_fc_track_range(inode, - (inode->i_size > 0 ? inode->i_size - 1 : 0) - >> inode->i_sb->s_blocksize_bits, - (off + len) >> inode->i_sb->s_blocksize_bits); i_size_write(inode, off + len); EXT4_I(inode)->i_disksize = inode->i_size; err2 = ext4_mark_inode_dirty(handle, inode); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 9cd2ecad07db..cc4f987687f3 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -77,7 +77,7 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock, if (error) return error; if (!buffer_mapped(bh_result)) - return -EIO; + return -ENODATA; return 0; } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 8dff9cbd0a87..62d9081d1e26 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1301,12 +1301,8 @@ int gfs2_block_map(struct inode *inode, sector_t lblock, trace_gfs2_bmap(ip, bh_map, lblock, create, 1); ret = gfs2_iomap_get(inode, pos, length, flags, &iomap, &mp); - if (!ret && iomap.type == IOMAP_HOLE) { - if (create) - ret = gfs2_iomap_alloc(inode, &iomap, &mp); - else - ret = -ENODATA; - } + if (create && !ret && iomap.type == IOMAP_HOLE) + ret = gfs2_iomap_alloc(inode, &iomap, &mp); release_metapath(&mp); if (ret) goto out; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index d98a2e5dab9f..35a6fd103761 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1035,6 +1035,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, gl->gl_node.next = NULL; gl->gl_flags = 0; gl->gl_name = name; + lockdep_set_subclass(&gl->gl_lockref.lock, glops->go_subclass); gl->gl_lockref.count = 1; gl->gl_state = LM_ST_UNLOCKED; gl->gl_target = LM_ST_UNLOCKED; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 6c1432d78dce..3faa421568b0 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -245,7 +245,7 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags) static void gfs2_rgrp_go_dump(struct seq_file *seq, struct gfs2_glock *gl, const char *fs_id_buf) { - struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); + struct gfs2_rgrpd *rgd = gl->gl_object; if (rgd) gfs2_rgrp_dump(seq, rgd, fs_id_buf); @@ -571,7 +571,19 @@ static int freeze_go_sync(struct gfs2_glock *gl) int error = 0; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - if (gl->gl_req == LM_ST_EXCLUSIVE && !gfs2_withdrawn(sdp)) { + /* + * We need to check gl_state == LM_ST_SHARED here and not gl_req == + * LM_ST_EXCLUSIVE. That's because when any node does a freeze, + * all the nodes should have the freeze glock in SH mode and they all + * call do_xmote: One for EX and the others for UN. They ALL must + * freeze locally, and they ALL must queue freeze work. The freeze_work + * calls freeze_func, which tries to reacquire the freeze glock in SH, + * effectively waiting for the thaw on the node who holds it in EX. + * Once thawed, the work func acquires the freeze glock in + * SH and everybody goes back to thawed. + */ + if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp) && + !test_bit(SDF_NORECOVERY, &sdp->sd_flags)) { atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE); error = freeze_super(sdp->sd_vfs); if (error) { @@ -770,6 +782,7 @@ const struct gfs2_glock_operations gfs2_iopen_glops = { .go_callback = iopen_go_callback, .go_demote_ok = iopen_go_demote_ok, .go_flags = GLOF_LRU | GLOF_NONDISK, + .go_subclass = 1, }; const struct gfs2_glock_operations gfs2_flock_glops = { diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index d7707307f4b1..f8858d995b24 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -247,6 +247,7 @@ struct gfs2_glock_operations { const char *fs_id_buf); void (*go_callback)(struct gfs2_glock *gl, bool remote); void (*go_free)(struct gfs2_glock *gl); + const int go_subclass; const int go_type; const unsigned long go_flags; #define GLOF_ASPACE 1 /* address space attached */ diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 077ccb1b3ccc..65ae4fc28ede 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -150,6 +150,8 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (unlikely(error)) goto fail; + if (blktype != GFS2_BLKST_UNLINKED) + gfs2_cancel_delete_work(io_gl); if (type == DT_UNKNOWN || blktype != GFS2_BLKST_FREE) { /* @@ -180,8 +182,6 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); if (unlikely(error)) goto fail; - if (blktype != GFS2_BLKST_UNLINKED) - gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl); glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_glock_put(io_gl); io_gl = NULL; @@ -725,13 +725,19 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, flush_delayed_work(&ip->i_gl->gl_work); glock_set_object(ip->i_gl, ip); - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); + error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (error) goto fail_free_inode; + gfs2_cancel_delete_work(io_gl); + glock_set_object(io_gl, ip); + + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); + if (error) + goto fail_gunlock2; error = gfs2_trans_begin(sdp, blocks, 0); if (error) - goto fail_free_inode; + goto fail_gunlock2; if (blocks > 1) { ip->i_eattr = ip->i_no_addr + 1; @@ -740,18 +746,12 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, init_dinode(dip, ip, symname); gfs2_trans_end(sdp); - error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl); - if (error) - goto fail_free_inode; - BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags)); error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); if (error) goto fail_gunlock2; - gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl); - glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_set_iop(inode); insert_inode_hash(inode); @@ -803,6 +803,7 @@ fail_gunlock3: gfs2_glock_dq_uninit(&ip->i_iopen_gh); fail_gunlock2: clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); + glock_clear_object(io_gl, ip); gfs2_glock_put(io_gl); fail_free_inode: if (ip->i_gl) { @@ -2116,6 +2117,25 @@ loff_t gfs2_seek_hole(struct file *file, loff_t offset) return vfs_setpos(file, ret, inode->i_sb->s_maxbytes); } +static int gfs2_update_time(struct inode *inode, struct timespec64 *time, + int flags) +{ + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_glock *gl = ip->i_gl; + struct gfs2_holder *gh; + int error; + + gh = gfs2_glock_is_locked_by_me(gl); + if (gh && !gfs2_glock_is_held_excl(gl)) { + gfs2_glock_dq(gh); + gfs2_holder_reinit(LM_ST_EXCLUSIVE, 0, gh); + error = gfs2_glock_nq(gh); + if (error) + return error; + } + return generic_update_time(inode, time, flags); +} + const struct inode_operations gfs2_file_iops = { .permission = gfs2_permission, .setattr = gfs2_setattr, @@ -2124,6 +2144,7 @@ const struct inode_operations gfs2_file_iops = { .fiemap = gfs2_fiemap, .get_acl = gfs2_get_acl, .set_acl = gfs2_set_acl, + .update_time = gfs2_update_time, }; const struct inode_operations gfs2_dir_iops = { @@ -2143,6 +2164,7 @@ const struct inode_operations gfs2_dir_iops = { .fiemap = gfs2_fiemap, .get_acl = gfs2_get_acl, .set_acl = gfs2_set_acl, + .update_time = gfs2_update_time, .atomic_open = gfs2_atomic_open, }; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 9133b3178677..2e9314091c81 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -132,6 +132,8 @@ __acquires(&sdp->sd_ail_lock) spin_unlock(&sdp->sd_ail_lock); ret = generic_writepages(mapping, wbc); spin_lock(&sdp->sd_ail_lock); + if (ret == -ENODATA) /* if a jdata write into a new hole */ + ret = 0; /* ignore it */ if (ret || wbc->nr_to_write <= 0) break; return -EBUSY; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 92d799a193b8..5e8eef9990e3 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -985,6 +985,10 @@ static int gfs2_ri_update(struct gfs2_inode *ip) if (error < 0) return error; + if (RB_EMPTY_ROOT(&sdp->sd_rindex_tree)) { + fs_err(sdp, "no resource groups found in the file system.\n"); + return -ENOENT; + } set_rgrp_preferences(sdp); sdp->sd_rindex_uptodate = 1; @@ -2529,13 +2533,13 @@ int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type) rbm.rgd = rgd; error = gfs2_rbm_from_block(&rbm, no_addr); - if (WARN_ON_ONCE(error)) - goto fail; - - if (gfs2_testbit(&rbm, false) != type) - error = -ESTALE; + if (!WARN_ON_ONCE(error)) { + if (gfs2_testbit(&rbm, false) != type) + error = -ESTALE; + } gfs2_glock_dq_uninit(&rgd_gh); + fail: return error; } diff --git a/fs/io_uring.c b/fs/io_uring.c index 8018c7076b25..86dac2b2e276 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -205,6 +205,7 @@ struct fixed_file_ref_node { struct list_head file_list; struct fixed_file_data *file_data; struct llist_node llist; + bool done; }; struct fixed_file_data { @@ -478,6 +479,7 @@ struct io_sr_msg { struct io_open { struct file *file; int dfd; + bool ignore_nonblock; struct filename *filename; struct open_how how; unsigned long nofile; @@ -1282,7 +1284,7 @@ static bool io_identity_cow(struct io_kiocb *req) */ io_init_identity(id); if (creds) - req->work.identity->creds = creds; + id->creds = creds; /* add one for this request */ refcount_inc(&id->count); @@ -1311,22 +1313,6 @@ static bool io_grab_identity(struct io_kiocb *req) return false; req->work.flags |= IO_WQ_WORK_FSIZE; } - - if (!(req->work.flags & IO_WQ_WORK_FILES) && - (def->work_flags & IO_WQ_WORK_FILES) && - !(req->flags & REQ_F_NO_FILE_TABLE)) { - if (id->files != current->files || - id->nsproxy != current->nsproxy) - return false; - atomic_inc(&id->files->count); - get_nsproxy(id->nsproxy); - req->flags |= REQ_F_INFLIGHT; - - spin_lock_irq(&ctx->inflight_lock); - list_add(&req->inflight_entry, &ctx->inflight_list); - spin_unlock_irq(&ctx->inflight_lock); - req->work.flags |= IO_WQ_WORK_FILES; - } #ifdef CONFIG_BLK_CGROUP if (!(req->work.flags & IO_WQ_WORK_BLKCG) && (def->work_flags & IO_WQ_WORK_BLKCG)) { @@ -1368,6 +1354,21 @@ static bool io_grab_identity(struct io_kiocb *req) } spin_unlock(¤t->fs->lock); } + if (!(req->work.flags & IO_WQ_WORK_FILES) && + (def->work_flags & IO_WQ_WORK_FILES) && + !(req->flags & REQ_F_NO_FILE_TABLE)) { + if (id->files != current->files || + id->nsproxy != current->nsproxy) + return false; + atomic_inc(&id->files->count); + get_nsproxy(id->nsproxy); + req->flags |= REQ_F_INFLIGHT; + + spin_lock_irq(&ctx->inflight_lock); + list_add(&req->inflight_entry, &ctx->inflight_list); + spin_unlock_irq(&ctx->inflight_lock); + req->work.flags |= IO_WQ_WORK_FILES; + } return true; } @@ -2577,7 +2578,6 @@ static bool io_resubmit_prep(struct io_kiocb *req, int error) } end_req: req_set_fail_links(req); - io_req_complete(req, ret); return false; } #endif @@ -3192,7 +3192,7 @@ static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec, rw->free_iovec = iovec; rw->bytes_done = 0; /* can only be fixed buffers, no need to do anything */ - if (iter->type == ITER_BVEC) + if (iov_iter_is_bvec(iter)) return; if (!iovec) { unsigned iov_off = 0; @@ -3547,8 +3547,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, * we return to userspace. */ if (req->flags & REQ_F_ISREG) { - __sb_start_write(file_inode(req->file)->i_sb, - SB_FREEZE_WRITE, true); + sb_start_write(file_inode(req->file)->i_sb); __sb_writers_release(file_inode(req->file)->i_sb, SB_FREEZE_WRITE); } @@ -3796,6 +3795,7 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe return ret; } req->open.nofile = rlimit(RLIMIT_NOFILE); + req->open.ignore_nonblock = false; req->flags |= REQ_F_NEED_CLEANUP; return 0; } @@ -3839,7 +3839,7 @@ static int io_openat2(struct io_kiocb *req, bool force_nonblock) struct file *file; int ret; - if (force_nonblock) + if (force_nonblock && !req->open.ignore_nonblock) return -EAGAIN; ret = build_open_flags(&req->open.how, &op); @@ -3854,6 +3854,21 @@ static int io_openat2(struct io_kiocb *req, bool force_nonblock) if (IS_ERR(file)) { put_unused_fd(ret); ret = PTR_ERR(file); + /* + * A work-around to ensure that /proc/self works that way + * that it should - if we get -EOPNOTSUPP back, then assume + * that proc_self_get_link() failed us because we're in async + * context. We should be safe to retry this from the task + * itself with force_nonblock == false set, as it should not + * block on lookup. Would be nice to know this upfront and + * avoid the async dance, but doesn't seem feasible. + */ + if (ret == -EOPNOTSUPP && io_wq_current_is_worker()) { + req->open.ignore_nonblock = true; + refcount_inc(&req->refs); + io_req_task_queue(req); + return 0; + } } else { fsnotify_open(file); fd_install(ret, file); @@ -4484,7 +4499,8 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, return -EFAULT; if (clen < 0) return -EINVAL; - sr->len = iomsg->iov[0].iov_len; + sr->len = clen; + iomsg->iov[0].iov_len = clen; iomsg->iov = NULL; } else { ret = __import_iovec(READ, (struct iovec __user *)uiov, len, @@ -6958,9 +6974,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) return -ENXIO; spin_lock(&data->lock); - if (!list_empty(&data->ref_list)) - ref_node = list_first_entry(&data->ref_list, - struct fixed_file_ref_node, node); + ref_node = data->node; spin_unlock(&data->lock); if (ref_node) percpu_ref_kill(&ref_node->refs); @@ -7309,10 +7323,6 @@ static void __io_file_put_work(struct fixed_file_ref_node *ref_node) kfree(pfile); } - spin_lock(&file_data->lock); - list_del(&ref_node->node); - spin_unlock(&file_data->lock); - percpu_ref_exit(&ref_node->refs); kfree(ref_node); percpu_ref_put(&file_data->refs); @@ -7339,17 +7349,32 @@ static void io_file_put_work(struct work_struct *work) static void io_file_data_ref_zero(struct percpu_ref *ref) { struct fixed_file_ref_node *ref_node; + struct fixed_file_data *data; struct io_ring_ctx *ctx; - bool first_add; + bool first_add = false; int delay = HZ; ref_node = container_of(ref, struct fixed_file_ref_node, refs); - ctx = ref_node->file_data->ctx; + data = ref_node->file_data; + ctx = data->ctx; + + spin_lock(&data->lock); + ref_node->done = true; + + while (!list_empty(&data->ref_list)) { + ref_node = list_first_entry(&data->ref_list, + struct fixed_file_ref_node, node); + /* recycle ref nodes in order */ + if (!ref_node->done) + break; + list_del(&ref_node->node); + first_add |= llist_add(&ref_node->llist, &ctx->file_put_llist); + } + spin_unlock(&data->lock); - if (percpu_ref_is_dying(&ctx->file_data->refs)) + if (percpu_ref_is_dying(&data->refs)) delay = 0; - first_add = llist_add(&ref_node->llist, &ctx->file_put_llist); if (!delay) mod_delayed_work(system_wq, &ctx->file_put_work, 0); else if (first_add) @@ -7373,6 +7398,7 @@ static struct fixed_file_ref_node *alloc_fixed_file_ref_node( INIT_LIST_HEAD(&ref_node->node); INIT_LIST_HEAD(&ref_node->file_list); ref_node->file_data = ctx->file_data; + ref_node->done = false; return ref_node; } @@ -7468,7 +7494,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, file_data->node = ref_node; spin_lock(&file_data->lock); - list_add(&ref_node->node, &file_data->ref_list); + list_add_tail(&ref_node->node, &file_data->ref_list); spin_unlock(&file_data->lock); percpu_ref_get(&file_data->refs); return ret; @@ -7627,7 +7653,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (needs_switch) { percpu_ref_kill(&data->node->refs); spin_lock(&data->lock); - list_add(&ref_node->node, &data->ref_list); + list_add_tail(&ref_node->node, &data->ref_list); data->node = ref_node; spin_unlock(&data->lock); percpu_ref_get(&ctx->file_data->refs); @@ -9157,6 +9183,7 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx) { struct file *file; int ret; + int fd; #if defined(CONFIG_UNIX) ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP, @@ -9168,12 +9195,12 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx) ret = get_unused_fd_flags(O_RDWR | O_CLOEXEC); if (ret < 0) goto err; + fd = ret; file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx, O_RDWR | O_CLOEXEC); if (IS_ERR(file)) { -err_fd: - put_unused_fd(ret); + put_unused_fd(fd); ret = PTR_ERR(file); goto err; } @@ -9181,12 +9208,14 @@ err_fd: #if defined(CONFIG_UNIX) ctx->ring_sock->file = file; #endif - if (unlikely(io_uring_add_task_file(ctx, file))) { - file = ERR_PTR(-ENOMEM); - goto err_fd; + ret = io_uring_add_task_file(ctx, file); + if (ret) { + fput(file); + put_unused_fd(fd); + goto err; } - fd_install(ret, file); - return ret; + fd_install(fd, file); + return fd; err: #if defined(CONFIG_UNIX) sock_release(ctx->ring_sock); @@ -9226,7 +9255,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, * to a power-of-two, if it isn't already. We do NOT impose * any cq vs sq ring sizing. */ - if (p->cq_entries < p->sq_entries) + if (!p->cq_entries) return -EINVAL; if (p->cq_entries > IORING_MAX_CQ_ENTRIES) { if (!(p->flags & IORING_SETUP_CLAMP)) @@ -9234,6 +9263,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, p->cq_entries = IORING_MAX_CQ_ENTRIES; } p->cq_entries = roundup_pow_of_two(p->cq_entries); + if (p->cq_entries < p->sq_entries) + return -EINVAL; } else { p->cq_entries = 2 * p->sq_entries; } diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 263f02ad8ebf..472932b9e6bc 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -106,6 +106,8 @@ static int __try_to_free_cp_buf(struct journal_head *jh) * for a checkpoint to free up some space in the log. */ void __jbd2_log_wait_for_space(journal_t *journal) +__acquires(&journal->j_state_lock) +__releases(&journal->j_state_lock) { int nblocks, space_left; /* assert_spin_locked(&journal->j_state_lock); */ diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index fa688e163a80..b121d7d434c6 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -450,6 +450,15 @@ void jbd2_journal_commit_transaction(journal_t *journal) schedule(); write_lock(&journal->j_state_lock); finish_wait(&journal->j_fc_wait, &wait); + /* + * TODO: by blocking fast commits here, we are increasing + * fsync() latency slightly. Strictly speaking, we don't need + * to block fast commits until the transaction enters T_FLUSH + * state. So an optimization is possible where we block new fast + * commits here and wait for existing ones to complete + * just before we enter T_FLUSH. That way, the existing fast + * commits and this full commit can proceed parallely. + */ } write_unlock(&journal->j_state_lock); @@ -801,7 +810,7 @@ start_journal_io: if (first_block < journal->j_tail) freed += journal->j_last - journal->j_first; /* Update tail only if we free significant amount of space */ - if (freed < journal->j_maxlen / 4) + if (freed < jbd2_journal_get_max_txn_bufs(journal)) update_tail = 0; } J_ASSERT(commit_transaction->t_state == T_COMMIT); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 0c7c42bd530f..188f79d76988 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -566,12 +566,14 @@ static int __jbd2_journal_force_commit(journal_t *journal) } /** - * Force and wait upon a commit if the calling process is not within - * transaction. This is used for forcing out undo-protected data which contains - * bitmaps, when the fs is running out of space. + * jbd2_journal_force_commit_nested - Force and wait upon a commit if the + * calling process is not within transaction. * * @journal: journal to force * Returns true if progress was made. + * + * This is used for forcing out undo-protected data which contains + * bitmaps, when the fs is running out of space. */ int jbd2_journal_force_commit_nested(journal_t *journal) { @@ -582,7 +584,7 @@ int jbd2_journal_force_commit_nested(journal_t *journal) } /** - * int journal_force_commit() - force any uncommitted transactions + * jbd2_journal_force_commit() - force any uncommitted transactions * @journal: journal to force * * Caller want unconditional commit. We can only force the running transaction @@ -727,6 +729,8 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid) { + if (unlikely(is_journal_aborted(journal))) + return -EIO; /* * Fast commits only allowed if at least one full commit has * been processed. @@ -734,10 +738,12 @@ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid) if (!journal->j_stats.ts_tid) return -EINVAL; - if (tid <= journal->j_commit_sequence) + write_lock(&journal->j_state_lock); + if (tid <= journal->j_commit_sequence) { + write_unlock(&journal->j_state_lock); return -EALREADY; + } - write_lock(&journal->j_state_lock); if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING || (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) { DEFINE_WAIT(wait); @@ -777,13 +783,19 @@ static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback) int jbd2_fc_end_commit(journal_t *journal) { - return __jbd2_fc_end_commit(journal, 0, 0); + return __jbd2_fc_end_commit(journal, 0, false); } EXPORT_SYMBOL(jbd2_fc_end_commit); -int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid) +int jbd2_fc_end_commit_fallback(journal_t *journal) { - return __jbd2_fc_end_commit(journal, tid, 1); + tid_t tid; + + read_lock(&journal->j_state_lock); + tid = journal->j_running_transaction ? + journal->j_running_transaction->t_tid : 0; + read_unlock(&journal->j_state_lock); + return __jbd2_fc_end_commit(journal, tid, true); } EXPORT_SYMBOL(jbd2_fc_end_commit_fallback); @@ -865,7 +877,6 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out) int fc_off; *bh_out = NULL; - write_lock(&journal->j_state_lock); if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) { fc_off = journal->j_fc_off; @@ -874,7 +885,6 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out) } else { ret = -EINVAL; } - write_unlock(&journal->j_state_lock); if (ret) return ret; @@ -887,11 +897,7 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out) if (!bh) return -ENOMEM; - lock_buffer(bh); - clear_buffer_uptodate(bh); - set_buffer_dirty(bh); - unlock_buffer(bh); journal->j_fc_wbuf[fc_off] = bh; *bh_out = bh; @@ -909,9 +915,7 @@ int jbd2_fc_wait_bufs(journal_t *journal, int num_blks) struct buffer_head *bh; int i, j_fc_off; - read_lock(&journal->j_state_lock); j_fc_off = journal->j_fc_off; - read_unlock(&journal->j_state_lock); /* * Wait in reverse order to minimize chances of us being woken up before @@ -939,9 +943,7 @@ int jbd2_fc_release_bufs(journal_t *journal) struct buffer_head *bh; int i, j_fc_off; - read_lock(&journal->j_state_lock); j_fc_off = journal->j_fc_off; - read_unlock(&journal->j_state_lock); /* * Wait in reverse order to minimize chances of us being woken up before @@ -1348,23 +1350,16 @@ static journal_t *journal_init_common(struct block_device *bdev, journal->j_dev = bdev; journal->j_fs_dev = fs_dev; journal->j_blk_offset = start; - journal->j_maxlen = len; + journal->j_total_len = len; /* We need enough buffers to write out full descriptor block. */ n = journal->j_blocksize / jbd2_min_tag_size(); journal->j_wbufsize = n; + journal->j_fc_wbuf = NULL; journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *), GFP_KERNEL); if (!journal->j_wbuf) goto err_cleanup; - if (journal->j_fc_wbufsize > 0) { - journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize, - sizeof(struct buffer_head *), - GFP_KERNEL); - if (!journal->j_fc_wbuf) - goto err_cleanup; - } - bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize); if (!bh) { pr_err("%s: Cannot get buffer for journal superblock\n", @@ -1378,23 +1373,11 @@ static journal_t *journal_init_common(struct block_device *bdev, err_cleanup: kfree(journal->j_wbuf); - kfree(journal->j_fc_wbuf); jbd2_journal_destroy_revoke(journal); kfree(journal); return NULL; } -int jbd2_fc_init(journal_t *journal, int num_fc_blks) -{ - journal->j_fc_wbufsize = num_fc_blks; - journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize, - sizeof(struct buffer_head *), GFP_KERNEL); - if (!journal->j_fc_wbuf) - return -ENOMEM; - return 0; -} -EXPORT_SYMBOL(jbd2_fc_init); - /* jbd2_journal_init_dev and jbd2_journal_init_inode: * * Create a journal structure assigned some fixed set of disk blocks to @@ -1512,16 +1495,7 @@ static int journal_reset(journal_t *journal) } journal->j_first = first; - - if (jbd2_has_feature_fast_commit(journal) && - journal->j_fc_wbufsize > 0) { - journal->j_fc_last = last; - journal->j_last = last - journal->j_fc_wbufsize; - journal->j_fc_first = journal->j_last + 1; - journal->j_fc_off = 0; - } else { - journal->j_last = last; - } + journal->j_last = last; journal->j_head = journal->j_first; journal->j_tail = journal->j_first; @@ -1531,7 +1505,14 @@ static int journal_reset(journal_t *journal) journal->j_commit_sequence = journal->j_transaction_sequence - 1; journal->j_commit_request = journal->j_commit_sequence; - journal->j_max_transaction_buffers = journal->j_maxlen / 4; + journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal); + + /* + * Now that journal recovery is done, turn fast commits off here. This + * way, if fast commit was enabled before the crash but if now FS has + * disabled it, we don't enable fast commits. + */ + jbd2_clear_feature_fast_commit(journal); /* * As a special case, if the on-disk copy is already marked as needing @@ -1792,15 +1773,15 @@ static int journal_get_superblock(journal_t *journal) goto out; } - if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen) - journal->j_maxlen = be32_to_cpu(sb->s_maxlen); - else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) { + if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len) + journal->j_total_len = be32_to_cpu(sb->s_maxlen); + else if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) { printk(KERN_WARNING "JBD2: journal file too short\n"); goto out; } if (be32_to_cpu(sb->s_first) == 0 || - be32_to_cpu(sb->s_first) >= journal->j_maxlen) { + be32_to_cpu(sb->s_first) >= journal->j_total_len) { printk(KERN_WARNING "JBD2: Invalid start block of journal: %u\n", be32_to_cpu(sb->s_first)); @@ -1872,6 +1853,7 @@ static int load_superblock(journal_t *journal) { int err; journal_superblock_t *sb; + int num_fc_blocks; err = journal_get_superblock(journal); if (err) @@ -1883,15 +1865,17 @@ static int load_superblock(journal_t *journal) journal->j_tail = be32_to_cpu(sb->s_start); journal->j_first = be32_to_cpu(sb->s_first); journal->j_errno = be32_to_cpu(sb->s_errno); + journal->j_last = be32_to_cpu(sb->s_maxlen); - if (jbd2_has_feature_fast_commit(journal) && - journal->j_fc_wbufsize > 0) { + if (jbd2_has_feature_fast_commit(journal)) { journal->j_fc_last = be32_to_cpu(sb->s_maxlen); - journal->j_last = journal->j_fc_last - journal->j_fc_wbufsize; + num_fc_blocks = be32_to_cpu(sb->s_num_fc_blks); + if (!num_fc_blocks) + num_fc_blocks = JBD2_MIN_FC_BLOCKS; + if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS) + journal->j_last = journal->j_fc_last - num_fc_blocks; journal->j_fc_first = journal->j_last + 1; journal->j_fc_off = 0; - } else { - journal->j_last = be32_to_cpu(sb->s_maxlen); } return 0; @@ -1899,7 +1883,7 @@ static int load_superblock(journal_t *journal) /** - * int jbd2_journal_load() - Read journal from disk. + * jbd2_journal_load() - Read journal from disk. * @journal: Journal to act on. * * Given a journal_t structure which tells us which disk blocks contain @@ -1954,9 +1938,6 @@ int jbd2_journal_load(journal_t *journal) */ journal->j_flags &= ~JBD2_ABORT; - if (journal->j_fc_wbufsize > 0) - jbd2_journal_set_features(journal, 0, 0, - JBD2_FEATURE_INCOMPAT_FAST_COMMIT); /* OK, we've finished with the dynamic journal bits: * reinitialise the dynamic contents of the superblock in memory * and reset them on disk. */ @@ -1972,7 +1953,7 @@ recovery_error: } /** - * void jbd2_journal_destroy() - Release a journal_t structure. + * jbd2_journal_destroy() - Release a journal_t structure. * @journal: Journal to act on. * * Release a journal_t structure once it is no longer in use by the @@ -2040,8 +2021,7 @@ int jbd2_journal_destroy(journal_t *journal) jbd2_journal_destroy_revoke(journal); if (journal->j_chksum_driver) crypto_free_shash(journal->j_chksum_driver); - if (journal->j_fc_wbufsize > 0) - kfree(journal->j_fc_wbuf); + kfree(journal->j_fc_wbuf); kfree(journal->j_wbuf); kfree(journal); @@ -2050,7 +2030,7 @@ int jbd2_journal_destroy(journal_t *journal) /** - *int jbd2_journal_check_used_features() - Check if features specified are used. + * jbd2_journal_check_used_features() - Check if features specified are used. * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -2085,7 +2065,7 @@ int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat, } /** - * int jbd2_journal_check_available_features() - Check feature set in journalling layer + * jbd2_journal_check_available_features() - Check feature set in journalling layer * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -2116,8 +2096,39 @@ int jbd2_journal_check_available_features(journal_t *journal, unsigned long comp return 0; } +static int +jbd2_journal_initialize_fast_commit(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; + unsigned long long num_fc_blks; + + num_fc_blks = be32_to_cpu(sb->s_num_fc_blks); + if (num_fc_blks == 0) + num_fc_blks = JBD2_MIN_FC_BLOCKS; + if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS) + return -ENOSPC; + + /* Are we called twice? */ + WARN_ON(journal->j_fc_wbuf != NULL); + journal->j_fc_wbuf = kmalloc_array(num_fc_blks, + sizeof(struct buffer_head *), GFP_KERNEL); + if (!journal->j_fc_wbuf) + return -ENOMEM; + + journal->j_fc_wbufsize = num_fc_blks; + journal->j_fc_last = journal->j_last; + journal->j_last = journal->j_fc_last - num_fc_blks; + journal->j_fc_first = journal->j_last + 1; + journal->j_fc_off = 0; + journal->j_free = journal->j_last - journal->j_first; + journal->j_max_transaction_buffers = + jbd2_journal_get_max_txn_bufs(journal); + + return 0; +} + /** - * int jbd2_journal_set_features() - Mark a given journal feature in the superblock + * jbd2_journal_set_features() - Mark a given journal feature in the superblock * @journal: Journal to act on. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -2159,6 +2170,13 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, sb = journal->j_superblock; + if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) { + if (jbd2_journal_initialize_fast_commit(journal)) { + pr_err("JBD2: Cannot enable fast commits.\n"); + return 0; + } + } + /* Load the checksum driver if necessary */ if ((journal->j_chksum_driver == NULL) && INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { @@ -2201,7 +2219,7 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, } /* - * jbd2_journal_clear_features () - Clear a given journal feature in the + * jbd2_journal_clear_features() - Clear a given journal feature in the * superblock * @journal: Journal to act on. * @compat: bitmask of compatible features @@ -2230,7 +2248,7 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat, EXPORT_SYMBOL(jbd2_journal_clear_features); /** - * int jbd2_journal_flush () - Flush journal + * jbd2_journal_flush() - Flush journal * @journal: Journal to act on. * * Flush all data for a given journal to disk and empty the journal. @@ -2305,7 +2323,7 @@ out: } /** - * int jbd2_journal_wipe() - Wipe journal contents + * jbd2_journal_wipe() - Wipe journal contents * @journal: Journal to act on. * @write: flag (see below) * @@ -2346,7 +2364,7 @@ int jbd2_journal_wipe(journal_t *journal, int write) } /** - * void jbd2_journal_abort () - Shutdown the journal immediately. + * jbd2_journal_abort () - Shutdown the journal immediately. * @journal: the journal to shutdown. * @errno: an error number to record in the journal indicating * the reason for the shutdown. @@ -2437,7 +2455,7 @@ void jbd2_journal_abort(journal_t *journal, int errno) } /** - * int jbd2_journal_errno () - returns the journal's error state. + * jbd2_journal_errno() - returns the journal's error state. * @journal: journal to examine. * * This is the errno number set with jbd2_journal_abort(), the last @@ -2461,7 +2479,7 @@ int jbd2_journal_errno(journal_t *journal) } /** - * int jbd2_journal_clear_err () - clears the journal's error state + * jbd2_journal_clear_err() - clears the journal's error state * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly @@ -2481,7 +2499,7 @@ int jbd2_journal_clear_err(journal_t *journal) } /** - * void jbd2_journal_ack_err() - Ack journal err. + * jbd2_journal_ack_err() - Ack journal err. * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index eb2606133cd8..dc0694fcfcd1 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -74,8 +74,8 @@ static int do_readahead(journal_t *journal, unsigned int start) /* Do up to 128K of readahead */ max = start + (128 * 1024 / journal->j_blocksize); - if (max > journal->j_maxlen) - max = journal->j_maxlen; + if (max > journal->j_total_len) + max = journal->j_total_len; /* Do the readahead itself. We'll submit MAXBUF buffer_heads at * a time to the block device IO layer. */ @@ -134,7 +134,7 @@ static int jread(struct buffer_head **bhp, journal_t *journal, *bhp = NULL; - if (offset >= journal->j_maxlen) { + if (offset >= journal->j_total_len) { printk(KERN_ERR "JBD2: corrupted journal superblock\n"); return -EFSCORRUPTED; } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 43985738aa86..9396666b7314 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -195,8 +195,10 @@ static void wait_transaction_switching(journal_t *journal) DEFINE_WAIT(wait); if (WARN_ON(!journal->j_running_transaction || - journal->j_running_transaction->t_state != T_SWITCH)) + journal->j_running_transaction->t_state != T_SWITCH)) { + read_unlock(&journal->j_state_lock); return; + } prepare_to_wait(&journal->j_wait_transaction_locked, &wait, TASK_UNINTERRUPTIBLE); read_unlock(&journal->j_state_lock); @@ -517,7 +519,7 @@ EXPORT_SYMBOL(jbd2__journal_start); /** - * handle_t *jbd2_journal_start() - Obtain a new handle. + * jbd2_journal_start() - Obtain a new handle. * @journal: Journal to start transaction on. * @nblocks: number of block buffer we might modify * @@ -564,7 +566,7 @@ void jbd2_journal_free_reserved(handle_t *handle) EXPORT_SYMBOL(jbd2_journal_free_reserved); /** - * int jbd2_journal_start_reserved() - start reserved handle + * jbd2_journal_start_reserved() - start reserved handle * @handle: handle to start * @type: for handle statistics * @line_no: for handle statistics @@ -618,7 +620,7 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, EXPORT_SYMBOL(jbd2_journal_start_reserved); /** - * int jbd2_journal_extend() - extend buffer credits. + * jbd2_journal_extend() - extend buffer credits. * @handle: handle to 'extend' * @nblocks: nr blocks to try to extend by. * @revoke_records: number of revoke records to try to extend by. @@ -743,7 +745,7 @@ static void stop_this_handle(handle_t *handle) } /** - * int jbd2_journal_restart() - restart a handle . + * jbd2__journal_restart() - restart a handle . * @handle: handle to restart * @nblocks: nr credits requested * @revoke_records: number of revoke record credits requested @@ -813,7 +815,7 @@ int jbd2_journal_restart(handle_t *handle, int nblocks) EXPORT_SYMBOL(jbd2_journal_restart); /** - * void jbd2_journal_lock_updates () - establish a transaction barrier. + * jbd2_journal_lock_updates () - establish a transaction barrier. * @journal: Journal to establish a barrier on. * * This locks out any further updates from being started, and blocks @@ -872,7 +874,7 @@ void jbd2_journal_lock_updates(journal_t *journal) } /** - * void jbd2_journal_unlock_updates (journal_t* journal) - release barrier + * jbd2_journal_unlock_updates () - release barrier * @journal: Journal to release the barrier on. * * Release a transaction barrier obtained with jbd2_journal_lock_updates(). @@ -1180,7 +1182,8 @@ out: } /** - * int jbd2_journal_get_write_access() - notify intent to modify a buffer for metadata (not data) update. + * jbd2_journal_get_write_access() - notify intent to modify a buffer + * for metadata (not data) update. * @handle: transaction to add buffer modifications to * @bh: bh to be used for metadata writes * @@ -1224,7 +1227,7 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) * unlocked buffer beforehand. */ /** - * int jbd2_journal_get_create_access () - notify intent to use newly created bh + * jbd2_journal_get_create_access () - notify intent to use newly created bh * @handle: transaction to new buffer to * @bh: new buffer. * @@ -1304,7 +1307,7 @@ out: } /** - * int jbd2_journal_get_undo_access() - Notify intent to modify metadata with + * jbd2_journal_get_undo_access() - Notify intent to modify metadata with * non-rewindable consequences * @handle: transaction * @bh: buffer to undo @@ -1381,7 +1384,7 @@ out: } /** - * void jbd2_journal_set_triggers() - Add triggers for commit writeout + * jbd2_journal_set_triggers() - Add triggers for commit writeout * @bh: buffer to trigger on * @type: struct jbd2_buffer_trigger_type containing the trigger(s). * @@ -1423,7 +1426,7 @@ void jbd2_buffer_abort_trigger(struct journal_head *jh, } /** - * int jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata + * jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata * @handle: transaction to add buffer to. * @bh: buffer to mark * @@ -1591,7 +1594,7 @@ out: } /** - * void jbd2_journal_forget() - bforget() for potentially-journaled buffers. + * jbd2_journal_forget() - bforget() for potentially-journaled buffers. * @handle: transaction handle * @bh: bh to 'forget' * @@ -1760,7 +1763,7 @@ drop: } /** - * int jbd2_journal_stop() - complete a transaction + * jbd2_journal_stop() - complete a transaction * @handle: transaction to complete. * * All done for a particular handle. @@ -2078,7 +2081,7 @@ out: } /** - * int jbd2_journal_try_to_free_buffers() - try to free page buffers. + * jbd2_journal_try_to_free_buffers() - try to free page buffers. * @journal: journal for operation * @page: to try and free * @@ -2409,7 +2412,7 @@ zap_buffer_unlocked: } /** - * void jbd2_journal_invalidatepage() + * jbd2_journal_invalidatepage() * @journal: journal to use for flush... * @page: page to flush * @offset: start of the range to invalidate diff --git a/fs/libfs.c b/fs/libfs.c index fc34361c1489..7124c2e8df2f 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -959,7 +959,7 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { struct simple_attr *attr; - u64 val; + unsigned long long val; size_t size; ssize_t ret; @@ -977,7 +977,9 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, goto out; attr->set_buf[size] = '\0'; - val = simple_strtoll(attr->set_buf, NULL, 0); + ret = kstrtoull(attr->set_buf, 0, &val); + if (ret) + goto out; ret = attr->set(attr->data, val); if (ret == 0) ret = len; /* on success, claim we got the whole input */ diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 88e1763e02f3..e2a488d403a6 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -205,3 +205,12 @@ config NFS_DISABLE_UDP_SUPPORT Choose Y here to disable the use of NFS over UDP. NFS over UDP on modern networks (1Gb+) can lead to data corruption caused by fragmentation during high loads. + +config NFS_V4_2_READ_PLUS + bool "NFS: Enable support for the NFSv4.2 READ_PLUS operation" + depends on NFS_V4_2 + default n + help + This is intended for developers only. The READ_PLUS operation has + been shown to have issues under specific conditions and should not + be used in production. diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index cb52db9a0cfb..4e011adaf967 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -955,7 +955,6 @@ out: static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) { - struct inode *inode = file_inode(filp); struct nfs_open_dir_context *dir_ctx = filp->private_data; dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n", @@ -967,15 +966,15 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) case SEEK_SET: if (offset < 0) return -EINVAL; - inode_lock(inode); + spin_lock(&filp->f_lock); break; case SEEK_CUR: if (offset == 0) return filp->f_pos; - inode_lock(inode); + spin_lock(&filp->f_lock); offset += filp->f_pos; if (offset < 0) { - inode_unlock(inode); + spin_unlock(&filp->f_lock); return -EINVAL; } } @@ -987,7 +986,7 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) dir_ctx->dir_cookie = 0; dir_ctx->duped = 0; } - inode_unlock(inode); + spin_unlock(&filp->f_lock); return offset; } @@ -998,13 +997,9 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end, int datasync) { - struct inode *inode = file_inode(filp); - dfprintk(FILE, "NFS: fsync dir(%pD2) datasync %d\n", filp, datasync); - inode_lock(inode); - nfs_inc_stats(inode, NFSIOS_VFSFSYNC); - inode_unlock(inode); + nfs_inc_stats(file_inode(filp), NFSIOS_VFSFSYNC); return 0; } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index a163533446fa..24bf5797f88a 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -838,7 +838,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_pgio_mirror *pgm; struct nfs4_ff_layout_mirror *mirror; struct nfs4_pnfs_ds *ds; - u32 ds_idx, i; + u32 ds_idx; retry: ff_layout_pg_check_layout(pgio, req); @@ -864,11 +864,9 @@ retry: goto retry; } - for (i = 0; i < pgio->pg_mirror_count; i++) { - mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); - pgm = &pgio->pg_mirrors[i]; - pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; - } + mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx); + pgm = &pgio->pg_mirrors[0]; + pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; pgio->pg_mirror_idx = ds_idx; @@ -985,6 +983,21 @@ out: return 1; } +static u32 +ff_layout_pg_set_mirror_write(struct nfs_pageio_descriptor *desc, u32 idx) +{ + u32 old = desc->pg_mirror_idx; + + desc->pg_mirror_idx = idx; + return old; +} + +static struct nfs_pgio_mirror * +ff_layout_pg_get_mirror_write(struct nfs_pageio_descriptor *desc, u32 idx) +{ + return &desc->pg_mirrors[idx]; +} + static const struct nfs_pageio_ops ff_layout_pg_read_ops = { .pg_init = ff_layout_pg_init_read, .pg_test = pnfs_generic_pg_test, @@ -998,6 +1011,8 @@ static const struct nfs_pageio_ops ff_layout_pg_write_ops = { .pg_doio = pnfs_generic_pg_writepages, .pg_get_mirror_count = ff_layout_pg_get_mirror_count_write, .pg_cleanup = pnfs_generic_pg_cleanup, + .pg_get_mirror = ff_layout_pg_get_mirror_write, + .pg_set_mirror = ff_layout_pg_set_mirror_write, }; static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 2b2211d1234e..4fc61e3d098d 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -1241,12 +1241,13 @@ static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf, .rpc_resp = &res, }; u32 xdrlen; - int ret, np; + int ret, np, i; + ret = -ENOMEM; res.scratch = alloc_page(GFP_KERNEL); if (!res.scratch) - return -ENOMEM; + goto out; xdrlen = nfs42_listxattr_xdrsize(buflen); if (xdrlen > server->lxasize) @@ -1254,9 +1255,12 @@ static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf, np = xdrlen / PAGE_SIZE + 1; pages = kcalloc(np, sizeof(struct page *), GFP_KERNEL); - if (pages == NULL) { - __free_page(res.scratch); - return -ENOMEM; + if (!pages) + goto out_free_scratch; + for (i = 0; i < np; i++) { + pages[i] = alloc_page(GFP_KERNEL); + if (!pages[i]) + goto out_free_pages; } arg.xattr_pages = pages; @@ -1271,14 +1275,15 @@ static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf, *eofp = res.eof; } +out_free_pages: while (--np >= 0) { if (pages[np]) __free_page(pages[np]); } - - __free_page(res.scratch); kfree(pages); - +out_free_scratch: + __free_page(res.scratch); +out: return ret; } diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index b51424ff8159..6c2ce799150f 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -1047,8 +1047,10 @@ out4: void nfs4_xattr_cache_exit(void) { + unregister_shrinker(&nfs4_xattr_large_entry_shrinker); unregister_shrinker(&nfs4_xattr_entry_shrinker); unregister_shrinker(&nfs4_xattr_cache_shrinker); + list_lru_destroy(&nfs4_xattr_large_entry_lru); list_lru_destroy(&nfs4_xattr_entry_lru); list_lru_destroy(&nfs4_xattr_cache_lru); kmem_cache_destroy(nfs4_xattr_cache_cachep); diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 0dc31ad2362e..8432bd6b95f0 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -196,7 +196,7 @@ 1 + nfs4_xattr_name_maxsz + 1) #define decode_setxattr_maxsz (op_decode_hdr_maxsz + decode_change_info_maxsz) #define encode_listxattrs_maxsz (op_encode_hdr_maxsz + 2 + 1) -#define decode_listxattrs_maxsz (op_decode_hdr_maxsz + 2 + 1 + 1) +#define decode_listxattrs_maxsz (op_decode_hdr_maxsz + 2 + 1 + 1 + 1) #define encode_removexattr_maxsz (op_encode_hdr_maxsz + 1 + \ nfs4_xattr_name_maxsz) #define decode_removexattr_maxsz (op_decode_hdr_maxsz + \ @@ -531,7 +531,7 @@ static void encode_listxattrs(struct xdr_stream *xdr, { __be32 *p; - encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz + 1, hdr); + encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz, hdr); p = reserve_space(xdr, 12); if (unlikely(!p)) @@ -1528,7 +1528,6 @@ static void nfs4_xdr_enc_listxattrs(struct rpc_rqst *req, rpc_prepare_reply_pages(req, args->xattr_pages, 0, args->count, hdr.replen); - req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES; encode_nops(&hdr); } diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 9d354de613da..57b3821d975a 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -377,10 +377,10 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, goto out_stateowner; set_bit(NFS_SRV_SSC_COPY_STATE, &ctx->state->flags); - set_bit(NFS_OPEN_STATE, &ctx->state->flags); memcpy(&ctx->state->open_stateid.other, &stateid->other, NFS4_STATEID_OTHER_SIZE); update_open_stateid(ctx->state, stateid, NULL, filep->f_mode); + set_bit(NFS_OPEN_STATE, &ctx->state->flags); nfs_file_set_open_context(filep, ctx); put_nfs_open_context(ctx); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 9e0ca9b2b210..e89468678ae1 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5309,7 +5309,7 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) nfs4_read_done_cb(task, hdr); } -#ifdef CONFIG_NFS_V4_2 +#if defined CONFIG_NFS_V4_2 && defined CONFIG_NFS_V4_2_READ_PLUS static void nfs42_read_plus_support(struct nfs_server *server, struct rpc_message *msg) { if (server->caps & NFS_CAP_READ_PLUS) diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index 8d3278805602..fa148308822c 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -88,7 +88,13 @@ #define NFS_ROOT "/tftpboot/%s" /* Default NFSROOT mount options. */ +#if defined(CONFIG_NFS_V2) #define NFS_DEF_OPTIONS "vers=2,tcp,rsize=4096,wsize=4096" +#elif defined(CONFIG_NFS_V3) +#define NFS_DEF_OPTIONS "vers=3,tcp,rsize=4096,wsize=4096" +#else +#define NFS_DEF_OPTIONS "vers=4,tcp,rsize=4096,wsize=4096" +#endif /* Parameters passed from the kernel command line */ static char nfs_root_parms[NFS_MAXPATHLEN + 1] __initdata = ""; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 6985cacf4700..78c9c4bdef2b 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -31,13 +31,29 @@ static struct kmem_cache *nfs_page_cachep; static const struct rpc_call_ops nfs_pgio_common_ops; +static struct nfs_pgio_mirror * +nfs_pgio_get_mirror(struct nfs_pageio_descriptor *desc, u32 idx) +{ + if (desc->pg_ops->pg_get_mirror) + return desc->pg_ops->pg_get_mirror(desc, idx); + return &desc->pg_mirrors[0]; +} + struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc) { - return &desc->pg_mirrors[desc->pg_mirror_idx]; + return nfs_pgio_get_mirror(desc, desc->pg_mirror_idx); } EXPORT_SYMBOL_GPL(nfs_pgio_current_mirror); +static u32 +nfs_pgio_set_current_mirror(struct nfs_pageio_descriptor *desc, u32 idx) +{ + if (desc->pg_ops->pg_set_mirror) + return desc->pg_ops->pg_set_mirror(desc, idx); + return desc->pg_mirror_idx; +} + void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)) @@ -1259,7 +1275,7 @@ static void nfs_pageio_error_cleanup(struct nfs_pageio_descriptor *desc) return; for (midx = 0; midx < desc->pg_mirror_count; midx++) { - mirror = &desc->pg_mirrors[midx]; + mirror = nfs_pgio_get_mirror(desc, midx); desc->pg_completion_ops->error_cleanup(&mirror->pg_list, desc->pg_error); } @@ -1293,12 +1309,12 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, goto out_failed; } - desc->pg_mirror_idx = midx; + nfs_pgio_set_current_mirror(desc, midx); if (!nfs_pageio_add_request_mirror(desc, dupreq)) goto out_cleanup_subreq; } - desc->pg_mirror_idx = 0; + nfs_pgio_set_current_mirror(desc, 0); if (!nfs_pageio_add_request_mirror(desc, req)) goto out_failed; @@ -1320,10 +1336,12 @@ out_failed: static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, u32 mirror_idx) { - struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[mirror_idx]; - u32 restore_idx = desc->pg_mirror_idx; + struct nfs_pgio_mirror *mirror; + u32 restore_idx; + + restore_idx = nfs_pgio_set_current_mirror(desc, mirror_idx); + mirror = nfs_pgio_current_mirror(desc); - desc->pg_mirror_idx = mirror_idx; for (;;) { nfs_pageio_doio(desc); if (desc->pg_error < 0 || !mirror->pg_recoalesce) @@ -1331,7 +1349,7 @@ static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, if (!nfs_do_recoalesce(desc)) break; } - desc->pg_mirror_idx = restore_idx; + nfs_pgio_set_current_mirror(desc, restore_idx); } /* @@ -1405,7 +1423,7 @@ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index) u32 midx; for (midx = 0; midx < desc->pg_mirror_count; midx++) { - mirror = &desc->pg_mirrors[midx]; + mirror = nfs_pgio_get_mirror(desc, midx); if (!list_empty(&mirror->pg_list)) { prev = nfs_list_entry(mirror->pg_list.prev); if (index != prev->wb_index + 1) { diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 14468613d150..a633044b0dc1 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -316,10 +316,6 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) fh_copy(&resp->dirfh, &argp->fh); fh_init(&resp->fh, NFS3_FHSIZE); - if (argp->ftype == 0 || argp->ftype >= NF3BAD) { - resp->status = nfserr_inval; - goto out; - } if (argp->ftype == NF3CHR || argp->ftype == NF3BLK) { rdev = MKDEV(argp->major, argp->minor); if (MAJOR(rdev) != argp->major || @@ -328,7 +324,7 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) goto out; } } else if (argp->ftype != NF3SOCK && argp->ftype != NF3FIFO) { - resp->status = nfserr_inval; + resp->status = nfserr_badtype; goto out; } diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 9c23b6acf234..2277f83da250 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -1114,6 +1114,7 @@ nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p) { struct nfsd3_pathconfres *resp = rqstp->rq_resp; + *p++ = resp->status; *p++ = xdr_zero; /* no post_op_attr */ if (resp->status == 0) { diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ad2fa1a8e7ad..e83b21778816 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1299,7 +1299,7 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, struct nfsd_file *dst) { nfs42_ssc_close(src->nf_file); - nfsd_file_put(src); + /* 'src' is freed by nfsd4_do_async_copy */ nfsd_file_put(dst); mntput(ss_mnt); } @@ -1486,6 +1486,7 @@ do_callback: cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); if (!cb_copy) goto out; + refcount_set(&cb_copy->refcount, 1); memcpy(&cb_copy->cp_res, ©->cp_res, sizeof(copy->cp_res)); cb_copy->cp_clp = copy->cp_clp; cb_copy->nfserr = copy->nfserr; diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index a960ec3a569a..8d3ad5ef2925 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -178,6 +178,7 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, struct inode *inode = d_inode(dentry); struct dentry *parent; bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED; + bool parent_needed, parent_interested; __u32 p_mask; struct inode *p_inode = NULL; struct name_snapshot name; @@ -193,7 +194,8 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, return 0; parent = NULL; - if (!parent_watched && !fsnotify_event_needs_parent(inode, mnt, mask)) + parent_needed = fsnotify_event_needs_parent(inode, mnt, mask); + if (!parent_watched && !parent_needed) goto notify; /* Does parent inode care about events on children? */ @@ -205,17 +207,17 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, /* * Include parent/name in notification either if some notification - * groups require parent info (!parent_watched case) or the parent is - * interested in this event. + * groups require parent info or the parent is interested in this event. */ - if (!parent_watched || (mask & p_mask & ALL_FSNOTIFY_EVENTS)) { + parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS; + if (parent_needed || parent_interested) { /* When notifying parent, child should be passed as data */ WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type)); /* Notify both parent and child with child name info */ take_dentry_name_snapshot(&name, dentry); file_name = &name.name; - if (parent_watched) + if (parent_interested) mask |= FS_EVENT_ON_CHILD; } diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index b9a9d69dde7e..db52e843002a 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -877,7 +877,7 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty) goto done; } - trace_ocfs2_journal_init_maxlen(j_journal->j_maxlen); + trace_ocfs2_journal_init_maxlen(j_journal->j_total_len); *dirty = (le32_to_cpu(di->id1.journal1.ij_flags) & OCFS2_JOURNAL_DIRTY_FL); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 1d91dd1e8711..2febc76e9de7 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1713,6 +1713,7 @@ static void ocfs2_inode_init_once(void *data) oi->ip_blkno = 0ULL; oi->ip_clusters = 0; + oi->ip_next_orphan = NULL; ocfs2_resv_init_once(&oi->ip_la_data_resv); diff --git a/fs/proc/self.c b/fs/proc/self.c index 72cd69bcaf4a..cc71ce3466dc 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -16,6 +16,13 @@ static const char *proc_self_get_link(struct dentry *dentry, pid_t tgid = task_tgid_nr_ns(current, ns); char *name; + /* + * Not currently supported. Once we can inherit all of struct pid, + * we can allow this. + */ + if (current->flags & PF_KTHREAD) + return ERR_PTR(-EOPNOTSUPP); + if (!tgid) return ERR_PTR(-ENOENT); /* max length of unsigned int in decimal + NULL term */ diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 217aa2705d5d..ee5a235b3056 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1599,11 +1599,15 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, src = *ppos; svpfn = src / PM_ENTRY_BYTES; - start_vaddr = svpfn << PAGE_SHIFT; end_vaddr = mm->task_size; /* watch out for wraparound */ - if (svpfn > mm->task_size >> PAGE_SHIFT) + start_vaddr = end_vaddr; + if (svpfn <= (ULONG_MAX >> PAGE_SHIFT)) + start_vaddr = untagged_addr(svpfn << PAGE_SHIFT); + + /* Ensure the address is inside the task */ + if (start_vaddr > mm->task_size) start_vaddr = end_vaddr; /* diff --git a/fs/seq_file.c b/fs/seq_file.c index 3b20e21604e7..03a369ccd28c 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -168,12 +168,14 @@ EXPORT_SYMBOL(seq_read); ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct seq_file *m = iocb->ki_filp->private_data; - size_t size = iov_iter_count(iter); size_t copied = 0; size_t n; void *p; int err = 0; + if (!iov_iter_count(iter)) + return 0; + mutex_lock(&m->lock); /* @@ -206,36 +208,34 @@ ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter) if (!m->buf) goto Enomem; } - /* if not empty - flush it first */ + // something left in the buffer - copy it out first if (m->count) { - n = min(m->count, size); - if (copy_to_iter(m->buf + m->from, n, iter) != n) - goto Efault; + n = copy_to_iter(m->buf + m->from, m->count, iter); m->count -= n; m->from += n; - size -= n; copied += n; - if (!size) + if (m->count) // hadn't managed to copy everything goto Done; } - /* we need at least one record in buffer */ + // get a non-empty record in the buffer m->from = 0; p = m->op->start(m, &m->index); while (1) { err = PTR_ERR(p); - if (!p || IS_ERR(p)) + if (!p || IS_ERR(p)) // EOF or an error break; err = m->op->show(m, p); - if (err < 0) + if (err < 0) // hard error break; - if (unlikely(err)) + if (unlikely(err)) // ->show() says "skip it" m->count = 0; - if (unlikely(!m->count)) { + if (unlikely(!m->count)) { // empty record p = m->op->next(m, p, &m->index); continue; } - if (m->count < m->size) + if (!seq_has_overflowed(m)) // got it goto Fill; + // need a bigger buffer m->op->stop(m, p); kvfree(m->buf); m->count = 0; @@ -244,11 +244,14 @@ ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter) goto Enomem; p = m->op->start(m, &m->index); } + // EOF or an error m->op->stop(m, p); m->count = 0; goto Done; Fill: - /* they want more? let's try to get some more */ + // one non-empty record is in the buffer; if they want more, + // try to fit more in, but in any case we need to advance + // the iterator once for every record shown. while (1) { size_t offs = m->count; loff_t pos = m->index; @@ -259,30 +262,27 @@ Fill: m->op->next); m->index++; } - if (!p || IS_ERR(p)) { - err = PTR_ERR(p); + if (!p || IS_ERR(p)) // no next record for us break; - } - if (m->count >= size) + if (m->count >= iov_iter_count(iter)) break; err = m->op->show(m, p); - if (seq_has_overflowed(m) || err) { + if (err > 0) { // ->show() says "skip it" m->count = offs; - if (likely(err <= 0)) - break; + } else if (err || seq_has_overflowed(m)) { + m->count = offs; + break; } } m->op->stop(m, p); - n = min(m->count, size); - if (copy_to_iter(m->buf, n, iter) != n) - goto Efault; + n = copy_to_iter(m->buf, m->count, iter); copied += n; m->count -= n; m->from = n; Done: - if (!copied) - copied = err; - else { + if (unlikely(!copied)) { + copied = m->count ? -EFAULT : err; + } else { iocb->ki_pos += copied; m->read_pos += copied; } @@ -291,9 +291,6 @@ Done: Enomem: err = -ENOMEM; goto Done; -Efault: - err = -EFAULT; - goto Done; } EXPORT_SYMBOL(seq_read_iter); diff --git a/fs/super.c b/fs/super.c index a51c2083cd6b..98bb0629ee10 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1631,55 +1631,6 @@ int super_setup_bdi(struct super_block *sb) } EXPORT_SYMBOL(super_setup_bdi); -/* - * This is an internal function, please use sb_end_{write,pagefault,intwrite} - * instead. - */ -void __sb_end_write(struct super_block *sb, int level) -{ - percpu_up_read(sb->s_writers.rw_sem + level-1); -} -EXPORT_SYMBOL(__sb_end_write); - -/* - * This is an internal function, please use sb_start_{write,pagefault,intwrite} - * instead. - */ -int __sb_start_write(struct super_block *sb, int level, bool wait) -{ - bool force_trylock = false; - int ret = 1; - -#ifdef CONFIG_LOCKDEP - /* - * We want lockdep to tell us about possible deadlocks with freezing - * but it's it bit tricky to properly instrument it. Getting a freeze - * protection works as getting a read lock but there are subtle - * problems. XFS for example gets freeze protection on internal level - * twice in some cases, which is OK only because we already hold a - * freeze protection also on higher level. Due to these cases we have - * to use wait == F (trylock mode) which must not fail. - */ - if (wait) { - int i; - - for (i = 0; i < level - 1; i++) - if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) { - force_trylock = true; - break; - } - } -#endif - if (wait && !force_trylock) - percpu_down_read(sb->s_writers.rw_sem + level-1); - else - ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1); - - WARN_ON(force_trylock && !ret); - return ret; -} -EXPORT_SYMBOL(__sb_start_write); - /** * sb_wait_write - wait until all writers to given file system finish * @sb: the super for which we wait diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index bb128db220ac..d6ef69ab1c67 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -515,7 +515,7 @@ xfs_attr_copy_value( *========================================================================*/ /* - * Query whether the requested number of additional bytes of extended + * Query whether the total requested number of attr fork bytes of extended * attribute space will be able to fit inline. * * Returns zero if not, else the di_forkoff fork offset to be used in the @@ -535,6 +535,12 @@ xfs_attr_shortform_bytesfit( int maxforkoff; int offset; + /* + * Check if the new size could fit at all first: + */ + if (bytes > XFS_LITINO(mp)) + return 0; + /* rounded down */ offset = (XFS_LITINO(mp) - bytes) >> 3; diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 340c83f76c80..2668ebe02865 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -1514,7 +1514,7 @@ xfs_rmap_convert_shared( * record for our insertion point. This will also give us the record for * start block contiguity tests. */ - error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, flags, + error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, oldext, &PREV, &i); if (error) goto done; diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 955302e7cdde..fed56d213a3f 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -113,6 +113,8 @@ xchk_bmap_get_rmap( if (info->whichfork == XFS_ATTR_FORK) rflags |= XFS_RMAP_ATTR_FORK; + if (irec->br_state == XFS_EXT_UNWRITTEN) + rflags |= XFS_RMAP_UNWRITTEN; /* * CoW staging extents are owned (on disk) by the refcountbt, so @@ -216,13 +218,13 @@ xchk_bmap_xref_rmap( * which doesn't track unwritten state. */ if (owner != XFS_RMAP_OWN_COW && - irec->br_state == XFS_EXT_UNWRITTEN && - !(rmap.rm_flags & XFS_RMAP_UNWRITTEN)) + !!(irec->br_state == XFS_EXT_UNWRITTEN) != + !!(rmap.rm_flags & XFS_RMAP_UNWRITTEN)) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); - if (info->whichfork == XFS_ATTR_FORK && - !(rmap.rm_flags & XFS_RMAP_ATTR_FORK)) + if (!!(info->whichfork == XFS_ATTR_FORK) != + !!(rmap.rm_flags & XFS_RMAP_ATTR_FORK)) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); if (rmap.rm_flags & XFS_RMAP_BMBT_BLOCK) diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index f52a7b8256f9..debf392e0515 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -452,32 +452,41 @@ xchk_btree_check_minrecs( int level, struct xfs_btree_block *block) { - unsigned int numrecs; - int ok_level; - - numrecs = be16_to_cpu(block->bb_numrecs); + struct xfs_btree_cur *cur = bs->cur; + unsigned int root_level = cur->bc_nlevels - 1; + unsigned int numrecs = be16_to_cpu(block->bb_numrecs); /* More records than minrecs means the block is ok. */ - if (numrecs >= bs->cur->bc_ops->get_minrecs(bs->cur, level)) + if (numrecs >= cur->bc_ops->get_minrecs(cur, level)) return; /* - * Certain btree blocks /can/ have fewer than minrecs records. Any - * level greater than or equal to the level of the highest dedicated - * btree block are allowed to violate this constraint. - * - * For a btree rooted in a block, the btree root can have fewer than - * minrecs records. If the btree is rooted in an inode and does not - * store records in the root, the direct children of the root and the - * root itself can have fewer than minrecs records. + * For btrees rooted in the inode, it's possible that the root block + * contents spilled into a regular ondisk block because there wasn't + * enough space in the inode root. The number of records in that + * child block might be less than the standard minrecs, but that's ok + * provided that there's only one direct child of the root. */ - ok_level = bs->cur->bc_nlevels - 1; - if (bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) - ok_level--; - if (level >= ok_level) + if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && + level == cur->bc_nlevels - 2) { + struct xfs_btree_block *root_block; + struct xfs_buf *root_bp; + int root_maxrecs; + + root_block = xfs_btree_get_block(cur, root_level, &root_bp); + root_maxrecs = cur->bc_ops->get_dmaxrecs(cur, root_level); + if (be16_to_cpu(root_block->bb_numrecs) != 1 || + numrecs <= root_maxrecs) + xchk_btree_set_corrupt(bs->sc, cur, level); return; + } - xchk_btree_set_corrupt(bs->sc, bs->cur, level); + /* + * Otherwise, only the root level is allowed to have fewer than minrecs + * records or keyptrs. + */ + if (level < root_level) + xchk_btree_set_corrupt(bs->sc, cur, level); } /* diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index 7c432997edad..b045e95c2ea7 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -558,14 +558,27 @@ xchk_directory_leaf1_bestfree( /* Check all the bestfree entries. */ for (i = 0; i < bestcount; i++, bestp++) { best = be16_to_cpu(*bestp); - if (best == NULLDATAOFF) - continue; error = xfs_dir3_data_read(sc->tp, sc->ip, - i * args->geo->fsbcount, 0, &dbp); + xfs_dir2_db_to_da(args->geo, i), + XFS_DABUF_MAP_HOLE_OK, + &dbp); if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error)) break; - xchk_directory_check_freesp(sc, lblk, dbp, best); + + if (!dbp) { + if (best != NULLDATAOFF) { + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, + lblk); + break; + } + continue; + } + + if (best == NULLDATAOFF) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk); + else + xchk_directory_check_freesp(sc, lblk, dbp, best); xfs_trans_brelse(sc->tp, dbp); if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) break; diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index beaeb6fa3119..dd672e6bbc75 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -170,7 +170,6 @@ xchk_refcountbt_process_rmap_fragments( */ INIT_LIST_HEAD(&worklist); rbno = NULLAGBLOCK; - nr = 1; /* Make sure the fragments actually /are/ in agbno order. */ bno = 0; @@ -184,15 +183,14 @@ xchk_refcountbt_process_rmap_fragments( * Find all the rmaps that start at or before the refc extent, * and put them on the worklist. */ + nr = 0; list_for_each_entry_safe(frag, n, &refchk->fragments, list) { - if (frag->rm.rm_startblock > refchk->bno) - goto done; + if (frag->rm.rm_startblock > refchk->bno || nr > target_nr) + break; bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; if (bno < rbno) rbno = bno; list_move_tail(&frag->list, &worklist); - if (nr == target_nr) - break; nr++; } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 3abb8b9d6f4c..7b9ff824e82d 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -706,6 +706,23 @@ relock: return 0; } +/* + * Check that the imap we are going to return to the caller spans the entire + * range that the caller requested for the IO. + */ +static bool +imap_spans_range( + struct xfs_bmbt_irec *imap, + xfs_fileoff_t offset_fsb, + xfs_fileoff_t end_fsb) +{ + if (imap->br_startoff > offset_fsb) + return false; + if (imap->br_startoff + imap->br_blockcount < end_fsb) + return false; + return true; +} + static int xfs_direct_write_iomap_begin( struct inode *inode, @@ -766,6 +783,18 @@ xfs_direct_write_iomap_begin( if (imap_needs_alloc(inode, flags, &imap, nimaps)) goto allocate_blocks; + /* + * NOWAIT IO needs to span the entire requested IO with a single map so + * that we avoid partial IO failures due to the rest of the IO range not + * covered by this map triggering an EAGAIN condition when it is + * subsequently mapped and aborting the IO. + */ + if ((flags & IOMAP_NOWAIT) && + !imap_spans_range(&imap, offset_fsb, end_fsb)) { + error = -EAGAIN; + goto out_unlock; + } + xfs_iunlock(ip, lockmode); trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap); return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags); diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c index 233dcc8784db..2a45138831e3 100644 --- a/fs/xfs/xfs_iwalk.c +++ b/fs/xfs/xfs_iwalk.c @@ -55,6 +55,9 @@ struct xfs_iwalk_ag { /* Where do we start the traversal? */ xfs_ino_t startino; + /* What was the last inode number we saw when iterating the inobt? */ + xfs_ino_t lastino; + /* Array of inobt records we cache. */ struct xfs_inobt_rec_incore *recs; @@ -301,6 +304,9 @@ xfs_iwalk_ag_start( if (XFS_IS_CORRUPT(mp, *has_more != 1)) return -EFSCORRUPTED; + iwag->lastino = XFS_AGINO_TO_INO(mp, agno, + irec->ir_startino + XFS_INODES_PER_CHUNK - 1); + /* * If the LE lookup yielded an inobt record before the cursor position, * skip it and see if there's another one after it. @@ -347,15 +353,17 @@ xfs_iwalk_run_callbacks( struct xfs_mount *mp = iwag->mp; struct xfs_trans *tp = iwag->tp; struct xfs_inobt_rec_incore *irec; - xfs_agino_t restart; + xfs_agino_t next_agino; int error; + next_agino = XFS_INO_TO_AGINO(mp, iwag->lastino) + 1; + ASSERT(iwag->nr_recs > 0); /* Delete cursor but remember the last record we cached... */ xfs_iwalk_del_inobt(tp, curpp, agi_bpp, 0); irec = &iwag->recs[iwag->nr_recs - 1]; - restart = irec->ir_startino + XFS_INODES_PER_CHUNK - 1; + ASSERT(next_agino == irec->ir_startino + XFS_INODES_PER_CHUNK); error = xfs_iwalk_ag_recs(iwag); if (error) @@ -372,7 +380,7 @@ xfs_iwalk_run_callbacks( if (error) return error; - return xfs_inobt_lookup(*curpp, restart, XFS_LOOKUP_GE, has_more); + return xfs_inobt_lookup(*curpp, next_agino, XFS_LOOKUP_GE, has_more); } /* Walk all inodes in a single AG, from @iwag->startino to the end of the AG. */ @@ -396,6 +404,7 @@ xfs_iwalk_ag( while (!error && has_more) { struct xfs_inobt_rec_incore *irec; + xfs_ino_t rec_fsino; cond_resched(); if (xfs_pwork_want_abort(&iwag->pwork)) @@ -407,6 +416,15 @@ xfs_iwalk_ag( if (error || !has_more) break; + /* Make sure that we always move forward. */ + rec_fsino = XFS_AGINO_TO_INO(mp, agno, irec->ir_startino); + if (iwag->lastino != NULLFSINO && + XFS_IS_CORRUPT(mp, iwag->lastino >= rec_fsino)) { + error = -EFSCORRUPTED; + goto out; + } + iwag->lastino = rec_fsino + XFS_INODES_PER_CHUNK - 1; + /* No allocated inodes in this chunk; skip it. */ if (iwag->skip_empty && irec->ir_freecount == irec->ir_count) { error = xfs_btree_increment(cur, 0, &has_more); @@ -535,6 +553,7 @@ xfs_iwalk( .trim_start = 1, .skip_empty = 1, .pwork = XFS_PWORK_SINGLE_THREADED, + .lastino = NULLFSINO, }; xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); int error; @@ -623,6 +642,7 @@ xfs_iwalk_threaded( iwag->data = data; iwag->startino = startino; iwag->sz_recs = xfs_iwalk_prefetch(inode_records); + iwag->lastino = NULLFSINO; xfs_pwork_queue(&pctl, &iwag->pwork); startino = XFS_AGINO_TO_INO(mp, agno + 1, 0); if (flags & XFS_INOBT_WALK_SAME_AG) @@ -696,6 +716,7 @@ xfs_inobt_walk( .startino = startino, .sz_recs = xfs_inobt_walk_prefetch(inobt_records), .pwork = XFS_PWORK_SINGLE_THREADED, + .lastino = NULLFSINO, }; xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); int error; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 150ee5cb8645..7110507a2b6b 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -194,20 +194,25 @@ xfs_initialize_perag( } pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL); - if (!pag) + if (!pag) { + error = -ENOMEM; goto out_unwind_new_pags; + } pag->pag_agno = index; pag->pag_mount = mp; spin_lock_init(&pag->pag_ici_lock); INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); - if (xfs_buf_hash_init(pag)) + + error = xfs_buf_hash_init(pag); + if (error) goto out_free_pag; init_waitqueue_head(&pag->pagb_wait); spin_lock_init(&pag->pagb_lock); pag->pagb_count = 0; pag->pagb_tree = RB_ROOT; - if (radix_tree_preload(GFP_NOFS)) + error = radix_tree_preload(GFP_NOFS); + if (error) goto out_hash_destroy; spin_lock(&mp->m_perag_lock); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index b101feb2aab4..f3082a957d5e 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -134,7 +134,7 @@ xfs_fs_map_blocks( goto out_unlock; error = invalidate_inode_pages2(inode->i_mapping); if (WARN_ON_ONCE(error)) - return error; + goto out_unlock; end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length); offset_fsb = XFS_B_TO_FSBT(mp, offset); diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index ff5930be096c..bec47f2d074b 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -691,21 +691,23 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) bio->bi_opf |= REQ_FUA; ret = bio_iov_iter_get_pages(bio, from); - if (unlikely(ret)) { - bio_io_error(bio); - return ret; - } + if (unlikely(ret)) + goto out_release; + size = bio->bi_iter.bi_size; - task_io_account_write(ret); + task_io_account_write(size); if (iocb->ki_flags & IOCB_HIPRI) bio_set_polled(bio, iocb); ret = submit_bio_wait(bio); + zonefs_file_write_dio_end_io(iocb, size, ret, 0); + +out_release: + bio_release_pages(bio, false); bio_put(bio); - zonefs_file_write_dio_end_io(iocb, size, ret, 0); if (ret >= 0) { iocb->ki_pos += size; return size; diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index 798027bb89be..640f09479bdf 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -13,6 +13,7 @@ #ifndef __ASSEMBLY__ +#include <linux/compiler.h> #include <asm/rwonce.h> #ifndef nop diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h index 35e4a53b83e6..6432a7fade91 100644 --- a/include/asm-generic/percpu.h +++ b/include/asm-generic/percpu.h @@ -114,21 +114,21 @@ do { \ #define __this_cpu_generic_read_nopreempt(pcp) \ ({ \ - typeof(pcp) __ret; \ + typeof(pcp) ___ret; \ preempt_disable_notrace(); \ - __ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \ + ___ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \ preempt_enable_notrace(); \ - __ret; \ + ___ret; \ }) #define __this_cpu_generic_read_noirq(pcp) \ ({ \ - typeof(pcp) __ret; \ - unsigned long __flags; \ - raw_local_irq_save(__flags); \ - __ret = raw_cpu_generic_read(pcp); \ - raw_local_irq_restore(__flags); \ - __ret; \ + typeof(pcp) ___ret; \ + unsigned long ___flags; \ + raw_local_irq_save(___flags); \ + ___ret = raw_cpu_generic_read(pcp); \ + raw_local_irq_restore(___flags); \ + ___ret; \ }) #define this_cpu_generic_read(pcp) \ diff --git a/include/kunit/test.h b/include/kunit/test.h index db1b0ae666c4..df60be7e22ca 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -1105,7 +1105,7 @@ do { \ KUNIT_ASSERTION(test, \ strcmp(__left, __right) op 0, \ kunit_binary_str_assert, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT(test, \ + KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(test, \ assert_type, \ #op, \ #left, \ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 639cae2c158b..033eb5f73b65 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1073,12 +1073,15 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, * file system requests. */ static inline unsigned int blk_max_size_offset(struct request_queue *q, - sector_t offset) -{ - unsigned int chunk_sectors = q->limits.chunk_sectors; - - if (!chunk_sectors) - return q->limits.max_sectors; + sector_t offset, + unsigned int chunk_sectors) +{ + if (!chunk_sectors) { + if (q->limits.chunk_sectors) + chunk_sectors = q->limits.chunk_sectors; + else + return q->limits.max_sectors; + } if (likely(is_power_of_2(chunk_sectors))) chunk_sectors -= offset & (chunk_sectors - 1); @@ -1101,7 +1104,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, req_op(rq) == REQ_OP_SECURE_ERASE) return blk_queue_get_max_sectors(q, req_op(rq)); - return min(blk_max_size_offset(q, offset), + return min(blk_max_size_offset(q, offset, 0), blk_queue_get_max_sectors(q, req_op(rq))); } diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 9903088891fa..2696eb0fc149 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -12,6 +12,9 @@ #define BOOTCONFIG_MAGIC "#BOOTCONFIG\n" #define BOOTCONFIG_MAGIC_LEN 12 +#define BOOTCONFIG_ALIGN_SHIFT 2 +#define BOOTCONFIG_ALIGN (1 << BOOTCONFIG_ALIGN_SHIFT) +#define BOOTCONFIG_ALIGN_MASK (BOOTCONFIG_ALIGN - 1) /* XBC tree node */ struct xbc_node { diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h index e3a0be2c90ad..7bb66e15b481 100644 --- a/include/linux/build_bug.h +++ b/include/linux/build_bug.h @@ -77,4 +77,9 @@ #define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr) #define __static_assert(expr, msg, ...) _Static_assert(expr, msg) +#ifdef __GENKSYMS__ +/* genksyms gets confused by _Static_assert */ +#define _Static_assert(expr, ...) +#endif + #endif /* _LINUX_BUILD_BUG_H */ diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 230604e7f057..98cff1b4b088 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -8,8 +8,10 @@ + __clang_patchlevel__) #if CLANG_VERSION < 100001 +#ifndef __BPF_TRACING__ # error Sorry, your version of Clang is too old - please use 10.0.1 or newer. #endif +#endif /* Compiler specific definitions for Clang compiler */ @@ -60,12 +62,6 @@ #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif -/* The following are for compatibility with GCC, from compiler-gcc.h, - * and may be redefined here because they should not be shared with other - * compilers, like ICC. - */ -#define barrier() __asm__ __volatile__("" : : : "memory") - #if __has_feature(shadow_call_stack) # define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index d1e3c6896b71..74c6c0486eed 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -15,25 +15,6 @@ # error Sorry, your version of GCC is too old - please use 4.9 or newer. #endif -/* Optimization barrier */ - -/* The "volatile" is due to gcc bugs */ -#define barrier() __asm__ __volatile__("": : :"memory") -/* - * This version is i.e. to prevent dead stores elimination on @ptr - * where gcc and llvm may behave differently when otherwise using - * normal barrier(): while gcc behavior gets along with a normal - * barrier(), llvm needs an explicit input variable to be assumed - * clobbered. The issue is as follows: while the inline asm might - * access any memory it wants, the compiler could have fit all of - * @ptr into memory registers instead, and since @ptr never escaped - * from that, it proved that the inline asm wasn't touching any of - * it. This version works well with both compilers, i.e. we're telling - * the compiler that the inline asm absolutely may see the contents - * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495 - */ -#define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory") - /* * This macro obfuscates arithmetic on a variable address so that gcc * shouldn't recognize the original var, and make assumptions about it. @@ -175,5 +156,3 @@ #else #define __diag_GCC_8(s) #endif - -#define __no_fgcse __attribute__((optimize("-fno-gcse"))) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index e512f5505dad..b8fe0c23cfff 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -80,11 +80,25 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Optimization barrier */ #ifndef barrier -# define barrier() __memory_barrier() +/* The "volatile" is due to gcc bugs */ +# define barrier() __asm__ __volatile__("": : :"memory") #endif #ifndef barrier_data -# define barrier_data(ptr) barrier() +/* + * This version is i.e. to prevent dead stores elimination on @ptr + * where gcc and llvm may behave differently when otherwise using + * normal barrier(): while gcc behavior gets along with a normal + * barrier(), llvm needs an explicit input variable to be assumed + * clobbered. The issue is as follows: while the inline asm might + * access any memory it wants, the compiler could have fit all of + * @ptr into memory registers instead, and since @ptr never escaped + * from that, it proved that the inline asm wasn't touching any of + * it. This version works well with both compilers, i.e. we're telling + * the compiler that the inline asm absolutely may see the contents + * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495 + */ +# define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory") #endif /* workaround for GCC PR82365 if needed */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 6e390d58a9f8..ac3fa37a84f9 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -247,10 +247,6 @@ struct ftrace_likely_data { #define asm_inline asm #endif -#ifndef __no_fgcse -# define __no_fgcse -#endif - /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 1eaa04f1bae6..acbad3b36322 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -110,6 +110,12 @@ struct cpufreq_policy { bool fast_switch_enabled; /* + * Set if the CPUFREQ_GOV_STRICT_TARGET flag is set for the current + * governor. + */ + bool strict_target; + + /* * Preferred average time interval between consecutive invocations of * the driver to set the frequency for this policy. To be set by the * scaling driver (0, which is the default, means no preference). @@ -570,12 +576,20 @@ struct cpufreq_governor { char *buf); int (*store_setspeed) (struct cpufreq_policy *policy, unsigned int freq); - /* For governors which change frequency dynamically by themselves */ - bool dynamic_switching; struct list_head governor_list; struct module *owner; + u8 flags; }; +/* Governor flags */ + +/* For governors which change frequency dynamically by themselves */ +#define CPUFREQ_GOV_DYNAMIC_SWITCHING BIT(0) + +/* For governors wanting the target frequency to be set exactly */ +#define CPUFREQ_GOV_STRICT_TARGET BIT(1) + + /* Pass a target to the cpufreq driver */ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq); diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 46c3d691f677..de51c1bef27d 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -104,6 +104,7 @@ static inline int elf_core_copy_task_fpregs(struct task_struct *t, struct pt_reg #endif } +#if defined(CONFIG_UM) || defined(CONFIG_IA64) /* * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out * extra segments containing the gate DSO contents. Dumping its @@ -118,5 +119,26 @@ elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset); extern int elf_core_write_extra_data(struct coredump_params *cprm); extern size_t elf_core_extra_data_size(void); +#else +static inline Elf_Half elf_core_extra_phdrs(void) +{ + return 0; +} + +static inline int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) +{ + return 1; +} + +static inline int elf_core_write_extra_data(struct coredump_params *cprm) +{ + return 1; +} + +static inline size_t elf_core_extra_data_size(void) +{ + return 0; +} +#endif #endif /* _LINUX_ELFCORE_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 72d62cbc1578..1b62397bd124 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -558,21 +558,21 @@ struct sk_filter { DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); #define __BPF_PROG_RUN(prog, ctx, dfunc) ({ \ - u32 ret; \ + u32 __ret; \ cant_migrate(); \ if (static_branch_unlikely(&bpf_stats_enabled_key)) { \ - struct bpf_prog_stats *stats; \ - u64 start = sched_clock(); \ - ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ - stats = this_cpu_ptr(prog->aux->stats); \ - u64_stats_update_begin(&stats->syncp); \ - stats->cnt++; \ - stats->nsecs += sched_clock() - start; \ - u64_stats_update_end(&stats->syncp); \ + struct bpf_prog_stats *__stats; \ + u64 __start = sched_clock(); \ + __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ + __stats = this_cpu_ptr(prog->aux->stats); \ + u64_stats_update_begin(&__stats->syncp); \ + __stats->cnt++; \ + __stats->nsecs += sched_clock() - __start; \ + u64_stats_update_end(&__stats->syncp); \ } else { \ - ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ + __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ } \ - ret; }) + __ret; }) #define BPF_PROG_RUN(prog, ctx) \ __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func) diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 5968df82b991..41a1bab98b7e 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -50,10 +50,6 @@ #define ZYNQMP_PM_CAPABILITY_WAKEUP 0x4U #define ZYNQMP_PM_CAPABILITY_UNUSABLE 0x8U -/* Feature check status */ -#define PM_FEATURE_INVALID -1 -#define PM_FEATURE_UNCHECKED 0 - /* * Firmware FPGA Manager flags * XILINX_ZYNQMP_PM_FPGA_FULL: FPGA full reconfiguration diff --git a/include/linux/fs.h b/include/linux/fs.h index 21cc971fd960..8667d0cdc71e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1580,8 +1580,24 @@ extern struct timespec64 current_time(struct inode *inode); * Snapshotting support. */ -void __sb_end_write(struct super_block *sb, int level); -int __sb_start_write(struct super_block *sb, int level, bool wait); +/* + * These are internal functions, please use sb_start_{write,pagefault,intwrite} + * instead. + */ +static inline void __sb_end_write(struct super_block *sb, int level) +{ + percpu_up_read(sb->s_writers.rw_sem + level-1); +} + +static inline void __sb_start_write(struct super_block *sb, int level) +{ + percpu_down_read(sb->s_writers.rw_sem + level - 1); +} + +static inline bool __sb_start_write_trylock(struct super_block *sb, int level) +{ + return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); +} #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) @@ -1645,12 +1661,12 @@ static inline void sb_end_intwrite(struct super_block *sb) */ static inline void sb_start_write(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_WRITE, true); + __sb_start_write(sb, SB_FREEZE_WRITE); } -static inline int sb_start_write_trylock(struct super_block *sb) +static inline bool sb_start_write_trylock(struct super_block *sb) { - return __sb_start_write(sb, SB_FREEZE_WRITE, false); + return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** @@ -1674,7 +1690,7 @@ static inline int sb_start_write_trylock(struct super_block *sb) */ static inline void sb_start_pagefault(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_PAGEFAULT, true); + __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } /* @@ -1692,12 +1708,12 @@ static inline void sb_start_pagefault(struct super_block *sb) */ static inline void sb_start_intwrite(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_FS, true); + __sb_start_write(sb, SB_FREEZE_FS); } -static inline int sb_start_intwrite_trylock(struct super_block *sb) +static inline bool sb_start_intwrite_trylock(struct super_block *sb) { - return __sb_start_write(sb, SB_FREEZE_FS, false); + return __sb_start_write_trylock(sb, SB_FREEZE_FS); } @@ -2756,14 +2772,14 @@ static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; - __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); + sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; - return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false); + return sb_start_write_trylock(file_inode(file)->i_sb); } static inline void file_end_write(struct file *file) diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 38f23d757013..03da3f603d30 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -315,7 +315,7 @@ static inline int get_disk_ro(struct gendisk *disk) extern void disk_block_events(struct gendisk *disk); extern void disk_unblock_events(struct gendisk *disk); extern void disk_flush_events(struct gendisk *disk, unsigned int mask); -void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, +bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, bool update_bdev); /* drivers/char/random.c */ diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index fbf5b3e7707e..d956987ed032 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -798,7 +798,6 @@ extern int iommu_calculate_agaw(struct intel_iommu *iommu); extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); extern int dmar_disabled; extern int intel_iommu_enabled; -extern int intel_iommu_tboot_noforce; extern int intel_iommu_gfx_mapped; #else static inline int iommu_calculate_agaw(struct intel_iommu *iommu) diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 71535e87109f..ea5a337e0f8b 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -384,11 +384,19 @@ extern void irq_domain_associate_many(struct irq_domain *domain, extern void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq); -extern unsigned int irq_create_mapping(struct irq_domain *host, - irq_hw_number_t hwirq); +extern unsigned int irq_create_mapping_affinity(struct irq_domain *host, + irq_hw_number_t hwirq, + const struct irq_affinity_desc *affinity); extern unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec); extern void irq_dispose_mapping(unsigned int virq); +static inline unsigned int irq_create_mapping(struct irq_domain *host, + irq_hw_number_t hwirq) +{ + return irq_create_mapping_affinity(host, hwirq, NULL); +} + + /** * irq_linear_revmap() - Find a linux irq from a hw irq number. * @domain: domain owning this hardware interrupt diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 1d5566af48ac..578ff196b3ce 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -68,6 +68,7 @@ extern void *jbd2_alloc(size_t size, gfp_t flags); extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 +#define JBD2_MIN_FC_BLOCKS 256 #ifdef __KERNEL__ @@ -400,7 +401,7 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) #define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** - * struct jbd_inode - The jbd_inode type is the structure linking inodes in + * struct jbd2_inode - The jbd_inode type is the structure linking inodes in * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { @@ -944,8 +945,9 @@ struct journal_s /** * @j_fc_off: * - * Number of fast commit blocks currently allocated. - * [j_state_lock]. + * Number of fast commit blocks currently allocated. Accessed only + * during fast commit. Currently only process can do fast commit, so + * this field is not protected by any lock. */ unsigned long j_fc_off; @@ -988,9 +990,9 @@ struct journal_s struct block_device *j_fs_dev; /** - * @j_maxlen: Total maximum capacity of the journal region on disk. + * @j_total_len: Total maximum capacity of the journal region on disk. */ - unsigned int j_maxlen; + unsigned int j_total_len; /** * @j_reserved_credits: @@ -1108,8 +1110,9 @@ struct journal_s struct buffer_head **j_wbuf; /** - * @j_fc_wbuf: Array of fast commit bhs for - * jbd2_journal_commit_transaction. + * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only + * during a fast commit. Currently only process can do fast commit, so + * this field is not protected by any lock. */ struct buffer_head **j_fc_wbuf; @@ -1614,16 +1617,20 @@ extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); /* Fast commit related APIs */ -int jbd2_fc_init(journal_t *journal, int num_fc_blks); int jbd2_fc_begin_commit(journal_t *journal, tid_t tid); int jbd2_fc_end_commit(journal_t *journal); -int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid); +int jbd2_fc_end_commit_fallback(journal_t *journal); int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); int jbd2_submit_inode_data(struct jbd2_inode *jinode); int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); int jbd2_fc_release_bufs(journal_t *journal); +static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal) +{ + return (journal->j_total_len - journal->j_fc_wbufsize) / 4; +} + /* * is_journal_abort * diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e391e3c56de5..922a7f600465 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -282,20 +282,6 @@ struct mem_cgroup { MEMCG_PADDING(_pad1_); - /* - * set > 0 if pages under this cgroup are moving to other cgroup. - */ - atomic_t moving_account; - struct task_struct *move_lock_task; - - /* Legacy local VM stats and events */ - struct memcg_vmstats_percpu __percpu *vmstats_local; - - /* Subtree VM stats and events (batched updates) */ - struct memcg_vmstats_percpu __percpu *vmstats_percpu; - - MEMCG_PADDING(_pad2_); - atomic_long_t vmstats[MEMCG_NR_STAT]; atomic_long_t vmevents[NR_VM_EVENT_ITEMS]; @@ -317,6 +303,20 @@ struct mem_cgroup { struct list_head objcg_list; /* list of inherited objcgs */ #endif + MEMCG_PADDING(_pad2_); + + /* + * set > 0 if pages under this cgroup are moving to other cgroup. + */ + atomic_t moving_account; + struct task_struct *move_lock_task; + + /* Legacy local VM stats and events */ + struct memcg_vmstats_percpu __percpu *vmstats_local; + + /* Subtree VM stats and events (batched updates) */ + struct memcg_vmstats_percpu __percpu *vmstats_percpu; + #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; @@ -900,12 +900,19 @@ static inline void count_memcg_event_mm(struct mm_struct *mm, static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { + bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX || + event == MEMCG_SWAP_FAIL; + atomic_long_inc(&memcg->memory_events_local[event]); - cgroup_file_notify(&memcg->events_local_file); + if (!swap_event) + cgroup_file_notify(&memcg->events_local_file); do { atomic_long_inc(&memcg->memory_events[event]); - cgroup_file_notify(&memcg->events_file); + if (swap_event) + cgroup_file_notify(&memcg->swap_events_file); + else + cgroup_file_notify(&memcg->events_file); if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) break; diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index d65c6fdc5cfc..551093b74596 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -281,20 +281,6 @@ static inline bool movable_node_is_enabled(void) } #endif /* ! CONFIG_MEMORY_HOTPLUG */ -#ifdef CONFIG_NUMA -extern int memory_add_physaddr_to_nid(u64 start); -extern int phys_to_target_node(u64 start); -#else -static inline int memory_add_physaddr_to_nid(u64 start) -{ - return 0; -} -static inline int phys_to_target_node(u64 start) -{ - return 0; -} -#endif - #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * pgdat resizing functions diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a092346c7b2d..233352447b1a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1223,6 +1223,11 @@ enum mlx5_fc_bulk_alloc_bitmask { #define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum)) +enum { + MLX5_STEERING_FORMAT_CONNECTX_5 = 0, + MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, +}; + struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x30]; u8 vhca_id[0x10]; @@ -1521,7 +1526,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 general_obj_types[0x40]; - u8 reserved_at_440[0x20]; + u8 reserved_at_440[0x4]; + u8 steering_format_version[0x4]; + u8 create_qp_start_hint[0x18]; u8 reserved_at_460[0x3]; u8 log_max_uctx[0x5]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 964b494b0e8d..7c3da0e1ea9d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2813,9 +2813,21 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); + int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); -int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); +int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id); + +static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) +{ + int ret; + + ret = __dev_direct_xmit(skb, queue_id); + if (!dev_xmit_complete(ret)) + kfree_skb(skb); + return ret; +} + int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head); @@ -3137,6 +3149,11 @@ static inline bool dev_validate_header(const struct net_device *dev, return false; } +static inline bool dev_has_header(const struct net_device *dev) +{ + return dev->header_ops && dev->header_ops->create; +} + typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len, int size); int register_gifconf(unsigned int family, gifconf_func_t *gifconf); diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 5deb099d156d..8ebb64193757 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -227,7 +227,7 @@ struct xt_table { unsigned int valid_hooks; /* Man behind the curtain... */ - struct xt_table_info *private; + struct xt_table_info __rcu *private; /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; @@ -448,6 +448,9 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); +struct xt_table_info +*xt_table_get_private_protected(const struct xt_table *table); + #ifdef CONFIG_COMPAT #include <net/compat.h> diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index c32c15216da3..f0373a6cb5fb 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -55,6 +55,7 @@ struct nfs_page { unsigned short wb_nio; /* Number of I/O attempts */ }; +struct nfs_pgio_mirror; struct nfs_pageio_descriptor; struct nfs_pageio_ops { void (*pg_init)(struct nfs_pageio_descriptor *, struct nfs_page *); @@ -64,6 +65,9 @@ struct nfs_pageio_ops { unsigned int (*pg_get_mirror_count)(struct nfs_pageio_descriptor *, struct nfs_page *); void (*pg_cleanup)(struct nfs_pageio_descriptor *); + struct nfs_pgio_mirror * + (*pg_get_mirror)(struct nfs_pageio_descriptor *, u32); + u32 (*pg_set_mirror)(struct nfs_pageio_descriptor *, u32); }; struct nfs_rw_ops { diff --git a/include/linux/numa.h b/include/linux/numa.h index 8cb33ccfb671..cb44cfe2b725 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -21,13 +21,41 @@ #endif #ifdef CONFIG_NUMA +#include <linux/printk.h> +#include <asm/sparsemem.h> + /* Generic implementation available */ int numa_map_to_online_node(int node); -#else + +#ifndef memory_add_physaddr_to_nid +static inline int memory_add_physaddr_to_nid(u64 start) +{ + pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +#endif +#ifndef phys_to_target_node +static inline int phys_to_target_node(u64 start) +{ + pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", + start); + return 0; +} +#endif +#else /* !CONFIG_NUMA */ static inline int numa_map_to_online_node(int node) { return NUMA_NO_NODE; } +static inline int memory_add_physaddr_to_nid(u64 start) +{ + return 0; +} +static inline int phys_to_target_node(u64 start) +{ + return 0; +} #endif #endif /* _LINUX_NUMA_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index e1e19c1f9ec9..d5570deff400 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -906,6 +906,8 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, xas_set(&xas, rac->_index); rcu_read_lock(); xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) { + if (xas_retry(&xas, page)) + continue; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0c19d279b97f..96450f6fb1de 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1022,13 +1022,7 @@ struct perf_sample_data { struct perf_callchain_entry *callchain; u64 aux_size; - /* - * regs_user may point to task_pt_regs or to regs_user_copy, depending - * on arch details. - */ struct perf_regs regs_user; - struct pt_regs regs_user_copy; - struct perf_regs regs_intr; u64 stack_user_size; @@ -1400,11 +1394,14 @@ perf_event_addr_filters(struct perf_event *event) extern void perf_event_addr_filters_sync(struct perf_event *event); extern int perf_output_begin(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_forward(struct perf_output_handle *handle, - struct perf_event *event, - unsigned int size); + struct perf_sample_data *data, + struct perf_event *event, + unsigned int size); extern int perf_output_begin_backward(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size); diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h index 2d12e97d5e7b..f632c5725f16 100644 --- a/include/linux/perf_regs.h +++ b/include/linux/perf_regs.h @@ -20,8 +20,7 @@ u64 perf_reg_value(struct pt_regs *regs, int idx); int perf_reg_validate(u64 mask); u64 perf_reg_abi(struct task_struct *task); void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy); + struct pt_regs *regs); #else #define PERF_REG_EXTENDED_MASK 0 @@ -42,8 +41,7 @@ static inline u64 perf_reg_abi(struct task_struct *task) } static inline void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 71125a4676c4..e237004d498d 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1427,6 +1427,19 @@ typedef unsigned int pgtbl_mod_mask; #endif /* !__ASSEMBLY__ */ +#if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT) +#ifdef CONFIG_PHYS_ADDR_T_64BIT +/* + * ZSMALLOC needs to know the highest PFN on 32-bit architectures + * with physical address space extension, but falls back to + * BITS_PER_LONG otherwise. + */ +#error Missing MAX_POSSIBLE_PHYSMEM_BITS definition +#else +#define MAX_POSSIBLE_PHYSMEM_BITS 32 +#endif +#endif + #ifndef has_transparent_hugepage #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define has_transparent_hugepage() 1 diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index c59999ce044e..240dce553a0b 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -50,6 +50,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_MODULE_QUIRK_ENA_RESETDONE BIT(25) #define SYSC_MODULE_QUIRK_PRUSS BIT(24) #define SYSC_MODULE_QUIRK_DSS_RESET BIT(23) #define SYSC_MODULE_QUIRK_RTC_UNLOCK BIT(22) diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 4b708f4e8eed..b492ae00cc90 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -387,6 +387,27 @@ static inline int pm_runtime_get_sync(struct device *dev) } /** + * pm_runtime_resume_and_get - Bump up usage counter of a device and resume it. + * @dev: Target device. + * + * Resume @dev synchronously and if that is successful, increment its runtime + * PM usage counter. Return 0 if the runtime PM usage counter of @dev has been + * incremented or a negative error code otherwise. + */ +static inline int pm_runtime_resume_and_get(struct device *dev) +{ + int ret; + + ret = __pm_runtime_resume(dev, RPM_GET_PUT); + if (ret < 0) { + pm_runtime_put_noidle(dev); + return ret; + } + + return 0; +} + +/** * pm_runtime_put - Drop device usage counter and queue up "idle check" if 0. * @dev: Target device. * diff --git a/include/linux/sched.h b/include/linux/sched.h index 063cd120b459..76cd21fa5501 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -552,7 +552,6 @@ struct sched_dl_entity { * overruns. */ unsigned int dl_throttled : 1; - unsigned int dl_boosted : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; @@ -571,6 +570,15 @@ struct sched_dl_entity { * time. */ struct hrtimer inactive_timer; + +#ifdef CONFIG_RT_MUTEXES + /* + * Priority Inheritance. When a DEADLINE scheduling entity is boosted + * pi_se points to the donor, otherwise points to the dl_se it belongs + * to (the original one/itself). + */ + struct sched_dl_entity *pi_se; +#endif }; #ifdef CONFIG_UCLAMP_TASK @@ -770,7 +778,6 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; - unsigned sched_remote_wakeup:1; #ifdef CONFIG_PSI unsigned sched_psi_wake_requeue:1; #endif @@ -780,6 +787,21 @@ struct task_struct { /* Unserialized, strictly 'current' */ + /* + * This field must not be in the scheduler word above due to wakelist + * queueing no longer being serialized by p->on_cpu. However: + * + * p->XXX = X; ttwu() + * schedule() if (p->on_rq && ..) // false + * smp_mb__after_spinlock(); if (smp_load_acquire(&p->on_cpu) && //true + * deactivate_task() ttwu_queue_wakelist()) + * p->on_rq = 0; p->sched_remote_wakeup = Y; + * + * guarantees all stores of 'current' are visible before + * ->sched_remote_wakeup gets used, so it can be in this word. + */ + unsigned sched_remote_wakeup:1; + /* Bit to tell LSMs we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; diff --git a/include/linux/security.h b/include/linux/security.h index bc2725491560..39642626a707 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -869,7 +869,7 @@ static inline int security_inode_killpriv(struct dentry *dentry) static inline int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) { - return -EOPNOTSUPP; + return cap_inode_getsecurity(inode, name, buffer, alloc); } static inline int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 99380c0825db..b390fdac1587 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -734,6 +734,25 @@ static inline struct spi_controller *spi_alloc_slave(struct device *host, return __spi_alloc_controller(host, size, true); } +struct spi_controller *__devm_spi_alloc_controller(struct device *dev, + unsigned int size, + bool slave); + +static inline struct spi_controller *devm_spi_alloc_master(struct device *dev, + unsigned int size) +{ + return __devm_spi_alloc_controller(dev, size, false); +} + +static inline struct spi_controller *devm_spi_alloc_slave(struct device *dev, + unsigned int size) +{ + if (!IS_ENABLED(CONFIG_SPI_SLAVE)) + return NULL; + + return __devm_spi_alloc_controller(dev, size, true); +} + extern int spi_register_controller(struct spi_controller *ctlr); extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 628e28903b8b..15ca6b4167cc 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -170,6 +170,7 @@ struct plat_stmmacenet_data { int unicast_filter_entries; int tx_fifo_size; int rx_fifo_size; + u32 addr64; u32 rx_queues_to_use; u32 tx_queues_to_use; u8 rx_sched_algorithm; diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 513913ff7486..fbdc65782195 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -5,6 +5,7 @@ #include <linux/dma-direction.h> #include <linux/init.h> #include <linux/types.h> +#include <linux/limits.h> struct device; struct page; @@ -45,13 +46,9 @@ enum dma_sync_target { SYNC_FOR_DEVICE = 1, }; -extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, - dma_addr_t tbl_dma_addr, - phys_addr_t phys, - size_t mapping_size, - size_t alloc_size, - enum dma_data_direction dir, - unsigned long attrs); +phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, + size_t mapping_size, size_t alloc_size, + enum dma_data_direction dir, unsigned long attrs); extern void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, diff --git a/include/linux/tty.h b/include/linux/tty.h index a99e9b8e4e31..eb33d948788c 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -306,6 +306,10 @@ struct tty_struct { struct termiox *termiox; /* May be NULL for unsupported */ char name[64]; struct pid *pgrp; /* Protected by ctrl lock */ + /* + * Writes protected by both ctrl lock and legacy mutex, readers must use + * at least one of them. + */ struct pid *session; unsigned long flags; int count; diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index 0fdbf653b173..4807ca4d52e0 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -20,7 +20,6 @@ * zsmalloc mapping modes * * NOTE: These only make a difference when a mapped object spans pages. - * They also have no effect when ZSMALLOC_PGTABLE_MAPPING is selected. */ enum zs_mapmode { ZS_MM_RW, /* normal read-write mapping */ diff --git a/include/net/bonding.h b/include/net/bonding.h index 7d132cc1e584..adc3da776970 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -86,10 +86,8 @@ #define bond_for_each_slave_rcu(bond, pos, iter) \ netdev_for_each_lower_private_rcu((bond)->dev, pos, iter) -#ifdef CONFIG_XFRM_OFFLOAD #define BOND_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) -#endif /* CONFIG_XFRM_OFFLOAD */ #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; @@ -185,6 +183,11 @@ struct slave { struct rtnl_link_stats64 slave_stats; }; +static inline struct slave *to_slave(struct kobject *kobj) +{ + return container_of(kobj, struct slave, kobj); +} + struct bond_up_slave { unsigned int count; struct rcu_head rcu; @@ -750,6 +753,9 @@ extern struct bond_parm_tbl ad_select_tbl[]; /* exported from bond_netlink.c */ extern struct rtnl_link_ops bond_link_ops; +/* exported from bond_sysfs_slave.c */ +extern const struct sysfs_ops slave_sysfs_ops; + static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb) { atomic_long_inc(&dev->tx_dropped); diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index e1eaf1780288..563457fec557 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -107,7 +107,7 @@ static inline int IP_ECN_set_ect1(struct iphdr *iph) if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0) return 0; - check += (__force u16)htons(0x100); + check += (__force u16)htons(0x1); iph->check = (__force __sum16)(check + (check>=0xFFFF)); iph->tos ^= INET_ECN_MASK; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 92560974ea67..ca6a3ea9057e 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -247,8 +247,9 @@ void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, unsigned long high_limit); int inet_hashinfo2_init_mod(struct inet_hashinfo *h); -bool inet_ehash_insert(struct sock *sk, struct sock *osk); -bool inet_ehash_nolisten(struct sock *sk, struct sock *osk); +bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk); +bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, + bool *found_dup_sk); int __inet_hash(struct sock *sk, struct sock *osk); int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 02ccd32542d0..61620677b034 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -478,9 +478,11 @@ static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, __be16 flags) { - memcpy(ip_tunnel_info_opts(info), from, len); info->options_len = len; - info->key.tun_flags |= flags; + if (len > 0) { + memcpy(ip_tunnel_info_opts(info), from, len); + info->key.tun_flags |= flags; + } } static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) @@ -526,7 +528,6 @@ static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, __be16 flags) { info->options_len = 0; - info->key.tun_flags |= flags; } #endif /* CONFIG_INET */ diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index a21e8b1381a1..851029ecff13 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -108,5 +108,35 @@ out_rcu_unlock: rcu_read_unlock(); inet_frag_put(&fq->q); } + +/* Check if the upper layer header is truncated in the first fragment. */ +static inline bool +ipv6frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp) +{ + u8 nexthdr = *nexthdrp; + __be16 frag_off; + int offset; + + offset = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off); + if (offset < 0 || (frag_off & htons(IP6_OFFSET))) + return false; + switch (nexthdr) { + case NEXTHDR_TCP: + offset += sizeof(struct tcphdr); + break; + case NEXTHDR_UDP: + offset += sizeof(struct udphdr); + break; + case NEXTHDR_ICMP: + offset += sizeof(struct icmp6hdr); + break; + default: + offset += 1; + } + if (offset > skb->len) + return true; + return false; +} + #endif #endif diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 81ee17594c32..22ced1381ede 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -204,6 +204,7 @@ struct neigh_table { int (*pconstructor)(struct pneigh_entry *); void (*pdestructor)(struct pneigh_entry *); void (*proxy_redo)(struct sk_buff *skb); + int (*is_multicast)(const void *pkey); bool (*allow_add)(const struct net_device *dev, struct netlink_ext_ack *extack); char *id; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 55b4cadf290a..c1c0a4ff92ae 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1524,4 +1524,8 @@ void __init nft_chain_route_init(void); void nft_chain_route_fini(void); void nf_tables_trans_destroy_flush_work(void); + +int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result); +__be64 nf_jiffies64_to_msecs(u64 input); + #endif /* _NET_NF_TABLES_H */ diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h index ea7d1d78b92d..1d34fe154fe0 100644 --- a/include/net/netfilter/nf_tables_offload.h +++ b/include/net/netfilter/nf_tables_offload.h @@ -37,6 +37,7 @@ void nft_offload_update_dependency(struct nft_offload_ctx *ctx, struct nft_flow_key { struct flow_dissector_key_basic basic; + struct flow_dissector_key_control control; union { struct flow_dissector_key_ipv4_addrs ipv4; struct flow_dissector_key_ipv6_addrs ipv6; @@ -62,6 +63,9 @@ struct nft_flow_rule { #define NFT_OFFLOAD_F_ACTION (1 << 0) +void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, + enum flow_dissector_key_id addr_type); + struct nft_rule; struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule); void nft_flow_rule_destroy(struct nft_flow_rule *flow); @@ -74,6 +78,9 @@ int nft_flow_rule_offload_commit(struct net *net); offsetof(struct nft_flow_key, __base.__field); \ (__reg)->len = __len; \ (__reg)->key = __key; \ + +#define NFT_OFFLOAD_MATCH_EXACT(__key, __base, __field, __len, __reg) \ + NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \ memset(&(__reg)->mask, 0xff, (__reg)->len); int nft_chain_offload_priority(struct nft_base_chain *basechain); diff --git a/include/net/tls.h b/include/net/tls.h index baf1e99d8193..2bdd802212fe 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -199,6 +199,12 @@ enum tls_context_flags { * to be atomic. */ TLS_TX_SYNC_SCHED = 1, + /* tls_dev_del was called for the RX side, device state was released, + * but tls_ctx->netdev might still be kept, because TX-side driver + * resources might not be released yet. Used to prevent the second + * tls_dev_del call in tls_device_down if it happens simultaneously. + */ + TLS_RX_DEV_CLOSED = 2, }; struct cipher_context { @@ -300,7 +306,8 @@ enum tls_offload_sync_type { #define TLS_DEVICE_RESYNC_ASYNC_LOGMAX 13 struct tls_offload_resync_async { atomic64_t req; - u32 loglen; + u16 loglen; + u16 rcd_delta; u32 log[TLS_DEVICE_RESYNC_ASYNC_LOGMAX]; }; @@ -471,6 +478,18 @@ static inline bool tls_bigint_increment(unsigned char *seq, int len) return (i == -1); } +static inline void tls_bigint_subtract(unsigned char *seq, int n) +{ + u64 rcd_sn; + __be64 *p; + + BUILD_BUG_ON(TLS_MAX_REC_SEQ_SIZE != 8); + + p = (__be64 *)seq; + rcd_sn = be64_to_cpu(*p); + *p = cpu_to_be64(rcd_sn - n); +} + static inline struct tls_context *tls_get_ctx(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -639,6 +658,7 @@ tls_offload_rx_resync_async_request_start(struct sock *sk, __be32 seq, u16 len) atomic64_set(&rx_ctx->resync_async->req, ((u64)ntohl(seq) << 32) | ((u64)len << 16) | RESYNC_REQ | RESYNC_REQ_ASYNC); rx_ctx->resync_async->loglen = 0; + rx_ctx->resync_async->rcd_delta = 0; } static inline void diff --git a/include/net/xdp.h b/include/net/xdp.h index 3814fb631d52..9dab2bc6f187 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -240,8 +240,6 @@ struct xdp_attachment_info { }; struct netdev_bpf; -bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, - struct netdev_bpf *bpf); void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf); diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 1a9559c0cbdd..4f4e93bf814c 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -31,6 +31,7 @@ struct xdp_umem { struct page **pgs; int id; struct list_head xsk_dma_list; + struct work_struct work; }; struct xsk_map { diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 0140d086dc84..01755b838c74 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -86,7 +86,7 @@ int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, void xp_destroy(struct xsk_buff_pool *pool); void xp_release(struct xdp_buff_xsk *xskb); void xp_get_pool(struct xsk_buff_pool *pool); -void xp_put_pool(struct xsk_buff_pool *pool); +bool xp_put_pool(struct xsk_buff_pool *pool); void xp_clear_dev(struct xsk_buff_pool *pool); void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index c25fb86ffae9..b3bbd10eb3f0 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -132,6 +132,9 @@ struct iscsi_task { void *dd_data; /* driver/transport data */ }; +/* invalid scsi_task pointer */ +#define INVALID_SCSI_TASK (struct iscsi_task *)-1l + static inline int iscsi_task_has_unsol_data(struct iscsi_task *task) { return task->unsol_r2t.data_length > task->unsol_r2t.sent; diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 1e9db9577441..49b46df476f2 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -618,6 +618,9 @@ struct ocelot { /* Keep track of the vlan port masks */ u32 vlan_mask[VLAN_N_VID]; + /* Switches like VSC9959 have flooding per traffic class */ + int num_flooding_pgids; + /* In tables like ANA:PORT and the ANA:PGID:PGID mask, * the CPU is located after the physical ports (at the * num_phys_ports index). diff --git a/include/sound/rt1015.h b/include/sound/rt1015.h new file mode 100644 index 000000000000..70a7538d4c89 --- /dev/null +++ b/include/sound/rt1015.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/sound/rt1015.h -- Platform data for RT1015 + * + * Copyright 2020 Realtek Microelectronics + */ + +#ifndef __LINUX_SND_RT1015_H +#define __LINUX_SND_RT1015_H + +struct rt1015_platform_data { + unsigned int power_up_delay_ms; +}; + +#endif diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index b14314fcf732..70ae5497b73a 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -100,11 +100,12 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B); { EXT4_FC_REASON_XATTR, "XATTR"}, \ { EXT4_FC_REASON_CROSS_RENAME, "CROSS_RENAME"}, \ { EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \ - { EXT4_FC_REASON_MEM, "NO_MEM"}, \ + { EXT4_FC_REASON_NOMEM, "NO_MEM"}, \ { EXT4_FC_REASON_SWAP_BOOT, "SWAP_BOOT"}, \ { EXT4_FC_REASON_RESIZE, "RESIZE"}, \ { EXT4_FC_REASON_RENAME_DIR, "RENAME_DIR"}, \ - { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}) + { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}, \ + { EXT4_FC_REASON_INODE_JOURNAL_DATA, "INODE_JOURNAL_DATA"}) TRACE_EVENT(ext4_other_inode_update_time, TP_PROTO(struct inode *inode, ino_t orig_ino), @@ -2917,17 +2918,18 @@ TRACE_EVENT(ext4_fc_stats, ), TP_printk("dev %d:%d fc ineligible reasons:\n" - "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s,%d; " + "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d; " "num_commits:%ld, ineligible: %ld, numblks: %ld", MAJOR(__entry->dev), MINOR(__entry->dev), FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR), FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME), FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE), - FC_REASON_NAME_STAT(EXT4_FC_REASON_MEM), + FC_REASON_NAME_STAT(EXT4_FC_REASON_NOMEM), FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT), FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE), FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR), FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE), + FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA), __entry->sbi->s_fc_stats.fc_num_commits, __entry->sbi->s_fc_stats.fc_ineligible_commits, __entry->sbi->s_fc_stats.fc_numblks) diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index f45b3c01370c..2a03263b5f9d 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -68,7 +68,8 @@ DECLARE_EVENT_CLASS(rpc_xdr_buf_class, TP_fast_assign( __entry->task_id = task->tk_pid; - __entry->client_id = task->tk_client->cl_clid; + __entry->client_id = task->tk_client ? + task->tk_client->cl_clid : -1; __entry->head_base = xdr->head[0].iov_base; __entry->head_len = xdr->head[0].iov_len; __entry->tail_base = xdr->tail[0].iov_base; @@ -655,10 +656,10 @@ TRACE_EVENT(rpc_xdr_overflow, __field(size_t, tail_len) __field(unsigned int, page_len) __field(unsigned int, len) - __string(progname, - xdr->rqst->rq_task->tk_client->cl_program->name) - __string(procedure, - xdr->rqst->rq_task->tk_msg.rpc_proc->p_name) + __string(progname, xdr->rqst ? + xdr->rqst->rq_task->tk_client->cl_program->name : "unknown") + __string(procedure, xdr->rqst ? + xdr->rqst->rq_task->tk_msg.rpc_proc->p_name : "unknown") ), TP_fast_assign( diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index e7cbccc7c14c..57d795365987 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -190,7 +190,7 @@ TRACE_EVENT(inode_foreign_history, ), TP_fast_assign( - strncpy(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); + strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); __entry->history = history; @@ -219,7 +219,7 @@ TRACE_EVENT(inode_switch_wbs, ), TP_fast_assign( - strncpy(__entry->name, bdi_dev_name(old_wb->bdi), 32); + strscpy_pad(__entry->name, bdi_dev_name(old_wb->bdi), 32); __entry->ino = inode->i_ino; __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb); __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb); @@ -252,7 +252,7 @@ TRACE_EVENT(track_foreign_dirty, struct address_space *mapping = page_mapping(page); struct inode *inode = mapping ? mapping->host : NULL; - strncpy(__entry->name, bdi_dev_name(wb->bdi), 32); + strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->bdi_id = wb->bdi->id; __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; @@ -285,7 +285,7 @@ TRACE_EVENT(flush_foreign, ), TP_fast_assign( - strncpy(__entry->name, bdi_dev_name(wb->bdi), 32); + strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->frn_bdi_id = frn_bdi_id; __entry->frn_memcg_id = frn_memcg_id; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e6ceac3f7d62..556216dc9703 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3897,8 +3897,8 @@ union bpf_attr { FN(seq_printf_btf), \ FN(skb_cgroup_classid), \ FN(redirect_neigh), \ - FN(bpf_per_cpu_ptr), \ - FN(bpf_this_cpu_ptr), \ + FN(per_cpu_ptr), \ + FN(this_cpu_ptr), \ FN(redirect_peer), \ /* */ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 0113bc4db9f5..5203f54a2be1 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -526,6 +526,8 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_STATS_LIMIT, /* u8 */ DEVLINK_ATTR_RELOAD_STATS_VALUE, /* u32 */ DEVLINK_ATTR_REMOTE_RELOAD_STATS, /* nested */ + DEVLINK_ATTR_RELOAD_ACTION_INFO, /* nested */ + DEVLINK_ATTR_RELOAD_ACTION_STATS, /* nested */ /* add new attributes above here, update the policy in devlink.c */ diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 07865c601099..2072c260f5d0 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -26,7 +26,7 @@ * struct gpiochip_info - Information about a certain GPIO chip * @name: the Linux kernel name of this GPIO chip * @label: a functional name for this GPIO chip, such as a product - * number, may be empty + * number, may be empty (i.e. label[0] == '\0') * @lines: number of GPIO lines on this chip */ struct gpiochip_info { @@ -98,7 +98,7 @@ struct gpio_v2_line_values { * identifying which field of the attribute union is in use. * @GPIO_V2_LINE_ATTR_ID_FLAGS: flags field is in use * @GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES: values field is in use - * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us is in use + * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us field is in use */ enum gpio_v2_line_attr_id { GPIO_V2_LINE_ATTR_ID_FLAGS = 1, @@ -110,17 +110,17 @@ enum gpio_v2_line_attr_id { * struct gpio_v2_line_attribute - a configurable attribute of a line * @id: attribute identifier with value from &enum gpio_v2_line_attr_id * @padding: reserved for future use and must be zero filled - * @flags: if id is GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO - * line, with values from enum gpio_v2_line_flag, such as - * GPIO_V2_LINE_FLAG_ACTIVE_LOW, GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed + * @flags: if id is %GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO + * line, with values from &enum gpio_v2_line_flag, such as + * %GPIO_V2_LINE_FLAG_ACTIVE_LOW, %GPIO_V2_LINE_FLAG_OUTPUT etc, added * together. This overrides the default flags contained in the &struct * gpio_v2_line_config for the associated line. - * @values: if id is GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap + * @values: if id is %GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap * containing the values to which the lines will be set, with each bit * number corresponding to the index into &struct * gpio_v2_line_request.offsets. - * @debounce_period_us: if id is GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the desired - * debounce period, in microseconds + * @debounce_period_us: if id is %GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the + * desired debounce period, in microseconds */ struct gpio_v2_line_attribute { __u32 id; @@ -147,12 +147,12 @@ struct gpio_v2_line_config_attribute { /** * struct gpio_v2_line_config - Configuration for GPIO lines - * @flags: flags for the GPIO lines, with values from enum - * gpio_v2_line_flag, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW, - * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together. This is the default for + * @flags: flags for the GPIO lines, with values from &enum + * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW, + * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together. This is the default for * all requested lines but may be overridden for particular lines using - * attrs. - * @num_attrs: the number of attributes in attrs + * @attrs. + * @num_attrs: the number of attributes in @attrs * @padding: reserved for future use and must be zero filled * @attrs: the configuration attributes associated with the requested * lines. Any attribute should only be associated with a particular line @@ -175,17 +175,17 @@ struct gpio_v2_line_config { * "my-bitbanged-relay" * @config: requested configuration for the lines. * @num_lines: number of lines requested in this request, i.e. the number - * of valid fields in the GPIO_V2_LINES_MAX sized arrays, set to 1 to + * of valid fields in the %GPIO_V2_LINES_MAX sized arrays, set to 1 to * request a single line * @event_buffer_size: a suggested minimum number of line events that the * kernel should buffer. This is only relevant if edge detection is * enabled in the configuration. Note that this is only a suggested value * and the kernel may allocate a larger buffer or cap the size of the * buffer. If this field is zero then the buffer size defaults to a minimum - * of num_lines*16. + * of @num_lines * 16. * @padding: reserved for future use and must be zero filled * @fd: if successful this field will contain a valid anonymous file handle - * after a GPIO_GET_LINE_IOCTL operation, zero or negative value means + * after a %GPIO_GET_LINE_IOCTL operation, zero or negative value means * error */ struct gpio_v2_line_request { @@ -203,15 +203,16 @@ struct gpio_v2_line_request { * struct gpio_v2_line_info - Information about a certain GPIO line * @name: the name of this GPIO line, such as the output pin of the line on * the chip, a rail or a pin header name on a board, as specified by the - * GPIO chip, may be empty + * GPIO chip, may be empty (i.e. name[0] == '\0') * @consumer: a functional name for the consumer of this GPIO line as set * by whatever is using it, will be empty if there is no current user but * may also be empty if the consumer doesn't set this up - * @flags: flags for the GPIO line, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW, - * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together * @offset: the local offset on this GPIO chip, fill this in when * requesting the line information from the kernel - * @num_attrs: the number of attributes in attrs + * @num_attrs: the number of attributes in @attrs + * @flags: flags for the GPIO lines, with values from &enum + * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW, + * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together. * @attrs: the configuration attributes associated with the line * @padding: reserved for future use */ @@ -244,7 +245,7 @@ enum gpio_v2_line_changed_type { * of a GPIO line * @info: updated line information * @timestamp_ns: estimate of time of status change occurrence, in nanoseconds - * @event_type: the type of change with a value from enum + * @event_type: the type of change with a value from &enum * gpio_v2_line_changed_type * @padding: reserved for future use */ @@ -269,10 +270,10 @@ enum gpio_v2_line_event_id { /** * struct gpio_v2_line_event - The actual event being pushed to userspace * @timestamp_ns: best estimate of time of event occurrence, in nanoseconds. - * The timestamp_ns is read from CLOCK_MONOTONIC and is intended to allow the - * accurate measurement of the time between events. It does not provide + * The @timestamp_ns is read from %CLOCK_MONOTONIC and is intended to allow + * the accurate measurement of the time between events. It does not provide * the wall-clock time. - * @id: event identifier with value from enum gpio_v2_line_event_id + * @id: event identifier with value from &enum gpio_v2_line_event_id * @offset: the offset of the line that triggered the event * @seqno: the sequence number for this event in the sequence of events for * all the lines in this line request @@ -291,7 +292,7 @@ struct gpio_v2_line_event { }; /* - * ABI v1 + * ABI v1 * * This version of the ABI is deprecated. * Use the latest version of the ABI, defined above, instead. @@ -314,13 +315,13 @@ struct gpio_v2_line_event { * @flags: various flags for this line * @name: the name of this GPIO line, such as the output pin of the line on the * chip, a rail or a pin header name on a board, as specified by the gpio - * chip, may be empty + * chip, may be empty (i.e. name[0] == '\0') * @consumer: a functional name for the consumer of this GPIO line as set by * whatever is using it, will be empty if there is no current user but may * also be empty if the consumer doesn't set this up * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_info instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_info instead. */ struct gpioline_info { __u32 line_offset; @@ -344,17 +345,18 @@ enum { * of a GPIO line * @info: updated line information * @timestamp: estimate of time of status change occurrence, in nanoseconds - * @event_type: one of GPIOLINE_CHANGED_REQUESTED, GPIOLINE_CHANGED_RELEASED - * and GPIOLINE_CHANGED_CONFIG + * @event_type: one of %GPIOLINE_CHANGED_REQUESTED, + * %GPIOLINE_CHANGED_RELEASED and %GPIOLINE_CHANGED_CONFIG + * @padding: reserved for future use * - * Note: struct gpioline_info embedded here has 32-bit alignment on its own, + * The &struct gpioline_info embedded here has 32-bit alignment on its own, * but it works fine with 64-bit alignment too. With its 72 byte size, we can * guarantee there are no implicit holes between it and subsequent members. * The 20-byte padding at the end makes sure we don't add any implicit padding * at the end of the structure on 64-bit architectures. * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_info_changed instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_info_changed instead. */ struct gpioline_info_changed { struct gpioline_info info; @@ -378,13 +380,13 @@ struct gpioline_info_changed { * @lineoffsets: an array of desired lines, specified by offset index for the * associated GPIO device * @flags: desired flags for the desired GPIO lines, such as - * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed + * %GPIOHANDLE_REQUEST_OUTPUT, %GPIOHANDLE_REQUEST_ACTIVE_LOW etc, added * together. Note that even if multiple lines are requested, the same flags * must be applicable to all of them, if you want lines with individual * flags set, request them one by one. It is possible to select * a batch of input or output lines, but they must all have the same * characteristics, i.e. all inputs or all outputs, all active low etc - * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set for a requested + * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set for a requested * line, this specifies the default output value, should be 0 (low) or * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high) * @consumer_label: a desired consumer label for the selected GPIO line(s) @@ -392,11 +394,11 @@ struct gpioline_info_changed { * @lines: number of lines requested in this request, i.e. the number of * valid fields in the above arrays, set to 1 to request a single line * @fd: if successful this field will contain a valid anonymous file handle - * after a GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value + * after a %GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value * means error * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_request instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_request instead. */ struct gpiohandle_request { __u32 lineoffsets[GPIOHANDLES_MAX]; @@ -410,15 +412,15 @@ struct gpiohandle_request { /** * struct gpiohandle_config - Configuration for a GPIO handle request * @flags: updated flags for the requested GPIO lines, such as - * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed + * %GPIOHANDLE_REQUEST_OUTPUT, %GPIOHANDLE_REQUEST_ACTIVE_LOW etc, added * together - * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set in flags, + * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set in flags, * this specifies the default output value, should be 0 (low) or * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high) * @padding: reserved for future use and should be zero filled * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_config instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_config instead. */ struct gpiohandle_config { __u32 flags; @@ -432,8 +434,8 @@ struct gpiohandle_config { * state of a line, when setting the state of lines these should contain * the desired target state * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_values instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_values instead. */ struct gpiohandle_data { __u8 values[GPIOHANDLES_MAX]; @@ -449,17 +451,17 @@ struct gpiohandle_data { * @lineoffset: the desired line to subscribe to events from, specified by * offset index for the associated GPIO device * @handleflags: desired handle flags for the desired GPIO line, such as - * GPIOHANDLE_REQUEST_ACTIVE_LOW or GPIOHANDLE_REQUEST_OPEN_DRAIN + * %GPIOHANDLE_REQUEST_ACTIVE_LOW or %GPIOHANDLE_REQUEST_OPEN_DRAIN * @eventflags: desired flags for the desired GPIO event line, such as - * GPIOEVENT_REQUEST_RISING_EDGE or GPIOEVENT_REQUEST_FALLING_EDGE + * %GPIOEVENT_REQUEST_RISING_EDGE or %GPIOEVENT_REQUEST_FALLING_EDGE * @consumer_label: a desired consumer label for the selected GPIO line(s) * such as "my-listener" * @fd: if successful this field will contain a valid anonymous file handle - * after a GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value + * after a %GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value * means error * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_request instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_request instead. */ struct gpioevent_request { __u32 lineoffset; @@ -469,7 +471,7 @@ struct gpioevent_request { int fd; }; -/** +/* * GPIO event types */ #define GPIOEVENT_EVENT_RISING_EDGE 0x01 @@ -480,8 +482,8 @@ struct gpioevent_request { * @timestamp: best estimate of time of event occurrence, in nanoseconds * @id: event identifier * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_event instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_event instead. */ struct gpioevent_data { __u64 timestamp; diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 8300cc29dec8..8d16744edc31 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -1058,4 +1058,6 @@ enum ovs_dec_ttl_attr { __OVS_DEC_TTL_ATTR_MAX }; +#define OVS_DEC_TTL_ATTR_MAX (__OVS_DEC_TTL_ATTR_MAX - 1) + #endif /* _LINUX_OPENVSWITCH_H */ diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 82cc58fe9368..1500a0f58041 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -171,9 +171,12 @@ struct statx { * be of use to ordinary userspace programs such as GUIs or ls rather than * specialised tools. * - * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS + * Note that the flags marked [I] correspond to the FS_IOC_SETFLAGS flags * semantically. Where possible, the numerical value is picked to correspond - * also. + * also. Note that the DAX attribute indicates that the file is in the CPU + * direct access state. It does not correspond to the per-inode flag that + * some filesystems support. + * */ #define STATX_ATTR_COMPRESSED 0x00000004 /* [I] File is compressed by the fs */ #define STATX_ATTR_IMMUTABLE 0x00000010 /* [I] File is marked immutable */ @@ -183,7 +186,7 @@ struct statx { #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ -#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */ +#define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 9bc5bc07d4d3..b9c937b3a149 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -198,6 +198,23 @@ void gnttab_free_auto_xlat_frames(void); int gnttab_alloc_pages(int nr_pages, struct page **pages); void gnttab_free_pages(int nr_pages, struct page **pages); +struct gnttab_page_cache { + spinlock_t lock; +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC + struct page *pages; +#else + struct list_head pages; +#endif + unsigned int num_pages; +}; + +void gnttab_page_cache_init(struct gnttab_page_cache *cache); +int gnttab_page_cache_get(struct gnttab_page_cache *cache, struct page **page); +void gnttab_page_cache_put(struct gnttab_page_cache *cache, struct page **page, + unsigned int num); +void gnttab_page_cache_shrink(struct gnttab_page_cache *cache, + unsigned int num); + #ifdef CONFIG_XEN_GRANT_DMA_ALLOC struct gnttab_dma_alloc_args { /* Device for which DMA memory will be/was allocated. */ diff --git a/init/Kconfig b/init/Kconfig index c9446911cf41..0872a5a2e759 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -47,6 +47,10 @@ config CLANG_VERSION int default $(shell,$(srctree)/scripts/clang-version.sh $(CC)) +config LLD_VERSION + int + default $(shell,$(srctree)/scripts/lld-version.sh $(LD)) + config CC_CAN_LINK bool default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(m64-flag)) if 64BIT @@ -719,7 +723,7 @@ config LOG_CPU_MAX_BUF_SHIFT with more CPUs. Therefore this value is used only when the sum of contributions is greater than the half of the default kernel ring buffer as defined by LOG_BUF_SHIFT. The default values are set - so that more than 64 CPUs are needed to trigger the allocation. + so that more than 16 CPUs are needed to trigger the allocation. Also this option is ignored when "log_buf_len" kernel parameter is used as it forces an exact (power of two) size of the ring buffer. @@ -1348,6 +1352,12 @@ config LD_DEAD_CODE_DATA_ELIMINATION present. This option is not well tested yet, so use at your own risk. +config LD_ORPHAN_WARN + def_bool y + depends on ARCH_WANT_LD_ORPHAN_WARN + depends on !LD_IS_LLD || LLD_VERSION >= 110000 + depends on $(ld-option,--orphan-handling=warn) + config SYSCTL bool diff --git a/init/initramfs.c b/init/initramfs.c index 1f97c0328a7a..55b74d7e5260 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -535,7 +535,7 @@ extern unsigned long __initramfs_size; #include <linux/initrd.h> #include <linux/kexec.h> -void __weak free_initrd_mem(unsigned long start, unsigned long end) +void __weak __init free_initrd_mem(unsigned long start, unsigned long end) { #ifdef CONFIG_ARCH_KEEP_MEMBLOCK unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE); diff --git a/init/main.c b/init/main.c index 130376ec10ba..32b2a8affafd 100644 --- a/init/main.c +++ b/init/main.c @@ -269,17 +269,27 @@ static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) u32 size, csum; char *data; u32 *hdr; + int i; if (!initrd_end) return NULL; data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; - if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) - return NULL; + /* + * Since Grub may align the size of initrd to 4, we must + * check the preceding 3 bytes as well. + */ + for (i = 0; i < 4; i++) { + if (!memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) + goto found; + data--; + } + return NULL; +found: hdr = (u32 *)(data - 8); - size = hdr[0]; - csum = hdr[1]; + size = le32_to_cpu(hdr[0]); + csum = le32_to_cpu(hdr[1]); data = ((void *)hdr) - size; if ((unsigned long)data < initrd_start) { diff --git a/kernel/Makefile b/kernel/Makefile index af601b9bda0e..6c9f19911be0 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -97,7 +97,6 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o obj-$(CONFIG_TRACEPOINTS) += tracepoint.o obj-$(CONFIG_LATENCYTOP) += latencytop.o -obj-$(CONFIG_ELFCORE) += elfcore.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_TRACE_CLOCK) += trace/ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index bdc8cd1b6767..c1b9f71ee6aa 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,6 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 obj-y := core.o -CFLAGS_core.o += $(call cc-disable-warning, override-init) +ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y) +# ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details +cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse +endif +CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 78ea8a7bd27f..56cc5a915f67 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -13,6 +13,7 @@ #include <linux/bpf_verifier.h> #include <net/bpf_sk_storage.h> #include <linux/bpf_local_storage.h> +#include <linux/btf_ids.h> /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. @@ -26,7 +27,11 @@ noinline RET bpf_lsm_##NAME(__VA_ARGS__) \ #include <linux/lsm_hook_defs.h> #undef LSM_HOOK -#define BPF_LSM_SYM_PREFX "bpf_lsm_" +#define LSM_HOOK(RET, DEFAULT, NAME, ...) BTF_ID(func, bpf_lsm_##NAME) +BTF_SET_START(bpf_lsm_hooks) +#include <linux/lsm_hook_defs.h> +#undef LSM_HOOK +BTF_SET_END(bpf_lsm_hooks) int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog) @@ -37,8 +42,7 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, return -EINVAL; } - if (strncmp(BPF_LSM_SYM_PREFX, prog->aux->attach_func_name, - sizeof(BPF_LSM_SYM_PREFX) - 1)) { + if (!btf_id_set_contains(&bpf_lsm_hooks, prog->aux->attach_btf_id)) { bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n", prog->aux->attach_btf_id, prog->aux->attach_func_name); return -EINVAL; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9268d77898b7..55454d2278b1 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1369,7 +1369,7 @@ u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) * * Decode and execute eBPF instructions. */ -static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) +static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) { #define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 1815e97d4c9c..1fccba6e88c4 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -821,6 +821,32 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, } } +static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr, + void *value, bool onallcpus) +{ + /* When using prealloc and not setting the initial value on all cpus, + * zero-fill element values for other cpus (just as what happens when + * not using prealloc). Otherwise, bpf program has no way to ensure + * known initial values for cpus other than current one + * (onallcpus=false always when coming from bpf prog). + */ + if (htab_is_prealloc(htab) && !onallcpus) { + u32 size = round_up(htab->map.value_size, 8); + int current_cpu = raw_smp_processor_id(); + int cpu; + + for_each_possible_cpu(cpu) { + if (cpu == current_cpu) + bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value, + size); + else + memset(per_cpu_ptr(pptr, cpu), 0, size); + } + } else { + pcpu_copy_value(htab, pptr, value, onallcpus); + } +} + static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab) { return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS && @@ -891,7 +917,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, } } - pcpu_copy_value(htab, pptr, value, onallcpus); + pcpu_init_value(htab, pptr, value, onallcpus); if (!prealloc) htab_elem_set_ptr(l_new, key_size, pptr); @@ -1183,7 +1209,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size), value, onallcpus); } else { - pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size), + pcpu_init_value(htab, htab_elem_get_ptr(l_new, key_size), value, onallcpus); hlist_nulls_add_head_rcu(&l_new->hash_node, head); l_new = NULL; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 25520f5eeaf6..deda1185237b 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -717,9 +717,9 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_snprintf_btf_proto; case BPF_FUNC_jiffies64: return &bpf_jiffies64_proto; - case BPF_FUNC_bpf_per_cpu_ptr: + case BPF_FUNC_per_cpu_ptr: return &bpf_per_cpu_ptr_proto; - case BPF_FUNC_bpf_this_cpu_ptr: + case BPF_FUNC_this_cpu_ptr: return &bpf_this_cpu_ptr_proto; default: break; diff --git a/kernel/bpf/preload/Kconfig b/kernel/bpf/preload/Kconfig index ace49111d3a3..26bced262473 100644 --- a/kernel/bpf/preload/Kconfig +++ b/kernel/bpf/preload/Kconfig @@ -6,6 +6,7 @@ config USERMODE_DRIVER menuconfig BPF_PRELOAD bool "Preload BPF file system with kernel specific program and map iterators" depends on BPF + depends on BPF_SYSCALL # The dependency on !COMPILE_TEST prevents it from being enabled # in allmodconfig or allyesconfig configurations depends on !COMPILE_TEST diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6200519582a6..53fe6ef6d931 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1298,9 +1298,7 @@ static void __reg_combine_32_into_64(struct bpf_reg_state *reg) static bool __reg64_bound_s32(s64 a) { - if (a > S32_MIN && a < S32_MAX) - return true; - return false; + return a > S32_MIN && a < S32_MAX; } static bool __reg64_bound_u32(u64 a) @@ -1314,10 +1312,10 @@ static void __reg_combine_64_into_32(struct bpf_reg_state *reg) { __mark_reg32_unbounded(reg); - if (__reg64_bound_s32(reg->smin_value)) + if (__reg64_bound_s32(reg->smin_value) && __reg64_bound_s32(reg->smax_value)) { reg->s32_min_value = (s32)reg->smin_value; - if (__reg64_bound_s32(reg->smax_value)) reg->s32_max_value = (s32)reg->smax_value; + } if (__reg64_bound_u32(reg->umin_value)) reg->u32_min_value = (u32)reg->umin_value; if (__reg64_bound_u32(reg->umax_value)) @@ -4895,6 +4893,8 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, ret_reg->smax_value = meta->msize_max_value; ret_reg->s32_max_value = meta->msize_max_value; + ret_reg->smin_value = -MAX_ERRNO; + ret_reg->s32_min_value = -MAX_ERRNO; __reg_deduce_bounds(ret_reg); __reg_bound_offset(ret_reg); __update_reg_bounds(ret_reg); @@ -7786,9 +7786,11 @@ static int check_return_code(struct bpf_verifier_env *env) struct tnum range = tnum_range(0, 1); enum bpf_prog_type prog_type = resolve_prog_type(env->prog); int err; + const bool is_subprog = env->cur_state->frame[0]->subprogno; /* LSM and struct_ops func-ptr's return type could be "void" */ - if ((prog_type == BPF_PROG_TYPE_STRUCT_OPS || + if (!is_subprog && + (prog_type == BPF_PROG_TYPE_STRUCT_OPS || prog_type == BPF_PROG_TYPE_LSM) && !prog->aux->attach_func_proto->type) return 0; @@ -7808,6 +7810,16 @@ static int check_return_code(struct bpf_verifier_env *env) return -EACCES; } + reg = cur_regs(env) + BPF_REG_0; + if (is_subprog) { + if (reg->type != SCALAR_VALUE) { + verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n", + reg_type_str[reg->type]); + return -EINVAL; + } + return 0; + } + switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || @@ -7861,7 +7873,6 @@ static int check_return_code(struct bpf_verifier_env *env) return 0; } - reg = cur_regs(env) + BPF_REG_0; if (reg->type != SCALAR_VALUE) { verbose(env, "At program exit the register R0 is not a known value (%s)\n", reg_type_str[reg->type]); @@ -9572,12 +9583,13 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_insn_aux_data *aux) { - u32 datasec_id, type, id = insn->imm; const struct btf_var_secinfo *vsi; const struct btf_type *datasec; const struct btf_type *t; const char *sym_name; bool percpu = false; + u32 type, id = insn->imm; + s32 datasec_id; u64 addr; int i; diff --git a/kernel/cpu.c b/kernel/cpu.c index 6ff2578ecf17..2b8d7a5db383 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -815,6 +815,10 @@ void __init cpuhp_threads_init(void) } #ifdef CONFIG_HOTPLUG_CPU +#ifndef arch_clear_mm_cpumask_cpu +#define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) +#endif + /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id @@ -850,7 +854,7 @@ void clear_tasks_mm_cpumask(int cpu) t = find_lock_task_mm(p); if (!t) continue; - cpumask_clear_cpu(cpu, mm_cpumask(t->mm)); + arch_clear_mm_cpumask_cpu(cpu, t->mm); task_unlock(t); } rcu_read_unlock(); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index b4eea0abc3f0..781b9dca197c 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -229,6 +229,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; } io_tlb_index = 0; + no_iotlb_memory = false; if (verbose) swiotlb_print_info(); @@ -260,9 +261,11 @@ swiotlb_init(int verbose) if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) return; - if (io_tlb_start) + if (io_tlb_start) { memblock_free_early(io_tlb_start, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + io_tlb_start = 0; + } pr_warn("Cannot allocate buffer"); no_iotlb_memory = true; } @@ -360,6 +363,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; } io_tlb_index = 0; + no_iotlb_memory = false; swiotlb_print_info(); @@ -441,14 +445,11 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr, } } -phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, - dma_addr_t tbl_dma_addr, - phys_addr_t orig_addr, - size_t mapping_size, - size_t alloc_size, - enum dma_data_direction dir, - unsigned long attrs) +phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr, + size_t mapping_size, size_t alloc_size, + enum dma_data_direction dir, unsigned long attrs) { + dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start); unsigned long flags; phys_addr_t tlb_addr; unsigned int nslots, stride, index, wrap; @@ -667,9 +668,8 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size, swiotlb_force); - swiotlb_addr = swiotlb_tbl_map_single(dev, - phys_to_dma_unencrypted(dev, io_tlb_start), - paddr, size, size, dir, attrs); + swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir, + attrs); if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; diff --git a/kernel/elfcore.c b/kernel/elfcore.c deleted file mode 100644 index 57fb4dcff434..000000000000 --- a/kernel/elfcore.c +++ /dev/null @@ -1,26 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/elf.h> -#include <linux/fs.h> -#include <linux/mm.h> -#include <linux/binfmts.h> -#include <linux/elfcore.h> - -Elf_Half __weak elf_core_extra_phdrs(void) -{ - return 0; -} - -int __weak elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) -{ - return 1; -} - -int __weak elf_core_write_extra_data(struct coredump_params *cprm) -{ - return 1; -} - -size_t __weak elf_core_extra_data_size(void) -{ - return 0; -} diff --git a/kernel/events/core.c b/kernel/events/core.c index 5a29ab09e72d..dc568ca295bd 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2312,9 +2312,6 @@ group_sched_out(struct perf_event *group_event, event_sched_out(event, cpuctx, ctx); perf_pmu_enable(ctx->pmu); - - if (group_event->attr.exclusive) - cpuctx->exclusive = 0; } #define DETACH_GROUP 0x01UL @@ -2583,11 +2580,8 @@ group_sched_in(struct perf_event *group_event, pmu->start_txn(pmu, PERF_PMU_TXN_ADD); - if (event_sched_in(group_event, cpuctx, ctx)) { - pmu->cancel_txn(pmu); - perf_mux_hrtimer_restart(cpuctx); - return -EAGAIN; - } + if (event_sched_in(group_event, cpuctx, ctx)) + goto error; /* * Schedule in siblings as one group (if any): @@ -2616,10 +2610,8 @@ group_error: } event_sched_out(group_event, cpuctx, ctx); +error: pmu->cancel_txn(pmu); - - perf_mux_hrtimer_restart(cpuctx); - return -EAGAIN; } @@ -2645,7 +2637,7 @@ static int group_can_go_on(struct perf_event *event, * If this group is exclusive and there are already * events on the CPU, it can't go on. */ - if (event->attr.exclusive && cpuctx->active_oncpu) + if (event->attr.exclusive && !list_empty(get_event_list(event))) return 0; /* * Otherwise, try to add it if all previous groups were able @@ -3679,6 +3671,7 @@ static int merge_sched_in(struct perf_event *event, void *data) *can_add_hw = 0; ctx->rotate_necessary = 1; + perf_mux_hrtimer_restart(cpuctx); } return 0; @@ -6374,14 +6367,13 @@ perf_output_sample_regs(struct perf_output_handle *handle, } static void perf_sample_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { if (user_mode(regs)) { regs_user->abi = perf_reg_abi(current); regs_user->regs = regs; } else if (!