diff --git a/.mailmap b/.mailmap index 87a8bbdbf749..85b93cdefc87 100644 --- a/.mailmap +++ b/.mailmap @@ -237,6 +237,7 @@ Maxime Ripard Mayuresh Janorkar Michael Buesch Michel Dänzer +Miguel Ojeda Mike Rapoport Mike Rapoport Mike Rapoport diff --git a/CREDITS b/CREDITS index be097156bd71..cef83b958cbe 100644 --- a/CREDITS +++ b/CREDITS @@ -2841,14 +2841,11 @@ S: Subiaco, 6008 S: Perth, Western Australia S: Australia -N: Miguel Ojeda Sandonis -E: miguel.ojeda.sandonis@gmail.com -W: http://miguelojeda.es -W: http://jair.lab.fi.uva.es/~migojed/ +N: Miguel Ojeda +E: ojeda@kernel.org +W: https://ojeda.dev D: Author of the ks0108, cfag12864b and cfag12864bfb auxiliary display drivers. D: Maintainer of the auxiliary display drivers tree (drivers/auxdisplay/*) -S: C/ Mieses 20, 9-B -S: Valladolid 47009 S: Spain N: Peter Oruba diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory index 246a45b96d22..d8b0f80b9e33 100644 --- a/Documentation/ABI/testing/sysfs-devices-memory +++ b/Documentation/ABI/testing/sysfs-devices-memory @@ -13,21 +13,22 @@ What: /sys/devices/system/memory/memoryX/removable Date: June 2008 Contact: Badari Pulavarty Description: - The file /sys/devices/system/memory/memoryX/removable - indicates whether this memory block is removable or not. - This is useful for a user-level agent to determine - identify removable sections of the memory before attempting - potentially expensive hot-remove memory operation + The file /sys/devices/system/memory/memoryX/removable is a + legacy interface used to indicated whether a memory block is + likely to be offlineable or not. Newer kernel versions return + "1" if and only if the kernel supports memory offlining. Users: hotplug memory remove tools http://www.ibm.com/developerworks/wikis/display/LinuxP/powerpc-utils + lsmem/chmem part of util-linux What: /sys/devices/system/memory/memoryX/phys_device Date: September 2008 Contact: Badari Pulavarty Description: The file /sys/devices/system/memory/memoryX/phys_device - is read-only and is designed to show the name of physical - memory device. Implementation is currently incomplete. + is read-only; it is a legacy interface only ever used on s390x + to expose the covered storage increment. +Users: Legacy s390-tools lsmem/chmem What: /sys/devices/system/memory/memoryX/phys_index Date: September 2008 @@ -43,23 +44,25 @@ Date: September 2008 Contact: Badari Pulavarty Description: The file /sys/devices/system/memory/memoryX/state - is read-write. When read, its contents show the - online/offline state of the memory section. When written, - root can toggle the the online/offline state of a removable - memory section (see removable file description above) - using the following commands:: + is read-write. When read, it returns the online/offline + state of the memory block. When written, root can toggle + the online/offline state of a memory block using the following + commands:: # echo online > /sys/devices/system/memory/memoryX/state # echo offline > /sys/devices/system/memory/memoryX/state - For example, if /sys/devices/system/memory/memory22/removable - contains a value of 1 and - /sys/devices/system/memory/memory22/state contains the - string "online" the following command can be executed by - by root to offline that section:: - - # echo offline > /sys/devices/system/memory/memory22/state + On newer kernel versions, advanced states can be specified + when onlining to select a target zone: "online_movable" + selects the movable zone. "online_kernel" selects the + applicable kernel zone (DMA, DMA32, or Normal). However, + after successfully setting one of the advanced states, + reading the file will return "online"; the zone information + can be obtained via "valid_zones" instead. + While onlining is unlikely to fail, there are no guarantees + that offlining will succeed. Offlining is more likely to + succeed if "valid_zones" indicates "Movable". Users: hotplug memory remove tools http://www.ibm.com/developerworks/wikis/display/LinuxP/powerpc-utils @@ -69,8 +72,19 @@ Date: July 2014 Contact: Zhang Zhen Description: The file /sys/devices/system/memory/memoryX/valid_zones is - read-only and is designed to show which zone this memory - block can be onlined to. + read-only. + + For online memory blocks, it returns in which zone memory + provided by a memory block is managed. If multiple zones + apply (not applicable for hotplugged memory), "None" is returned + and the memory block cannot be offlined. + + For offline memory blocks, it returns by which zone memory + provided by a memory block can be managed when onlining. + The first returned zone ("default") will be used when setting + the state of an offline memory block to "online". Only one of + the kernel zones (DMA, DMA32, Normal) is applicable for a single + memory block. What: /sys/devices/system/memoryX/nodeY Date: October 2009 diff --git a/Documentation/ABI/testing/sysfs-devices-xenbus b/Documentation/ABI/testing/sysfs-devices-xenbus new file mode 100644 index 000000000000..fd796cb4f315 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-xenbus @@ -0,0 +1,41 @@ +What: /sys/devices/*/xenbus/event_channels +Date: February 2021 +Contact: Xen Developers mailing list +Description: + Number of Xen event channels associated with a kernel based + paravirtualized device frontend or backend. + +What: /sys/devices/*/xenbus/events +Date: February 2021 +Contact: Xen Developers mailing list +Description: + Total number of Xen events received for a Xen pv device + frontend or backend. + +What: /sys/devices/*/xenbus/jiffies_eoi_delayed +Date: February 2021 +Contact: Xen Developers mailing list +Description: + Summed up time in jiffies the EOI of an interrupt for a Xen + pv device has been delayed in order to avoid stalls due to + event storms. This value rising is a first sign for a rogue + other end of the pv device. + +What: /sys/devices/*/xenbus/spurious_events +Date: February 2021 +Contact: Xen Developers mailing list +Description: + Number of events received for a Xen pv device which did not + require any action. Too many spurious events in a row will + trigger delayed EOI processing. + +What: /sys/devices/*/xenbus/spurious_threshold +Date: February 2021 +Contact: Xen Developers mailing list +Description: + Controls the tolerated number of subsequent spurious events + before delayed EOI processing is triggered for a Xen pv + device. Default is 1. This can be modified in case the other + end of the pv device is issuing spurious events on a regular + basis and is known not to be malicious on purpose. Raising + the value for such cases can improve pv device performance. diff --git a/Documentation/ABI/testing/sysfs-firmware-acpi b/Documentation/ABI/testing/sysfs-firmware-acpi index b16d30a71709..819939d858c9 100644 --- a/Documentation/ABI/testing/sysfs-firmware-acpi +++ b/Documentation/ABI/testing/sysfs-firmware-acpi @@ -1,3 +1,46 @@ +What: /sys/firmware/acpi/fpdt/ +Date: Jan 2021 +Contact: Zhang Rui +Description: + ACPI Firmware Performance Data Table (FPDT) provides + information for firmware performance data for system boot, + S3 suspend and S3 resume. This sysfs entry contains the + performance data retrieved from the FPDT. + + boot: + firmware_start_ns: Timer value logged at the beginning + of firmware image execution. In nanoseconds. + bootloader_load_ns: Timer value logged just prior to + loading the OS boot loader into memory. + In nanoseconds. + bootloader_launch_ns: Timer value logged just prior to + launching the currently loaded OS boot loader + image. In nanoseconds. + exitbootservice_start_ns: Timer value logged at the + point when the OS loader calls the + ExitBootServices function for UEFI compatible + firmware. In nanoseconds. + exitbootservice_end_ns: Timer value logged at the point + just prior to the OS loader gaining control + back from the ExitBootServices function for + UEFI compatible firmware. In nanoseconds. + suspend: + suspend_start_ns: Timer value recorded at the previous + OS write to SLP_TYP upon entry to S3. In + nanoseconds. + suspend_end_ns: Timer value recorded at the previous + firmware write to SLP_TYP used to trigger + hardware entry to S3. In nanoseconds. + resume: + resume_count: A count of the number of S3 resume cycles + since the last full boot sequence. + resume_avg_ns: Average timer value of all resume cycles + logged since the last full boot sequence, + including the most recent resume. In nanoseconds. + resume_prev_ns: Timer recorded at the end of the previous + platform runtime firmware S3 resume, just prior to + handoff to the OS waking vector. In nanoseconds. + What: /sys/firmware/acpi/bgrt/ Date: January 2012 Contact: Matthew Garrett diff --git a/Documentation/ABI/testing/sysfs-platform_profile b/Documentation/ABI/testing/sysfs-platform_profile index 9d6b89b66cca..dae9c8941905 100644 --- a/Documentation/ABI/testing/sysfs-platform_profile +++ b/Documentation/ABI/testing/sysfs-platform_profile @@ -5,13 +5,17 @@ Description: This file contains a space-separated list of profiles supported for Drivers must use the following standard profile-names: - ============ ============================================ - low-power Low power consumption - cool Cooler operation - quiet Quieter operation - balanced Balance between low power consumption and performance - performance High performance operation - ============ ============================================ + ==================== ======================================== + low-power Low power consumption + cool Cooler operation + quiet Quieter operation + balanced Balance between low power consumption + and performance + balanced-performance Balance between performance and low + power consumption with a slight bias + towards performance + performance High performance operation + ==================== ======================================== Userspace may expect drivers to offer more than one of these standard profile names. diff --git a/Documentation/admin-guide/auxdisplay/cfag12864b.rst b/Documentation/admin-guide/auxdisplay/cfag12864b.rst index 18c2865bd322..da385d851acc 100644 --- a/Documentation/admin-guide/auxdisplay/cfag12864b.rst +++ b/Documentation/admin-guide/auxdisplay/cfag12864b.rst @@ -3,7 +3,7 @@ cfag12864b LCD Driver Documentation =================================== :License: GPLv2 -:Author & Maintainer: Miguel Ojeda Sandonis +:Author & Maintainer: Miguel Ojeda :Date: 2006-10-27 diff --git a/Documentation/admin-guide/auxdisplay/ks0108.rst b/Documentation/admin-guide/auxdisplay/ks0108.rst index c0b7faf73136..a7d3fe509373 100644 --- a/Documentation/admin-guide/auxdisplay/ks0108.rst +++ b/Documentation/admin-guide/auxdisplay/ks0108.rst @@ -3,7 +3,7 @@ ks0108 LCD Controller Driver Documentation ========================================== :License: GPLv2 -:Author & Maintainer: Miguel Ojeda Sandonis +:Author & Maintainer: Miguel Ojeda :Date: 2006-10-27 diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index e5ca9b489259..d468f3b99541 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5186,6 +5186,12 @@ growing up) the main stack are reserved for no other mapping. Default value is 256 pages. + stack_depot_disable= [KNL] + Setting this to true through kernel command line will + disable the stack depot thereby saving the static memory + consumed by the stack hash table. By default this is set + to false. + stacktrace [FTRACE] Enabled the stack tracer on boot up. diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst index 5c4432c96c4b..5307f90738aa 100644 --- a/Documentation/admin-guide/mm/memory-hotplug.rst +++ b/Documentation/admin-guide/mm/memory-hotplug.rst @@ -160,16 +160,16 @@ Under each memory block, you can see 5 files: "online_movable", "online", "offline" command which will be performed on all sections in the block. -``phys_device`` read-only: designed to show the name of physical memory - device. This is not well implemented now. -``removable`` read-only: contains an integer value indicating - whether the memory block is removable or not - removable. A value of 1 indicates that the memory - block is removable and a value of 0 indicates that - it is not removable. A memory block is removable only if - every section in the block is removable. -``valid_zones`` read-only: designed to show which zones this memory block - can be onlined to. +``phys_device`` read-only: legacy interface only ever used on s390x to + expose the covered storage increment. +``removable`` read-only: legacy interface that indicated whether a memory + block was likely to be offlineable or not. Newer kernel + versions return "1" if and only if the kernel supports + memory offlining. +``valid_zones`` read-only: designed to show by which zone memory provided by + a memory block is managed, and to show by which zone memory + provided by an offline memory block could be managed when + onlining. The first column shows it`s default zone. diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/index.rst index f7809c7b1ba9..1b1cf4f5c9d9 100644 --- a/Documentation/dev-tools/index.rst +++ b/Documentation/dev-tools/index.rst @@ -22,6 +22,7 @@ whole; patches welcome! ubsan kmemleak kcsan + kfence gdb-kernel-debugging kgdb kselftest diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index 6092b4d36726..ddfe053afda6 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -155,7 +155,7 @@ Boot parameters ~~~~~~~~~~~~~~~ Hardware tag-based KASAN mode (see the section about various modes below) is -intended for use in production as a security mitigation. Therefore it supports +intended for use in production as a security mitigation. Therefore, it supports boot parameters that allow to disable KASAN competely or otherwise control particular KASAN features. @@ -165,7 +165,8 @@ particular KASAN features. traces collection (default: ``on``). - ``kasan.fault=report`` or ``=panic`` controls whether to only print a KASAN - report or also panic the kernel (default: ``report``). + report or also panic the kernel (default: ``report``). Note, that tag + checking gets disabled after the first reported bug. For developers ~~~~~~~~~~~~~~ @@ -295,6 +296,9 @@ Note, that enabling CONFIG_KASAN_HW_TAGS always results in in-kernel TBI being enabled. Even when kasan.mode=off is provided, or when the hardware doesn't support MTE (but supports TBI). +Hardware tag-based KASAN only reports the first found bug. After that MTE tag +checking gets disabled. + What memory accesses are sanitised by KASAN? -------------------------------------------- diff --git a/Documentation/dev-tools/kfence.rst b/Documentation/dev-tools/kfence.rst new file mode 100644 index 000000000000..fdf04e741ea5 --- /dev/null +++ b/Documentation/dev-tools/kfence.rst @@ -0,0 +1,298 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. Copyright (C) 2020, Google LLC. + +Kernel Electric-Fence (KFENCE) +============================== + +Kernel Electric-Fence (KFENCE) is a low-overhead sampling-based memory safety +error detector. KFENCE detects heap out-of-bounds access, use-after-free, and +invalid-free errors. + +KFENCE is designed to be enabled in production kernels, and has near zero +performance overhead. Compared to KASAN, KFENCE trades performance for +precision. The main motivation behind KFENCE's design, is that with enough +total uptime KFENCE will detect bugs in code paths not typically exercised by +non-production test workloads. One way to quickly achieve a large enough total +uptime is when the tool is deployed across a large fleet of machines. + +Usage +----- + +To enable KFENCE, configure the kernel with:: + + CONFIG_KFENCE=y + +To build a kernel with KFENCE support, but disabled by default (to enable, set +``kfence.sample_interval`` to non-zero value), configure the kernel with:: + + CONFIG_KFENCE=y + CONFIG_KFENCE_SAMPLE_INTERVAL=0 + +KFENCE provides several other configuration options to customize behaviour (see +the respective help text in ``lib/Kconfig.kfence`` for