(current->flags & PF_KTHREAD)) { - perf_get_regs_user(regs_user, regs, regs_user_copy); + perf_get_regs_user(regs_user, regs); } else { regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE; regs_user->regs = NULL; @@ -7083,8 +7075,7 @@ void perf_prepare_sample(struct perf_event_header *header, } if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER)) - perf_sample_regs_user(&data->regs_user, regs, - &data->regs_user_copy); + perf_sample_regs_user(&data->regs_user, regs); if (sample_type & PERF_SAMPLE_REGS_USER) { /* regs dump ABI info */ @@ -7186,6 +7177,7 @@ __perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs, int (*output_begin)(struct perf_output_handle *, + struct perf_sample_data *, struct perf_event *, unsigned int)) { @@ -7198,7 +7190,7 @@ __perf_event_output(struct perf_event *event, perf_prepare_sample(&header, data, event, regs); - err = output_begin(&handle, event, header.size); + err = output_begin(&handle, data, event, header.size); if (err) goto exit; @@ -7264,7 +7256,7 @@ perf_event_read_event(struct perf_event *event, int ret; perf_event_header__init_id(&read_event.header, &sample, event); - ret = perf_output_begin(&handle, event, read_event.header.size); + ret = perf_output_begin(&handle, &sample, event, read_event.header.size); if (ret) return; @@ -7533,7 +7525,7 @@ static void perf_event_task_output(struct perf_event *event, perf_event_header__init_id(&task_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, task_event->event_id.header.size); if (ret) goto out; @@ -7636,7 +7628,7 @@ static void perf_event_comm_output(struct perf_event *event, return; perf_event_header__init_id(&comm_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, comm_event->event_id.header.size); if (ret) @@ -7736,7 +7728,7 @@ static void perf_event_namespaces_output(struct perf_event *event, perf_event_header__init_id(&namespaces_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, namespaces_event->event_id.header.size); if (ret) goto out; @@ -7863,7 +7855,7 @@ static void perf_event_cgroup_output(struct perf_event *event, void *data) perf_event_header__init_id(&cgroup_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, cgroup_event->event_id.header.size); if (ret) goto out; @@ -7989,7 +7981,7 @@ static void perf_event_mmap_output(struct perf_event *event, } perf_event_header__init_id(&mmap_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, mmap_event->event_id.header.size); if (ret) goto out; @@ -8299,7 +8291,7 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head, int ret; perf_event_header__init_id(&rec.header, &sample, event); - ret = perf_output_begin(&handle, event, rec.header.size); + ret = perf_output_begin(&handle, &sample, event, rec.header.size); if (ret) return; @@ -8333,7 +8325,7 @@ void perf_log_lost_samples(struct perf_event *event, u64 lost) perf_event_header__init_id(&lost_samples_event.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, lost_samples_event.header.size); if (ret) return; @@ -8388,7 +8380,7 @@ static void perf_event_switch_output(struct perf_event *event, void *data) perf_event_header__init_id(&se->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, se->event_id.header.size); + ret = perf_output_begin(&handle, &sample, event, se->event_id.header.size); if (ret) return; @@ -8463,7 +8455,7 @@ static void perf_log_throttle(struct perf_event *event, int enable) perf_event_header__init_id(&throttle_event.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, throttle_event.header.size); if (ret) return; @@ -8506,7 +8498,7 @@ static void perf_event_ksymbol_output(struct perf_event *event, void *data) perf_event_header__init_id(&ksymbol_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, ksymbol_event->event_id.header.size); if (ret) return; @@ -8596,7 +8588,7 @@ static void perf_event_bpf_output(struct perf_event *event, void *data) perf_event_header__init_id(&bpf_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, data, event, bpf_event->event_id.header.size); if (ret) return; @@ -8705,7 +8697,8 @@ static void perf_event_text_poke_output(struct perf_event *event, void *data) perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size); + ret = perf_output_begin(&handle, &sample, event, + text_poke_event->event_id.header.size); if (ret) return; @@ -8786,7 +8779,7 @@ static void perf_log_itrace_start(struct perf_event *event) rec.tid = perf_event_tid(event, current); perf_event_header__init_id(&rec.header, &sample, event); - ret = perf_output_begin(&handle, event, rec.header.size); + ret = perf_output_begin(&handle, &sample, event, rec.header.size); if (ret) return; diff --git a/kernel/events/internal.h b/kernel/events/internal.h index fcbf5616a441..228801e20788 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -205,16 +205,12 @@ DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user) static inline int get_recursion_context(int *recursion) { - int rctx; - - if (unlikely(in_nmi())) - rctx = 3; - else if (in_irq()) - rctx = 2; - else if (in_softirq()) - rctx = 1; - else - rctx = 0; + unsigned int pc = preempt_count(); + unsigned char rctx = 0; + + rctx += !!(pc & (NMI_MASK)); + rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK)); + rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)); if (recursion[rctx]) return -1; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 192b8abc6330..ef91ae75ca56 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -147,6 +147,7 @@ ring_buffer_has_space(unsigned long head, unsigned long tail, static __always_inline int __perf_output_begin(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size, bool backward) { @@ -237,18 +238,16 @@ __perf_output_begin(struct perf_output_handle *handle, handle->size = (1UL << page_shift) - offset; if (unlikely(have_lost)) { - struct perf_sample_data sample_data; - lost_event.header.size = sizeof(lost_event); lost_event.header.type = PERF_RECORD_LOST; lost_event.header.misc = 0; lost_event.id = event->id; lost_event.lost = local_xchg(&rb->lost, 0); - perf_event_header__init_id(&lost_event.header, - &sample_data, event); + /* XXX mostly redundant; @data is already fully initializes */ + perf_event_header__init_id(&lost_event.header, data, event); perf_output_put(handle, lost_event); - perf_event__output_id_sample(event, handle, &sample_data); + perf_event__output_id_sample(event, handle, data); } return 0; @@ -263,22 +262,25 @@ out: } int perf_output_begin_forward(struct perf_output_handle *handle, - struct perf_event *event, unsigned int size) + struct perf_sample_data *data, + struct perf_event *event, unsigned int size) { - return __perf_output_begin(handle, event, size, false); + return __perf_output_begin(handle, data, event, size, false); } int perf_output_begin_backward(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size) { - return __perf_output_begin(handle, event, size, true); + return __perf_output_begin(handle, data, event, size, true); } int perf_output_begin(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size) { - return __perf_output_begin(handle, event, size, + return __perf_output_begin(handle, data, event, size, unlikely(is_write_backward(event))); } diff --git a/kernel/exit.c b/kernel/exit.c index 87a2d515de0d..1f236ed375f8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -454,7 +454,10 @@ static void exit_mm(void) mmap_read_unlock(mm); self.task = current; - self.next = xchg(&core_state->dumper.next, &self); + if (self.task->flags & PF_SIGNALED) + self.next = xchg(&core_state->dumper.next, &self); + else + self.task = NULL; /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. diff --git a/kernel/fail_function.c b/kernel/fail_function.c index 63b349168da7..b0b1ad93fa95 100644 --- a/kernel/fail_function.c +++ b/kernel/fail_function.c @@ -253,7 +253,7 @@ static ssize_t fei_write(struct file *file, const char __user *buffer, if (copy_from_user(buf, buffer, count)) { ret = -EFAULT; - goto out; + goto out_free; } buf[count] = '\0'; sym = strstrip(buf); @@ -307,8 +307,9 @@ static ssize_t fei_write(struct file *file, const char __user *buffer, ret = count; } out: - kfree(buf); mutex_unlock(&fei_lock); +out_free: + kfree(buf); return ret; } diff --git a/kernel/futex.c b/kernel/futex.c index ac328874f6e5..00259c7e288e 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -788,8 +788,9 @@ static void put_pi_state(struct futex_pi_state *pi_state) */ if (pi_state->owner) { struct task_struct *owner; + unsigned long flags; - raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags); owner = pi_state->owner; if (owner) { raw_spin_lock(&owner->pi_lock); @@ -797,7 +798,7 @@ static void put_pi_state(struct futex_pi_state *pi_state) raw_spin_unlock(&owner->pi_lock); } rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); - raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags); } if (current->pi_state_cache) { diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index cf8b374b892d..e4ca69608f3b 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -624,17 +624,19 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain) EXPORT_SYMBOL_GPL(irq_create_direct_mapping); /** - * irq_create_mapping() - Map a hardware interrupt into linux irq space + * irq_create_mapping_affinity() - Map a hardware interrupt into linux irq space * @domain: domain owning this hardware interrupt or NULL for default domain * @hwirq: hardware irq number in that domain space + * @affinity: irq affinity * * Only one mapping per hardware interrupt is permitted. Returns a linux * irq number. * If the sense/trigger is to be specified, set_irq_type() should be called * on the number returned from that call. */ -unsigned int irq_create_mapping(struct irq_domain *domain, - irq_hw_number_t hwirq) +unsigned int irq_create_mapping_affinity(struct irq_domain *domain, + irq_hw_number_t hwirq, + const struct irq_affinity_desc *affinity) { struct device_node *of_node; int virq; @@ -660,7 +662,8 @@ unsigned int irq_create_mapping(struct irq_domain *domain, } /* Allocate a virtual interrupt number */ - virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), NULL); + virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), + affinity); if (virq <= 0) { pr_debug("-> virq allocation failed\n"); return 0; @@ -676,7 +679,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain, return virq; } -EXPORT_SYMBOL_GPL(irq_create_mapping); +EXPORT_SYMBOL_GPL(irq_create_mapping_affinity); /** * irq_create_strict_mappings() - Map a range of hw irqs to fixed linux irqs diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index b71ad8d9f1c9..c1418b47f625 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -108,19 +108,21 @@ static inline void lockdep_lock(void) { DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + __this_cpu_inc(lockdep_recursion); arch_spin_lock(&__lock); __owner = current; - __this_cpu_inc(lockdep_recursion); } static inline void lockdep_unlock(void) { + DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + if (debug_locks && DEBUG_LOCKS_WARN_ON(__owner != current)) return; - __this_cpu_dec(lockdep_recursion); __owner = NULL; arch_spin_unlock(&__lock); + __this_cpu_dec(lockdep_recursion); } static inline bool lockdep_assert_locked(void) @@ -2765,7 +2767,9 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, * (Note that this has to be done separately, because the graph cannot * detect such classes of deadlocks.) * - * Returns: 0 on deadlock detected, 1 on OK, 2 on recursive read + * Returns: 0 on deadlock detected, 1 on OK, 2 if another lock with the same + * lock class is held but nest_lock is also held, i.e. we rely on the + * nest_lock to avoid the deadlock. */ static int check_deadlock(struct task_struct *curr, struct held_lock *next) @@ -2788,7 +2792,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next) * lock class (i.e. read_lock(lock)+read_lock(lock)): */ if ((next->read == 2) && prev->read) - return 2; + continue; /* * We're holding the nest_lock, which serializes this lock's @@ -3593,15 +3597,12 @@ static int validate_chain(struct task_struct *curr, if (!ret) return 0; /* - * Mark recursive read, as we jump over it when - * building dependencies (just like we jump over - * trylock entries): - */ - if (ret == 2) - hlock->read = 2; - /* * Add dependency only if this lock is not the head - * of the chain, and if it's not a secondary read-lock: + * of the chain, and if the new lock introduces no more + * lock dependency (because we already hold a lock with the + * same lock class) nor deadlock (because the nest_lock + * serializes nesting locks), see the comments for + * check_deadlock(). */ if (!chain_head && ret != 2) { if (!check_prevs_add(curr, hlock)) diff --git a/kernel/panic.c b/kernel/panic.c index 396142ee43fd..332736a72a58 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -605,7 +605,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint, panic("panic_on_warn set ...\n"); } - dump_stack(); + if (!regs) + dump_stack(); print_irqtrace_events(current); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index fe64a49344bf..bc1e3b5a97bd 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -528,8 +528,8 @@ static int log_store(u32 caller_id, int facility, int level, if (dev_info) memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info)); - /* insert message */ - if ((flags & LOG_CONT) || !(flags & LOG_NEWLINE)) + /* A message without a trailing newline can be continued. */ + if (!(flags & LOG_NEWLINE)) prb_commit(&e); else prb_final_commit(&e); diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c index 6b1525685277..74e25a1704f2 100644 --- a/kernel/printk/printk_ringbuffer.c +++ b/kernel/printk/printk_ringbuffer.c @@ -882,8 +882,6 @@ static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out) head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */ do { - desc = to_desc(desc_ring, head_id); - id = DESC_ID(head_id + 1); id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 43d6179508d6..79de1294f8eb 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -264,17 +264,11 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) return ret; } -static bool ptrace_has_cap(const struct cred *cred, struct user_namespace *ns, - unsigned int mode) +static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { - int ret; - if (mode & PTRACE_MODE_NOAUDIT) - ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT); - else - ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NONE); - - return ret == 0; + return ns_capable_noaudit(ns, CAP_SYS_PTRACE); + return ns_capable(ns, CAP_SYS_PTRACE); } /* Returns 0 on success, -errno on denial. */ @@ -326,7 +320,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; - if (ptrace_has_cap(cred, tcred->user_ns, mode)) + if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; @@ -345,7 +339,7 @@ ok: mm = task->mm; if (mm && ((get_dumpable(mm) != SUID_DUMP_USER) && - !ptrace_has_cap(cred, mm->user_ns, mode))) + !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; return security_ptrace_access_check(task, mode); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 2a52f42f64b6..bd04b09b84b3 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4077,7 +4077,6 @@ void rcu_cpu_starting(unsigned int cpu) smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ } -#ifdef CONFIG_HOTPLUG_CPU /* * The outgoing function has no further need of RCU, so remove it from * the rcu_node tree's ->qsmaskinitnext bit masks. @@ -4117,6 +4116,7 @@ void rcu_report_dead(unsigned int cpu) rdp->cpu_started = false; } +#ifdef CONFIG_HOTPLUG_CPU /* * The outgoing CPU has just passed through the dying-idle state, and we * are being invoked from the CPU that was IPIed to continue the offline diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 0fde39b8daab..ca21d28a0f98 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -249,13 +249,16 @@ static bool check_slow_task(struct task_struct *t, void *arg) /* * Scan the current list of tasks blocked within RCU read-side critical - * sections, printing out the tid of each. + * sections, printing out the tid of each of the first few of them. */ -static int rcu_print_task_stall(struct rcu_node *rnp) +static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags) + __releases(rnp->lock) { + int i = 0; int ndetected = 0; struct rcu_stall_chk_rdr rscr; struct task_struct *t; + struct task_struct *ts[8]; if (!rcu_preempt_blocked_readers_cgp(rnp)) return 0; @@ -264,6 +267,14 @@ static int rcu_print_task_stall(struct rcu_node *rnp) t = list_entry(rnp->gp_tasks->prev, struct task_struct, rcu_node_entry); list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { + get_task_struct(t); + ts[i++] = t; + if (i >= ARRAY_SIZE(ts)) + break; + } + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + for (i--; i; i--) { + t = ts[i]; if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr)) pr_cont(" P%d", t->pid); else @@ -273,6 +284,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp) ".q"[rscr.rs.b.need_qs], ".e"[rscr.rs.b.exp_hint], ".l"[rscr.on_blkd_list]); + put_task_struct(t); ndetected++; } pr_cont("\n"); @@ -293,8 +305,9 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) * Because preemptible RCU does not exist, we never have to check for * tasks blocked within RCU read-side critical sections. */ -static int rcu_print_task_stall(struct rcu_node *rnp) +static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags) { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ @@ -472,7 +485,6 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name); rcu_for_each_leaf_node(rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); - ndetected += rcu_print_task_stall(rnp); if (rnp->qsmask != 0) { for_each_leaf_node_possible_cpu(rnp, cpu) if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) { @@ -480,7 +492,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) ndetected++; } } - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + ndetected += rcu_print_task_stall(rnp, flags); // Releases rnp->lock. } for_each_possible_cpu(cpu) diff --git a/kernel/reboot.c b/kernel/reboot.c index e7b78d5ae1ab..af6f23d8bea1 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -551,22 +551,22 @@ static int __init reboot_setup(char *str) break; case 's': - { - int rc; - - if (isdigit(*(str+1))) { - rc = kstrtoint(str+1, 0, &reboot_cpu); - if (rc) - return rc; - } else if (str[1] == 'm' && str[2] == 'p' && - isdigit(*(str+3))) { - rc = kstrtoint(str+3, 0, &reboot_cpu); - if (rc) - return rc; - } else + if (isdigit(*(str+1))) + reboot_cpu = simple_strtoul(str+1, NULL, 0); + else if (str[1] == 'm' && str[2] == 'p' && + isdigit(*(str+3))) + reboot_cpu = simple_strtoul(str+3, NULL, 0); + else *mode = REBOOT_SOFT; + if (reboot_cpu >= num_possible_cpus()) { + pr_err("Ignoring the CPU number in reboot= option. " + "CPU %d exceeds possible cpu number %d\n", + reboot_cpu, num_possible_cpus()); + reboot_cpu = 0; + break; + } break; - } + case 'g': *mode = REBOOT_GPIO; break; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d2003a7d5ab5..e7e453492cff 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2501,7 +2501,12 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, #ifdef CONFIG_SMP if (wake_flags & WF_MIGRATED) en_flags |= ENQUEUE_MIGRATED; + else #endif + if (p->in_iowait) { + delayacct_blkio_end(p); + atomic_dec(&task_rq(p)->nr_iowait); + } activate_task(rq, p, en_flags); ttwu_do_wakeup(rq, p, wake_flags, rf); @@ -2888,11 +2893,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags)) goto unlock; - if (p->in_iowait) { - delayacct_blkio_end(p); - atomic_dec(&task_rq(p)->nr_iowait); - } - #ifdef CONFIG_SMP /* * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be @@ -2963,6 +2963,11 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); if (task_cpu(p) != cpu) { + if (p->in_iowait) { + delayacct_blkio_end(p); + atomic_dec(&task_rq(p)->nr_iowait); + } + wake_flags |= WF_MIGRATED; psi_ttwu_dequeue(p); set_task_cpu(p, cpu); @@ -4907,20 +4912,21 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) if (!dl_prio(p->normal_prio) || (pi_task && dl_prio(pi_task->prio) && dl_entity_preempt(&pi_task->dl, &p->dl))) { - p->dl.dl_boosted = 1; + p->dl.pi_se = pi_task->dl.pi_se; queue_flag |= ENQUEUE_REPLENISH; - } else - p->dl.dl_boosted = 0; + } else { + p->dl.pi_se = &p->dl; + } p->sched_class = &dl_sched_class; } else if (rt_prio(prio)) { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + p->dl.pi_se = &p->dl; if (oldprio < prio) queue_flag |= ENQUEUE_HEAD; p->sched_class = &rt_sched_class; } else { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + p->dl.pi_se = &p->dl; if (rt_prio(oldprio)) p->rt.timeout = 0; p->sched_class = &fair_sched_class; diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index d73bccde2720..97d318b0cd0c 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -881,7 +881,7 @@ static void sugov_limits(struct cpufreq_policy *policy) struct cpufreq_governor schedutil_gov = { .name = "schedutil", .owner = THIS_MODULE, - .dynamic_switching = true, + .flags = CPUFREQ_GOV_DYNAMIC_SWITCHING, .init = sugov_init, .exit = sugov_exit, .start = sugov_start, diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index f232305dcefe..1d3c97268ec0 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -43,6 +43,28 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se) return !RB_EMPTY_NODE(&dl_se->rb_node); } +#ifdef CONFIG_RT_MUTEXES +static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se) +{ + return dl_se->pi_se; +} + +static inline bool is_dl_boosted(struct sched_dl_entity *dl_se) +{ + return pi_of(dl_se) != dl_se; +} +#else +static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se) +{ + return dl_se; +} + +static inline bool is_dl_boosted(struct sched_dl_entity *dl_se) +{ + return false; +} +#endif + #ifdef CONFIG_SMP static inline struct dl_bw *dl_bw_of(int i) { @@ -698,7 +720,7 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - WARN_ON(dl_se->dl_boosted); + WARN_ON(is_dl_boosted(dl_se)); WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline)); /* @@ -736,21 +758,20 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) * could happen are, typically, a entity voluntarily trying to overcome its * runtime, or it just underestimated it during sched_setattr(). */ -static void replenish_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se) +static void replenish_dl_entity(struct sched_dl_entity *dl_se) { struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - BUG_ON(pi_se->dl_runtime <= 0); + BUG_ON(pi_of(dl_se)->dl_runtime <= 0); /* * This could be the case for a !-dl task that is boosted. * Just go with full inherited parameters. */ if (dl_se->dl_deadline == 0) { - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } if (dl_se->dl_yielded && dl_se->runtime > 0) @@ -763,8 +784,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * arbitrary large. */ while (dl_se->runtime <= 0) { - dl_se->deadline += pi_se->dl_period; - dl_se->runtime += pi_se->dl_runtime; + dl_se->deadline += pi_of(dl_se)->dl_period; + dl_se->runtime += pi_of(dl_se)->dl_runtime; } /* @@ -778,8 +799,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, */ if (dl_time_before(dl_se->deadline, rq_clock(rq))) { printk_deferred_once("sched: DL replenish lagged too much\n"); - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } if (dl_se->dl_yielded) @@ -812,8 +833,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * task with deadline equal to period this is the same of using * dl_period instead of dl_deadline in the equation above. */ -static bool dl_entity_overflow(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se, u64 t) +static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t) { u64 left, right; @@ -835,9 +855,9 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, * of anything below microseconds resolution is actually fiction * (but still we want to give the user that illusion >;). */ - left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); + left = (pi_of(dl_se)->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); right = ((dl_se->deadline - t) >> DL_SCALE) * - (pi_se->dl_runtime >> DL_SCALE); + (pi_of(dl_se)->dl_runtime >> DL_SCALE); return dl_time_before(right, left); } @@ -922,24 +942,23 @@ static inline bool dl_is_implicit(struct sched_dl_entity *dl_se) * Please refer to the comments update_dl_revised_wakeup() function to find * more about the Revised CBS rule. */ -static void update_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se) +static void update_dl_entity(struct sched_dl_entity *dl_se) { struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); if (dl_time_before(dl_se->deadline, rq_clock(rq)) || - dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { + dl_entity_overflow(dl_se, rq_clock(rq))) { if (unlikely(!dl_is_implicit(dl_se) && !dl_time_before(dl_se->deadline, rq_clock(rq)) && - !dl_se->dl_boosted)){ + !is_dl_boosted(dl_se))) { update_dl_revised_wakeup(dl_se, rq); return; } - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } } @@ -1038,7 +1057,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * The task might have been boosted by someone else and might be in the * boosting/deboosting path, its not throttled. */ - if (dl_se->dl_boosted) + if (is_dl_boosted(dl_se)) goto unlock; /* @@ -1066,7 +1085,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * but do not enqueue -- wait for our wakeup to do that. */ if (!task_on_rq_queued(p)) { - replenish_dl_entity(dl_se, dl_se); + replenish_dl_entity(dl_se); goto unlock; } @@ -1156,7 +1175,7 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) if (dl_time_before(dl_se->deadline, rq_clock(rq)) && dl_time_before(rq_clock(rq), dl_next_period(dl_se))) { - if (unlikely(dl_se->dl_boosted || !start_dl_timer(p))) + if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p))) return; dl_se->dl_throttled = 1; if (dl_se->runtime > 0) @@ -1287,7 +1306,7 @@ throttle: dl_se->dl_overrun = 1; __dequeue_task_dl(rq, curr, 0); - if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr))) + if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr))) enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH); if (!is_leftmost(curr, &rq->dl)) @@ -1481,8 +1500,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se) } static void -enqueue_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se, int flags) +enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags) { BUG_ON(on_dl_rq(dl_se)); @@ -1493,9 +1511,9 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, */ if (flags & ENQUEUE_WAKEUP) { task_contending(dl_se, flags); - update_dl_entity(dl_se, pi_se); + update_dl_entity(dl_se); } else if (flags & ENQUEUE_REPLENISH) { - replenish_dl_entity(dl_se, pi_se); + replenish_dl_entity(dl_se); } else if ((flags & ENQUEUE_RESTORE) && dl_time_before(dl_se->deadline, rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) { @@ -1512,19 +1530,7 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se) static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) { - struct task_struct *pi_task = rt_mutex_get_top_task(p); - struct sched_dl_entity *pi_se = &p->dl; - - /* - * Use the scheduling parameters of the top pi-waiter task if: - * - we have a top pi-waiter which is a SCHED_DEADLINE task AND - * - our dl_boosted is set (i.e. the pi-waiter's (absolute) deadline is - * smaller than our deadline OR we are a !SCHED_DEADLINE task getting - * boosted due to a SCHED_DEADLINE pi-waiter). - * Otherwise we keep our runtime and deadline. - */ - if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) { - pi_se = &pi_task->dl; + if (is_dl_boosted(&p->dl)) { /* * Because of delays in the detection of the overrun of a * thread's runtime, it might be the case that a thread @@ -1557,7 +1563,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) * the throttle. */ p->dl.dl_throttled = 0; - BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH); + BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH); return; } @@ -1594,7 +1600,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) return; } - enqueue_dl_entity(&p->dl, pi_se, flags); + enqueue_dl_entity(&p->dl, flags); if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); @@ -2787,11 +2793,14 @@ void __dl_clear_params(struct task_struct *p) dl_se->dl_bw = 0; dl_se->dl_density = 0; - dl_se->dl_boosted = 0; dl_se->dl_throttled = 0; dl_se->dl_yielded = 0; dl_se->dl_non_contending = 0; dl_se->dl_overrun = 0; + +#ifdef CONFIG_RT_MUTEXES + dl_se->pi_se = dl_se; +#endif } bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 0655524700d2..2357921580f9 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -251,7 +251,7 @@ static int sd_ctl_doflags(struct ctl_table *table, int write, unsigned long flags = *(unsigned long *)table->data; size_t data_size = 0; size_t len = 0; - char *tmp; + char *tmp, *buf; int idx; if (write) @@ -269,17 +269,17 @@ static int sd_ctl_doflags(struct ctl_table *table, int write, return 0; } - tmp = kcalloc(data_size + 1, sizeof(*tmp), GFP_KERNEL); - if (!tmp) + buf = kcalloc(data_size + 1, sizeof(*buf), GFP_KERNEL); + if (!buf) return -ENOMEM; for_each_set_bit(idx, &flags, __SD_FLAG_CNT) { char *name = sd_flag_debug[idx].name; - len += snprintf(tmp + len, strlen(name) + 2, "%s ", name); + len += snprintf(buf + len, strlen(name) + 2, "%s ", name); } - tmp += *ppos; + tmp = buf + *ppos; len -= *ppos; if (len > *lenp) @@ -294,7 +294,7 @@ static int sd_ctl_doflags(struct ctl_table *table, int write, *lenp = len; *ppos += len; - kfree(tmp); + kfree(buf); return 0; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 290f9e38378c..ae7ceba8fd4f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5477,6 +5477,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; int idle_h_nr_running = task_has_idle_policy(p); + int task_new = !(flags & ENQUEUE_WAKEUP); /* * The code below (indirectly) updates schedutil which looks at @@ -5549,7 +5550,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) * into account, but that is not straightforward to implement, * and the following generally works well enough in practice. */ - if (flags & ENQUEUE_WAKEUP) + if (!task_new) update_overutilized_status(rq); enqueue_throttle: @@ -6172,21 +6173,21 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t static int select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) { - unsigned long best_cap = 0; + unsigned long task_util, best_cap = 0; int cpu, best_cpu = -1; struct cpumask *cpus; - sync_entity_load_avg(&p->se); - cpus = this_cpu_cpumask_var_ptr(select_idle_mask); cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); + task_util = uclamp_task_util(p); + for_each_cpu_wrap(cpu, cpus, target) { unsigned long cpu_cap = capacity_of(cpu); if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu)) continue; - if (task_fits_capacity(p, cpu_cap)) + if (fits_capacity(task_util, cpu_cap)) return cpu; if (cpu_cap > best_cap) { @@ -6198,44 +6199,42 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) return best_cpu; } +static inline bool asym_fits_capacity(int task_util, int cpu) +{ + if (static_branch_unlikely(&sched_asym_cpucapacity)) + return fits_capacity(task_util, capacity_of(cpu)); + + return true; +} + /* * Try and locate an idle core/thread in the LLC cache domain. */ static int select_idle_sibling(struct task_struct *p, int prev, int target) { struct sched_domain *sd; + unsigned long task_util; int i, recent_used_cpu; /* - * For asymmetric CPU capacity systems, our domain of interest is - * sd_asym_cpucapacity rather than sd_llc. + * On asymmetric system, update task utilization because we will check + * that the task fits with cpu's capacity. */ if (static_branch_unlikely(&sched_asym_cpucapacity)) { - sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target)); - /* - * On an asymmetric CPU capacity system where an exclusive - * cpuset defines a symmetric island (i.e. one unique - * capacity_orig value through the cpuset), the key will be set - * but the CPUs within that cpuset will not have a domain with - * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric - * capacity path. - */ - if (!sd) - goto symmetric; - - i = select_idle_capacity(p, sd, target); - return ((unsigned)i < nr_cpumask_bits) ? i : target; + sync_entity_load_avg(&p->se); + task_util = uclamp_task_util(p); } -symmetric: - if (available_idle_cpu(target) || sched_idle_cpu(target)) + if ((available_idle_cpu(target) || sched_idle_cpu(target)) && + asym_fits_capacity(task_util, target)) return target; /* * If the previous CPU is cache affine and idle, don't be stupid: */ if (prev != target && cpus_share_cache(prev, target) && - (available_idle_cpu(prev) || sched_idle_cpu(prev))) + (available_idle_cpu(prev) || sched_idle_cpu(prev)) && + asym_fits_capacity(task_util, prev)) return prev; /* @@ -6258,7 +6257,8 @@ symmetric: recent_used_cpu != target && cpus_share_cache(recent_used_cpu, target) && (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) && - cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) { + cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) && + asym_fits_capacity(task_util, recent_used_cpu)) { /* * Replace recent_used_cpu with prev as it is a potential * candidate for the next wake: @@ -6267,6 +6267,26 @@ symmetric: return recent_used_cpu; } + /* + * For asymmetric CPU capacity systems, our domain of interest is + * sd_asym_cpucapacity rather than sd_llc. + */ + if (static_branch_unlikely(&sched_asym_cpucapacity)) { + sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target)); + /* + * On an asymmetric CPU capacity system where an exclusive + * cpuset defines a symmetric island (i.e. one unique + * capacity_orig value through the cpuset), the key will be set + * but the CPUs within that cpuset will not have a domain with + * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric + * capacity path. + */ + if (sd) { + i = select_idle_capacity(p, sd, target); + return ((unsigned)i < nr_cpumask_bits) ? i : target; + } + } + sd = rcu_dereference(per_cpu(sd_llc, target)); if (!sd) return target; @@ -9031,7 +9051,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * emptying busiest. */ if (local->group_type == group_has_spare) { - if (busiest->group_type > group_fully_busy) { + if ((busiest->group_type > group_fully_busy) && + !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) { /* * If busiest is overloaded, try to fill spare * capacity. This might end up creating spare capacity diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 24d0ee26377d..c6932b8f4467 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -78,7 +78,7 @@ void __weak arch_cpu_idle_dead(void) { } void __weak arch_cpu_idle(void) { cpu_idle_force_poll = 1; - local_irq_enable(); + raw_local_irq_enable(); } /** @@ -94,9 +94,35 @@ void __cpuidle default_idle_call(void) trace_cpu_idle(1, smp_processor_id()); stop_critical_timings(); + + /* + * arch_cpu_idle() is supposed to enable IRQs, however + * we can't do that because of RCU and tracing. + * + * Trace IRQs enable here, then switch off RCU, and have + * arch_cpu_idle() use raw_local_irq_enable(). Note that + * rcu_idle_enter() relies on lockdep IRQ state, so switch that + * last -- this is very similar to the entry code. + */ + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(_THIS_IP_); rcu_idle_enter(); + lockdep_hardirqs_on(_THIS_IP_); + arch_cpu_idle(); + + /* + * OK, so IRQs are enabled here, but RCU needs them disabled to + * turn itself back on.. funny thing is that disabling IRQs + * will cause tracing, which needs RCU. Jump through hoops to + * make it 'work'. + */ + raw_local_irq_disable(); + lockdep_hardirqs_off(_THIS_IP_); rcu_idle_exit(); + lockdep_hardirqs_on(_THIS_IP_); + raw_local_irq_enable(); + start_critical_timings(); trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index e23e74d52db5..9d8df34bea75 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -38,8 +38,33 @@ static void ipi_mb(void *info) smp_mb(); /* IPIs should be serializing but paranoid. */ } +static void ipi_sync_core(void *info) +{ + /* + * The smp_mb() in membarrier after all the IPIs is supposed to + * ensure that memory on remote CPUs that occur before the IPI + * become visible to membarrier()'s caller -- see scenario B in + * the big comment at the top of this file. + * + * A sync_core() would provide this guarantee, but + * sync_core_before_usermode() might end up being deferred until + * after membarrier()'s smp_mb(). + */ + smp_mb(); /* IPIs should be serializing but paranoid. */ + + sync_core_before_usermode(); +} + static void ipi_rseq(void *info) { + /* + * Ensure that all stores done by the calling thread are visible + * to the current task before the current task resumes. We could + * probably optimize this away on most architectures, but by the + * time we've already sent an IPI, the cost of the extra smp_mb() + * is negligible. + */ + smp_mb(); rseq_preempt(current); } @@ -154,6 +179,7 @@ static int membarrier_private_expedited(int flags, int cpu_id) if (!(atomic_read(&mm->membarrier_state) & MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY)) return -EPERM; + ipi_func = ipi_sync_core; } else if (flags == MEMBARRIER_FLAG_RSEQ) { if (!IS_ENABLED(CONFIG_RSEQ)) return -EINVAL; @@ -168,7 +194,8 @@ static int membarrier_private_expedited(int flags, int cpu_id) return -EPERM; } - if (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1) + if (flags != MEMBARRIER_FLAG_SYNC_CORE && + (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1)) return 0; /* @@ -187,8 +214,6 @@ static int membarrier_private_expedited(int flags, int cpu_id) if (cpu_id >= nr_cpu_ids || !cpu_online(cpu_id)) goto out; - if (cpu_id == raw_smp_processor_id()) - goto out; rcu_read_lock(); p = rcu_dereference(cpu_rq(cpu_id)->curr); if (!p || p->mm != mm) { @@ -203,16 +228,6 @@ static int membarrier_private_expedited(int flags, int cpu_id) for_each_online_cpu(cpu) { struct task_struct *p; - /* - * Skipping the current CPU is OK even through we can be - * migrated at any point. The current CPU, at the point - * where we read raw_smp_processor_id(), is ensured to - * be in program order with respect to the caller - * thread. Therefore, we can skip this CPU from the - * iteration. - */ - if (cpu == raw_smp_processor_id()) - continue; p = rcu_dereference(cpu_rq(cpu)->curr); if (p && p->mm == mm) __cpumask_set_cpu(cpu, tmpmask); @@ -220,12 +235,38 @@ static int membarrier_private_expedited(int flags, int cpu_id) rcu_read_unlock(); } - preempt_disable(); - if (cpu_id >= 0) + if (cpu_id >= 0) { + /* + * smp_call_function_single() will call ipi_func() if cpu_id + * is the calling CPU. + */ smp_call_function_single(cpu_id, ipi_func, NULL, 1); - else - smp_call_function_many(tmpmask, ipi_func, NULL, 1); - preempt_enable(); + } else { + /* + * For regular membarrier, we can save a few cycles by + * skipping the current cpu -- we're about to do smp_mb() + * below, and if we migrate to a different cpu, this cpu + * and the new cpu will execute a full barrier in the + * scheduler. + * + * For SYNC_CORE, we do need a barrier on the current cpu -- + * otherwise, if we are migrated and replaced by a different + * task in the same mm just before, during, or after + * membarrier, we will end up with some thread in the mm + * running without a core sync. + * + * For RSEQ, don't rseq_preempt() the caller. User code + * is not supposed to issue syscalls at all from inside an + * rseq critical section. + */ + if (flags != MEMBARRIER_FLAG_SYNC_CORE) { + preempt_disable(); + smp_call_function_many(tmpmask, ipi_func, NULL, true); + preempt_enable(); + } else { + on_each_cpu_mask(tmpmask, ipi_func, NULL, true); + } + } out: if (cpu_id < 0) diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 8ad7a293255a..53a7d1512dd7 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -38,7 +38,7 @@ #include <linux/filter.h> #include <linux/pid.h> #include <linux/ptrace.h> -#include <linux/security.h> +#include <linux/capability.h> #include <linux/tracehook.h> #include <linux/uaccess.h> #include <linux/anon_inodes.h> @@ -558,8 +558,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) * behavior of privileged children. */ if (!task_no_new_privs(current) && - security_capable(current_cred(), current_user_ns(), - CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) != 0) + !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)) return ERR_PTR(-EACCES); /* Allocate a new seccomp_filter */ diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index a4020c0b4508..e1bf5228fb69 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -202,7 +202,7 @@ config DYNAMIC_FTRACE_WITH_REGS config DYNAMIC_FTRACE_WITH_DIRECT_CALLS def_bool y - depends on DYNAMIC_FTRACE + depends on DYNAMIC_FTRACE_WITH_REGS depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS config FUNCTION_PROFILER diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 4517c8b66518..a125ea5e04cd 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -181,6 +181,16 @@ bpf_probe_read_user_str_common(void *dst, u32 size, { int ret; + /* + * NB: We rely on strncpy_from_user() not copying junk past the NUL + * terminator into `dst`. + * + * strncpy_from_user() does long-sized strides in the fast path. If the + * strncpy does not mask out the bytes after the NUL in `unsafe_ptr`, + * then there could be junk after the NUL in `dst`. If user takes `dst` + * and keys a hash map with it, then semantically identical strings can + * occupy multiple entries in the map. + */ ret = strncpy_from_user_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); @@ -1198,7 +1208,7 @@ static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, *btf = bpf_get_btf_vmlinux(); if (IS_ERR_OR_NULL(*btf)) - return PTR_ERR(*btf); + return IS_ERR(*btf) ? PTR_ERR(*btf) : -EINVAL; if (ptr->type_id > 0) *btf_id = ptr->type_id; @@ -1327,9 +1337,9 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; - case BPF_FUNC_bpf_per_cpu_ptr: + case BPF_FUNC_per_cpu_ptr: return &bpf_per_cpu_ptr_proto; - case BPF_FUNC_bpf_this_cpu_ptr: + case BPF_FUNC_this_cpu_ptr: return &bpf_this_cpu_ptr_proto; default: return NULL; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 8185f7240095..9c1bba8cc51b 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1629,6 +1629,8 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec) static struct ftrace_ops * ftrace_find_tramp_ops_any(struct dyn_ftrace *rec); static struct ftrace_ops * +ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude); +static struct ftrace_ops * ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops); static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, @@ -1778,7 +1780,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, * to it. */ if (ftrace_rec_count(rec) == 1 && - ftrace_find_tramp_ops_any(rec)) + ftrace_find_tramp_ops_any_other(rec, ops)) rec->flags |= FTRACE_FL_TRAMP; else rec->flags &= ~FTRACE_FL_TRAMP; @@ -2245,6 +2247,24 @@ ftrace_find_tramp_ops_any(struct dyn_ftrace *rec) } static struct ftrace_ops * +ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude) +{ + struct ftrace_ops *op; + unsigned long ip = rec->ip; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + + if (op == op_exclude || !op->trampoline) + continue; + + if (hash_contains_ip(ip, op->func_hash)) + return op; + } while_for_each_ftrace_op(op); + + return NULL; +} + +static struct ftrace_ops * ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *op) { diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index dc83b3fa9fe7..a6268e09160a 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3234,14 +3234,12 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* See if we shot pass the end of this buffer page */ if (unlikely(write > BUF_PAGE_SIZE)) { - if (tail != w) { - /* before and after may now different, fix it up*/ - b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - if (a_ok && b_ok && info->before != info->after) - (void)rb_time_cmpxchg(&cpu_buffer->before_stamp, - info->before, info->after); - } + /* before and after may now different, fix it up*/ + b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); + a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); + if (a_ok && b_ok && info->before != info->after) + (void)rb_time_cmpxchg(&cpu_buffer->before_stamp, + info->before, info->after); return rb_move_tail(cpu_buffer, tail, info); } @@ -3287,11 +3285,11 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, ts = rb_time_stamp(cpu_buffer->buffer); barrier(); /*E*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) && - info->after < ts) { + info->after < ts && + rb_time_cmpxchg(&cpu_buffer->write_stamp, + info->after, ts)) { /* Nothing came after this event between C and E */ info->delta = ts - info->after; - (void)rb_time_cmpxchg(&cpu_buffer->write_stamp, - info->after, info->ts); info->ts = ts; } else { /* diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 410cfeb16db5..06134189e9a7 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -163,7 +163,8 @@ static union trace_eval_map_item *trace_eval_maps; #endif /* CONFIG_TRACE_EVAL_MAP_FILE */ int tracing_set_tracer(struct trace_array *tr, const char *buf); -static void ftrace_trace_userstack(struct trace_buffer *buffer, +static void ftrace_trace_userstack(struct trace_array *tr, + struct trace_buffer *buffer, unsigned long flags, int pc); #define MAX_TRACER_SIZE 100 @@ -2870,7 +2871,7 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, * two. They are not that meaningful. */ ftrace_trace_stack(tr, buffer, flags, regs ? 0 : STACK_SKIP, pc, regs); - ftrace_trace_userstack(buffer, flags, pc); + ftrace_trace_userstack(tr, buffer, flags, pc); } /* @@ -3056,13 +3057,14 @@ EXPORT_SYMBOL_GPL(trace_dump_stack); static DEFINE_PER_CPU(int, user_stack_count); static void -ftrace_trace_userstack(struct trace_buffer *buffer, unsigned long flags, int pc) +ftrace_trace_userstack(struct trace_array *tr, + struct trace_buffer *buffer, unsigned long flags, int pc) { struct trace_event_call *call = &event_user_stack; struct ring_buffer_event *event; struct userstack_entry *entry; - if (!(global_trace.trace_flags & TRACE_ITER_USERSTACKTRACE)) + if (!(tr->trace_flags & TRACE_ITER_USERSTACKTRACE)) return; /* @@ -3101,7 +3103,8 @@ ftrace_trace_userstack(struct trace_buffer *buffer, unsigned long flags, int pc) preempt_enable(); } #else /* CONFIG_USER_STACKTRACE_SUPPORT */ -static void ftrace_trace_userstack(struct trace_buffer *buffer, +static void ftrace_trace_userstack(struct trace_array *tr, + struct trace_buffer *buffer, unsigned long flags, int pc) { } @@ -3534,7 +3537,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, } #define STATIC_TEMP_BUF_SIZE 128 -static char static_temp_buf[STATIC_TEMP_BUF_SIZE]; +static char static_temp_buf[STATIC_TEMP_BUF_SIZE] __aligned(4); /* Find the next real entry, without updating the iterator itself */ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index c9ad5c6fbaad..d071fc271eef 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -368,7 +368,7 @@ static int start_kthread(struct trace_array *tr) struct task_struct *kthread; int next_cpu; - if (WARN_ON(hwlat_kthread)) + if (hwlat_kthread) return 0; /* Just pick the first CPU on first iteration */ diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 5abb5b22ad13..71109065bd8e 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -44,8 +44,6 @@ int __read_mostly soft_watchdog_user_enabled = 1; int __read_mostly watchdog_thresh = 10; static int __read_mostly nmi_watchdog_available; -static struct cpumask watchdog_allowed_mask __read_mostly; - struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); @@ -162,6 +160,8 @@ static void lockup_detector_update_enable(void) int __read_mostly sysctl_softlockup_all_cpu_backtrace; #endif +static struct cpumask watchdog_allowed_mask __read_mostly; + /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; diff --git a/lib/Makefile b/lib/Makefile index ce45af50983a..d415fc7067c5 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -107,7 +107,7 @@ obj-$(CONFIG_TEST_FREE_PAGES) += test_free_pages.o # off the generation of FPU/SSE* instructions for kernel proper but FPU_FLAGS # get appended last to CFLAGS and thus override those previous compiler options. # -FPU_CFLAGS := -mhard-float -msse -msse2 +FPU_CFLAGS := -msse -msse2 ifdef CONFIG_CC_IS_GCC # Stack alignment mismatch, proceed with caution. # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 @@ -120,6 +120,7 @@ ifdef CONFIG_CC_IS_GCC # -mpreferred-stack-boundary=3 is not between 4 and 12 # # can be triggered. Otherwise gcc doesn't complain. +FPU_CFLAGS += -mhard-float FPU_CFLAGS += $(call cc-option,-msse -mpreferred-stack-boundary=3,-mpreferred-stack-boundary=4) endif diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index e6d5fcc2cdf3..122d8d0e253c 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -35,17 +35,32 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src, goto byte_at_a_time; while (max >= sizeof(unsigned long)) { - unsigned long c, data; + unsigned long c, data, mask; /* Fall back to byte-at-a-time if we get a page fault */ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); - *(unsigned long *)(dst+res) = c; + /* + * Note that we mask out the bytes following the NUL. This is + * important to do because string oblivious code may read past + * the NUL. For those routines, we don't want to give them + * potentially random bytes after the NUL in `src`. + * + * One example of such code is BPF map keys. BPF treats map keys + * as an opaque set of bytes. Without the post-NUL mask, any BPF + * maps keyed by strings returned from strncpy_from_user() may + * have multiple entries for semantically identical strings. + */ if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); + mask = zero_bytemask(data); + *(unsigned long *)(dst+res) = c & mask; return res + find_zero(data); } + + *(unsigned long *)(dst+res) = c; + res += sizeof(unsigned long); max -= sizeof(unsigned long); } diff --git a/lib/syscall.c b/lib/syscall.c index 8533d2fea2d7..ba13e924c430 100644 --- a/lib/syscall.c +++ b/lib/syscall.c @@ -7,6 +7,7 @@ static int collect_syscall(struct task_struct *target, struct syscall_info *info) { + unsigned long args[6] = { }; struct pt_regs *regs; if (!try_get_task_stack(target)) { @@ -27,8 +28,14 @@ static int collect_syscall(struct task_struct *target, struct syscall_info *info info->data.nr = syscall_get_nr(target, regs); if (info->data.nr != -1L) - syscall_get_arguments(target, regs, - (unsigned long *)&info->data.args[0]); + syscall_get_arguments(target, regs, args); + + info->data.args[0] = args[0]; + info->data.args[1] = args[1]; + info->data.args[2] = args[2]; + info->data.args[3] = args[3]; + info->data.args[4] = args[4]; + info->data.args[5] = args[5]; put_task_stack(target); return 0; diff --git a/lib/zlib_dfltcc/dfltcc_inflate.c b/lib/zlib_dfltcc/dfltcc_inflate.c index aa9ef23474df..db107016d29b 100644 --- a/lib/zlib_dfltcc/dfltcc_inflate.c +++ b/lib/zlib_dfltcc/dfltcc_inflate.c @@ -4,6 +4,7 @@ #include "dfltcc_util.h" #include "dfltcc.h" #include <asm/setup.h> +#include <linux/export.h> #include <linux/zutil.h> /* @@ -29,6 +30,7 @@ int dfltcc_can_inflate( return is_bit_set(dfltcc_state->af.fns, DFLTCC_XPND) && is_bit_set(dfltcc_state->af.fmts, DFLTCC_FMT0); } +EXPORT_SYMBOL(dfltcc_can_inflate); static int dfltcc_was_inflate_used( z_streamp strm @@ -147,3 +149,4 @@ dfltcc_inflate_action dfltcc_inflate( return (cc == DFLTCC_CC_OP1_TOO_SHORT || cc == DFLTCC_CC_OP2_TOO_SHORT) ? DFLTCC_INFLATE_BREAK : DFLTCC_INFLATE_CONTINUE; } +EXPORT_SYMBOL(dfltcc_inflate); diff --git a/mm/Kconfig b/mm/Kconfig index d42423f884a7..390165ffbb0f 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -707,19 +707,6 @@ config ZSMALLOC returned by an alloc(). This handle must be mapped in order to access the allocated space. -config ZSMALLOC_PGTABLE_MAPPING - bool "Use page table mapping to access object in zsmalloc" - depends on ZSMALLOC=y - help - By default, zsmalloc uses a copy-based object mapping method to - access allocations that span two pages. However, if a particular - architecture (ex, ARM) performs VM mapping faster than copying, - then you should select this. This causes zsmalloc to use page table - mapping rather than copying for object mapping. - - You can check speed with zsmalloc benchmark: - https://github.com/spartacus06/zsmapbench - config ZSMALLOC_STAT bool "Export zsmalloc statistics" depends on ZSMALLOC diff --git a/mm/compaction.c b/mm/compaction.c index 6e0ee5641788..13cb7a961b31 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -817,6 +817,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, * delay for some time until fewer pages are isolated */ while (unlikely(too_many_isolated(pgdat))) { + /* stop isolation if there are still pages not migrated */ + if (cc->nr_migratepages) + return 0; + /* async migration should just abort */ if (cc->mode == MIGRATE_ASYNC) return 0; @@ -1012,8 +1016,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, isolate_success: list_add(&page->lru, &cc->migratepages); - cc->nr_migratepages++; - nr_isolated++; + cc->nr_migratepages += compound_nr(page); + nr_isolated += compound_nr(page); /* * Avoid isolating too much unless this block is being @@ -1021,7 +1025,7 @@ isolate_success: * or a lock is contended. For contention, isolate quickly to * potentially remove one source of contention. */ - if (cc->nr_migratepages == COMPACT_CLUSTER_MAX && + if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX && !cc->rescan && !cc->contended) { ++low_pfn; break; @@ -1132,7 +1136,7 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, if (!pfn) break; - if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) + if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX) break; } diff --git a/mm/filemap.c b/mm/filemap.c index d5e7c2029d16..0b2067b3c328 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1484,11 +1484,19 @@ void end_page_writeback(struct page *page) rotate_reclaimable_page(page); } + /* + * Writeback does not hold a page reference of its own, relying + * on truncation to wait for the clearing of PG_writeback. + * But here we must make sure that the page is not freed and + * reused before the wake_up_page(). + */ + get_page(page); if (!test_clear_page_writeback(page)) BUG(); smp_mb__after_atomic(); wake_up_page(page, PG_writeback); + put_page(page); } EXPORT_SYMBOL(end_page_writeback); @@ -2347,10 +2355,15 @@ page_ok: page_not_up_to_date: /* Get exclusive access to the page ... */ - if (iocb->ki_flags & IOCB_WAITQ) + if (iocb->ki_flags & IOCB_WAITQ) { + if (written) { + put_page(page); + goto out; + } error = lock_page_async(page, iocb->ki_waitq); - else + } else { error = lock_page_killable(page); + } if (unlikely(error)) goto readpage_error; @@ -2393,10 +2406,15 @@ readpage: } if (!PageUptodate(page)) { - if (iocb->ki_flags & IOCB_WAITQ) + if (iocb->ki_flags & IOCB_WAITQ) { + if (written) { + put_page(page); + goto out; + } error = lock_page_async(page, iocb->ki_waitq); - else + } else { error = lock_page_killable(page); + } if (unlikely(error)) goto readpage_error; @@ -1647,8 +1647,11 @@ check_again: /* * drop the above get_user_pages reference. */ - for (i = 0; i < nr_pages; i++) - put_page(pages[i]); + if (gup_flags & FOLL_PIN) + unpin_user_pages(pages, nr_pages); + else + for (i = 0; i < nr_pages; i++) + put_page(pages[i]); if (migrate_pages(&cma_page_list, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) { @@ -1728,8 +1731,11 @@ static long __gup_longterm_locked(struct mm_struct *mm, goto out; if (check_dax_vmas(vmas_tmp, rc)) { - for (i = 0; i < rc; i++) - put_page(pages[i]); + if (gup_flags & FOLL_PIN) + unpin_user_pages(pages, rc); + else + for (i = 0; i < rc; i++) + put_page(pages[i]); rc = -EOPNOTSUPP; goto out; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9474dbc150ed..ec2bb93f7431 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -710,7 +710,6 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) transparent_hugepage_use_zero_page()) { pgtable_t pgtable; struct page *zero_page; - bool set; vm_fault_t ret; pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) @@ -723,25 +722,25 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); ret = 0; - set = false; if (pmd_none(*vmf->pmd)) { ret = check_stable_address_space(vma->vm_mm); if (ret) { spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); } else if (userfaultfd_missing(vma)) { spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); } else { set_huge_zero_page(pgtable, vma->vm_mm, vma, haddr, vmf->pmd, zero_page); spin_unlock(vmf->ptl); - set = true; } - } else + } else { spin_unlock(vmf->ptl); - if (!set) pte_free(vma->vm_mm, pgtable); + } return ret; } gfp = alloc_hugepage_direct_gfpmask(vma); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5a620f690911..d029d938d26d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1216,6 +1216,7 @@ static void destroy_compound_gigantic_page(struct page *page, } set_compound_order(page, 0); + page[1].compound_nr = 0; __ClearPageHead(page); } @@ -1568,103 +1569,23 @@ int PageHeadHuge(struct page *page_head) } /* - * Find address_space associated with hugetlbfs page. - * Upon entry page is locked and page 'was' mapped although mapped state - * could change. If necessary, use anon_vma to find vma and associated - * address space. The returned mapping may be stale, but it can not be - * invalid as page lock (which is held) is required to destroy mapping. - */ -static struct address_space *_get_hugetlb_page_mapping(struct page *hpage) -{ - struct anon_vma *anon_vma; - pgoff_t pgoff_start, pgoff_end; - struct anon_vma_chain *avc; - struct address_space *mapping = page_mapping(hpage); - - /* Simple file based mapping */ - if (mapping) - return mapping; - - /* - * Even anonymous hugetlbfs mappings are associated with an - * underlying hugetlbfs file (see hugetlb_file_setup in mmap - * code). Find a vma associated with the anonymous vma, and - * use the file pointer to get address_space. - */ - anon_vma = page_lock_anon_vma_read(hpage); - if (!anon_vma) - return mapping; /* NULL */ - - /* Use first found vma */ - pgoff_start = page_to_pgoff(hpage); - pgoff_end = pgoff_start + pages_per_huge_page(page_hstate(hpage)) - 1; - anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, - pgoff_start, pgoff_end) { - struct vm_area_struct *vma = avc->vma; - - mapping = vma->vm_file->f_mapping; - break; - } - - anon_vma_unlock_read(anon_vma); - return mapping; -} - -/* * Find and lock address space (mapping) in write mode. * - * Upon entry, the page is locked which allows us to find the mapping - * even in the case of an anon page. However, locking order dictates - * the i_mmap_rwsem be acquired BEFORE the page lock. This is hugetlbfs - * specific. So, we first try to lock the sema while still holding the - * page lock. If this works, great! If not, then we need to drop the - * page lock and then acquire i_mmap_rwsem and reacquire page lock. Of - * course, need to revalidate state along the way. + * Upon entry, the page is locked which means that page_mapping() is + * stable. Due to locking order, we can only trylock_write. If we can + * not get the lock, simply return NULL to caller. */ struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) { - struct address_space *mapping, *mapping2; + struct address_space *mapping = page_mapping(hpage); - mapping = _get_hugetlb_page_mapping(hpage); -retry: if (!mapping) return mapping; - /* - * If no contention, take lock and return - */ if (i_mmap_trylock_write(mapping)) return mapping; - /* - * Must drop page lock and wait on mapping sema. - * Note: Once page lock is dropped, mapping could become invalid. - * As a hack, increase map count until we lock page again. - */ - atomic_inc(&hpage->_mapcount); - unlock_page(hpage); - i_mmap_lock_write(mapping); - lock_page(hpage); - atomic_add_negative(-1, &hpage->_mapcount); - - /* verify page is still mapped */ - if (!page_mapped(hpage)) { - i_mmap_unlock_write(mapping); - return NULL; - } - - /* - * Get address space again and verify it is the same one - * we locked. If not, drop lock and retry. - */ - mapping2 = _get_hugetlb_page_mapping(hpage); - if (mapping2 != mapping) { - i_mmap_unlock_write(mapping); - mapping = mapping2; - goto retry; - } - - return mapping; + return NULL; } pgoff_t __basepage_index(struct page *page) diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 1f87aec9ab5c..9182848dda3e 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -82,11 +82,8 @@ static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) for (idx = 0; idx < hugetlb_max_hstate; idx++) { if (page_counter_read( - hugetlb_cgroup_counter_from_cgroup(h_cg, idx)) || - page_counter_read(hugetlb_cgroup_counter_from_cgroup_rsvd( - h_cg, idx))) { + hugetlb_cgroup_counter_from_cgroup(h_cg, idx))) return true; - } } return false; } @@ -202,9 +199,10 @@ static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); struct hstate *h; struct page *page; - int idx = 0; + int idx; do { + idx = 0; for_each_hstate(h) { spin_lock(&hugetlb_lock); list_for_each_entry(page, &h->hugepage_activelist, lru) diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 4c5375810449..0e3f8494628f 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -29,6 +29,7 @@ #include <linux/srcu.h> #include <linux/string.h> #include <linux/types.h> +#include <linux/cpuhotplug.h> #include "../slab.h" #include "kasan.h" @@ -43,6 +44,7 @@ struct qlist_head { struct qlist_node *head; struct qlist_node *tail; size_t bytes; + bool offline; }; #define QLIST_INIT { NULL, NULL, 0 } @@ -188,6 +190,10 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) local_irq_save(flags); q = this_cpu_ptr(&cpu_quarantine); + if (q->offline) { + local_irq_restore(flags); + return; + } qlist_put(q, &info->quarantine_link, cache->size); if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) { qlist_move_all(q, &temp); @@ -328,3 +334,36 @@ void quarantine_remove_cache(struct kmem_cache *cache) synchronize_srcu(&remove_cache_srcu); } + +static int kasan_cpu_online(unsigned int cpu) +{ + this_cpu_ptr(&cpu_quarantine)->offline = false; + return 0; +} + +static int kasan_cpu_offline(unsigned int cpu) +{ + struct qlist_head *q; + + q = this_cpu_ptr(&cpu_quarantine); + /* Ensure the ordering between the writing to q->offline and + * qlist_free_all. Otherwise, cpu_quarantine may be corrupted + * by interrupt. + */ + WRITE_ONCE(q->offline, true); + barrier(); + qlist_free_all(q, NULL); + return 0; +} + +static int __init kasan_cpu_quarantine_init(void) +{ + int ret = 0; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/kasan:online", + kasan_cpu_online, kasan_cpu_offline); + if (ret < 0) + pr_err("kasan cpu quarantine register failed [%d]\n", ret); + return ret; +} +late_initcall(kasan_cpu_quarantine_init); diff --git a/mm/list_lru.c b/mm/list_lru.c index 5aa6e44bc2ae..fe230081690b 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -534,7 +534,6 @@ static void memcg_drain_list_lru_node(struct list_lru *lru, int nid, struct list_lru_node *nlru = &lru->node[nid]; int dst_idx = dst_memcg->kmemcg_id; struct list_lru_one *src, *dst; - bool set; /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, @@ -546,11 +545,12 @@ static void memcg_drain_list_lru_node(struct list_lru *lru, int nid, dst = list_lru_from_memcg_idx(nlru, dst_idx); list_splice_init(&src->list, &dst->list); - set = (!dst->nr_items && src->nr_items); - dst->nr_items += src->nr_items; - if (set) + + if (src->nr_items) { + dst->nr_items += src->nr_items; memcg_set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); - src->nr_items = 0; + src->nr_items = 0; + } spin_unlock_irq(&nlru->lock); } diff --git a/mm/madvise.c b/mm/madvise.c index 416a56b8e757..13f5677b9322 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -226,7 +226,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, struct address_space *mapping) { XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start)); - pgoff_t end_index = end / PAGE_SIZE; + pgoff_t end_index = linear_page_index(vma, end + PAGE_SIZE - 1); struct page *page; rcu_read_lock(); @@ -1204,8 +1204,7 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, goto put_pid; } - if (task->mm != current->mm && - !process_madvise_behavior_valid(behavior)) { + if (!process_madvise_behavior_valid(behavior)) { ret = -EINVAL; goto release_task; } @@ -1231,8 +1230,6 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, ret = total_len - iov_iter_count(&iter); mmput(mm); - return ret; - release_task: put_task_struct(task); put_pid: diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 48021b002722..54557b5673a4 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -867,8 +867,13 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) rcu_read_lock(); memcg = mem_cgroup_from_obj(p); - /* Untracked pages have no memcg, no lruvec. Update only the node */ - if (!memcg || memcg == root_mem_cgroup) { + /* + * Untracked pages have no memcg, no lruvec. Update only the + * node. If we reparent the slab objects to the root memcg, + * when we free the slab object, we need to update the per-memcg + * vmstats to keep it correct for the root memcg. + */ + if (!memcg) { __mod_node_page_state(pgdat, idx, val); } else { lruvec = mem_cgroup_lruvec(memcg, pgdat); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index c0bb186bba62..5d880d4eb9a2 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1057,27 +1057,25 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, if (!PageHuge(hpage)) { unmap_success = try_to_unmap(hpage, ttu); } else { - /* - * For hugetlb pages, try_to_unmap could potentially call - * huge_pmd_unshare. Because of this, take semaphore in - * write mode here and set TTU_RMAP_LOCKED to indicate we - * have taken the lock at this higer level. - * - * Note that the call to hugetlb_page_mapping_lock_write - * is necessary even if mapping is already set. It handles - * ugliness of potentially having to drop page lock to obtain - * i_mmap_rwsem. - */ - mapping = hugetlb_page_mapping_lock_write(hpage); - - if (mapping) { - unmap_success = try_to_unmap(hpage, + if (!PageAnon(hpage)) { + /* + * For hugetlb pages in shared mappings, try_to_unmap + * could potentially call huge_pmd_unshare. Because of + * this, take semaphore in write mode here and set + * TTU_RMAP_LOCKED to indicate we have taken the lock + * at this higer level. + */ + mapping = hugetlb_page_mapping_lock_write(hpage); + if (mapping) { + unmap_success = try_to_unmap(hpage, ttu|TTU_RMAP_LOCKED); - i_mmap_unlock_write(mapping); + i_mmap_unlock_write(mapping); + } else { + pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn); + unmap_success = false; + } } else { - pr_info("Memory failure: %#lx: could not find mapping for mapped huge page\n", - pfn); - unmap_success = false; + unmap_success = try_to_unmap(hpage, ttu); } } if (!unmap_success) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b44d4c7ba73b..63b2e46b6555 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -350,24 +350,6 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, return err; } -#ifdef CONFIG_NUMA -int __weak memory_add_physaddr_to_nid(u64 start) -{ - pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); - -int __weak phys_to_target_node(u64 start) -{ - pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} -EXPORT_SYMBOL_GPL(phys_to_target_node); -#endif - /* find the smallest valid pfn in the range [start_pfn, end_pfn) */ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, diff --git a/mm/migrate.c b/mm/migrate.c index 5ca5842df5db..5795cb82e27c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1328,34 +1328,38 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, goto put_anon; if (page_mapped(hpage)) { - /* - * try_to_unmap could potentially call huge_pmd_unshare. - * Because of this, take semaphore in write mode here and - * set TTU_RMAP_LOCKED to let lower levels know we have - * taken the lock. - */ - mapping = hugetlb_page_mapping_lock_write(hpage); - if (unlikely(!mapping)) - goto unlock_put_anon; + bool mapping_locked = false; + enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK| + TTU_IGNORE_ACCESS; + + if (!PageAnon(hpage)) { + /* + * In shared mappings, try_to_unmap could potentially + * call huge_pmd_unshare. Because of this, take + * semaphore in write mode here and set TTU_RMAP_LOCKED + * to let lower levels know we have taken the lock. + */ + mapping = hugetlb_page_mapping_lock_write(hpage); + if (unlikely(!mapping)) + goto unlock_put_anon; + + mapping_locked = true; + ttu |= TTU_RMAP_LOCKED; + } - try_to_unmap(hpage, - TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS| - TTU_RMAP_LOCKED); + try_to_unmap(hpage, ttu); page_was_mapped = 1; - /* - * Leave mapping locked until after subsequent call to - * remove_migration_ptes() - */ + + if (mapping_locked) + i_mmap_unlock_write(mapping); } if (!page_mapped(hpage)) rc = move_to_new_page(new_hpage, hpage, mode); - if (page_was_mapped) { + if (page_was_mapped) remove_migration_ptes(hpage, - rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, true); - i_mmap_unlock_write(mapping); - } + rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false); unlock_put_anon: unlock_page(new_hpage); diff --git a/mm/mmap.c b/mm/mmap.c index d91ecb00d38c..5c8b4485860d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1808,6 +1808,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr, if (error) goto unmap_and_free_vma; + /* Can addr have changed?? + * + * Answer: Yes, several device drivers can do it in their + * f_op->mmap method. -DaveM + * Bug: If addr is changed, prev, rb_link, rb_parent should + * be updated for vma_link() + */ + WARN_ON_ONCE(addr != vma->vm_start); + + addr = vma->vm_start; + /* If vm_flags changed after call_mmap(), we should try merge vma again * as we may succeed this time. */ @@ -1822,25 +1833,12 @@ unsigned long mmap_region(struct file *file, unsigned long addr, fput(vma->vm_file); vm_area_free(vma); vma = merge; - /* Update vm_flags and possible addr to pick up the change. We don't - * warn here if addr changed as the vma is not linked by vma_link(). - */ - addr = vma->vm_start; + /* Update vm_flags to pick up the change. */ vm_flags = vma->vm_flags; goto unmap_writable; } } - /* Can addr have changed?? - * - * Answer: Yes, several device drivers can do it in their - * f_op->mmap method. -DaveM - * Bug: If addr is changed, prev, rb_link, rb_parent should - * be updated for vma_link() - */ - WARN_ON_ONCE(addr != vma->vm_start); - - addr = vma->vm_start; vm_flags = vma->vm_flags; } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 7709f0e223f5..586042472ac9 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2754,12 +2754,6 @@ int test_clear_page_writeback(struct page *page) } else { ret = TestClearPageWriteback(page); } - /* - * NOTE: Page might be free now! Writeback doesn't hold a page - * reference on its own, it relies on truncation to wait for - * the clearing of PG_writeback. The below can only access - * page state that is static across allocation cycles. - */ if (ret) { dec_lruvec_state(lruvec, NR_WRITEBACK); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 23f5066bd4a5..eaa227a479e4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5103,6 +5103,11 @@ refill: if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) goto refill; + if (unlikely(nc->pfmemalloc)) { + free_the_page(page, compound_order(page)); + goto refill; + } + #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) /* if size can vary use size else just use PAGE_SIZE */ size = nc->size; diff --git a/mm/percpu.c b/mm/percpu.c index 66a93f096394..ad7a37ee74ef 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1315,8 +1315,8 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, region_size = ALIGN(start_offset + map_size, lcm_align); /* allocate chunk */ - alloc_size = sizeof(struct pcpu_chunk) + - BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long); + alloc_size = struct_size(chunk, populated, + BITS_TO_LONGS(region_size >> PAGE_SHIFT)); chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk) panic("%s: Failed to allocate %zu bytes\n", __func__, @@ -2521,8 +2521,8 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT; pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; pcpu_atom_size = ai->atom_size; - pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) + - BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long); + pcpu_chunk_struct_size = struct_size(chunk, populated, + BITS_TO_LONGS(pcpu_unit_pages)); pcpu_stats_save_ai(ai); diff --git a/mm/rmap.c b/mm/rmap.c index 1b84945d655c..31b29321adfe 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1413,9 +1413,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* * If sharing is possible, start and end will be adjusted * accordingly. - * - * If called for a huge page, caller must hold i_mmap_rwsem - * in write mode as it is possible to call huge_pmd_unshare. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); @@ -1462,7 +1459,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); address = pvmw.address; - if (PageHuge(page)) { + if (PageHuge(page) && !PageAnon(page)) { /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly diff --git a/mm/slab.h b/mm/slab.h index 6d7c6a5056ba..f9977d6613d6 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -274,22 +274,32 @@ static inline size_t obj_full_size(struct kmem_cache *s) return s->size + sizeof(struct obj_cgroup *); } -static inline struct obj_cgroup *memcg_slab_pre_alloc_hook(struct kmem_cache *s, - size_t objects, - gfp_t flags) +/* + * Returns false if the allocation should fail. + */ +static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, + struct obj_cgroup **objcgp, + size_t objects, gfp_t flags) { struct obj_cgroup *objcg; + if (!memcg_kmem_enabled()) + return true; + + if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT)) + return true; + objcg = get_obj_cgroup_from_current(); if (!objcg) - return NULL; + return true; if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) { obj_cgroup_put(objcg); - return NULL; + return false; } - return objcg; + *objcgp = objcg; + return true; } static inline void mod_objcg_state(struct obj_cgroup *objcg, @@ -315,7 +325,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, unsigned long off; size_t i; - if (!objcg) + if (!memcg_kmem_enabled() || !objcg) return; flags &= ~__GFP_ACCOUNT; @@ -400,11 +410,11 @@ static inline void memcg_free_page_obj_cgroups(struct page *page) { } -static inline struct obj_cgroup *memcg_slab_pre_alloc_hook(struct kmem_cache *s, - size_t objects, - gfp_t flags) +static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, + struct obj_cgroup **objcgp, + size_t objects, gfp_t flags) { - return NULL; + return true; } static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, @@ -508,9 +518,8 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, if (should_failslab(s, flags)) return NULL; - if (memcg_kmem_enabled() && - ((flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT))) - *objcgp = memcg_slab_pre_alloc_hook(s, size, flags); + if (!memcg_slab_pre_alloc_hook(s, objcgp, size, flags)) + return NULL; return s; } @@ -529,8 +538,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, s->flags, flags); } - if (memcg_kmem_enabled()) - memcg_slab_post_alloc_hook(s, objcg, flags, size, p); + memcg_slab_post_alloc_hook(s, objcg, flags, size, p); } #ifndef CONFIG_SLOB diff --git a/mm/slub.c b/mm/slub.c index b30be2385d1c..34dcc09e2ec9 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2852,7 +2852,7 @@ redo: object = c->freelist; page = c->page; - if (unlikely(!object || !node_match(page, node))) { + if (unlikely(!object || !page || !node_match(page, node))) { object = __slab_alloc(s, gfpflags, node, addr, c); } else { void *next_object = get_freepointer_safe(s, object); diff --git a/mm/swapfile.c b/mm/swapfile.c index c4a613688a17..d58361109066 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2867,6 +2867,7 @@ late_initcall(max_swapfiles_check); static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; + struct swap_info_struct *defer = NULL; unsigned int type; int i; @@ -2895,7 +2896,7 @@ static struct swap_info_struct *alloc_swap_info(void) smp_wmb(); WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1); } else { - kvfree(p); + defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() @@ -2908,6 +2909,7 @@ static struct swap_info_struct *alloc_swap_info(void) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); + kvfree(defer); spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); diff --git a/mm/vmscan.c b/mm/vmscan.c index 1b8f0e059767..7b4e31eac2cf 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1516,7 +1516,8 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, TTU_IGNORE_ACCESS, &stat, true); list_splice(&clean_pages, page_list); - mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -nr_reclaimed); + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, + -(long)nr_reclaimed); /* * Since lazyfree pages are isolated from file LRU from the beginning, * they will rotate back to anonymous LRU in the end if it failed to @@ -1526,7 +1527,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, stat.nr_lazyfree_fail); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, - -stat.nr_lazyfree_fail); + -(long)stat.nr_lazyfree_fail); return nr_reclaimed; } diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 918c7b019b3d..cdfaaadea8ff 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -293,11 +293,7 @@ struct zspage { }; struct mapping_area { -#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING - struct vm_struct *vm; /* vm area for mapping object that span pages */ -#else char *vm_buf; /* copy buffer for objects that span pages */ -#endif char *vm_addr; /* address of kmap_atomic()'ed pages */ enum zs_mapmode vm_mm; /* mapping mode */ }; @@ -1113,54 +1109,6 @@ static struct zspage *find_get_zspage(struct size_class *class) return zspage; } -#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING -static inline int __zs_cpu_up(struct mapping_area *area) -{ - /* - * Make sure we don't leak memory if a cpu UP notification - * and zs_init() race and both call zs_cpu_up() on the same cpu - */ - if (area->vm) - return 0; - area->vm = get_vm_area(PAGE_SIZE * 2, 0); - if (!area->vm) - return -ENOMEM; - - /* - * Populate ptes in advance to avoid pte allocation with GFP_KERNEL - * in non-preemtible context of zs_map_object. - */ - return apply_to_page_range(&init_mm, (unsigned long)area->vm->addr, - PAGE_SIZE * 2, NULL, NULL); -} - -static inline void __zs_cpu_down(struct mapping_area *area) -{ - if (area->vm) - free_vm_area(area->vm); - area->vm = NULL; -} - -static inline void *__zs_map_object(struct mapping_area *area, - struct page *pages[2], int off, int size) -{ - unsigned long addr = (unsigned long)area->vm->addr; - - BUG_ON(map_kernel_range(addr, PAGE_SIZE * 2, PAGE_KERNEL, pages) < 0); - area->vm_addr = area->vm->addr; - return area->vm_addr + off; -} - -static inline void __zs_unmap_object(struct mapping_area *area, - struct page *pages[2], int off, int size) -{ - unsigned long addr = (unsigned long)area->vm_addr; - - unmap_kernel_range(addr, PAGE_SIZE * 2); -} - -#else /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */ - static inline int __zs_cpu_up(struct mapping_area *area) { /* @@ -1241,8 +1189,6 @@ out: pagefault_enable(); } -#endif /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */ - static int zs_cpu_prepare(unsigned int cpu) { struct mapping_area *area; diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 9a47ef8b95c4..1f1f5b0873b2 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -391,6 +391,7 @@ out: /** * batadv_frag_create() - create a fragment from skb + * @net_dev: outgoing device for fragment * @skb: skb to create fragment from * @frag_head: header to use in new fragment * @fragment_size: size of new fragment @@ -401,22 +402,25 @@ out: * * Return: the new fragment, NULL on error. */ -static struct sk_buff *batadv_frag_create(struct sk_buff *skb, +static struct sk_buff *batadv_frag_create(struct net_device *net_dev, + struct sk_buff *skb, struct batadv_frag_packet *frag_head, unsigned int fragment_size) { + unsigned int ll_reserved = LL_RESERVED_SPACE(net_dev); + unsigned int tailroom = net_dev->needed_tailroom; struct sk_buff *skb_fragment; unsigned int header_size = sizeof(*frag_head); unsigned int mtu = fragment_size + header_size; - skb_fragment = netdev_alloc_skb(NULL, mtu + ETH_HLEN); + skb_fragment = dev_alloc_skb(ll_reserved + mtu + tailroom); if (!skb_fragment) goto err; skb_fragment->priority = skb->priority; /* Eat the last mtu-bytes of the skb */ - skb_reserve(skb_fragment, header_size + ETH_HLEN); + skb_reserve(skb_fragment, ll_reserved + header_size); skb_split(skb, skb_fragment, skb->len - fragment_size); /* Add the header */ @@ -439,11 +443,12 @@ int batadv_frag_send_packet(struct sk_buff *skb, struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node) { + struct net_device *net_dev = neigh_node->if_incoming->net_dev; struct batadv_priv *bat_priv; struct batadv_hard_iface *primary_if = NULL; struct batadv_frag_packet frag_header; struct sk_buff *skb_fragment; - unsigned int mtu = neigh_node->if_incoming->net_dev->mtu; + unsigned int mtu = net_dev->mtu; unsigned int header_size = sizeof(frag_header); unsigned int max_fragment_size, num_fragments; int ret; @@ -503,7 +508,7 @@ int batadv_frag_send_packet(struct sk_buff *skb, goto put_primary_if; } - skb_fragment = batadv_frag_create(skb, &frag_header, + skb_fragment = batadv_frag_create(net_dev, skb, &frag_header, max_fragment_size); if (!skb_fragment) { ret = -ENOMEM; @@ -522,13 +527,14 @@ int batadv_frag_send_packet(struct sk_buff *skb, frag_header.no++; } - /* Make room for the fragment header. */ - if (batadv_skb_head_push(skb, header_size) < 0 || - pskb_expand_head(skb, header_size + ETH_HLEN, 0, GFP_ATOMIC) < 0) { - ret = -ENOMEM; + /* make sure that there is at least enough head for the fragmentation + * and ethernet headers + */ + ret = skb_cow_head(skb, ETH_HLEN + header_size); + if (ret < 0) goto put_primary_if; - } + skb_push(skb, header_size); memcpy(skb->data, &frag_header, header_size); /* Send the last fragment */ diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index dad99641df2a..33904595fc56 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -554,6 +554,9 @@ static void batadv_hardif_recalc_extra_skbroom(struct net_device *soft_iface) needed_headroom = lower_headroom + (lower_header_len - ETH_HLEN); needed_headroom += batadv_max_header_len(); + /* fragmentation headers don't strip the unicast/... header */ + needed_headroom += sizeof(struct batadv_frag_packet); + soft_iface->needed_headroom = needed_headroom; soft_iface->needed_tailroom = lower_tailroom; } diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index a67b2b091447..c0ca5fbe5b08 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -180,6 +180,7 @@ static const struct file_operations batadv_log_fops = { .read = batadv_log_read, .poll = batadv_log_poll, .llseek = no_llseek, + .owner = THIS_MODULE, }; /** diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 6f742fee874a..d3ea9d0779fb 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -177,6 +177,9 @@ static int br_dev_open(struct net_device *dev) br_stp_enable_bridge(br); br_multicast_open(br); + if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) + br_multicast_join_snoopers(br); + return 0; } @@ -197,6 +200,9 @@ static int br_dev_stop(struct net_device *dev) br_stp_disable_bridge(br); br_multicast_stop(br); + if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) + br_multicast_leave_snoopers(br); + netif_stop_queue(dev); return 0; @@ -207,6 +213,7 @@ static void br_get_stats64(struct net_device *dev, { struct net_bridge *br = netdev_priv(dev); + netdev_stats_to_stats64(stats, &dev->stats); dev_fetch_sw_netstats(stats, br->stats); } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index cb30d2b4ebe7..c7a2cab8295f 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -3293,7 +3293,7 @@ static inline void br_ip6_multicast_join_snoopers(struct net_bridge *br) } #endif -static void br_multicast_join_snoopers(struct net_bridge *br) +void br_multicast_join_snoopers(struct net_bridge *br) { br_ip4_multicast_join_snoopers(br); br_ip6_multicast_join_snoopers(br); @@ -3324,7 +3324,7 @@ static inline void br_ip6_multicast_leave_snoopers(struct net_bridge *br) } #endif -static void br_multicast_leave_snoopers(struct net_bridge *br) +void br_multicast_leave_snoopers(struct net_bridge *br) { br_ip4_multicast_leave_snoopers(br); br_ip6_multicast_leave_snoopers(br); @@ -3343,9 +3343,6 @@ static void __br_multicast_open(struct net_bridge *br, void br_multicast_open(struct net_bridge *br) { - if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) - br_multicast_join_snoopers(br); - __br_multicast_open(br, &br->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) __br_multicast_open(br, &br->ip6_own_query); @@ -3361,9 +3358,6 @@ void br_multicast_stop(struct net_bridge *br) del_timer_sync(&br->ip6_other_query.timer); del_timer_sync(&br->ip6_own_query.timer); #endif - - if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) - br_multicast_leave_snoopers(br); } void br_multicast_dev_del(struct net_bridge *br) @@ -3494,6 +3488,7 @@ static void br_multicast_start_querier(struct net_bridge *br, int br_multicast_toggle(struct net_bridge *br, unsigned long val) { struct net_bridge_port *port; + bool change_snoopers = false; spin_lock_bh(&br->multicast_lock); if (!!br_opt_get(br, BROPT_MULTICAST_ENABLED) == !!val) @@ -3502,7 +3497,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val) br_mc_disabled_update(br->dev, val); br_opt_toggle(br, BROPT_MULTICAST_ENABLED, !!val); if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) { - br_multicast_leave_snoopers(br); + change_snoopers = true; goto unlock; } @@ -3513,9 +3508,30 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val) list_for_each_entry(port, &br->port_list, list) __br_multicast_enable_port(port); + change_snoopers = true; + unlock: spin_unlock_bh(&br->multicast_lock); + /* br_multicast_join_snoopers has the potential to cause + * an MLD Report/Leave to be delivered to br_multicast_rcv, + * which would in turn call br_multicast_add_group, which would + * attempt to acquire multicast_lock. This function should be + * called after the lock has been released to avoid deadlocks on + * multicast_lock. + * + * br_multicast_leave_snoopers does not have the problem since + * br_multicast_rcv first checks BROPT_MULTICAST_ENABLED, and + * returns without calling br_multicast_ipv4/6_rcv if it's not + * enabled. Moved both functions out just for symmetry. + */ + if (change_snoopers) { + if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) + br_multicast_join_snoopers(br); + else + br_multicast_leave_snoopers(br); + } + return 0; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 04c3f9a82650..8edfb98ae1d5 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -735,6 +735,11 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff mtu_reserved = nf_bridge_mtu_reduction(skb); mtu = skb->dev->mtu; + if (nf_bridge->pkt_otherhost) { + skb->pkt_type = PACKET_OTHERHOST; + nf_bridge->pkt_otherhost = false; + } + if (nf_bridge->frag_max_size && nf_bridge->frag_max_size < mtu) mtu = nf_bridge->frag_max_size; @@ -835,8 +840,6 @@ static unsigned int br_nf_post_routing(void *priv, else return NF_ACCEPT; - /* We assume any code from br_dev_queue_push_xmit onwards doesn't care - * about the value of skb->pkt_type. */ if (skb->pkt_type == PACKET_OTHERHOST) { skb->pkt_type = PACKET_HOST; nf_bridge->pkt_otherhost = true; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 345118e35c42..8424464186a6 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -792,6 +792,8 @@ void br_multicast_del_port(struct net_bridge_port *port); void br_multicast_enable_port(struct net_bridge_port *port); void br_multicast_disable_port(struct net_bridge_port *port); void br_multicast_init(struct net_bridge *br); +void br_multicast_join_snoopers(struct net_bridge *br); +void br_multicast_leave_snoopers(struct net_bridge *br); void br_multicast_open(struct net_bridge *br); void br_multicast_stop(struct net_bridge *br); void br_multicast_dev_del(struct net_bridge *br); @@ -969,6 +971,14 @@ static inline void br_multicast_init(struct net_bridge *br) { } +static inline void br_multicast_join_snoopers(struct net_bridge *br) +{ +} + +static inline void br_multicast_leave_snoopers(struct net_bridge *br) +{ +} + static inline void br_multicast_open(struct net_bridge *br) { } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 3e493eb85bb2..08c77418c687 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -266,8 +266,10 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, } masterv = br_vlan_get_master(br, v->vid, extack); - if (!masterv) + if (!masterv) { + err = -ENOMEM; goto out_filt; + } v->brvlan = masterv; if (br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)) { v->stats = netdev_alloc_pcpu_stats(struct br_vlan_stats); diff --git a/net/can/af_can.c b/net/can/af_can.c index 6373ab9c5507..4c343b43067f 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -541,10 +541,13 @@ void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id, /* Check for bugs in CAN protocol implementations using af_can.c: * 'rcv' will be NULL if no matching list item was found for removal. + * As this case may potentially happen when closing a socket while + * the notifier for removing the CAN netdev is running we just print + * a warning here. */ if (!rcv) { - WARN(1, "BUG: receive list entry not found for dev %s, id %03X, mask %03X\n", - DNAME(dev), can_id, mask); + pr_warn("can: receive list entry not found for dev %s, id %03X, mask %03X\n", + DNAME(dev), can_id, mask); goto out; } @@ -677,16 +680,25 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU || - cfd->len > CAN_MAX_DLEN)) { - pr_warn_once("PF_CAN: dropped non conform CAN skbuf: dev type %d, len %d, datalen %d\n", + if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU)) { + pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d\n", + dev->type, skb->len); + goto free_skb; + } + + /* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */ + if (unlikely(cfd->len > CAN_MAX_DLEN)) { + pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d, datalen %d\n", dev->type, skb->len, cfd->len); - kfree_skb(skb); - return NET_RX_DROP; + goto free_skb; } can_receive(skb, dev); return NET_RX_SUCCESS; + +free_skb: + kfree_skb(skb); + return NET_RX_DROP; } static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, @@ -694,16 +706,25 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU || - cfd->len > CANFD_MAX_DLEN)) { - pr_warn_once("PF_CAN: dropped non conform CAN FD skbuf: dev type %d, len %d, datalen %d\n", + if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU)) { + pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d\n", + dev->type, skb->len); + goto free_skb; + } + + /* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */ + if (unlikely(cfd->len > CANFD_MAX_DLEN)) { + pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d, datalen %d\n", dev->type, skb->len, cfd->len); - kfree_skb(skb); - return NET_RX_DROP; + goto free_skb; } can_receive(skb, dev); return NET_RX_SUCCESS; + +free_skb: + kfree_skb(skb); + return NET_RX_DROP; } /* af_can protocol functions */ diff --git a/net/can/isotp.c b/net/can/isotp.c index d78ab13bd8be..26bdc3c20b7e 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1157,6 +1157,9 @@ static int isotp_setsockopt(struct socket *sock, int level, int optname, if (level != SOL_CAN_ISOTP) return -EINVAL; + if (so->bound) + return -EISCONN; + switch (optname) { case CAN_ISOTP_OPTS: if (optlen != sizeof(struct can_isotp_options)) diff --git a/net/core/dev.c b/net/core/dev.c index 82dc6b48e45f..38412e70f761 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4180,7 +4180,7 @@ int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev) } EXPORT_SYMBOL(dev_queue_xmit_accel); -int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) +int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { struct net_device *dev = skb->dev; struct sk_buff *orig_skb = skb; @@ -4210,17 +4210,13 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) dev_xmit_recursion_dec(); local_bh_enable(); - - if (!dev_xmit_complete(ret)) - kfree_skb(skb); - return ret; drop: atomic_long_inc(&dev->tx_dropped); kfree_skb_list(skb); return NET_XMIT_DROP; } -EXPORT_SYMBOL(dev_direct_xmit); +EXPORT_SYMBOL(__dev_direct_xmit); /************************************************************************* * Receiver routines @@ -8921,6 +8917,17 @@ static struct bpf_prog *dev_xdp_prog(struct net_device *dev, return dev->xdp_state[mode].prog; } +static u8 dev_xdp_prog_count(struct net_device *dev) +{ + u8 count = 0; + int i; + + for (i = 0; i < __MAX_XDP_MODE; i++) + if (dev->xdp_state[i].prog || dev->xdp_state[i].link) + count++; + return count; +} + u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_prog *prog = dev_xdp_prog(dev, mode); @@ -9011,6 +9018,7 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack struct bpf_xdp_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog, u32 flags) { + unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES); struct bpf_prog *cur_prog; enum bpf_xdp_mode mode; bpf_op_t bpf_op; @@ -9026,11 +9034,17 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment"); return -EINVAL; } - /* just one XDP mode bit should be set, zero defaults to SKB mode */ - if (hweight32(flags & XDP_FLAGS_MODES) > 1) { + /* just one XDP mode bit should be set, zero defaults to drv/skb mode */ + if (num_modes > 1) { NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set"); return -EINVAL; } + /* avoid ambiguity if offload + drv/skb mode progs are both loaded */ + if (!num_modes && dev_xdp_prog_count(dev) > 1) { + NL_SET_ERR_MSG(extack, + "More than one program loaded, unset mode is ambiguous"); + return -EINVAL; + } /* old_prog != NULL implies XDP_FLAGS_REPLACE is set */ if (old_prog && !(flags & XDP_FLAGS_REPLACE)) { NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified"); diff --git a/net/core/devlink.c b/net/core/devlink.c index a932d95be798..8c5ddffd707d 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -517,7 +517,7 @@ devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_l return test_bit(limit, &devlink->ops->reload_limits); } -static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_action action, +static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_limit limit, u32 value) { struct nlattr *reload_stats_entry; @@ -526,8 +526,7 @@ static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_acti if (!reload_stats_entry) return -EMSGSIZE; - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, action) || - nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) goto nla_put_failure; nla_nest_end(msg, reload_stats_entry); @@ -540,7 +539,7 @@ nla_put_failure: static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) { - struct nlattr *reload_stats_attr; + struct nlattr *reload_stats_attr, *act_info, *act_stats; int i, j, stat_idx; u32 value; @@ -552,17 +551,29 @@ static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink if (!reload_stats_attr) return -EMSGSIZE; - for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { - /* Remote stats are shown even if not locally supported. Stats - * of actions with unspecified limit are shown though drivers - * don't need to register unspecified limit. - */ - if (!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && - !devlink_reload_limit_is_supported(devlink, j)) + for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { + if ((!is_remote && + !devlink_reload_action_is_supported(devlink, i)) || + i == DEVLINK_RELOAD_ACTION_UNSPEC) continue; - for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { - if ((!is_remote && !devlink_reload_action_is_supported(devlink, i)) || - i == DEVLINK_RELOAD_ACTION_UNSPEC || + act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO); + if (!act_info) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i)) + goto action_info_nest_cancel; + act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS); + if (!act_stats) + goto action_info_nest_cancel; + + for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { + /* Remote stats are shown even if not locally supported. + * Stats of actions with unspecified limit are shown + * though drivers don't need to register unspecified + * limit. + */ + if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && + !devlink_reload_limit_is_supported(devlink, j)) || devlink_reload_combination_is_invalid(i, j)) continue; @@ -571,13 +582,19 @@ static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink value = devlink->stats.reload_stats[stat_idx]; else value = devlink->stats.remote_reload_stats[stat_idx]; - if (devlink_reload_stat_put(msg, i, j, value)) - goto nla_put_failure; + if (devlink_reload_stat_put(msg, j, value)) + goto action_stats_nest_cancel; } + nla_nest_end(msg, act_stats); + nla_nest_end(msg, act_info); } nla_nest_end(msg, reload_stats_attr); return 0; +action_stats_nest_cancel: + nla_nest_cancel(msg, act_stats); +action_info_nest_cancel: + nla_nest_cancel(msg, act_info); nla_put_failure: nla_nest_cancel(msg, reload_stats_attr); return -EMSGSIZE; @@ -755,6 +772,8 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; + /* Hold rtnl lock while accessing port's netdev attributes. */ + rtnl_lock(); spin_lock_bh(&devlink_port->type_lock); if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure_type_locked; @@ -763,9 +782,10 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, devlink_port->desired_type)) goto nla_put_failure_type_locked; if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { + struct net *net = devlink_net(devlink_port->devlink); struct net_device *netdev = devlink_port->type_dev; - if (netdev && + if (netdev && net_eq(net, dev_net(netdev)) && (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, netdev->ifindex) || nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, @@ -781,6 +801,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, goto nla_put_failure_type_locked; } spin_unlock_bh(&devlink_port->type_lock); + rtnl_unlock(); if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure; if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack)) @@ -791,6 +812,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, nla_put_failure_type_locked: spin_unlock_bh(&devlink_port->type_lock); + rtnl_unlock(); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; @@ -1448,7 +1470,7 @@ static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index, pool_index, &cur, &max); if (err && err != -EOPNOTSUPP) - return err; + goto sb_occ_get_failure; if (!err) { if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur)) goto nla_put_failure; @@ -1461,8 +1483,10 @@ static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, return 0; nla_put_failure: + err = -EMSGSIZE; +sb_occ_get_failure: genlmsg_cancel(msg, hdr); - return -EMSGSIZE; + return err; } static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb, @@ -8254,8 +8278,6 @@ static int __devlink_port_attrs_set(struct devlink_port *devlink_port, { struct devlink_port_attrs *attrs = &devlink_port->attrs; - if (WARN_ON(devlink_port->registered)) - return -EEXIST; devlink_port->attrs_set = true; attrs->flavour = flavour; if (attrs->switch_id.id_len) { @@ -8279,6 +8301,8 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port, { int ret; + if (WARN_ON(devlink_port->registered)) + return; devlink_port->attrs = *attrs; ret = __devlink_port_attrs_set(devlink_port, attrs->flavour); if (ret) @@ -8301,6 +8325,8 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 contro struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; + if (WARN_ON(devlink_port->registered)) + return; ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_PF); if (ret) @@ -8326,6 +8352,8 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; + if (WARN_ON(devlink_port->registered)) + return; ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_VF); if (ret) diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index d4474c812b64..715b67f6c62f 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -381,10 +381,8 @@ static void __flow_block_indr_cleanup(void (*release)(void *cb_priv), list_for_each_entry_safe(this, next, &flow_block_indr_list, indr.list) { if (this->release == release && - this->indr.cb_priv == cb_priv) { + this->indr.cb_priv == cb_priv) list_move(&this->indr.list, cleanup_list); - return; - } } } diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index e095fb871d91..6eb2e5ec2c50 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -99,9 +99,14 @@ void gro_cells_destroy(struct gro_cells *gcells) struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); napi_disable(&cell->napi); - netif_napi_del(&cell->napi); + __netif_napi_del(&cell->napi); __skb_queue_purge(&cell->napi_skbs); } + /* This barrier is needed because netpoll could access dev->napi_list + * under rcu protection. + */ + synchronize_net(); + free_percpu(gcells->cells); gcells->cells = NULL; } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 7d3438215f32..2f7940bcf715 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -39,12 +39,11 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, { int ret; - /* Preempt disable is needed to protect per-cpu redirect_info between - * BPF prog and skb_do_redirect(). The call_rcu in bpf_prog_put() and - * access to maps strictly require a rcu_read_lock() for protection, - * mixing with BH RCU lock doesn't work. + /* Migration disable and BH disable are needed to protect per-cpu + * redirect_info between BPF prog and skb_do_redirect(). */ - preempt_disable(); + migrate_disable(); + local_bh_disable(); bpf_compute_data_pointers(skb); ret = bpf_prog_run_save_cb(lwt->prog, skb); @@ -78,7 +77,8 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, break; } - preempt_enable(); + local_bh_enable(); + migrate_enable(); return ret; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8e39e28b0a8d..9500d28a43b0 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -235,6 +235,8 @@ static int neigh_forced_gc(struct neigh_table *tbl) write_lock(&n->lock); if ((n->nud_state == NUD_FAILED) || + (tbl->is_multicast && + tbl->is_multicast(n->primary_key)) || time_after(tref, n->updated)) remove = true; write_unlock(&n->lock); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index c310c7c1cef7..960948290001 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -29,6 +29,7 @@ #include <linux/slab.h> #include <linux/export.h> #include <linux/if_vlan.h> +#include <net/dsa.h> #include <net/tcp.h> #include <net/udp.h> #include <net/addrconf.h> @@ -657,15 +658,15 @@ EXPORT_SYMBOL_GPL(__netpoll_setup); int netpoll_setup(struct netpoll *np) { - struct net_device *ndev = NULL; + struct net_device *ndev = NULL, *dev = NULL; + struct net *net = current->nsproxy->net_ns; struct in_device *in_dev; int err; rtnl_lock(); - if (np->dev_name[0]) { - struct net *net = current->nsproxy->net_ns; + if (np->dev_name[0]) ndev = __dev_get_by_name(net, np->dev_name); - } + if (!ndev) { np_err(np, "%s doesn't exist, aborting\n", np->dev_name); err = -ENODEV; @@ -673,6 +674,19 @@ int netpoll_setup(struct netpoll *np) } dev_hold(ndev); + /* bring up DSA management network devices up first */ + for_each_netdev(net, dev) { + if (!netdev_uses_dsa(dev)) + continue; + + err = dev_change_flags(dev, dev->flags | IFF_UP, NULL); + if (err < 0) { + np_err(np, "%s failed to open %s\n", + np->dev_name, dev->name); + goto put; + } + } + if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); err = -EBUSY; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1ba8f0163744..e578544b2cc7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4549,7 +4549,7 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk) if (skb && (skb_next = skb_peek(q))) { icmp_next = is_icmp_err_skb(skb_next); if (icmp_next) - sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_origin; + sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno; } spin_unlock_irqrestore(&q->lock, flags); @@ -5786,6 +5786,9 @@ int skb_mpls_dec_ttl(struct sk_buff *skb) if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; + if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) + return -ENOMEM; + lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry); ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; if (!--ttl) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 654182ecf87b..25cdbb20f3a0 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -170,10 +170,12 @@ static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i, struct scatterlist *sge = sk_msg_elem(msg, i); u32 len = sge->length; - if (charge) - sk_mem_uncharge(sk, len); - if (!msg->skb) + /* When the skb owns the memory we free it from consume_skb path. */ + if (!msg->skb) { + if (charge) + sk_mem_uncharge(sk, len); put_page(sg_page(sge)); + } memset(sge, 0, sizeof(*sge)); return len; } @@ -397,28 +399,45 @@ out: } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); -static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, + struct sk_buff *skb) { - struct sock *sk = psock->sk; - int copied = 0, num_sge; struct sk_msg *msg; + if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) + return NULL; + + if (!sk_rmem_schedule(sk, skb, skb->truesize)) + return NULL; + msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); if (unlikely(!msg)) - return -EAGAIN; - if (!sk_rmem_schedule(sk, skb, skb->len)) { - kfree(msg); - return -EAGAIN; - } + return NULL; sk_msg_init(msg); + return msg; +} + +static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, + struct sk_psock *psock, + struct sock *sk, + struct sk_msg *msg) +{ + int num_sge, copied; + + /* skb linearize may fail with ENOMEM, but lets simply try again + * later if this happens. Under memory pressure we don't want to + * drop the skb. We need to linearize the skb so that the mapping + * in skb_to_sgvec can not error. + */ + if (skb_linearize(skb)) + return -EAGAIN; num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); if (unlikely(num_sge < 0)) { kfree(msg); return num_sge; } - sk_mem_charge(sk, skb->len); copied = skb->len; msg->sg.start = 0; msg->sg.size = copied; @@ -430,6 +449,48 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) return copied; } +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb); + +static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +{ + struct sock *sk = psock->sk; + struct sk_msg *msg; + + /* If we are receiving on the same sock skb->sk is already assigned, + * skip memory accounting and owner transition seeing it already set + * correctly. + */ + if (unlikely(skb->sk == sk)) + return sk_psock_skb_ingress_self(psock, skb); + msg = sk_psock_create_ingress_msg(sk, skb); + if (!msg) + return -EAGAIN; + + /* This will transition ownership of the data from the socket where + * the BPF program was run initiating the redirect to the socket + * we will eventually receive this data on. The data will be released + * from skb_consume found in __tcp_bpf_recvmsg() after its been copied + * into user buffers. + */ + skb_set_owner_r(skb, sk); + return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); +} + +/* Puts an skb on the ingress queue of the socket already assigned to the + * skb. In this case we do not need to check memory limits or skb_set_owner_r + * because the skb is already accounted for here. + */ +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb) +{ + struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); + struct sock *sk = psock->sk; + + if (unlikely(!msg)) + return -EAGAIN; + sk_msg_init(msg); + return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); +} + static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len, bool ingress) { @@ -789,7 +850,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, * retrying later from workqueue. */ if (skb_queue_empty(&psock->ingress_skb)) { - err = sk_psock_skb_ingress(psock, skb); + err = sk_psock_skb_ingress_self(psock, skb); } if (err < 0) { skb_queue_tail(&psock->ingress_skb, skb); diff --git a/net/core/xdp.c b/net/core/xdp.c index 48aba933a5a8..d900cebc0acd 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -335,11 +335,10 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); * scenarios (e.g. queue full), it is possible to return the xdp_frame * while still leveraging this protection. The @napi_direct boolean * is used for those calls sites. Thus, allowing for faster recycling - * of xdp_frames/pages in those cases. This path is never used by the - * MEM_TYPE_XSK_BUFF_POOL memory type, so it's explicitly not part of - * the switch-statement. + * of xdp_frames/pages in those cases. */ -static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct) +static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, + struct xdp_buff *xdp) { struct xdp_mem_allocator *xa; struct page *page; @@ -361,6 +360,10 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct) page = virt_to_page(data); /* Assumes order0 page*/ put_page(page); break; + case MEM_TYPE_XSK_BUFF_POOL: + /* NB! Only valid from an xdp_buff! */ + xsk_buff_free(xdp); + break; default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ WARN(1, "Incorrect XDP memory type (%d) usage", mem->type); @@ -370,19 +373,19 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct) void xdp_return_frame(struct xdp_frame *xdpf) { - __xdp_return(xdpf->data, &xdpf->mem, false); + __xdp_return(xdpf->data, &xdpf->mem, false, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { - __xdp_return(xdpf->data, &xdpf->mem, true); + __xdp_return(xdpf->data, &xdpf->mem, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); void xdp_return_buff(struct xdp_buff *xdp) { - __xdp_return(xdp->data, &xdp->rxq->mem, true); + __xdp_return(xdp->data, &xdp->rxq->mem, true, xdp); } /* Only called for MEM_TYPE_PAGE_POOL see xdp.h */ @@ -400,18 +403,6 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem) } EXPORT_SYMBOL_GPL(__xdp_release_frame); -bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, - struct netdev_bpf *bpf) -{ - if (info->prog && (bpf->flags ^ info->flags) & XDP_FLAGS_MODES) { - NL_SET_ERR_MSG(bpf->extack, - "program loaded with different flags"); - return false; - } - return true; -} -EXPORT_SYMBOL_GPL(xdp_attachment_flags_ok); - void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index bb3d70664dde..b0b6e6a4784e 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -427,7 +427,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); if (*own_req) ireq->ireq_opt = NULL; else diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index ef4ab28cfde0..78ee1b5acf1f 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -533,7 +533,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, dccp_done(newsk); goto out; } - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); /* Clone pktoptions received with SYN, if we own the req */ if (*own_req && ireq->pktopts) { newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC); diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index 1fb3603d92ad..0515d6604b3b 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -628,6 +628,8 @@ int ethnl_parse_bitset(unsigned long *val, unsigned long *mask, return ret; change_bits = nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]); + if (change_bits > nbits) + change_bits = nbits; bitmap_from_arr32(val, nla_data(tb[ETHTOOL_A_BITSET_VALUE]), change_bits); if (change_bits < nbits) diff --git a/net/ethtool/features.c b/net/ethtool/features.c index 8ee4cdbd6b82..1c9f4df273bd 100644 --- a/net/ethtool/features.c +++ b/net/ethtool/features.c @@ -280,7 +280,7 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) active_diff_mask, compact); } if (mod) - ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF, NULL); + netdev_features_change(dev); out_rtnl: rtnl_unlock(); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 687971d83b4e..922dd73e5740 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -125,6 +125,7 @@ static int arp_constructor(struct neighbour *neigh); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb); static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb); static void parp_redo(struct sk_buff *skb); +static int arp_is_multicast(const void *pkey); static const struct neigh_ops arp_generic_ops = { .family = AF_INET, @@ -156,6 +157,7 @@ struct neigh_table arp_tbl = { .key_eq = arp_key_eq, .constructor = arp_constructor, .proxy_redo = parp_redo, + .is_multicast = arp_is_multicast, .id = "arp_cache", .parms = { .tbl = &arp_tbl, @@ -928,6 +930,10 @@ static void parp_redo(struct sk_buff *skb) arp_process(dev_net(skb->dev), NULL, skb); } +static int arp_is_multicast(const void *pkey) +{ + return ipv4_is_multicast(*((__be32 *)pkey)); +} /* * Receive an arp request from the device layer. diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 86a23e4a6a50..cdf6ec5aa45d 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -696,7 +696,7 @@ int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, cfg->fc_gw4 = *((__be32 *)via->rtvia_addr); break; case AF_INET6: -#ifdef CONFIG_IPV6 +#if IS_ENABLED(CONFIG_IPV6) if (alen != sizeof(struct in6_addr)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA"); return -EINVAL; @@ -825,7 +825,7 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, if (has_gw && has_via) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); - goto errout; + return -EINVAL; } return 0; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 4148f5f78f31..f60869acbef0 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -787,7 +787,7 @@ static void reqsk_queue_hash_req(struct request_sock *req, timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); - inet_ehash_insert(req_to_sk(req), NULL); + inet_ehash_insert(req_to_sk(req), NULL, NULL); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 366a4507b5a3..93474b1bea4e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -479,8 +479,10 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, r->idiag_inode = 0; if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, - inet_rsk(reqsk)->ir_mark)) + inet_rsk(reqsk)->ir_mark)) { + nlmsg_cancel(skb, nlh); return -EMSGSIZE; + } nlmsg_end(skb, nlh); return 0; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 8cbe74313f38..45fb450b4522 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -20,6 +20,9 @@ #include <net/addrconf.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/inet6_hashtables.h> +#endif #include <net/secure_seq.h> #include <net/ip.h> #include <net/tcp.h> @@ -508,10 +511,52 @@ static u32 inet_sk_port_offset(const struct sock *sk) inet->inet_dport); } -/* insert a socket into ehash, and eventually remove another one - * (The another one can be a SYN_RECV or TIMEWAIT +/* Searches for an exsiting socket in the ehash bucket list. + * Returns true if found, false otherwise. */ -bool inet_ehash_insert(struct sock *sk, struct sock *osk) +static bool inet_ehash_lookup_by_sk(struct sock *sk, + struct hlist_nulls_head *list) +{ + const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport, sk->sk_num); + const int sdif = sk->sk_bound_dev_if; + const int dif = sk->sk_bound_dev_if; + const struct hlist_nulls_node *node; + struct net *net = sock_net(sk); + struct sock *esk; + + INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr); + + sk_nulls_for_each_rcu(esk, node, list) { + if (esk->sk_hash != sk->sk_hash) + continue; + if (sk->sk_family == AF_INET) { + if (unlikely(INET_MATCH(esk, net, acookie, + sk->sk_daddr, + sk->sk_rcv_saddr, + ports, dif, sdif))) { + return true; + } + } +#if IS_ENABLED(CONFIG_IPV6) + else if (sk->sk_family == AF_INET6) { + if (unlikely(INET6_MATCH(esk, net, + &sk->sk_v6_daddr, + &sk->sk_v6_rcv_saddr, + ports, dif, sdif))) { + return true; + } + } +#endif + } + return false; +} + +/* Insert a socket into ehash, and eventually remove another one + * (The another one can be a SYN_RECV or TIMEWAIT) + * If an existing socket already exists, socket sk is not inserted, + * and sets found_dup_sk parameter to true. + */ +bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct hlist_nulls_head *list; @@ -530,16 +575,23 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk) if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); ret = sk_nulls_del_node_init_rcu(osk); + } else if (found_dup_sk) { + *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); + if (*found_dup_sk) + ret = false; } + if (ret) __sk_nulls_add_node_rcu(sk, list); + spin_unlock(lock); + return ret; } -bool inet_ehash_nolisten(struct sock *sk, struct sock *osk) +bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk) { - bool ok = inet_ehash_insert(sk, osk); + bool ok = inet_ehash_insert(sk, osk, found_dup_sk); if (ok) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -583,7 +635,7 @@ int __inet_hash(struct sock *sk, struct sock *osk) int err = 0; if (sk->sk_state != TCP_LISTEN) { - inet_ehash_nolisten(sk, osk); + inet_ehash_nolisten(sk, osk, NULL); return 0; } WARN_ON(!sk_unhashed(sk)); @@ -679,7 +731,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, tb = inet_csk(sk)->icsk_bind_hash; spin_lock_bh(&head->lock); if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) { - inet_ehash_nolisten(sk, NULL); + inet_ehash_nolisten(sk, NULL, NULL); spin_unlock_bh(&head->lock); return 0; } @@ -758,7 +810,7 @@ ok: inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); - inet_ehash_nolisten(sk, (struct sock *)tw); + inet_ehash_nolisten(sk, (struct sock *)tw, NULL); } if (tw) inet_twsk_bind_unhash(tw, hinfo); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 25f1caf5abf9..e25be2d01a7a 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -263,7 +263,7 @@ static int iptunnel_pmtud_check_icmp(struct sk_buff *skb, int mtu) const struct icmphdr *icmph = icmp_hdr(skb); const struct iphdr *iph = ip_hdr(skb); - if (mtu <= 576 || iph->frag_off != htons(IP_DF)) + if (mtu < 576 || iph->frag_off != htons(IP_DF)) return 0; if (ipv4_is_lbcast(iph->daddr) || ipv4_is_multicast(iph->daddr) || @@ -359,7 +359,7 @@ static int iptunnel_pmtud_check_icmpv6(struct sk_buff *skb, int mtu) __be16 frag_off; int offset; - if (mtu <= IPV6_MIN_MTU) + if (mtu < IPV6_MIN_MTU) return 0; if (stype == IPV6_ADDR_ANY || stype == IPV6_ADDR_MULTICAST || diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index d1e04d2b5170..563b62b76a5f 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -203,7 +203,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); - private = READ_ONCE(table->private); /* Address dependency. */ + private = rcu_access_pointer(table->private); cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct arpt_entry **)private->jumpstack[cpu]; @@ -649,7 +649,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); /* We need atomic snapshot of counters: rest doesn't change * (other than comefrom, which userspace doesn't care @@ -673,7 +673,7 @@ static int copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct arpt_entry *e; struct xt_counters *counters; - struct xt_table_info *private = table->private; + struct xt_table_info *private = xt_table_get_private_protected(table); int ret = 0; void *loc_cpu_entry; @@ -807,7 +807,7 @@ static int get_info(struct net *net, void __user *user, const int *len) t = xt_request_find_table_lock(net, NFPROTO_ARP, name); if (!IS_ERR(t)) { struct arpt_getinfo info; - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); #ifdef CONFIG_COMPAT struct xt_table_info tmp; @@ -860,7 +860,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr, t = xt_find_table_lock(net, NFPROTO_ARP, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); if (get.size == private->size) ret = copy_entries_to_user(private->size, @@ -1017,7 +1017,7 @@ static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) } local_bh_disable(); - private = t->private; + private = xt_table_get_private_protected(t); if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1330,7 +1330,7 @@ static int compat_copy_entries_to_user(unsigned int total_size, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); void __user *pos; unsigned int size; int ret = 0; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index f15bc21d7301..6e2851f8d3a3 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -258,7 +258,7 @@ ipt_do_table(struct sk_buff *skb, WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); - private = READ_ONCE(table->private); /* Address dependency. */ + private = rcu_access_pointer(table->private); cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; @@ -791,7 +791,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -815,7 +815,7 @@ copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct ipt_entry *e; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); int ret = 0; const void *loc_cpu_entry; @@ -964,7 +964,7 @@ static int get_info(struct net *net, void __user *user, const int *len) t = xt_request_find_table_lock(net, AF_INET, name); if (!IS_ERR(t)) { struct ipt_getinfo info; - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); #ifdef CONFIG_COMPAT struct xt_table_info tmp; @@ -1018,7 +1018,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr, t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); @@ -1173,7 +1173,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len) } local_bh_disable(); - private = t->private; + private = xt_table_get_private_protected(t); if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1543,7 +1543,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); void __user *pos; unsigned int size; int ret = 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index dc2a399cd9f4..9f43abeac3a8 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3222,7 +3222,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.daddr = dst; fl4.saddr = src; - fl4.flowi4_tos = rtm->rtm_tos; + fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK; fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; @@ -3246,8 +3246,9 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; - err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos, - dev, &res); + err = ip_route_input_rcu(skb, dst, src, + rtm->rtm_tos & IPTOS_RT_MASK, dev, + &res); rt = skb_rtable(skb); if (err == 0 && rt->dst.error) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 6ac473b47f30..00dc3f943c80 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -331,7 +331,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) __u32 cookie = ntohl(th->ack_seq) - 1; struct sock *ret = sk; struct request_sock *req; - int mss; + int full_space, mss; struct rtable *rt; __u8 rcv_wscale; struct flowi4 fl4; @@ -427,8 +427,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) /* Try to redo what tcp_v4_send_synack did. */ req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); + /* limit the window selection if the user enforce a smaller rx buffer */ + full_space = tcp_full_space(sk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) + req->rsk_window_clamp = full_space; - tcp_select_initial_window(sk, tcp_full_space(sk), req->mss, + tcp_select_initial_window(sk, full_space, req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 6c4d79baff26..6ea3dc2e4219 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -945,7 +945,7 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) filter_expired = after(tcp_jiffies32, bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ); if (rs->rtt_us >= 0 && - (rs->rtt_us <= bbr->min_rtt_us || + (rs->rtt_us < bbr->min_rtt_us || (filter_expired && !rs->is_ack_delayed))) { bbr->min_rtt_us = rs->rtt_us; bbr->min_rtt_stamp = tcp_jiffies32; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 37f4cb2bba5c..bc7d2a586e18 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -15,8 +15,8 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, { struct iov_iter *iter = &msg->msg_iter; int peek = flags & MSG_PEEK; - int i, ret, copied = 0; struct sk_msg *msg_rx; + int i, copied = 0; msg_rx = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list); @@ -37,17 +37,16 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, page = sg_page(sge); if (copied + copy > len) copy = len - copied; - ret = copy_page_to_iter(page, sge->offset, copy, iter); - if (ret != copy) { - msg_rx->sg.start = i; - return -EFAULT; - } + copy = copy_page_to_iter(page, sge->offset, copy, iter); + if (!copy) + return copied ? copied : -EFAULT; copied += copy; if (likely(!peek)) { sge->offset += copy; sge->length -= copy; - sk_mem_uncharge(sk, copy); + if (!msg_rx->skb) + sk_mem_uncharge(sk, copy); msg_rx->sg.size -= copy; if (!sge->length) { @@ -56,6 +55,11 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, put_page(page); } } else { + /* Lets not optimize peek case if copy_page_to_iter + * didn't copy the entire length lets just break. + */ + if (copy != sge->length) + return copied; sk_msg_iter_var_next(i); } diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index db47ac24d057..563d016e7478 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -198,6 +198,11 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); + if (ca->flags & TCP_CONG_NEEDS_ECN) + INET_ECN_xmit(sk); + else + INET_ECN_dontxmit(sk); + if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) tcp_init_congestion_control(sk); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 389d1b340248..ef4bdb038a4b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -510,7 +510,6 @@ static void tcp_init_buffer_space(struct sock *sk) if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) tcp_sndbuf_expand(sk); - tp->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND * tp->advmss); tcp_mstamp_refresh(tp); tp->rcvq_space.time = tp->tcp_mstamp; tp->rcvq_space.seq = tp->copied_seq; @@ -534,6 +533,8 @@ static void tcp_init_buffer_space(struct sock *sk) tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp); tp->snd_cwnd_stamp = tcp_jiffies32; + tp->rcvq_space.space = min3(tp->rcv_ssthresh, tp->rcv_wnd, + (u32)TCP_INIT_CWND * tp->advmss); } /* 4. Recalculate window clamp after socket hit its memory bounds. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7352c097ae48..595dcc3afac5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -980,17 +980,23 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); - tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos : inet_sk(sk)->tos; - if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); + tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? + (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | + (inet_sk(sk)->tos & INET_ECN_MASK) : + inet_sk(sk)->tos; + + if (!INET_ECN_is_capable(tos) && + tcp_bpf_ca_needs_ecn((struct sock *)req)) + tos |= INET_ECN_ECT_0; + rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, rcu_dereference(ireq->ireq_opt), - tos & ~INET_ECN_MASK); + tos); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -1498,6 +1504,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, bool *own_req) { struct inet_request_sock *ireq; + bool found_dup_sk = false; struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; @@ -1535,7 +1542,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = prandom_u32(); - /* Set ToS of the new socket based upon the value of incoming SYN. */ + /* Set ToS of the new socket based upon the value of incoming SYN. + * ECT bits are set later in tcp_init_transfer(). + */ if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; @@ -1575,12 +1584,22 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), + &found_dup_sk); if (likely(*own_req)) { tcp_move_syn(newtp, req); ireq->ireq_opt = NULL; } else { - newinet->inet_opt = NULL; + if (!req_unhash && found_dup_sk) { + /* This code path should only be executed in the + * syncookie case only + */ + bh_unlock_sock(newsk); + sock_put(newsk); + newsk = NULL; + } else { + newinet->inet_opt = NULL; + } } return newsk; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index bf48cd73e967..99011768c264 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1880,7 +1880,8 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) * window, and remember whether we were cwnd-limited then. */ if (!before(tp->snd_una, tp->max_packets_seq) || - tp->packets_out > tp->max_packets_out) { + tp->packets_out > tp->max_packets_out || + is_cwnd_limited) { tp->max_packets_out = tp->packets_out; tp->max_packets_seq = tp->snd_nxt; tp->is_cwnd_limited = is_cwnd_limited; @@ -2702,6 +2703,10 @@ repair: else tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED); + is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); + if (likely(sent_pkts || is_cwnd_limited)) + tcp_cwnd_validate(sk, is_cwnd_limited); + if (likely(sent_pkts)) { if (tcp_in_cwnd_reduction(sk)) tp->prr_out += sent_pkts; @@ -2709,8 +2714,6 @@ repair: /* Send one loss probe per tail loss episode. */ if (push_one != 2) tcp_schedule_loss_probe(sk, false); - is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); - tcp_cwnd_validate(sk, is_cwnd_limited); return false; } return !tp->packets_out && !tcp_write_queue_empty(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 09f0a23d1a01..9eeebd4a0054 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2173,7 +2173,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) __skb_pull(skb, skb_transport_offset(skb)); ret = udp_queue_rcv_one_skb(sk, skb); if (ret > 0) - ip_protocol_deliver_rcu(dev_net(skb->dev), skb, -ret); + ip_protocol_deliver_rcu(dev_net(skb->dev), skb, ret); } return 0; } diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index e67a66fbf27b..c62805cd3131 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -366,7 +366,7 @@ out: static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *skb) { - struct udphdr *uh = udp_hdr(skb); + struct udphdr *uh = udp_gro_udphdr(skb); struct sk_buff *pp = NULL; struct udphdr *uh2; struct sk_buff *p; @@ -500,12 +500,22 @@ out: } EXPORT_SYMBOL(udp_gro_receive); +static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, + __be16 dport) +{ + const struct iphdr *iph = skb_gro_network_header(skb); + + return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, + iph->daddr, dport, inet_iif(skb), + inet_sdif(skb), &udp_table, NULL); +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); + struct sock *sk = NULL; struct sk_buff *pp; - struct sock *sk; if (unlikely(!uh)) goto flush; @@ -523,7 +533,10 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) skip: NAPI_GRO_CB(skb)->is_ipv6 = 0; rcu_read_lock(); - sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL; + + if (static_branch_unlikely(&udp_encap_needed_key)) + sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest); + pp = udp_gro_receive(head, skb, uh, sk); rcu_read_unlock(); return pp; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 01146b66d666..8b6eb384bac7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5022,8 +5022,10 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, return -EMSGSIZE; if (args->netnsid >= 0 && - nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) { + nlmsg_cancel(skb, nlh); return -EMSGSIZE; + } put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || @@ -5054,8 +5056,10 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, return -EMSGSIZE; if (args->netnsid >= 0 && - nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) { + nlmsg_cancel(skb, nlh); return -EMSGSIZE; + } put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 || diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 642fc6ac13d2..8a22486cf270 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -306,7 +306,9 @@ static int ip6addrlbl_del(struct net *net, /* add default label */ static int __net_init ip6addrlbl_net_init(struct net *net) { - int err = 0; + struct ip6addrlbl_entry *p = NULL; + struct hlist_node *n; + int err; int i; ADDRLABEL(KERN_DEBUG "%s\n", __func__); @@ -315,14 +317,20 @@ static int __net_init ip6addrlbl_net_init(struct net *net) INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head); for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) { - int ret = ip6addrlbl_add(net, - ip6addrlbl_init_table[i].prefix, - ip6addrlbl_init_table[i].prefixlen, - 0, - ip6addrlbl_init_table[i].label, 0); - /* XXX: should we free all rules when we catch an error? */ - if (ret && (!err || err != -ENOMEM)) - err = ret; + err = ip6addrlbl_add(net, + ip6addrlbl_init_table[i].prefix, + ip6addrlbl_init_table[i].prefixlen, + 0, + ip6addrlbl_init_table[i].label, 0); + if (err) + goto err_ip6addrlbl_add; + } + return 0; + +err_ip6addrlbl_add: + hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { + hlist_del_rcu(&p->list); + kfree_rcu(p, rcu); } return err; } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index d88d97617f7e..440080da805b 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -588,7 +588,8 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); memset(ah->auth_data, 0, ahp->icv_trunc_len); - if (ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN)) + err = ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN); + if (err) goto out_free; ip6h->priority = 0; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 931b186d2e48..cf6e1380b527 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1133,8 +1133,13 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu, return; if (rt->dst.dev) { - dev->needed_headroom = rt->dst.dev->hard_header_len + - t_hlen; + unsigned short dst_len = rt->dst.dev->hard_header_len + + t_hlen; + + if (t->dev->header_ops) + dev->hard_header_len = dst_len; + else + dev->needed_headroom = dst_len; if (set_mtu) { dev->mtu = rt->dst.dev->mtu - t_hlen; @@ -1159,7 +1164,12 @@ static int ip6gre_calc_hlen(struct ip6_tnl *tunnel) tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; t_hlen = tunnel->hlen + sizeof(struct ipv6hdr); - tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; + + if (tunnel->dev->header_ops) + tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen; + else + tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; + return t_hlen; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 27f29b957ee7..76717478f173 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -81,6 +81,7 @@ static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); static int pndisc_constructor(struct pneigh_entry *n); static void pndisc_destructor(struct pneigh_entry *n); static void pndisc_redo(struct sk_buff *skb); +static int ndisc_is_multicast(const void *pkey); static const struct neigh_ops ndisc_generic_ops = { .family = AF_INET6, @@ -115,6 +116,7 @@ struct neigh_table nd_tbl = { .pconstructor = pndisc_constructor, .pdestructor = pndisc_destructor, .proxy_redo = pndisc_redo, + .is_multicast = ndisc_is_multicast, .allow_add = ndisc_allow_add, .id = "ndisc_cache", .parms = { @@ -1706,6 +1708,11 @@ static void pndisc_redo(struct sk_buff *skb) kfree_skb(skb); } +static int ndisc_is_multicast(const void *pkey) +{ + return ipv6_addr_is_multicast((struct in6_addr *)pkey); +} + static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 2e2119bfcf13..c4f532f4d311 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -280,7 +280,7 @@ ip6t_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); - private = READ_ONCE(table->private); /* Address dependency. */ + private = rcu_access_pointer(table->private); cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; @@ -807,7 +807,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -831,7 +831,7 @@ copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct ip6t_entry *e; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); int ret = 0; const void *loc_cpu_entry; @@ -980,7 +980,7 @@ static int get_info(struct net *net, void __user *user, const int *len) t = xt_request_find_table_lock(net, AF_INET6, name); if (!IS_ERR(t)) { struct ip6t_getinfo info; - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); #ifdef CONFIG_COMPAT struct xt_table_info tmp; @@ -1035,7 +1035,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr, t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { - struct xt_table_info *private = t->private; + struct xt_table_info *private = xt_table_get_private_protected(t); if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); @@ -1189,7 +1189,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len) } local_bh_disable(); - private = t->private; + private = xt_table_get_private_protected(t); if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1552,7 +1552,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); void __user *pos; unsigned int size; int ret = 0; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 054d287eb13d..c129ad334eb3 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -440,6 +440,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { u16 savethdr = skb->transport_header; + u8 nexthdr = NEXTHDR_FRAGMENT; int fhoff, nhoff, ret; struct frag_hdr *fhdr; struct frag_queue *fq; @@ -455,6 +456,14 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) return 0; + /* Discard the first fragment if it does not include all headers + * RFC 8200, Section 4.5 + */ + if (ipv6frag_thdr_truncated(skb, fhoff, &nexthdr)) { + pr_debug("Drop incomplete fragment\n"); + return 0; + } + if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr))) return -ENOMEM; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index c8cf1bbad74a..47a0dc46cbdb 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -324,9 +324,8 @@ static int ipv6_frag_rcv(struct sk_buff *skb) struct frag_queue *fq; const struct ipv6hdr *hdr = ipv6_hdr(skb); struct net *net = dev_net(skb_dst(skb)->dev); - __be16 frag_off; - int iif, offset; u8 nexthdr; + int iif; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED) goto fail_hdr; @@ -362,24 +361,11 @@ static int ipv6_frag_rcv(struct sk_buff *skb) * the source of the fragment, with the Pointer field set to zero. */ nexthdr = hdr->nexthdr; - offset = ipv6_skip_exthdr(skb, skb_transport_offset(skb), &nexthdr, &frag_off); - if (offset >= 0) { - /* Check some common protocols' header */ - if (nexthdr == IPPROTO_TCP) - offset += sizeof(struct tcphdr); - else if (nexthdr == IPPROTO_UDP) - offset += sizeof(struct udphdr); - else if (nexthdr == IPPROTO_ICMPV6) - offset += sizeof(struct icmp6hdr); - else - offset += 1; - - if (!(frag_off & htons(IP6_OFFSET)) && offset > skb->len) { - __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), - IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0); - return -1; - } + if (ipv6frag_thdr_truncated(skb, skb_transport_offset(skb), &nexthdr)) { + __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), + IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0); + return -1; } iif = skb->dev ? skb->dev->ifindex : 0; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 5e2c34c0ac97..5e7983cb6154 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1128,7 +1128,6 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) if (tdev && !netif_is_l3_master(tdev)) { int t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr); dev->mtu = tdev->mtu - t_hlen; if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; @@ -1426,7 +1425,6 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->priv_destructor = ipip6_dev_free; dev->type = ARPHRD_SIT; - dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - t_hlen; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index e796a64be308..9b6cae1e49d9 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -136,7 +136,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) __u32 cookie = ntohl(th->ack_seq) - 1; struct sock *ret = sk; struct request_sock *req; - int mss; + int full_space, mss; struct dst_entry *dst; __u8 rcv_wscale; u32 tsoff = 0; @@ -241,7 +241,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) } req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); - tcp_select_initial_window(sk, tcp_full_space(sk), req->mss, + /* limit the window selection if the user enforce a smaller rx buffer */ + full_space = tcp_full_space(sk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) + req->rsk_window_clamp = full_space; + + tcp_select_initial_window(sk, full_space, req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8db59f4e5f13..991dc36f95ff 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -527,15 +527,21 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, if (np->repflow && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); + tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? + (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | + (np->tclass & INET_ECN_MASK) : + np->tclass; + + if (!INET_ECN_is_capable(tclass) && + tcp_bpf_ca_needs_ecn((struct sock *)req)) + tclass |= INET_ECN_ECT_0; + rcu_read_lock(); opt = ireq->ipv6_opt; - tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos : np->tclass; if (!opt) opt = rcu_dereference(np->opt); err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, - tclass & ~INET_ECN_MASK, - sk->sk_priority); + tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -1193,6 +1199,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * const struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct ipv6_txoptions *opt; struct inet_sock *newinet; + bool found_dup_sk = false; struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG @@ -1314,7 +1321,9 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * if (np->repflow) newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); - /* Set ToS of the new socket based upon the value of incoming SYN. */ + /* Set ToS of the new socket based upon the value of incoming SYN. + * ECT bits are set later in tcp_init_transfer(). + */ if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; @@ -1368,7 +1377,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * tcp_done(newsk); goto out; } - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), + &found_dup_sk); if (*own_req) { tcp_move_syn(newtp, req); @@ -1383,6 +1393,15 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * skb_set_owner_r(newnp->pktoptions, newsk); } } + } else { + if (!req_unhash && found_dup_sk) { + /* This code path should only be executed in the + * syncookie case only + */ + bh_unlock_sock(newsk); + sock_put(newsk); + newsk = NULL; + } } return newsk; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 584157a07759..f9e888d1b9af 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -111,12 +111,22 @@ out: return segs; } +static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport, + __be16 dport) +{ + const struct ipv6hdr *iph = skb_gro_network_header(skb); + + return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, + &iph->daddr, dport, inet6_iif(skb), + inet6_sdif(skb), &udp_table, NULL); +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); + struct sock *sk = NULL; struct sk_buff *pp; - struct sock *sk; if (unlikely(!uh)) goto flush; @@ -135,7 +145,10 @@ struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) skip: NAPI_GRO_CB(skb)->is_ipv6 = 1; rcu_read_lock(); - sk = static_branch_unlikely(&udpv6_encap_needed_key) ? udp6_lib_lookup_skb(skb, uh->source, uh->dest) : NULL; + + if (static_branch_unlikely(&udpv6_encap_needed_key)) + sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest); + pp = udp_gro_receive(head, skb, uh, sk); rcu_read_unlock(); return pp; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index d80572074667..db7d888914fa 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1434,7 +1434,8 @@ static int iucv_sock_shutdown(struct socket *sock, int how) break; } - if (how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) { + if ((how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) && + sk->sk_state == IUCV_CONNECTED) { if (iucv->transport == AF_IUCV_TRANS_IUCV) { txmsg.class = 0; txmsg.tag = 0; @@ -1644,7 +1645,7 @@ static int iucv_callback_connreq(struct iucv_path *path, } /* Create the new socket */ - nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0); + nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0); if (!nsk) { err = pr_iucv->path_sever(path, user_data); iucv_path_free(path); @@ -1850,7 +1851,7 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb) goto out; } - nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0); + nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0); bh_lock_sock(sk); if ((sk->sk_state != IUCV_LISTEN) || sk_acceptq_is_full(sk) || diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 1be775979132..44154cc596cd 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -948,6 +948,8 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) return ret; } + set_bit(SDATA_STATE_RUNNING, &sdata->state); + ret = ieee80211_check_queues(sdata, NL80211_IFTYPE_MONITOR); if (ret) { kfree(sdata); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 48f31ac9233c..620ecf922408 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -60,6 +60,7 @@ static struct mesh_table *mesh_table_alloc(void) atomic_set(&newtbl->entries, 0); spin_lock_init(&newtbl->gates_lock); spin_lock_init(&newtbl->walk_lock); + rhashtable_init(&newtbl->rhead, &mesh_rht_params); return newtbl; } @@ -773,9 +774,6 @@ int mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata) goto free_path; } - rhashtable_init(&tbl_path->rhead, &mesh_rht_params); - rhashtable_init(&tbl_mpp->rhead, &mesh_rht_params); - sdata->u.mesh.mesh_paths = tbl_path; sdata->u.mesh.mpp_paths = tbl_mpp; diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 86bc469a28bc..b13b1da19386 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -274,7 +274,7 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, success = !!