more info). + +Tuning performance +~~~~~~~~~~~~~~~~~~ + +The most important parameter is KFENCE's sample interval, which can be set via +the kernel boot parameter ``kfence.sample_interval`` in milliseconds. The +sample interval determines the frequency with which heap allocations will be +guarded by KFENCE. The default is configurable via the Kconfig option +``CONFIG_KFENCE_SAMPLE_INTERVAL``. Setting ``kfence.sample_interval=0`` +disables KFENCE. + +The KFENCE memory pool is of fixed size, and if the pool is exhausted, no +further KFENCE allocations occur. With ``CONFIG_KFENCE_NUM_OBJECTS`` (default +255), the number of available guarded objects can be controlled. Each object +requires 2 pages, one for the object itself and the other one used as a guard +page; object pages are interleaved with guard pages, and every object page is +therefore surrounded by two guard pages. + +The total memory dedicated to the KFENCE memory pool can be computed as:: + + ( #objects + 1 ) * 2 * PAGE_SIZE + +Using the default config, and assuming a page size of 4 KiB, results in +dedicating 2 MiB to the KFENCE memory pool. + +Note: On architectures that support huge pages, KFENCE will ensure that the +pool is using pages of size ``PAGE_SIZE``. This will result in additional page +tables being allocated. + +Error reports +~~~~~~~~~~~~~ + +A typical out-of-bounds access looks like this:: + + ================================================================== + BUG: KFENCE: out-of-bounds read in test_out_of_bounds_read+0xa3/0x22b + + Out-of-bounds read at 0xffffffffb672efff (1B left of kfence-#17): + test_out_of_bounds_read+0xa3/0x22b + kunit_try_run_case+0x51/0x85 + kunit_generic_run_threadfn_adapter+0x16/0x30 + kthread+0x137/0x160 + ret_from_fork+0x22/0x30 + + kfence-#17 [0xffffffffb672f000-0xffffffffb672f01f, size=32, cache=kmalloc-32] allocated by task 507: + test_alloc+0xf3/0x25b + test_out_of_bounds_read+0x98/0x22b + kunit_try_run_case+0x51/0x85 + kunit_generic_run_threadfn_adapter+0x16/0x30 + kthread+0x137/0x160 + ret_from_fork+0x22/0x30 + + CPU: 4 PID: 107 Comm: kunit_try_catch Not tainted 5.8.0-rc6+ #7 + Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014 + ================================================================== + +The header of the report provides a short summary of the function involved in +the access. It is followed by more detailed information about the access and +its origin. Note that, real kernel addresses are only shown when using the +kernel command line option ``no_hash_pointers``. + +Use-after-free accesses are reported as:: + + ================================================================== + BUG: KFENCE: use-after-free read in test_use_after_free_read+0xb3/0x143 + + Use-after-free read at 0xffffffffb673dfe0 (in kfence-#24): + test_use_after_free_read+0xb3/0x143 + kunit_try_run_case+0x51/0x85 + kunit_generic_run_threadfn_adapter+0x16/0x30 + kthread+0x137/0x160 + ret_from_fork+0x22/0x30 + + kfence-#24 [0xffffffffb673dfe0-0xffffffffb673dfff, size=32, cache=kmalloc-32] allocated by task 507: + test_alloc+0xf3/0x25b + test_use_after_free_read+0x76/0x143 + kunit_try_run_case+0x51/0x85 + kunit_generic_run_threadfn_adapter+0x16/0x30 + kthread+0x137/0x160 + ret_from_fork+0x22/0x30 + + freed by task 507: + test_use_after_free_read+0xa8/0x143 + kunit_try_run_case+0x51/0x85 + kunit_generic_run_threadfn_adapter+0x16/0x30 + kthread+0x137/0x160 + ret_from_fork+0x22/0x30 + + CPU: 4 PID: 109 Comm: kunit_try_catch Tainted: G W 5.8.0-rc6+ #7 + Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014 + ================================================================== + +KFENCE also reports on invalid frees, such as double-frees:: + + ================================================================== + BUG: KFENCE: invalid free in test_double_free+0xdc/0x171 + + Invalid free of 0xffffffffb6741000: + test_double_free+0xdc/0x171 + kunit_try_run_case+0x51/0x85 + kunit_generic_run_threadfn_adapter+0x16/0x30 + kthread+0x137/0x160 + ret_from_fork+0x22/0x30 + + kfence-#26 [0xffffffffb6741000-0xffffffffb674101f, size=32, cache=kmalloc-32] allocated by task 507: + test_alloc+0xf3/0x25b + test_double_free+0x76/0x171 + kunit_try_run_case+0x51/0x85 + kunit_generic_run_threadfn_adapter+0x16/0x30 + kthread+0x137/0x160 + ret_from_fork+0x22/0x30 + + freed by task 507: + test_double_free+0xa8/0x171 + kunit_try_run_case+0x51/0x85 + kunit_generic_run_threadfn_adapter+0x16/0x30 + kthread+0x137/0x160 + ret_from_fork+0x22/0x30 + + CPU: 4 PID: 111 Comm: kunit_try_catch Tainted: G W 5.8.0-rc6+ #7 + Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014 + ================================================================== + +KFENCE also uses pattern-based redzones on the other side of an object's guard +page, to detect out-of-bounds writes on the unprotected side of the object. +These are reported on frees:: + + ================================================================== + BUG: KFENCE: memory corruption in test_kmalloc_aligned_oob_write+0xef/0x184 + + Corrupted memory at 0xffffffffb6797ff9 [ 0xac . . . . . . ] (in kfence-#69): + test_kmalloc_aligned_oob_write+0xef/0x184 + kunit_try_run_case+0x51/0x85 + kunit_generic_run_threadfn_adapter+0x16/0x30 + kthread+0x137/0x160 + ret_from_fork+0x22/0x30 + + kfence-#69 [0xffffffffb6797fb0-0xffffffffb6797ff8, size=73, cache=kmalloc-96] allocated by task 507: + test_alloc+0xf3/0x25b + test_kmalloc_aligned_oob_write+0x57/0x184 + kunit_try_run_case+0x51/0x85 + kunit_generic_run_threadfn_adapter+0x16/0x30 + kthread+0x137/0x160 + ret_from_fork+0x22/0x30 + + CPU: 4 PID: 120 Comm: kunit_try_catch Tainted: G W 5.8.0-rc6+ #7 + Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014 + ================================================================== + +For such errors, the address where the corruption occurred as well as the +invalidly written bytes (offset from the address) are shown; in this +representation, '.' denote untouched bytes. In the example above ``0xac`` is +the value written to the invalid address at offset 0, and the remaining '.' +denote that no following bytes have been touched. Note that, real values are +only shown if the kernel was booted with ``no_hash_pointers``; to avoid +information disclosure otherwise, '!' is used instead to denote invalidly +written bytes. + +And finally, KFENCE may also report on invalid accesses to any protected page +where it was not possible to determine an associated object, e.g. if adjacent +object pages had not yet been allocated:: + + ================================================================== + BUG: KFENCE: invalid read in test_invalid_access+0x26/0xe0 + + Invalid read at 0xffffffffb670b00a: + test_invalid_access+0x26/0xe0 + kunit_try_run_case+0x51/0x85 + kunit_generic_run_threadfn_adapter+0x16/0x30 + kthread+0x137/0x160 + ret_from_fork+0x22/0x30 + + CPU: 4 PID: 124 Comm: kunit_try_catch Tainted: G W 5.8.0-rc6+ #7 + Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014 + ================================================================== + +DebugFS interface +~~~~~~~~~~~~~~~~~ + +Some debugging information is exposed via debugfs: + +* The file ``/sys/kernel/debug/kfence/stats`` provides runtime statistics. + +* The file ``/sys/kernel/debug/kfence/objects`` provides a list of objects + allocated via KFENCE, including those already freed but protected. + +Implementation Details +---------------------- + +Guarded allocations are set up based on the sample interval. After expiration +of the sample interval, the next allocation through the main allocator (SLAB or +SLUB) returns a guarded allocation from the KFENCE object pool (allocation +sizes up to PAGE_SIZE are supported). At this point, the timer is reset, and +the next allocation is set up after the expiration of the interval. To "gate" a +KFENCE allocation through the main allocator's fast-path without overhead, +KFENCE relies on static branches via the static keys infrastructure. The static +branch is toggled to redirect the allocation to KFENCE. + +KFENCE objects each reside on a dedicated page, at either the left or right +page boundaries selected at random. The pages to the left and right of the +object page are "guard pages", whose attributes are changed to a protected +state, and cause page faults on any attempted access. Such page faults are then +intercepted by KFENCE, which handles the fault gracefully by reporting an +out-of-bounds access, and marking the page as accessible so that the faulting +code can (wrongly) continue executing (set ``panic_on_warn`` to panic instead). + +To detect out-of-bounds writes to memory within the object's page itself, +KFENCE also uses pattern-based redzones. For each object page, a redzone is set +up for all non-object memory. For typical alignments, the redzone is only +required on the unguarded side of an object. Because KFENCE must honor the +cache's requested alignment, special alignments may result in unprotected gaps +on either side of an object, all of which are redzoned. + +The following figure illustrates the page layout:: + + ---+-----------+-----------+-----------+-----------+-----------+--- + | xxxxxxxxx | O : | xxxxxxxxx | : O | xxxxxxxxx | + | xxxxxxxxx | B : | xxxxxxxxx | : B | xxxxxxxxx | + | x GUARD x | J : RED- | x GUARD x | RED- : J | x GUARD x | + | xxxxxxxxx | E : ZONE | xxxxxxxxx | ZONE : E | xxxxxxxxx | + | xxxxxxxxx | C : | xxxxxxxxx | : C | xxxxxxxxx | + | xxxxxxxxx | T : | xxxxxxxxx | : T | xxxxxxxxx | + ---+-----------+-----------+-----------+-----------+-----------+--- + +Upon deallocation of a KFENCE object, the object's page is again protected and +the object is marked as freed. Any further access to the object causes a fault +and KFENCE reports a use-after-free access. Freed objects are inserted at the +tail of KFENCE's freelist, so that the least recently freed objects are reused +first, and the chances of detecting use-after-frees of recently freed objects +is increased. + +Interface +--------- + +The following describes the functions which are used by allocators as well as +page handling code to set up and deal with KFENCE allocations. + +.. kernel-doc:: include/linux/kfence.h + :functions: is_kfence_address + kfence_shutdown_cache + kfence_alloc kfence_free __kfence_free + kfence_ksize kfence_object_start + kfence_handle_page_fault + +Related Tools +------------- + +In userspace, a similar approach is taken by `GWP-ASan +`_. GWP-ASan also relies on guard pages and +a sampling strategy to detect memory unsafety bugs at scale. KFENCE's design is +directly influenced by GWP-ASan, and can be seen as its kernel sibling. Another +similar but non-sampling approach, that also inspired the name "KFENCE", can be +found in the userspace `Electric Fence Malloc Debugger +`_. + +In the kernel, several tools exist to debug memory access errors, and in +particular KASAN can detect all bug classes that KFENCE can detect. While KASAN +is more precise, relying on compiler instrumentation, this comes at a +performance cost. + +It is worth highlighting that KASAN and KFENCE are complementary, with +different target environments. For instance, KASAN is the better debugging-aid, +where test cases or reproducers exists: due to the lower chance to detect the +error, it would require more effort using KFENCE to debug. Deployments at scale +that cannot afford to enable KASAN, however, would benefit from using KFENCE to +discover bugs due to code paths not exercised by test cases or fuzzers. diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile index f5530c91d655..780e5618ec0a 100644 --- a/Documentation/devicetree/bindings/Makefile +++ b/Documentation/devicetree/bindings/Makefile @@ -78,10 +78,10 @@ $(obj)/processed-schema.json: $(DT_SCHEMA_FILES) check_dtschema_version FORCE endif -extra-$(CHECK_DT_BINDING) += processed-schema-examples.json -extra-$(CHECK_DTBS) += processed-schema.json -extra-$(CHECK_DT_BINDING) += $(patsubst $(src)/%.yaml,%.example.dts, $(DT_SCHEMA_FILES)) -extra-$(CHECK_DT_BINDING) += $(patsubst $(src)/%.yaml,%.example.dt.yaml, $(DT_SCHEMA_FILES)) +always-$(CHECK_DT_BINDING) += processed-schema-examples.json +always-$(CHECK_DTBS) += processed-schema.json +always-$(CHECK_DT_BINDING) += $(patsubst $(src)/%.yaml,%.example.dts, $(DT_SCHEMA_FILES)) +always-$(CHECK_DT_BINDING) += $(patsubst $(src)/%.yaml,%.example.dt.yaml, $(DT_SCHEMA_FILES)) # Hack: avoid 'Argument list too long' error for 'make clean'. Remove most of # build artifacts here before they are processed by scripts/Makefile.clean diff --git a/Documentation/devicetree/bindings/display/connector/dp-connector.yaml b/Documentation/devicetree/bindings/display/connector/dp-connector.yaml index 1c17d60e7760..22792a79e7ce 100644 --- a/Documentation/devicetree/bindings/display/connector/dp-connector.yaml +++ b/Documentation/devicetree/bindings/display/connector/dp-connector.yaml @@ -26,7 +26,6 @@ properties: dp-pwr-supply: description: Power supply for the DP_PWR pin - maxItems: 1 port: $ref: /schemas/graph.yaml#/properties/port diff --git a/Documentation/devicetree/bindings/gpio/sifive,gpio.yaml b/Documentation/devicetree/bindings/gpio/sifive,gpio.yaml index a0efd8dc2538..c2902aac2514 100644 --- a/Documentation/devicetree/bindings/gpio/sifive,gpio.yaml +++ b/Documentation/devicetree/bindings/gpio/sifive,gpio.yaml @@ -13,7 +13,10 @@ maintainers: properties: compatible: items: - - const: sifive,fu540-c000-gpio + - enum: + - sifive,fu540-c000-gpio + - sifive,fu740-c000-gpio + - canaan,k210-gpiohs - const: sifive,gpio0 reg: @@ -21,9 +24,9 @@ properties: interrupts: description: - interrupt mapping one per GPIO. Maximum 16 GPIOs. + Interrupt mapping, one per GPIO. Maximum 32 GPIOs. minItems: 1 - maxItems: 16 + maxItems: 32 interrupt-controller: true @@ -36,6 +39,14 @@ properties: "#gpio-cells": const: 2 + ngpios: + description: + The number of GPIOs available on the controller implementation. + It is 16 for the SiFive SoCs and 32 for the Canaan K210. + minimum: 1 + maximum: 32 + default: 16 + gpio-controller: true required: @@ -44,10 +55,20 @@ required: - interrupts - interrupt-controller - "#interrupt-cells" - - clocks - "#gpio-cells" - gpio-controller +if: + properties: + compatible: + contains: + enum: + - sifive,fu540-c000-gpio + - sifive,fu740-c000-gpio +then: + required: + - clocks + additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml index b9a61c9f7530..08d5a57ce00f 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml @@ -8,10 +8,11 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: SiFive Platform-Level Interrupt Controller (PLIC) description: - SiFive SOCs include an implementation of the Platform-Level Interrupt Controller - (PLIC) high-level specification in the RISC-V Privileged Architecture - specification. The PLIC connects all external interrupts in the system to all - hart contexts in the system, via the external interrupt source in each hart. + SiFive SoCs and other RISC-V SoCs include an implementation of the + Platform-Level Interrupt Controller (PLIC) high-level specification in + the RISC-V Privileged Architecture specification. The PLIC connects all + external interrupts in the system to all hart contexts in the system, via + the external interrupt source in each hart. A hart context is a privilege mode in a hardware execution thread. For example, in an 4 core system with 2-way SMT, you have 8 harts and probably at least two @@ -42,7 +43,9 @@ maintainers: properties: compatible: items: - - const: sifive,fu540-c000-plic + - enum: + - sifive,fu540-c000-plic + - canaan,k210-plic - const: sifive,plic-1.0.0 reg: diff --git a/Documentation/devicetree/bindings/leds/leds-lgm.yaml b/Documentation/devicetree/bindings/leds/leds-lgm.yaml new file mode 100644 index 000000000000..32bbf146c01d --- /dev/null +++ b/Documentation/devicetree/bindings/leds/leds-lgm.yaml @@ -0,0 +1,113 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/leds/leds-lgm.