(info->flags & IEEE80211_TX_STAT_ACK); for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { - if (ar[i].idx < 0) + if (ar[i].idx < 0 || !ar[i].count) break; ndx = rix_to_ndx(mi, ar[i].idx); @@ -287,12 +287,6 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, mi->r[ndx].stats.success += success; } - if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) && (i >= 0)) - mi->sample_packets++; - - if (mi->sample_deferred > 0) - mi->sample_deferred--; - if (time_after(jiffies, mi->last_stats_update + mp->update_interval / (mp->new_avg ? 2 : 1))) minstrel_update_stats(mp, mi); @@ -367,7 +361,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, return; delta = (mi->total_packets * sampling_ratio / 100) - - (mi->sample_packets + mi->sample_deferred / 2); + mi->sample_packets; /* delta < 0: no sampling required */ prev_sample = mi->prev_sample; @@ -376,7 +370,6 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, return; if (mi->total_packets >= 10000) { - mi->sample_deferred = 0; mi->sample_packets = 0; mi->total_packets = 0; } else if (delta > mi->n_rates * 2) { @@ -401,19 +394,8 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, * rate sampling method should be used. * Respect such rates that are not sampled for 20 interations. */ - if (mrr_capable && - msr->perfect_tx_time > mr->perfect_tx_time && - msr->stats.sample_skipped < 20) { - /* Only use IEEE80211_TX_CTL_RATE_CTRL_PROBE to mark - * packets that have the sampling rate deferred to the - * second MRR stage. Increase the sample counter only - * if the deferred sample rate was actually used. - * Use the sample_deferred counter to make sure that - * the sampling is not done in large bursts */ - info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE; - rate++; - mi->sample_deferred++; - } else { + if (msr->perfect_tx_time < mr->perfect_tx_time || + msr->stats.sample_skipped >= 20) { if (!msr->sample_limit) return; @@ -433,6 +415,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, rate->idx = mi->r[ndx].rix; rate->count = minstrel_get_retry_count(&mi->r[ndx], info); + info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE; } diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h index dbb43bcd3c45..86cd80b3ffde 100644 --- a/net/mac80211/rc80211_minstrel.h +++ b/net/mac80211/rc80211_minstrel.h @@ -126,7 +126,6 @@ struct minstrel_sta_info { u8 max_prob_rate; unsigned int total_packets; unsigned int sample_packets; - int sample_deferred; unsigned int sample_row; unsigned int sample_column; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 4fe284ff1ea3..ec6973ee88ef 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -705,7 +705,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) out_drop_sta: local->num_sta--; synchronize_net(); - __cleanup_single_sta(sta); + cleanup_single_sta(sta); out_err: mutex_unlock(&local->sta_mtx); kfree(sinfo); @@ -724,19 +724,13 @@ int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU) err = sta_info_insert_check(sta); if (err) { + sta_info_free(local, sta); mutex_unlock(&local->sta_mtx); rcu_read_lock(); - goto out_free; + return err; } - err = sta_info_insert_finish(sta); - if (err) - goto out_free; - - return 0; - out_free: - sta_info_free(local, sta); - return err; + return sta_info_insert_finish(sta); } int sta_info_insert(struct sta_info *sta) diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 6feb45135020..3485610755ef 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -49,7 +49,8 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, int ac; if (info->flags & (IEEE80211_TX_CTL_NO_PS_BUFFER | - IEEE80211_TX_CTL_AMPDU)) { + IEEE80211_TX_CTL_AMPDU | + IEEE80211_TX_CTL_HW_80211_ENCAP)) { ieee80211_free_txskb(&local->hw, skb); return; } @@ -915,15 +916,6 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, ieee80211_mpsp_trigger_process( ieee80211_get_qos_ctl(hdr), sta, true, acked); - if (!acked && test_sta_flag(sta, WLAN_STA_PS_STA)) { - /* - * The STA is in power save mode, so assume - * that this TX packet failed because of that. - */ - ieee80211_handle_filtered_frame(local, sta, skb); - return; - } - if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL) && (ieee80211_is_data(hdr->frame_control)) && (rates_idx != -1)) @@ -1150,6 +1142,12 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, -info->status.ack_signal); } } else if (test_sta_flag(sta, WLAN_STA_PS_STA)) { + /* + * The STA is in power save mode, so assume + * that this TX packet failed because of that. + */ + if (skb) + ieee80211_handle_filtered_frame(local, sta, skb); return; } else if (noack_success) { /* nothing to do here, do not account as lost */ diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 49342060490f..94e624e9439b 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3455,7 +3455,7 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, *chandef = he_chandef; - return false; + return true; } bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper, diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 84d119436b22..b921cbdd9aaa 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -67,6 +67,7 @@ void mptcp_seq_show(struct seq_file *seq) for (i = 0; mptcp_snmp_list[i].name; i++) seq_puts(seq, " 0"); + seq_putc(seq, '\n'); return; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e7419fd15d84..88f2a7a0ccb8 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2467,6 +2467,7 @@ static struct proto mptcp_prot = { .memory_pressure = &tcp_memory_pressure, .stream_memory_free = mptcp_memory_free, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .sysctl_mem = sysctl_tcp_mem, .obj_size = sizeof(struct mptcp_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ac4a1fe3550b..953906e40742 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -543,9 +543,8 @@ create_msk: fallback = true; } else if (subflow_req->mp_join) { mptcp_get_options(skb, &mp_opt); - if (!mp_opt.mp_join || - !mptcp_can_accept_new_subflow(subflow_req->msk) || - !subflow_hmac_valid(req, &mp_opt)) { + if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) || + !mptcp_can_accept_new_subflow(subflow_req->msk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); fallback = true; } diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index f1be3e3f6425..a9cb355324d1 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -1726,9 +1726,6 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, ndp->ptype.dev = dev; dev_add_pack(&ndp->ptype); - /* Set up generic netlink interface */ - ncsi_init_netlink(dev); - pdev = to_platform_device(dev->dev.parent); if (pdev) { np = pdev->dev.of_node; @@ -1892,8 +1889,6 @@ void ncsi_unregister_dev(struct ncsi_dev *nd) list_del_rcu(&ndp->node); spin_unlock_irqrestore(&ncsi_dev_lock, flags); - ncsi_unregister_netlink(nd->dev); - kfree(ndp); } EXPORT_SYMBOL_GPL(ncsi_unregister_dev); diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index adddc7707aa4..bb5f1650f11c 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -766,24 +766,8 @@ static struct genl_family ncsi_genl_family __ro_after_init = { .n_small_ops = ARRAY_SIZE(ncsi_ops), }; -int ncsi_init_netlink(struct net_device *dev) +static int __init ncsi_init_netlink(void) { - int rc; - - rc = genl_register_family(&ncsi_genl_family); - if (rc) - netdev_err(dev, "ncsi: failed to register netlink family\n"); - - return rc; -} - -int ncsi_unregister_netlink(struct net_device *dev) -{ - int rc; - - rc = genl_unregister_family(&ncsi_genl_family); - if (rc) - netdev_err(dev, "ncsi: failed to unregister netlink family\n"); - - return rc; + return genl_register_family(&ncsi_genl_family); } +subsys_initcall(ncsi_init_netlink); diff --git a/net/ncsi/ncsi-netlink.h b/net/ncsi/ncsi-netlink.h index 7502723fba83..39a1a9d7bf77 100644 --- a/net/ncsi/ncsi-netlink.h +++ b/net/ncsi/ncsi-netlink.h @@ -22,7 +22,4 @@ int ncsi_send_netlink_err(struct net_device *dev, struct nlmsghdr *nlhdr, int err); -int ncsi_init_netlink(struct net_device *dev); -int ncsi_unregister_netlink(struct net_device *dev); - #endif /* __NCSI_NETLINK_H__ */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 7cff6e5e7445..2b19189a930f 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -271,8 +271,7 @@ flag_nested(const struct nlattr *nla) static const struct nla_policy ipaddr_policy[IPSET_ATTR_IPADDR_MAX + 1] = { [IPSET_ATTR_IPADDR_IPV4] = { .type = NLA_U32 }, - [IPSET_ATTR_IPADDR_IPV6] = { .type = NLA_BINARY, - .len = sizeof(struct in6_addr) }, + [IPSET_ATTR_IPADDR_IPV6] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), }; int diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index e279ded4e306..d45dbcba8b49 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -4167,12 +4167,18 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) spin_lock_init(&ipvs->tot_stats.lock); - proc_create_net("ip_vs", 0, ipvs->net->proc_net, &ip_vs_info_seq_ops, - sizeof(struct ip_vs_iter)); - proc_create_net_single("ip_vs_stats", 0, ipvs->net->proc_net, - ip_vs_stats_show, NULL); - proc_create_net_single("ip_vs_stats_percpu", 0, ipvs->net->proc_net, - ip_vs_stats_percpu_show, NULL); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs", 0, ipvs->net->proc_net, + &ip_vs_info_seq_ops, sizeof(struct ip_vs_iter))) + goto err_vs; + if (!proc_create_net_single("ip_vs_stats", 0, ipvs->net->proc_net, + ip_vs_stats_show, NULL)) + goto err_stats; + if (!proc_create_net_single("ip_vs_stats_percpu", 0, + ipvs->net->proc_net, + ip_vs_stats_percpu_show, NULL)) + goto err_percpu; +#endif if (ip_vs_control_net_init_sysctl(ipvs)) goto err; @@ -4180,6 +4186,17 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) return 0; err: +#ifdef CONFIG_PROC_FS + remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net); + +err_percpu: + remove_proc_entry("ip_vs_stats", ipvs->net->proc_net); + +err_stats: + remove_proc_entry("ip_vs", ipvs->net->proc_net); + +err_vs: +#endif free_percpu(ipvs->tot_stats.cpustats); return -ENOMEM; } @@ -4188,9 +4205,11 @@ void __net_exit ip_vs_control_net_cleanup(struct netns_ipvs *ipvs) { ip_vs_trash_cleanup(ipvs); ip_vs_control_net_cleanup_sysctl(ipvs); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net); remove_proc_entry("ip_vs_stats", ipvs->net->proc_net); remove_proc_entry("ip_vs", ipvs->net->proc_net); +#endif free_percpu(ipvs->tot_stats.cpustats); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0f58e98542be..9a080767667b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -619,7 +619,8 @@ static int nft_request_module(struct net *net, const char *fmt, ...) static void lockdep_nfnl_nft_mutex_not_held(void) { #ifdef CONFIG_PROVE_LOCKING - WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); + if (debug_locks) + WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); #endif } @@ -1722,6 +1723,10 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, } nla_strlcpy(ifname, attr, IFNAMSIZ); + /* nf_tables_netdev_event() is called under rtnl_mutex, this is + * indirectly serializing all the other holders of the commit_mutex with + * the rtnl_mutex. + */ dev = __dev_get_by_name(net, ifname); if (!dev) { err = -ENOENT; @@ -3718,7 +3723,7 @@ cont: return 0; } -static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) +int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) { u64 ms = be64_to_cpu(nla_get_be64(nla)); u64 max = (u64)(~((u64)0)); @@ -3732,7 +3737,7 @@ static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) return 0; } -static __be64 nf_jiffies64_to_msecs(u64 input) +__be64 nf_jiffies64_to_msecs(u64 input) { return cpu_to_be64(jiffies64_to_msecs(input)); } diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 9f625724a20f..9ae14270c543 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -28,6 +28,23 @@ static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions) return flow; } +void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, + enum flow_dissector_key_id addr_type) +{ + struct nft_flow_match *match = &flow->match; + struct nft_flow_key *mask = &match->mask; + struct nft_flow_key *key = &match->key; + + if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) + return; + + key->control.addr_type = addr_type; + mask->control.addr_type = 0xffff; + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); + match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] = + offsetof(struct nft_flow_key, control); +} + struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule) { diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index bc079d68a536..00e563a72d3d 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -123,11 +123,11 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx, u8 *mask = (u8 *)&flow->match.mask; u8 *key = (u8 *)&flow->match.key; - if (priv->op != NFT_CMP_EQ || reg->len != priv->len) + if (priv->op != NFT_CMP_EQ || priv->len > reg->len) return -EOPNOTSUPP; - memcpy(key + reg->offset, &priv->data, priv->len); - memcpy(mask + reg->offset, ®->mask, priv->len); + memcpy(key + reg->offset, &priv->data, reg->len); + memcpy(mask + reg->offset, ®->mask, reg->len); flow->match.dissector.used_keys |= BIT(reg->key); flow->match.dissector.offset[reg->key] = reg->base_offset; @@ -137,7 +137,7 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx, nft_reg_load16(priv->data.data) != ARPHRD_ETHER) return -EOPNOTSUPP; - nft_offload_update_dependency(ctx, &priv->data, priv->len); + nft_offload_update_dependency(ctx, &priv->data, reg->len); return 0; } diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 322bd674963e..a1b0aac46e9e 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -177,8 +177,6 @@ static void nft_ct_get_eval(const struct nft_expr *expr, } #endif case NFT_CT_ID: - if (!nf_ct_is_confirmed(ct)) - goto err; *dest = nf_ct_get_id(ct); return; default: diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 64ca13a1885b..9af4f93c7f0e 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -157,8 +157,10 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (tb[NFTA_DYNSET_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( - tb[NFTA_DYNSET_TIMEOUT]))); + + err = nf_msecs_to_jiffies64(tb[NFTA_DYNSET_TIMEOUT], &timeout); + if (err) + return err; } priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]); @@ -267,7 +269,7 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) if (nla_put_string(skb, NFTA_DYNSET_SET_NAME, priv->set->name)) goto nla_put_failure; if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT, - cpu_to_be64(jiffies_to_msecs(priv->timeout)), + nf_jiffies64_to_msecs(priv->timeout), NFTA_DYNSET_PAD)) goto nla_put_failure; if (priv->expr && nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr)) diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index b37bd02448d8..bf4b3ad5314c 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -724,22 +724,22 @@ static int nft_meta_get_offload(struct nft_offload_ctx *ctx, switch (priv->key) { case NFT_META_PROTOCOL: - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, n_proto, - sizeof(__u16), reg); + NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_BASIC, basic, n_proto, + sizeof(__u16), reg); nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK); break; case NFT_META_L4PROTO: - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, - sizeof(__u8), reg); + NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, + sizeof(__u8), reg); nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT); break; case NFT_META_IIF: - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_META, meta, - ingress_ifindex, sizeof(__u32), reg); + NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_META, meta, + ingress_ifindex, sizeof(__u32), reg); break; case NFT_META_IIFTYPE: - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_META, meta, - ingress_iftype, sizeof(__u16), reg); + NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_META, meta, + ingress_iftype, sizeof(__u16), reg); break; default: return -EOPNOTSUPP; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index dcd3c7b8a367..47d4e0e21651 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -165,6 +165,34 @@ nla_put_failure: return -1; } +static bool nft_payload_offload_mask(struct nft_offload_reg *reg, + u32 priv_len, u32 field_len) +{ + unsigned int remainder, delta, k; + struct nft_data mask = {}; + __be32 remainder_mask; + + if (priv_len == field_len) { + memset(®->mask, 0xff, priv_len); + return true; + } else if (priv_len > field_len) { + return false; + } + + memset(&mask, 0xff, field_len); + remainder = priv_len % sizeof(u32); + if (remainder) { + k = priv_len / sizeof(u32); + delta = field_len - priv_len; + remainder_mask = htonl(~((1 << (delta * BITS_PER_BYTE)) - 1)); + mask.data[k] = (__force u32)remainder_mask; + } + + memcpy(®->mask, &mask, field_len); + + return true; +} + static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow, const struct nft_payload *priv) @@ -173,21 +201,21 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct ethhdr, h_source): - if (priv->len != ETH_ALEN) + if (!nft_payload_offload_mask(reg, priv->len, ETH_ALEN)) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs, src, ETH_ALEN, reg); break; case offsetof(struct ethhdr, h_dest): - if (priv->len != ETH_ALEN) + if (!nft_payload_offload_mask(reg, priv->len, ETH_ALEN)) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs, dst, ETH_ALEN, reg); break; case offsetof(struct ethhdr, h_proto): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, @@ -195,14 +223,14 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK); break; case offsetof(struct vlan_ethhdr, h_vlan_TCI): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_VLAN, vlan, vlan_tci, sizeof(__be16), reg); break; case offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_VLAN, vlan, @@ -210,7 +238,7 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK); break; case offsetof(struct vlan_ethhdr, h_vlan_TCI) + sizeof(struct vlan_hdr): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_CVLAN, vlan, @@ -218,7 +246,7 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, break; case offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto) + sizeof(struct vlan_hdr): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_CVLAN, vlan, @@ -239,21 +267,25 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct iphdr, saddr): - if (priv->len != sizeof(struct in_addr)) + if (!nft_payload_offload_mask(reg, priv->len, + sizeof(struct in_addr))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, src, sizeof(struct in_addr), reg); + nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV4_ADDRS); break; case offsetof(struct iphdr, daddr): - if (priv->len != sizeof(struct in_addr)) + if (!nft_payload_offload_mask(reg, priv->len, + sizeof(struct in_addr))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, dst, sizeof(struct in_addr), reg); + nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV4_ADDRS); break; case offsetof(struct iphdr, protocol): - if (priv->len != sizeof(__u8)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__u8))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, @@ -275,21 +307,25 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct ipv6hdr, saddr): - if (priv->len != sizeof(struct in6_addr)) + if (!nft_payload_offload_mask(reg, priv->len, + sizeof(struct in6_addr))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, src, sizeof(struct in6_addr), reg); + nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV6_ADDRS); break; case offsetof(struct ipv6hdr, daddr): - if (priv->len != sizeof(struct in6_addr)) + if (!nft_payload_offload_mask(reg, priv->len, + sizeof(struct in6_addr))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, dst, sizeof(struct in6_addr), reg); + nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV6_ADDRS); break; case offsetof(struct ipv6hdr, nexthdr): - if (priv->len != sizeof(__u8)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__u8))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, @@ -331,14 +367,14 @@ static int nft_payload_offload_tcp(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct tcphdr, source): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src, sizeof(__be16), reg); break; case offsetof(struct tcphdr, dest): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst, @@ -359,14 +395,14 @@ static int nft_payload_offload_udp(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct udphdr, source): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src, sizeof(__be16), reg); break; case offsetof(struct udphdr, dest): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst, diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index af22dbe85e2c..acce622582e3 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1349,6 +1349,14 @@ struct xt_counters *xt_counters_alloc(unsigned int counters) } EXPORT_SYMBOL(xt_counters_alloc); +struct xt_table_info +*xt_table_get_private_protected(const struct xt_table *table) +{ + return rcu_dereference_protected(table->private, + mutex_is_locked(&xt[table->af].mutex)); +} +EXPORT_SYMBOL(xt_table_get_private_protected); + struct xt_table_info * xt_replace_table(struct xt_table *table, unsigned int num_counters, @@ -1356,7 +1364,6 @@ xt_replace_table(struct xt_table *table, int *error) { struct xt_table_info *private; - unsigned int cpu; int ret; ret = xt_jumpstack_alloc(newinfo); @@ -1366,47 +1373,20 @@ xt_replace_table(struct xt_table *table, } /* Do the substitution. */ - local_bh_disable(); - private = table->private; + private = xt_table_get_private_protected(table); /* Check inside lock: is the old number correct? */ if (num_counters != private->number) { pr_debug("num_counters != table->private->number (%u/%u)\n", num_counters, private->number); - local_bh_enable(); *error = -EAGAIN; return NULL; } newinfo->initial_entries = private->initial_entries; - /* - * Ensure contents of newinfo are visible before assigning to - * private. - */ - smp_wmb(); - table->private = newinfo; - - /* make sure all cpus see new ->private value */ - smp_wmb(); - /* - * Even though table entries have now been swapped, other CPU's - * may still be using the old entries... - */ - local_bh_enable(); - - /* ... so wait for even xt_recseq on all cpus */ - for_each_possible_cpu(cpu) { - seqcount_t *s = &per_cpu(xt_recseq, cpu); - u32 seq = raw_read_seqcount(s); - - if (seq & 1) { - do { - cond_resched(); - cpu_relax(); - } while (seq == raw_read_seqcount(s)); - } - } + rcu_assign_pointer(table->private, newinfo); + synchronize_rcu(); audit_log_nfcfg(table->name, table->af, private->number, !private->number ? AUDIT_XT_OP_REGISTER : @@ -1442,12 +1422,12 @@ struct xt_table *xt_register_table(struct net *net, } /* Simplifies replace_table code. */ - table->private = bootstrap; + rcu_assign_pointer(table->private, bootstrap); if (!xt_replace_table(table, 0, newinfo, &ret)) goto unlock; - private = table->private; + private = xt_table_get_private_protected(table); pr_debug("table->private->number = %u\n", private->number); /* save number of initial entries */ @@ -1470,7 +1450,8 @@ void *xt_unregister_table(struct xt_table *table) struct xt_table_info *private; mutex_lock(&xt[table->af].mutex); - private = table->private; + private = xt_table_get_private_protected(table); + RCU_INIT_POINTER(table->private, NULL); list_del(&table->list); mutex_unlock(&xt[table->af].mutex); audit_log_nfcfg(table->name, table->af, private->number, diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 2e8e3f7b2111..ccb491642811 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1166,12 +1166,13 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, struct netlbl_unlhsh_walk_arg cb_arg; u32 skip_bkt = cb->args[0]; u32 skip_chain = cb->args[1]; - u32 iter_bkt; - u32 iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0; + u32 skip_addr4 = cb->args[2]; + u32 iter_bkt, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0; struct netlbl_unlhsh_iface *iface; struct list_head *iter_list; struct netlbl_af4list *addr4; #if IS_ENABLED(CONFIG_IPV6) + u32 skip_addr6 = cb->args[3]; struct netlbl_af6list *addr6; #endif @@ -1182,7 +1183,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, rcu_read_lock(); for (iter_bkt = skip_bkt; iter_bkt < rcu_dereference(netlbl_unlhsh)->size; - iter_bkt++, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0) { + iter_bkt++) { iter_list = &rcu_dereference(netlbl_unlhsh)->tbl[iter_bkt]; list_for_each_entry_rcu(iface, iter_list, list) { if (!iface->valid || @@ -1190,7 +1191,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, continue; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { - if (iter_addr4++ < cb->args[2]) + if (iter_addr4++ < skip_addr4) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1203,10 +1204,12 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, goto unlabel_staticlist_return; } } + iter_addr4 = 0; + skip_addr4 = 0; #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { - if (iter_addr6++ < cb->args[3]) + if (iter_addr6++ < skip_addr6) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1219,8 +1222,12 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, goto unlabel_staticlist_return; } } + iter_addr6 = 0; + skip_addr6 = 0; #endif /* IPv6 */ } + iter_chain = 0; + skip_chain = 0; } unlabel_staticlist_return: diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index b87bfc82f44f..c3a664871cb5 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -199,6 +199,9 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key, __be32 lse; int err; + if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) + return -ENOMEM; + stack = mpls_hdr(skb); lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask); err = skb_mpls_update_lse(skb, lse); @@ -958,14 +961,13 @@ static int dec_ttl_exception_handler(struct datapath *dp, struct sk_buff *skb, { /* The first action is always 'OVS_DEC_TTL_ATTR_ARG'. */ struct nlattr *dec_ttl_arg = nla_data(attr); - int rem = nla_len(attr); if (nla_len(dec_ttl_arg)) { - struct nlattr *actions = nla_next(dec_ttl_arg, &rem); + struct nlattr *actions = nla_data(dec_ttl_arg); if (actions) - return clone_execute(dp, skb, key, 0, actions, rem, - last, false); + return clone_execute(dp, skb, key, 0, nla_data(actions), + nla_len(actions), last, false); } consume_skb(skb); return 0; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 9d3e50c4d29f..4c5c2331e764 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2503,28 +2503,42 @@ static int validate_and_copy_dec_ttl(struct net *net, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, bool log) { - int start, err; - u32 nested = true; + const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1]; + int start, action_start, err, rem; + const struct nlattr *a, *actions; + + memset(attrs, 0, sizeof(attrs)); + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); - if (!nla_len(attr)) - return ovs_nla_add_action(sfa, OVS_ACTION_ATTR_DEC_TTL, - NULL, 0, log); + /* Ignore unknown attributes to be future proof. */ + if (type > OVS_DEC_TTL_ATTR_MAX) + continue; + + if (!type || attrs[type]) + return -EINVAL; + + attrs[type] = a; + } + + actions = attrs[OVS_DEC_TTL_ATTR_ACTION]; + if (rem || !actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN)) + return -EINVAL; start = add_nested_action_start(sfa, OVS_ACTION_ATTR_DEC_TTL, log); if (start < 0) return start; - err = ovs_nla_add_action(sfa, OVS_DEC_TTL_ATTR_ACTION, &nested, - sizeof(nested), log); + action_start = add_nested_action_start(sfa, OVS_DEC_TTL_ATTR_ACTION, log); + if (action_start < 0) + return action_start; - if (err) - return err; - - err = __ovs_nla_copy_actions(net, attr, key, sfa, eth_type, + err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, vlan_tci, mpls_label_count, log); if (err) return err; + add_nested_action_end(*sfa, action_start); add_nested_action_end(*sfa, start); return 0; } @@ -3487,20 +3501,42 @@ out: static int dec_ttl_action_to_attr(const struct nlattr *attr, struct sk_buff *skb) { - int err = 0, rem = nla_len(attr); - struct nlattr *start; + struct nlattr *start, *action_start; + const struct nlattr *a; + int err = 0, rem; start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_DEC_TTL); - if (!start) return -EMSGSIZE; - err = ovs_nla_put_actions(nla_data(attr), rem, skb); - if (err) - nla_nest_cancel(skb, start); - else - nla_nest_end(skb, start); + nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) { + switch (nla_type(a)) { + case OVS_DEC_TTL_ATTR_ACTION: + + action_start = nla_nest_start_noflag(skb, OVS_DEC_TTL_ATTR_ACTION); + if (!action_start) { + err = -EMSGSIZE; + goto out; + } + + err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb); + if (err) + goto out; + + nla_nest_end(skb, action_start); + break; + default: + /* Ignore all other option to be future compatible */ + break; + } + } + + nla_nest_end(skb, start); + return 0; + +out: + nla_nest_cancel(skb, start); return err; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index cefbd50c1090..7a18ffff8551 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -93,8 +93,8 @@ /* Assumptions: - - If the device has no dev->header_ops, there is no LL header visible - above the device. In this case, its hard_header_len should be 0. + - If the device has no dev->header_ops->create, there is no LL header + visible above the device. In this case, its hard_header_len should be 0. The device may prepend its own header internally. In this case, its needed_headroom should be set to the space needed for it to add its internal header. @@ -108,26 +108,26 @@ On receive: ----------- -Incoming, dev->header_ops != NULL +Incoming, dev_has_header(dev) == true mac_header -> ll header data -> data -Outgoing, dev->header_ops != NULL +Outgoing, dev_has_header(dev) == true mac_header -> ll header data -> ll header -Incoming, dev->header_ops == NULL +Incoming, dev_has_header(dev) == false mac_header -> data However drivers often make it point to the ll header. This is incorrect because the ll header should be invisible to us. data -> data -Outgoing, dev->header_ops == NULL +Outgoing, dev_has_header(dev) == false mac_header -> data. ll header is invisible to us. data -> data Resume - If dev->header_ops == NULL we are unable to restore the ll header, + If dev_has_header(dev) == false we are unable to restore the ll header, because it is invisible to us. @@ -2069,7 +2069,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, skb->dev = dev; - if (dev->header_ops) { + if (dev_has_header(dev)) { /* The device has an explicit notion of ll header, * exported to higher levels. * @@ -2198,7 +2198,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; - if (dev->header_ops) { + if (dev_has_header(dev)) { if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 971c73c7d34c..97101c55763d 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -876,6 +876,9 @@ static int rfkill_resume(struct device *dev) rfkill->suspended = false; + if (!rfkill->registered) + return 0; + if (!rfkill->persistent) { cur = !!(rfkill->state & RFKILL_BLOCK_SW); rfkill_set_block(rfkill, cur); diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 7b094275ea8b..11c45c8c6c16 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -96,10 +96,19 @@ static void rose_loopback_timer(struct timer_list *unused) } if (frametype == ROSE_CALL_REQUEST) { - if ((dev = rose_dev_get(dest)) != NULL) { - if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0) - kfree_skb(skb); - } else { + if (!rose_loopback_neigh->dev) { + kfree_skb(skb); + continue; + } + + dev = rose_dev_get(dest); + if (!dev) { + kfree_skb(skb); + continue; + } + + if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0) { + dev_put(dev); kfree_skb(skb); } } else { diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 5c7456e5b5cf..d1486ea496a2 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -105,6 +105,9 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, goto drop; break; case TCA_MPLS_ACT_MODIFY: + if (!pskb_may_pull(skb, + skb_network_offset(skb) + MPLS_HLEN)) + goto drop; new_lse = tcf_mpls_get_lse(mpls_hdr(skb), p, false); if (skb_mpls_update_lse(skb, new_lse)) goto drop; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index fed18fd2c50b..1319986693fc 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2424,8 +2424,8 @@ static int fl_dump_key_mpls_opt_lse(struct sk_buff *skb, return err; } if (lse_mask->mpls_label) { - err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL, - lse_key->mpls_label); + err = nla_put_u32(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL, + lse_key->mpls_label); if (err) return err; } diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 4dda15588cf4..949163fe68af 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -401,6 +401,7 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, INIT_LIST_HEAD(&q->new_flows); INIT_LIST_HEAD(&q->old_flows); + timer_setup(&q->adapt_timer, fq_pie_timer, 0); if (opt) { err = fq_pie_change(sch, opt, extack); @@ -426,7 +427,6 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, pie_vars_init(&flow->vars); } - timer_setup(&q->adapt_timer, fq_pie_timer, 0); mod_timer(&q->adapt_timer, jiffies + HZ / 2); return 0; diff --git a/net/sctp/input.c b/net/sctp/input.c index 55d4fc6f371d..d508f6f3dd08 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -449,7 +449,7 @@ void sctp_icmp_proto_unreachable(struct sock *sk, else { if (!mod_timer(&t->proto_unreach_timer, jiffies + (HZ/20))) - sctp_association_hold(asoc); + sctp_transport_hold(t); } } else { struct net *net = sock_net(sk); @@ -458,7 +458,7 @@ void sctp_icmp_proto_unreachable(struct sock *sk, "encountered!\n", __func__); if (del_timer(&t->proto_unreach_timer)) - sctp_association_put(asoc); + sctp_transport_put(t); sctp_do_sm(net, SCTP_EVENT_T_OTHER, SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH), diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 813d30767204..0948f14ce221 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -419,7 +419,7 @@ void sctp_generate_proto_unreach_event(struct timer_list *t) /* Try again later. */ if (!mod_timer(&transport->proto_unreach_timer, jiffies + (HZ/20))) - sctp_association_hold(asoc); + sctp_transport_hold(transport); goto out_unlock; } @@ -435,7 +435,7 @@ void sctp_generate_proto_unreach_event(struct timer_list *t) out_unlock: bh_unlock_sock(sk); - sctp_association_put(asoc); + sctp_transport_put(transport); } /* Handle the timeout of the RE-CONFIG timer. */ diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 806af58f4375..60fcf31cdcfb 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -133,7 +133,7 @@ void sctp_transport_free(struct sctp_transport *transport) /* Delete the ICMP proto unreachable timer if it's active. */ if (del_timer(&transport->proto_unreach_timer)) - sctp_association_put(transport->asoc); + sctp_transport_put(transport); sctp_transport_put(transport); } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index e9f487c8c6d5..5dd4faaf7d6e 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -979,7 +979,8 @@ static int __smc_connect(struct smc_sock *smc) /* check if smc modes and versions of CLC proposal and accept match */ rc = smc_connect_check_aclc(ini, aclc); - version = aclc->hdr.version == SMC_V1 ? SMC_V1 : version; + version = aclc->hdr.version == SMC_V1 ? SMC_V1 : SMC_V2; + ini->smcd_version = version; if (rc) goto vlan_cleanup; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2b19863f7171..af96f813c075 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1309,7 +1309,8 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) ini->ism_peer_gid[ini->ism_selected]) : smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) && !lgr->sync_err && - lgr->vlan_id == ini->vlan_id && + (ini->smcd_version == SMC_V2 || + lgr->vlan_id == ini->vlan_id) && (role == SMC_CLNT || ini->is_smcd || lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) { /* link group found */ diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 1c314dbdc7fa..fc766b537ac7 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -198,9 +198,9 @@ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, rcu_read_lock(); ndev = rdma_read_gid_attr_ndev_rcu(attr); if (!IS_ERR(ndev) && - ((!vlan_id && !is_vlan_dev(attr->ndev)) || - (vlan_id && is_vlan_dev(attr->ndev) && - vlan_dev_vlan_id(attr->ndev) == vlan_id)) && + ((!vlan_id && !is_vlan_dev(ndev)) || + (vlan_id && is_vlan_dev(ndev) && + vlan_dev_vlan_id(ndev) == vlan_id)) && attr->gid_type == IB_GID_TYPE_ROCE) { rcu_read_unlock(); if (gid) diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index a18b36b5422d..3aad6ef18504 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -63,19 +63,20 @@ static int proc_do_xprt(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char tmpbuf[256]; - size_t len; + ssize_t len; - if ((*ppos && !write) || !*lenp) { + if (write || *ppos) { *lenp = 0; return 0; } len = svc_print_xprts(tmpbuf, sizeof(tmpbuf)); - *lenp = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len); + len = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len); - if (*lenp < 0) { + if (len < 0) { *lenp = 0; return -EINVAL; } + *lenp = len; return 0; } diff --git a/net/tipc/node.c b/net/tipc/node.c index d269ebe382e1..83978d5dae59 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2181,7 +2181,11 @@ void tipc_node_apply_property(struct net *net, struct tipc_bearer *b, &xmitq); else if (prop == TIPC_NLA_PROP_MTU) tipc_link_set_mtu(e->link, b->mtu); + + /* Update MTU for node link entry */ + e->mtu = tipc_link_mss(e->link); } + tipc_node_write_unlock(n); tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr, NULL); } diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 5f6f86051c83..13f3143609f9 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -664,12 +664,18 @@ static int tipc_topsrv_start(struct net *net) ret = tipc_topsrv_work_start(srv); if (ret < 0) - return ret; + goto err_start; ret = tipc_topsrv_create_listener(srv); if (ret < 0) - tipc_topsrv_work_stop(srv); + goto err_create; + return 0; + +err_create: + tipc_topsrv_work_stop(srv); +err_start: + kfree(srv); return ret; } diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index cec86229a6a0..a3ab2d3d4e4e 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -694,36 +694,51 @@ static void tls_device_resync_rx(struct tls_context *tls_ctx, static bool tls_device_rx_resync_async(struct tls_offload_resync_async *resync_async, - s64 resync_req, u32 *seq) + s64 resync_req, u32 *seq, u16 *rcd_delta) { u32 is_async = resync_req & RESYNC_REQ_ASYNC; u32 req_seq = resync_req >> 32; u32 req_end = req_seq + ((resync_req >> 16) & 0xffff); + u16 i; + + *rcd_delta = 0; if (is_async) { + /* shouldn't get to wraparound: + * too long in async stage, something bad happened + */ + if (WARN_ON_ONCE(resync_async->rcd_delta == USHRT_MAX)) + return false; + /* asynchronous stage: log all headers seq such that * req_seq <= seq <= end_seq, and wait for real resync request */ - if (between(*seq, req_seq, req_end) && + if (before(*seq, req_seq)) + return false; + if (!after(*seq, req_end) && resync_async->loglen < TLS_DEVICE_RESYNC_ASYNC_LOGMAX) resync_async->log[resync_async->loglen++] = *seq; + resync_async->rcd_delta++; + return false; } /* synchronous stage: check against the logged entries and * proceed to check the next entries if no match was found */ - while (resync_async->loglen) { - if (req_seq == resync_async->log[resync_async->loglen - 1] && - atomic64_try_cmpxchg(&resync_async->req, - &resync_req, 0)) { - resync_async->loglen = 0; + for (i = 0; i < resync_async->loglen; i++) + if (req_seq == resync_async->log[i] && + atomic64_try_cmpxchg(&resync_async->req, &resync_req, 0)) { + *rcd_delta = resync_async->rcd_delta - i; *seq = req_seq; + resync_async->loglen = 0; + resync_async->rcd_delta = 0; return true; } - resync_async->loglen--; - } + + resync_async->loglen = 0; + resync_async->rcd_delta = 0; if (req_seq == *seq && atomic64_try_cmpxchg(&resync_async->req, @@ -741,6 +756,7 @@ void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) u32 sock_data, is_req_pending; struct tls_prot_info *prot; s64 resync_req; + u16 rcd_delta; u32 req_seq; if (tls_ctx->rx_conf != TLS_HW) @@ -786,8 +802,9 @@ void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) return; if (!tls_device_rx_resync_async(rx_ctx->resync_async, - resync_req, &seq)) + resync_req, &seq, &rcd_delta)) return; + tls_bigint_subtract(rcd_sn, rcd_delta); break; } @@ -1245,6 +1262,8 @@ void tls_device_offload_cleanup_rx(struct sock *sk) if (tls_ctx->tx_conf != TLS_HW) { dev_put(netdev); tls_ctx->netdev = NULL; + } else { + set_bit(TLS_RX_DEV_CLOSED, &tls_ctx->flags); } out: up_read(&device_offload_lock); @@ -1274,7 +1293,8 @@ static int tls_device_down(struct net_device *netdev) if (ctx->tx_conf == TLS_HW) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); - if (ctx->rx_conf == TLS_HW) + if (ctx->rx_conf == TLS_HW && + !test_bit(TLS_RX_DEV_CLOSED, &ctx->flags)) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_RX); WRITE_ONCE(ctx->netdev, NULL); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 95ab5545a931..845c628ac1b2 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1295,6 +1295,12 @@ static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock, return NULL; } + if (!skb_queue_empty(&sk->sk_receive_queue)) { + __strp_unpause(&ctx->strp); + if (ctx->recv_pkt) + return ctx->recv_pkt; + } + if (sk->sk_shutdown & RCV_SHUTDOWN) return NULL; @@ -1913,7 +1919,7 @@ pick_next_record: * another message type */ msg->msg_flags |= MSG_EOR; - if (ctx->control != TLS_RECORD_TYPE_DATA) + if (control != TLS_RECORD_TYPE_DATA) goto recv_end; } else { break; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index b4d7b8aba003..d10916ab4526 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -438,7 +438,7 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) case SOCK_STREAM: if (vsock_use_local_transport(remote_cid)) new_transport = transport_local; - else if (remote_cid <= VMADDR_CID_HOST) + else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g) new_transport = transport_g2h; else new_transport = transport_h2g; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 0edda1edf988..5956939eebb7 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -841,8 +841,10 @@ void virtio_transport_release(struct vsock_sock *vsk) virtio_transport_free_pkt(pkt); } - if (remove_sock) + if (remove_sock) { + sock_set_flag(sk, SOCK_DONE); vsock_remove_sock(vsk); + } } EXPORT_SYMBOL_GPL(virtio_transport_release); @@ -1132,8 +1134,8 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, lock_sock(sk); - /* Check if sk has been released before lock_sock */ - if (sk->sk_shutdown == SHUTDOWN_MASK) { + /* Check if sk has been closed before lock_sock */ + if (sock_flag(sk, SOCK_DONE)) { (void)virtio_transport_reset_no_sock(t, pkt); release_sock(sk); sock_put(sk); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index a77174b99b07..f67ddf2cebcb 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12634,7 +12634,7 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; struct nlattr *tb[NUM_NL80211_REKEY_DATA]; - struct cfg80211_gtk_rekey_data rekey_data; + struct cfg80211_gtk_rekey_data rekey_data = {}; int err; if (!info->attrs[NL80211_ATTR_REKEY_DATA]) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 0bbb283f23c9..e65a50192432 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -681,7 +681,8 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) int len, i, rc = 0; if (addr_len != sizeof(struct sockaddr_x25) || - addr->sx25_family != AF_X25) { + addr->sx25_family != AF_X25 || + strnlen(addr->sx25_addr.x25_addr, X25_ADDR_LEN) == X25_ADDR_LEN) { rc = -EINVAL; goto out; } @@ -775,7 +776,8 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, rc = -EINVAL; if (addr_len != sizeof(struct sockaddr_x25) || - addr->sx25_family != AF_X25) + addr->sx25_family != AF_X25 || + strnlen(addr->sx25_addr.x25_addr, X25_ADDR_LEN) == X25_ADDR_LEN) goto out; rc = -ENETUNREACH; @@ -825,7 +827,7 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTED; rc = 0; out_put_neigh: - if (rc) { + if (rc && x25->neighbour) { read_lock_bh(&x25_list_lock); x25_neigh_put(x25->neighbour); x25->neighbour = NULL; @@ -1050,6 +1052,7 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, makex25->lci = lci; makex25->dest_addr = dest_addr; makex25->source_addr = source_addr; + x25_neigh_hold(nb); makex25->neighbour = nb; makex25->facilities = facilities; makex25->dte_facilities= dte_facilities; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 56d052bc65cb..56a28a686988 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -66,18 +66,31 @@ static void xdp_umem_release(struct xdp_umem *umem) kfree(umem); } +static void xdp_umem_release_deferred(struct work_struct *work) +{ + struct xdp_umem *umem = container_of(work, struct xdp_umem, work); + + xdp_umem_release(umem); +} + void xdp_get_umem(struct xdp_umem *umem) { refcount_inc(&umem->users); } -void xdp_put_umem(struct xdp_umem *umem) +void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup) { if (!umem) return; - if (refcount_dec_and_test(&umem->users)) - xdp_umem_release(umem); + if (refcount_dec_and_test(&umem->users)) { + if (defer_cleanup) { + INIT_WORK(&umem->work, xdp_umem_release_deferred); + schedule_work(&umem->work); + } else { + xdp_umem_release(umem); + } + } } static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h index 181fdda2f2a8..aa9fe2780410 100644 --- a/net/xdp/xdp_umem.h +++ b/net/xdp/xdp_umem.h @@ -9,7 +9,7 @@ #include <net/xdp_sock_drv.h> void xdp_get_umem(struct xdp_umem *umem); -void xdp_put_umem(struct xdp_umem *umem); +void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup); struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr); #endif /* XDP_UMEM_H_ */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index b71a32eeae65..62504471fd20 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -211,6 +211,14 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len, return 0; } +static bool xsk_tx_writeable(struct xdp_sock *xs) +{ + if (xskq_cons_present_entries(xs->tx) > xs->tx->nentries / 2) + return false; + + return true; +} + static bool xsk_is_bound(struct xdp_sock *xs) { if (READ_ONCE(xs->state) == XSK_BOUND) { @@ -296,7 +304,8 @@ void xsk_tx_release(struct xsk_buff_pool *pool) rcu_read_lock(); list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { __xskq_cons_release(xs->tx); - xs->sk.sk_write_space(&xs->sk); + if (xsk_tx_writeable(xs)) + xs->sk.sk_write_space(&xs->sk); } rcu_read_unlock(); } @@ -411,11 +420,7 @@ static int xsk_generic_xmit(struct sock *sk) skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr; skb->destructor = xsk_destruct_skb; - /* Hinder dev_direct_xmit from freeing the packet and - * therefore completing it in the destructor - */ - refcount_inc(&skb->users); - err = dev_direct_xmit(skb, xs->queue_id); + err = __dev_direct_xmit(skb, xs->queue_id); if (err == NETDEV_TX_BUSY) { /* Tell user-space to retry the send */ skb->destructor = sock_wfree; @@ -429,12 +434,10 @@ static int xsk_generic_xmit(struct sock *sk) /* Ignore NET_XMIT_CN as packet might have been sent */ if (err == NET_XMIT_DROP) { /* SKB completed but not sent */ - kfree_skb(skb); err = -EBUSY; goto out; } - consume_skb(skb); sent_frame = true; } @@ -442,7 +445,8 @@ static int xsk_generic_xmit(struct sock *sk) out: if (sent_frame) - sk->sk_write_space(sk); + if (xsk_tx_writeable(xs)) + sk->sk_write_space(sk); mutex_unlock(&xs->mutex); return err; @@ -477,11 +481,13 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) static __poll_t xsk_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { - __poll_t mask = datagram_poll(file, sock, wait); + __poll_t mask = 0; struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct xsk_buff_pool *pool; + sock_poll_wait(file, sock, wait); + if (unlikely(!xsk_is_bound(xs))) return mask; @@ -497,7 +503,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, if (xs->rx && !xskq_prod_is_empty(xs->rx)) mask |= EPOLLIN | EPOLLRDNORM; - if (xs->tx && !xskq_cons_is_full(xs->tx)) + if (xs->tx && xsk_tx_writeable(xs)) mask |= EPOLLOUT | EPOLLWRNORM; return mask; @@ -1146,7 +1152,8 @@ static void xsk_destruct(struct sock *sk) if (!sock_flag(sk, SOCK_DEAD)) return; - xp_put_pool(xs->pool); + if (!xp_put_pool(xs->pool)) + xdp_put_umem(xs->umem, !xs->pool); sk_refcnt_debug_dec(sk); } diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 64c9e55d4d4e..d5adeee9d5d9 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -175,6 +175,7 @@ static int __xp_assign_dev(struct xsk_buff_pool *pool, if (!pool->dma_pages) { WARN(1, "Driver did not DMA map zero-copy buffers"); + err = -EINVAL; goto err_unreg_xsk; } pool->umem->zc = true; @@ -185,8 +186,10 @@ err_unreg_xsk: err_unreg_pool: if (!force_zc) err = 0; /* fallback to copy mode */ - if (err) + if (err) { xsk_clear_pool_at_qid(netdev, queue_id); + dev_put(netdev); + } return err; } @@ -242,7 +245,7 @@ static void xp_release_deferred(struct work_struct *work) pool->cq = NULL; } - xdp_put_umem(pool->umem); + xdp_put_umem(pool->umem, false); xp_destroy(pool); } @@ -251,15 +254,18 @@ void xp_get_pool(struct xsk_buff_pool *pool) refcount_inc(&pool->users); } -void xp_put_pool(struct xsk_buff_pool *pool) +bool xp_put_pool(struct xsk_buff_pool *pool) { if (!pool) - return; + return false; if (refcount_dec_and_test(&pool->users)) { INIT_WORK(&pool->work, xp_release_deferred); schedule_work(&pool->work); + return true; } + + return false; } static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool) diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index cdb9cf3cd136..9e71b9f27679 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -264,6 +264,12 @@ static inline bool xskq_cons_is_full(struct xsk_queue *q) q->nentries; } +static inline u32 xskq_cons_present_entries(struct xsk_queue *q) +{ + /* No barriers needed since data is not accessed */ + return READ_ONCE(q->ring->producer) - READ_ONCE(q->ring->consumer); +} + /* Functions for producers */ static inline bool xskq_prod_is_full(struct xsk_queue *q) diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index e28f0c9ecd6a..d8e8a11ca845 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -234,6 +234,7 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) case XFRMA_PAD: /* Ignore */ return 0; + case XFRMA_UNSPEC: case XFRMA_ALG_AUTH: case XFRMA_ALG_CRYPT: case XFRMA_ALG_COMP: @@ -387,7 +388,7 @@ static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src, memcpy(nla, src, nla_attr_size(copy_len)); nla->nla_len = nla_attr_size(payload); - *pos += nla_attr_size(payload); + *pos += nla_attr_size(copy_len); nlmsg->nlmsg_len += nla->nla_len; memset(dst + *pos, 0, payload - copy_len); @@ -563,7 +564,7 @@ static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32, return NULL; len += NLMSG_HDRLEN; - h64 = kvmalloc(len, GFP_KERNEL | __GFP_ZERO); + h64 = kvmalloc(len, GFP_KERNEL); if (!h64) return ERR_PTR(-ENOMEM); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index a77da7aae6fe..2f1517827995 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2382,8 +2382,10 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) if (in_compat_syscall()) { struct xfrm_translator *xtr = xfrm_get_translator(); - if (!xtr) + if (!xtr) { + kfree(data); return -EOPNOTSUPP; + } err = xtr->xlate_user_policy_sockptr(&data, optlen); xfrm_put_translator(xtr); diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c index 4a74531dc403..b68bd2f8fdc9 100644 --- a/samples/bpf/task_fd_query_user.c +++ b/samples/bpf/task_fd_query_user.c @@ -290,7 +290,7 @@ static int test_debug_fs_uprobe(char *binary_path, long offset, bool is_return) int main(int argc, char **argv) { - struct rlimit r = {1024*1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; extern char __executable_start; char filename[256], buf[256]; __u64 uprobe_file_offset; diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c index 3e36b3e4e3ef..3d6eab711d23 100644 --- a/samples/bpf/tracex2_user.c +++ b/samples/bpf/tracex2_user.c @@ -116,7 +116,7 @@ static void int_exit(int sig) int main(int ac, char **argv) { - struct rlimit r = {1024*1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; long key, next_key, value; struct bpf_link *links[2]; struct bpf_program *prog; diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c index 70e987775c15..83e0fecbb01a 100644 --- a/samples/bpf/tracex3_user.c +++ b/samples/bpf/tracex3_user.c @@ -107,7 +107,7 @@ static void print_hist(int fd) int main(int ac, char **argv) { - struct rlimit r = {1024*1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_link *links[2]; struct bpf_program *prog; struct bpf_object *obj; diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index 6fb8dbde62c5..f78cb18319aa 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -765,7 +765,7 @@ static int load_cpumap_prog(char *file_name, char *prog_name, int main(int argc, char **argv) { - struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; char *prog_name = "xdp_cpu_map5_lb_hash_ip_pairs"; char *mprog_filename = "xdp_redirect_kern.o"; char *redir_interface = NULL, *redir_map = NULL; diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index caa4e7ffcfc7..93fa1bc54f13 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -450,7 +450,7 @@ static void stats_poll(int interval, int action, __u32 cfg_opt) int main(int argc, char **argv) { __u32 cfg_options= NO_TOUCH ; /* Default: Don't touch packet memory */ - struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c index c13a5bc5095b..5b9a09957c6e 100644 --- a/samples/ftrace/ftrace-direct-modify.c +++ b/samples/ftrace/ftrace-direct-modify.c @@ -21,6 +21,7 @@ static unsigned long my_ip = (unsigned long)schedule; asm ( " .pushsection .text, \"ax\", @progbits\n" " .type my_tramp1, @function\n" +" .globl my_tramp1\n" " my_tramp1:" " pushq %rbp\n" " movq %rsp, %rbp\n" @@ -29,6 +30,7 @@ asm ( " .size my_tramp1, .-my_tramp1\n" " ret\n" " .type my_tramp2, @function\n" +" .globl my_tramp2\n" " my_tramp2:" " pushq %rbp\n" " movq %rsp, %rbp\n" diff --git a/samples/ftrace/ftrace-direct-too.c b/samples/ftrace/ftrace-direct-too.c index d5c5022be664..3f0079c9bd6f 100644 --- a/samples/ftrace/ftrace-direct-too.c +++ b/samples/ftrace/ftrace-direct-too.c @@ -16,6 +16,7 @@ extern void my_tramp(void *); asm ( " .pushsection .text, \"ax\", @progbits\n" " .type my_tramp, @function\n" +" .globl my_tramp\n" " my_tramp:" " pushq %rbp\n" " movq %rsp, %rbp\n" diff --git a/samples/ftrace/ftrace-direct.c b/samples/ftrace/ftrace-direct.c index 63ca06d42c80..a2729d1ef17f 100644 --- a/samples/ftrace/ftrace-direct.c +++ b/samples/ftrace/ftrace-direct.c @@ -14,6 +14,7 @@ extern void my_tramp(void *); asm ( " .pushsection .text, \"ax\", @progbits\n" " .type my_tramp, @function\n" +" .globl my_tramp\n" " my_tramp:" " pushq %rbp\n" " movq %rsp, %rbp\n" diff --git a/scripts/Makefile.build b/scripts/Makefile.build index ae647379b579..4c058f12dd73 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -252,6 +252,9 @@ objtool_dep = $(objtool_obj) \ ifdef CONFIG_TRIM_UNUSED_KSYMS cmd_gen_ksymdeps = \ $(CONFIG_SHELL) $(srctree)/scripts/gen_ksymdeps.sh $@ >> $(dot-target).cmd + +# List module undefined symbols +undefined_syms = $(NM) $< | $(AWK) '$$1 == "U" { printf("%s%s", x++ ? " " : "", $$2) }'; endif define rule_cc_o_c @@ -271,13 +274,6 @@ define rule_as_o_S $(call cmd,modversions_S) endef -# List module undefined symbols (or empty line if not enabled) -ifdef CONFIG_TRIM_UNUSED_KSYMS -cmd_undef_syms = $(NM) $< | sed -n 's/^ *U //p' | xargs echo -else -cmd_undef_syms = echo -endif - # Built-in and composite module parts $(obj)/%.o: $(src)/%.c $(recordmcount_source) $(objtool_dep) FORCE $(call if_changed_rule,cc_o_c) @@ -285,7 +281,7 @@ $(obj)/%.o: $(src)/%.c $(recordmcount_source) $(objtool_dep) FORCE cmd_mod = { \ echo $(if $($*-objs)$($*-y)$($*-m), $(addprefix $(obj)/, $($*-objs) $($*-y) $($*-m)), $(@:.mod=.o)); \ - $(cmd_undef_syms); \ + $(undefined_syms) echo; \ } > $@ $(obj)/%.mod: $(obj)/%.o FORCE diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 95e4cdb94fe9..6baee1200615 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -60,7 +60,6 @@ endif # ifneq ($(findstring 2, $(KBUILD_EXTRA_WARN)),) -KBUILD_CFLAGS += -Wcast-align KBUILD_CFLAGS += -Wdisabled-optimization KBUILD_CFLAGS += -Wnested-externs KBUILD_CFLAGS += -Wshadow @@ -80,6 +79,7 @@ endif ifneq ($(findstring 3, $(KBUILD_EXTRA_WARN)),) KBUILD_CFLAGS += -Wbad-function-cast +KBUILD_CFLAGS += -Wcast-align KBUILD_CFLAGS += -Wcast-qual KBUILD_CFLAGS += -Wconversion KBUILD_CFLAGS += -Wpacked diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index 6769caae142f..31484377b8b1 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -408,6 +408,7 @@ class PrinterHelpers(Printer): 'struct bpf_perf_event_data', 'struct bpf_perf_event_value', 'struct bpf_pidns_info', + 'struct bpf_redir_neigh', 'struct bpf_sock', 'struct bpf_sock_addr', 'struct bpf_sock_ops', diff --git a/scripts/lld-version.sh b/scripts/lld-version.sh new file mode 100755 index 000000000000..d70edb4d8a4f --- /dev/null +++ b/scripts/lld-version.sh @@ -0,0 +1,20 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Usage: $ ./scripts/lld-version.sh ld.lld +# +# Print the linker version of `ld.lld' in a 5 or 6-digit form +# such as `100001' for ld.lld 10.0.1 etc. + +linker_string="$($* --version)" + +if ! ( echo $linker_string | grep -q LLD ); then + echo 0 + exit 1 +fi + +VERSION=$(echo $linker_string | cut -d ' ' -f 2) +MAJOR=$(echo $VERSION | cut -d . -f 1) +MINOR=$(echo $VERSION | cut -d . -f 2) +PATCHLEVEL=$(echo $VERSION | cut -d . -f 3) +printf "%d%02d%02d\\n" $MAJOR $MINOR $PATCHLEVEL diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 1b11f8993629..91a502bb97e8 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -45,6 +45,8 @@ create_package() { chmod -R go-w "$pdir" # in case we are in a restrictive umask environment like 0077 chmod -R a+rX "$pdir" + # in case we build in a setuid/setgid directory + chmod -R ug-s "$pdir" # Create the package dpkg-gencontrol -p$pname -P"$pdir" diff --git a/security/selinux/ibpkey.c b/security/selinux/ibpkey.c index f68a7617cfb9..3a63a989e55e 100644 --- a/security/selinux/ibpkey.c +++ b/security/selinux/ibpkey.c @@ -151,8 +151,10 @@ static int sel_ib_pkey_sid_slow(u64 subnet_prefix, u16 pkey_num, u32 *sid) * is valid, it just won't be added to the cache. */ new = kzalloc(sizeof(*new), GFP_ATOMIC); - if (!new) + if (!new) { + ret = -ENOMEM; goto out; + } new->psec.subnet_prefix = subnet_prefix; new->psec.pkey = pkey_num; diff --git a/sound/core/control.c b/sound/core/control.c index 4373de42a5a0..3b44378b9dec 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1539,7 +1539,7 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, unlock: up_write(&card->controls_rwsem); - return 0; + return err; } static int snd_ctl_elem_add_user(struct snd_ctl_file *file, diff --git a/sound/firewire/fireworks/fireworks_transaction.c b/sound/firewire/fireworks/fireworks_transaction.c index 0f533f5bd960..9f8c53b39f95 100644 --- a/sound/firewire/fireworks/fireworks_transaction.c +++ b/sound/firewire/fireworks/fireworks_transaction.c @@ -123,7 +123,7 @@ copy_resp_to_buf(struct snd_efw *efw, void *data, size_t length, int *rcode) t = (struct snd_efw_transaction *)data; length = min_t(size_t, be32_to_cpu(t->length) * sizeof(u32), length); - spin_lock_irq(&efw->lock); + spin_lock(&efw->lock); if (efw->push_ptr < efw->pull_ptr) capacity = (unsigned int)(efw->pull_ptr - efw->push_ptr); @@ -190,7 +190,7 @@ handle_resp_for_user(struct fw_card *card, int generation, int source, copy_resp_to_buf(efw, data, length, rcode); end: - spin_unlock_irq(&instances_lock); + spin_unlock(&instances_lock); } static void diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index bbb17481159e..8060cc86dfea 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -1364,16 +1364,20 @@ static int try_assign_dacs(struct hda_codec *codec, int num_outs, struct nid_path *path; hda_nid_t pin = pins[i]; - path = snd_hda_get_path_from_idx(codec, path_idx[i]); - if (path) { - badness += assign_out_path_ctls(codec, path); - continue; + if (!spec->obey_preferred_dacs) { + path = snd_hda_get_path_from_idx(codec, path_idx[i]); + if (path) { + badness += assign_out_path_ctls(codec, path); + continue; + } } dacs[i] = get_preferred_dac(codec, pin); if (dacs[i]) { if (is_dac_already_used(codec, dacs[i])) badness += bad->shared_primary; + } else if (spec->obey_preferred_dacs) { + badness += BAD_NO_PRIMARY_DAC; } if (!dacs[i]) diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h index a43f0bb77dae..0886bc81f40b 100644 --- a/sound/pci/hda/hda_generic.h +++ b/sound/pci/hda/hda_generic.h @@ -237,6 +237,7 @@ struct hda_gen_spec { unsigned int power_down_unused:1; /* power down unused widgets */ unsigned int dac_min_mute:1; /* minimal = mute for DACs */ unsigned int suppress_vmaster:1; /* don't create vmaster kctls */ + unsigned int obey_preferred_dacs:1; /* obey preferred_dacs assignment */ /* other internal flags */ unsigned int no_analog:1; /* digital I/O only */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index d539f52009a1..6852668f1bcb 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2506,6 +2506,9 @@ static const struct pci_device_id azx_ids[] = { /* DG1 */ { PCI_DEVICE(0x8086, 0x490d), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* Alderlake-S */ + { PCI_DEVICE(0x8086, 0x7ad0), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Elkhart Lake */ { PCI_DEVICE(0x8086, 0x4b55), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index e0c38f2735c6..d8370a417e3d 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -9183,6 +9183,8 @@ static void ca0132_mmio_init(struct hda_codec *codec) case QUIRK_AE5: ca0132_mmio_init_ae5(codec); break; + default: + break; } } diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 9dfc05761a53..58638b5f0ec9 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4252,6 +4252,7 @@ HDA_CODEC_ENTRY(0x8086280d, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862814, "DG1 HDMI", patch_i915_tgl_hdmi), +HDA_CODEC_ENTRY(0x80862815, "Alderlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862816, "Rocketlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI", patch_i915_icl_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 6899089d132e..8616c5624870 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -119,6 +119,7 @@ struct alc_spec { unsigned int no_shutup_pins:1; unsigned int ultra_low_power:1; unsigned int has_hs_key:1; + unsigned int no_internal_mic_pin:1; /* for PLL fix */ hda_nid_t pll_nid; @@ -445,6 +446,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) alc_update_coef_idx(codec, 0x7, 1<<5, 0); break; case 0x10ec0892: + case 0x10ec0897: alc_update_coef_idx(codec, 0x7, 1<<5, 0); break; case 0x10ec0899: @@ -2522,13 +2524,23 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x9506, "Clevo P955HQ", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x950A, "Clevo P955H[PR]", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e3, "Clevo P955[ER]T", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e4, "Clevo P955ER", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e5, "Clevo P955EE6", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e6, "Clevo P950R[CDF]", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x96e1, "Clevo P960[ER][CDFN]-K", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x97e1, "Clevo P970[ER][CDFN]", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x97e2, "Clevo P970RC-M", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65d1, "Clevo PB51[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x65d2, "Clevo PB51R[CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x65e1, "Clevo PB51[ED][DF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), - SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x67e1, "Clevo PB71[DE][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x70d1, "Clevo PC70[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x7714, "Clevo X170", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), @@ -4216,6 +4228,12 @@ static void alc286_fixup_hp_gpio_led(struct hda_codec *codec, alc_fixup_hp_gpio_led(codec, action, 0x02, 0x20); } +static void alc287_fixup_hp_gpio_led(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + alc_fixup_hp_gpio_led(codec, action, 0x10, 0); +} + /* turn on/off mic-mute LED per capture hook via VREF change */ static int vref_micmute_led_set(struct led_classdev *led_cdev, enum led_brightness brightness) @@ -4507,6 +4525,7 @@ static const struct coef_fw alc225_pre_hsmode[] = { static void alc_headset_mode_unplugged(struct hda_codec *codec) { + struct alc_spec *spec = codec->spec; static const struct coef_fw coef0255[] = { WRITE_COEF(0x1b, 0x0c0b), /* LDO and MISC control */ WRITE_COEF(0x45, 0xd089), /* UAJ function set to menual mode */ @@ -4581,6 +4600,11 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec) {} }; + if (spec->no_internal_mic_pin) { + alc_update_coef_idx(codec, 0x45, 0xf<<12 | 1<<10, 5<<12); + return; + } + switch (codec->core.vendor_id) { case 0x10ec0255: alc_process_coef_fw(codec, coef0255); @@ -5147,6 +5171,11 @@ static void alc_determine_headset_type(struct hda_codec *codec) {} }; + if (spec->no_internal_mic_pin) { + alc_update_coef_idx(codec, 0x45, 0xf<<12 | 1<<10, 5<<12); + return; + } + switch (codec->core.vendor_id) { case 0x10ec0255: alc_process_coef_fw(codec, coef0255); @@ -5998,6 +6027,21 @@ static void alc274_fixup_bind_dacs(struct hda_codec *codec, codec->power_save_node = 0; } +/* avoid DAC 0x06 for bass speaker 0x17; it has no volume control */ +static void alc289_fixup_asus_ga401(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + static const hda_nid_t preferred_pairs[] = { + 0x14, 0x02, 0x17, 0x02, 0x21, 0x03, 0 + }; + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + spec->gen.preferred_dacs = preferred_pairs; + spec->gen.obey_preferred_dacs = 1; + } +} + /* The DAC of NID 0x3 will introduce click/pop noise on headphones, so invalidate it */ static void alc285_fixup_invalidate_dacs(struct hda_codec *codec, const struct hda_fixup *fix, int action) @@ -6105,6 +6149,23 @@ static void alc274_fixup_hp_headset_mic(struct hda_codec *codec, } } +static void alc_fixup_no_int_mic(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + /* Mic RING SLEEVE swap for combo jack */ + alc_update_coef_idx(codec, 0x45, 0xf<<12 | 1<<10, 5<<12); + spec->no_internal_mic_pin = true; + break; + case HDA_FIXUP_ACT_INIT: + alc_combo_jack_hp_jd_restart(codec); + break; + } +} + /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" @@ -6301,6 +6362,10 @@ enum { ALC274_FIXUP_HP_MIC, ALC274_FIXUP_HP_HEADSET_MIC, ALC256_FIXUP_ASUS_HPE, + ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, + ALC287_FIXUP_HP_GPIO_LED, + ALC256_FIXUP_HP_HEADSET_MIC, + ALC236_FIXUP_DELL_AIO_HEADSET_MIC, }; static const struct hda_fixup alc269_fixups[] = { @@ -7550,11 +7615,10 @@ static const struct hda_fixup alc269_fixups[] = { .chain_id = ALC269_FIXUP_HEADSET_MIC }, [ALC289_FIXUP_ASUS_GA401] = { - .type = HDA_FIXUP_PINS, - .v.pins = (const struct hda_pintbl[]) { - { 0x19, 0x03a11020 }, /* headset mic with jack detect */ - { } - }, + .type = HDA_FIXUP_FUNC, + .v.func = alc289_fixup_asus_ga401, + .chained = true, + .chain_id = ALC289_FIXUP_ASUS_GA502, }, [ALC289_FIXUP_ASUS_GA502] = { .type = HDA_FIXUP_PINS, @@ -7678,7 +7742,7 @@ static const struct hda_fixup alc269_fixups[] = { { } }, .chained = true, - .chain_id = ALC289_FIXUP_ASUS_GA401 + .chain_id = ALC289_FIXUP_ASUS_GA502 }, [ALC274_FIXUP_HP_MIC] = { .type = HDA_FIXUP_VERBS, @@ -7705,6 +7769,26 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC }, + [ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_headset_jack, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI + }, + [ALC287_FIXUP_HP_GPIO_LED] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_hp_gpio_led, + }, + [ALC256_FIXUP_HP_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc274_fixup_hp_headset_mic, + }, + [ALC236_FIXUP_DELL_AIO_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_no_int_mic, + .chained = true, + .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7782,6 +7866,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x097d, "Dell Precision", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x098d, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x09bf, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x0a2e, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC), + SND_PCI_QUIRK(0x1028, 0x0a30, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -7848,6 +7934,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8256, "HP", ALC221_FIXUP_HP_FRONT_MIC), SND_PCI_QUIRK(0x103c, 0x827e, "HP x360", ALC295_FIXUP_HP_X360), + SND_PCI_QUIRK(0x103c, 0x827f, "HP x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x82bf, "HP G3 mini", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x82c0, "HP G3 mini premium", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), @@ -7859,6 +7946,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8760, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -7924,11 +8013,49 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1558, 0x1323, "Clevo N130ZU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x1325, "System76 Darter Pro (darp5)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x1401, "Clevo L140[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x1403, "Clevo N140CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x1404, "Clevo N150CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x14a1, "Clevo L141MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x4018, "Clevo NV40M[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x4019, "Clevo NV40MZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x4020, "Clevo NV40MB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x40a1, "Clevo NL40GU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x40c1, "Clevo NL40[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x40d1, "Clevo NL41DU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50a3, "Clevo NJ51GU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50b3, "Clevo NK50S[BEZ]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50b6, "Clevo NK50S5", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50b8, "Clevo NK50SZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50d5, "Clevo NP50D5", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50f0, "Clevo NH50A[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x50f3, "Clevo NH58DPQ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x5101, "Clevo S510WU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x5157, "Clevo W517GU1", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x51a1, "Clevo NS50MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x70a1, "Clevo NB70T[HJK]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x70b3, "Clevo NK70SB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8228, "Clevo NR40BU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8520, "Clevo NH50D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8521, "Clevo NH77D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8535, "Clevo NH50D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8536, "Clevo NH79D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8550, "System76 Gazelle (gaze14)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8551, "System76 Gazelle (gaze14)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8560, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1558, 0x8561, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1558, 0x8668, "Clevo NP50B[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8680, "Clevo NJ50LU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8686, "Clevo NH50[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8a20, "Clevo NH55DCQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8a51, "Clevo NH70RCQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x8d50, "Clevo NH55RCQ-M", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x951d, "Clevo N950T[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x961d, "Clevo N960S[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x971d, "Clevo N970T[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0xa500, "Clevo NL53RU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS), SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), @@ -7966,6 +8093,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), + SND_PCI_QUIRK(0x17aa, 0x22c1, "Thinkpad P1 Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK), + SND_PCI_QUIRK(0x17aa, 0x22c2, "Thinkpad X1 Extreme Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), @@ -8278,6 +8407,12 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x19, 0x02a11020}, {0x1a, 0x02a11030}, {0x21, 0x0221101f}), + SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC, + {0x21, 0x02211010}), + SND_HDA_PIN_QUIRK(0x10ec0236, 0x103c, "HP", ALC256_FIXUP_HP_HEADSET_MIC, + {0x14, 0x90170110}, + {0x19, 0x02a11020}, + {0x21, 0x02211030}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, {0x14, 0x90170110}, {0x21, 0x02211020}), @@ -8380,6 +8515,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x1a, 0x90a70130}, {0x1b, 0x90170110}, {0x21, 0x03211020}), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x103c, "HP", ALC256_FIXUP_HP_HEADSET_MIC, + {0x14, 0x90170110}, + {0x19, 0x02a11020}, + {0x21, 0x0221101f}), SND_HDA_PIN_QUIRK(0x10ec0274, 0x103c, "HP", ALC274_FIXUP_HP_HEADSET_MIC, {0x17, 0x90170110}, {0x19, 0x03a11030}, @@ -8502,6 +8641,9 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE, ALC292_STANDARD_PINS, {0x13, 0x90a60140}), + SND_HDA_PIN_QUIRK(0x10ec0294, 0x1043, "ASUS", ALC294_FIXUP_ASUS_HPE, + {0x17, 0x90170110}, + {0x21, 0x04211020}), SND_HDA_PIN_QUIRK(0x10ec0294, 0x1043, "ASUS", ALC294_FIXUP_ASUS_MIC, {0x14, 0x90170110}, {0x1b, 0x90a70130}, @@ -10088,6 +10230,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = { HDA_CODEC_ENTRY(0x10ec0888, "ALC888", patch_alc882), HDA_CODEC_ENTRY(0x10ec0889, "ALC889", patch_alc882), HDA_CODEC_ENTRY(0x10ec0892, "ALC892", patch_alc662), + HDA_CODEC_ENTRY(0x10ec0897, "ALC897", patch_alc662), HDA_CODEC_ENTRY(0x10ec0899, "ALC898", patch_alc882), HDA_CODEC_ENTRY(0x10ec0900, "ALC1150", patch_alc882), HDA_CODEC_ENTRY(0x10ec0b00, "ALCS1200A", patch_alc882), diff --git a/sound/pci/mixart/mixart_core.c b/sound/pci/mixart/mixart_core.c index 0bdd33b0af65..fb8895af0363 100644 --- a/sound/pci/mixart/mixart_core.c +++ b/sound/pci/mixart/mixart_core.c @@ -70,7 +70,6 @@ static int get_msg(struct mixart_mgr *mgr, struct mixart_msg *resp, unsigned int i; #endif - mutex_lock(&mgr->msg_lock); err = 0; /* copy message descriptor from miXart to driver */ @@ -119,8 +118,6 @@ static int get_msg(struct mixart_mgr *mgr, struct mixart_msg *resp, writel_be(headptr, MIXART_MEM(mgr, MSG_OUTBOUND_FREE_HEAD)); _clean_exit: - mutex_unlock(&mgr->msg_lock); - return err; } @@ -258,7 +255,9 @@ int snd_mixart_send_msg(struct mixart_mgr *mgr, struct mixart_msg *request, int resp.data = resp_data; resp.size = max_resp_size; + mutex_lock(&mgr->msg_lock); err = get_msg(mgr, &resp, msg_frame); + mutex_unlock(&mgr->msg_lock); if( request->message_id != resp.message_id ) dev_err(&mgr->pci->dev, "RESPONSE ERROR!\n"); diff --git a/sound/soc/codecs/rt1015.c b/sound/soc/codecs/rt1015.c index 25fe2ddedd54..3db07293c70b 100644 --- a/sound/soc/codecs/rt1015.c +++ b/sound/soc/codecs/rt1015.c @@ -27,10 +27,15 @@ #include <sound/soc-dapm.h> #include <sound/soc.h> #include <sound/tlv.h> +#include <sound/rt1015.h> #include "rl6231.h" #include "rt1015.h" +static const struct rt1015_platform_data i2s_default_platform_data = { + .power_up_delay_ms = 50, +}; + static const struct reg_default rt1015_reg[] = { { 0x0000, 0x0000 }, { 0x0004, 0xa000 }, @@ -539,7 +544,7 @@ static void rt1015_flush_work(struct work_struct *work) struct rt1015_priv *rt1015 = container_of(work, struct rt1015_priv, flush_work.work); struct snd_soc_component *component = rt1015->component; - unsigned int val, i = 0, count = 20; + unsigned int val, i = 0, count = 200; while (i < count) { usleep_range(1000, 1500); @@ -650,6 +655,7 @@ static int rt1015_amp_drv_event(struct snd_soc_dapm_widget *w, case SND_SOC_DAPM_POST_PMU: if (rt1015->hw_config == RT1015_HW_28) schedule_delayed_work(&rt1015->flush_work, msecs_to_jiffies(10)); + msleep(rt1015->pdata.power_up_delay_ms); break; default: break; @@ -1067,9 +1073,16 @@ static struct acpi_device_id rt1015_acpi_match[] = { MODULE_DEVICE_TABLE(acpi, rt1015_acpi_match); #endif +static void rt1015_parse_dt(struct rt1015_priv *rt1015, struct device *dev) +{ + device_property_read_u32(dev, "realtek,power-up-delay-ms", + &rt1015->pdata.power_up_delay_ms); +} + static int rt1015_i2c_probe(struct i2c_client *i2c, const struct i2c_device_id *id) { + struct rt1015_platform_data *pdata = dev_get_platdata(&i2c->dev); struct rt1015_priv *rt1015; int ret; unsigned int val; @@ -1081,6 +1094,13 @@ static int rt1015_i2c_probe(struct i2c_client *i2c, i2c_set_clientdata(i2c, rt1015); + rt1015->pdata = i2s_default_platform_data; + + if (pdata) + rt1015->pdata = *pdata; + else + rt1015_parse_dt(rt1015, &i2c->dev); + rt1015->regmap = devm_regmap_init_i2c(i2c, &rt1015_regmap); if (IS_ERR(rt1015->regmap)) { ret = PTR_ERR(rt1015->regmap); diff --git a/sound/soc/codecs/rt1015.h b/sound/soc/codecs/rt1015.h index d3fdd30aca6d..15cadb361ec3 100644 --- a/sound/soc/codecs/rt1015.h +++ b/sound/soc/codecs/rt1015.h @@ -12,6 +12,7 @@ #ifndef __RT1015_H__ #define __RT1015_H__ +#include <sound/rt1015.h> #define RT1015_DEVICE_ID_VAL 0x1011 #define RT1015_DEVICE_ID_VAL2 0x1015 @@ -380,6 +381,7 @@ enum { struct rt1015_priv { struct snd_soc_component *component; + struct rt1015_platform_data pdata; struct regmap *regmap; int sysclk; int sysclk_src; diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index a9acce7b6cca..d9878173ff89 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -43,6 +43,7 @@ static const struct reg_sequence patch_list[] = { {RT5682_DAC_ADC_DIG_VOL1, 0xa020}, {RT5682_I2C_CTRL, 0x000f}, {RT5682_PLL2_INTERNAL, 0x8266}, + {RT5682_SAR_IL_CMD_3, 0x8365}, }; void rt5682_apply_patch_list(struct rt5682_priv *rt5682, struct device *dev) diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index bcf18bf15a02..e61d00486c65 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -1937,6 +1937,7 @@ static int wm_adsp_load(struct wm_adsp *dsp) mem = wm_adsp_find_region(dsp, type); if (!mem) { adsp_err(dsp, "No region of type: %x\n", type); + ret = -EINVAL; goto out_fw; } diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 9dadf6561444..f790514a147d 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -520,10 +520,10 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { .driver_data = (void *)(BYT_RT5640_IN1_MAP | BYT_RT5640_MCLK_EN), }, - { /* HP Pavilion x2 10-n000nd */ + { /* HP Pavilion x2 10-k0XX, 10-n0XX */ .matches = { - DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HP Pavilion x2 Detachable"), + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion x2 Detachable"), }, .driver_data = (void *)(BYT_RT5640_DMIC1_MAP | BYT_RT5640_JD_SRC_JD2_IN4N | @@ -532,6 +532,17 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { /* HP Pavilion x2 10-p0XX */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP x2 Detachable 10-p0XX"), + }, + .driver_data = (void *)(BYT_RT5640_DMIC1_MAP | + BYT_RT5640_JD_SRC_JD1_IN4P | + BYT_RT5640_OVCD_TH_1500UA | + BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_MCLK_EN), + }, { /* HP Stream 7 */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c index 922cd0176e1f..f95546c184aa 100644 --- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c +++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c @@ -700,6 +700,8 @@ static int kabylake_set_bias_level(struct snd_soc_card *card, switch (level) { case SND_SOC_BIAS_PREPARE: if (dapm->bias_level == SND_SOC_BIAS_ON) { + if (!__clk_is_enabled(priv->mclk)) + return 0; dev_dbg(card->dev, "Disable mclk"); clk_disable_unprepare(priv->mclk); } else { diff --git a/sound/soc/intel/catpt/pcm.c b/sound/soc/intel/catpt/pcm.c index ba653ebea7d1..408e64e3b5fb 100644 --- a/sound/soc/intel/catpt/pcm.c +++ b/sound/soc/intel/catpt/pcm.c @@ -458,10 +458,6 @@ static int catpt_dai_prepare(struct snd_pcm_substream *substream, if (ret) return CATPT_IPC_ERROR(ret); - ret = catpt_dsp_update_lpclock(cdev); - if (ret) - return ret; - ret = catpt_dai_apply_usettings(dai, stream); if (ret) return ret; @@ -500,6 +496,7 @@ static int catpt_dai_trigger(struct snd_pcm_substream *substream, int cmd, case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: resume_stream: + catpt_dsp_update_lpclock(cdev); ret = catpt_ipc_resume_stream(cdev, stream->info.stream_hw_id); if (ret) return CATPT_IPC_ERROR(ret); @@ -507,11 +504,11 @@ static int catpt_dai_trigger(struct snd_pcm_substream *substream, int cmd, case SNDRV_PCM_TRIGGER_STOP: stream->prepared = false; - catpt_dsp_update_lpclock(cdev); fallthrough; case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: ret = catpt_ipc_pause_stream(cdev, stream->info.stream_hw_id); + catpt_dsp_update_lpclock(cdev); if (ret) return CATPT_IPC_ERROR(ret); break; @@ -534,6 +531,8 @@ void catpt_stream_update_position(struct catpt_dev *cdev, dsppos = bytes_to_frames(r, pos->stream_position); + if (!stream->prepared) + goto exit; /* only offload is set_write_pos driven */ if (stream->template->type != CATPT_STRM_TYPE_RENDER) goto exit; diff --git a/sound/soc/intel/keembay/kmb_platform.c b/sound/soc/intel/keembay/kmb_platform.c index f54b710ee1c2..291a686568c2 100644 --- a/sound/soc/intel/keembay/kmb_platform.c +++ b/sound/soc/intel/keembay/kmb_platform.c @@ -487,9 +487,9 @@ static int kmb_dai_hw_params(struct snd_pcm_substream *substream, kmb_i2s->xfer_resolution = 0x02; break; case SNDRV_PCM_FORMAT_S24_LE: - config->data_width = 24; - kmb_i2s->ccr = 0x08; - kmb_i2s->xfer_resolution = 0x04; + config->data_width = 32; + kmb_i2s->ccr = 0x14; + kmb_i2s->xfer_resolution = 0x05; break; case SNDRV_PCM_FORMAT_S32_LE: config->data_width = 32; diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index 9d17c87445a9..426235a217ec 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -263,28 +263,6 @@ static int lpass_cpu_daiops_hw_params(struct snd_pcm_substream *substream, return 0; } -static int lpass_cpu_daiops_prepare(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai); - struct lpaif_i2sctl *i2sctl = drvdata->i2sctl; - unsigned int id = dai->driver->id; - int ret; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { - ret = regmap_fields_write(i2sctl->spken, id, - LPAIF_I2SCTL_SPKEN_ENABLE); - } else { - ret = regmap_fields_write(i2sctl->micen, id, - LPAIF_I2SCTL_MICEN_ENABLE); - } - - if (ret) - dev_err(dai->dev, "error writing to i2sctl enable: %d\n", ret); - - return ret; -} - static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, int cmd, struct snd_soc_dai *dai) { @@ -292,6 +270,18 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, struct lpaif_i2sctl *i2sctl = drvdata->i2sctl; unsigned int id = dai->driver->id; int ret = -EINVAL; + unsigned int val = 0; + + ret = regmap_read(drvdata->lpaif_map, + LPAIF_I2SCTL_REG(drvdata->variant, dai->driver->id), &val); + if (ret) { + dev_err(dai->dev, "error reading from i2sctl reg: %d\n", ret); + return ret; + } + if (val == LPAIF_I2SCTL_RESET_STATE) { + dev_err(dai->dev, "error in i2sctl register state\n"); + return -ENOTRECOVERABLE; + } switch (cmd) { case SNDRV_PCM_TRIGGER_START: @@ -308,11 +298,14 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, dev_err(dai->dev, "error writing to i2sctl reg: %d\n", ret); - ret = clk_enable(drvdata->mi2s_bit_clk[id]); - if (ret) { - dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret); - clk_disable(drvdata->mi2s_osr_clk[id]); - return ret; + if (drvdata->bit_clk_state[id] == LPAIF_BIT_CLK_DISABLE) { + ret = clk_enable(drvdata->mi2s_bit_clk[id]); + if (ret) { + dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret); + clk_disable(drvdata->mi2s_osr_clk[id]); + return ret; + } + drvdata->bit_clk_state[id] = LPAIF_BIT_CLK_ENABLE; } break; @@ -329,7 +322,10 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream, if (ret) dev_err(dai->dev, "error writing to i2sctl reg: %d\n", ret); - clk_disable(drvdata->mi2s_bit_clk[dai->driver->id]); + if (drvdata->bit_clk_state[id] == LPAIF_BIT_CLK_ENABLE) { + clk_disable(drvdata->mi2s_bit_clk[dai->driver->id]); + drvdata->bit_clk_state[id] = LPAIF_BIT_CLK_DISABLE; + } break; } @@ -341,7 +337,6 @@ const struct snd_soc_dai_ops asoc_qcom_lpass_cpu_dai_ops = { .startup = lpass_cpu_daiops_startup, .shutdown = lpass_cpu_daiops_shutdown, .hw_params = lpass_cpu_daiops_hw_params, - .prepare = lpass_cpu_daiops_prepare, .trigger = lpass_cpu_daiops_trigger, }; EXPORT_SYMBOL_GPL(asoc_qcom_lpass_cpu_dai_ops); @@ -459,16 +454,20 @@ static bool lpass_cpu_regmap_volatile(struct device *dev, unsigned int reg) struct lpass_variant *v = drvdata->variant; int i; + for (i = 0; i < v->i2s_ports; ++i) + if (reg == LPAIF_I2SCTL_REG(v, i)) + return true; for (i = 0; i < v->irq_ports; ++i) if (reg == LPAIF_IRQSTAT_REG(v, i)) return true; for (i = 0; i < v->rdma_channels; ++i) - if (reg == LPAIF_RDMACURR_REG(v, i)) + if (reg == LPAIF_RDMACURR_REG(v, i) || reg == LPAIF_RDMACTL_REG(v, i)) return true; for (i = 0; i < v->wrdma_channels; ++i) - if (reg == LPAIF_WRDMACURR_REG(v, i + v->wrdma_channel_start)) + if (reg == LPAIF_WRDMACURR_REG(v, i + v->wrdma_channel_start) || + reg == LPAIF_WRDMACTL_REG(v, i + v->wrdma_channel_start)) return true; return false; @@ -861,6 +860,7 @@ int asoc_qcom_lpass_cpu_platform_probe(struct platform_device *pdev) PTR_ERR(drvdata->mi2s_bit_clk[dai_id])); return PTR_ERR(drvdata->mi2s_bit_clk[dai_id]); } + drvdata->bit_clk_state[dai_id] = LPAIF_BIT_CLK_DISABLE; } /* Allocation for i2sctl regmap fields */ diff --git a/sound/soc/qcom/lpass-lpaif-reg.h b/sound/soc/qcom/lpass-lpaif-reg.h index 08f3fe508b85..405542832e99 100644 --- a/sound/soc/qcom/lpass-lpaif-reg.h +++ b/sound/soc/qcom/lpass-lpaif-reg.h @@ -60,6 +60,13 @@ #define LPAIF_I2SCTL_BITWIDTH_24 1 #define LPAIF_I2SCTL_BITWIDTH_32 2 +#define LPAIF_BIT_CLK_DISABLE 0 +#define LPAIF_BIT_CLK_ENABLE 1 + +#define LPAIF_I2SCTL_RESET_STATE 0x003C0004 +#define LPAIF_DMACTL_RESET_STATE 0x00200000 + + /* LPAIF IRQ */ #define LPAIF_IRQ_REG_ADDR(v, addr, port) \ (v->irq_reg_base + (addr) + v->irq_reg_stride * (port)) diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c index 36d1512ffd1f..80b09dede5f9 100644 --- a/sound/soc/qcom/lpass-platform.c +++ b/sound/soc/qcom/lpass-platform.c @@ -110,6 +110,7 @@ static int lpass_platform_pcmops_open(struct snd_soc_component *component, struct regmap *map; unsigned int dai_id = cpu_dai->driver->id; + component->id = dai_id; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; @@ -122,8 +123,10 @@ static int lpass_platform_pcmops_open(struct snd_soc_component *component, else dma_ch = 0; - if (dma_ch < 0) + if (dma_ch < 0) { + kfree(data); return dma_ch; + } if (cpu_dai->driver->id == LPASS_DP_RX) { map = drvdata->hdmiif_map; @@ -147,6 +150,7 @@ static int lpass_platform_pcmops_open(struct snd_soc_component *component, ret = snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); if (ret < 0) { + kfree(data); dev_err(soc_runtime->dev, "setting constraints failed: %d\n", ret); return -EINVAL; @@ -448,19 +452,34 @@ static int lpass_platform_pcmops_trigger(struct snd_soc_component *component, unsigned int reg_irqclr = 0, val_irqclr = 0; unsigned int reg_irqen = 0, val_irqen = 0, val_mask = 0; unsigned int dai_id = cpu_dai->driver->id; + unsigned int dma_ctrl_reg = 0; ch = pcm_data->dma_ch; if (dir == SNDRV_PCM_STREAM_PLAYBACK) { id = pcm_data->dma_ch; - if (dai_id == LPASS_DP_RX) + if (dai_id == LPASS_DP_RX) { dmactl = drvdata->hdmi_rd_dmactl; - else + map = drvdata->hdmiif_map; + } else { dmactl = drvdata->rd_dmactl; + map = drvdata->lpaif_map; + } } else { dmactl = drvdata->wr_dmactl; id = pcm_data->dma_ch - v->wrdma_channel_start; + map = drvdata->lpaif_map; + } + ret = regmap_read(map, LPAIF_DMACTL_REG(v, ch, dir, dai_id), &dma_ctrl_reg); + if (ret) { + dev_err(soc_runtime->dev, "error reading from rdmactl reg: %d\n", ret); + return ret; } + if (dma_ctrl_reg == LPAIF_DMACTL_RESET_STATE || + dma_ctrl_reg == LPAIF_DMACTL_RESET_STATE + 1) { + dev_err(soc_runtime->dev, "error in rdmactl register state\n"); + return -ENOTRECOVERABLE; + } switch (cmd) { case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: diff --git a/sound/soc/qcom/lpass.h b/sound/soc/qcom/lpass.h index b4830f353796..bccd1a05d771 100644 --- a/sound/soc/qcom/lpass.h +++ b/sound/soc/qcom/lpass.h @@ -68,6 +68,7 @@ struct lpass_data { unsigned int mi2s_playback_sd_mode[LPASS_MAX_MI2S_PORTS]; unsigned int mi2s_capture_sd_mode[LPASS_MAX_MI2S_PORTS]; int hdmi_port_enable; + int bit_clk_state[LPASS_MAX_MI2S_PORTS]; /* low-power audio interface (LPAIF) registers */ void __iomem *lpaif; diff --git a/sound/usb/card.c b/sound/usb/card.c index fa764b61fe9c..4457214a3ae6 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -379,6 +379,10 @@ static const struct usb_audio_device_name usb_audio_names[] = { DEVICE_NAME(0x046d, 0x0990, "Logitech, Inc.", "QuickCam Pro 9000"), + /* ASUS ROG Strix */ + PROFILE_NAME(0x0b05, 0x1917, + "Realtek", "ALC1220-VB-DT", "Realtek-ALC1220-VB-Desktop"), + /* Dell WD15 Dock */ PROFILE_NAME(0x0bda, 0x4014, "Dell", "WD15 Dock", "Dell-WD15-Dock"), /* Dell WD19 Dock */ diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index c369c81e74c4..a7212f16660e 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -561,7 +561,8 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { }, { /* ASUS ROG Strix */ .id = USB_ID(0x0b05, 0x1917), - .map = asus_rog_map, + .map = trx40_mobo_map, + .connector_map = trx40_mobo_connector_map, }, { /* MSI TRX40 Creator */ .id = USB_ID(0x0db0, 0x0d64), diff --git a/sound/usb/mixer_us16x08.c b/sound/usb/mixer_us16x08.c index 92b1a6d9c931..bd63a9ce6a70 100644 --- a/sound/usb/mixer_us16x08.c +++ b/sound/usb/mixer_us16x08.c @@ -607,7 +607,7 @@ static int snd_us16x08_eq_put(struct snd_kcontrol *kcontrol, static int snd_us16x08_meter_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { - uinfo->count = 1; + uinfo->count = 34; uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; uinfo->value.integer.max = 0x7FFF; uinfo->value.integer.min = 0; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index c989ad8052ae..c50be2f75f70 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1672,13 +1672,13 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) msleep(20); - /* Zoom R16/24, Logitech H650e/H570e, Jabra 550a, Kingston HyperX - * needs a tiny delay here, otherwise requests like get/set - * frequency return as failed despite actually succeeding. + /* Zoom R16/24, many Logitech(at least H650e/H570e/BCC950), + * Jabra 550a, Kingston HyperX needs a tiny delay here, + * otherwise requests like get/set frequency return + * as failed despite actually succeeding. */ if ((chip->usb_id == USB_ID(0x1686, 0x00dd) || - chip->usb_id == USB_ID(0x046d, 0x0a46) || - chip->usb_id == USB_ID(0x046d, 0x0a56) || + USB_ID_VENDOR(chip->usb_id) == 0x046d || /* Logitech */ chip->usb_id == USB_ID(0x0b0e, 0x0349) || chip->usb_id == USB_ID(0x0951, 0x16ad)) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h index 568854b14d0a..52c6262e6bfd 100644 --- a/tools/arch/x86/include/asm/insn.h +++ b/tools/arch/x86/include/asm/insn.h @@ -201,6 +201,21 @@ static inline int insn_offset_immediate(struct insn *insn) return insn_offset_displacement(insn) + insn->displacement.nbytes; } +/** + * for_each_insn_prefix() -- Iterate prefixes in the instruction + * @insn: Pointer to struct insn. + * @idx: Index storage. + * @prefix: Prefix byte. + * + * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix + * and the index is stored in @idx (note that this @idx is just for a cursor, + * do not change it.) + * Since prefixes.nbytes can be bigger than 4 if some prefixes + * are repeated, it cannot be used for looping over the prefixes. + */ +#define for_each_insn_prefix(insn, idx, prefix) \ + for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++) + #define POP_SS_OPCODE 0x1f #define MOV_SREG_OPCODE 0x8e diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 0b5b8ae56bd9..1e299ac73c86 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -16,8 +16,6 @@ * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. */ -.weak memcpy - /* * memcpy - Copy a memory block. * @@ -30,7 +28,7 @@ * rax original destination */ SYM_FUNC_START_ALIAS(__memcpy) -SYM_FUNC_START_LOCAL(memcpy) +SYM_FUNC_START_WEAK(memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS @@ -51,14 +49,14 @@ EXPORT_SYMBOL(__memcpy) * memcpy_erms() - enhanced fast string memcpy. This is faster and * simpler than memcpy. Use memcpy_erms when possible. */ -SYM_FUNC_START(memcpy_erms) +SYM_FUNC_START_LOCAL(memcpy_erms) movq %rdi, %rax movq %rdx, %rcx rep movsb ret SYM_FUNC_END(memcpy_erms) -SYM_FUNC_START(memcpy_orig) +SYM_FUNC_START_LOCAL(memcpy_orig) movq %rdi, %rax cmpq $0x20, %rdx diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index fd5d25a474b7..0bfd26e4ca9e 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -4,8 +4,7 @@ #include <linux/linkage.h> #include <asm/cpufeatures.h> #include <asm/alternative-asm.h> - -.weak memset +#include <asm/export.h> /* * ISO C memset - set a memory block to a byte value. This function uses fast @@ -18,7 +17,7 @@ * * rax original destination */ -SYM_FUNC_START_ALIAS(memset) +SYM_FUNC_START_WEAK(memset) SYM_FUNC_START(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended @@ -44,6 +43,8 @@ SYM_FUNC_START(__memset) ret SYM_FUNC_END(__memset) SYM_FUNC_END_ALIAS(memset) +EXPORT_SYMBOL(memset) +EXPORT_SYMBOL(__memset) /* * ISO C memset - set a memory block to a byte value. This function uses @@ -56,7 +57,7 @@ SYM_FUNC_END_ALIAS(memset) * * rax original destination */ -SYM_FUNC_START(memset_erms) +SYM_FUNC_START_LOCAL(memset_erms) movq %rdi,%r9 movb %sil,%al movq %rdx,%rcx @@ -65,7 +66,7 @@ SYM_FUNC_START(memset_erms) ret SYM_FUNC_END(memset_erms) -SYM_FUNC_START(memset_orig) +SYM_FUNC_START_LOCAL(memset_orig) movq %rdi,%r10 /* expand byte value */ diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index eb92027817a7..7362bef1a368 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -10,6 +10,7 @@ #include <unistd.h> #include <string.h> #include <errno.h> +#include <endian.h> #include <linux/kernel.h> #include <linux/bootconfig.h> @@ -147,6 +148,12 @@ static int load_xbc_file(const char *path, char **buf) return ret; } +static int pr_errno(const char *msg, int err) +{ + pr_err("%s: %d\n", msg, err); + return err; +} + static int load_xbc_from_initrd(int fd, char **buf) { struct stat stat; @@ -162,26 +169,26 @@ static int load_xbc_from_initrd(int fd, char **buf) if (stat.st_size < 8 + BOOTCONFIG_MAGIC_LEN) return 0; - if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) { - pr_err("Failed to lseek: %d\n", -errno); - return -errno; - } + if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) + return pr_errno("Failed to lseek for magic", -errno); + if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0) - return -errno; + return pr_errno("Failed to read", -errno); + /* Check the bootconfig magic bytes */ if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0) return 0; - if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) { - pr_err("Failed to lseek: %d\n", -errno); - return -errno; - } + if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) + return pr_errno("Failed to lseek for size", -errno); if (read(fd, &size, sizeof(u32)) < 0) - return -errno; + return pr_errno("Failed to read size", -errno); + size = le32toh(size); if (read(fd, &csum, sizeof(u32)) < 0) - return -errno; + return pr_errno("Failed to read checksum", -errno); + csum = le32toh(csum); /* Wrong size error */ if (stat.st_size < size + 8 + BOOTCONFIG_MAGIC_LEN) { @@ -190,10 +197,8 @@ static int load_xbc_from_initrd(int fd, char **buf) } if (lseek(fd, stat.st_size - (size + 8 + BOOTCONFIG_MAGIC_LEN), - SEEK_SET) < 0) { - pr_err("Failed to lseek: %d\n", -errno); - return -errno; - } + SEEK_SET) < 0) + return pr_errno("Failed to lseek", -errno); ret = load_xbc_fd(fd, buf, size); if (ret < 0) @@ -262,14 +267,16 @@ static int show_xbc(const char *path, bool list) ret = stat(path, &st); if (ret < 0) { - pr_err("Failed to stat %s: %d\n", path, -errno); - return -errno; + ret = -errno; + pr_err("Failed to stat %s: %d\n", path, ret); + return ret; } fd = open(path, O_RDONLY); if (fd < 0) { - pr_err("Failed to open initrd %s: %d\n", path, fd); - return -errno; + ret = -errno; + pr_err("Failed to open initrd %s: %d\n", path, ret); + return ret; } ret = load_xbc_from_initrd(fd, &buf); @@ -307,8 +314,9 @@ static int delete_xbc(const char *path) fd = open(path, O_RDWR); if (fd < 0) { - pr_err("Failed to open initrd %s: %d\n", path, fd); - return -errno; + ret = -errno; + pr_err("Failed to open initrd %s: %d\n", path, ret); + return ret; } size = load_xbc_from_initrd(fd, &buf); @@ -332,11 +340,13 @@ static int delete_xbc(const char *path) static int apply_xbc(const char *path, const char *xbc_path) { + char *buf, *data, *p; + size_t total_size; + struct stat stat; + const char *msg; u32 size, csum; - char *buf, *data; + int pos, pad; int ret, fd; - const char *msg; - int pos; ret = load_xbc_file(xbc_path, &buf); if (ret < 0) { @@ -346,13 +356,12 @@ static int apply_xbc(const char *path, const char *xbc_path) size = strlen(buf) + 1; csum = checksum((unsigned char *)buf, size); - /* Prepare xbc_path data */ - data = malloc(size + 8); + /* Backup the bootconfig data */ + data = calloc(size + BOOTCONFIG_ALIGN + + sizeof(u32) + sizeof(u32) + BOOTCONFIG_MAGIC_LEN, 1); if (!data) return -ENOMEM; - strcpy(data, buf); - *(u32 *)(data + size) = size; - *(u32 *)(data + size + 4) = csum; + memcpy(data, buf, size); /* Check the data format */ ret = xbc_init(buf, &msg, &pos); @@ -383,28 +392,61 @@ static int apply_xbc(const char *path, const char *xbc_path) /* Apply new one */ fd = open(path, O_RDWR | O_APPEND); if (fd < 0) { - pr_err("Failed to open %s: %d\n", path, fd); + ret = -errno; + pr_err("Failed to open %s: %d\n", path, ret); free(data); - return fd; + return ret; } /* TODO: Ensure the @path is initramfs/initrd image */ - ret = write(fd, data, size + 8); - if (ret < 0) { - pr_err("Failed to apply a boot config: %d\n", ret); + if (fstat(fd, &stat) < 0) { + pr_err("Failed to get the size of %s\n", path); goto out; } - /* Write a magic word of the bootconfig */ - ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); - if (ret < 0) { - pr_err("Failed to apply a boot config magic: %d\n", ret); - goto out; - } - ret = 0; + + /* To align up the total size to BOOTCONFIG_ALIGN, get padding size */ + total_size = stat.st_size + size + sizeof(u32) * 2 + BOOTCONFIG_MAGIC_LEN; + pad = ((total_size + BOOTCONFIG_ALIGN - 1) & (~BOOTCONFIG_ALIGN_MASK)) - total_size; + size += pad; + + /* Add a footer */ + p = data + size; + *(u32 *)p = htole32(size); + p += sizeof(u32); + + *(u32 *)p = htole32(csum); + p += sizeof(u32); + + memcpy(p, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); + p += BOOTCONFIG_MAGIC_LEN; + + total_size = p - data; + + ret = write(fd, data, total_size); + if (ret < total_size) { + if (ret < 0) + ret = -errno; + pr_err("Failed to apply a boot config: %d\n", ret); + if (ret >= 0) + goto out_rollback; + } else + ret = 0; + out: close(fd); free(data); return ret; + +out_rollback: + /* Map the partial write to -ENOSPC */ + if (ret >= 0) + ret = -ENOSPC; + if (ftruncate(fd, stat.st_size) < 0) { + ret = -errno; + pr_err("Failed to rollback the write error: %d\n", ret); + pr_err("The initrd %s may be corrupted. Recommend to rebuild.\n", path); + } + goto out; } static int usage(void) diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh index d295e406a756..baed891d0ba4 100755 --- a/tools/bootconfig/test-bootconfig.sh +++ b/tools/bootconfig/test-bootconfig.sh @@ -9,6 +9,7 @@ else TESTDIR=. fi BOOTCONF=${TESTDIR}/bootconfig +ALIGN=4 INITRD=`mktemp ${TESTDIR}/initrd-XXXX` TEMPCONF=`mktemp ${TESTDIR}/temp-XXXX.bconf` @@ -59,7 +60,10 @@ echo "Show command test" xpass $BOOTCONF $INITRD echo "File size check" -xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9 + 12) +total_size=$(expr $bconf_size + $initrd_size + 9 + 12 + $ALIGN - 1 ) +total_size=$(expr $total_size / $ALIGN) +total_size=$(expr $total_size \* $ALIGN) +xpass test $new_size -eq $total_size echo "Apply command repeat test" xpass $BOOTCONF -a $TEMPCONF $INITRD diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 8ab142ff5eac..2afb7d5b1aca 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -693,6 +693,7 @@ build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type, obj_node = calloc(1, sizeof(*obj_node)); if (!obj_node) { p_err("failed to allocate memory: %s", strerror(errno)); + err = -ENOMEM; goto err_free; } diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index a43a6f10b564..359960a8f1de 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -843,9 +843,14 @@ static int handle_perms(void) else p_err("missing %s%s%s%s%s%s%s%srequired for full feature probing; run as root or use 'unprivileged'", capability_msg(bpf_caps, 0), +#ifdef CAP_BPF capability_msg(bpf_caps, 1), capability_msg(bpf_caps, 2), - capability_msg(bpf_caps, 3)); + capability_msg(bpf_caps, 3) +#else + "", "", "", "", "", "" +#endif /* CAP_BPF */ + ); goto exit_free; } diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 910e7bac6e9e..3fae61ef6339 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -578,8 +578,8 @@ static int do_attach(int argc, char **argv) ifindex = net_parse_dev(&argc, &argv); if (ifindex < 1) { - close(progfd); - return -EINVAL; + err = -EINVAL; + goto cleanup; } if (argc) { @@ -587,8 +587,8 @@ static int do_attach(int argc, char **argv) overwrite = true; } else { p_err("expected 'overwrite', got: '%s'?", *argv); - close(progfd); - return -EINVAL; + err = -EINVAL; + goto cleanup; } } @@ -596,17 +596,17 @@ static int do_attach(int argc, char **argv) if (is_prefix("xdp", attach_type_strings[attach_type])) err = do_attach_detach_xdp(progfd, attach_type, ifindex, overwrite); - - if (err < 0) { + if (err) { p_err("interface %s attach failed: %s", attach_type_strings[attach_type], strerror(-err)); - return err; + goto cleanup; } if (json_output) jsonw_null(json_wtr); - - return 0; +cleanup: + close(progfd); + return err; } static int do_detach(int argc, char **argv) diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c index df7d8ec76036..477e55d59c34 100644 --- a/tools/bpf/bpftool/pids.c +++ b/tools/bpf/bpftool/pids.c @@ -89,9 +89,9 @@ libbpf_print_none(__maybe_unused enum libbpf_print_level level, int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type) { - char buf[4096]; - struct pid_iter_bpf *skel; struct pid_iter_entry *e; + char buf[4096 / sizeof(*e) * sizeof(*e)]; + struct pid_iter_bpf *skel; int err, ret, fd = -1, i; libbpf_print_fn_t default_print; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index d942c1e3372c..acdb2c245f0a 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -940,7 +940,7 @@ static int parse_attach_detach_args(int argc, char **argv, int *progfd, } if (*attach_type == BPF_FLOW_DISSECTOR) { - *mapfd = -1; + *mapfd = 0; return 0; } diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c index 4e3512f700c0..ce5b65e07ab1 100644 --- a/tools/bpf/bpftool/skeleton/profiler.bpf.c +++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c @@ -70,7 +70,7 @@ int BPF_PROG(fentry_XXX) static inline void fexit_update_maps(u32 id, struct bpf_perf_event_value *after) { - struct bpf_perf_event_value *before, diff, *accum; + struct bpf_perf_event_value *before, diff; before = bpf_map_lookup_elem(&fentry_readings, &id); /* only account samples with a valid fentry_reading */ @@ -95,7 +95,7 @@ int BPF_PROG(fexit_XXX) { struct bpf_perf_event_value readings[MAX_NUM_MATRICS]; u32 cpu = bpf_get_smp_processor_id(); - u32 i, one = 1, zero = 0; + u32 i, zero = 0; int err; u64 *count; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e6ceac3f7d62..556216dc9703 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3897,8 +3897,8 @@ union bpf_attr { FN(seq_printf_btf), \ FN(skb_cgroup_classid), \ FN(redirect_neigh), \ - FN(bpf_per_cpu_ptr), \ - FN(bpf_this_cpu_ptr), \ + FN(per_cpu_ptr), \ + FN(this_cpu_ptr), \ FN(redirect_peer), \ /* */ diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index d199a3694be8..b0bf56c5f120 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -742,7 +742,11 @@ class DebugfsProvider(Provider): The fields are all available KVM debugfs files """ - return self.walkdir(PATH_DEBUGFS_KVM)[2] + exempt_list = ['halt_poll_fail_ns', 'halt_poll_success_ns'] + fields = [field for field in self.walkdir(PATH_DEBUGFS_KVM)[2] + if field not in exempt_list] + + return fields def update_fields(self, fields_filter): """Refresh fields, applying fields_filter""" diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 5f9abed3e226..55bd78b3496f 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -146,6 +146,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) @@ -214,6 +215,7 @@ check_abi: $(OUTPUT)libbpf.so awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \ diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h index d9b385fe808c..10a4c4cd13cf 100644 --- a/tools/lib/bpf/hashmap.h +++ b/tools/lib/bpf/hashmap.h @@ -15,6 +15,9 @@ static inline size_t hash_bits(size_t h, int bits) { /* shuffle bits and return requested number of upper bits */ + if (bits == 0) + return 0; + #if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__) /* LP64 case */ return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits); @@ -174,17 +177,17 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value); * @key: key to iterate entries for */ #define hashmap__for_each_key_entry(map, cur, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur; \ cur = cur->next) \ if (map->equal_fn(cur->key, (_key), map->ctx)) #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - cur = map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur && ({ tmp = cur->next; true; }); \ cur = tmp) \ if (map->equal_fn(cur->key, (_key), map->ctx)) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 313034117070..28baee7ba1ca 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -560,8 +560,6 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, const char *name, size_t sec_idx, const char *sec_name, size_t sec_off, void *insn_data, size_t insn_data_sz) { - int i; - if (insn_data_sz == 0 || insn_data_sz % BPF_INSN_SZ || sec_off % BPF_INSN_SZ) { pr_warn("sec '%s': corrupted program '%s', offset %zu, size %zu\n", sec_name, name, sec_off, insn_data_sz); @@ -600,13 +598,6 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, goto errout; memcpy(prog->insns, insn_data, insn_data_sz); - for (i = 0; i < prog->insns_cnt; i++) { - if (insn_is_subprog_call(&prog->insns[i])) { - obj->has_subcalls = true; - break; - } - } - return 0; errout: pr_warn("sec '%s': failed to allocate memory for prog '%s'\n", sec_name, name); @@ -3280,7 +3271,19 @@ bpf_object__find_program_by_title(const struct bpf_object *obj, static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog) { - return prog->sec_idx == obj->efile.text_shndx && obj->has_subcalls; + /* For legacy reasons, libbpf supports an entry-point BPF programs + * without SEC() attribute, i.e., those in the .text section. But if + * there are 2 or more such programs in the .text section, they all + * must be subprograms called from entry-point BPF programs in + * designated SEC()'tions, otherwise there is no way to distinguish + * which of those programs should be loaded vs which are a subprogram. + * Similarly, if there is a function/program in .text and at least one + * other BPF program with custom SEC() attribute, then we just assume + * .text programs are subprograms (even if they are not called from + * other programs), because libbpf never explicitly supported mixing + * SEC()-designated BPF programs and .text entry-point BPF programs. + */ + return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1; } struct bpf_program * diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index 5c6522c89af1..98537ff2679e 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -278,7 +278,7 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms) err = ringbuf_process_ring(ring); if (err < 0) return err; - res += cnt; + res += err; } return cnt < 0 ? -errno : res; } diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index e3c98c007825..9bc537d0b92d 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -891,13 +891,16 @@ int xsk_umem__delete(struct xsk_umem *umem) void xsk_socket__delete(struct xsk_socket *xsk) { size_t desc_sz = sizeof(struct xdp_desc); - struct xsk_ctx *ctx = xsk->ctx; struct xdp_mmap_offsets off; + struct xsk_umem *umem; + struct xsk_ctx *ctx; int err; if (!xsk) return; + ctx = xsk->ctx; + umem = ctx->umem; if (ctx->prog_fd != -1) { xsk_delete_bpf_maps(xsk); close(ctx->prog_fd); @@ -917,11 +920,11 @@ void xsk_socket__delete(struct xsk_socket *xsk) xsk_put_ctx(ctx); - ctx->umem->refcount--; + umem->refcount--; /* Do not close an fd that also has an associated umem connected * to it. */ - if (xsk->fd != ctx->umem->fd) + if (xsk->fd != umem->fd) close(xsk->fd); free(xsk); } diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index 4e40402a4f81..478078fb0f22 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -38,6 +38,13 @@ static int sample_ustack(struct perf_sample *sample, stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; memcpy(buf, (void *) sp, stack_size); +#ifdef MEMORY_SANITIZER + /* + * Copying the stack may copy msan poison, avoid false positives in the + * unwinder by removing the poison here. + */ + __msan_unpoison(buf, stack_size); +#endif stack->data = (char *) buf; stack->size = stack_size; return 0; diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 9ad015a1e202..6eb45a2aa8db 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -2,6 +2,9 @@ /* Various wrappers to make the kernel .S file build in user-space: */ +// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memcpy MEMCPY /* don't hide glibc's memcpy() */ #define altinstr_replacement text #define globl p2align 4; .globl diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index d550bd526162..6f093c483842 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memset MEMSET /* don't hide glibc's memset() */ #define altinstr_replacement text #define globl p2align 4; .globl diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 584e2e1a3793..cefc71506409 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -1222,8 +1222,10 @@ static int __cmd_diff(void) if (compute == COMPUTE_STREAM) { d->evlist_streams = evlist__create_streams( d->session->evlist, 5); - if (!d->evlist_streams) + if (!d->evlist_streams) { + ret = -ENOMEM; goto out_delete; + } } } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 452a75fe68e5..0462dc8db2e3 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -779,25 +779,15 @@ static int __cmd_inject(struct perf_inject *inject) dsos__hit_all(session); /* * The AUX areas have been removed and replaced with - * synthesized hardware events, so clear the feature flag and - * remove the evsel. + * synthesized hardware events, so clear the feature flag. */ if (inject->itrace_synth_opts.set) { - struct evsel *evsel; - perf_header__clear_feat(&session->header, HEADER_AUXTRACE); if (inject->itrace_synth_opts.last_branch || inject->itrace_synth_opts.add_last_branch) perf_header__set_feat(&session->header, HEADER_BRANCH_STACK); - evsel = perf_evlist__id2evsel_strict(session->evlist, - inject->aux_id); - if (evsel) { - pr_debug("Deleting %s\n", evsel__name(evsel)); - evlist__remove(session->evlist, evsel); - evsel__delete(evsel); - } } session->header.data_offset = output_data_offset; session->header.data_size = inject->bytes_written; diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index f0a1dbacb46c..a2f1e53f37a7 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -406,7 +406,7 @@ static int report_lock_acquire_event(struct evsel *evsel, struct lock_seq_stat *seq; const char *name = evsel__strval(evsel, sample, "name"); u64 tmp = evsel__intval(evsel, sample, "lockdep_addr"); - int flag = evsel__intval(evsel, sample, "flag"); + int flag = evsel__intval(evsel, sample, "flags"); memcpy(&addr, &tmp, sizeof(void *)); @@ -621,7 +621,7 @@ static int report_lock_release_event(struct evsel *evsel, case SEQ_STATE_READ_ACQUIRED: seq->read_count--; BUG_ON(seq->read_count < 0); - if (!seq->read_count) { + if (seq->read_count) { ls->nr_release++; goto end; } diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index 8d84fdbed6a6..18fde2f179cd 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -44,7 +44,7 @@ perf_script_branch_samples() { # touch 6512 1 branches:u: ffffb22082e0 strcmp+0xa0 (/lib/aarch64-linux-gnu/ld-2.27.so) # touch 6512 1 branches:u: ffffb2208320 strcmp+0xe0 (/lib/aarch64-linux-gnu/ld-2.27.so) perf script -F,-time -i ${perfdata} | \ - egrep " +$1 +[0-9]+ .* +branches:([u|k]:)? +" + egrep " +$1 +[0-9]+ .* +branches:(.*:)? +" } perf_report_branch_samples() { @@ -105,7 +105,7 @@ arm_cs_iterate_devices() { # `> device_name = 'tmc_etf0' device_name=$(basename $path) - if is_device_sink $path $devce_name; then + if is_device_sink $path $device_name; then record_touch_file $device_name $2 && perf_script_branch_samples touch && diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index aa898014ad12..7b2d471a6419 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -356,9 +356,25 @@ bool die_is_signed_type(Dwarf_Die *tp_die) bool die_is_func_def(Dwarf_Die *dw_die) { Dwarf_Attribute attr; + Dwarf_Addr addr = 0; + + if (dwarf_tag(dw_die) != DW_TAG_subprogram) + return false; + + if (dwarf_attr(dw_die, DW_AT_declaration, &attr)) + return false; - return (dwarf_tag(dw_die) == DW_TAG_subprogram && - dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL); + /* + * DW_AT_declaration can be lost from function declaration + * by gcc's bug #97060. + * So we need to check this subprogram DIE has DW_AT_inline + * or an entry address. + */ + if (!dwarf_attr(dw_die, DW_AT_inline, &attr) && + die_entrypc(dw_die, &addr) < 0) + return false; + + return true; } /** @@ -373,6 +389,7 @@ bool die_is_func_def(Dwarf_Die *dw_die) int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr) { Dwarf_Addr base, end; + Dwarf_Attribute attr; if (!addr) return -EINVAL; @@ -380,6 +397,13 @@ int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr) if (dwarf_entrypc(dw_die, addr) == 0) return 0; + /* + * Since the dwarf_ranges() will return 0 if there is no + * DW_AT_ranges attribute, we should check it first. + */ + if (!dwarf_attr(dw_die, DW_AT_ranges, &attr)) + return -ENOENT; + return dwarf_ranges(dw_die, 0, &base, addr, &end) < 0 ? -ENOENT : 0; } diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h index d9b385fe808c..10a4c4cd13cf 100644 --- a/tools/perf/util/hashmap.h +++ b/tools/perf/util/hashmap.h @@ -15,6 +15,9 @@ static inline size_t hash_bits(size_t h, int bits) { /* shuffle bits and return requested number of upper bits */ + if (bits == 0) + return 0; + #if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__) /* LP64 case */ return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits); @@ -174,17 +177,17 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value); * @key: key to iterate entries for */ #define hashmap__for_each_key_entry(map, cur, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur; \ cur = cur->next) \ if (map->equal_fn(cur->key, (_key), map->ctx)) #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - cur = map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur && ({ tmp = cur->next; true; }); \ cur = tmp) \ if (map->equal_fn(cur->key, (_key), map->ctx)) diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index b8a5159361b4..5acf053fca7d 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -25,6 +25,7 @@ /* SYM_L_* -- linkage of symbols */ #define SYM_L_GLOBAL(name) .globl name +#define SYM_L_WEAK(name) .weak name #define SYM_L_LOCAL(name) /* nothing */ #define ALIGN __ALIGN @@ -84,6 +85,12 @@ SYM_END(name, SYM_T_FUNC) #endif +/* SYM_FUNC_START_WEAK -- use for weak functions */ +#ifndef SYM_FUNC_START_WEAK +#define SYM_FUNC_START_WEAK(name) \ + SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN) +#endif + /* * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START, * SYM_FUNC_START_WEAK, ... diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 2c4061035f77..76dd349aa48d 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1885,8 +1885,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die))) return DWARF_CB_OK; - if (die_is_func_def(sp_die) && - die_match_name(sp_die, lr->function)) { + if (die_match_name(sp_die, lr->function) && die_is_func_def(sp_die)) { lf->fname = dwarf_decl_file(sp_die); dwarf_decl_line(sp_die, &lr->offset); pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 4b57c0c07632..a963b5b8eb72 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -324,13 +324,10 @@ static int first_shadow_cpu(struct perf_stat_config *config, struct evlist *evlist = evsel->evlist; int i; - if (!config->aggr_get_id) - return 0; - if (config->aggr_mode == AGGR_NONE) return id; - if (config->aggr_mode == AGGR_GLOBAL) + if (!config->aggr_get_id) return 0; for (i = 0; i < evsel__nr_cpus(evsel); i++) { diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 8a23391558cf..d9c624377da7 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -563,6 +563,9 @@ int perf_event__synthesize_cgroups(struct perf_tool *tool, char cgrp_root[PATH_MAX]; size_t mount_len; /* length of mount point in the path */ + if (!tool || !tool->cgroup_events) + return 0; + if (cgroupfs_find_mountpoint(cgrp_root, PATH_MAX, "perf_event") < 0) { pr_debug("cannot find cgroup mount point\n"); return -1; diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index 2b6551269e43..f3e3c94ab9bd 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -12,11 +12,12 @@ turbostat : turbostat.c override CFLAGS += -O2 -Wall -I../../../include override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' override CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"' +override CFLAGS += -D_FILE_OFFSET_BITS=64 override CFLAGS += -D_FORTIFY_SOURCE=2 %: %.c @mkdir -p $(BUILD_OUTPUT) - $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap + $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap -lrt .PHONY : clean clean : diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index a6db83a88e85..f6b7e85b121c 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -335,7 +335,7 @@ that they count at TSC rate, which is true on all processors tested to date. .SH REFERENCES Volume 3B: System Programming Guide" -http://www.intel.com/products/processor/manuals/ +https://www.intel.com/products/processor/manuals/ .SH FILES .ta diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 33b370865d16..f3a1746f7f45 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -79,6 +79,7 @@ unsigned long long gfx_cur_rc6_ms; unsigned long long cpuidle_cur_cpu_lpi_us; unsigned long long cpuidle_cur_sys_lpi_us; unsigned int gfx_cur_mhz; +unsigned int gfx_act_mhz; unsigned int tcc_activation_temp; unsigned int tcc_activation_temp_override; double rapl_power_units, rapl_time_units; @@ -210,13 +211,14 @@ struct pkg_data { unsigned long long pkg_both_core_gfxe_c0; long long gfx_rc6_ms; unsigned int gfx_mhz; + unsigned int gfx_act_mhz; unsigned int package_id; - unsigned int energy_pkg; /* MSR_PKG_ENERGY_STATUS */ - unsigned int energy_dram; /* MSR_DRAM_ENERGY_STATUS */ - unsigned int energy_cores; /* MSR_PP0_ENERGY_STATUS */ - unsigned int energy_gfx; /* MSR_PP1_ENERGY_STATUS */ - unsigned int rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ - unsigned int rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ + unsigned long long energy_pkg; /* MSR_PKG_ENERGY_STATUS */ + unsigned long long energy_dram; /* MSR_DRAM_ENERGY_STATUS */ + unsigned long long energy_cores; /* MSR_PP0_ENERGY_STATUS */ + unsigned long long energy_gfx; /* MSR_PP1_ENERGY_STATUS */ + unsigned long long rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ + unsigned long long rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ unsigned int pkg_temp_c; unsigned long long counter[MAX_ADDED_COUNTERS]; } *package_even, *package_odd; @@ -259,6 +261,113 @@ struct msr_counter { #define SYSFS_PERCPU (1 << 1) }; +/* + * The accumulated sum of MSR is defined as a monotonic + * increasing MSR, it will be accumulated periodically, + * despite its register's bit width. + */ +enum { + IDX_PKG_ENERGY, + IDX_DRAM_ENERGY, + IDX_PP0_ENERGY, + IDX_PP1_ENERGY, + IDX_PKG_PERF, + IDX_DRAM_PERF, + IDX_COUNT, +}; + +int get_msr_sum(int cpu, off_t offset, unsigned long long *msr); + +struct msr_sum_array { + /* get_msr_sum() = sum + (get_msr() - last) */ + struct { + /*The accumulated MSR value is updated by the timer*/ + unsigned long long sum; + /*The MSR footprint recorded in last timer*/ + unsigned long long last; + } entries[IDX_COUNT]; +}; + +/* The percpu MSR sum array.*/ +struct msr_sum_array *per_cpu_msr_sum; + +int idx_to_offset(int idx) +{ + int offset; + + switch (idx) { + case IDX_PKG_ENERGY: + offset = MSR_PKG_ENERGY_STATUS; + break; + case IDX_DRAM_ENERGY: + offset = MSR_DRAM_ENERGY_STATUS; + break; + case IDX_PP0_ENERGY: + offset = MSR_PP0_ENERGY_STATUS; + break; + case IDX_PP1_ENERGY: + offset = MSR_PP1_ENERGY_STATUS; + break; + case IDX_PKG_PERF: + offset = MSR_PKG_PERF_STATUS; + break; + case IDX_DRAM_PERF: + offset = MSR_DRAM_PERF_STATUS; + break; + default: + offset = -1; + } + return offset; +} + +int offset_to_idx(int offset) +{ + int idx; + + switch (offset) { + case MSR_PKG_ENERGY_STATUS: + idx = IDX_PKG_ENERGY; + break; + case MSR_DRAM_ENERGY_STATUS: + idx = IDX_DRAM_ENERGY; + break; + case MSR_PP0_ENERGY_STATUS: + idx = IDX_PP0_ENERGY; + break; + case MSR_PP1_ENERGY_STATUS: + idx = IDX_PP1_ENERGY; + break; + case MSR_PKG_PERF_STATUS: + idx = IDX_PKG_PERF; + break; + case MSR_DRAM_PERF_STATUS: + idx = IDX_DRAM_PERF; + break; + default: + idx = -1; + } + return idx; +} + +int idx_valid(int idx) +{ + switch (idx) { + case IDX_PKG_ENERGY: + return do_rapl & RAPL_PKG; + case IDX_DRAM_ENERGY: + return do_rapl & RAPL_DRAM; + case IDX_PP0_ENERGY: + return do_rapl & RAPL_CORES_ENERGY_STATUS; + case IDX_PP1_ENERGY: + return do_rapl & RAPL_GFX; + case IDX_PKG_PERF: + return do_rapl & RAPL_PKG_PERF_STATUS; + case IDX_DRAM_PERF: + return do_rapl & RAPL_DRAM_PERF_STATUS; + default: + return 0; + } +} struct sys_counters { unsigned int added_thread_counters; unsigned int added_core_counters; @@ -451,6 +560,7 @@ struct msr_counter bic[] = { { 0x0, "APIC" }, { 0x0, "X2APIC" }, { 0x0, "Die" }, + { 0x0, "GFXAMHz" }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -505,6 +615,7 @@ struct msr_counter bic[] = { #define BIC_APIC (1ULL << 48) #define BIC_X2APIC (1ULL << 49) #define BIC_Die (1ULL << 50) +#define BIC_GFXACTMHz (1ULL << 51) #define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) @@ -724,6 +835,9 @@ void print_header(char *delim) if (DO_BIC(BIC_GFXMHz)) outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_GFXACTMHz)) + outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : "")); if (DO_BIC(BIC_Any_c0)) @@ -858,13 +972,13 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "pc10: %016llX\n", p->pc10); outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi); outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi); - outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg); - outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores); - outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx); - outp += sprintf(outp, "Joules RAM: %0X\n", p->energy_dram); - outp += sprintf(outp, "Throttle PKG: %0X\n", + outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg); + outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores); + outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx); + outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram); + outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status); - outp += sprintf(outp, "Throttle RAM: %0X\n", + outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status); outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c); @@ -1062,14 +1176,7 @@ int format_counters(struct thread_data *t, struct core_data *c, } } - /* - * If measurement interval exceeds minimum RAPL Joule Counter range, - * indicate that results are suspect by printing "**" in fraction place. - */ - if (interval_float < rapl_joule_counter_range) - fmt8 = "%s%.2f"; - else - fmt8 = "%6.0f**"; + fmt8 = "%s%.2f"; if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float); @@ -1098,6 +1205,10 @@ int format_counters(struct thread_data *t, struct core_data *c, if (DO_BIC(BIC_GFXMHz)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz); + /* GFXACTMHz */ + if (DO_BIC(BIC_GFXACTMHz)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz); + /* Totl%C0, Any%C0 GFX%C0 CPUGFX% */ if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc); @@ -1210,11 +1321,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_ } #define DELTA_WRAP32(new, old) \ - if (new > old) { \ - old = new - old; \ - } else { \ - old = 0x100000000 + new - old; \ - } + old = ((((unsigned long long)new << 32) - ((unsigned long long)old << 32)) >> 32); int delta_package(struct pkg_data *new, struct pkg_data *old) @@ -1253,13 +1360,14 @@ delta_package(struct pkg_data *new, struct pkg_data *old) old->gfx_rc6_ms = new->gfx_rc6_ms - old->gfx_rc6_ms; old->gfx_mhz = new->gfx_mhz; + old->gfx_act_mhz = new->gfx_act_mhz; - DELTA_WRAP32(new->energy_pkg, old->energy_pkg); - DELTA_WRAP32(new->energy_cores, old->energy_cores); - DELTA_WRAP32(new->energy_gfx, old->energy_gfx); - DELTA_WRAP32(new->energy_dram, old->energy_dram); - DELTA_WRAP32(new->rapl_pkg_perf_status, old->rapl_pkg_perf_status); - DELTA_WRAP32(new->rapl_dram_perf_status, old->rapl_dram_perf_status); + old->energy_pkg = new->energy_pkg - old->energy_pkg; + old->energy_cores = new->energy_cores - old->energy_cores; + old->energy_gfx = new->energy_gfx - old->energy_gfx; + old->energy_dram = new->energy_dram - old->energy_dram; + old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status; + old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -1469,6 +1577,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->gfx_rc6_ms = 0; p->gfx_mhz = 0; + p->gfx_act_mhz = 0; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) t->counter[i] = 0; @@ -1564,6 +1673,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, average.packages.gfx_rc6_ms = p->gfx_rc6_ms; average.packages.gfx_mhz = p->gfx_mhz; + average.packages.gfx_act_mhz = p->gfx_act_mhz; average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c); @@ -1784,7 +1894,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) int i; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "get_counters: Could not migrate to CPU %d\n", cpu); return -1; } @@ -1966,39 +2076,39 @@ retry: p->sys_lpi = cpuidle_cur_sys_lpi_us; if (do_rapl & RAPL_PKG) { - if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr)) return -13; - p->energy_pkg = msr & 0xFFFFFFFF; + p->energy_pkg = msr; } if (do_rapl & RAPL_CORES_ENERGY_STATUS) { - if (get_msr(cpu, MSR_PP0_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr)) return -14; - p->energy_cores = msr & 0xFFFFFFFF; + p->energy_cores = msr; } if (do_rapl & RAPL_DRAM) { - if (get_msr(cpu, MSR_DRAM_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr)) return -15; - p->energy_dram = msr & 0xFFFFFFFF; + p->energy_dram = msr; } if (do_rapl & RAPL_GFX) { - if (get_msr(cpu, MSR_PP1_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr)) return -16; - p->energy_gfx = msr & 0xFFFFFFFF; + p->energy_gfx = msr; } if (do_rapl & RAPL_PKG_PERF_STATUS) { - if (get_msr(cpu, MSR_PKG_PERF_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr)) return -16; - p->rapl_pkg_perf_status = msr & 0xFFFFFFFF; + p->rapl_pkg_perf_status = msr; } if (do_rapl & RAPL_DRAM_PERF_STATUS) { - if (get_msr(cpu, MSR_DRAM_PERF_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr)) return -16; - p->rapl_dram_perf_status = msr & 0xFFFFFFFF; + p->rapl_dram_perf_status = msr; } if (do_rapl & RAPL_AMD_F17H) { - if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr)) + if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr)) return -13; - p->energy_pkg = msr & 0xFFFFFFFF; + p->energy_pkg = msr; } if (DO_BIC(BIC_PkgTmp)) { if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr)) @@ -2012,6 +2122,9 @@ retry: if (DO_BIC(BIC_GFXMHz)) p->gfx_mhz = gfx_cur_mhz; + if (DO_BIC(BIC_GFXACTMHz)) + p->gfx_act_mhz = gfx_act_mhz; + for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (get_mp(cpu, mp, &p->counter[i])) return -10; @@ -2173,6 +2286,7 @@ int has_turbo_ratio_group_limits(int family, int model) case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_ATOM_GOLDMONT_D: + case INTEL_FAM6_ATOM_TREMONT_D: return 1; } return 0; @@ -2650,7 +2764,12 @@ int get_thread_siblings(struct cpu_topology *thiscpu) sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", cpu); - filep = fopen_or_die(path, "r"); + filep = fopen(path, "r"); + + if (!filep) { + warnx("%s: open failed", path); + return -1; + } do { offset -= BITMASK_SIZE; if (fscanf(filep, "%lx%c", &map, &character) != 2) @@ -2763,18 +2882,25 @@ void re_initialize(void) { free_all_buffers(); setup_all_buffers(); - printf("turbostat: re-initialized with num_cpus %d\n", topo.num_cpus); + fprintf(outf, "turbostat: re-initialized with num_cpus %d\n", topo.num_cpus); } void set_max_cpu_num(void) { FILE *filep; + int base_cpu; unsigned long dummy; + char pathname[64]; + + base_cpu = sched_getcpu(); + if (base_cpu < 0) + err(1, "cannot find calling cpu ID"); + sprintf(pathname, + "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", + base_cpu); + filep = fopen_or_die(pathname, "r"); topo.max_cpu_num = 0; - filep = fopen_or_die( - "/sys/devices/system/cpu/cpu0/topology/thread_siblings", - "r"); while (fscanf(filep, "%lx,", &dummy) == 1) topo.max_cpu_num += BITMASK_SIZE; fclose(filep); @@ -2916,6 +3042,33 @@ int snapshot_gfx_mhz(void) } /* + * snapshot_gfx_cur_mhz() + * + * record snapshot of + * /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz + * + * return 1 if config change requires a restart, else return 0 + */ +int snapshot_gfx_act_mhz(void) +{ + static FILE *fp; + int retval; + + if (fp == NULL) + fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r"); + else { + rewind(fp); + fflush(fp); + } + + retval = fscanf(fp, "%d", &gfx_act_mhz); + if (retval != 1) + err(1, "GFX ACT MHz"); + + return 0; +} + +/* * snapshot_cpu_lpi() * * record snapshot of @@ -2980,6 +3133,9 @@ int snapshot_proc_sysfs_files(void) if (DO_BIC(BIC_GFXMHz)) snapshot_gfx_mhz(); + if (DO_BIC(BIC_GFXACTMHz)) + snapshot_gfx_act_mhz(); + if (DO_BIC(BIC_CPU_LPI)) snapshot_cpu_lpi_us(); @@ -3057,6 +3213,111 @@ void do_sleep(void) } } +int get_msr_sum(int cpu, off_t offset, unsigned long long *msr) +{ + int ret, idx; + unsigned long long msr_cur, msr_last; + + if (!per_cpu_msr_sum) + return 1; + + idx = offset_to_idx(offset); + if (idx < 0) + return idx; + /* get_msr_sum() = sum + (get_msr() - last) */ + ret = get_msr(cpu, offset, &msr_cur); + if (ret) + return ret; + msr_last = per_cpu_msr_sum[cpu].entries[idx].last; + DELTA_WRAP32(msr_cur, msr_last); + *msr = msr_last + per_cpu_msr_sum[cpu].entries[idx].sum; + + return 0; +} + +timer_t timerid; + +/* Timer callback, update the sum of MSRs periodically. */ +static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ + int i, ret; + int cpu = t->cpu_id; + + for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) { + unsigned long long msr_cur, msr_last; + int offset; + + if (!idx_valid(i)) + continue; + offset = idx_to_offset(i); + if (offset < 0) + continue; + ret = get_msr(cpu, offset, &msr_cur); + if (ret) { + fprintf(outf, "Can not update msr(0x%x)\n", offset); + continue; + } + + msr_last = per_cpu_msr_sum[cpu].entries[i].last; + per_cpu_msr_sum[cpu].entries[i].last = msr_cur & 0xffffffff; + + DELTA_WRAP32(msr_cur, msr_last); + per_cpu_msr_sum[cpu].entries[i].sum += msr_last; + } + return 0; +} + +static void +msr_record_handler(union sigval v) +{ + for_all_cpus(update_msr_sum, EVEN_COUNTERS); +} + +void msr_sum_record(void) +{ + struct itimerspec its; + struct sigevent sev; + + per_cpu_msr_sum = calloc(topo.max_cpu_num + 1, sizeof(struct msr_sum_array)); + if (!per_cpu_msr_sum) { + fprintf(outf, "Can not allocate memory for long time MSR.\n"); + return; + } + /* + * Signal handler might be restricted, so use thread notifier instead. + */ + memset(&sev, 0, sizeof(struct sigevent)); + sev.sigev_notify = SIGEV_THREAD; + sev.sigev_notify_function = msr_record_handler; + + sev.sigev_value.sival_ptr = &timerid; + if (timer_create(CLOCK_REALTIME, &sev, &timerid) == -1) { + fprintf(outf, "Can not create timer.\n"); + goto release_msr; + } + + its.it_value.tv_sec = 0; + its.it_value.tv_nsec = 1; + /* + * A wraparound time has been calculated early. + * Some sources state that the peak power for a + * microprocessor is usually 1.5 times the TDP rating, + * use 2 * TDP for safety. + */ + its.it_interval.tv_sec = rapl_joule_counter_range / 2; + its.it_interval.tv_nsec = 0; + + if (timer_settime(timerid, 0, &its, NULL) == -1) { + fprintf(outf, "Can not set timer.\n"); + goto release_timer; + } + return; + + release_timer: + timer_delete(timerid); + release_msr: + free(per_cpu_msr_sum); +} void turbostat_loop() { @@ -3075,7 +3336,7 @@ restart: if (retval < -1) { exit(retval); } else if (retval == -1) { - if (restarted > 1) { + if (restarted > 10) { exit(retval); } re_initialize(); @@ -3279,6 +3540,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ case INTEL_FAM6_ATOM_TREMONT: /* EHL */ + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ pkg_cstate_limits = glm_pkg_cstate_limits; break; default: @@ -3361,6 +3623,17 @@ int is_ehl(unsigned int family, unsigned int model) } return 0; } +int is_jvl(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_TREMONT_D: + return 1; + } + return 0; +} int has_turbo_ratio_limit(unsigned int family, unsigned int model) { @@ -3475,6 +3748,20 @@ int has_config_tdp(unsigned int family, unsigned int model) } static void +remove_underbar(char *s) +{ + char *to = s; + + while (*s) { + if (*s != '_') + *to++ = *s; + s++; + } + + *to = 0; +} + +static void dump_cstate_pstate_config_info(unsigned int family, unsigned int model) { if (!do_nhm_platform_info) @@ -3530,9 +3817,6 @@ dump_sysfs_cstate_config(void) int state; char *sp; - if (!DO_BIC(BIC_sysfs)) - return; - if (access("/sys/devices/system/cpu/cpuidle", R_OK)) { fprintf(outf, "cpuidle not loaded\n"); return; @@ -3559,6 +3843,8 @@ dump_sysfs_cstate_config(void) *sp = '\0'; fclose(input); + remove_underbar(name_buf); + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc", base_cpu, state); input = fopen(path, "r"); @@ -3645,7 +3931,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_epb: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3689,7 +3975,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_hwp: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3777,7 +4063,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_perf_limit: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3881,13 +4167,8 @@ double get_tdp_intel(unsigned int model) double get_tdp_amd(unsigned int family) { - switch (family) { - case 0x17: - case 0x18: - default: - /* This is the max stock TDP of HEDT/Server Fam17h chips */ - return 250.0; - } + /* This is the max stock TDP of HEDT/Server Fam17h+ chips */ + return 280.0; } /* @@ -3959,6 +4240,14 @@ void rapl_probe_intel(unsigned int family, unsigned int model) BIC_PRESENT(BIC_GFXWatt); } break; + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ + do_rapl = RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; + BIC_PRESENT(BIC_PKG__); + if (rapl_joules) + BIC_PRESENT(BIC_Pkg_J); + else + BIC_PRESENT(BIC_PkgWatt); + break; case INTEL_FAM6_SKYLAKE_L: /* SKL */ case INTEL_FAM6_CANNONLAKE_L: /* CNL */ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO; @@ -4069,27 +4358,20 @@ void rapl_probe_amd(unsigned int family, unsigned int model) if (max_extended_level >= 0x80000007) { __cpuid(0x80000007, eax, ebx, ecx, edx); - /* RAPL (Fam 17h) */ + /* RAPL (Fam 17h+) */ has_rapl = edx & (1 << 14); } - if (!has_rapl) + if (!has_rapl || family < 0x17) return; - switch (family) { - case 0x17: /* Zen, Zen+ */ - case 0x18: /* Hygon Dhyana */ - do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; - if (rapl_joules) { - BIC_PRESENT(BIC_Pkg_J); - BIC_PRESENT(BIC_Cor_J); - } else { - BIC_PRESENT(BIC_PkgWatt); - BIC_PRESENT(BIC_CorWatt); - } - break; - default: - return; + do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); } if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr)) @@ -4162,7 +4444,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu); return -1; } @@ -4234,7 +4516,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) cpu = t->cpu_id; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_rapl: Could not migrate to CPU %d\n", cpu); return -1; } @@ -4361,6 +4643,7 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ case INTEL_FAM6_ATOM_TREMONT: /* EHL */ + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ return 1; } return 0; @@ -4507,12 +4790,33 @@ double discover_bclk(unsigned int family, unsigned int model) * below this value, including the Digital Thermal Sensor (DTS), * Package Thermal Management Sensor (PTM), and thermal event thresholds. */ -int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int read_tcc_activation_temp() { unsigned long long msr; - unsigned int target_c_local; - int cpu; + unsigned int tcc, target_c, offset_c; + /* Temperature Target MSR is Nehalem and newer only */ + if (!do_nhm_platform_info) + return 0; + + if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) + return 0; + + target_c = (msr >> 16) & 0xFF; + + offset_c = (msr >> 24) & 0xF; + + tcc = target_c - offset_c; + + if (!quiet) + fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n", + base_cpu, msr, tcc, target_c, offset_c); + + return tcc; +} + +int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ /* tcc_activation_temp is used only for dts or ptm */ if (!