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Intel Lightning Mountain (LGM) SoC LED Serial Shift Output (SSO) Controller driver + +maintainers: + - Zhu, Yi Xin + - Amireddy Mallikarjuna reddy + +properties: + compatible: + const: intel,lgm-ssoled + + gpio-controller: true + + '#gpio-cells': + const: 2 + + ngpios: + minimum: 0 + maximum: 32 + description: + Number of GPIOs this controller provides. + + intel,sso-update-rate-hz: + description: + Blink frequency for SOUTs in Hz. + + led-controller: + type: object + description: + This sub-node must contain a sub-node for each leds. + + additionalProperties: false + + patternProperties: + "^led@[0-23]$": + type: object + + properties: + reg: + description: Index of the LED. + minimum: 0 + maximum: 2 + + intel,sso-hw-trigger: + type: boolean + description: This property indicates Hardware driven/control LED. + + intel,sso-hw-blink: + type: boolean + description: This property indicates Enable LED blink by Hardware. + + intel,sso-blink-rate-hz: + description: LED HW blink frequency. + + retain-state-suspended: + type: boolean + description: The suspend state of LED can be retained. + + retain-state-shutdown: + type: boolean + description: Retain the state of the LED on shutdown. + +required: + - compatible + - reg + - clocks + - clock-names + - "#gpio-cells" + - gpio-controller + +additionalProperties: false + +examples: + - | + #include + #include + + ssogpio: ssogpio@e0d40000 { + compatible = "intel,sso-led"; + reg = <0xE0D40000 0x2E4>; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_ledc>; + clocks = <&cgu0 LGM_GCLK_LEDC0>, <&afeclk>; + clock-names = "sso", "fpid"; + intel,sso-update-rate-hz = <250000>; + + led-controller { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + function = "gphy"; + color = ; + led-gpio = <&ssogpio 0 0>; + }; + + led@23 { + reg = <23>; + function = LED_FUNCTION_POWER; + color = ; + led-gpio = <&ssogpio 23 0>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml b/Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml new file mode 100644 index 000000000000..c24ad45cabb5 --- /dev/null +++ b/Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml @@ -0,0 +1,109 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mfd/canaan,k210-sysctl.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Canaan Kendryte K210 System Controller Device Tree Bindings + +maintainers: + - Damien Le Moal + +description: + Canaan Inc. Kendryte K210 SoC system controller which provides a + register map for controlling the clocks, reset signals and pin power + domains of the SoC. + +properties: + compatible: + items: + - const: canaan,k210-sysctl + - const: syscon + - const: simple-mfd + + clocks: + maxItems: 1 + description: + System controller Advanced Power Bus (APB) interface clock source. + + clock-names: + items: + - const: pclk + + reg: + maxItems: 1 + + clock-controller: + # Child node + type: object + $ref: "../clock/canaan,k210-clk.yaml" + description: + Clock controller for the SoC clocks. This child node definition + should follow the bindings specified in + Documentation/devicetree/bindings/clock/canaan,k210-clk.yaml. + + reset-controller: + # Child node + type: object + $ref: "../reset/canaan,k210-rst.yaml" + description: + Reset controller for the SoC. This child node definition + should follow the bindings specified in + Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml. + + syscon-reboot: + # Child node + type: object + $ref: "../power/reset/syscon-reboot.yaml" + description: + Reboot method for the SoC. This child node definition + should follow the bindings specified in + Documentation/devicetree/bindings/power/reset/syscon-reboot.yaml. + +required: + - compatible + - clocks + - reg + - clock-controller + +additionalProperties: false + +examples: + - | + #include + #include + + clocks { + in0: oscllator { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <26000000>; + }; + }; + + sysctl: syscon@50440000 { + compatible = "canaan,k210-sysctl", + "syscon", "simple-mfd"; + reg = <0x50440000 0x100>; + clocks = <&sysclk K210_CLK_APB1>; + clock-names = "pclk"; + + sysclk: clock-controller { + #clock-cells = <1>; + compatible = "canaan,k210-clk"; + clocks = <&in0>; + }; + + sysrst: reset-controller { + compatible = "canaan,k210-rst"; + #reset-cells = <1>; + }; + + reboot: syscon-reboot { + compatible = "syscon-reboot"; + regmap = <&sysctl>; + offset = <48>; + mask = <1>; + value = <1>; + }; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml b/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml new file mode 100644 index 000000000000..46fbc73ab26b --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml @@ -0,0 +1,171 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/canaan,k210-fpioa.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Canaan Kendryte K210 FPIOA Device Tree Bindings + +maintainers: + - Damien Le Moal + +description: + The Canaan Kendryte K210 SoC Fully Programmable IO Array (FPIOA) + controller allows assiging any of 256 possible functions to any of + 48 IO pins of the SoC. Pin function configuration is performed on + a per-pin basis. + +properties: + compatible: + const: canaan,k210-fpioa + + reg: + maxItems: 1 + description: + Address and length of the register set for the FPIOA controller. + + clocks: + items: + - description: Controller reference clock source + - description: APB interface clock source + + clock-names: + items: + - const: ref + - const: pclk + + resets: + maxItems: 1 + + canaan,k210-sysctl-power: + $ref: /schemas/types.yaml#/definitions/phandle-array + description: | + phandle of the K210 system controller node and offset of its + power domain control register. + +patternProperties: + '-pinmux$': + type: object + $ref: /schemas/pinctrl/pinmux-node.yaml + description: + FPIOA client devices use sub-nodes to define the desired pin + configuration. Client device sub-nodes use the pinux property + below. + + properties: + pinmux: + description: + List of IO pins alternate functions. The values for each IO + pin is a combination of an IO pin number (0 to 47) with the + desired function for the IO pin. Functions are defined as + macros in include/dt-bindings/pinctrl/k210-fpioa.h. + The K210_FPIOA(IO pin, function) macro is provided to + facilitate the combination of IO pin numbers and functions. + + required: + - pinmux + + additionalProperties: false + + '-pins$': + type: object + $ref: /schemas/pinctrl/pincfg-node.yaml + description: + FPIOA client devices use sub-nodes to define the desired + configuration of pins. Client device sub-nodes use the + properties below. + + properties: + pins: + description: + List of IO pins affected by the properties specified in this + subnode. IO pins are identified using the pin names "IO_xx". + Pin configuration nodes can also define the power domain to + be used for the SoC pin groups A0 (IO pins 0-5), + A1 (IO pins 6-11), A2 (IO pins 12-17), B0 (IO pins 18-23), + B1 (IO pins 24-29), B2 (IO pins 30-35), B3 (IO pins 30-35), + C0 (IO pins 36-41) and C1 (IO pins 42-47) using the + power-source property. + items: + anyOf: + - pattern: "^(IO_([0-9]*))|(A[0-2])|(B[3-5])|(C[6-7])$" + - enum: [ IO_0, IO_1, IO_2, IO_3, IO_4, IO_5, IO_6, IO_7, + IO_8, IO_9, IO_10, IO_11, IO_12, IO_13, IO_14, + IO_15, IO_16, IO_17, IO_18, IO_19, IO_20, IO_21, + IO_22, IO_23, IO_24, IO_25, IO_26, IO_27, IO_28, + IO_29, IO_30, IO_31, IO_32, IO_33, IO_34, IO_35, + IO_36, IO_37, IO_38, IO_39, IO_40, IO_41, IO_42, + IO_43, IO_44, IO_45, IO_46, IO_47, + A0, A1, A2, B3, B4, B5, C6, C7 ] + bias-disable: true + + bias-pull-down: true + + bias-pull-up: true + + drive-strength: true + + drive-strength-microamp: true + + input-enable: true + + input-disable: true + + input-schmitt-enable: true + + input-schmitt-disable: true + + input-polarity-invert: + description: + Enable or disable pin input polarity inversion. + + output-enable: true + + output-disable: true + + output-high: true + + output-low: true + + output-polarity-invert: + description: + Enable or disable pin output polarity inversion. + + slew-rate: true + + power-source: true + + additionalProperties: false + +required: + - compatible + - reg + - clocks + - canaan,k210-sysctl-power + +additionalProperties: false + +examples: + - | + #include + #include + #include + + fpioa: pinmux@502B0000 { + compatible = "canaan,k210-fpioa"; + reg = <0x502B0000 0x100>; + clocks = <&sysclk K210_CLK_FPIOA>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_FPIOA>; + canaan,k210-sysctl-power = <&sysctl 108>; + pinctrl-0 = <&jtag_pinctrl>; + pinctrl-names = "default"; + + jtag_pinctrl: jtag-pinmux { + pinmux = , + , + , + ; + }; + }; diff --git a/Documentation/devicetree/bindings/pwm/pwm-sifive.yaml b/Documentation/devicetree/bindings/pwm/pwm-sifive.yaml index 5ac25275d8bf..84e66913d042 100644 --- a/Documentation/devicetree/bindings/pwm/pwm-sifive.yaml +++ b/Documentation/devicetree/bindings/pwm/pwm-sifive.yaml @@ -25,12 +25,15 @@ description: properties: compatible: items: - - const: sifive,fu540-c000-pwm + - enum: + - sifive,fu540-c000-pwm + - sifive,fu740-c000-pwm - const: sifive,pwm0 description: Should be "sifive,-pwm" and "sifive,pwm". Supported - compatible strings are "sifive,fu540-c000-pwm" for the SiFive PWM v0 - as integrated onto the SiFive FU540 chip, and "sifive,pwm0" for the + compatible strings are "sifive,fu540-c000-pwm" and + "sifive,fu740-c000-pwm" for the SiFive PWM v0 as integrated onto the + SiFive FU540 and FU740 chip respectively, and "sifive,pwm0" for the SiFive PWM v0 IP block with no chip integration tweaks. Please refer to sifive-blocks-ip-versioning.txt for details. diff --git a/Documentation/devicetree/bindings/pwm/pwm-zx.txt b/Documentation/devicetree/bindings/pwm/pwm-zx.txt deleted file mode 100644 index 3c8fe7aa8269..000000000000 --- a/Documentation/devicetree/bindings/pwm/pwm-zx.txt +++ /dev/null @@ -1,22 +0,0 @@ -ZTE ZX PWM controller - -Required properties: - - compatible: Should be "zte,zx296718-pwm". - - reg: Physical base address and length of the controller's registers. - - clocks : The phandle and specifier referencing the controller's clocks. - - clock-names: "pclk" for PCLK, "wclk" for WCLK to the PWM controller. The - PCLK is for register access, while WCLK is the reference clock for - calculating period and duty cycles. - - #pwm-cells: Should be 3. See pwm.yaml in this directory for a description of - the cells format. - -Example: - - pwm: pwm@1439000 { - compatible = "zte,zx296718-pwm"; - reg = <0x1439000 0x1000>; - clocks = <&lsp1crm LSP1_PWM_PCLK>, - <&lsp1crm LSP1_PWM_WCLK>; - clock-names = "pclk", "wclk"; - #pwm-cells = <3>; - }; diff --git a/Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml b/Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml new file mode 100644 index 000000000000..53e4ede9c0bd --- /dev/null +++ b/Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/reset/canaan,k210-rst.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Canaan Kendryte K210 Reset Controller Device Tree Bindings + +maintainers: + - Damien Le Moal + +description: | + Canaan Kendryte K210 reset controller driver which supports the SoC + system controller supplied reset registers for the various peripherals + of the SoC. The K210 reset controller node must be defined as a child + node of the K210 system controller node. + + See also: + - dt-bindings/reset/k210-rst.h + +properties: + compatible: + const: canaan,k210-rst + + '#reset-cells': + const: 1 + +required: + - '#reset-cells' + - compatible + +additionalProperties: false + +examples: + - | + #include + sysrst: reset-controller { + compatible = "canaan,k210-rst"; + #reset-cells = <1>; + }; diff --git a/Documentation/devicetree/bindings/riscv/canaan.yaml b/Documentation/devicetree/bindings/riscv/canaan.yaml new file mode 100644 index 000000000000..f8f3f286bd55 --- /dev/null +++ b/Documentation/devicetree/bindings/riscv/canaan.yaml @@ -0,0 +1,47 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/riscv/canaan.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Canaan SoC-based boards + +maintainers: + - Damien Le Moal + +description: + Canaan Kendryte K210 SoC-based boards + +properties: + $nodename: + const: '/' + compatible: + oneOf: + - items: + - const: sipeed,maix-bit + - const: sipeed,maix-bitm + - const: canaan,kendryte-k210 + + - items: + - const: sipeed,maix-go + - const: canaan,kendryte-k210 + + - items: + - const: sipeed,maix-dock-m1 + - const: sipeed,maix-dock-m1w + - const: canaan,kendryte-k210 + + - items: + - const: sipeed,maixduino + - const: canaan,kendryte-k210 + + - items: + - const: canaan,kendryte-kd233 + - const: canaan,kendryte-k210 + + - items: + - const: canaan,kendryte-k210 + +additionalProperties: true + +... diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index c6925e0b16e4..e534f6a7cfa1 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -28,11 +28,18 @@ properties: - items: - enum: - sifive,rocket0 + - sifive,bullet0 - sifive,e5 + - sifive,e7 - sifive,e51 + - sifive,e71 - sifive,u54-mc + - sifive,u74-mc - sifive,u54 + - sifive,u74 - sifive,u5 + - sifive,u7 + - canaan,k210 - const: riscv - const: riscv # Simulator only description: @@ -50,6 +57,7 @@ properties: - riscv,sv32 - riscv,sv39 - riscv,sv48 + - riscv,none riscv,isa: description: diff --git a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml b/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml index 2ece8630dc68..23b227614366 100644 --- a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml +++ b/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml @@ -27,6 +27,7 @@ select: items: - enum: - sifive,fu540-c000-ccache + - sifive,fu740-c000-ccache required: - compatible @@ -34,7 +35,9 @@ select: properties: compatible: items: - - const: sifive,fu540-c000-ccache + - enum: + - sifive,fu540-c000-ccache + - sifive,fu740-c000-ccache - const: cache cache-block-size: @@ -52,10 +55,13 @@ properties: cache-unified: true interrupts: - description: | - Must contain entries for DirError, DataError and DataFail signals. minItems: 3 - maxItems: 3 + maxItems: 4 + items: + - description: DirError interrupt + - description: DataError interrupt + - description: DataFail interrupt + - description: DirFail interrupt reg: maxItems: 1 @@ -68,6 +74,26 @@ properties: The reference to the reserved-memory for the L2 Loosely Integrated Memory region. The reserved memory node should be defined as per the bindings in reserved-memory.txt. +if: + properties: + compatible: + contains: + const: sifive,fu540-c000-ccache + +then: + properties: + interrupts: + description: | + Must contain entries for DirError, DataError and DataFail signals. + maxItems: 3 + +else: + properties: + interrupts: + description: | + Must contain entries for DirError, DataError, DataFail, DirFail signals. + minItems: 4 + additionalProperties: false required: diff --git a/Documentation/devicetree/bindings/riscv/sifive.yaml b/Documentation/devicetree/bindings/riscv/sifive.yaml index 3a8647d1da4c..ee0a239af4c2 100644 --- a/Documentation/devicetree/bindings/riscv/sifive.yaml +++ b/Documentation/devicetree/bindings/riscv/sifive.yaml @@ -17,11 +17,18 @@ properties: $nodename: const: '/' compatible: - items: - - enum: - - sifive,hifive-unleashed-a00 - - const: sifive,fu540-c000 - - const: sifive,fu540 + oneOf: + - items: + - enum: + - sifive,hifive-unleashed-a00 + - const: sifive,fu540-c000 + - const: sifive,fu540 + + - items: + - enum: + - sifive,hifive-unmatched-a00 + - const: sifive,fu740-c000 + - const: sifive,fu740 additionalProperties: true diff --git a/Documentation/devicetree/bindings/serial/sifive-serial.yaml b/Documentation/devicetree/bindings/serial/sifive-serial.yaml index 3ac5c7ff2758..5fa94dacbba9 100644 --- a/Documentation/devicetree/bindings/serial/sifive-serial.yaml +++ b/Documentation/devicetree/bindings/serial/sifive-serial.yaml @@ -20,6 +20,7 @@ properties: - enum: - sifive,fu540-c000-uart - sifive,fu740-c000-uart + - canaan,k210-uarths - const: sifive,uart0 description: diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml index 2a0e9cd9fbcf..a35952f48742 100644 --- a/Documentation/devicetree/bindings/timer/sifive,clint.yaml +++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml @@ -23,15 +23,19 @@ description: properties: compatible: items: - - const: sifive,fu540-c000-clint + - enum: + - sifive,fu540-c000-clint + - canaan,k210-clint - const: sifive,clint0 description: - Should be "sifive,-clint" and "sifive,clint". + Should be ",-clint" and "sifive,clint". Supported compatible strings are - "sifive,fu540-c000-clint" for the SiFive CLINT v0 as integrated - onto the SiFive FU540 chip, and "sifive,clint0" for the SiFive - CLINT v0 IP block with no chip integration tweaks. + onto the SiFive FU540 chip, "canaan,k210-clint" for the SiFive + CLINT v0 as integrated onto the Canaan Kendryte K210 chip, and + "sifive,clint0" for the SiFive CLINT v0 IP block with no chip + integration tweaks. Please refer to sifive-blocks-ip-versioning.txt for details reg: diff --git a/Documentation/devicetree/bindings/timer/snps,dw-apb-timer.yaml b/Documentation/devicetree/bindings/timer/snps,dw-apb-timer.yaml index d65faf289a83..d33c9205a909 100644 --- a/Documentation/devicetree/bindings/timer/snps,dw-apb-timer.yaml +++ b/Documentation/devicetree/bindings/timer/snps,dw-apb-timer.yaml @@ -24,6 +24,9 @@ properties: interrupts: maxItems: 1 + resets: + maxItems: 1 + clocks: minItems: 1 items: diff --git a/Documentation/filesystems/seq_file.rst b/Documentation/filesystems/seq_file.rst index 56856481dc8d..a6726082a7c2 100644 --- a/Documentation/filesystems/seq_file.rst +++ b/Documentation/filesystems/seq_file.rst @@ -217,6 +217,12 @@ between the calls to start() and stop(), so holding a lock during that time is a reasonable thing to do. The seq_file code will also avoid taking any other locks while the iterator is active. +The iterater value returned by start() or next() is guaranteed to be +passed to a subsequent next() or stop() call. This allows resources +such as locks that were taken to be reliably released. There is *no* +guarantee that the iterator will be passed to show(), though in practice +it often will be. + Formatted output ================ diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index de669c2f1fcd..db3af0b45baf 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -12,7 +12,7 @@ This document describes the Linux kernel Makefiles. --- 3.1 Goal definitions --- 3.2 Built-in object goals - obj-y --- 3.3 Loadable module goals - obj-m - --- 3.4 Objects which export symbols + --- 3.4 --- 3.5 Library file goals - lib-y --- 3.6 Descending down in directories --- 3.7 Non-builtin vmlinux targets - extra-y @@ -247,12 +247,6 @@ more details, with real examples. kbuild will build an ext2.o file for you out of the individual parts and then link this into built-in.a, as you would expect. -3.4 Objects which export symbols --------------------------------- - - No special notation is required in the makefiles for - modules exporting symbols. - 3.5 Library file goals - lib-y ------------------------------ diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 45fd862ac128..aed52b0fc16e 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4519,6 +4519,7 @@ KVM_GET_SUPPORTED_CPUID ioctl because some of them intersect with KVM feature leaves (0x40000000, 0x40000001). Currently, the following list of CPUID leaves are returned: + - HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS - HYPERV_CPUID_INTERFACE - HYPERV_CPUID_VERSION @@ -4543,6 +4544,7 @@ userspace should not expect to get any particular value there. Note, vcpu version of KVM_GET_SUPPORTED_HV_CPUID is currently deprecated. Unlike system ioctl which exposes all supported feature bits unconditionally, vcpu version has the following quirks: + - HYPERV_CPUID_NESTED_FEATURES leaf and HV_X64_ENLIGHTENED_VMCS_RECOMMENDED feature bit are only exposed when Enlightened VMCS was previously enabled on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS). diff --git a/MAINTAINERS b/MAINTAINERS index d6709c1f0b4f..ad70aeffef00 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -261,6 +261,8 @@ ABI/API L: linux-api@vger.kernel.org F: include/linux/syscalls.h F: kernel/sys_ni.c +F: include/uapi/ +F: arch/*/include/uapi/ ABIT UGURU 1,2 HARDWARE MONITOR DRIVER M: Hans de Goede @@ -2982,7 +2984,7 @@ F: include/uapi/linux/audit.h F: kernel/audit* AUXILIARY DISPLAY DRIVERS -M: Miguel Ojeda Sandonis +M: Miguel Ojeda S: Maintained F: drivers/auxdisplay/ F: include/linux/cfag12864b.h @@ -3853,6 +3855,29 @@ W: https://github.com/Cascoda/ca8210-linux.git F: Documentation/devicetree/bindings/net/ieee802154/ca8210.txt F: drivers/net/ieee802154/ca8210.c +CANAAN/KENDRYTE K210 SOC FPIOA DRIVER +M: Damien Le Moal +L: linux-riscv@lists.infradead.org +L: linux-gpio@vger.kernel.org (pinctrl driver) +F: Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml +F: drivers/pinctrl/pinctrl-k210.c + +CANAAN/KENDRYTE K210 SOC RESET CONTROLLER DRIVER +M: Damien Le Moal +L: linux-kernel@vger.kernel.org +L: linux-riscv@lists.infradead.org +S: Maintained +F: Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml +F: drivers/reset/reset-k210.c + +CANAAN/KENDRYTE K210 SOC SYSTEM CONTROLLER DRIVER +M: Damien Le Moal +L: linux-riscv@lists.infradead.org +S: Maintained +F: Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml +F: drivers/soc/canaan/ +F: include/soc/canaan/ + CACHEFILES: FS-CACHE BACKEND FOR CACHING ON MOUNTED FILESYSTEMS M: David Howells L: linux-cachefs@redhat.com (moderated for non-subscribers) @@ -4128,13 +4153,13 @@ F: scripts/extract-cert.c F: scripts/sign-file.c CFAG12864B LCD DRIVER -M: Miguel Ojeda Sandonis +M: Miguel Ojeda S: Maintained F: drivers/auxdisplay/cfag12864b.c F: include/linux/cfag12864b.h CFAG12864BFB LCD FRAMEBUFFER DRIVER -M: Miguel Ojeda Sandonis +M: Miguel Ojeda S: Maintained F: drivers/auxdisplay/cfag12864bfb.c F: include/linux/cfag12864b.h @@ -4304,7 +4329,7 @@ S: Supported F: drivers/infiniband/hw/usnic/ CLANG-FORMAT FILE -M: Miguel Ojeda +M: Miguel Ojeda S: Maintained F: .clang-format @@ -4319,8 +4344,6 @@ C: irc://chat.freenode.net/clangbuiltlinux F: Documentation/kbuild/llvm.rst F: include/linux/compiler-clang.h F: scripts/clang-tools/ -F: scripts/clang-version.sh -F: scripts/lld-version.sh K: \b(?i:clang|llvm)\b CLEANCACHE API @@ -4446,7 +4469,7 @@ S: Maintained F: drivers/platform/x86/compal-laptop.c COMPILER ATTRIBUTES -M: Miguel Ojeda +M: Miguel Ojeda S: Maintained F: include/linux/compiler_attributes.h @@ -9876,6 +9899,18 @@ F: include/linux/keyctl.h F: include/uapi/linux/keyctl.h F: security/keys/ +KFENCE +M: Alexander Potapenko +M: Marco Elver +R: Dmitry Vyukov +L: kasan-dev@googlegroups.com +S: Maintained +F: Documentation/dev-tools/kfence.rst +F: arch/*/include/asm/kfence.h +F: include/linux/kfence.h +F: lib/Kconfig.kfence +F: mm/kfence/ + KFIFO M: Stefani Seibold S: Maintained @@ -9936,7 +9971,7 @@ F: include/linux/kprobes.h F: kernel/kprobes.c KS0108 LCD CONTROLLER DRIVER -M: Miguel Ojeda Sandonis +M: Miguel Ojeda S: Maintained F: Documentation/admin-guide/auxdisplay/ks0108.rst F: drivers/auxdisplay/ks0108.c diff --git a/Makefile b/Makefile index 00878f99022e..1bebbfdd38d0 100644 --- a/Makefile +++ b/Makefile @@ -100,6 +100,36 @@ endif export quiet Q KBUILD_VERBOSE +# Call a source code checker (by default, "sparse") as part of the +# C compilation. +# +# Use 'make C=1' to enable checking of only re-compiled files. +# Use 'make C=2' to enable checking of *all* source files, regardless +# of whether they are re-compiled or not. +# +# See the file "Documentation/dev-tools/sparse.rst" for more details, +# including where to get the "sparse" utility. + +ifeq ("$(origin C)", "command line") + KBUILD_CHECKSRC = $(C) +endif +ifndef KBUILD_CHECKSRC + KBUILD_CHECKSRC = 0 +endif + +export KBUILD_CHECKSRC + +# Use make M=dir or set the environment variable KBUILD_EXTMOD to specify the +# directory of external module to build. Setting M= takes precedence. +ifeq ("$(origin M)", "command line") + KBUILD_EXTMOD := $(M) +endif + +$(if $(word 2, $(KBUILD_EXTMOD)), \ + $(error building multiple external modules is not supported)) + +export KBUILD_EXTMOD + # Kbuild will save output files in the current working directory. # This does not need to match to the root of the kernel source tree. # @@ -145,7 +175,8 @@ else need-sub-make := 1 endif -abs_srctree := $(realpath $(dir $(lastword $(MAKEFILE_LIST)))) +this-makefile := $(lastword $(MAKEFILE_LIST)) +abs_srctree := $(realpath $(dir $(this-makefile))) ifneq ($(words $(subst :, ,$(abs_srctree))), 1) $(error source directory cannot contain spaces or colons) @@ -160,8 +191,6 @@ MAKEFLAGS += --include-dir=$(abs_srctree) need-sub-make := 1 endif -this-makefile := $(lastword $(MAKEFILE_LIST)) - ifneq ($(filter 3.%,$(MAKE_VERSION)),) # 'MAKEFLAGS += -rR' does not immediately become effective for GNU Make 3.x # We need to invoke sub-make to avoid implicit rules in the top Makefile. @@ -195,36 +224,6 @@ ifeq ($(need-sub-make),) # so that IDEs/editors are able to understand relative filenames. MAKEFLAGS += --no-print-directory -# Call a source code checker (by default, "sparse") as part of the -# C compilation. -# -# Use 'make C=1' to enable checking of only re-compiled files. -# Use 'make C=2' to enable checking of *all* source files, regardless -# of whether they are re-compiled or not. -# -# See the file "Documentation/dev-tools/sparse.rst" for more details, -# including where to get the "sparse" utility. - -ifeq ("$(origin C)", "command line") - KBUILD_CHECKSRC = $(C) -endif -ifndef KBUILD_CHECKSRC - KBUILD_CHECKSRC = 0 -endif - -# Use make M=dir or set the environment variable KBUILD_EXTMOD to specify the -# directory of external module to build. Setting M= takes precedence. -ifeq ("$(origin M)", "command line") - KBUILD_EXTMOD := $(M) -endif - -$(if $(word 2, $(KBUILD_EXTMOD)), \ - $(error building multiple external modules is not supported)) - -export KBUILD_CHECKSRC KBUILD_EXTMOD - -extmod-prefix = $(if $(KBUILD_EXTMOD),$(KBUILD_EXTMOD)/) - ifeq ($(abs_srctree),$(abs_objtree)) # building in the source tree srctree := . @@ -257,7 +256,6 @@ export building_out_of_srctree srctree objtree VPATH # of make so .config is not included in this case either (for *config). version_h := include/generated/uapi/linux/version.h -old_version_h := include/linux/version.h clean-targets := %clean mrproper cleandocs no-dot-config-targets := $(clean-targets) \ @@ -559,7 +557,13 @@ ifdef building_out_of_srctree { echo "# this is build directory, ignore it"; echo "*"; } > .gitignore endif -ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) +# The expansion should be delayed until arch/$(SRCARCH)/Makefile is included. +# Some architectures define CROSS_COMPILE in arch/$(SRCARCH)/Makefile. +# CC_VERSION_TEXT is referenced from Kconfig (so it needs export), +# and from include/config/auto.conf.cmd to detect the compiler upgrade. +CC_VERSION_TEXT = $(shell $(CC) --version 2>/dev/null | head -n 1 | sed 's/\#//g') + +ifneq ($(findstring clang,$(CC_VERSION_TEXT)),) ifneq ($(CROSS_COMPILE),) CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%)) GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit)) @@ -578,12 +582,6 @@ KBUILD_AFLAGS += $(CLANG_FLAGS) export CLANG_FLAGS endif -# The expansion should be delayed until arch/$(SRCARCH)/Makefile is included. -# Some architectures define CROSS_COMPILE in arch/$(SRCARCH)/Makefile. -# CC_VERSION_TEXT is referenced from Kconfig (so it needs export), -# and from include/config/auto.conf.cmd to detect the compiler upgrade. -CC_VERSION_TEXT = $(shell $(CC) --version 2>/dev/null | head -n 1) - ifdef config-build # =========================================================================== # *config targets only - make sure prerequisites are updated, and descend @@ -833,8 +831,10 @@ ifneq ($(LLVM_IAS),1) KBUILD_AFLAGS += -Wa,-gdwarf-2 endif -ifdef CONFIG_DEBUG_INFO_DWARF4 -DEBUG_CFLAGS += -gdwarf-4 +ifndef CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT +dwarf-version-$(CONFIG_DEBUG_INFO_DWARF4) := 4 +dwarf-version-$(CONFIG_DEBUG_INFO_DWARF5) := 5 +DEBUG_CFLAGS += -gdwarf-$(dwarf-version-y) endif ifdef CONFIG_DEBUG_INFO_REDUCED @@ -1073,7 +1073,7 @@ ifdef CONFIG_MODULE_COMPRESS mod_compress_cmd = $(KGZIP) -n -f endif # CONFIG_MODULE_COMPRESS_GZIP ifdef CONFIG_MODULE_COMPRESS_XZ - mod_compress_cmd = $(XZ) -f + mod_compress_cmd = $(XZ) --lzma2=dict=2MiB -f endif # CONFIG_MODULE_COMPRESS_XZ endif # CONFIG_MODULE_COMPRESS export mod_compress_cmd @@ -1125,6 +1125,7 @@ endif # CONFIG_BPF PHONY += prepare0 +extmod-prefix = $(if $(KBUILD_EXTMOD),$(KBUILD_EXTMOD)/) export MODORDER := $(extmod-prefix)modules.order export MODULES_NSDEPS := $(extmod-prefix)modules.nsdeps @@ -1323,14 +1324,22 @@ define filechk_utsrelease.h endef define filechk_version.h - echo \#define LINUX_VERSION_CODE $(shell \ - expr $(VERSION) \* 65536 + 0$(PATCHLEVEL) \* 256 + 0$(SUBLEVEL)); \ - echo '#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c))' + if [ $(SUBLEVEL) -gt 255 ]; then \ + echo \#define LINUX_VERSION_CODE $(shell \ + expr $(VERSION) \* 65536 + 0$(PATCHLEVEL) \* 256 + 255); \ + else \ + echo \#define LINUX_VERSION_CODE $(shell \ + expr $(VERSION) \* 65536 + 0$(PATCHLEVEL) \* 256 + $(SUBLEVEL)); \ + fi; \ + echo '#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + \ + ((c) > 255 ? 255 : (c)))'; \ + echo \#define LINUX_VERSION_MAJOR $(VERSION); \ + echo \#define LINUX_VERSION_PATCHLEVEL $(PATCHLEVEL); \ + echo \#define LINUX_VERSION_SUBLEVEL $(SUBLEVEL) endef $(version_h): FORCE $(call filechk,version.h) - $(Q)rm -f $(old_version_h) include/generated/utsrelease.h: include/config/kernel.release FORCE $(call filechk,utsrelease.h) @@ -1517,7 +1526,7 @@ endif # CONFIG_MODULES # Directories & files removed with 'make clean' CLEAN_FILES += include/ksym vmlinux.symvers \ modules.builtin modules.builtin.modinfo modules.nsdeps \ - compile_commands.json + compile_commands.json .thinlto-cache # Directories & files removed with 'make mrproper' MRPROPER_FILES += include/config include/generated \ @@ -1531,7 +1540,7 @@ MRPROPER_FILES += include/config include/generated \ *.spec # Directories & files removed with 'make distclean' -DISTCLEAN_FILES += tags TAGS cscope* GPATH GTAGS GRTAGS GSYMS .thinlto-cache +DISTCLEAN_FILES += tags TAGS cscope* GPATH GTAGS GRTAGS GSYMS # clean - Delete most, but leave enough to build external modules # diff --git a/arch/alpha/configs/defconfig b/arch/alpha/configs/defconfig index 6293675db164..724c4075df40 100644 --- a/arch/alpha/configs/defconfig +++ b/arch/alpha/configs/defconfig @@ -1,4 +1,3 @@ -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 diff --git a/arch/alpha/kernel/syscalls/Makefile b/arch/alpha/kernel/syscalls/Makefile index 659faefdcb1d..285aaba832d9 100644 --- a/arch/alpha/kernel/syscalls/Makefile +++ b/arch/alpha/kernel/syscalls/Makefile @@ -5,7 +5,7 @@ uapi := arch/$(SRCARCH)/include/generated/uapi/asm _dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') -syscall := $(srctree)/$(src)/syscall.tbl +syscall := $(src)/syscall.tbl syshdr := $(srctree)/$(src)/syscallhdr.sh systbl := $(srctree)/$(src)/syscalltbl.sh @@ -21,18 +21,19 @@ quiet_cmd_systbl = SYSTBL $@ '$(systbl_abi_$(basetarget))' \ '$(systbl_offset_$(basetarget))' -$(uapi)/unistd_32.h: $(syscall) $(syshdr) +$(uapi)/unistd_32.h: $(syscall) $(syshdr) FORCE $(call if_changed,syshdr) -$(kapi)/syscall_table.h: $(syscall) $(systbl) +$(kapi)/syscall_table.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) uapisyshdr-y += unistd_32.h kapisyshdr-y += syscall_table.h -targets += $(uapisyshdr-y) $(kapisyshdr-y) +uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) +kapisyshdr-y := $(addprefix $(kapi)/, $(kapisyshdr-y)) +targets += $(addprefix ../../../../, $(uapisyshdr-y) $(kapisyshdr-y)) PHONY += all -all: $(addprefix $(uapi)/,$(uapisyshdr-y)) -all: $(addprefix $(kapi)/,$(kapisyshdr-y)) +all: $(uapisyshdr-y) $(kapisyshdr-y) @: diff --git a/arch/arm/tools/Makefile b/arch/arm/tools/Makefile index 27d8beb7c941..3654f979851b 100644 --- a/arch/arm/tools/Makefile +++ b/arch/arm/tools/Makefile @@ -11,7 +11,7 @@ uapi := $(gen)/uapi/asm syshdr := $(srctree)/$(src)/syscallhdr.sh sysnr := $(srctree)/$(src)/syscallnr.sh systbl := $(srctree)/$(src)/syscalltbl.sh -syscall := $(srctree)/$(src)/syscall.tbl +syscall := $(src)/syscall.tbl gen-y := $(gen)/calls-oabi.S gen-y += $(gen)/calls-eabi.S diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index fd8abf9cb312..1f212b47a48a 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -140,6 +140,7 @@ config ARM64 select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48) select HAVE_ARCH_KASAN_SW_TAGS if HAVE_ARCH_KASAN select HAVE_ARCH_KASAN_HW_TAGS if (HAVE_ARCH_KASAN && ARM64_MTE) + select HAVE_ARCH_KFENCE select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT @@ -998,6 +999,7 @@ config HOTPLUG_CPU # Common NUMA Features config NUMA bool "NUMA Memory Allocation and Scheduler Support" + select GENERIC_ARCH_NUMA select ACPI_NUMA if ACPI select OF_NUMA help @@ -1485,7 +1487,7 @@ config ARM64_PTR_AUTH depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC # Modern compilers insert a .note.gnu.property section note for PAC # which is only understood by binutils starting with version 2.33.1. - depends on LD_IS_LLD || LD_VERSION >= 233010000 || (CC_IS_GCC && GCC_VERSION < 90100) + depends on LD_IS_LLD || LD_VERSION >= 23301 || (CC_IS_GCC && GCC_VERSION < 90100) depends on !CC_IS_CLANG || AS_HAS_CFI_NEGATE_RA_STATE depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS) help diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 77cbbe3625f2..a074459f8f2f 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -6,7 +6,6 @@ #define __ASM_CACHE_H #include -#include #define CTR_L1IP_SHIFT 14 #define CTR_L1IP_MASK 3 diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h index 0aaf9044cd6a..12d5f47f7dbe 100644 --- a/arch/arm64/include/asm/kasan.h +++ b/arch/arm64/include/asm/kasan.h @@ -6,6 +6,7 @@ #include #include +#include #include #define arch_kasan_set_tag(addr, tag) __tag_set(addr, tag) diff --git a/arch/arm64/include/asm/kfence.h b/arch/arm64/include/asm/kfence.h new file mode 100644 index 000000000000..d061176d57ea --- /dev/null +++ b/arch/arm64/include/asm/kfence.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * arm64 KFENCE support. + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef __ASM_KFENCE_H +#define __ASM_KFENCE_H + +#include + +static inline bool arch_kfence_init_pool(void) { return true; } + +static inline bool kfence_protect_page(unsigned long addr, bool protect) +{ + set_memory_valid(addr, 1, !protect); + + return true; +} + +#endif /* __ASM_KFENCE_H */ diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h index 691f15af788e..810045628c66 100644 --- a/arch/arm64/include/asm/module.lds.h +++ b/arch/arm64/include/asm/module.lds.h @@ -1,7 +1,7 @@ #ifdef CONFIG_ARM64_MODULE_PLTS SECTIONS { - .plt (NOLOAD) : { BYTE(0) } - .init.plt (NOLOAD) : { BYTE(0) } - .text.ftrace_trampoline (NOLOAD) : { BYTE(0) } + .plt 0 (NOLOAD) : { BYTE(0) } + .init.plt 0 (NOLOAD) : { BYTE(0) } + .text.ftrace_trampoline 0 (NOLOAD) : { BYTE(0) } } #endif diff --git a/arch/arm64/include/asm/mte-def.h b/arch/arm64/include/asm/mte-def.h index 2d73a1612f09..cf241b0f0a42 100644 --- a/arch/arm64/include/asm/mte-def.h +++ b/arch/arm64/include/asm/mte-def.h @@ -11,4 +11,6 @@ #define MTE_TAG_SIZE 4 #define MTE_TAG_MASK GENMASK((MTE_TAG_SHIFT + (MTE_TAG_SIZE - 1)), MTE_TAG_SHIFT) +#define __MTE_PREAMBLE ARM64_ASM_PREAMBLE ".arch_extension memtag\n" + #endif /* __ASM_MTE_DEF_H */ diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h index 3748d5bb88c0..7ab500e2ad17 100644 --- a/arch/arm64/include/asm/mte-kasan.h +++ b/arch/arm64/include/asm/mte-kasan.h @@ -11,12 +11,15 @@ #include -/* - * The functions below are meant to be used only for the - * KASAN_HW_TAGS interface defined in asm/memory.h. - */ #ifdef CONFIG_ARM64_MTE +/* + * These functions are meant to be only used from KASAN runtime through + * the arch_*() interface defined in asm/memory.h. + * These functions don't include system_supports_mte() checks, + * as KASAN only calls them when MTE is supported and enabled. + */ + static inline u8 mte_get_ptr_tag(void *ptr) { /* Note: The format of KASAN tags is 0xF */ @@ -25,9 +28,54 @@ static inline u8 mte_get_ptr_tag(void *ptr) return tag; } -u8 mte_get_mem_tag(void *addr); -u8 mte_get_random_tag(void); -void *mte_set_mem_tag_range(void *addr, size_t size, u8 tag); +/* Get allocation tag for the address. */ +static inline u8 mte_get_mem_tag(void *addr) +{ + asm(__MTE_PREAMBLE "ldg %0, [%0]" + : "+r" (addr)); + + return mte_get_ptr_tag(addr); +} + +/* Generate a random tag. */ +static inline u8 mte_get_random_tag(void) +{ + void *addr; + + asm(__MTE_PREAMBLE "irg %0, %0" + : "=r" (addr)); + + return mte_get_ptr_tag(addr); +} + +/* + * Assign allocation tags for a region of memory based on the pointer tag. + * Note: The address must be non-NULL and MTE_GRANULE_SIZE aligned and + * size must be non-zero and MTE_GRANULE_SIZE aligned. + */ +static inline void mte_set_mem_tag_range(void *addr, size_t size, u8 tag) +{ + u64 curr, end; + + if (!size) + return; + + curr = (u64)__tag_set(addr, tag); + end = curr + size; + + do { + /* + * 'asm volatile' is required to prevent the compiler to move + * the statement outside of the loop. + */ + asm volatile(__MTE_PREAMBLE "stg %0, [%0]" + : + : "r" (curr) + : "memory"); + + curr += MTE_GRANULE_SIZE; + } while (curr != end); +} void mte_enable_kernel(void); void mte_init_tags(u64 max_tag); @@ -46,13 +94,14 @@ static inline u8 mte_get_mem_tag(void *addr) { return 0xFF; } + static inline u8 mte_get_random_tag(void) { return 0xFF; } -static inline void *mte_set_mem_tag_range(void *addr, size_t size, u8 tag) + +static inline void mte_set_mem_tag_range(void *addr, size_t size, u8 tag) { - return addr; } static inline void mte_enable_kernel(void) diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h index d02aff9f493d..9b557a457f24 100644 --- a/arch/arm64/include/asm/mte.h +++ b/arch/arm64/include/asm/mte.h @@ -8,8 +8,6 @@ #include #include -#define __MTE_PREAMBLE ARM64_ASM_PREAMBLE ".arch_extension memtag\n" - #ifndef __ASSEMBLY__ #include diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h index dd870390d639..8c8cf4297cc3 100644 --- a/arch/arm64/include/asm/numa.h +++ b/arch/arm64/include/asm/numa.h @@ -3,52 +3,6 @@ #define __ASM_NUMA_H #include - -#ifdef CONFIG_NUMA - -#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2) - -int __node_distance(int from, int to); -#define node_distance(a, b) __node_distance(a, b) - -extern nodemask_t numa_nodes_parsed __initdata; - -extern bool numa_off; - -/* Mappings between node number and cpus on that node. */ -extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; -void numa_clear_node(unsigned int cpu); - -#ifdef CONFIG_DEBUG_PER_CPU_MAPS -const struct cpumask *cpumask_of_node(int node); -#else -/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ -static inline const struct cpumask *cpumask_of_node(int node) -{ - if (node == NUMA_NO_NODE) - return cpu_all_mask; - - return node_to_cpumask_map[node]; -} -#endif - -void __init arm64_numa_init(void); -int __init numa_add_memblk(int nodeid, u64 start, u64 end); -void __init numa_set_distance(int from, int to, int distance); -void __init numa_free_distance(void); -void __init early_map_cpu_to_node(unsigned int cpu, int nid); -void numa_store_cpu_info(unsigned int cpu); -void numa_add_cpu(unsigned int cpu); -void numa_remove_cpu(unsigned int cpu); - -#else /* CONFIG_NUMA */ - -static inline void numa_store_cpu_info(unsigned int cpu) { } -static inline void numa_add_cpu(unsigned int cpu) { } -static inline void numa_remove_cpu(unsigned int cpu) { } -static inline void arm64_numa_init(void) { } -static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { } - -#endif /* CONFIG_NUMA */ +#include #endif /* __ASM_NUMA_H */ diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c index 7ff800045434..fdfecf0991ce 100644 --- a/arch/arm64/kernel/acpi_numa.c +++ b/arch/arm64/kernel/acpi_numa.c @@ -118,15 +118,3 @@ void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) node_set(node, numa_nodes_parsed); } -int __init arm64_acpi_numa_init(void) -{ - int ret; - - ret = acpi_numa_init(); - if (ret) { - pr_info("Failed to initialise from firmware\n"); - return ret; - } - - return srat_disabled() ? -EINVAL : 0; -} diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 1e30b5550d2a..66b0e0b66e31 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -837,6 +837,7 @@ SYM_FUNC_START_LOCAL(__primary_switch) tlbi vmalle1 // Remove any stale TLB entries dsb nsh + isb set_sctlr_el1 x19 // re-enable the MMU diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index 678cd2c618ee..5eccbd62fec8 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -75,9 +75,6 @@ SYM_CODE_END(el1_sync) // nVHE? No way! Give me the real thing! SYM_CODE_START_LOCAL(mutate_to_vhe) - // Be prepared to fail - mov_q x0, HVC_STUB_ERR - // Sanity check: MMU *must* be off mrs x1, sctlr_el2 tbnz x1, #0, 1f @@ -96,8 +93,11 @@ SYM_CODE_START_LOCAL(mutate_to_vhe) cmp x1, xzr and x2, x2, x1 csinv x2, x2, xzr, ne - cbz x2, 1f + cbnz x2, 2f +1: mov_q x0, HVC_STUB_ERR + eret +2: // Engage the VHE magic! mov_q x0, HCR_HOST_VHE_FLAGS msr hcr_el2, x0 @@ -131,9 +131,28 @@ SYM_CODE_START_LOCAL(mutate_to_vhe) msr mair_el1, x0 isb + // Hack the exception return to stay at EL2 + mrs x0, spsr_el1 + and x0, x0, #~PSR_MODE_MASK + mov x1, #PSR_MODE_EL2h + orr x0, x0, x1 + msr spsr_el1, x0 + + b enter_vhe +SYM_CODE_END(mutate_to_vhe) + + // At the point where we reach enter_vhe(), we run with + // the MMU off (which is enforced by mutate_to_vhe()). + // We thus need to be in the idmap, or everything will + // explode when enabling the MMU. + + .pushsection .idmap.text, "ax" + +SYM_CODE_START_LOCAL(enter_vhe) // Invalidate TLBs before enabling the MMU tlbi vmalle1 dsb nsh + isb // Enable the EL2 S1 MMU, as set up from EL1 mrs_s x0, SYS_SCTLR_EL12 @@ -143,17 +162,12 @@ SYM_CODE_START_LOCAL(mutate_to_vhe) mov_q x0, INIT_SCTLR_EL1_MMU_OFF msr_s SYS_SCTLR_EL12, x0 - // Hack the exception return to stay at EL2 - mrs x0, spsr_el1 - and x0, x0, #~PSR_MODE_MASK - mov x1, #PSR_MODE_EL2h - orr x0, x0, x1 - msr spsr_el1, x0 - mov x0, xzr -1: eret -SYM_CODE_END(mutate_to_vhe) + eret +SYM_CODE_END(enter_vhe) + + .popsection .macro invalid_vector label SYM_CODE_START_LOCAL(\label) diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 03210f644790..0cde47a63beb 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -182,8 +182,10 @@ static int create_dtb(struct kimage *image, /* duplicate a device tree blob */ ret = fdt_open_into(initial_boot_params, buf, buf_size); - if (ret) + if (ret) { + vfree(buf); return -EINVAL; + } ret = setup_dtb(image, initrd_load_addr, initrd_len, cmdline, buf); diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 2cfc850809ce..b3c70a612c7a 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include @@ -88,51 +87,6 @@ int memcmp_pages(struct page *page1, struct page *page2) return ret; } -u8 mte_get_mem_tag(void *addr) -{ - if (!system_supports_mte()) - return 0xFF; - - asm(__MTE_PREAMBLE "ldg %0, [%0]" - : "+r" (addr)); - - return mte_get_ptr_tag(addr); -} - -u8 mte_get_random_tag(void) -{ - void *addr; - - if (!system_supports_mte()) - return 0xFF; - - asm(__MTE_PREAMBLE "irg %0, %0" - : "+r" (addr)); - - return mte_get_ptr_tag(addr); -} - -void *mte_set_mem_tag_range(void *addr, size_t size, u8 tag) -{ - void *ptr = addr; - - if ((!system_supports_mte()) || (size == 0)) - return addr; - - /* Make sure that size is MTE granule aligned. */ - WARN_ON(size & (MTE_GRANULE_SIZE - 1)); - - /* Make sure that the address is MTE granule aligned. */ - WARN_ON((u64)addr & (MTE_GRANULE_SIZE - 1)); - - tag = 0xF0 | tag; - ptr = (void *)__tag_set(ptr, tag); - - mte_assign_mem_tag_range(ptr, size); - - return ptr; -} - void mte_init_tags(u64 max_tag) { static bool gcr_kernel_excl_initialized; diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c index a412d8edbcd2..2c247634552b 100644 --- a/arch/arm64/kernel/probes/uprobes.c +++ b/arch/arm64/kernel/probes/uprobes.c @@ -38,7 +38,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, /* TODO: Currently we do not support AARCH32 instruction probing */ if (mm->context.flags & MMCF_AARCH32) - return -ENOTSUPP; + return -EOPNOTSUPP; else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE)) return -EINVAL; diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 3d5c8afca75b..170f42fd6101 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1797,7 +1797,7 @@ int syscall_trace_enter(struct pt_regs *regs) if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) { tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER); - if (!in_syscall(regs) || (flags & _TIF_SYSCALL_EMU)) + if (flags & _TIF_SYSCALL_EMU) return NO_SYSCALL; } diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index a3f3163eb697..f7e66cca9f12 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -46,7 +46,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) /* Terminal record; nothing to unwind */ if (!fp) - return -EINVAL; + return -ENOENT; if (fp & 0xf) return -EINVAL; diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index a67b37a7a47e..d7564891ffe1 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -119,7 +119,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) if (!ret) ret = -EOPNOTSUPP; } else { - __cpu_suspend_exit(); + RCU_NONIDLE(__cpu_suspend_exit()); } unpause_graph_tracing(); diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index d179056e1af8..5f49df4ffdd8 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -119,7 +119,7 @@ el2_error: .macro invalid_vector label, target = __guest_exit_panic .align 2 -SYM_CODE_START(\label) +SYM_CODE_START_LOCAL(\label) b \target SYM_CODE_END(\label) .endm diff --git a/arch/arm64/lib/mte.S b/arch/arm64/lib/mte.S index 9e1a12e10053..351537c12f36 100644 --- a/arch/arm64/lib/mte.S +++ b/arch/arm64/lib/mte.S @@ -149,19 +149,3 @@ SYM_FUNC_START(mte_restore_page_tags) ret SYM_FUNC_END(mte_restore_page_tags) - -/* - * Assign allocation tags for a region of memory based on the pointer tag - * x0 - source pointer - * x1 - size - * - * Note: The address must be non-NULL and MTE_GRANULE_SIZE aligned and - * size must be non-zero and MTE_GRANULE_SIZE aligned. - */ -SYM_FUNC_START(mte_assign_mem_tag_range) -1: stg x0, [x0] - add x0, x0, #MTE_GRANULE_SIZE - subs x1, x1, #MTE_GRANULE_SIZE - b.gt 1b - ret -SYM_FUNC_END(mte_assign_mem_tag_range) diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index 77222d92667a..f188c9092696 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -7,7 +7,6 @@ obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_PTDUMP_CORE) += ptdump.o obj-$(CONFIG_PTDUMP_DEBUGFS) += ptdump_debugfs.o obj-$(CONFIG_TRANS_TABLE) += trans_pgd.o -obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o obj-$(CONFIG_ARM64_MTE) += mteswap.o KASAN_SANITIZE_physaddr.o += n diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index dc9f96442edc..f37d4e3830b7 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -389,6 +390,9 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { + if (kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) + return; + msg = "paging request"; } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 709d98fea90c..0ace5e68efba 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -416,10 +416,10 @@ void __init bootmem_init(void) max_pfn = max_low_pfn = max; min_low_pfn = min; - arm64_numa_init(); + arch_numa_init(); /* - * must be done after arm64_numa_init() which calls numa_init() to + * must be done after arch_numa_init() which calls numa_init() to * initialize node_online_map that gets used in hugetlb_cma_reserve() * while allocating required CMA size across online nodes. */ diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 25af183e4bed..3802cfbdd20d 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1155,7 +1155,7 @@ void vmemmap_free(unsigned long start, unsigned long end, } #endif /* CONFIG_SPARSEMEM_VMEMMAP */ -static inline pud_t * fixmap_pud(unsigned long addr) +static inline pud_t *fixmap_pud(unsigned long addr) { pgd_t *pgdp = pgd_offset_k(addr); p4d_t *p4dp = p4d_offset(pgdp, addr); @@ -1166,7 +1166,7 @@ static inline pud_t * fixmap_pud(unsigned long addr) return pud_offset_kimg(p4dp, addr); } -static inline pmd_t * fixmap_pmd(unsigned long addr) +static inline pmd_t *fixmap_pmd(unsigned long addr) { pud_t *pudp = fixmap_pud(addr); pud_t pud = READ_ONCE(*pudp); @@ -1176,7 +1176,7 @@ static inline pmd_t * fixmap_pmd(unsigned long addr) return pmd_offset_kimg(pudp, addr); } -static inline pte_t * fixmap_pte(unsigned long addr) +static inline pte_t *fixmap_pte(unsigned long addr) { return &bm_pte[pte_index(addr)]; } @@ -1444,16 +1444,19 @@ 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) +struct range arch_get_mappable_range(void) { + struct range mhp_range; + /* * 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); + mhp_range.start = __pa(_PAGE_OFFSET(vabits_actual)); + mhp_range.end = __pa(PAGE_END - 1); + return mhp_range; } int arch_add_memory(int nid, u64 start, u64 size, @@ -1461,12 +1464,14 @@ int arch_add_memory(int nid, u64 start, u64 size, { 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; - } + VM_BUG_ON(!mhp_range_allowed(start, size, true)); - if (rodata_full || debug_pagealloc_enabled()) + /* + * KFENCE requires linear map to be mapped at page granularity, so that + * it is possible to protect/unprotect single pages in the KFENCE pool. + */ + if (rodata_full || debug_pagealloc_enabled() || + IS_ENABLED(CONFIG_KFENCE)) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile index f3328a29e881..3e9da5e6c3bd 100644 --- a/arch/ia64/Makefile +++ b/arch/ia64/Makefile @@ -85,9 +85,3 @@ define archhelp echo ' install - Install compressed kernel image' echo '* unwcheck - Check vmlinux for invalid unwind info' endef - -archprepare: make_nr_irqs_h -PHONY += make_nr_irqs_h - -make_nr_irqs_h: - $(Q)$(MAKE) $(build)=arch/ia64/kernel include/generated/nr-irqs.h diff --git a/arch/ia64/include/asm/irq.h b/arch/ia64/include/asm/irq.h index 5acf52e90872..0eccf33dfe8b 100644 --- a/arch/ia64/include/asm/irq.h +++ b/arch/ia64/include/asm/irq.h @@ -14,7 +14,9 @@ #include #include -#include +#include + +#define NR_IRQS IA64_NATIVE_NR_IRQS static __inline__ int irq_canonicalize (int irq) diff --git a/arch/ia64/include/asm/mca.h b/arch/ia64/include/asm/mca.h index 726df17f1b51..05805249296c 100644 --- a/arch/ia64/include/asm/mca.h +++ b/arch/ia64/include/asm/mca.h @@ -14,13 +14,10 @@ #if !defined(__ASSEMBLY__) -#include +#include +#include #include - -#include -#include -#include -#include +#include #define IA64_MCA_RENDEZ_TIMEOUT (20 * 1000) /* value in milliseconds - 20 seconds */ @@ -83,7 +80,7 @@ struct ia64_sal_os_state { /* common */ unsigned long sal_ra; /* Return address in SAL, physical */ unsigned long sal_gp; /* GP of the SAL - physical */ - pal_min_state_area_t *pal_min_state; /* from R17. physical in asm, virtual in C */ + struct pal_min_state_area *pal_min_state; /* from R17. physical in asm, virtual in C */ /* Previous values of IA64_KR(CURRENT) and IA64_KR(CURRENT_STACK). * Note: if the MCA/INIT recovery code wants to resume to a new context * then it must change these values to reflect the new kernel stack. diff --git a/arch/ia64/include/asm/pal.h b/arch/ia64/include/asm/pal.h index f9d2b3b2dfad..b1d87955e8cc 100644 --- a/arch/ia64/include/asm/pal.h +++ b/arch/ia64/include/asm/pal.h @@ -750,7 +750,7 @@ typedef union pal_mc_error_info_u { * for PAL. */ -typedef struct pal_min_state_area_s { +struct pal_min_state_area { u64 pmsa_nat_bits; /* nat bits for saved GRs */ u64 pmsa_gr[15]; /* GR1 - GR15 */ u64 pmsa_bank0_gr[16]; /* GR16 - GR31 */ @@ -766,7 +766,7 @@ typedef struct pal_min_state_area_s { u64 pmsa_xfs; /* previous ifs */ u64 pmsa_br1; /* branch register 1 */ u64 pmsa_reserved[70]; /* pal_min_state_area should total to 1KB */ -} pal_min_state_area_t; +}; struct ia64_pal_retval { diff --git a/arch/ia64/include/asm/sal.h b/arch/ia64/include/asm/sal.h index 08f5b6aaed73..78f4f7b40435 100644 --- a/arch/ia64/include/asm/sal.h +++ b/arch/ia64/include/asm/sal.h @@ -385,7 +385,7 @@ typedef struct sal_processor_static_info { fr : 1, reserved : 58; } valid; - pal_min_state_area_t min_state_area; + struct pal_min_state_area min_state_area; u64 br[8]; u64 cr[128]; u64 ar[128]; diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index c89bd5f8cbf8..78717819131c 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -47,8 +47,3 @@ CFLAGS_traps.o += -mfixed-range=f2-f5,f16-f31 # The gate DSO image is built using a special linker script. include $(src)/Makefile.gate - -include/generated/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s FORCE - $(call filechk,offsets,__ASM_NR_IRQS_H__) - -targets += nr-irqs.s diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c index fb0deb8a4221..be3b90fef2e9 100644 --- a/arch/ia64/kernel/asm-offsets.c +++ b/arch/ia64/kernel/asm-offsets.c @@ -245,23 +245,23 @@ void foo(void) BLANK(); DEFINE(IA64_PMSA_GR_OFFSET, - offsetof (struct pal_min_state_area_s, pmsa_gr)); + offsetof(struct pal_min_state_area, pmsa_gr)); DEFINE(IA64_PMSA_BANK1_GR_OFFSET, - offsetof (struct pal_min_state_area_s, pmsa_bank1_gr)); + offsetof(struct pal_min_state_area, pmsa_bank1_gr)); DEFINE(IA64_PMSA_PR_OFFSET, - offsetof (struct pal_min_state_area_s, pmsa_pr)); + offsetof(struct pal_min_state_area, pmsa_pr)); DEFINE(IA64_PMSA_BR0_OFFSET, - offsetof (struct pal_min_state_area_s, pmsa_br0)); + offsetof(struct pal_min_state_area, pmsa_br0)); DEFINE(IA64_PMSA_RSC_OFFSET, - offsetof (struct pal_min_state_area_s, pmsa_rsc)); + offsetof(struct pal_min_state_area, pmsa_rsc)); DEFINE(IA64_PMSA_IIP_OFFSET, - offsetof (struct pal_min_state_area_s, pmsa_iip)); + offsetof(struct pal_min_state_area, pmsa_iip)); DEFINE(IA64_PMSA_IPSR_OFFSET, - offsetof (struct pal_min_state_area_s, pmsa_ipsr)); + offsetof(struct pal_min_state_area, pmsa_ipsr)); DEFINE(IA64_PMSA_IFS_OFFSET, - offsetof (struct pal_min_state_area_s, pmsa_ifs)); + offsetof(struct pal_min_state_area, pmsa_ifs)); DEFINE(IA64_PMSA_XIP_OFFSET, - offsetof (struct pal_min_state_area_s, pmsa_xip)); + offsetof(struct pal_min_state_area, pmsa_xip)); BLANK(); /* used by fsys_gettimeofday in arch/ia64/kernel/fsys.S */ diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c index 4f47741005d2..76730f34685c 100644 --- a/arch/ia64/kernel/crash.c +++ b/arch/ia64/kernel/crash.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index dd7fd750bb93..c5fe21de46a8 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 0fea266b4d39..d4cae2fc69ca 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -97,6 +97,7 @@ #include #include #include +#include #include #include @@ -895,7 +896,7 @@ static void finish_pt_regs(struct pt_regs *regs, struct ia64_sal_os_state *sos, unsigned long *nat) { - const pal_min_state_area_t *ms = sos->pal_min_state; + const struct pal_min_state_area *ms = sos->pal_min_state; const u64 *bank; /* If ipsr.ic then use pmsa_{iip,ipsr,ifs}, else use @@ -971,7 +972,7 @@ ia64_mca_modify_original_stack(struct pt_regs *regs, char *p; ia64_va va; extern char ia64_leave_kernel[]; /* Need asm address, not function descriptor */ - const pal_min_state_area_t *ms = sos->pal_min_state; + const struct pal_min_state_area *ms = sos->pal_min_state; struct task_struct *previous_current; struct pt_regs *old_regs; struct switch_stack *old_sw; diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index 4d0ab323dee8..36a69b4e6169 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -496,7 +496,7 @@ recover_from_read_error(slidx_table_t *slidx, struct ia64_sal_os_state *sos) { u64 target_identifier; - pal_min_state_area_t *pmsa; + struct pal_min_state_area *pmsa; struct ia64_psr *psr1, *psr2; ia64_fptr_t *mca_hdlr_bh = (ia64_fptr_t*)mca_handler_bhhook; diff --git a/arch/ia64/kernel/nr-irqs.c b/arch/ia64/kernel/nr-irqs.c deleted file mode 100644 index f2633b22d3be..000000000000 --- a/arch/ia64/kernel/nr-irqs.c +++ /dev/null @@ -1,22 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * calculate - * NR_IRQS = max(IA64_NATIVE_NR_IRQS, XEN_NR_IRQS, FOO_NR_IRQS...) - * depending on config. - * This must be calculated before processing asm-offset.c. - */ - -#define ASM_OFFSETS_C 1 - -#include -#include -#include - -void foo(void) -{ - union paravirt_nr_irqs_max { - char ia64_native_nr_irqs[IA64_NATIVE_NR_IRQS]; - }; - - DEFINE(NR_IRQS, sizeof (union paravirt_nr_irqs_max)); -} diff --git a/arch/ia64/kernel/syscalls/Makefile b/arch/ia64/kernel/syscalls/Makefile index 813a58cba39c..bf4bda0f63eb 100644 --- a/arch/ia64/kernel/syscalls/Makefile +++ b/arch/ia64/kernel/syscalls/Makefile @@ -5,7 +5,7 @@ uapi := arch/$(SRCARCH)/include/generated/uapi/asm _dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') -syscall := $(srctree)/$(src)/syscall.tbl +syscall := $(src)/syscall.tbl syshdr := $(srctree)/$(src)/syscallhdr.sh systbl := $(srctree)/$(src)/syscalltbl.sh @@ -22,19 +22,20 @@ quiet_cmd_systbl = SYSTBL $@ '$(systbl_offset_$(basetarget))' syshdr_offset_unistd_64 := __NR_Linux -$(uapi)/unistd_64.h: $(syscall) $(syshdr) +$(uapi)/unistd_64.h: $(syscall) $(syshdr) FORCE $(call if_changed,syshdr) systbl_offset_syscall_table := 1024 -$(kapi)/syscall_table.h: $(syscall) $(systbl) +$(kapi)/syscall_table.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) uapisyshdr-y += unistd_64.h kapisyshdr-y += syscall_table.h -targets += $(uapisyshdr-y) $(kapisyshdr-y) +uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) +kapisyshdr-y := $(addprefix $(kapi)/, $(kapisyshdr-y)) +targets += $(addprefix ../../../../, $(uapisyshdr-y) $(kapisyshdr-y)) PHONY += all -all: $(addprefix $(uapi)/,$(uapisyshdr-y)) -all: $(addprefix $(kapi)/,$(kapisyshdr-y)) +all: $(uapisyshdr-y) $(kapisyshdr-y) @: diff --git a/arch/m68k/coldfire/clk.c b/arch/m68k/coldfire/clk.c index 7bc666e482eb..076a9caa9557 100644 --- a/arch/m68k/coldfire/clk.c +++ b/arch/m68k/coldfire/clk.c @@ -90,6 +90,10 @@ EXPORT_SYMBOL(clk_get); int clk_enable(struct clk *clk) { unsigned long flags; + + if (!clk) + return -EINVAL; + spin_lock_irqsave(&clk_lock, flags); if ((clk->enabled++ == 0) && clk->clk_ops) clk->clk_ops->enable(clk); diff --git a/arch/m68k/kernel/syscalls/Makefile b/arch/m68k/kernel/syscalls/Makefile index 659faefdcb1d..285aaba832d9 100644 --- a/arch/m68k/kernel/syscalls/Makefile +++ b/arch/m68k/kernel/syscalls/Makefile @@ -5,7 +5,7 @@ uapi := arch/$(SRCARCH)/include/generated/uapi/asm _dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') -syscall := $(srctree)/$(src)/syscall.tbl +syscall := $(src)/syscall.tbl syshdr := $(srctree)/$(src)/syscallhdr.sh systbl := $(srctree)/$(src)/syscalltbl.sh @@ -21,18 +21,19 @@ quiet_cmd_systbl = SYSTBL $@ '$(systbl_abi_$(basetarget))' \ '$(systbl_offset_$(basetarget))' -$(uapi)/unistd_32.h: $(syscall) $(syshdr) +$(uapi)/unistd_32.h: $(syscall) $(syshdr) FORCE $(call if_changed,syshdr) -$(kapi)/syscall_table.h: $(syscall) $(systbl) +$(kapi)/syscall_table.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) uapisyshdr-y += unistd_32.h kapisyshdr-y += syscall_table.h -targets += $(uapisyshdr-y) $(kapisyshdr-y) +uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) +kapisyshdr-y := $(addprefix $(kapi)/, $(kapisyshdr-y)) +targets += $(addprefix ../../../../, $(uapisyshdr-y) $(kapisyshdr-y)) PHONY += all -all: $(addprefix $(uapi)/,$(uapisyshdr-y)) -all: $(addprefix $(kapi)/,$(kapisyshdr-y)) +all: $(uapisyshdr-y) $(kapisyshdr-y) @: diff --git a/arch/microblaze/kernel/syscalls/Makefile b/arch/microblaze/kernel/syscalls/Makefile index 659faefdcb1d..285aaba832d9 100644 --- a/arch/microblaze/kernel/syscalls/Makefile +++ b/arch/microblaze/kernel/syscalls/Makefile @@ -5,7 +5,7 @@ uapi := arch/$(SRCARCH)/include/generated/uapi/asm _dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') -syscall := $(srctree)/$(src)/syscall.tbl +syscall := $(src)/syscall.tbl syshdr := $(srctree)/$(src)/syscallhdr.sh systbl := $(srctree)/$(src)/syscalltbl.sh @@ -21,18 +21,19 @@ quiet_cmd_systbl = SYSTBL $@ '$(systbl_abi_$(basetarget))' \ '$(systbl_offset_$(basetarget))' -$(uapi)/unistd_32.h: $(syscall) $(syshdr) +$(uapi)/unistd_32.h: $(syscall) $(syshdr) FORCE $(call if_changed,syshdr) -$(kapi)/syscall_table.h: $(syscall) $(systbl) +$(kapi)/syscall_table.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) uapisyshdr-y += unistd_32.h kapisyshdr-y += syscall_table.h -targets += $(uapisyshdr-y) $(kapisyshdr-y) +uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) +kapisyshdr-y := $(addprefix $(kapi)/, $(kapisyshdr-y)) +targets += $(addprefix ../../../../, $(uapisyshdr-y) $(kapisyshdr-y)) PHONY += all -all: $(addprefix $(uapi)/,$(uapisyshdr-y)) -all: $(addprefix $(kapi)/,$(kapisyshdr-y)) +all: $(uapisyshdr-y) $(kapisyshdr-y) @: diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index 95f8f10d8697..31bcfa4e08b9 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -196,4 +196,4 @@ static int __init plat_dev_init(void) return 0; } -device_initcall(plat_dev_init); +arch_initcall(plat_dev_init); diff --git a/arch/mips/kernel/r4k-bugs64.c b/arch/mips/kernel/r4k-bugs64.c index 1ff19f1ea5ca..35729c9e6cfa 100644 --- a/arch/mips/kernel/r4k-bugs64.c +++ b/arch/mips/kernel/r4k-bugs64.c @@ -18,7 +18,7 @@ static char bug64hit[] __initdata = "reliable operation impossible!\n%s"; static char nowar[] __initdata = - "Please report to ."; + "Please report to ."; static char r4kwar[] __initdata = "Enable CPU_R4000_WORKAROUNDS to rectify."; static char daddiwar[] __initdata = diff --git a/arch/mips/kernel/syscalls/Makefile b/arch/mips/kernel/syscalls/Makefile index a1ce8b7dbcfa..51f8b805f2ed 100644 --- a/arch/mips/kernel/syscalls/Makefile +++ b/arch/mips/kernel/syscalls/Makefile @@ -5,9 +5,9 @@ uapi := arch/$(SRCARCH)/include/generated/uapi/asm _dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') -syscalln32 := $(srctree)/$(src)/syscall_n32.tbl -syscalln64 := $(srctree)/$(src)/syscall_n64.tbl -syscallo32 := $(srctree)/$(src)/syscall_o32.tbl +syscalln32 := $(src)/syscall_n32.tbl +syscalln64 := $(src)/syscall_n64.tbl +syscallo32 := $(src)/syscall_o32.tbl syshdr := $(srctree)/$(src)/syscallhdr.sh sysnr := $(srctree)/$(src)/syscallnr.sh systbl := $(srctree)/$(src)/syscalltbl.sh @@ -31,50 +31,50 @@ quiet_cmd_systbl = SYSTBL $@ '$(systbl_offset_$(basetarget))' syshdr_offset_unistd_n32 := __NR_Linux -$(uapi)/unistd_n32.h: $(syscalln32) $(syshdr) +$(uapi)/unistd_n32.h: $(syscalln32) $(syshdr) FORCE $(call if_changed,syshdr) syshdr_offset_unistd_n64 := __NR_Linux -$(uapi)/unistd_n64.h: $(syscalln64) $(syshdr) +$(uapi)/unistd_n64.h: $(syscalln64) $(syshdr) FORCE $(call if_changed,syshdr) syshdr_offset_unistd_o32 := __NR_Linux -$(uapi)/unistd_o32.h: $(syscallo32) $(syshdr) +$(uapi)/unistd_o32.h: $(syscallo32) $(syshdr) FORCE $(call if_changed,syshdr) sysnr_pfx_unistd_nr_n32 := N32 sysnr_offset_unistd_nr_n32 := 6000 -$(kapi)/unistd_nr_n32.h: $(syscalln32) $(sysnr) +$(kapi)/unistd_nr_n32.h: $(syscalln32) $(sysnr) FORCE $(call if_changed,sysnr) sysnr_pfx_unistd_nr_n64 := 64 sysnr_offset_unistd_nr_n64 := 5000 -$(kapi)/unistd_nr_n64.h: $(syscalln64) $(sysnr) +$(kapi)/unistd_nr_n64.h: $(syscalln64) $(sysnr) FORCE $(call if_changed,sysnr) sysnr_pfx_unistd_nr_o32 := O32 sysnr_offset_unistd_nr_o32 := 4000 -$(kapi)/unistd_nr_o32.h: $(syscallo32) $(sysnr) +$(kapi)/unistd_nr_o32.h: $(syscallo32) $(sysnr) FORCE $(call if_changed,sysnr) systbl_abi_syscall_table_32_o32 := 32_o32 systbl_offset_syscall_table_32_o32 := 4000 -$(kapi)/syscall_table_32_o32.h: $(syscallo32) $(systbl) +$(kapi)/syscall_table_32_o32.h: $(syscallo32) $(systbl) FORCE $(call if_changed,systbl) systbl_abi_syscall_table_64_n32 := 64_n32 systbl_offset_syscall_table_64_n32 := 6000 -$(kapi)/syscall_table_64_n32.h: $(syscalln32) $(systbl) +$(kapi)/syscall_table_64_n32.h: $(syscalln32) $(systbl) FORCE $(call if_changed,systbl) systbl_abi_syscall_table_64_n64 := 64_n64 systbl_offset_syscall_table_64_n64 := 5000 -$(kapi)/syscall_table_64_n64.h: $(syscalln64) $(systbl) +$(kapi)/syscall_table_64_n64.h: $(syscalln64) $(systbl) FORCE $(call if_changed,systbl) systbl_abi_syscall_table_64_o32 := 64_o32 systbl_offset_syscall_table_64_o32 := 4000 -$(kapi)/syscall_table_64_o32.h: $(syscallo32) $(systbl) +$(kapi)/syscall_table_64_o32.h: $(syscallo32) $(systbl) FORCE $(call if_changed,systbl) uapisyshdr-y += unistd_n32.h \ @@ -88,9 +88,10 @@ kapisyshdr-y += syscall_table_32_o32.h \ unistd_nr_n64.h \ unistd_nr_o32.h -targets += $(uapisyshdr-y) $(kapisyshdr-y) +uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) +kapisyshdr-y := $(addprefix $(kapi)/, $(kapisyshdr-y)) +targets += $(addprefix ../../../../, $(uapisyshdr-y) $(kapisyshdr-y)) PHONY += all -all: $(addprefix $(uapi)/,$(uapisyshdr-y)) -all: $(addprefix $(kapi)/,$(kapisyshdr-y)) +all: $(uapisyshdr-y) $(kapisyshdr-y) @: diff --git a/arch/mips/lib/iomap-pci.c b/arch/mips/lib/iomap-pci.c index 210f5a95ecb1..a9cb28813f0b 100644 --- a/arch/mips/lib/iomap-pci.c +++ b/arch/mips/lib/iomap-pci.c @@ -32,7 +32,7 @@ void __iomem *__pci_ioport_map(struct pci_dev *dev, sprintf(name, "%04x:%02x", pci_domain_nr(bus), bus->number); printk(KERN_WARNING "io_map_base of root PCI bus %s unset. " "Trying to continue but you better\nfix this issue or " - "report it to linux-mips@linux-mips.org or your " + "report it to linux-mips@vger.kernel.org or your " "vendor.