(do_dts || do_ptm)) return 0; @@ -4521,43 +4825,18 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) return 0; - cpu = t->cpu_id; - if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); - return -1; - } - if (tcc_activation_temp_override != 0) { tcc_activation_temp = tcc_activation_temp_override; - fprintf(outf, "cpu%d: Using cmdline TCC Target (%d C)\n", - cpu, tcc_activation_temp); + fprintf(outf, "Using cmdline TCC Target (%d C)\n", tcc_activation_temp); return 0; } - /* Temperature Target MSR is Nehalem and newer only */ - if (!do_nhm_platform_info) - goto guess; - - if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) - goto guess; - - target_c_local = (msr >> 16) & 0xFF; - - if (!quiet) - fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n", - cpu, msr, target_c_local); - - if (!target_c_local) - goto guess; - - tcc_activation_temp = target_c_local; - - return 0; + tcc_activation_temp = read_tcc_activation_temp(); + if (tcc_activation_temp) + return 0; -guess: tcc_activation_temp = TJMAX_DEFAULT; - fprintf(outf, "cpu%d: Guessing tjMax %d C, Please use -T to specify\n", - cpu, tcc_activation_temp); + fprintf(outf, "Guessing tjMax %d C, Please use -T to specify\n", tcc_activation_temp); return 0; } @@ -4685,19 +4964,46 @@ unsigned int intel_model_duplicates(unsigned int model) case INTEL_FAM6_ICELAKE_NNPI: case INTEL_FAM6_TIGERLAKE_L: case INTEL_FAM6_TIGERLAKE: + case INTEL_FAM6_ROCKETLAKE: + case INTEL_FAM6_LAKEFIELD: + case INTEL_FAM6_ALDERLAKE: return INTEL_FAM6_CANNONLAKE_L; - case INTEL_FAM6_ATOM_TREMONT_D: - return INTEL_FAM6_ATOM_GOLDMONT_D; - case INTEL_FAM6_ATOM_TREMONT_L: return INTEL_FAM6_ATOM_TREMONT; case INTEL_FAM6_ICELAKE_X: + case INTEL_FAM6_SAPPHIRERAPIDS_X: return INTEL_FAM6_SKYLAKE_X; } return model; } + +void print_dev_latency(void) +{ + char *path = "/dev/cpu_dma_latency"; + int fd; + int value; + int retval; + + fd = open(path, O_RDONLY); + if (fd < 0) { + warn("fopen %s\n", path); + return; + } + + retval = read(fd, (void *)&value, sizeof(int)); + if (retval != sizeof(int)) { + warn("read %s\n", path); + close(fd); + return; + } + fprintf(outf, "/dev/cpu_dma_latency: %d usec (%s)\n", + value, value == 2000000000 ? "default" : "constrained"); + + close(fd); +} + void process_cpuid() { unsigned int eax, ebx, ecx, edx; @@ -4916,6 +5222,14 @@ void process_cpuid() BIC_PRESENT(BIC_Mod_c6); use_c1_residency_msr = 1; } + if (is_jvl(family, model)) { + BIC_NOT_PRESENT(BIC_CPU_c3); + BIC_NOT_PRESENT(BIC_CPU_c7); + BIC_NOT_PRESENT(BIC_Pkgpc2); + BIC_NOT_PRESENT(BIC_Pkgpc3); + BIC_NOT_PRESENT(BIC_Pkgpc6); + BIC_NOT_PRESENT(BIC_Pkgpc7); + } if (is_dnv(family, model)) { BIC_PRESENT(BIC_CPU_c1); BIC_NOT_PRESENT(BIC_CPU_c3); @@ -4935,9 +5249,12 @@ void process_cpuid() BIC_NOT_PRESENT(BIC_Pkgpc7); } if (has_c8910_msrs(family, model)) { - BIC_PRESENT(BIC_Pkgpc8); - BIC_PRESENT(BIC_Pkgpc9); - BIC_PRESENT(BIC_Pkgpc10); + if (pkg_cstate_limit >= PCL__8) + BIC_PRESENT(BIC_Pkgpc8); + if (pkg_cstate_limit >= PCL__9) + BIC_PRESENT(BIC_Pkgpc9); + if (pkg_cstate_limit >= PCL_10) + BIC_PRESENT(BIC_Pkgpc10); } do_irtl_hsw = has_c8910_msrs(family, model); if (has_skl_msrs(family, model)) { @@ -4967,6 +5284,8 @@ void process_cpuid() dump_cstate_pstate_config_info(family, model); if (!quiet) + print_dev_latency(); + if (!quiet) dump_sysfs_cstate_config(); if (!quiet) dump_sysfs_pstate_config(); @@ -4980,6 +5299,9 @@ void process_cpuid() if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) BIC_PRESENT(BIC_GFXMHz); + if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK)) + BIC_PRESENT(BIC_GFXACTMHz); + if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK)) BIC_PRESENT(BIC_CPU_LPI); else @@ -5390,7 +5712,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 20.03.20" + fprintf(outf, "turbostat version 20.09.30" " - Len Brown <lenb@kernel.org>\n"); } @@ -5597,6 +5919,8 @@ void probe_sysfs(void) *sp = '%'; *(sp + 1) = '\0'; + remove_underbar(name_buf); + fclose(input); sprintf(path, "cpuidle/state%d/time", state); @@ -5624,6 +5948,8 @@ void probe_sysfs(void) *sp = '\0'; fclose(input); + remove_underbar(name_buf); + sprintf(path, "cpuidle/state%d/usage", state); if (is_deferred_skip(name_buf)) @@ -5868,6 +6194,7 @@ int main(int argc, char **argv) return 0; } + msr_sum_record(); /* * if any params left, it must be a command to fork */ diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c index 3fe1eed900d4..ff6c6661f075 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c @@ -622,6 +622,57 @@ void cmdline(int argc, char **argv) } } +/* + * Open a file, and exit on failure + */ +FILE *fopen_or_die(const char *path, const char *mode) +{ + FILE *filep = fopen(path, "r"); + + if (!filep) + err(1, "%s: open failed", path); + return filep; +} + +void err_on_hypervisor(void) +{ + FILE *cpuinfo; + char *flags, *hypervisor; + char *buffer; + + /* On VMs /proc/cpuinfo contains a "flags" entry for hypervisor */ + cpuinfo = fopen_or_die("/proc/cpuinfo", "ro"); + + buffer = malloc(4096); + if (!buffer) { + fclose(cpuinfo); + err(-ENOMEM, "buffer malloc fail"); + } + + if (!fread(buffer, 1024, 1, cpuinfo)) { + fclose(cpuinfo); + free(buffer); + err(1, "Reading /proc/cpuinfo failed"); + } + + flags = strstr(buffer, "flags"); + rewind(cpuinfo); + fseek(cpuinfo, flags - buffer, SEEK_SET); + if (!fgets(buffer, 4096, cpuinfo)) { + fclose(cpuinfo); + free(buffer); + err(1, "Reading /proc/cpuinfo failed"); + } + fclose(cpuinfo); + + hypervisor = strstr(buffer, "hypervisor"); + + free(buffer); + + if (hypervisor) + err(-1, + "not supported on this virtual machine"); +} int get_msr(int cpu, int offset, unsigned long long *msr) { @@ -635,8 +686,10 @@ int get_msr(int cpu, int offset, unsigned long long *msr) err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname); retval = pread(fd, msr, sizeof(*msr), offset); - if (retval != sizeof(*msr)) + if (retval != sizeof(*msr)) { + err_on_hypervisor(); err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset); + } if (debug > 1) fprintf(stderr, "get_msr(cpu%d, 0x%X, 0x%llX)\n", cpu, offset, *msr); @@ -1086,18 +1139,6 @@ int update_cpu_msrs(int cpu) return 0; } -/* - * Open a file, and exit on failure - */ -FILE *fopen_or_die(const char *path, const char *mode) -{ - FILE *filep = fopen(path, "r"); - - if (!filep) - err(1, "%s: open failed", path); - return filep; -} - unsigned int get_pkg_num(int cpu) { FILE *fp; diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index cb16d2aac51c..54188ee16c48 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -2040,7 +2040,7 @@ sub reboot_to { if ($reboot_type eq "grub") { run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch)'"; - } elsif ($reboot_type eq "grub2") { + } elsif (($reboot_type eq "grub2") or ($reboot_type eq "grub2bls")) { run_ssh "$grub_reboot $grub_number"; } elsif ($reboot_type eq "syslinux") { run_ssh "$syslinux --once \\\"$syslinux_label\\\" $syslinux_path"; diff --git a/tools/testing/kunit/.gitattributes b/tools/testing/kunit/.gitattributes deleted file mode 100644 index 5b7da1fc3b8f..000000000000 --- a/tools/testing/kunit/.gitattributes +++ /dev/null @@ -1 +0,0 @@ -test_data/* binary diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index ebf5f5763dee..d4f7846d0745 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -11,7 +11,6 @@ import argparse import sys import os import time -import shutil from collections import namedtuple from enum import Enum, auto @@ -44,11 +43,6 @@ class KunitStatus(Enum): BUILD_FAILURE = auto() TEST_FAILURE = auto() -def create_default_kunitconfig(): - if not os.path.exists(kunit_kernel.kunitconfig_path): - shutil.copyfile('arch/um/configs/kunit_defconfig', - kunit_kernel.kunitconfig_path) - def get_kernel_root_path(): parts = sys.argv[0] if not __file__ else __file__ parts = os.path.realpath(parts).split('tools/testing/kunit') @@ -61,7 +55,6 @@ def config_tests(linux: kunit_kernel.LinuxSourceTree, kunit_parser.print_with_timestamp('Configuring KUnit Kernel ...') config_start = time.time() - create_default_kunitconfig() success = linux.build_reconfig(request.build_dir, request.make_options) config_end = time.time() if not success: @@ -262,12 +255,12 @@ def main(argv, linux=None): if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() - if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + request = KunitRequest(cli_args.raw_output, cli_args.timeout, cli_args.jobs, @@ -283,12 +276,12 @@ def main(argv, linux=None): not os.path.exists(cli_args.build_dir)): os.mkdir(cli_args.build_dir) - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() - if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + request = KunitConfigRequest(cli_args.build_dir, cli_args.make_options) result = config_tests(linux, request) @@ -301,6 +294,9 @@ def main(argv, linux=None): if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + request = KunitBuildRequest(cli_args.jobs, cli_args.build_dir, cli_args.alltests, @@ -315,6 +311,9 @@ def main(argv, linux=None): if not linux: linux = kunit_kernel.LinuxSourceTree() + linux.create_kunitconfig(cli_args.build_dir) + linux.read_kunitconfig(cli_args.build_dir) + exec_request = KunitExecRequest(cli_args.timeout, cli_args.build_dir, cli_args.alltests) @@ -337,7 +336,7 @@ def main(argv, linux=None): kunit_output = f.read().splitlines() request = KunitParseRequest(cli_args.raw_output, kunit_output, - cli_args.build_dir, + None, cli_args.json) result = parse_tests(request) if result.status != KunitStatus.SUCCESS: diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index b557b1e93f98..2e3cc0fac726 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -6,10 +6,10 @@ # Author: Felix Guo <felixguoxiuping@gmail.com> # Author: Brendan Higgins <brendanhiggins@google.com> - import logging import subprocess import os +import shutil import signal from contextlib import ExitStack @@ -18,8 +18,10 @@ import kunit_config import kunit_parser KCONFIG_PATH = '.config' -kunitconfig_path = '.kunitconfig' +KUNITCONFIG_PATH = '.kunitconfig' +DEFAULT_KUNITCONFIG_PATH = 'arch/um/configs/kunit_defconfig' BROKEN_ALLCONFIG_PATH = 'tools/testing/kunit/configs/broken_on_uml.config' +OUTFILE_PATH = 'test.log' class ConfigError(Exception): """Represents an error trying to configure the Linux kernel.""" @@ -82,36 +84,51 @@ class LinuxSourceTreeOperations(object): if build_dir: command += ['O=' + build_dir] try: - subprocess.check_output(command, stderr=subprocess.STDOUT) + proc = subprocess.Popen(command, + stderr=subprocess.PIPE, + stdout=subprocess.DEVNULL) except OSError as e: - raise BuildError('Could not call execute make: ' + str(e)) - except subprocess.CalledProcessError as e: - raise BuildError(e.output.decode()) - - def linux_bin(self, params, timeout, build_dir, outfile): + raise BuildError('Could not call make command: ' + str(e)) + _, stderr = proc.communicate() + if proc.returncode != 0: + raise BuildError(stderr.decode()) + if stderr: # likely only due to build warnings + print(stderr.decode()) + + def linux_bin(self, params, timeout, build_dir): """Runs the Linux UML binary. Must be named 'linux'.""" linux_bin = './linux' if build_dir: linux_bin = os.path.join(build_dir, 'linux') + outfile = get_outfile_path(build_dir) with open(outfile, 'w') as output: process = subprocess.Popen([linux_bin] + params, stdout=output, stderr=subprocess.STDOUT) process.wait(timeout) - def get_kconfig_path(build_dir): kconfig_path = KCONFIG_PATH if build_dir: kconfig_path = os.path.join(build_dir, KCONFIG_PATH) return kconfig_path +def get_kunitconfig_path(build_dir): + kunitconfig_path = KUNITCONFIG_PATH + if build_dir: + kunitconfig_path = os.path.join(build_dir, KUNITCONFIG_PATH) + return kunitconfig_path + +def get_outfile_path(build_dir): + outfile_path = OUTFILE_PATH + if build_dir: + outfile_path = os.path.join(build_dir, OUTFILE_PATH) + return outfile_path + class LinuxSourceTree(object): """Represents a Linux kernel source tree with KUnit tests.""" def __init__(self): - self._kconfig = kunit_config.Kconfig() - self._kconfig.read_from_file(kunitconfig_path) self._ops = LinuxSourceTreeOperations() signal.signal(signal.SIGINT, self.signal_handler) @@ -123,6 +140,16 @@ class LinuxSourceTree(object): return False return True + def create_kunitconfig(self, build_dir, defconfig=DEFAULT_KUNITCONFIG_PATH): + kunitconfig_path = get_kunitconfig_path(build_dir) + if not os.path.exists(kunitconfig_path): + shutil.copyfile(defconfig, kunitconfig_path) + + def read_kunitconfig(self, build_dir): + kunitconfig_path = get_kunitconfig_path(build_dir) + self._kconfig = kunit_config.Kconfig() + self._kconfig.read_from_file(kunitconfig_path) + def validate_config(self, build_dir): kconfig_path = get_kconfig_path(build_dir) validated_kconfig = kunit_config.Kconfig() @@ -178,8 +205,8 @@ class LinuxSourceTree(object): def run_kernel(self, args=[], build_dir='', timeout=None): args.extend(['mem=1G']) - outfile = 'test.log' - self._ops.linux_bin(args, timeout, build_dir, outfile) + self._ops.linux_bin(args, timeout, build_dir) + outfile = get_outfile_path(build_dir) subprocess.call(['stty', 'sane']) with open(outfile, 'r') as file: for line in file: diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index 84a1af2581f5..bbfe1b4e4c1c 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -12,7 +12,7 @@ from collections import namedtuple from datetime import datetime from enum import Enum, auto from functools import reduce -from typing import List +from typing import List, Optional, Tuple TestResult = namedtuple('TestResult', ['status','suites','log']) @@ -54,6 +54,7 @@ kunit_end_re = re.compile('(List of all partitions:|' def isolate_kunit_output(kernel_output): started = False for line in kernel_output: + line = line.rstrip() # line always has a trailing \n if kunit_start_re.search(line): prefix_len = len(line.split('TAP version')[0]) started = True @@ -65,7 +66,7 @@ def isolate_kunit_output(kernel_output): def raw_output(kernel_output): for line in kernel_output: - print(line) + print(line.rstrip()) DIVIDER = '=' * 60 @@ -151,7 +152,7 @@ def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool: else: return False -def parse_test_case(lines: List[str]) -> TestCase: +def parse_test_case(lines: List[str]) -> Optional[TestCase]: test_case = TestCase() save_non_diagnositic(lines, test_case) while parse_diagnostic(lines, test_case): @@ -163,7 +164,7 @@ def parse_test_case(lines: List[str]) -> TestCase: SUBTEST_HEADER = re.compile(r'^[\s]+# Subtest: (.*)$') -def parse_subtest_header(lines: List[str]) -> str: +def parse_subtest_header(lines: List[str]) -> Optional[str]: consume_non_diagnositic(lines) if not lines: return None @@ -176,7 +177,7 @@ def parse_subtest_header(lines: List[str]) -> str: SUBTEST_PLAN = re.compile(r'[\s]+[0-9]+\.\.([0-9]+)') -def parse_subtest_plan(lines: List[str]) -> int: +def parse_subtest_plan(lines: List[str]) -> Optional[int]: consume_non_diagnositic(lines) match = SUBTEST_PLAN.match(lines[0]) if match: @@ -230,7 +231,7 @@ def bubble_up_test_case_errors(test_suite: TestSuite) -> TestStatus: max_test_case_status = bubble_up_errors(lambda x: x.status, test_suite.cases) return max_status(max_test_case_status, test_suite.status) -def parse_test_suite(lines: List[str], expected_suite_index: int) -> TestSuite: +def parse_test_suite(lines: List[str], expected_suite_index: int) -> Optional[TestSuite]: if not lines: return None consume_non_diagnositic(lines) @@ -271,7 +272,7 @@ def parse_tap_header(lines: List[str]) -> bool: TEST_PLAN = re.compile(r'[0-9]+\.\.([0-9]+)') -def parse_test_plan(lines: List[str]) -> int: +def parse_test_plan(lines: List[str]) -> Optional[int]: consume_non_diagnositic(lines) match = TEST_PLAN.match(lines[0]) if match: @@ -310,7 +311,7 @@ def parse_test_result(lines: List[str]) -> TestResult: else: return TestResult(TestStatus.NO_TESTS, [], lines) -def print_and_count_results(test_result: TestResult) -> None: +def print_and_count_results(test_result: TestResult) -> Tuple[int, int, int]: total_tests = 0 failed_tests = 0 crashed_tests = 0 diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 0b60855fb819..497ab51bc170 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -102,7 +102,7 @@ class KUnitParserTest(unittest.TestCase): 'test_data/test_output_isolated_correctly.log') file = open(log_path) result = kunit_parser.isolate_kunit_output(file.readlines()) - self.assertContains('TAP version 14\n', result) + self.assertContains('TAP version 14', result) self.assertContains(' # Subtest: example', result) self.assertContains(' 1..2', result) self.assertContains(' ok 1 - example_simple_test', result) @@ -115,7 +115,7 @@ class KUnitParserTest(unittest.TestCase): 'test_data/test_pound_sign.log') with open(log_path) as file: result = kunit_parser.isolate_kunit_output(file.readlines()) - self.assertContains('TAP version 14\n', result) + self.assertContains('TAP version 14', result) self.assertContains(' # Subtest: kunit-resource-test', result) self.assertContains(' 1..5', result) self.assertContains(' ok 1 - kunit_resource_test_init_resources', result) diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h index 6ae907f375d2..f9a12005fcea 100644 --- a/tools/testing/scatterlist/linux/mm.h +++ b/tools/testing/scatterlist/linux/mm.h @@ -33,6 +33,7 @@ typedef unsigned long dma_addr_t; #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) +#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c index b2c7e9f7b8d3..f561aed7c657 100644 --- a/tools/testing/scatterlist/main.c +++ b/tools/testing/scatterlist/main.c @@ -52,9 +52,9 @@ int main(void) { const unsigned int sgmax = SCATTERLIST_MAX_SEGMENT; struct test *test, tests[] = { - { -EINVAL, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 }, { -EINVAL, 1, pfn(0), PAGE_SIZE, 0, 1 }, - { -EINVAL, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 }, + { 0, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 }, + { 0, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 }, { 0, 1, pfn(0), PAGE_SIZE, sgmax, 1 }, { 0, 1, pfn(0), 1, sgmax, 1 }, { 0, 2, pfn(0, 1), 2 * PAGE_SIZE, sgmax, 1 }, diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c index 52414058a627..5861446d0777 100644 --- a/tools/testing/selftests/bpf/prog_tests/align.c +++ b/tools/testing/selftests/bpf/prog_tests/align.c @@ -456,10 +456,10 @@ static struct bpf_align_test tests[] = { */ {7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>=0 */ - {9, "R5=inv(id=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"}, + {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* packet pointer + nonnegative (4n+2) */ - {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"}, - {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"}, + {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. * We checked the bounds, but it might have been able * to overflow if the packet pointer started in the @@ -467,7 +467,7 @@ static struct bpf_align_test tests[] = { * So we did not get a 'range' on R6, and the access * attempt will fail. */ - {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"}, + {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, } }, { diff --git a/tools/testing/selftests/bpf/prog_tests/map_init.c b/tools/testing/selftests/bpf/prog_tests/map_init.c new file mode 100644 index 000000000000..14a31109dd0e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/map_init.c @@ -0,0 +1,214 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */ + +#include <test_progs.h> +#include "test_map_init.skel.h" + +#define TEST_VALUE 0x1234 +#define FILL_VALUE 0xdeadbeef + +static int nr_cpus; +static int duration; + +typedef unsigned long long map_key_t; +typedef unsigned long long map_value_t; +typedef struct { + map_value_t v; /* padding */ +} __bpf_percpu_val_align pcpu_map_value_t; + + +static int map_populate(int map_fd, int num) +{ + pcpu_map_value_t value[nr_cpus]; + int i, err; + map_key_t key; + + for (i = 0; i < nr_cpus; i++) + bpf_percpu(value, i) = FILL_VALUE; + + for (key = 1; key <= num; key++) { + err = bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + return -1; + } + + return 0; +} + +static struct test_map_init *setup(enum bpf_map_type map_type, int map_sz, + int *map_fd, int populate) +{ + struct test_map_init *skel; + int err; + + skel = test_map_init__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return NULL; + + err = bpf_map__set_type(skel->maps.hashmap1, map_type); + if (!ASSERT_OK(err, "bpf_map__set_type")) + goto error; + + err = bpf_map__set_max_entries(skel->maps.hashmap1, map_sz); + if (!ASSERT_OK(err, "bpf_map__set_max_entries")) + goto error; + + err = test_map_init__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto error; + + *map_fd = bpf_map__fd(skel->maps.hashmap1); + if (CHECK(*map_fd < 0, "bpf_map__fd", "failed\n")) + goto error; + + err = map_populate(*map_fd, populate); + if (!ASSERT_OK(err, "map_populate")) + goto error_map; + + return skel; + +error_map: + close(*map_fd); +error: + test_map_init__destroy(skel); + return NULL; +} + +/* executes bpf program that updates map with key, value */ +static int prog_run_insert_elem(struct test_map_init *skel, map_key_t key, + map_value_t value) +{ + struct test_map_init__bss *bss; + + bss = skel->bss; + + bss->inKey = key; + bss->inValue = value; + bss->inPid = getpid(); + + if (!ASSERT_OK(test_map_init__attach(skel), "skel_attach")) + return -1; + + /* Let tracepoint trigger */ + syscall(__NR_getpgid); + + test_map_init__detach(skel); + + return 0; +} + +static int check_values_one_cpu(pcpu_map_value_t *value, map_value_t expected) +{ + int i, nzCnt = 0; + map_value_t val; + + for (i = 0; i < nr_cpus; i++) { + val = bpf_percpu(value, i); + if (val) { + if (CHECK(val != expected, "map value", + "unexpected for cpu %d: 0x%llx\n", i, val)) + return -1; + nzCnt++; + } + } + + if (CHECK(nzCnt != 1, "map value", "set for %d CPUs instead of 1!\n", + nzCnt)) + return -1; + + return 0; +} + +/* Add key=1 elem with values set for all CPUs + * Delete elem key=1 + * Run bpf prog that inserts new key=1 elem with value=0x1234 + * (bpf prog can only set value for current CPU) + * Lookup Key=1 and check value is as expected for all CPUs: + * value set by bpf prog for one CPU, 0 for all others + */ +static void test_pcpu_map_init(void) +{ + pcpu_map_value_t value[nr_cpus]; + struct test_map_init *skel; + int map_fd, err; + map_key_t key; + + /* max 1 elem in map so insertion is forced to reuse freed entry */ + skel = setup(BPF_MAP_TYPE_PERCPU_HASH, 1, &map_fd, 1); + if (!ASSERT_OK_PTR(skel, "prog_setup")) + return; + + /* delete element so the entry can be re-used*/ + key = 1; + err = bpf_map_delete_elem(map_fd, &key); + if (!ASSERT_OK(err, "bpf_map_delete_elem")) + goto cleanup; + + /* run bpf prog that inserts new elem, re-using the slot just freed */ + err = prog_run_insert_elem(skel, key, TEST_VALUE); + if (!ASSERT_OK(err, "prog_run_insert_elem")) + goto cleanup; + + /* check that key=1 was re-created by bpf prog */ + err = bpf_map_lookup_elem(map_fd, &key, value); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + goto cleanup; + + /* and has expected values */ + check_values_one_cpu(value, TEST_VALUE); + +cleanup: + test_map_init__destroy(skel); +} + +/* Add key=1 and key=2 elems with values set for all CPUs + * Run bpf prog that inserts new key=3 elem + * (only for current cpu; other cpus should have initial value = 0) + * Lookup Key=1 and check value is as expected for all CPUs + */ +static void test_pcpu_lru_map_init(void) +{ + pcpu_map_value_t value[nr_cpus]; + struct test_map_init *skel; + int map_fd, err; + map_key_t key; + + /* Set up LRU map with 2 elements, values filled for all CPUs. + * With these 2 elements, the LRU map is full + */ + skel = setup(BPF_MAP_TYPE_LRU_PERCPU_HASH, 2, &map_fd, 2); + if (!ASSERT_OK_PTR(skel, "prog_setup")) + return; + + /* run bpf prog that inserts new key=3 element, re-using LRU slot */ + key = 3; + err = prog_run_insert_elem(skel, key, TEST_VALUE); + if (!ASSERT_OK(err, "prog_run_insert_elem")) + goto cleanup; + + /* check that key=3 replaced one of earlier elements */ + err = bpf_map_lookup_elem(map_fd, &key, value); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + goto cleanup; + + /* and has expected values */ + check_values_one_cpu(value, TEST_VALUE); + +cleanup: + test_map_init__destroy(skel); +} + +void test_map_init(void) +{ + nr_cpus = bpf_num_possible_cpus(); + if (nr_cpus <= 1) { + printf("%s:SKIP: >1 cpu needed for this test\n", __func__); + test__skip(); + return; + } + + if (test__start_subtest("pcpu_map_init")) + test_pcpu_map_init(); + if (test__start_subtest("pcpu_lru_map_init")) + test_pcpu_lru_map_init(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c b/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c new file mode 100644 index 000000000000..e419298132b5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/probe_read_user_str.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "test_probe_read_user_str.skel.h" + +static const char str1[] = "mestring"; +static const char str2[] = "mestringalittlebigger"; +static const char str3[] = "mestringblubblubblubblubblub"; + +static int test_one_str(struct test_probe_read_user_str *skel, const char *str, + size_t len) +{ + int err, duration = 0; + char buf[256]; + + /* Ensure bytes after string are ones */ + memset(buf, 1, sizeof(buf)); + memcpy(buf, str, len); + + /* Give prog our userspace pointer */ + skel->bss->user_ptr = buf; + + /* Trigger tracepoint */ + usleep(1); + + /* Did helper fail? */ + if (CHECK(skel->bss->ret < 0, "prog_ret", "prog returned: %ld\n", + skel->bss->ret)) + return 1; + + /* Check that string was copied correctly */ + err = memcmp(skel->bss->buf, str, len); + if (CHECK(err, "memcmp", "prog copied wrong string")) + return 1; + + /* Now check that no extra trailing bytes were copied */ + memset(buf, 0, sizeof(buf)); + err = memcmp(skel->bss->buf + len, buf, sizeof(buf) - len); + if (CHECK(err, "memcmp", "trailing bytes were not stripped")) + return 1; + + return 0; +} + +void test_probe_read_user_str(void) +{ + struct test_probe_read_user_str *skel; + int err, duration = 0; + + skel = test_probe_read_user_str__open_and_load(); + if (CHECK(!skel, "test_probe_read_user_str__open_and_load", + "skeleton open and load failed\n")) + return; + + /* Give pid to bpf prog so it doesn't read from anyone else */ + skel->bss->pid = getpid(); + + err = test_probe_read_user_str__attach(skel); + if (CHECK(err, "test_probe_read_user_str__attach", + "skeleton attach failed: %d\n", err)) + goto out; + + if (test_one_str(skel, str1, sizeof(str1))) + goto out; + if (test_one_str(skel, str2, sizeof(str2))) + goto out; + if (test_one_str(skel, str3, sizeof(str3))) + goto out; + +out: + test_probe_read_user_str__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index c1650548433c..fddbc5db5d6a 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -217,9 +217,15 @@ void test_ringbuf(void) if (CHECK(err, "join_bg", "err %d\n", err)) goto cleanup; - if (CHECK(bg_ret != 1, "bg_ret", "epoll_wait result: %ld", bg_ret)) + if (CHECK(bg_ret <= 0, "bg_ret", "epoll_wait result: %ld", bg_ret)) goto cleanup; + /* due to timing variations, there could still be non-notified + * samples, so consume them here to collect all the samples + */ + err = ring_buffer__consume(ringbuf); + CHECK(err < 0, "rb_consume", "failed: %d\b", err); + /* 3 rounds, 2 samples each */ cnt = atomic_xchg(&sample_cnt, 0); CHECK(cnt != 6, "cnt", "exp %d samples, got %d\n", 6, cnt); diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c index 78e450609803..d37161e59bb2 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c @@ -81,7 +81,7 @@ void test_ringbuf_multi(void) /* poll for samples, should get 2 ringbufs back */ err = ring_buffer__poll(ringbuf, -1); - if (CHECK(err != 4, "poll_res", "expected 4 records, got %d\n", err)) + if (CHECK(err != 2, "poll_res", "expected 2 records, got %d\n", err)) goto cleanup; /* expect extra polling to return nothing */ diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index 29188d6f5c8d..51fac975b316 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -138,7 +138,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, */ buf = 0x40; - if (setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1) < 0) { + err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1); + if (err < 0) { log_err("Failed to call setsockopt(IP_TOS)"); goto detach; } diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs.c b/tools/testing/selftests/bpf/prog_tests/subprogs.c index a00abf58c037..3f3d2ac4dd57 100644 --- a/tools/testing/selftests/bpf/prog_tests/subprogs.c +++ b/tools/testing/selftests/bpf/prog_tests/subprogs.c @@ -3,12 +3,14 @@ #include <test_progs.h> #include <time.h> #include "test_subprogs.skel.h" +#include "test_subprogs_unused.skel.h" static int duration; void test_subprogs(void) { struct test_subprogs *skel; + struct test_subprogs_unused *skel2; int err; skel = test_subprogs__open_and_load(); @@ -26,6 +28,10 @@ void test_subprogs(void) CHECK(skel->bss->res3 != 19, "res3", "got %d, exp %d\n", skel->bss->res3, 19); CHECK(skel->bss->res4 != 36, "res4", "got %d, exp %d\n", skel->bss->res4, 36); + skel2 = test_subprogs_unused__open_and_load(); + ASSERT_OK_PTR(skel2, "unused_progs_skel"); + test_subprogs_unused__destroy(skel2); + cleanup: test_subprogs__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c index 193002b14d7f..32e4348b714b 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -60,6 +60,7 @@ void test_test_global_funcs(void) { "test_global_func5.o" , "expected pointer to ctx, but got PTR" }, { "test_global_func6.o" , "modified ctx ptr R2" }, { "test_global_func7.o" , "foo() doesn't return scalar" }, + { "test_global_func8.o" }, }; libbpf_print_fn_t old_print_fn = NULL; int err, i, duration = 0; diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 00578311a423..30982a7e4d0f 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -243,7 +243,10 @@ static ino_t get_inode_from_kernfs(struct kernfs_node* node) } } -int pids_cgrp_id = 1; +extern bool CONFIG_CGROUP_PIDS __kconfig __weak; +enum cgroup_subsys_id___local { + pids_cgrp_id___local = 123, /* value doesn't matter */ +}; static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, struct task_struct* task, @@ -253,7 +256,9 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, BPF_CORE_READ(task, nsproxy, cgroup_ns, root_cset, dfl_cgrp, kn); struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn); - if (ENABLE_CGROUP_V1_RESOLVER) { + if (ENABLE_CGROUP_V1_RESOLVER && CONFIG_CGROUP_PIDS) { + int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local, + pids_cgrp_id___local); #ifdef UNROLL #pragma unroll #endif @@ -262,7 +267,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, BPF_CORE_READ(task, cgroups, subsys[i]); if (subsys != NULL) { int subsys_id = BPF_CORE_READ(subsys, ss, id); - if (subsys_id == pids_cgrp_id) { + if (subsys_id == cgrp_id) { proc_kernfs = BPF_CORE_READ(subsys, cgroup, kn); root_kernfs = BPF_CORE_READ(subsys, ss, root, kf_root, kn); break; diff --git a/tools/testing/selftests/bpf/progs/test_global_func8.c b/tools/testing/selftests/bpf/progs/test_global_func8.c new file mode 100644 index 000000000000..d55a6544b1ab --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func8.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__noinline int foo(struct __sk_buff *skb) +{ + return bpf_get_prandom_u32(); +} + +SEC("cgroup_skb/ingress") +int test_cls(struct __sk_buff *skb) +{ + if (!foo(skb)) + return 0; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/test_map_init.c b/tools/testing/selftests/bpf/progs/test_map_init.c new file mode 100644 index 000000000000..c89d28ead673 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_map_init.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +__u64 inKey = 0; +__u64 inValue = 0; +__u32 inPid = 0; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 2); + __type(key, __u64); + __type(value, __u64); +} hashmap1 SEC(".maps"); + + +SEC("tp/syscalls/sys_enter_getpgid") +int sysenter_getpgid(const void *ctx) +{ + /* Just do it for once, when called from our own test prog. This + * ensures the map value is only updated for a single CPU. + */ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + + if (cur_pid == inPid) + bpf_map_update_elem(&hashmap1, &inKey, &inValue, BPF_NOEXIST); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c new file mode 100644 index 000000000000..3ae398b75dcd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_probe_read_user_str.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#include <sys/types.h> + +pid_t pid = 0; +long ret = 0; +void *user_ptr = 0; +char buf[256] = {}; + +SEC("tracepoint/syscalls/sys_enter_nanosleep") +int on_write(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + ret = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_unused.c b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c new file mode 100644 index 000000000000..bc49e050d342 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subprogs_unused.c @@ -0,0 +1,21 @@ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +const char LICENSE[] SEC("license") = "GPL"; + +__attribute__((unused)) __noinline int unused1(int x) +{ + return x + 1; +} + +static __attribute__((unused)) __noinline int unused2(int x) +{ + return x + 2; +} + +SEC("raw_tp/sys_enter") +int main_prog(void *ctx) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 43c9cda199b8..b99bb8ed3ed4 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -184,9 +184,7 @@ def bpftool_prog_list(expected=None, ns=""): def bpftool_map_list(expected=None, ns=""): _, maps = bpftool("map show", JSON=True, ns=ns, fail=True) # Remove the base maps - for m in base_maps: - if m in maps: - maps.remove(m) + maps = [m for m in maps if m not in base_maps and m.get('name') not in base_map_names] if expected is not None: if len(maps) != expected: fail(True, "%d BPF maps loaded, expected %d" % @@ -716,13 +714,11 @@ def test_multi_prog(simdev, sim, obj, modename, modeid): fail(ret == 0, "Replaced one of programs without -force") check_extack(err, "XDP program already attached.", args) - if modename == "" or modename == "drv": - othermode = "" if modename == "drv" else "drv" - start_test("Test multi-attachment XDP - detach...") - ret, _, err = sim.unset_xdp(othermode, force=True, - fail=False, include_stderr=True) - fail(ret == 0, "Removed program with a bad mode") - check_extack(err, "program loaded with different flags.", args) + start_test("Test multi-attachment XDP - remove without mode...") + ret, _, err = sim.unset_xdp("", force=True, + fail=False, include_stderr=True) + fail(ret == 0, "Removed program without a mode flag") + check_extack(err, "More than one program loaded, unset mode is ambiguous.", args) sim.unset_xdp("offload") xdp = sim.ip_link_show(xdp=True)["xdp"] @@ -772,6 +768,9 @@ ret, progs = bpftool("prog", fail=False) skip(ret != 0, "bpftool not installed") base_progs = progs _, base_maps = bpftool("map") +base_map_names = [ + 'pid_iter.rodata' # created on each bpftool invocation +] # Check netdevsim ret, out = cmd("modprobe netdevsim", fail=False) @@ -913,11 +912,18 @@ try: sim.tc_flush_filters() + start_test("Test TC offloads failure...") + sim.dfs["dev/bpf_bind_verifier_accept"] = 0 + ret, _, err = sim.cls_bpf_add_filter(obj, verbose=True, skip_sw=True, + fail=False, include_stderr=True) + fail(ret == 0, "TC filter did not reject with TC offloads enabled") + check_verifier_log(err, "[netdevsim] Hello from netdevsim!") + sim.dfs["dev/bpf_bind_verifier_accept"] = 1 + start_test("Test TC offloads work...") ret, _, err = sim.cls_bpf_add_filter(obj, verbose=True, skip_sw=True, fail=False, include_stderr=True) fail(ret != 0, "TC filter did not load with TC offloads enabled") - check_verifier_log(err, "[netdevsim] Hello from netdevsim!") start_test("Test TC offload basics...") dfs = simdev.dfs_get_bound_progs(expected=1) @@ -941,6 +947,7 @@ try: start_test("Test disabling TC offloads is rejected while filters installed...") ret, _ = sim.set_ethtool_tc_offloads(False, fail=False) fail(ret == 0, "Driver should refuse to disable TC offloads with filters installed...") + sim.set_ethtool_tc_offloads(True) start_test("Test qdisc removal frees things...") sim.tc_flush_filters() @@ -999,18 +1006,8 @@ try: fail=False, include_stderr=True) fail(ret == 0, "Replaced XDP program with a program in different mode") check_extack(err, - "native and generic XDP can't be active at the same time.", + "Native and generic XDP can't be active at the same time.", args) - ret, _, err = sim.set_xdp(obj, "", force=True, - fail=False, include_stderr=True) - fail(ret == 0, "Replaced XDP program with a program in different mode") - check_extack(err, "program loaded with different flags.", args) - - start_test("Test XDP prog remove with bad flags...") - ret, _, err = sim.unset_xdp("", force=True, - fail=False, include_stderr=True) - fail(ret == 0, "Removed program with a bad mode") - check_extack(err, "program loaded with different flags.", args) start_test("Test MTU restrictions...") ret, _ = sim.set_mtu(9000, fail=False) @@ -1040,10 +1037,19 @@ try: offload = bpf_pinned("/sys/fs/bpf/offload") ret, _, err = sim.set_xdp(offload, "drv", fail=False, include_stderr=True) fail(ret == 0, "attached offloaded XDP program to drv") - check_extack(err, "using device-bound program without HW_MODE flag is not supported.", args) + check_extack(err, "Using device-bound program without HW_MODE flag is not supported.", args) rm("/sys/fs/bpf/offload") sim.wait_for_flush() + start_test("Test XDP load failure...") + sim.dfs["dev/bpf_bind_verifier_accept"] = 0 + ret, _, err = bpftool_prog_load("sample_ret0.o", "/sys/fs/bpf/offload", + dev=sim['ifname'], fail=False, include_stderr=True) + fail(ret == 0, "verifier should fail on load") + check_verifier_log(err, "[netdevsim] Hello from netdevsim!") + sim.dfs["dev/bpf_bind_verifier_accept"] = 1 + sim.wait_for_flush() + start_test("Test XDP offload...") _, _, err = sim.set_xdp(obj, "offload", verbose=True, include_stderr=True) ipl = sim.ip_link_show(xdp=True) @@ -1051,7 +1057,6 @@ try: progs = bpftool_prog_list(expected=1) prog = progs[0] fail(link_xdp["id"] != prog["id"], "Loaded program has wrong ID") - check_verifier_log(err, "[netdevsim] Hello from netdevsim!") start_test("Test XDP offload is device bound...") dfs = simdev.dfs_get_bound_progs(expected=1) diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c index 1c4b1939f5a8..bed53b561e04 100644 --- a/tools/testing/selftests/bpf/verifier/array_access.c +++ b/tools/testing/selftests/bpf/verifier/array_access.c @@ -68,7 +68,7 @@ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), - BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 0xffffffff, 1), + BPF_JMP32_IMM(BPF_JSGT, BPF_REG_1, 0xffffffff, 1), BPF_MOV32_IMM(BPF_REG_1, 0), BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES), BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1), diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index dac40de3f868..57ed67b86074 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -703,3 +703,44 @@ .fixup_map_hash_8b = { 3 }, .result = ACCEPT, }, +{ + "bounds checks after 32-bit truncation. test 1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + /* This used to reduce the max bound to 0x7fffffff */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0x7fffffff, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .errstr_unpriv = "R0 leaks addr", + .result_unpriv = REJECT, + .result = ACCEPT, +}, +{ + "bounds checks after 32-bit truncation. test 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_1, 1, 1), + BPF_JMP32_IMM(BPF_JSLT, BPF_REG_1, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .errstr_unpriv = "R0 leaks addr", + .result_unpriv = REJECT, + .result = ACCEPT, +}, diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index d2c2d6205008..7a2c242b7152 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,10 +1,13 @@ # SPDX-License-Identifier: GPL-2.0-only +/aarch64/get-reg-list +/aarch64/get-reg-list-sve /s390x/memop /s390x/resets /s390x/sync_regs_test /x86_64/cr4_cpuid_sync_test /x86_64/debug_regs /x86_64/evmcs_test +/x86_64/kvm_pv_test /x86_64/hyperv_cpuid /x86_64/mmio_warning_test /x86_64/platform_info_test @@ -24,6 +27,7 @@ /clear_dirty_log_test /demand_paging_test /dirty_log_test +/dirty_log_perf_test /kvm_create_max_vcpus /set_memory_region_test /steal_time diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 30afbad36cd5..3d14ef77755e 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -34,13 +34,14 @@ ifeq ($(ARCH),s390) endif LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c -LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c +LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid +TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test @@ -58,14 +59,15 @@ TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/user_msr_test -TEST_GEN_PROGS_x86_64 += clear_dirty_log_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test +TEST_GEN_PROGS_x86_64 += dirty_log_perf_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time -TEST_GEN_PROGS_aarch64 += clear_dirty_log_test +TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list +TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus @@ -111,14 +113,21 @@ LDFLAGS += -pthread $(no-pie-option) $(pgste-option) include ../lib.mk STATIC_LIBS := $(OUTPUT)/libkvm.a -LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM)) -EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.* +LIBKVM_C := $(filter %.c,$(LIBKVM)) +LIBKVM_S := $(filter %.S,$(LIBKVM)) +LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) +LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S)) +EXTRA_CLEAN += $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(STATIC_LIBS) cscope.* + +x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)))) +$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ -x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ)))) -$(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c +$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ -$(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) +LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) +$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS) $(AR) crs $@ $^ x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c new file mode 100644 index 000000000000..efba76682b4b --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define REG_LIST_SVE +#include "get-reg-list.c" diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c new file mode 100644 index 000000000000..33218a395d9f --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -0,0 +1,841 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Check for KVM_GET_REG_LIST regressions. + * + * Copyright (C) 2020, Red Hat, Inc. + * + * When attempting to migrate from a host with an older kernel to a host + * with a newer kernel we allow the newer kernel on the destination to + * list new registers with get-reg-list. We assume they'll be unused, at + * least until the guest reboots, and so they're relatively harmless. + * However, if the destination host with the newer kernel is missing + * registers which the source host with the older kernel has, then that's + * a regression in get-reg-list. This test checks for that regression by + * checking the current list against a blessed list. We should never have + * missing registers, but if new ones appear then they can probably be + * added to the blessed list. A completely new blessed list can be created + * by running the test with the --list command line argument. + * + * Note, the blessed list should be created from the oldest possible + * kernel. We can't go older than v4.15, though, because that's the first + * release to expose the ID system registers in KVM_GET_REG_LIST, see + * commit 93390c0a1b20 ("arm64: KVM: Hide unsupported AArch64 CPU features + * from guests"). Also, one must use the --core-reg-fixup command line + * option when running on an older kernel that doesn't include df205b5c6328 + * ("KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST") + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include "kvm_util.h" +#include "test_util.h" +#include "processor.h" + +#ifdef REG_LIST_SVE +#define reg_list_sve() (true) +#else +#define reg_list_sve() (false) +#endif + +#define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK) + +#define for_each_reg(i) \ + for ((i) = 0; (i) < reg_list->n; ++(i)) + +#define for_each_missing_reg(i) \ + for ((i) = 0; (i) < blessed_n; ++(i)) \ + if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) + +#define for_each_new_reg(i) \ + for ((i) = 0; (i) < reg_list->n; ++(i)) \ + if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i])) + + +static struct kvm_reg_list *reg_list; + +static __u64 base_regs[], vregs[], sve_regs[], rejects_set[]; +static __u64 base_regs_n, vregs_n, sve_regs_n, rejects_set_n; +static __u64 *blessed_reg, blessed_n; + +static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg) +{ + int i; + + for (i = 0; i < nr_regs; ++i) + if (reg == regs[i]) + return true; + return false; +} + +static const char *str_with_index(const char *template, __u64 index) +{ + char *str, *p; + int n; + + str = strdup(template); + p = strstr(str, "##"); + n = sprintf(p, "%lld", index); + strcat(p + n, strstr(template, "##") + 2); + + return (const char *)str; +} + +#define CORE_REGS_XX_NR_WORDS 2 +#define CORE_SPSR_XX_NR_WORDS 2 +#define CORE_FPREGS_XX_NR_WORDS 4 + +static const char *core_id_to_str(__u64 id) +{ + __u64 core_off = id & ~REG_MASK, idx; + + /* + * core_off is the offset into struct kvm_regs + */ + switch (core_off) { + case KVM_REG_ARM_CORE_REG(regs.regs[0]) ... + KVM_REG_ARM_CORE_REG(regs.regs[30]): + idx = (core_off - KVM_REG_ARM_CORE_REG(regs.regs[0])) / CORE_REGS_XX_NR_WORDS; + TEST_ASSERT(idx < 31, "Unexpected regs.regs index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(regs.regs[##])", idx); + case KVM_REG_ARM_CORE_REG(regs.sp): + return "KVM_REG_ARM_CORE_REG(regs.sp)"; + case KVM_REG_ARM_CORE_REG(regs.pc): + return "KVM_REG_ARM_CORE_REG(regs.pc)"; + case KVM_REG_ARM_CORE_REG(regs.pstate): + return "KVM_REG_ARM_CORE_REG(regs.pstate)"; + case KVM_REG_ARM_CORE_REG(sp_el1): + return "KVM_REG_ARM_CORE_REG(sp_el1)"; + case KVM_REG_ARM_CORE_REG(elr_el1): + return "KVM_REG_ARM_CORE_REG(elr_el1)"; + case KVM_REG_ARM_CORE_REG(spsr[0]) ... + KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]): + idx = (core_off - KVM_REG_ARM_CORE_REG(spsr[0])) / CORE_SPSR_XX_NR_WORDS; + TEST_ASSERT(idx < KVM_NR_SPSR, "Unexpected spsr index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(spsr[##])", idx); + case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... + KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): + idx = (core_off - KVM_REG_ARM_CORE_REG(fp_regs.vregs[0])) / CORE_FPREGS_XX_NR_WORDS; + TEST_ASSERT(idx < 32, "Unexpected fp_regs.vregs index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(fp_regs.vregs[##])", idx); + case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): + return "KVM_REG_ARM_CORE_REG(fp_regs.fpsr)"; + case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): + return "KVM_REG_ARM_CORE_REG(fp_regs.fpcr)"; + } + + TEST_FAIL("Unknown core reg id: 0x%llx", id); + return NULL; +} + +static const char *sve_id_to_str(__u64 id) +{ + __u64 sve_off, n, i; + + if (id == KVM_REG_ARM64_SVE_VLS) + return "KVM_REG_ARM64_SVE_VLS"; + + sve_off = id & ~(REG_MASK | ((1ULL << 5) - 1)); + i = id & (KVM_ARM64_SVE_MAX_SLICES - 1); + + TEST_ASSERT(i == 0, "Currently we don't expect slice > 0, reg id 0x%llx", id); + + switch (sve_off) { + case KVM_REG_ARM64_SVE_ZREG_BASE ... + KVM_REG_ARM64_SVE_ZREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_ZREGS - 1: + n = (id >> 5) & (KVM_ARM64_SVE_NUM_ZREGS - 1); + TEST_ASSERT(id == KVM_REG_ARM64_SVE_ZREG(n, 0), + "Unexpected bits set in SVE ZREG id: 0x%llx", id); + return str_with_index("KVM_REG_ARM64_SVE_ZREG(##, 0)", n); + case KVM_REG_ARM64_SVE_PREG_BASE ... + KVM_REG_ARM64_SVE_PREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_PREGS - 1: + n = (id >> 5) & (KVM_ARM64_SVE_NUM_PREGS - 1); + TEST_ASSERT(id == KVM_REG_ARM64_SVE_PREG(n, 0), + "Unexpected bits set in SVE PREG id: 0x%llx", id); + return str_with_index("KVM_REG_ARM64_SVE_PREG(##, 0)", n); + case KVM_REG_ARM64_SVE_FFR_BASE: + TEST_ASSERT(id == KVM_REG_ARM64_SVE_FFR(0), + "Unexpected bits set in SVE FFR id: 0x%llx", id); + return "KVM_REG_ARM64_SVE_FFR(0)"; + } + + return NULL; +} + +static void print_reg(__u64 id) +{ + unsigned op0, op1, crn, crm, op2; + const char *reg_size = NULL; + + TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_ARM64, + "KVM_REG_ARM64 missing in reg id: 0x%llx", id); + + switch (id & KVM_REG_SIZE_MASK) { + case KVM_REG_SIZE_U8: + reg_size = "KVM_REG_SIZE_U8"; + break; + case KVM_REG_SIZE_U16: + reg_size = "KVM_REG_SIZE_U16"; + break; + case KVM_REG_SIZE_U32: + reg_size = "KVM_REG_SIZE_U32"; + break; + case KVM_REG_SIZE_U64: + reg_size = "KVM_REG_SIZE_U64"; + break; + case KVM_REG_SIZE_U128: + reg_size = "KVM_REG_SIZE_U128"; + break; + case KVM_REG_SIZE_U256: + reg_size = "KVM_REG_SIZE_U256"; + break; + case KVM_REG_SIZE_U512: + reg_size = "KVM_REG_SIZE_U512"; + break; + case KVM_REG_SIZE_U1024: + reg_size = "KVM_REG_SIZE_U1024"; + break; + case KVM_REG_SIZE_U2048: + reg_size = "KVM_REG_SIZE_U2048"; + break; + default: + TEST_FAIL("Unexpected reg size: 0x%llx in reg id: 0x%llx", + (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id); + } + + switch (id & KVM_REG_ARM_COPROC_MASK) { + case KVM_REG_ARM_CORE: + printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(id)); + break; + case KVM_REG_ARM_DEMUX: + TEST_ASSERT(!(id & ~(REG_MASK | KVM_REG_ARM_DEMUX_ID_MASK | KVM_REG_ARM_DEMUX_VAL_MASK)), + "Unexpected bits set in DEMUX reg id: 0x%llx", id); + printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | %lld,\n", + reg_size, id & KVM_REG_ARM_DEMUX_VAL_MASK); + break; + case KVM_REG_ARM64_SYSREG: + op0 = (id & KVM_REG_ARM64_SYSREG_OP0_MASK) >> KVM_REG_ARM64_SYSREG_OP0_SHIFT; + op1 = (id & KVM_REG_ARM64_SYSREG_OP1_MASK) >> KVM_REG_ARM64_SYSREG_OP1_SHIFT; + crn = (id & KVM_REG_ARM64_SYSREG_CRN_MASK) >> KVM_REG_ARM64_SYSREG_CRN_SHIFT; + crm = (id & KVM_REG_ARM64_SYSREG_CRM_MASK) >> KVM_REG_ARM64_SYSREG_CRM_SHIFT; + op2 = (id & KVM_REG_ARM64_SYSREG_OP2_MASK) >> KVM_REG_ARM64_SYSREG_OP2_SHIFT; + TEST_ASSERT(id == ARM64_SYS_REG(op0, op1, crn, crm, op2), + "Unexpected bits set in SYSREG reg id: 0x%llx", id); + printf("\tARM64_SYS_REG(%d, %d, %d, %d, %d),\n", op0, op1, crn, crm, op2); + break; + case KVM_REG_ARM_FW: + TEST_ASSERT(id == KVM_REG_ARM_FW_REG(id & 0xffff), + "Unexpected bits set in FW reg id: 0x%llx", id); + printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff); + break; + case KVM_REG_ARM64_SVE: + if (reg_list_sve()) + printf("\t%s,\n", sve_id_to_str(id)); + else + TEST_FAIL("KVM_REG_ARM64_SVE is an unexpected coproc type in reg id: 0x%llx", id); + break; + default: + TEST_FAIL("Unexpected coproc type: 0x%llx in reg id: 0x%llx", + (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id); + } +} + +/* + * Older kernels listed each 32-bit word of CORE registers separately. + * For 64 and 128-bit registers we need to ignore the extra words. We + * also need to fixup the sizes, because the older kernels stated all + * registers were 64-bit, even when they weren't. + */ +static void core_reg_fixup(void) +{ + struct kvm_reg_list *tmp; + __u64 id, core_off; + int i; + + tmp = calloc(1, sizeof(*tmp) + reg_list->n * sizeof(__u64)); + + for (i = 0; i < reg_list->n; ++i) { + id = reg_list->reg[i]; + + if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM_CORE) { + tmp->reg[tmp->n++] = id; + continue; + } + + core_off = id & ~REG_MASK; + + switch (core_off) { + case 0x52: case 0xd2: case 0xd6: + /* + * These offsets are pointing at padding. + * We need to ignore them too. + */ + continue; + case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... + KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): + if (core_off & 3) + continue; + id &= ~KVM_REG_SIZE_MASK; + id |= KVM_REG_SIZE_U128; + tmp->reg[tmp->n++] = id; + continue; + case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): + case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): + id &= ~KVM_REG_SIZE_MASK; + id |= KVM_REG_SIZE_U32; + tmp->reg[tmp->n++] = id; + continue; + default: + if (core_off & 1) + continue; + tmp->reg[tmp->n++] = id; + break; + } + } + + free(reg_list); + reg_list = tmp; +} + +static void prepare_vcpu_init(struct kvm_vcpu_init *init) +{ + if (reg_list_sve()) + init->features[0] |= 1 << KVM_ARM_VCPU_SVE; +} + +static void finalize_vcpu(struct kvm_vm *vm, uint32_t vcpuid) +{ + int feature; + + if (reg_list_sve()) { + feature = KVM_ARM_VCPU_SVE; + vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_FINALIZE, &feature); + } +} + +static void check_supported(void) +{ + if (reg_list_sve() && !kvm_check_cap(KVM_CAP_ARM_SVE)) { + fprintf(stderr, "SVE not available, skipping tests\n"); + exit(KSFT_SKIP); + } +} + +int main(int ac, char **av) +{ + struct kvm_vcpu_init init = { .target = -1, }; + int new_regs = 0, missing_regs = 0, i; + int failed_get = 0, failed_set = 0, failed_reject = 0; + bool print_list = false, fixup_core_regs = false; + struct kvm_vm *vm; + __u64 *vec_regs; + + check_supported(); + + for (i = 1; i < ac; ++i) { + if (strcmp(av[i], "--core-reg-fixup") == 0) + fixup_core_regs = true; + else if (strcmp(av[i], "--list") == 0) + print_list = true; + else + fprintf(stderr, "Ignoring unknown option: %s\n", av[i]); + } + + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + prepare_vcpu_init(&init); + aarch64_vcpu_add_default(vm, 0, &init, NULL); + finalize_vcpu(vm, 0); + + reg_list = vcpu_get_reg_list(vm, 0); + + if (fixup_core_regs) + core_reg_fixup(); + + if (print_list) { + putchar('\n'); + for_each_reg(i) + print_reg(reg_list->reg[i]); + putchar('\n'); + return 0; + } + + /* + * We only test that we can get the register and then write back the + * same value. Some registers may allow other values to be written + * back, but others only allow some bits to be changed, and at least + * for ID registers set will fail if the value does not exactly match + * what was returned by get. If registers that allow other values to + * be written need to have the other values tested, then we should + * create a new set of tests for those in a new independent test + * executable. + */ + for_each_reg(i) { + uint8_t addr[2048 / 8]; + struct kvm_one_reg reg = { + .id = reg_list->reg[i], + .addr = (__u64)&addr, + }; + int ret; + + ret = _vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, ®); + if (ret) { + puts("Failed to get "); + print_reg(reg.id); + putchar('\n'); + ++failed_get; + } + + /* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */ + if (find_reg(rejects_set, rejects_set_n, reg.id)) { + ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); + if (ret != -1 || errno != EPERM) { + printf("Failed to reject (ret=%d, errno=%d) ", ret, errno); + print_reg(reg.id); + putchar('\n'); + ++failed_reject; + } + continue; + } + + ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); + if (ret) { + puts("Failed to set "); + print_reg(reg.id); + putchar('\n'); + ++failed_set; + } + } + + if (reg_list_sve()) { + blessed_n = base_regs_n + sve_regs_n; + vec_regs = sve_regs; + } else { + blessed_n = base_regs_n + vregs_n; + vec_regs = vregs; + } + + blessed_reg = calloc(blessed_n, sizeof(__u64)); + for (i = 0; i < base_regs_n; ++i) + blessed_reg[i] = base_regs[i]; + for (i = 0; i < blessed_n - base_regs_n; ++i) + blessed_reg[base_regs_n + i] = vec_regs[i]; + + for_each_new_reg(i) + ++new_regs; + + for_each_missing_reg(i) + ++missing_regs; + + if (new_regs || missing_regs) { + printf("Number blessed registers: %5lld\n", blessed_n); + printf("Number registers: %5lld\n", reg_list->n); + } + + if (new_regs) { + printf("\nThere are %d new registers.\n" + "Consider adding them to the blessed reg " + "list with the following lines:\n\n", new_regs); + for_each_new_reg(i) + print_reg(reg_list->reg[i]); + putchar('\n'); + } + + if (missing_regs) { + printf("\nThere are %d missing registers.\n" + "The following lines are missing registers:\n\n", missing_regs); + for_each_missing_reg(i) + print_reg(blessed_reg[i]); + putchar('\n'); + } + + TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject, + "There are %d missing registers; " + "%d registers failed get; %d registers failed set; %d registers failed reject", + missing_regs, failed_get, failed_set, failed_reject); + + return 0; +} + +/* + * The current blessed list was primed with the output of kernel version + * v4.15 with --core-reg-fixup and then later updated with new registers. + */ +static __u64 base_regs[] = { + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[5]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[6]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[7]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[8]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[9]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[10]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[11]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[12]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[13]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[14]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[15]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[16]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[17]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[18]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[19]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[20]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[21]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[22]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[23]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[24]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[25]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[26]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[27]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[28]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[29]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[30]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.sp), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pc), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pstate), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(sp_el1), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(elr_el1), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr), + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr), + KVM_REG_ARM_FW_REG(0), + KVM_REG_ARM_FW_REG(1), + KVM_REG_ARM_FW_REG(2), + ARM64_SYS_REG(3, 3, 14, 3, 1), /* CNTV_CTL_EL0 */ + ARM64_SYS_REG(3, 3, 14, 3, 2), /* CNTV_CVAL_EL0 */ + ARM64_SYS_REG(3, 3, 14, 0, 2), + ARM64_SYS_REG(3, 0, 0, 0, 0), /* MIDR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 0, 6), /* REVIDR_EL1 */ + ARM64_SYS_REG(3, 1, 0, 0, 1), /* CLIDR_EL1 */ + ARM64_SYS_REG(3, 1, 0, 0, 7), /* AIDR_EL1 */ + ARM64_SYS_REG(3, 3, 0, 0, 1), /* CTR_EL0 */ + ARM64_SYS_REG(2, 0, 0, 0, 4), + ARM64_SYS_REG(2, 0, 0, 0, 5), + ARM64_SYS_REG(2, 0, 0, 0, 6), + ARM64_SYS_REG(2, 0, 0, 0, 7), + ARM64_SYS_REG(2, 0, 0, 1, 4), + ARM64_SYS_REG(2, 0, 0, 1, 5), + ARM64_SYS_REG(2, 0, 0, 1, 6), + ARM64_SYS_REG(2, 0, 0, 1, 7), + ARM64_SYS_REG(2, 0, 0, 2, 0), /* MDCCINT_EL1 */ + ARM64_SYS_REG(2, 0, 0, 2, 2), /* MDSCR_EL1 */ + ARM64_SYS_REG(2, 0, 0, 2, 4), + ARM64_SYS_REG(2, 0, 0, 2, 5), + ARM64_SYS_REG(2, 0, 0, 2, 6), + ARM64_SYS_REG(2, 0, 0, 2, 7), + ARM64_SYS_REG(2, 0, 0, 3, 4), + ARM64_SYS_REG(2, 0, 0, 3, 5), + ARM64_SYS_REG(2, 0, 0, 3, 6), + ARM64_SYS_REG(2, 0, 0, 3, 7), + ARM64_SYS_REG(2, 0, 0, 4, 4), + ARM64_SYS_REG(2, 0, 0, 4, 5), + ARM64_SYS_REG(2, 0, 0, 4, 6), + ARM64_SYS_REG(2, 0, 0, 4, 7), + ARM64_SYS_REG(2, 0, 0, 5, 4), + ARM64_SYS_REG(2, 0, 0, 5, 5), + ARM64_SYS_REG(2, 0, 0, 5, 6), + ARM64_SYS_REG(2, 0, 0, 5, 7), + ARM64_SYS_REG(2, 0, 0, 6, 4), + ARM64_SYS_REG(2, 0, 0, 6, 5), + ARM64_SYS_REG(2, 0, 0, 6, 6), + ARM64_SYS_REG(2, 0, 0, 6, 7), + ARM64_SYS_REG(2, 0, 0, 7, 4), + ARM64_SYS_REG(2, 0, 0, 7, 5), + ARM64_SYS_REG(2, 0, 0, 7, 6), + ARM64_SYS_REG(2, 0, 0, 7, 7), + ARM64_SYS_REG(2, 0, 0, 8, 4), + ARM64_SYS_REG(2, 0, 0, 8, 5), + ARM64_SYS_REG(2, 0, 0, 8, 6), + ARM64_SYS_REG(2, 0, 0, 8, 7), + ARM64_SYS_REG(2, 0, 0, 9, 4), + ARM64_SYS_REG(2, 0, 0, 9, 5), + ARM64_SYS_REG(2, 0, 0, 9, 6), + ARM64_SYS_REG(2, 0, 0, 9, 7), + ARM64_SYS_REG(2, 0, 0, 10, 4), + ARM64_SYS_REG(2, 0, 0, 10, 5), + ARM64_SYS_REG(2, 0, 0, 10, 6), + ARM64_SYS_REG(2, 0, 0, 10, 7), + ARM64_SYS_REG(2, 0, 0, 11, 4), + ARM64_SYS_REG(2, 0, 0, 11, 5), + ARM64_SYS_REG(2, 0, 0, 11, 6), + ARM64_SYS_REG(2, 0, 0, 11, 7), + ARM64_SYS_REG(2, 0, 0, 12, 4), + ARM64_SYS_REG(2, 0, 0, 12, 5), + ARM64_SYS_REG(2, 0, 0, 12, 6), + ARM64_SYS_REG(2, 0, 0, 12, 7), + ARM64_SYS_REG(2, 0, 0, 13, 4), + ARM64_SYS_REG(2, 0, 0, 13, 5), + ARM64_SYS_REG(2, 0, 0, 13, 6), + ARM64_SYS_REG(2, 0, 0, 13, 7), + ARM64_SYS_REG(2, 0, 0, 14, 4), + ARM64_SYS_REG(2, 0, 0, 14, 5), + ARM64_SYS_REG(2, 0, 0, 14, 6), + ARM64_SYS_REG(2, 0, 0, 14, 7), + ARM64_SYS_REG(2, 0, 0, 15, 4), + ARM64_SYS_REG(2, 0, 0, 15, 5), + ARM64_SYS_REG(2, 0, 0, 15, 6), + ARM64_SYS_REG(2, 0, 0, 15, 7), + ARM64_SYS_REG(2, 4, 0, 7, 0), /* DBGVCR32_EL2 */ + ARM64_SYS_REG(3, 0, 0, 0, 5), /* MPIDR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 0), /* ID_PFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 1), /* ID_PFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 2), /* ID_DFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 3), /* ID_AFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 4), /* ID_MMFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 5), /* ID_MMFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 6), /* ID_MMFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 7), /* ID_MMFR3_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 0), /* ID_ISAR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 1), /* ID_ISAR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 2), /* ID_ISAR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 3), /* ID_ISAR3_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 4), /* ID_ISAR4_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 5), /* ID_ISAR5_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 6), /* ID_MMFR4_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 7), /* ID_ISAR6_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 0), /* MVFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 1), /* MVFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 2), /* MVFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 3), + ARM64_SYS_REG(3, 0, 0, 3, 4), /* ID_PFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 5), /* ID_DFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 6), /* ID_MMFR5_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 7), + ARM64_SYS_REG(3, 0, 0, 4, 0), /* ID_AA64PFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 1), /* ID_AA64PFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 2), + ARM64_SYS_REG(3, 0, 0, 4, 3), + ARM64_SYS_REG(3, 0, 0, 4, 4), /* ID_AA64ZFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 5), + ARM64_SYS_REG(3, 0, 0, 4, 6), + ARM64_SYS_REG(3, 0, 0, 4, 7), + ARM64_SYS_REG(3, 0, 0, 5, 0), /* ID_AA64DFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 1), /* ID_AA64DFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 2), + ARM64_SYS_REG(3, 0, 0, 5, 3), + ARM64_SYS_REG(3, 0, 0, 5, 4), /* ID_AA64AFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 5), /* ID_AA64AFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 6), + ARM64_SYS_REG(3, 0, 0, 5, 7), + ARM64_SYS_REG(3, 0, 0, 6, 0), /* ID_AA64ISAR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 6, 1), /* ID_AA64ISAR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 6, 2), + ARM64_SYS_REG(3, 0, 0, 6, 3), + ARM64_SYS_REG(3, 0, 0, 6, 4), + ARM64_SYS_REG(3, 0, 0, 6, 5), + ARM64_SYS_REG(3, 0, 0, 6, 6), + ARM64_SYS_REG(3, 0, 0, 6, 7), + ARM64_SYS_REG(3, 0, 0, 7, 0), /* ID_AA64MMFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 1), /* ID_AA64MMFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 2), /* ID_AA64MMFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), + ARM64_SYS_REG(3, 0, 0, 7, 4), + ARM64_SYS_REG(3, 0, 0, 7, 5), + ARM64_SYS_REG(3, 0, 0, 7, 6), + ARM64_SYS_REG(3, 0, 0, 7, 7), + ARM64_SYS_REG(3, 0, 1, 0, 0), /* SCTLR_EL1 */ + ARM64_SYS_REG(3, 0, 1, 0, 1), /* ACTLR_EL1 */ + ARM64_SYS_REG(3, 0, 1, 0, 2), /* CPACR_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 0), /* TTBR0_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 1), /* TTBR1_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 2), /* TCR_EL1 */ + ARM64_SYS_REG(3, 0, 5, 1, 0), /* AFSR0_EL1 */ + ARM64_SYS_REG(3, 0, 5, 1, 1), /* AFSR1_EL1 */ + ARM64_SYS_REG(3, 0, 5, 2, 0), /* ESR_EL1 */ + ARM64_SYS_REG(3, 0, 6, 0, 0), /* FAR_EL1 */ + ARM64_SYS_REG(3, 0, 7, 4, 0), /* PAR_EL1 */ + ARM64_SYS_REG(3, 0, 9, 14, 1), /* PMINTENSET_EL1 */ + ARM64_SYS_REG(3, 0, 9, 14, 2), /* PMINTENCLR_EL1 */ + ARM64_SYS_REG(3, 0, 10, 2, 0), /* MAIR_EL1 */ + ARM64_SYS_REG(3, 0, 10, 3, 0), /* AMAIR_EL1 */ + ARM64_SYS_REG(3, 0, 12, 0, 0), /* VBAR_EL1 */ + ARM64_SYS_REG(3, 0, 12, 1, 1), /* DISR_EL1 */ + ARM64_SYS_REG(3, 0, 13, 0, 1), /* CONTEXTIDR_EL1 */ + ARM64_SYS_REG(3, 0, 13, 0, 4), /* TPIDR_EL1 */ + ARM64_SYS_REG(3, 0, 14, 1, 0), /* CNTKCTL_EL1 */ + ARM64_SYS_REG(3, 2, 0, 0, 0), /* CSSELR_EL1 */ + ARM64_SYS_REG(3, 3, 9, 12, 0), /* PMCR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 1), /* PMCNTENSET_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 2), /* PMCNTENCLR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 3), /* PMOVSCLR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 4), /* PMSWINC_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 5), /* PMSELR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 13, 0), /* PMCCNTR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 14, 0), /* PMUSERENR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 14, 3), /* PMOVSSET_EL0 */ + ARM64_SYS_REG(3, 3, 13, 0, 2), /* TPIDR_EL0 */ + ARM64_SYS_REG(3, 3, 13, 0, 3), /* TPIDRRO_EL0 */ + ARM64_SYS_REG(3, 3, 14, 8, 0), + ARM64_SYS_REG(3, 3, 14, 8, 1), + ARM64_SYS_REG(3, 3, 14, 8, 2), + ARM64_SYS_REG(3, 3, 14, 8, 3), + ARM64_SYS_REG(3, 3, 14, 8, 4), + ARM64_SYS_REG(3, 3, 14, 8, 5), + ARM64_SYS_REG(3, 3, 14, 8, 6), + ARM64_SYS_REG(3, 3, 14, 8, 7), + ARM64_SYS_REG(3, 3, 14, 9, 0), + ARM64_SYS_REG(3, 3, 14, 9, 1), + ARM64_SYS_REG(3, 3, 14, 9, 2), + ARM64_SYS_REG(3, 3, 14, 9, 3), + ARM64_SYS_REG(3, 3, 14, 9, 4), + ARM64_SYS_REG(3, 3, 14, 9, 5), + ARM64_SYS_REG(3, 3, 14, 9, 6), + ARM64_SYS_REG(3, 3, 14, 9, 7), + ARM64_SYS_REG(3, 3, 14, 10, 0), + ARM64_SYS_REG(3, 3, 14, 10, 1), + ARM64_SYS_REG(3, 3, 14, 10, 2), + ARM64_SYS_REG(3, 3, 14, 10, 3), + ARM64_SYS_REG(3, 3, 14, 10, 4), + ARM64_SYS_REG(3, 3, 14, 10, 5), + ARM64_SYS_REG(3, 3, 14, 10, 6), + ARM64_SYS_REG(3, 3, 14, 10, 7), + ARM64_SYS_REG(3, 3, 14, 11, 0), + ARM64_SYS_REG(3, 3, 14, 11, 1), + ARM64_SYS_REG(3, 3, 14, 11, 2), + ARM64_SYS_REG(3, 3, 14, 11, 3), + ARM64_SYS_REG(3, 3, 14, 11, 4), + ARM64_SYS_REG(3, 3, 14, 11, 5), + ARM64_SYS_REG(3, 3, 14, 11, 6), + ARM64_SYS_REG(3, 3, 14, 12, 0), + ARM64_SYS_REG(3, 3, 14, 12, 1), + ARM64_SYS_REG(3, 3, 14, 12, 2), + ARM64_SYS_REG(3, 3, 14, 12, 3), + ARM64_SYS_REG(3, 3, 14, 12, 4), + ARM64_SYS_REG(3, 3, 14, 12, 5), + ARM64_SYS_REG(3, 3, 14, 12, 6), + ARM64_SYS_REG(3, 3, 14, 12, 7), + ARM64_SYS_REG(3, 3, 14, 13, 0), + ARM64_SYS_REG(3, 3, 14, 13, 1), + ARM64_SYS_REG(3, 3, 14, 13, 2), + ARM64_SYS_REG(3, 3, 14, 13, 3), + ARM64_SYS_REG(3, 3, 14, 13, 4), + ARM64_SYS_REG(3, 3, 14, 13, 5), + ARM64_SYS_REG(3, 3, 14, 13, 6), + ARM64_SYS_REG(3, 3, 14, 13, 7), + ARM64_SYS_REG(3, 3, 14, 14, 0), + ARM64_SYS_REG(3, 3, 14, 14, 1), + ARM64_SYS_REG(3, 3, 14, 14, 2), + ARM64_SYS_REG(3, 3, 14, 14, 3), + ARM64_SYS_REG(3, 3, 14, 14, 4), + ARM64_SYS_REG(3, 3, 14, 14, 5), + ARM64_SYS_REG(3, 3, 14, 14, 6), + ARM64_SYS_REG(3, 3, 14, 14, 7), + ARM64_SYS_REG(3, 3, 14, 15, 0), + ARM64_SYS_REG(3, 3, 14, 15, 1), + ARM64_SYS_REG(3, 3, 14, 15, 2), + ARM64_SYS_REG(3, 3, 14, 15, 3), + ARM64_SYS_REG(3, 3, 14, 15, 4), + ARM64_SYS_REG(3, 3, 14, 15, 5), + ARM64_SYS_REG(3, 3, 14, 15, 6), + ARM64_SYS_REG(3, 3, 14, 15, 7), /* PMCCFILTR_EL0 */ + ARM64_SYS_REG(3, 4, 3, 0, 0), /* DACR32_EL2 */ + ARM64_SYS_REG(3, 4, 5, 0, 1), /* IFSR32_EL2 */ + ARM64_SYS_REG(3, 4, 5, 3, 0), /* FPEXC32_EL2 */ + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 0, + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 1, + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 2, +}; +static __u64 base_regs_n = ARRAY_SIZE(base_regs); + +static __u64 vregs[] = { + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[5]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[6]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[7]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[8]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[9]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[10]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[11]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[12]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[13]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[14]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[15]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[16]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[17]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[18]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[19]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[20]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[21]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[22]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[23]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[24]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[25]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[26]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[27]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[28]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[29]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[30]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]), +}; +static __u64 vregs_n = ARRAY_SIZE(vregs); + +static __u64 sve_regs[] = { + KVM_REG_ARM64_SVE_VLS, + KVM_REG_ARM64_SVE_ZREG(0, 0), + KVM_REG_ARM64_SVE_ZREG(1, 0), + KVM_REG_ARM64_SVE_ZREG(2, 0), + KVM_REG_ARM64_SVE_ZREG(3, 0), + KVM_REG_ARM64_SVE_ZREG(4, 0), + KVM_REG_ARM64_SVE_ZREG(5, 0), + KVM_REG_ARM64_SVE_ZREG(6, 0), + KVM_REG_ARM64_SVE_ZREG(7, 0), + KVM_REG_ARM64_SVE_ZREG(8, 0), + KVM_REG_ARM64_SVE_ZREG(9, 0), + KVM_REG_ARM64_SVE_ZREG(10, 0), + KVM_REG_ARM64_SVE_ZREG(11, 0), + KVM_REG_ARM64_SVE_ZREG(12, 0), + KVM_REG_ARM64_SVE_ZREG(13, 0), + KVM_REG_ARM64_SVE_ZREG(14, 0), + KVM_REG_ARM64_SVE_ZREG(15, 0), + KVM_REG_ARM64_SVE_ZREG(16, 0), + KVM_REG_ARM64_SVE_ZREG(17, 0), + KVM_REG_ARM64_SVE_ZREG(18, 0), + KVM_REG_ARM64_SVE_ZREG(19, 0), + KVM_REG_ARM64_SVE_ZREG(20, 0), + KVM_REG_ARM64_SVE_ZREG(21, 0), + KVM_REG_ARM64_SVE_ZREG(22, 0), + KVM_REG_ARM64_SVE_ZREG(23, 0), + KVM_REG_ARM64_SVE_ZREG(24, 0), + KVM_REG_ARM64_SVE_ZREG(25, 0), + KVM_REG_ARM64_SVE_ZREG(26, 0), + KVM_REG_ARM64_SVE_ZREG(27, 0), + KVM_REG_ARM64_SVE_ZREG(28, 0), + KVM_REG_ARM64_SVE_ZREG(29, 0), + KVM_REG_ARM64_SVE_ZREG(30, 0), + KVM_REG_ARM64_SVE_ZREG(31, 0), + KVM_REG_ARM64_SVE_PREG(0, 0), + KVM_REG_ARM64_SVE_PREG(1, 0), + KVM_REG_ARM64_SVE_PREG(2, 0), + KVM_REG_ARM64_SVE_PREG(3, 0), + KVM_REG_ARM64_SVE_PREG(4, 0), + KVM_REG_ARM64_SVE_PREG(5, 0), + KVM_REG_ARM64_SVE_PREG(6, 0), + KVM_REG_ARM64_SVE_PREG(7, 0), + KVM_REG_ARM64_SVE_PREG(8, 0), + KVM_REG_ARM64_SVE_PREG(9, 0), + KVM_REG_ARM64_SVE_PREG(10, 0), + KVM_REG_ARM64_SVE_PREG(11, 0), + KVM_REG_ARM64_SVE_PREG(12, 0), + KVM_REG_ARM64_SVE_PREG(13, 0), + KVM_REG_ARM64_SVE_PREG(14, 0), + KVM_REG_ARM64_SVE_PREG(15, 0), + KVM_REG_ARM64_SVE_FFR(0), + ARM64_SYS_REG(3, 0, 1, 2, 0), /* ZCR_EL1 */ +}; +static __u64 sve_regs_n = ARRAY_SIZE(sve_regs); + +static __u64 rejects_set[] = { +#ifdef REG_LIST_SVE + KVM_REG_ARM64_SVE_VLS, +#endif +}; +static __u64 rejects_set_n = ARRAY_SIZE(rejects_set); diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c deleted file mode 100644 index 11672ec6f74e..000000000000 --- a/tools/testing/selftests/kvm/clear_dirty_log_test.c +++ /dev/null @@ -1,6 +0,0 @@ -#define USE_CLEAR_DIRTY_LOG -#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) -#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) -#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ - KVM_DIRTY_LOG_INITIALLY_SET) -#include "dirty_log_test.c" diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 360cd3ea4cd6..3d96a7bfaff3 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -21,20 +21,12 @@ #include <linux/bitops.h> #include <linux/userfaultfd.h> -#include "test_util.h" -#include "kvm_util.h" +#include "perf_test_util.h" #include "processor.h" +#include "test_util.h" #ifdef __NR_userfaultfd -/* The memory slot index demand page */ -#define TEST_MEM_SLOT_INDEX 1 - -/* Default guest test virtual memory offset */ -#define DEFAULT_GUEST_TEST_MEM 0xc0000000 - -#define DEFAULT_GUEST_TEST_MEM_SIZE (1 << 30) /* 1G */ - #ifdef PRINT_PER_PAGE_UPDATES #define PER_PAGE_DEBUG(...) printf(__VA_ARGS__) #else @@ -47,77 +39,17 @@ #define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__) #endif -#define MAX_VCPUS 512 - -/* - * Guest/Host shared variables. Ensure addr_gva2hva() and/or - * sync_global_to/from_guest() are used when accessing from - * the host. READ/WRITE_ONCE() should also be used with anything - * that may change. - */ -static uint64_t host_page_size; -static uint64_t guest_page_size; - static char *guest_data_prototype; -/* - * Guest physical memory offset of the testing memory slot. - * This will be set to the topmost valid physical address minus - * the test memory size. - */ -static uint64_t guest_test_phys_mem; - -/* - * Guest virtual memory offset of the testing memory slot. - * Must not conflict with identity mapped test code. - */ -static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; - -struct vcpu_args { - uint64_t gva; - uint64_t pages; - - /* Only used by the host userspace part of the vCPU thread */ - int vcpu_id; - struct kvm_vm *vm; -}; - -static struct vcpu_args vcpu_args[MAX_VCPUS]; - -/* - * Continuously write to the first 8 bytes of each page in the demand paging - * memory region. - */ -static void guest_code(uint32_t vcpu_id) -{ - uint64_t gva; - uint64_t pages; - int i; - - /* Make sure vCPU args data structure is not corrupt. */ - GUEST_ASSERT(vcpu_args[vcpu_id].vcpu_id == vcpu_id); - - gva = vcpu_args[vcpu_id].gva; - pages = vcpu_args[vcpu_id].pages; - - for (i = 0; i < pages; i++) { - uint64_t addr = gva + (i * guest_page_size); - - addr &= ~(host_page_size - 1); - *(uint64_t *)addr = 0x0123456789ABCDEF; - } - - GUEST_SYNC(1); -} - static void *vcpu_worker(void *data) { int ret; - struct vcpu_args *args = (struct vcpu_args *)data; - struct kvm_vm *vm = args->vm; - int vcpu_id = args->vcpu_id; + struct vcpu_args *vcpu_args = (struct vcpu_args *)data; + int vcpu_id = vcpu_args->vcpu_id; + struct kvm_vm *vm = perf_test_args.vm; struct kvm_run *run; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; vcpu_args_set(vm, vcpu_id, 1, vcpu_id); run = vcpu_state(vm, vcpu_id); @@ -133,52 +65,18 @@ static void *vcpu_worker(void *data) exit_reason_str(run->exit_reason)); } - clock_gettime(CLOCK_MONOTONIC, &end); - ts_diff = timespec_sub(end, start); + ts_diff = timespec_diff_now(start); PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id, ts_diff.tv_sec, ts_diff.tv_nsec); return NULL; } -#define PAGE_SHIFT_4K 12 -#define PTES_PER_4K_PT 512 - -static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus, - uint64_t vcpu_memory_bytes) -{ - struct kvm_vm *vm; - uint64_t pages = DEFAULT_GUEST_PHY_PAGES; - - /* Account for a few pages per-vCPU for stacks */ - pages += DEFAULT_STACK_PGS * vcpus; - - /* - * Reserve twice the ammount of memory needed to map the test region and - * the page table / stacks region, at 4k, for page tables. Do the - * calculation with 4K page size: the smallest of all archs. (e.g., 64K - * page size guest will need even less memory for page tables). - */ - pages += (2 * pages) / PTES_PER_4K_PT; - pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) / - PTES_PER_4K_PT; - pages = vm_adjust_num_guest_pages(mode, pages); - - pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - - vm = _vm_create(mode, pages, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); -#ifdef __x86_64__ - vm_create_irqchip(vm); -#endif - return vm; -} - static int handle_uffd_page_request(int uffd, uint64_t addr) { pid_t tid; struct timespec start; - struct timespec end; + struct timespec ts_diff; struct uffdio_copy copy; int r; @@ -186,7 +84,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) copy.src = (uint64_t)guest_data_prototype; copy.dst = addr; - copy.len = host_page_size; + copy.len = perf_test_args.host_page_size; copy.mode = 0; clock_gettime(CLOCK_MONOTONIC, &start); @@ -198,12 +96,12 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) return r; } - clock_gettime(CLOCK_MONOTONIC, &end); + ts_diff = timespec_diff_now(start); PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid, - timespec_to_ns(timespec_sub(end, start))); + timespec_to_ns(ts_diff)); PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n", - host_page_size, addr, tid); + perf_test_args.host_page_size, addr, tid); return 0; } @@ -223,7 +121,8 @@ static void *uffd_handler_thread_fn(void *arg) int pipefd = uffd_args->pipefd; useconds_t delay = uffd_args->delay; int64_t pages = 0; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; clock_gettime(CLOCK_MONOTONIC, &start); while (!quit_uffd_thread) { @@ -292,8 +191,7 @@ static void *uffd_handler_thread_fn(void *arg) pages++; } - clock_gettime(CLOCK_MONOTONIC, &end); - ts_diff = timespec_sub(end, start); + ts_diff = timespec_diff_now(start); PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n", pages, ts_diff.tv_sec, ts_diff.tv_nsec, pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); @@ -351,99 +249,54 @@ static int setup_demand_paging(struct kvm_vm *vm, } static void run_test(enum vm_guest_mode mode, bool use_uffd, - useconds_t uffd_delay, int vcpus, - uint64_t vcpu_memory_bytes) + useconds_t uffd_delay) { pthread_t *vcpu_threads; pthread_t *uffd_handler_threads = NULL; struct uffd_handler_args *uffd_args = NULL; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; int *pipefds = NULL; struct kvm_vm *vm; - uint64_t guest_num_pages; int vcpu_id; int r; - vm = create_vm(mode, vcpus, vcpu_memory_bytes); - - guest_page_size = vm_get_page_size(vm); - - TEST_ASSERT(vcpu_memory_bytes % guest_page_size == 0, - "Guest memory size is not guest page size aligned."); - - guest_num_pages = (vcpus * vcpu_memory_bytes) / guest_page_size; - guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); - - /* - * If there should be more memory in the guest test region than there - * can be pages in the guest, it will definitely cause problems. - */ - TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), - "Requested more guest memory than address space allows.