\n", name); #ifdef CONFIG_PCI_DOMAINS panic("To avoid data corruption io_map_base MUST be set with " diff --git a/arch/mips/loongson64/Platform b/arch/mips/loongson64/Platform index e2354e128d9a..3e660d6d3c2b 100644 --- a/arch/mips/loongson64/Platform +++ b/arch/mips/loongson64/Platform @@ -13,7 +13,7 @@ cflags-$(CONFIG_CPU_LOONGSON64) += -Wa,--trap # can't easily be used safely within the kbuild framework. # ifeq ($(call cc-ifversion, -ge, 0409, y), y) - ifeq ($(call ld-ifversion, -ge, 225000000, y), y) + ifeq ($(call ld-ifversion, -ge, 22500, y), y) cflags-$(CONFIG_CPU_LOONGSON64) += \ $(call cc-option,-march=loongson3a -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) else diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index 1754498b0717..7719d632df8d 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -157,29 +157,31 @@ unsigned long _page_cachable_default; EXPORT_SYMBOL(_page_cachable_default); #define PM(p) __pgprot(_page_cachable_default | (p)) +#define PVA(p) PM(_PAGE_VALID | _PAGE_ACCESSED | (p)) static inline void setup_protection_map(void) { protection_map[0] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); - protection_map[1] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC); - protection_map[2] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); - protection_map[3] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC); - protection_map[4] = PM(_PAGE_PRESENT); - protection_map[5] = PM(_PAGE_PRESENT); - protection_map[6] = PM(_PAGE_PRESENT); - protection_map[7] = PM(_PAGE_PRESENT); + protection_map[1] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC); + protection_map[2] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); + protection_map[3] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC); + protection_map[4] = PVA(_PAGE_PRESENT); + protection_map[5] = PVA(_PAGE_PRESENT); + protection_map[6] = PVA(_PAGE_PRESENT); + protection_map[7] = PVA(_PAGE_PRESENT); protection_map[8] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); - protection_map[9] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC); - protection_map[10] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | + protection_map[9] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC); + protection_map[10] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | _PAGE_NO_READ); - protection_map[11] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE); - protection_map[12] = PM(_PAGE_PRESENT); - protection_map[13] = PM(_PAGE_PRESENT); - protection_map[14] = PM(_PAGE_PRESENT | _PAGE_WRITE); - protection_map[15] = PM(_PAGE_PRESENT | _PAGE_WRITE); + protection_map[11] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE); + protection_map[12] = PVA(_PAGE_PRESENT); + protection_map[13] = PVA(_PAGE_PRESENT); + protection_map[14] = PVA(_PAGE_PRESENT); + protection_map[15] = PVA(_PAGE_PRESENT); } +#undef _PVA #undef PM void cpu_cache_init(void) diff --git a/arch/mips/sgi-ip32/ip32-irq.c b/arch/mips/sgi-ip32/ip32-irq.c index 1bbd5bfb5458..e21ea1de05e3 100644 --- a/arch/mips/sgi-ip32/ip32-irq.c +++ b/arch/mips/sgi-ip32/ip32-irq.c @@ -343,7 +343,7 @@ static void ip32_unknown_interrupt(void) printk("Register dump:\n"); show_regs(get_irq_regs()); - printk("Please mail this report to linux-mips@linux-mips.org\n"); + printk("Please mail this report to linux-mips@vger.kernel.org\n"); printk("Spinning..."); while(1) ; } diff --git a/arch/mips/vdso/Kconfig b/arch/mips/vdso/Kconfig index 7aec721398d5..a665f6108cb5 100644 --- a/arch/mips/vdso/Kconfig +++ b/arch/mips/vdso/Kconfig @@ -12,7 +12,7 @@ # the lack of relocations. As such, we disable the VDSO for microMIPS builds. config MIPS_LD_CAN_LINK_VDSO - def_bool LD_VERSION >= 225000000 || LD_IS_LLD + def_bool LD_VERSION >= 22500 || LD_IS_LLD config MIPS_DISABLE_VDSO def_bool CPU_MICROMIPS || (!CPU_MIPSR6 && !MIPS_LD_CAN_LINK_VDSO) diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 07fbe1a82f3e..4e53ac46e857 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -61,6 +61,7 @@ config PARISC select HAVE_KRETPROBES select HAVE_DYNAMIC_FTRACE if $(cc-option,-fpatchable-function-entry=1,1) select HAVE_FTRACE_MCOUNT_RECORD if HAVE_DYNAMIC_FTRACE + select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE select HAVE_KPROBES_ON_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_SOFTIRQ_ON_OWN_STACK if IRQSTACKS diff --git a/arch/parisc/kernel/syscalls/Makefile b/arch/parisc/kernel/syscalls/Makefile index c22a21c39f30..283f64407b07 100644 --- a/arch/parisc/kernel/syscalls/Makefile +++ b/arch/parisc/kernel/syscalls/Makefile @@ -5,7 +5,7 @@ uapi := arch/$(SRCARCH)/include/generated/uapi/asm _dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') -syscall := $(srctree)/$(src)/syscall.tbl +syscall := $(src)/syscall.tbl syshdr := $(srctree)/$(src)/syscallhdr.sh systbl := $(srctree)/$(src)/syscalltbl.sh @@ -22,24 +22,24 @@ quiet_cmd_systbl = SYSTBL $@ '$(systbl_offset_$(basetarget))' syshdr_abis_unistd_32 := common,32 -$(uapi)/unistd_32.h: $(syscall) $(syshdr) +$(uapi)/unistd_32.h: $(syscall) $(syshdr) FORCE $(call if_changed,syshdr) syshdr_abis_unistd_64 := common,64 -$(uapi)/unistd_64.h: $(syscall) $(syshdr) +$(uapi)/unistd_64.h: $(syscall) $(syshdr) FORCE $(call if_changed,syshdr) systbl_abis_syscall_table_32 := common,32 -$(kapi)/syscall_table_32.h: $(syscall) $(systbl) +$(kapi)/syscall_table_32.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) systbl_abis_syscall_table_64 := common,64 -$(kapi)/syscall_table_64.h: $(syscall) $(systbl) +$(kapi)/syscall_table_64.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) systbl_abis_syscall_table_c32 := common,32 systbl_abi_syscall_table_c32 := c32 -$(kapi)/syscall_table_c32.h: $(syscall) $(systbl) +$(kapi)/syscall_table_c32.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) uapisyshdr-y += unistd_32.h unistd_64.h @@ -47,9 +47,10 @@ kapisyshdr-y += syscall_table_32.h \ syscall_table_64.h \ syscall_table_c32.h -targets += $(uapisyshdr-y) $(kapisyshdr-y) +uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) +kapisyshdr-y := $(addprefix $(kapi)/, $(kapisyshdr-y)) +targets += $(addprefix ../../../../, $(uapisyshdr-y) $(kapisyshdr-y)) PHONY += all -all: $(addprefix $(uapi)/,$(uapisyshdr-y)) -all: $(addprefix $(kapi)/,$(kapisyshdr-y)) +all: $(uapisyshdr-y) $(kapisyshdr-y) @: diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index b959fdaec713..5f8544cf724a 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -65,7 +65,7 @@ UTS_MACHINE := $(subst $(space),,$(machine-y)) ifdef CONFIG_PPC32 KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o else -ifeq ($(call ld-ifversion, -ge, 225000000, y),y) +ifeq ($(call ld-ifversion, -ge, 22500, y),y) # Have the linker provide sfpr if possible. # There is a corresponding test in arch/powerpc/lib/Makefile KBUILD_LDFLAGS_MODULE += --save-restore-funcs diff --git a/arch/powerpc/kernel/syscalls/Makefile b/arch/powerpc/kernel/syscalls/Makefile index 27b48954808d..9e3be295dbba 100644 --- a/arch/powerpc/kernel/syscalls/Makefile +++ b/arch/powerpc/kernel/syscalls/Makefile @@ -5,7 +5,7 @@ uapi := arch/$(SRCARCH)/include/generated/uapi/asm _dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') -syscall := $(srctree)/$(src)/syscall.tbl +syscall := $(src)/syscall.tbl syshdr := $(srctree)/$(src)/syscallhdr.sh systbl := $(srctree)/$(src)/syscalltbl.sh @@ -22,31 +22,31 @@ quiet_cmd_systbl = SYSTBL $@ '$(systbl_offset_$(basetarget))' syshdr_abis_unistd_32 := common,nospu,32 -$(uapi)/unistd_32.h: $(syscall) $(syshdr) +$(uapi)/unistd_32.h: $(syscall) $(syshdr) FORCE $(call if_changed,syshdr) syshdr_abis_unistd_64 := common,nospu,64 -$(uapi)/unistd_64.h: $(syscall) $(syshdr) +$(uapi)/unistd_64.h: $(syscall) $(syshdr) FORCE $(call if_changed,syshdr) systbl_abis_syscall_table_32 := common,nospu,32 systbl_abi_syscall_table_32 := 32 -$(kapi)/syscall_table_32.h: $(syscall) $(systbl) +$(kapi)/syscall_table_32.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) systbl_abis_syscall_table_64 := common,nospu,64 systbl_abi_syscall_table_64 := 64 -$(kapi)/syscall_table_64.h: $(syscall) $(systbl) +$(kapi)/syscall_table_64.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) systbl_abis_syscall_table_c32 := common,nospu,32 systbl_abi_syscall_table_c32 := c32 -$(kapi)/syscall_table_c32.h: $(syscall) $(systbl) +$(kapi)/syscall_table_c32.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) systbl_abis_syscall_table_spu := common,spu systbl_abi_syscall_table_spu := spu -$(kapi)/syscall_table_spu.h: $(syscall) $(systbl) +$(kapi)/syscall_table_spu.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) uapisyshdr-y += unistd_32.h unistd_64.h @@ -55,9 +55,10 @@ kapisyshdr-y += syscall_table_32.h \ syscall_table_c32.h \ syscall_table_spu.h -targets += $(uapisyshdr-y) $(kapisyshdr-y) +uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) +kapisyshdr-y := $(addprefix $(kapi)/, $(kapisyshdr-y)) +targets += $(addprefix ../../../../, $(uapisyshdr-y) $(kapisyshdr-y)) PHONY += all -all: $(addprefix $(uapi)/,$(uapisyshdr-y)) -all: $(addprefix $(kapi)/,$(kapisyshdr-y)) +all: $(uapisyshdr-y) $(kapisyshdr-y) @: diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index c77f2d4f44ca..bb6773594cf8 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -591,7 +591,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu, } else { /* Call KVM generic code to do the slow-path check */ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, - writing, &write_ok); + writing, &write_ok, NULL); if (is_error_noslot_pfn(pfn)) return -EFAULT; page = NULL; diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index bb35490400e9..e603de7ade52 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -822,7 +822,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu, /* Call KVM generic code to do the slow-path check */ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, - writing, upgrade_p); + writing, upgrade_p, NULL); if (is_error_noslot_pfn(pfn)) return -EFAULT; page = NULL; diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 69a91b571845..d4efc182662a 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -31,7 +31,7 @@ obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o # 64-bit linker creates .sfpr on demand for final link (vmlinux), # so it is only needed for modules, and only for older linkers which # do not support --save-restore-funcs -ifeq ($(call ld-ifversion, -lt, 225000000, y),y) +ifeq ($(call ld-ifversion, -lt, 22500, y),y) extra-$(CONFIG_PPC64) += crtsavres.o endif diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index e0a34eb5ed3b..a998babc1237 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -57,6 +57,7 @@ config RISCV select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN if MMU && 64BIT + select HAVE_ARCH_KASAN_VMALLOC if MMU && 64BIT select HAVE_ARCH_KGDB select HAVE_ARCH_KGDB_QXFER_PKT select HAVE_ARCH_MMAP_RND_BITS if MMU @@ -67,14 +68,19 @@ config RISCV select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS if MMU select HAVE_EBPF_JIT if MMU + select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_GCC_PLUGINS select HAVE_GENERIC_VDSO if MMU && 64BIT select HAVE_IRQ_TIME_ACCOUNTING + select HAVE_KPROBES + select HAVE_KPROBES_ON_FTRACE + select HAVE_KRETPROBES select HAVE_PCI select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select IRQ_DOMAIN @@ -143,7 +149,7 @@ config PAGE_OFFSET default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB config ARCH_FLATMEM_ENABLE - def_bool y + def_bool !NUMA config ARCH_SPARSEMEM_ENABLE def_bool y @@ -156,6 +162,9 @@ config ARCH_SELECT_MEMORY_MODEL config ARCH_WANT_GENERAL_HUGETLB def_bool y +config ARCH_SUPPORTS_UPROBES + def_bool y + config SYS_SUPPORTS_HUGETLBFS depends on MMU def_bool y @@ -302,6 +311,35 @@ config TUNE_GENERIC endchoice +# Common NUMA Features +config NUMA + bool "NUMA Memory Allocation and Scheduler Support" + select GENERIC_ARCH_NUMA + select OF_NUMA + select ARCH_SUPPORTS_NUMA_BALANCING + help + Enable NUMA (Non-Uniform Memory Access) support. + + The kernel will try to allocate memory used by a CPU on the + local memory of the CPU and add some more NUMA awareness to the kernel. + +config NODES_SHIFT + int "Maximum NUMA Nodes (as a power of 2)" + range 1 10 + default "2" + depends on NEED_MULTIPLE_NODES + help + Specify the maximum number of NUMA Nodes available on the target + system. Increases memory reserved to accommodate various tables. + +config USE_PERCPU_NUMA_NODE_ID + def_bool y + depends on NUMA + +config NEED_PER_CPU_EMBED_FIRST_CHUNK + def_bool y + depends on NUMA + config RISCV_ISA_C bool "Emit compressed instructions when building Linux" default y @@ -416,11 +454,17 @@ config EFI allow the kernel to be booted as an EFI application. This is only useful on systems that have UEFI firmware. +config CC_HAVE_STACKPROTECTOR_TLS + def_bool $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=tp -mstack-protector-guard-offset=0) + +config STACKPROTECTOR_PER_TASK + def_bool y + depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_TLS + endmenu config BUILTIN_DTB def_bool n - depends on RISCV_M_MODE depends on OF menu "Power management options" diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 3284d5c291be..7efcece8896c 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -22,30 +22,41 @@ config SOC_VIRT help This enables support for QEMU Virt Machine. -config SOC_KENDRYTE - bool "Kendryte K210 SoC" +config SOC_CANAAN + bool "Canaan Kendryte K210 SoC" depends on !MMU select CLINT_TIMER if RISCV_M_MODE select SERIAL_SIFIVE if TTY select SERIAL_SIFIVE_CONSOLE if TTY select SIFIVE_PLIC + select ARCH_HAS_RESET_CONTROLLER + select PINCTRL help - This enables support for Kendryte K210 SoC platform hardware. + This enables support for Canaan Kendryte K210 SoC platform hardware. -config SOC_KENDRYTE_K210_DTB - def_bool y - depends on SOC_KENDRYTE_K210_DTB_BUILTIN +if SOC_CANAAN -config SOC_KENDRYTE_K210_DTB_BUILTIN - bool "Builtin device tree for the Kendryte K210" - depends on SOC_KENDRYTE +config SOC_CANAAN_K210_DTB_BUILTIN + bool "Builtin device tree for the Canaan Kendryte K210" + depends on SOC_CANAAN default y select OF