\n" - " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", - guest_num_pages, vm_get_max_gfn(vm), vcpus, - vcpu_memory_bytes); - - host_page_size = getpagesize(); - TEST_ASSERT(vcpu_memory_bytes % host_page_size == 0, - "Guest memory size is not host page size aligned."); + vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size); - guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * - guest_page_size; - guest_test_phys_mem &= ~(host_page_size - 1); + perf_test_args.wr_fract = 1; -#ifdef __s390x__ - /* Align to 1M (segment size) */ - guest_test_phys_mem &= ~((1 << 20) - 1); -#endif - - pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); - - /* Add an extra memory slot for testing demand paging */ - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, - guest_test_phys_mem, - TEST_MEM_SLOT_INDEX, - guest_num_pages, 0); - - /* Do mapping for the demand paging memory slot */ - virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); - - ucall_init(vm, NULL); - - guest_data_prototype = malloc(host_page_size); + guest_data_prototype = malloc(perf_test_args.host_page_size); TEST_ASSERT(guest_data_prototype, "Failed to allocate buffer for guest data pattern"); - memset(guest_data_prototype, 0xAB, host_page_size); + memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size); - vcpu_threads = malloc(vcpus * sizeof(*vcpu_threads)); + vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); TEST_ASSERT(vcpu_threads, "Memory allocation failed"); + add_vcpus(vm, nr_vcpus, guest_percpu_mem_size); + if (use_uffd) { uffd_handler_threads = - malloc(vcpus * sizeof(*uffd_handler_threads)); + malloc(nr_vcpus * sizeof(*uffd_handler_threads)); TEST_ASSERT(uffd_handler_threads, "Memory allocation failed"); - uffd_args = malloc(vcpus * sizeof(*uffd_args)); + uffd_args = malloc(nr_vcpus * sizeof(*uffd_args)); TEST_ASSERT(uffd_args, "Memory allocation failed"); - pipefds = malloc(sizeof(int) * vcpus * 2); + pipefds = malloc(sizeof(int) * nr_vcpus * 2); TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd"); - } - - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { - vm_paddr_t vcpu_gpa; - void *vcpu_hva; - vm_vcpu_add_default(vm, vcpu_id, guest_code); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + vm_paddr_t vcpu_gpa; + void *vcpu_hva; - vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes); - PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", - vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes); + vcpu_gpa = guest_test_phys_mem + (vcpu_id * guest_percpu_mem_size); + PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_gpa, vcpu_gpa + guest_percpu_mem_size); - /* Cache the HVA pointer of the region */ - vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); + /* Cache the HVA pointer of the region */ + vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); - if (use_uffd) { /* * Set up user fault fd to handle demand paging * requests. @@ -456,53 +309,41 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd, &uffd_handler_threads[vcpu_id], pipefds[vcpu_id * 2], uffd_delay, &uffd_args[vcpu_id], - vcpu_hva, vcpu_memory_bytes); + vcpu_hva, guest_percpu_mem_size); if (r < 0) exit(-r); } - -#ifdef __x86_64__ - vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid()); -#endif - - vcpu_args[vcpu_id].vm = vm; - vcpu_args[vcpu_id].vcpu_id = vcpu_id; - vcpu_args[vcpu_id].gva = guest_test_virt_mem + - (vcpu_id * vcpu_memory_bytes); - vcpu_args[vcpu_id].pages = vcpu_memory_bytes / guest_page_size; } /* Export the shared variables to the guest */ - sync_global_to_guest(vm, host_page_size); - sync_global_to_guest(vm, guest_page_size); - sync_global_to_guest(vm, vcpu_args); + sync_global_to_guest(vm, perf_test_args); pr_info("Finished creating vCPUs and starting uffd threads\n"); clock_gettime(CLOCK_MONOTONIC, &start); - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &vcpu_args[vcpu_id]); + &perf_test_args.vcpu_args[vcpu_id]); } pr_info("Started all vCPUs\n"); /* Wait for the vcpu threads to quit */ - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { pthread_join(vcpu_threads[vcpu_id], NULL); PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id); } - pr_info("All vCPU threads joined\n"); + ts_diff = timespec_diff_now(start); - clock_gettime(CLOCK_MONOTONIC, &end); + pr_info("All vCPU threads joined\n"); if (use_uffd) { char c; /* Tell the user fault fd handler threads to quit */ - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { r = write(pipefds[vcpu_id * 2 + 1], &c, 1); TEST_ASSERT(r == 1, "Unable to write to pipefd"); @@ -510,11 +351,11 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd, } } - ts_diff = timespec_sub(end, start); pr_info("Total guest execution time: %ld.%.9lds\n", ts_diff.tv_sec, ts_diff.tv_nsec); pr_info("Overall demand paging rate: %f pgs/sec\n", - guest_num_pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); + perf_test_args.vcpu_args[0].pages * nr_vcpus / + ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); ucall_uninit(vm); kvm_vm_free(vm); @@ -568,9 +409,8 @@ static void help(char *name) int main(int argc, char *argv[]) { + int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); bool mode_selected = false; - uint64_t vcpu_memory_bytes = DEFAULT_GUEST_TEST_MEM_SIZE; - int vcpus = 1; unsigned int mode; int opt, i; bool use_uffd = false; @@ -619,15 +459,12 @@ int main(int argc, char *argv[]) "A negative UFFD delay is not supported."); break; case 'b': - vcpu_memory_bytes = parse_size(optarg); + guest_percpu_mem_size = parse_size(optarg); break; case 'v': - vcpus = atoi(optarg); - TEST_ASSERT(vcpus > 0, - "Must have a positive number of vCPUs"); - TEST_ASSERT(vcpus <= MAX_VCPUS, - "This test does not currently support\n" - "more than %d vCPUs.", MAX_VCPUS); + nr_vcpus = atoi(optarg); + TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, + "Invalid number of vcpus, must be between 1 and %d", max_vcpus); break; case 'h': default: @@ -642,7 +479,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(guest_modes[i].supported, "Guest mode ID %d (%s) not supported.", i, vm_guest_mode_string(i)); - run_test(i, use_uffd, uffd_delay, vcpus, vcpu_memory_bytes); + run_test(i, use_uffd, uffd_delay); } return 0; diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c new file mode 100644 index 000000000000..85c9b8f73142 --- /dev/null +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -0,0 +1,376 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KVM dirty page logging performance test + * + * Based on dirty_log_test.c + * + * Copyright (C) 2018, Red Hat, Inc. + * Copyright (C) 2020, Google, Inc. + */ + +#define _GNU_SOURCE /* for program_invocation_name */ + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <time.h> +#include <pthread.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> + +#include "kvm_util.h" +#include "perf_test_util.h" +#include "processor.h" +#include "test_util.h" + +/* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/ +#define TEST_HOST_LOOP_N 2UL + +/* Host variables */ +static bool host_quit; +static uint64_t iteration; +static uint64_t vcpu_last_completed_iteration[MAX_VCPUS]; + +static void *vcpu_worker(void *data) +{ + int ret; + struct kvm_vm *vm = perf_test_args.vm; + uint64_t pages_count = 0; + struct kvm_run *run; + struct timespec start; + struct timespec ts_diff; + struct timespec total = (struct timespec){0}; + struct timespec avg; + struct vcpu_args *vcpu_args = (struct vcpu_args *)data; + int vcpu_id = vcpu_args->vcpu_id; + + vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + run = vcpu_state(vm, vcpu_id); + + while (!READ_ONCE(host_quit)) { + uint64_t current_iteration = READ_ONCE(iteration); + + clock_gettime(CLOCK_MONOTONIC, &start); + ret = _vcpu_run(vm, vcpu_id); + ts_diff = timespec_diff_now(start); + + TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); + TEST_ASSERT(get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC, + "Invalid guest sync status: exit_reason=%s\n", + exit_reason_str(run->exit_reason)); + + pr_debug("Got sync event from vCPU %d\n", vcpu_id); + vcpu_last_completed_iteration[vcpu_id] = current_iteration; + pr_debug("vCPU %d updated last completed iteration to %lu\n", + vcpu_id, vcpu_last_completed_iteration[vcpu_id]); + + if (current_iteration) { + pages_count += vcpu_args->pages; + total = timespec_add(total, ts_diff); + pr_debug("vCPU %d iteration %lu dirty memory time: %ld.%.9lds\n", + vcpu_id, current_iteration, ts_diff.tv_sec, + ts_diff.tv_nsec); + } else { + pr_debug("vCPU %d iteration %lu populate memory time: %ld.%.9lds\n", + vcpu_id, current_iteration, ts_diff.tv_sec, + ts_diff.tv_nsec); + } + + while (current_iteration == READ_ONCE(iteration) && + !READ_ONCE(host_quit)) {} + } + + avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_id]); + pr_debug("\nvCPU %d dirtied 0x%lx pages over %lu iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id], + total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec); + + return NULL; +} + +#ifdef USE_CLEAR_DIRTY_LOG +static u64 dirty_log_manual_caps; +#endif + +static void run_test(enum vm_guest_mode mode, unsigned long iterations, + uint64_t phys_offset, int wr_fract) +{ + pthread_t *vcpu_threads; + struct kvm_vm *vm; + unsigned long *bmap; + uint64_t guest_num_pages; + uint64_t host_num_pages; + int vcpu_id; + struct timespec start; + struct timespec ts_diff; + struct timespec get_dirty_log_total = (struct timespec){0}; + struct timespec vcpu_dirty_total = (struct timespec){0}; + struct timespec avg; +#ifdef USE_CLEAR_DIRTY_LOG + struct kvm_enable_cap cap = {}; + struct timespec clear_dirty_log_total = (struct timespec){0}; +#endif + + vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size); + + perf_test_args.wr_fract = wr_fract; + + guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm); + guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); + host_num_pages = vm_num_host_pages(mode, guest_num_pages); + bmap = bitmap_alloc(host_num_pages); + +#ifdef USE_CLEAR_DIRTY_LOG + cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; + cap.args[0] = dirty_log_manual_caps; + vm_enable_cap(vm, &cap); +#endif + + vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); + TEST_ASSERT(vcpu_threads, "Memory allocation failed"); + + add_vcpus(vm, nr_vcpus, guest_percpu_mem_size); + + sync_global_to_guest(vm, perf_test_args); + + /* Start the iterations */ + iteration = 0; + host_quit = false; + + clock_gettime(CLOCK_MONOTONIC, &start); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, + &perf_test_args.vcpu_args[vcpu_id]); + } + + /* Allow the vCPU to populate memory */ + pr_debug("Starting iteration %lu - Populating\n", iteration); + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration) + pr_debug("Waiting for vcpu_last_completed_iteration == %lu\n", + iteration); + + ts_diff = timespec_diff_now(start); + pr_info("Populate memory time: %ld.%.9lds\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + /* Enable dirty logging */ + clock_gettime(CLOCK_MONOTONIC, &start); + vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, + KVM_MEM_LOG_DIRTY_PAGES); + ts_diff = timespec_diff_now(start); + pr_info("Enabling dirty logging time: %ld.%.9lds\n\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + while (iteration < iterations) { + /* + * Incrementing the iteration number will start the vCPUs + * dirtying memory again. + */ + clock_gettime(CLOCK_MONOTONIC, &start); + iteration++; + + pr_debug("Starting iteration %lu\n", iteration); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration) + pr_debug("Waiting for vCPU %d vcpu_last_completed_iteration == %lu\n", + vcpu_id, iteration); + } + + ts_diff = timespec_diff_now(start); + vcpu_dirty_total = timespec_add(vcpu_dirty_total, ts_diff); + pr_info("Iteration %lu dirty memory time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); + + clock_gettime(CLOCK_MONOTONIC, &start); + kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); + + ts_diff = timespec_diff_now(start); + get_dirty_log_total = timespec_add(get_dirty_log_total, + ts_diff); + pr_info("Iteration %lu get dirty log time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); + +#ifdef USE_CLEAR_DIRTY_LOG + clock_gettime(CLOCK_MONOTONIC, &start); + kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, + host_num_pages); + + ts_diff = timespec_diff_now(start); + clear_dirty_log_total = timespec_add(clear_dirty_log_total, + ts_diff); + pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); +#endif + } + + /* Tell the vcpu thread to quit */ + host_quit = true; + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) + pthread_join(vcpu_threads[vcpu_id], NULL); + + /* Disable dirty logging */ + clock_gettime(CLOCK_MONOTONIC, &start); + vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, 0); + ts_diff = timespec_diff_now(start); + pr_info("Disabling dirty logging time: %ld.%.9lds\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + avg = timespec_div(get_dirty_log_total, iterations); + pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + iterations, get_dirty_log_total.tv_sec, + get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); + +#ifdef USE_CLEAR_DIRTY_LOG + avg = timespec_div(clear_dirty_log_total, iterations); + pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + iterations, clear_dirty_log_total.tv_sec, + clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); +#endif + + free(bmap); + free(vcpu_threads); + ucall_uninit(vm); + kvm_vm_free(vm); +} + +struct guest_mode { + bool supported; + bool enabled; +}; +static struct guest_mode guest_modes[NUM_VM_MODES]; + +#define guest_mode_init(mode, supported, enabled) ({ \ + guest_modes[mode] = (struct guest_mode){ supported, enabled }; \ +}) + +static void help(char *name) +{ + int i; + + puts(""); + printf("usage: %s [-h] [-i iterations] [-p offset] " + "[-m mode] [-b vcpu bytes] [-v vcpus]\n", name); + puts(""); + printf(" -i: specify iteration counts (default: %"PRIu64")\n", + TEST_HOST_LOOP_N); + printf(" -p: specify guest physical test memory offset\n" + " Warning: a low offset can conflict with the loaded test code.\n"); + printf(" -m: specify the guest mode ID to test " + "(default: test all supported modes)\n" + " This option may be used multiple times.\n" + " Guest mode IDs:\n"); + for (i = 0; i < NUM_VM_MODES; ++i) { + printf(" %d: %s%s\n", i, vm_guest_mode_string(i), + guest_modes[i].supported ? " (supported)" : ""); + } + printf(" -b: specify the size of the memory region which should be\n" + " dirtied by each vCPU. e.g. 10M or 3G.\n" + " (default: 1G)\n"); + printf(" -f: specify the fraction of pages which should be written to\n" + " as opposed to simply read, in the form\n" + " 1/<fraction of pages to write>.\n" + " (default: 1 i.e. all pages are written to.)\n"); + printf(" -v: specify the number of vCPUs to run.\n"); + puts(""); + exit(0); +} + +int main(int argc, char *argv[]) +{ + unsigned long iterations = TEST_HOST_LOOP_N; + bool mode_selected = false; + uint64_t phys_offset = 0; + unsigned int mode; + int opt, i; + int wr_fract = 1; + +#ifdef USE_CLEAR_DIRTY_LOG + dirty_log_manual_caps = + kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + if (!dirty_log_manual_caps) { + print_skip("KVM_CLEAR_DIRTY_LOG not available"); + exit(KSFT_SKIP); + } + dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); +#endif + +#ifdef __x86_64__ + guest_mode_init(VM_MODE_PXXV48_4K, true, true); +#endif +#ifdef __aarch64__ + guest_mode_init(VM_MODE_P40V48_4K, true, true); + guest_mode_init(VM_MODE_P40V48_64K, true, true); + + { + unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); + + if (limit >= 52) + guest_mode_init(VM_MODE_P52V48_64K, true, true); + if (limit >= 48) { + guest_mode_init(VM_MODE_P48V48_4K, true, true); + guest_mode_init(VM_MODE_P48V48_64K, true, true); + } + } +#endif +#ifdef __s390x__ + guest_mode_init(VM_MODE_P40V48_4K, true, true); +#endif + + while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:")) != -1) { + switch (opt) { + case 'i': + iterations = strtol(optarg, NULL, 10); + break; + case 'p': + phys_offset = strtoull(optarg, NULL, 0); + break; + case 'm': + if (!mode_selected) { + for (i = 0; i < NUM_VM_MODES; ++i) + guest_modes[i].enabled = false; + mode_selected = true; + } + mode = strtoul(optarg, NULL, 10); + TEST_ASSERT(mode < NUM_VM_MODES, + "Guest mode ID %d too big", mode); + guest_modes[mode].enabled = true; + break; + case 'b': + guest_percpu_mem_size = parse_size(optarg); + break; + case 'f': + wr_fract = atoi(optarg); + TEST_ASSERT(wr_fract >= 1, + "Write fraction cannot be less than one"); + break; + case 'v': + nr_vcpus = atoi(optarg); + TEST_ASSERT(nr_vcpus > 0, + "Must have a positive number of vCPUs"); + TEST_ASSERT(nr_vcpus <= MAX_VCPUS, + "This test does not currently support\n" + "more than %d vCPUs.", MAX_VCPUS); + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + TEST_ASSERT(iterations >= 2, "The test should have at least two iterations"); + + pr_info("Test iterations: %"PRIu64"\n", iterations); + + for (i = 0; i < NUM_VM_MODES; ++i) { + if (!guest_modes[i].enabled) + continue; + TEST_ASSERT(guest_modes[i].supported, + "Guest mode ID %d (%s) not supported.", + i, vm_guest_mode_string(i)); + run_test(i, iterations, phys_offset, wr_fract); + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 752ec158ac59..54da9cc20db4 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -128,6 +128,78 @@ static uint64_t host_dirty_count; static uint64_t host_clear_count; static uint64_t host_track_next_count; +enum log_mode_t { + /* Only use KVM_GET_DIRTY_LOG for logging */ + LOG_MODE_DIRTY_LOG = 0, + + /* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */ + LOG_MODE_CLEAR_LOG = 1, + + LOG_MODE_NUM, + + /* Run all supported modes */ + LOG_MODE_ALL = LOG_MODE_NUM, +}; + +/* Mode of logging to test. Default is to run all supported modes */ +static enum log_mode_t host_log_mode_option = LOG_MODE_ALL; +/* Logging mode for current run */ +static enum log_mode_t host_log_mode; + +static bool clear_log_supported(void) +{ + return kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); +} + +static void clear_log_create_vm_done(struct kvm_vm *vm) +{ + struct kvm_enable_cap cap = {}; + u64 manual_caps; + + manual_caps = kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + TEST_ASSERT(manual_caps, "MANUAL_CAPS is zero!"); + manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); + cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; + cap.args[0] = manual_caps; + vm_enable_cap(vm, &cap); +} + +static void dirty_log_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + kvm_vm_get_dirty_log(vm, slot, bitmap); +} + +static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + kvm_vm_get_dirty_log(vm, slot, bitmap); + kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages); +} + +struct log_mode { + const char *name; + /* Return true if this mode is supported, otherwise false */ + bool (*supported)(void); + /* Hook when the vm creation is done (before vcpu creation) */ + void (*create_vm_done)(struct kvm_vm *vm); + /* Hook to collect the dirty pages into the bitmap provided */ + void (*collect_dirty_pages) (struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages); +} log_modes[LOG_MODE_NUM] = { + { + .name = "dirty-log", + .collect_dirty_pages = dirty_log_collect_dirty_pages, + }, + { + .name = "clear-log", + .supported = clear_log_supported, + .create_vm_done = clear_log_create_vm_done, + .collect_dirty_pages = clear_log_collect_dirty_pages, + }, +}; + /* * We use this bitmap to track some pages that should have its dirty * bit set in the _next_ iteration. For example, if we detected the @@ -137,6 +209,44 @@ static uint64_t host_track_next_count; */ static unsigned long *host_bmap_track; +static void log_modes_dump(void) +{ + int i; + + printf("all"); + for (i = 0; i < LOG_MODE_NUM; i++) + printf(", %s", log_modes[i].name); + printf("\n"); +} + +static bool log_mode_supported(void) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->supported) + return mode->supported(); + + return true; +} + +static void log_mode_create_vm_done(struct kvm_vm *vm) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->create_vm_done) + mode->create_vm_done(vm); +} + +static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + TEST_ASSERT(mode->collect_dirty_pages != NULL, + "collect_dirty_pages() is required for any log mode!"); + mode->collect_dirty_pages(vm, slot, bitmap, num_pages); +} + static void generate_random_array(uint64_t *guest_array, uint64_t size) { uint64_t i; @@ -195,7 +305,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap) page); } - if (test_bit_le(page, bmap)) { + if (test_and_clear_bit_le(page, bmap)) { host_dirty_count++; /* * If the bit is set, the value written onto @@ -252,11 +362,12 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - vm = _vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); + vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); kvm_vm_elf_load(vm, program_invocation_name, 0, 0); #ifdef __x86_64__ vm_create_irqchip(vm); #endif + log_mode_create_vm_done(vm); vm_vcpu_add_default(vm, vcpuid, guest_code); return vm; } @@ -264,10 +375,6 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, #define DIRTY_MEM_BITS 30 /* 1G */ #define PAGE_SHIFT_4K 12 -#ifdef USE_CLEAR_DIRTY_LOG -static u64 dirty_log_manual_caps; -#endif - static void run_test(enum vm_guest_mode mode, unsigned long iterations, unsigned long interval, uint64_t phys_offset) { @@ -275,6 +382,12 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, struct kvm_vm *vm; unsigned long *bmap; + if (!log_mode_supported()) { + print_skip("Log mode '%s' not supported", + log_modes[host_log_mode].name); + return; + } + /* * We reserve page table for 2 times of extra dirty mem which * will definitely cover the original (1G+) test range. Here @@ -317,14 +430,6 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, bmap = bitmap_alloc(host_num_pages); host_bmap_track = bitmap_alloc(host_num_pages); -#ifdef USE_CLEAR_DIRTY_LOG - struct kvm_enable_cap cap = {}; - - cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; - cap.args[0] = dirty_log_manual_caps; - vm_enable_cap(vm, &cap); -#endif - /* Add an extra memory slot for testing dirty logging */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, guest_test_phys_mem, @@ -362,11 +467,8 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, while (iteration < iterations) { /* Give the vcpu thread some time to dirty some pages */ usleep(interval * 1000); - kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); -#ifdef USE_CLEAR_DIRTY_LOG - kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, - host_num_pages); -#endif + log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX, + bmap, host_num_pages); vm_dirty_log_verify(mode, bmap); iteration++; sync_global_to_guest(vm, iteration); @@ -410,6 +512,9 @@ static void help(char *name) TEST_HOST_LOOP_INTERVAL); printf(" -p: specify guest physical test memory offset\n" " Warning: a low offset can conflict with the loaded test code.\n"); + printf(" -M: specify the host logging mode " + "(default: run all log modes). Supported modes: \n\t"); + log_modes_dump(); printf(" -m: specify the guest mode ID to test " "(default: test all supported modes)\n" " This option may be used multiple times.\n" @@ -429,18 +534,7 @@ int main(int argc, char *argv[]) bool mode_selected = false; uint64_t phys_offset = 0; unsigned int mode; - int opt, i; - -#ifdef USE_CLEAR_DIRTY_LOG - dirty_log_manual_caps = - kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); - if (!dirty_log_manual_caps) { - print_skip("KVM_CLEAR_DIRTY_LOG not available"); - exit(KSFT_SKIP); - } - dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | - KVM_DIRTY_LOG_INITIALLY_SET); -#endif + int opt, i, j; #ifdef __x86_64__ guest_mode_init(VM_MODE_PXXV48_4K, true, true); @@ -464,7 +558,7 @@ int main(int argc, char *argv[]) guest_mode_init(VM_MODE_P40V48_4K, true, true); #endif - while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) { + while ((opt = getopt(argc, argv, "hi:I:p:m:M:")) != -1) { switch (opt) { case 'i': iterations = strtol(optarg, NULL, 10); @@ -486,6 +580,26 @@ int main(int argc, char *argv[]) "Guest mode ID %d too big", mode); guest_modes[mode].enabled = true; break; + case 'M': + if (!strcmp(optarg, "all")) { + host_log_mode_option = LOG_MODE_ALL; + break; + } + for (i = 0; i < LOG_MODE_NUM; i++) { + if (!strcmp(optarg, log_modes[i].name)) { + pr_info("Setting log mode to: '%s'\n", + optarg); + host_log_mode_option = i; + break; + } + } + if (i == LOG_MODE_NUM) { + printf("Log mode '%s' invalid. Please choose " + "from: ", optarg); + log_modes_dump(); + exit(1); + } + break; case 'h': default: help(argv[0]); @@ -507,7 +621,18 @@ int main(int argc, char *argv[]) TEST_ASSERT(guest_modes[i].supported, "Guest mode ID %d (%s) not supported.", i, vm_guest_mode_string(i)); - run_test(i, iterations, interval, phys_offset); + if (host_log_mode_option == LOG_MODE_ALL) { + /* Run each log mode */ + for (j = 0; j < LOG_MODE_NUM; j++) { + pr_info("Testing Log Mode '%s'\n", + log_modes[j].name); + host_log_mode = j; + run_test(i, iterations, interval, phys_offset); + } + } else { + host_log_mode = host_log_mode_option; + run_test(i, iterations, interval, phys_offset); + } } return 0; diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 919e161dd289..7d29aa786959 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -63,9 +63,11 @@ enum vm_mem_backing_src_type { int kvm_check_cap(long cap); int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); +int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_enable_cap *cap); +void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); -struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); void kvm_vm_free(struct kvm_vm *vmp); void kvm_vm_restart(struct kvm_vm *vmp, int perm); void kvm_vm_release(struct kvm_vm *vmp); @@ -149,6 +151,7 @@ void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_guest_debug *debug); void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_mp_state *mp_state); +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); @@ -294,6 +297,8 @@ int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd); memcpy(&(g), _p, sizeof(g)); \ }) +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid); + /* Common ucalls */ enum { UCALL_NONE, diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h new file mode 100644 index 000000000000..2618052057b1 --- /dev/null +++ b/tools/testing/selftests/kvm/include/perf_test_util.h @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * tools/testing/selftests/kvm/include/perf_test_util.h + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef SELFTEST_KVM_PERF_TEST_UTIL_H +#define SELFTEST_KVM_PERF_TEST_UTIL_H + +#include "kvm_util.h" +#include "processor.h" + +#define MAX_VCPUS 512 + +#define PAGE_SHIFT_4K 12 +#define PTES_PER_4K_PT 512 + +#define TEST_MEM_SLOT_INDEX 1 + +/* Default guest test virtual memory offset */ +#define DEFAULT_GUEST_TEST_MEM 0xc0000000 + +#define DEFAULT_PER_VCPU_MEM_SIZE (1 << 30) /* 1G */ + +/* + * Guest physical memory offset of the testing memory slot. + * This will be set to the topmost valid physical address minus + * the test memory size. + */ +static uint64_t guest_test_phys_mem; + +/* + * Guest virtual memory offset of the testing memory slot. + * Must not conflict with identity mapped test code. + */ +static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; +static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; + +/* Number of VCPUs for the test */ +static int nr_vcpus = 1; + +struct vcpu_args { + uint64_t gva; + uint64_t pages; + + /* Only used by the host userspace part of the vCPU thread */ + int vcpu_id; +}; + +struct perf_test_args { + struct kvm_vm *vm; + uint64_t host_page_size; + uint64_t guest_page_size; + int wr_fract; + + struct vcpu_args vcpu_args[MAX_VCPUS]; +}; + +static struct perf_test_args perf_test_args; + +/* + * Continuously write to the first 8 bytes of each page in the + * specified region. + */ +static void guest_code(uint32_t vcpu_id) +{ + struct vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + uint64_t gva; + uint64_t pages; + int i; + + /* Make sure vCPU args data structure is not corrupt. */ + GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id); + + gva = vcpu_args->gva; + pages = vcpu_args->pages; + + while (true) { + for (i = 0; i < pages; i++) { + uint64_t addr = gva + (i * perf_test_args.guest_page_size); + + if (i % perf_test_args.wr_fract == 0) + *(uint64_t *)addr = 0x0123456789ABCDEF; + else + READ_ONCE(*(uint64_t *)addr); + } + + GUEST_SYNC(1); + } +} + +static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus, + uint64_t vcpu_memory_bytes) +{ + struct kvm_vm *vm; + uint64_t pages = DEFAULT_GUEST_PHY_PAGES; + uint64_t guest_num_pages; + + /* Account for a few pages per-vCPU for stacks */ + pages += DEFAULT_STACK_PGS * vcpus; + + /* + * Reserve twice the ammount of memory needed to map the test region and + * the page table / stacks region, at 4k, for page tables. Do the + * calculation with 4K page size: the smallest of all archs. (e.g., 64K + * page size guest will need even less memory for page tables). + */ + pages += (2 * pages) / PTES_PER_4K_PT; + pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) / + PTES_PER_4K_PT; + pages = vm_adjust_num_guest_pages(mode, pages); + + pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); + + vm = vm_create(mode, pages, O_RDWR); + kvm_vm_elf_load(vm, program_invocation_name, 0, 0); +#ifdef __x86_64__ + vm_create_irqchip(vm); +#endif + + perf_test_args.vm = vm; + perf_test_args.guest_page_size = vm_get_page_size(vm); + perf_test_args.host_page_size = getpagesize(); + + TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0, + "Guest memory size is not guest page size aligned."); + + guest_num_pages = (vcpus * vcpu_memory_bytes) / + perf_test_args.guest_page_size; + guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); + + /* + * If there should be more memory in the guest test region than there + * can be pages in the guest, it will definitely cause problems. + */ + TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), + "Requested more guest memory than address space allows.\n" + " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", + guest_num_pages, vm_get_max_gfn(vm), vcpus, + vcpu_memory_bytes); + + TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0, + "Guest memory size is not host page size aligned."); + + guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * + perf_test_args.guest_page_size; + guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1); + +#ifdef __s390x__ + /* Align to 1M (segment size) */ + guest_test_phys_mem &= ~((1 << 20) - 1); +#endif + + pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); + + /* Add an extra memory slot for testing */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + guest_test_phys_mem, + TEST_MEM_SLOT_INDEX, + guest_num_pages, 0); + + /* Do mapping for the demand paging memory slot */ + virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); + + ucall_init(vm, NULL); + + return vm; +} + +static void add_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes) +{ + vm_paddr_t vcpu_gpa; + struct vcpu_args *vcpu_args; + int vcpu_id; + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + + vm_vcpu_add_default(vm, vcpu_id, guest_code); + +#ifdef __x86_64__ + vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid()); +#endif + + vcpu_args->vcpu_id = vcpu_id; + vcpu_args->gva = guest_test_virt_mem + + (vcpu_id * vcpu_memory_bytes); + vcpu_args->pages = vcpu_memory_bytes / + perf_test_args.guest_page_size; + + vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes); + pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes); + } +} + +#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 5eb01bf51b86..ffffa560436b 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -64,5 +64,7 @@ int64_t timespec_to_ns(struct timespec ts); struct timespec timespec_add_ns(struct timespec ts, int64_t ns); struct timespec timespec_add(struct timespec ts1, struct timespec ts2); struct timespec timespec_sub(struct timespec ts1, struct timespec ts2); +struct timespec timespec_diff_now(struct timespec start); +struct timespec timespec_div(struct timespec ts, int divisor); #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 82b7fe16a824..8e61340b3911 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -36,6 +36,8 @@ #define X86_CR4_SMAP (1ul << 21) #define X86_CR4_PKE (1ul << 22) +#define UNEXPECTED_VECTOR_PORT 0xfff0u + /* General Registers in 64-Bit Mode */ struct gpr64_regs { u64 rax; @@ -59,7 +61,7 @@ struct gpr64_regs { struct desc64 { uint16_t limit0; uint16_t base0; - unsigned base1:8, s:1, type:4, dpl:2, p:1; + unsigned base1:8, type:4, s:1, dpl:2, p:1; unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8; uint32_t base3; uint32_t zero1; @@ -239,6 +241,11 @@ static inline struct desc_ptr get_idt(void) return idt; } +static inline void outl(uint16_t port, uint32_t value) +{ + __asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value)); +} + #define SET_XMM(__var, __xmm) \ asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm) @@ -338,6 +345,35 @@ uint32_t kvm_get_cpuid_max_basic(void); uint32_t kvm_get_cpuid_max_extended(void); void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); +struct ex_regs { + uint64_t rax, rcx, rdx, rbx; + uint64_t rbp, rsi, rdi; + uint64_t r8, r9, r10, r11; + uint64_t r12, r13, r14, r15; + uint64_t vector; + uint64_t error_code; + uint64_t rip; + uint64_t cs; + uint64_t rflags; +}; + +void vm_init_descriptor_tables(struct kvm_vm *vm); +void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid); +void vm_handle_exception(struct kvm_vm *vm, int vector, + void (*handler)(struct ex_regs *)); + +/* + * set_cpuid() - overwrites a matching cpuid entry with the provided value. + * matches based on ent->function && ent->index. returns true + * if a match was found and successfully overwritten. + * @cpuid: the kvm cpuid list to modify. + * @ent: cpuid entry to insert + */ +bool set_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *ent); + +uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t a3); + /* * Basic CPU control in CR0 */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 2afa6618b396..d6c32c328e9a 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -350,3 +350,7 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) va_end(ap); } + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ +} diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index c8e0ec20d3bf..2f37b90ee1a9 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -94,6 +94,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_MMIO && run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) { vm_vaddr_t gva; diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 3327cebc1095..126c6727a6b0 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -86,6 +86,34 @@ int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap) return ret; } +/* VCPU Enable Capability + * + * Input Args: + * vm - Virtual Machine + * vcpu_id - VCPU + * cap - Capability + * + * Output Args: None + * + * Return: On success, 0. On failure a TEST_ASSERT failure is produced. + * + * Enables a capability (KVM_CAP_*) on the VCPU. + */ +int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_enable_cap *cap) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpu_id); + int r; + + TEST_ASSERT(vcpu, "cannot find vcpu %d", vcpu_id); + + r = ioctl(vcpu->fd, KVM_ENABLE_CAP, cap); + TEST_ASSERT(!r, "KVM_ENABLE_CAP vCPU ioctl failed,\n" + " rc: %i, errno: %i", r, errno); + + return r; +} + static void vm_open(struct kvm_vm *vm, int perm) { vm->kvm_fd = open(KVM_DEV_PATH, perm); @@ -152,7 +180,7 @@ _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) * descriptor to control the created VM is created with the permissions * given by perm (e.g. O_RDWR). */ -struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) +struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) { struct kvm_vm *vm; @@ -243,11 +271,6 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) return vm; } -struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) -{ - return _vm_create(mode, phy_pages, perm); -} - /* * VM Restart * @@ -1204,6 +1227,9 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) do { rc = ioctl(vcpu->fd, KVM_RUN, NULL); } while (rc == -1 && errno == EINTR); + + assert_on_unhandled_exception(vm, vcpuid); + return rc; } @@ -1261,6 +1287,35 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, } /* + * VM VCPU Get Reg List + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * + * Output Args: + * None + * + * Return: + * A pointer to an allocated struct kvm_reg_list + * + * Get the list of guest registers which are supported for + * KVM_GET_ONE_REG/KVM_SET_ONE_REG calls + */ +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list; + int ret; + + ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, ®_list_n); + TEST_ASSERT(ret == -1 && errno == E2BIG, "KVM_GET_REG_LIST n=0"); + reg_list = calloc(1, sizeof(*reg_list) + reg_list_n.n * sizeof(__u64)); + reg_list->n = reg_list_n.n; + vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, reg_list); + return reg_list; +} + +/* * VM VCPU Regs Get * * Input Args: diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 2ef446520748..f07d383d03a1 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -50,6 +50,8 @@ struct kvm_vm { vm_paddr_t pgd; vm_vaddr_t gdt; vm_vaddr_t tss; + vm_vaddr_t idt; + vm_vaddr_t handlers; }; struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid); diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index a88c5d665725..7349bb2e1a24 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -241,3 +241,7 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n", indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr); } + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ +} diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390x/ucall.c index fd589dc9bfab..9d3b0f15249a 100644 --- a/tools/testing/selftests/kvm/lib/s390x/ucall.c +++ b/tools/testing/selftests/kvm/lib/s390x/ucall.c @@ -38,6 +38,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_S390_SIEIC && run->s390_sieic.icptcode == 4 && (run->s390_sieic.ipa >> 8) == 0x83 && /* 0x83 means DIAGNOSE */ diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 689e97c27ee2..8e04c0b1608e 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -4,10 +4,13 @@ * * Copyright (C) 2020, Google LLC. */ -#include <stdlib.h> + +#include <assert.h> #include <ctype.h> #include <limits.h> -#include <assert.h> +#include <stdlib.h> +#include <time.h> + #include "test_util.h" /* @@ -81,6 +84,21 @@ struct timespec timespec_sub(struct timespec ts1, struct timespec ts2) return timespec_add_ns((struct timespec){0}, ns1 - ns2); } +struct timespec timespec_diff_now(struct timespec start) +{ + struct timespec end; + + clock_gettime(CLOCK_MONOTONIC, &end); + return timespec_sub(end, start); +} + +struct timespec timespec_div(struct timespec ts, int divisor) +{ + int64_t ns = timespec_to_ns(ts) / divisor; + + return timespec_add_ns((struct timespec){0}, ns); +} + void print_skip(const char *fmt, ...) { va_list ap; diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S new file mode 100644 index 000000000000..aaf7bc7d2ce1 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S @@ -0,0 +1,81 @@ +handle_exception: + push %r15 + push %r14 + push %r13 + push %r12 + push %r11 + push %r10 + push %r9 + push %r8 + + push %rdi + push %rsi + push %rbp + push %rbx + push %rdx + push %rcx + push %rax + mov %rsp, %rdi + + call route_exception + + pop %rax + pop %rcx + pop %rdx + pop %rbx + pop %rbp + pop %rsi + pop %rdi + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %r12 + pop %r13 + pop %r14 + pop %r15 + + /* Discard vector and error code. */ + add $16, %rsp + iretq + +/* + * Build the handle_exception wrappers which push the vector/error code on the + * stack and an array of pointers to those wrappers. + */ +.pushsection .rodata +.globl idt_handlers +idt_handlers: +.popsection + +.macro HANDLERS has_error from to + vector = \from + .rept \to - \from + 1 + .align 8 + + /* Fetch current address and append it to idt_handlers. */ + current_handler = . +.pushsection .rodata +.quad current_handler +.popsection + + .if ! \has_error + pushq $0 + .endif + pushq $vector + jmp handle_exception + vector = vector + 1 + .endr +.endm + +.global idt_handler_code +idt_handler_code: + HANDLERS has_error=0 from=0 to=7 + HANDLERS has_error=1 from=8 to=8 + HANDLERS has_error=0 from=9 to=9 + HANDLERS has_error=1 from=10 to=14 + HANDLERS has_error=0 from=15 to=16 + HANDLERS has_error=1 from=17 to=17 + HANDLERS has_error=0 from=18 to=255 + +.section .note.GNU-stack, "", %progbits diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index f6eb34eaa0d2..d10c5c05bdf0 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -12,9 +12,18 @@ #include "../kvm_util_internal.h" #include "processor.h" +#ifndef NUM_INTERRUPTS +#define NUM_INTERRUPTS 256 +#endif + +#define DEFAULT_CODE_SELECTOR 0x8 +#define DEFAULT_DATA_SELECTOR 0x10 + /* Minimum physical address used for virtual translation tables. */ #define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 +vm_vaddr_t exception_handlers; + /* Virtual translation table structure declarations */ struct pageMapL4Entry { uint64_t present:1; @@ -392,11 +401,12 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp) desc->limit0 = segp->limit & 0xFFFF; desc->base0 = segp->base & 0xFFFF; desc->base1 = segp->base >> 16; - desc->s = segp->s; desc->type = segp->type; + desc->s = segp->s; desc->dpl = segp->dpl; desc->p = segp->present; desc->limit1 = segp->limit >> 16; + desc->avl = segp->avl; desc->l = segp->l; desc->db = segp->db; desc->g = segp->g; @@ -556,9 +566,9 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX); kvm_seg_set_unusable(&sregs.ldt); - kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs); - kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds); - kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es); + kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs); + kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds); + kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es); kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot); break; @@ -1118,3 +1128,131 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) *va_bits = (entry->eax >> 8) & 0xff; } } + +struct idt_entry { + uint16_t offset0; + uint16_t selector; + uint16_t ist : 3; + uint16_t : 5; + uint16_t type : 4; + uint16_t : 1; + uint16_t dpl : 2; + uint16_t p : 1; + uint16_t offset1; + uint32_t offset2; uint32_t reserved; +}; + +static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, + int dpl, unsigned short selector) +{ + struct idt_entry *base = + (struct idt_entry *)addr_gva2hva(vm, vm->idt); + struct idt_entry *e = &base[vector]; + + memset(e, 0, sizeof(*e)); + e->offset0 = addr; + e->selector = selector; + e->ist = 0; + e->type = 14; + e->dpl = dpl; + e->p = 1; + e->offset1 = addr >> 16; + e->offset2 = addr >> 32; +} + +void kvm_exit_unexpected_vector(uint32_t value) +{ + outl(UNEXPECTED_VECTOR_PORT, value); +} + +void route_exception(struct ex_regs *regs) +{ + typedef void(*handler)(struct ex_regs *); + handler *handlers = (handler *)exception_handlers; + + if (handlers && handlers[regs->vector]) { + handlers[regs->vector](regs); + return; + } + + kvm_exit_unexpected_vector(regs->vector); +} + +void vm_init_descriptor_tables(struct kvm_vm *vm) +{ + extern void *idt_handlers; + int i; + + vm->idt = vm_vaddr_alloc(vm, getpagesize(), 0x2000, 0, 0); + vm->handlers = vm_vaddr_alloc(vm, 256 * sizeof(void *), 0x2000, 0, 0); + /* Handlers have the same address in both address spaces.*/ + for (i = 0; i < NUM_INTERRUPTS; i++) + set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0, + DEFAULT_CODE_SELECTOR); +} + +void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct kvm_sregs sregs; + + vcpu_sregs_get(vm, vcpuid, &sregs); + sregs.idt.base = vm->idt; + sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1; + sregs.gdt.base = vm->gdt; + sregs.gdt.limit = getpagesize() - 1; + kvm_seg_set_kernel_data_64bit(NULL, DEFAULT_DATA_SELECTOR, &sregs.gs); + vcpu_sregs_set(vm, vcpuid, &sregs); + *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; +} + +void vm_handle_exception(struct kvm_vm *vm, int vector, + void (*handler)(struct ex_regs *)) +{ + vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers); + + handlers[vector] = (vm_vaddr_t)handler; +} + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ + if (vcpu_state(vm, vcpuid)->exit_reason == KVM_EXIT_IO + && vcpu_state(vm, vcpuid)->io.port == UNEXPECTED_VECTOR_PORT + && vcpu_state(vm, vcpuid)->io.size == 4) { + /* Grab pointer to io data */ + uint32_t *data = (void *)vcpu_state(vm, vcpuid) + + vcpu_state(vm, vcpuid)->io.data_offset; + + TEST_ASSERT(false, + "Unexpected vectored event in guest (vector:0x%x)", + *data); + } +} + +bool set_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 *ent) +{ + int i; + + for (i = 0; i < cpuid->nent; i++) { + struct kvm_cpuid_entry2 *cur = &cpuid->entries[i]; + + if (cur->function != ent->function || cur->index != ent->index) + continue; + + memcpy(cur, ent, sizeof(struct kvm_cpuid_entry2)); + return true; + } + + return false; +} + +uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t a3) +{ + uint64_t r; + + asm volatile("vmcall" + : "=a"(r) + : "b"(a0), "c"(a1), "d"(a2), "S"(a3)); + return r; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c index da4d89ad5419..a3489973e290 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c +++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c @@ -40,6 +40,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) { struct kvm_regs regs; diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index b3ece55a2da6..6f441dd9f33c 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -156,14 +156,23 @@ static void guest_code_move_memory_region(void) GUEST_SYNC(0); /* - * Spin until the memory region is moved to a misaligned address. This - * may or may not trigger MMIO, as the window where the memslot is - * invalid is quite small. + * Spin until the memory region starts getting moved to a + * misaligned address. + * Every region move may or may not trigger MMIO, as the + * window where the memslot is invalid is usually quite small. */ val = guest_spin_on_val(0); GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val); - /* Spin until the memory region is realigned. */ + /* Spin until the misaligning memory region move completes. */ + val = guest_spin_on_val(MMIO_VAL); + GUEST_ASSERT_1(val == 1 || val == 0, val); + + /* Spin until the memory region starts to get re-aligned. */ + val = guest_spin_on_val(0); + GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val); + + /* Spin until the re-aligning memory region move completes. */ val = guest_spin_on_val(MMIO_VAL); GUEST_ASSERT_1(val == 1, val); diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c new file mode 100644 index 000000000000..b10a27485bad --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020, Google LLC. + * + * Tests for KVM paravirtual feature disablement + */ +#include <asm/kvm_para.h> +#include <linux/kvm_para.h> +#include <stdint.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +extern unsigned char rdmsr_start; +extern unsigned char rdmsr_end; + +static u64 do_rdmsr(u32 idx) +{ + u32 lo, hi; + + asm volatile("rdmsr_start: rdmsr;" + "rdmsr_end:" + : "=a"(lo), "=c"(hi) + : "c"(idx)); + + return (((u64) hi) << 32) | lo; +} + +extern unsigned char wrmsr_start; +extern unsigned char wrmsr_end; + +static void do_wrmsr(u32 idx, u64 val) +{ + u32 lo, hi; + + lo = val; + hi = val >> 32; + + asm volatile("wrmsr_start: wrmsr;" + "wrmsr_end:" + : : "a"(lo), "c"(idx), "d"(hi)); +} + +static int nr_gp; + +static void guest_gp_handler(struct ex_regs *regs) +{ + unsigned char *rip = (unsigned char *)regs->rip; + bool r, w; + + r = rip == &rdmsr_start; + w = rip == &wrmsr_start; + GUEST_ASSERT(r || w); + + nr_gp++; + + if (r) + regs->rip = (uint64_t)&rdmsr_end; + else + regs->rip = (uint64_t)&wrmsr_end; +} + +struct msr_data { + uint32_t idx; + const char *name; +}; + +#define TEST_MSR(msr) { .idx = msr, .name = #msr } +#define UCALL_PR_MSR 0xdeadbeef +#define PR_MSR(msr) ucall(UCALL_PR_MSR, 1, msr) + +/* + * KVM paravirtual msrs to test. Expect a #GP if any of these msrs are read or + * written, as the KVM_CPUID_FEATURES leaf is cleared. + */ +static struct msr_data msrs_to_test[] = { + TEST_MSR(MSR_KVM_SYSTEM_TIME), + TEST_MSR(MSR_KVM_SYSTEM_TIME_NEW), + TEST_MSR(MSR_KVM_WALL_CLOCK), + TEST_MSR(MSR_KVM_WALL_CLOCK_NEW), + TEST_MSR(MSR_KVM_ASYNC_PF_EN), + TEST_MSR(MSR_KVM_STEAL_TIME), + TEST_MSR(MSR_KVM_PV_EOI_EN), + TEST_MSR(MSR_KVM_POLL_CONTROL), + TEST_MSR(MSR_KVM_ASYNC_PF_INT), + TEST_MSR(MSR_KVM_ASYNC_PF_ACK), +}; + +static void test_msr(struct msr_data *msr) +{ + PR_MSR(msr); + do_rdmsr(msr->idx); + GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + + nr_gp = 0; + do_wrmsr(msr->idx, 0); + GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + nr_gp = 0; +} + +struct hcall_data { + uint64_t nr; + const char *name; +}; + +#define TEST_HCALL(hc) { .nr = hc, .name = #hc } +#define UCALL_PR_HCALL 0xdeadc0de +#define PR_HCALL(hc) ucall(UCALL_PR_HCALL, 1, hc) + +/* + * KVM hypercalls to test. Expect -KVM_ENOSYS when called, as the corresponding + * features have been cleared in KVM_CPUID_FEATURES. + */ +static struct hcall_data hcalls_to_test[] = { + TEST_HCALL(KVM_HC_KICK_CPU), + TEST_HCALL(KVM_HC_SEND_IPI), + TEST_HCALL(KVM_HC_SCHED_YIELD), +}; + +static void test_hcall(struct hcall_data *hc) +{ + uint64_t r; + + PR_HCALL(hc); + r = kvm_hypercall(hc->nr, 0, 0, 0, 0); + GUEST_ASSERT(r == -KVM_ENOSYS); +} + +static void guest_main(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(msrs_to_test); i++) { + test_msr(&msrs_to_test[i]); + } + + for (i = 0; i < ARRAY_SIZE(hcalls_to_test); i++) { + test_hcall(&hcalls_to_test[i]); + } + + GUEST_DONE(); +} + +static void clear_kvm_cpuid_features(struct kvm_cpuid2 *cpuid) +{ + struct kvm_cpuid_entry2 ent = {0}; + + ent.function = KVM_CPUID_FEATURES; + TEST_ASSERT(set_cpuid(cpuid, &ent), + "failed to clear KVM_CPUID_FEATURES leaf"); +} + +static void pr_msr(struct ucall *uc) +{ + struct msr_data *msr = (struct msr_data *)uc->args[0]; + + pr_info("testing msr: %s (%#x)\n", msr->name, msr->idx); +} + +static void pr_hcall(struct ucall *uc) +{ + struct hcall_data *hc = (struct hcall_data *)uc->args[0]; + + pr_info("testing hcall: %s (%lu)\n", hc->name, hc->nr); +} + +static void handle_abort(struct ucall *uc) +{ + TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], + __FILE__, uc->args[1]); +} + +#define VCPU_ID 0 + +static void enter_guest(struct kvm_vm *vm) +{ + struct kvm_run *run; + struct ucall uc; + int r; + + run = vcpu_state(vm, VCPU_ID); + + while (true) { + r = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_PR_MSR: + pr_msr(&uc); + break; + case UCALL_PR_HCALL: + pr_hcall(&uc); + break; + case UCALL_ABORT: + handle_abort(&uc); + return; + case UCALL_DONE: + return; + } + } +} + +int main(void) +{ + struct kvm_enable_cap cap = {0}; + struct kvm_cpuid2 *best; + struct kvm_vm *vm; + + if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) { + pr_info("will skip kvm paravirt restriction tests.\n"); + return 0; + } + + vm = vm_create_default(VCPU_ID, 0, guest_main); + + cap.cap = KVM_CAP_ENFORCE_PV_FEATURE_CPUID; + cap.args[0] = 1; + vcpu_enable_cap(vm, VCPU_ID, &cap); + + best = kvm_get_supported_cpuid(); + clear_kvm_cpuid_features(best); + vcpu_set_cpuid(vm, VCPU_ID, best); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_handle_exception(vm, GP_VECTOR, guest_gp_handler); + + enter_guest(vm); + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index fb5c55dd6df8..02b0b9ead40b 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -256,6 +256,28 @@ setup_cmd_nsb() fi } +setup_cmd_nsc() +{ + local cmd="$*" + local rc + + run_cmd_nsc ${cmd} + rc=$? + if [ $rc -ne 0 ]; then + # show user the command if not done so already + if [ "$VERBOSE" = "0" ]; then + echo "setup command: $cmd" + fi + echo "failed. stopping tests" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue" + read a + fi + exit $rc + fi +} + # set sysctl values in NS-A set_sysctl() { @@ -471,6 +493,36 @@ setup() sleep 1 } +setup_lla_only() +{ + # make sure we are starting with a clean slate + kill_procs + cleanup 2>/dev/null + + log_debug "Configuring network namespaces" + set -e + + create_ns ${NSA} "-" "-" + create_ns ${NSB} "-" "-" + create_ns ${NSC} "-" "-" + connect_ns ${NSA} ${NSA_DEV} "-" "-" \ + ${NSB} ${NSB_DEV} "-" "-" + connect_ns ${NSA} ${NSA_DEV2} "-" "-" \ + ${NSC} ${NSC_DEV} "-" "-" + + NSA_LINKIP6=$(get_linklocal ${NSA} ${NSA_DEV}) + NSB_LINKIP6=$(get_linklocal ${NSB} ${NSB_DEV}) + NSC_LINKIP6=$(get_linklocal ${NSC} ${NSC_DEV}) + + create_vrf ${NSA} ${VRF} ${VRF_TABLE} "-" "-" + ip -netns ${NSA} link set dev ${NSA_DEV} vrf ${VRF} + ip -netns ${NSA} link set dev ${NSA_DEV2} vrf ${VRF} + + set +e + + sleep 1 +} + ################################################################################ # IPv4 @@ -3787,10 +3839,53 @@ use_case_br() setup_cmd_nsb ip li del vlan100 2>/dev/null } +# VRF only. +# ns-A device is connected to both ns-B and ns-C on a single VRF but only has +# LLA on the interfaces +use_case_ping_lla_multi() +{ + setup_lla_only + # only want reply from ns-A + setup_cmd_nsb sysctl -qw net.ipv6.icmp.echo_ignore_multicast=1 + setup_cmd_nsc sysctl -qw net.ipv6.icmp.echo_ignore_multicast=1 + + log_start + run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV} + log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Pre cycle, ping out ns-B" + + run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV} + log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Pre cycle, ping out ns-C" + + # cycle/flap the first ns-A interface + setup_cmd ip link set ${NSA_DEV} down + setup_cmd ip link set ${NSA_DEV} up + sleep 1 + + log_start + run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV} + log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV}, ping out ns-B" + run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV} + log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV}, ping out ns-C" + + # cycle/flap the second ns-A interface + setup_cmd ip link set ${NSA_DEV2} down + setup_cmd ip link set ${NSA_DEV2} up + sleep 1 + + log_start + run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV} + log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV2}, ping out ns-B" + run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV} + log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV2}, ping out ns-C" +} + use_cases() { log_section "Use cases" + log_subsection "Device enslaved to bridge" use_case_br + log_subsection "Ping LLA with multiple interfaces" + use_case_ping_lla_multi } ################################################################################ diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index db3d4a8b5a4c..76a24052f4b4 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -113,6 +113,9 @@ static void do_poll(int fd, int timeout_ms) interrupted = true; break; } + + /* no events and more time to wait, do poll again */ + continue; } if (pfd.revents != POLLIN) error(1, errno, "poll: 0x%x expected 0x%x\n", diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index 052b5a775dc2..b7d188fc87c7 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -42,6 +42,11 @@ int perf_event_enable(int fd); int perf_event_disable(int fd); int perf_event_reset(int fd); +struct perf_event_read { + __u64 nr; + __u64 l1d_misses; +}; + #if !defined(__GLIBC_PREREQ) || !__GLIBC_PREREQ(2, 30) #include <unistd.h> #include <sys/syscall.h> diff --git a/tools/testing/selftests/powerpc/security/.gitignore b/tools/testing/selftests/powerpc/security/.gitignore index f795e06f5ae3..4257a1f156bb 100644 --- a/tools/testing/selftests/powerpc/security/.gitignore +++ b/tools/testing/selftests/powerpc/security/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only rfi_flush +entry_flush diff --git a/tools/testing/selftests/powerpc/security/Makefile b/tools/testing/selftests/powerpc/security/Makefile index eadbbff50be6..f25e854fe370 100644 --- a/tools/testing/selftests/powerpc/security/Makefile +++ b/tools/testing/selftests/powerpc/security/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0+ -TEST_GEN_PROGS := rfi_flush spectre_v2 +TEST_GEN_PROGS := rfi_flush entry_flush spectre_v2 top_srcdir = ../../../../.. CFLAGS += -I../../../../../usr/include @@ -11,3 +11,5 @@ $(TEST_GEN_PROGS): ../harness.c ../utils.c $(OUTPUT)/spectre_v2: CFLAGS += -m64 $(OUTPUT)/spectre_v2: ../pmu/event.c branch_loops.S +$(OUTPUT)/rfi_flush: flush_utils.c +$(OUTPUT)/entry_flush: flush_utils.c diff --git a/tools/testing/selftests/powerpc/security/entry_flush.c b/tools/testing/selftests/powerpc/security/entry_flush.c new file mode 100644 index 000000000000..78cf914fa321 --- /dev/null +++ b/tools/testing/selftests/powerpc/security/entry_flush.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Copyright 2018 IBM Corporation. + */ + +#define __SANE_USERSPACE_TYPES__ + +#include <sys/types.h> +#include <stdint.h> +#include <malloc.h> +#include <unistd.h> +#include <signal.h> +#include <stdlib.h> +#include <string.h> +#include <stdio.h> +#include "utils.h" +#include "flush_utils.h" + +int entry_flush_test(void) +{ + char *p; + int repetitions = 10; + int fd, passes = 0, iter, rc = 0; + struct perf_event_read v; + __u64 l1d_misses_total = 0; + unsigned long iterations = 100000, zero_size = 24 * 1024; + unsigned long l1d_misses_expected; + int rfi_flush_orig; + int entry_flush, entry_flush_orig; + + SKIP_IF(geteuid() != 0); + + // The PMU event we use only works on Power7 or later + SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); + + if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { + perror("Unable to read powerpc/rfi_flush debugfs file"); + SKIP_IF(1); + } + + if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + perror("Unable to read powerpc/entry_flush debugfs file"); + SKIP_IF(1); + } + + if (rfi_flush_orig != 0) { + if (write_debugfs_file("powerpc/rfi_flush", 0) < 0) { + perror("error writing to powerpc/rfi_flush debugfs file"); + FAIL_IF(1); + } + } + + entry_flush = entry_flush_orig; + + fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1); + FAIL_IF(fd < 0); + + p = (char *)memalign(zero_size, CACHELINE_SIZE); + + FAIL_IF(perf_event_enable(fd)); + + // disable L1 prefetching + set_dscr(1); + + iter = repetitions; + + /* + * We expect to see l1d miss for each cacheline access when entry_flush + * is set. Allow a small variation on this. + */ + l1d_misses_expected = iterations * (zero_size / CACHELINE_SIZE - 2); + +again: + FAIL_IF(perf_event_reset(fd)); + + syscall_loop(p, iterations, zero_size); + + FAIL_IF(read(fd, &v, sizeof(v)) != sizeof(v)); + + if (entry_flush && v.l1d_misses >= l1d_misses_expected) + passes++; + else if (!entry_flush && v.l1d_misses < (l1d_misses_expected / 2)) + passes++; + + l1d_misses_total += v.l1d_misses; + + while (--iter) + goto again; + + if (passes < repetitions) { + printf("FAIL (L1D misses with entry_flush=%d: %llu %c %lu) [%d/%d failures]\n", + entry_flush, l1d_misses_total, entry_flush ? '<' : '>', + entry_flush ? repetitions * l1d_misses_expected : + repetitions * l1d_misses_expected / 2, + repetitions - passes, repetitions); + rc = 1; + } else { + printf("PASS (L1D misses with entry_flush=%d: %llu %c %lu) [%d/%d pass]\n", + entry_flush, l1d_misses_total, entry_flush ? '>' : '<', + entry_flush ? repetitions * l1d_misses_expected : + repetitions * l1d_misses_expected / 2, + passes, repetitions); + } + + if (entry_flush == entry_flush_orig) { + entry_flush = !entry_flush_orig; + if (write_debugfs_file("powerpc/entry_flush", entry_flush) < 0) { + perror("error writing to powerpc/entry_flush debugfs file"); + return 1; + } + iter = repetitions; + l1d_misses_total = 0; + passes = 0; + goto again; + } + + perf_event_disable(fd); + close(fd); + + set_dscr(0); + + if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { + perror("unable to restore original value of powerpc/rfi_flush debugfs file"); + return 1; + } + + if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + perror("unable to restore original value of powerpc/entry_flush debugfs file"); + return 1; + } + + return rc; +} + +int main(int argc, char *argv[]) +{ + return test_harness(entry_flush_test, "entry_flush_test"); +} diff --git a/tools/testing/selftests/powerpc/security/flush_utils.c b/tools/testing/selftests/powerpc/security/flush_utils.c new file mode 100644 index 000000000000..0c3c4c40c7fb --- /dev/null +++ b/tools/testing/selftests/powerpc/security/flush_utils.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Copyright 2018 IBM Corporation. + */ + +#define __SANE_USERSPACE_TYPES__ + +#include <sys/types.h> +#include <stdint.h> +#include <unistd.h> +#include <signal.h> +#include <stdlib.h> +#include <string.h> +#include <stdio.h> +#include "utils.h" +#include "flush_utils.h" + +static inline __u64 load(void *addr) +{ + __u64 tmp; + + asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr)); + + return tmp; +} + +void syscall_loop(char *p, unsigned long iterations, + unsigned long zero_size) +{ + for (unsigned long i = 0; i < iterations; i++) { + for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE) + load(p + j); + getppid(); + } +} + +static void sigill_handler(int signr, siginfo_t *info, void *unused) +{ + static int warned; + ucontext_t *ctx = (ucontext_t *)unused; + unsigned long *pc = &UCONTEXT_NIA(ctx); + + /* mtspr 3,RS to check for move to DSCR below */ + if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) { + if (!warned++) + printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n"); + *pc += 4; + } else { + printf("SIGILL at %p\n", pc); + abort(); + } +} + +void set_dscr(unsigned long val) +{ + static int init; + struct sigaction sa; + + if (!init) { + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = sigill_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGILL, &sa, NULL)) + perror("sigill_handler"); + init = 1; + } + + asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); +} diff --git a/tools/testing/selftests/powerpc/security/flush_utils.h b/tools/testing/selftests/powerpc/security/flush_utils.h new file mode 100644 index 000000000000..07a5eb301466 --- /dev/null +++ b/tools/testing/selftests/powerpc/security/flush_utils.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +/* + * Copyright 2018 IBM Corporation. + */ + +#ifndef _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H +#define _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H + +#define CACHELINE_SIZE 128 + +void syscall_loop(char *p, unsigned long iterations, + unsigned long zero_size); + +void set_dscr(unsigned long val); + +#endif /* _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H */ diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c index 93a65bd1f231..7565fd786640 100644 --- a/tools/testing/selftests/powerpc/security/rfi_flush.c +++ b/tools/testing/selftests/powerpc/security/rfi_flush.c @@ -10,71 +10,12 @@ #include <stdint.h> #include <malloc.h> #include <unistd.h> -#include <signal.h> #include <stdlib.h> #include <string.h> #include <stdio.h> #include "utils.h" +#include "flush_utils.h" -#define CACHELINE_SIZE 128 - -struct perf_event_read { - __u64 nr; - __u64 l1d_misses; -}; - -static inline __u64 load(void *addr) -{ - __u64 tmp; - - asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr)); - - return tmp; -} - -static void syscall_loop(char *p, unsigned long iterations, - unsigned long zero_size) -{ - for (unsigned long i = 0; i < iterations; i++) { - for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE) - load(p + j); - getppid(); - } -} - -static void sigill_handler(int signr, siginfo_t *info, void *unused) -{ - static int warned = 0; - ucontext_t *ctx = (ucontext_t *)unused; - unsigned long *pc = &UCONTEXT_NIA(ctx); - - /* mtspr 3,RS to check for move to DSCR below */ - if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) { - if (!warned++) - printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n"); - *pc += 4; - } else { - printf("SIGILL at %p\n", pc); - abort(); - } -} - -static void set_dscr(unsigned long val) -{ - static int init = 0; - struct sigaction sa; - - if (!init) { - memset(&sa, 0, sizeof(sa)); - sa.sa_sigaction = sigill_handler; - sa.sa_flags = SA_SIGINFO; - if (sigaction(SIGILL, &sa, NULL)) - perror("sigill_handler"); - init = 1; - } - - asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); -} int rfi_flush_test(void) { @@ -85,19 +26,33 @@ int rfi_flush_test(void) __u64 l1d_misses_total = 0; unsigned long iterations = 100000, zero_size = 24 * 1024; unsigned long l1d_misses_expected; - int rfi_flush_org, rfi_flush; + int rfi_flush_orig, rfi_flush; + int have_entry_flush, entry_flush_orig; SKIP_IF(geteuid() != 0); // The PMU event we use only works on Power7 or later SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); - if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_org)) { + if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) { perror("Unable to read powerpc/rfi_flush debugfs file"); SKIP_IF(1); } - rfi_flush = rfi_flush_org; + if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) { + have_entry_flush = 0; + } else { + have_entry_flush = 1; + + if (entry_flush_orig != 0) { + if (write_debugfs_file("powerpc/entry_flush", 0) < 0) { + perror("error writing to powerpc/entry_flush debugfs file"); + return 1; + } + } + } + + rfi_flush = rfi_flush_orig; fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1); FAIL_IF(fd < 0); @@ -106,6 +61,7 @@ int rfi_flush_test(void) FAIL_IF(perf_event_enable(fd)); + // disable L1 prefetching set_dscr(1); iter = repetitions; @@ -147,8 +103,8 @@ again: repetitions * l1d_misses_expected / 2, passes, repetitions); - if (rfi_flush == rfi_flush_org) { - rfi_flush = !rfi_flush_org; + if (rfi_flush == rfi_flush_orig) { + rfi_flush = !rfi_flush_orig; if (write_debugfs_file("powerpc/rfi_flush", rfi_flush) < 0) { perror("error writing to powerpc/rfi_flush debugfs file"); return 1; @@ -164,11 +120,19 @@ again: set_dscr(0); - if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_org) < 0) { + if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) { perror("unable to restore original value of powerpc/rfi_flush debugfs file"); return 1; } + if (have_entry_flush) { + if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) { + perror("unable to restore original value of powerpc/entry_flush " + "debugfs file"); + return 1; + } + } + return rc; } diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 4a180439ee9e..26c72f2b61b1 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1758,10 +1758,10 @@ TEST_F(TRACE_poke, getpid_runs_normally) * and the code is stored as a positive value. \ */ \ if (_result < 0) { \ - SYSCALL_RET(_regs) = -result; \ + SYSCALL_RET(_regs) = -_result; \ (_regs).ccr |= 0x10000000; \ } else { \ - SYSCALL_RET(_regs) = result; \ + SYSCALL_RET(_regs) = _result; \ (_regs).ccr &= ~0x10000000; \ } \ } while (0) @@ -1804,8 +1804,8 @@ TEST_F(TRACE_poke, getpid_runs_normally) #define SYSCALL_RET(_regs) (_regs).a[(_regs).windowbase * 4 + 2] #elif defined(__sh__) # define ARCH_REGS struct pt_regs -# define SYSCALL_NUM(_regs) (_regs).gpr[3] -# define SYSCALL_RET(_regs) (_regs).gpr[0] +# define SYSCALL_NUM(_regs) (_regs).regs[3] +# define SYSCALL_RET(_regs) (_regs).regs[0] #else # error "Do not know how to find your architecture's registers and syscalls" #endif diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index c33a7aac27ff..b71828df5a6d 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -59,6 +59,7 @@ CONFIG_NET_IFE_SKBPRIO=m CONFIG_NET_IFE_SKBTCINDEX=m CONFIG_NET_SCH_FIFO=y CONFIG_NET_SCH_ETS=m +CONFIG_NET_SCH_RED=m # ## Network testing diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json index bb543bf69d69..361235ad574b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@ -100,7 +100,7 @@ ], "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop", "expExitCode": "0", - "verifyCmd": "$TC filter show terse dev $DEV2 ingress", + "verifyCmd": "$TC -br filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower.*handle", "matchCount": "1", "teardown": [ @@ -119,7 +119,7 @@ ], "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop", "expExitCode": "0", - "verifyCmd": "$TC filter show terse dev $DEV2 ingress", + "verifyCmd": "$TC -br filter show dev $DEV2 ingress", "matchPattern": " dst_mac e4:11:22:11:4a:51", "matchCount": "0", "teardown": [ diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 30873b19d04b..691893afc15d 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -60,9 +60,13 @@ ifeq ($(CAN_BUILD_X86_64),1) TEST_GEN_FILES += $(BINARIES_64) endif else + +ifneq (,$(findstring $(ARCH),powerpc)) TEST_GEN_FILES += protection_keys endif +endif + ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64)) TEST_GEN_FILES += va_128TBswitch TEST_GEN_FILES += virtual_address_range diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 9b0912a01777..c4425597769a 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -206,19 +206,19 @@ static int hugetlb_release_pages(char *rel_area) return ret; } - static void hugetlb_allocate_area(void **alloc_area) { void *area_alias = NULL; char **alloc_area_alias; + *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, (map_shared ? MAP_SHARED : MAP_PRIVATE) | MAP_HUGETLB, huge_fd, *alloc_area == area_src ? 0 : nr_pages * page_size); if (*alloc_area == MAP_FAILED) { - fprintf(stderr, "mmap of hugetlbfs file failed\n"); - *alloc_area = NULL; + perror("mmap of hugetlbfs file failed"); + goto fail; } if (map_shared) { @@ -227,14 +227,11 @@ static void hugetlb_allocate_area(void **alloc_area) huge_fd, *alloc_area == area_src ? 0 : nr_pages * page_size); if (area_alias == MAP_FAILED) { - if (munmap(*alloc_area, nr_pages * page_size) < 0) { - perror("hugetlb munmap"); - exit(1); - } - *alloc_area = NULL; - return; + perror("mmap of hugetlb file alias failed"); + goto fail_munmap; } } + if (*alloc_area == area_src) { huge_fd_off0 = *alloc_area; alloc_area_alias = &area_src_alias; @@ -243,6 +240,16 @@ static void hugetlb_allocate_area(void **alloc_area) } if (area_alias) *alloc_area_alias = area_alias; + + return; + +fail_munmap: + if (munmap(*alloc_area, nr_pages * page_size) < 0) { + perror("hugetlb munmap"); + exit(1); + } +fail: + *alloc_area = NULL; } static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset) |