select BUILTIN_DTB - select SOC_KENDRYTE_K210_DTB help - Builds a device tree for the Kendryte K210 into the Linux image. + Build a device tree for the Kendryte K210 into the Linux image. This option should be selected if no bootloader is being used. If unsure, say Y. +config SOC_CANAAN_K210_DTB_SOURCE + string "Source file for the Canaan Kendryte K210 builtin DTB" + depends on SOC_CANAAN + depends on SOC_CANAAN_K210_DTB_BUILTIN + default "k210_generic" + help + Base name (without suffix, relative to arch/riscv/boot/dts/canaan) + for the DTS file that will be used to produce the DTB linked into the + kernel. + +endif + endmenu diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 8c29e553ef7f..1368d943f1f3 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -12,6 +12,8 @@ OBJCOPYFLAGS := -O binary LDFLAGS_vmlinux := ifeq ($(CONFIG_DYNAMIC_FTRACE),y) LDFLAGS_vmlinux := --no-relax + KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY + CC_FLAGS_FTRACE := -fpatchable-function-entry=8 endif ifeq ($(CONFIG_64BIT)$(CONFIG_CMODEL_MEDLOW),yy) @@ -65,6 +67,16 @@ KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) # architectures. It's faster to have GCC emit only aligned accesses. KBUILD_CFLAGS += $(call cc-option,-mstrict-align) +ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y) +prepare: stack_protector_prepare +stack_protector_prepare: prepare0 + $(eval KBUILD_CFLAGS += -mstack-protector-guard=tls \ + -mstack-protector-guard-reg=tp \ + -mstack-protector-guard-offset=$(shell \ + awk '{if ($$2 == "TSK_STACK_CANARY") print $$3;}' \ + include/generated/asm-offsets.h)) +endif + # arch specific predefines for sparse CHECKFLAGS += -D__riscv -D__riscv_xlen=$(BITS) @@ -83,7 +95,7 @@ PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@ -ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_SOC_KENDRYTE),yy) +ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_SOC_CANAAN),yy) KBUILD_IMAGE := $(boot)/loader.bin else KBUILD_IMAGE := $(boot)/Image.gz diff --git a/arch/riscv/boot/dts/Makefile b/arch/riscv/boot/dts/Makefile index ca1f8cbd78c0..7ffd502e3e7b 100644 --- a/arch/riscv/boot/dts/Makefile +++ b/arch/riscv/boot/dts/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 subdir-y += sifive -subdir-y += kendryte +subdir-$(CONFIG_SOC_CANAAN_K210_DTB_BUILTIN) += canaan obj-$(CONFIG_BUILTIN_DTB) := $(addsuffix /, $(subdir-y)) diff --git a/arch/riscv/boot/dts/canaan/Makefile b/arch/riscv/boot/dts/canaan/Makefile new file mode 100644 index 000000000000..9ee7156c0c31 --- /dev/null +++ b/arch/riscv/boot/dts/canaan/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 +ifneq ($(CONFIG_SOC_CANAAN_K210_DTB_SOURCE),"") +dtb-y += $(strip $(shell echo $(CONFIG_SOC_CANAAN_K210_DTB_SOURCE))).dtb +obj-$(CONFIG_SOC_CANAAN_K210_DTB_BUILTIN) += $(addsuffix .o, $(dtb-y)) +endif diff --git a/arch/riscv/boot/dts/canaan/canaan_kd233.dts b/arch/riscv/boot/dts/canaan/canaan_kd233.dts new file mode 100644 index 000000000000..039b92abf046 --- /dev/null +++ b/arch/riscv/boot/dts/canaan/canaan_kd233.dts @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +/dts-v1/; + +#include "k210.dtsi" + +#include +#include + +/ { + model = "Kendryte KD233"; + compatible = "canaan,kendryte-kd233", "canaan,kendryte-k210"; + + chosen { + bootargs = "earlycon console=ttySIF0"; + stdout-path = "serial0:115200n8"; + }; + + gpio-leds { + compatible = "gpio-leds"; + + led0 { + gpios = <&gpio0 8 GPIO_ACTIVE_LOW>; + }; + + led1 { + gpios = <&gpio0 9 GPIO_ACTIVE_LOW>; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + key0 { + label = "KEY0"; + linux,code = ; + gpios = <&gpio0 10 GPIO_ACTIVE_LOW>; + }; + }; +}; + +&fpioa { + pinctrl-0 = <&jtag_pinctrl>; + pinctrl-names = "default"; + status = "okay"; + + jtag_pinctrl: jtag-pinmux { + pinmux = , + , + , + ; + }; + + uarths_pinctrl: uarths-pinmux { + pinmux = , + ; + }; + + spi0_pinctrl: spi0-pinmux { + pinmux = , /* cs */ + , /* wr */ + ; /* dc */ + }; + + dvp_pinctrl: dvp-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; + + gpiohs_pinctrl: gpiohs-pinmux { + pinmux = , + , /* Rot. dip sw line 8 */ + , /* Rot. dip sw line 4 */ + , /* Rot. dip sw line 2 */ + , /* Rot. dip sw line 1 */ + , + , + ; + }; + + spi1_pinctrl: spi1-pinmux { + pinmux = , + , + , + ; /* cs */ + }; + + i2s0_pinctrl: i2s0-pinmux { + pinmux = , + , + ; + }; +}; + +&uarths0 { + pinctrl-0 = <&uarths_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio0 { + pinctrl-0 = <&gpiohs_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2s0 { + #sound-dai-cells = <1>; + pinctrl-0 = <&i2s0_pinctrl>; + pinctrl-names = "default"; +}; + +&spi0 { + pinctrl-0 = <&spi0_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + + panel@0 { + compatible = "ilitek,ili9341"; + reg = <0>; + dc-gpios = <&gpio0 21 GPIO_ACTIVE_HIGH>; + spi-max-frequency = <15000000>; + status = "disabled"; + }; +}; + +&spi1 { + pinctrl-0 = <&spi1_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 16 GPIO_ACTIVE_LOW>; + status = "okay"; + + slot@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + voltage-ranges = <3300 3300>; + spi-max-frequency = <25000000>; + broken-cd; + }; +}; diff --git a/arch/riscv/boot/dts/canaan/k210.dtsi b/arch/riscv/boot/dts/canaan/k210.dtsi new file mode 100644 index 000000000000..5e8ca8142482 --- /dev/null +++ b/arch/riscv/boot/dts/canaan/k210.dtsi @@ -0,0 +1,459 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ +#include +#include +#include + +/ { + /* + * Although the K210 is a 64-bit CPU, the address bus is only 32-bits + * wide, and the upper half of all addresses is ignored. + */ + #address-cells = <1>; + #size-cells = <1>; + compatible = "canaan,kendryte-k210"; + + aliases { + serial0 = &uarths0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + }; + + /* + * The K210 has an sv39 MMU following the privileged specification v1.9. + * Since this is a non-ratified draft specification, the kernel does not + * support it and the K210 support enabled only for the !MMU case. + * Be consistent with this by setting the CPUs MMU type to "none". + */ + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <7800000>; + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "canaan,k210", "riscv"; + reg = <0>; + riscv,isa = "rv64imafdc"; + mmu-type = "riscv,none"; + i-cache-block-size = <64>; + i-cache-size = <0x8000>; + d-cache-block-size = <64>; + d-cache-size = <0x8000>; + cpu0_intc: interrupt-controller { + #interrupt-cells = <1>; + interrupt-controller; + compatible = "riscv,cpu-intc"; + }; + }; + cpu1: cpu@1 { + device_type = "cpu"; + compatible = "canaan,k210", "riscv"; + reg = <1>; + riscv,isa = "rv64imafdc"; + mmu-type = "riscv,none"; + i-cache-block-size = <64>; + i-cache-size = <0x8000>; + d-cache-block-size = <64>; + d-cache-size = <0x8000>; + cpu1_intc: interrupt-controller { + #interrupt-cells = <1>; + interrupt-controller; + compatible = "riscv,cpu-intc"; + }; + }; + }; + + sram: memory@80000000 { + device_type = "memory"; + compatible = "canaan,k210-sram"; + reg = <0x80000000 0x400000>, + <0x80400000 0x200000>, + <0x80600000 0x200000>; + reg-names = "sram0", "sram1", "aisram"; + clocks = <&sysclk K210_CLK_SRAM0>, + <&sysclk K210_CLK_SRAM1>, + <&sysclk K210_CLK_AI>; + clock-names = "sram0", "sram1", "aisram"; + }; + + clocks { + in0: oscillator { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <26000000>; + }; + }; + + soc { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-bus"; + ranges; + interrupt-parent = <&plic0>; + + rom0: nvmem@1000 { + reg = <0x1000 0x1000>; + read-only; + }; + + clint0: timer@2000000 { + compatible = "canaan,k210-clint", "sifive,clint0"; + reg = <0x2000000 0xC000>; + interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7 + &cpu1_intc 3 &cpu1_intc 7>; + }; + + plic0: interrupt-controller@c000000 { + #interrupt-cells = <1>; + #address-cells = <0>; + compatible = "canaan,k210-plic", "sifive,plic-1.0.0"; + reg = <0xC000000 0x4000000>; + interrupt-controller; + interrupts-extended = <&cpu0_intc 11 &cpu1_intc 11>; + riscv,ndev = <65>; + }; + + uarths0: serial@38000000 { + compatible = "canaan,k210-uarths", "sifive,uart0"; + reg = <0x38000000 0x1000>; + interrupts = <33>; + clocks = <&sysclk K210_CLK_CPU>; + }; + + gpio0: gpio-controller@38001000 { + #interrupt-cells = <2>; + #gpio-cells = <2>; + compatible = "canaan,k210-gpiohs", "sifive,gpio0"; + reg = <0x38001000 0x1000>; + interrupt-controller; + interrupts = <34 35 36 37 38 39 40 41 + 42 43 44 45 46 47 48 49 + 50 51 52 53 54 55 56 57 + 58 59 60 61 62 63 64 65>; + gpio-controller; + ngpios = <32>; + }; + + dmac0: dma-controller@50000000 { + compatible = "snps,axi-dma-1.01a"; + reg = <0x50000000 0x1000>; + interrupts = <27 28 29 30 31 32>; + #dma-cells = <1>; + clocks = <&sysclk K210_CLK_DMA>, <&sysclk K210_CLK_DMA>; + clock-names = "core-clk", "cfgr-clk"; + resets = <&sysrst K210_RST_DMA>; + dma-channels = <6>; + snps,dma-masters = <2>; + snps,priority = <0 1 2 3 4 5>; + snps,data-width = <5>; + snps,block-size = <0x200000 0x200000 0x200000 + 0x200000 0x200000 0x200000>; + snps,axi-max-burst-len = <256>; + }; + + apb0: bus@50200000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-pm-bus"; + ranges; + clocks = <&sysclk K210_CLK_APB0>; + + gpio1: gpio@50200000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dw-apb-gpio"; + reg = <0x50200000 0x80>; + clocks = <&sysclk K210_CLK_APB0>, + <&sysclk K210_CLK_GPIO>; + clock-names = "bus", "db"; + resets = <&sysrst K210_RST_GPIO>; + + gpio1_0: gpio-port@0 { + #gpio-cells = <2>; + #interrupt-cells = <2>; + compatible = "snps,dw-apb-gpio-port"; + reg = <0>; + interrupt-controller; + interrupts = <23>; + gpio-controller; + ngpios = <8>; + }; + }; + + uart1: serial@50210000 { + compatible = "snps,dw-apb-uart"; + reg = <0x50210000 0x100>; + interrupts = <11>; + clocks = <&sysclk K210_CLK_UART1>, + <&sysclk K210_CLK_APB0>; + clock-names = "baudclk", "apb_pclk"; + resets = <&sysrst K210_RST_UART1>; + reg-io-width = <4>; + reg-shift = <2>; + dcd-override; + dsr-override; + cts-override; + ri-override; + }; + + uart2: serial@50220000 { + compatible = "snps,dw-apb-uart"; + reg = <0x50220000 0x100>; + interrupts = <12>; + clocks = <&sysclk K210_CLK_UART2>, + <&sysclk K210_CLK_APB0>; + clock-names = "baudclk", "apb_pclk"; + resets = <&sysrst K210_RST_UART2>; + reg-io-width = <4>; + reg-shift = <2>; + dcd-override; + dsr-override; + cts-override; + ri-override; + }; + + uart3: serial@50230000 { + compatible = "snps,dw-apb-uart"; + reg = <0x50230000 0x100>; + interrupts = <13>; + clocks = <&sysclk K210_CLK_UART3>, + <&sysclk K210_CLK_APB0>; + clock-names = "baudclk", "apb_pclk"; + resets = <&sysrst K210_RST_UART3>; + reg-io-width = <4>; + reg-shift = <2>; + dcd-override; + dsr-override; + cts-override; + ri-override; + }; + + spi2: spi@50240000 { + compatible = "canaan,k210-spi"; + spi-slave; + reg = <0x50240000 0x100>; + #address-cells = <0>; + #size-cells = <0>; + interrupts = <3>; + clocks = <&sysclk K210_CLK_SPI2>, + <&sysclk K210_CLK_APB0>; + clock-names = "ssi_clk", "pclk"; + resets = <&sysrst K210_RST_SPI2>; + spi-max-frequency = <25000000>; + }; + + i2s0: i2s@50250000 { + compatible = "snps,designware-i2s"; + reg = <0x50250000 0x200>; + interrupts = <5>; + clocks = <&sysclk K210_CLK_I2S0>; + clock-names = "i2sclk"; + resets = <&sysrst K210_RST_I2S0>; + }; + + i2s1: i2s@50260000 { + compatible = "snps,designware-i2s"; + reg = <0x50260000 0x200>; + interrupts = <6>; + clocks = <&sysclk K210_CLK_I2S1>; + clock-names = "i2sclk"; + resets = <&sysrst K210_RST_I2S1>; + }; + + i2s2: i2s@50270000 { + compatible = "snps,designware-i2s"; + reg = <0x50270000 0x200>; + interrupts = <7>; + clocks = <&sysclk K210_CLK_I2S2>; + clock-names = "i2sclk"; + resets = <&sysrst K210_RST_I2S2>; + }; + + i2c0: i2c@50280000 { + compatible = "snps,designware-i2c"; + reg = <0x50280000 0x100>; + interrupts = <8>; + clocks = <&sysclk K210_CLK_I2C0>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_I2C0>; + }; + + i2c1: i2c@50290000 { + compatible = "snps,designware-i2c"; + reg = <0x50290000 0x100>; + interrupts = <9>; + clocks = <&sysclk K210_CLK_I2C1>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_I2C1>; + }; + + i2c2: i2c@502a0000 { + compatible = "snps,designware-i2c"; + reg = <0x502A0000 0x100>; + interrupts = <10>; + clocks = <&sysclk K210_CLK_I2C2>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_I2C2>; + }; + + fpioa: pinmux@502b0000 { + compatible = "canaan,k210-fpioa"; + reg = <0x502B0000 0x100>; + clocks = <&sysclk K210_CLK_FPIOA>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_FPIOA>; + canaan,k210-sysctl-power = <&sysctl 108>; + }; + + timer0: timer@502d0000 { + compatible = "snps,dw-apb-timer"; + reg = <0x502D0000 0x100>; + interrupts = <14 15>; + clocks = <&sysclk K210_CLK_TIMER0>, + <&sysclk K210_CLK_APB0>; + clock-names = "timer", "pclk"; + resets = <&sysrst K210_RST_TIMER0>; + }; + + timer1: timer@502e0000 { + compatible = "snps,dw-apb-timer"; + reg = <0x502E0000 0x100>; + interrupts = <16 17>; + clocks = <&sysclk K210_CLK_TIMER1>, + <&sysclk K210_CLK_APB0>; + clock-names = "timer", "pclk"; + resets = <&sysrst K210_RST_TIMER1>; + }; + + timer2: timer@502f0000 { + compatible = "snps,dw-apb-timer"; + reg = <0x502F0000 0x100>; + interrupts = <18 19>; + clocks = <&sysclk K210_CLK_TIMER2>, + <&sysclk K210_CLK_APB0>; + clock-names = "timer", "pclk"; + resets = <&sysrst K210_RST_TIMER2>; + }; + }; + + apb1: bus@50400000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-pm-bus"; + ranges; + clocks = <&sysclk K210_CLK_APB1>; + + wdt0: watchdog@50400000 { + compatible = "snps,dw-wdt"; + reg = <0x50400000 0x100>; + interrupts = <21>; + clocks = <&sysclk K210_CLK_WDT0>, + <&sysclk K210_CLK_APB1>; + clock-names = "tclk", "pclk"; + resets = <&sysrst K210_RST_WDT0>; + }; + + wdt1: watchdog@50410000 { + compatible = "snps,dw-wdt"; + reg = <0x50410000 0x100>; + interrupts = <22>; + clocks = <&sysclk K210_CLK_WDT1>, + <&sysclk K210_CLK_APB1>; + clock-names = "tclk", "pclk"; + resets = <&sysrst K210_RST_WDT1>; + }; + + sysctl: syscon@50440000 { + compatible = "canaan,k210-sysctl", + "syscon", "simple-mfd"; + reg = <0x50440000 0x100>; + clocks = <&sysclk K210_CLK_APB1>; + clock-names = "pclk"; + + sysclk: clock-controller { + #clock-cells = <1>; + compatible = "canaan,k210-clk"; + clocks = <&in0>; + }; + + sysrst: reset-controller { + compatible = "canaan,k210-rst"; + #reset-cells = <1>; + }; + + reboot: syscon-reboot { + compatible = "syscon-reboot"; + regmap = <&sysctl>; + offset = <48>; + mask = <1>; + value = <1>; + }; + }; + }; + + apb2: bus@52000000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-pm-bus"; + ranges; + clocks = <&sysclk K210_CLK_APB2>; + + spi0: spi@52000000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "canaan,k210-spi"; + reg = <0x52000000 0x100>; + interrupts = <1>; + clocks = <&sysclk K210_CLK_SPI0>, + <&sysclk K210_CLK_APB2>; + clock-names = "ssi_clk", "pclk"; + resets = <&sysrst K210_RST_SPI0>; + reset-names = "spi"; + spi-max-frequency = <25000000>; + num-cs = <4>; + reg-io-width = <4>; + }; + + spi1: spi@53000000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "canaan,k210-spi"; + reg = <0x53000000 0x100>; + interrupts = <2>; + clocks = <&sysclk K210_CLK_SPI1>, + <&sysclk K210_CLK_APB2>; + clock-names = "ssi_clk", "pclk"; + resets = <&sysrst K210_RST_SPI1>; + reset-names = "spi"; + spi-max-frequency = <25000000>; + num-cs = <4>; + reg-io-width = <4>; + }; + + spi3: spi@54000000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwc-ssi-1.01a"; + reg = <0x54000000 0x200>; + interrupts = <4>; + clocks = <&sysclk K210_CLK_SPI3>, + <&sysclk K210_CLK_APB2>; + clock-names = "ssi_clk", "pclk"; + resets = <&sysrst K210_RST_SPI3>; + reset-names = "spi"; + /* Could possibly go up to 200 MHz */ + spi-max-frequency = <100000000>; + num-cs = <4>; + reg-io-width = <4>; + }; + }; + }; +}; diff --git a/arch/riscv/boot/dts/canaan/k210_generic.dts b/arch/riscv/boot/dts/canaan/k210_generic.dts new file mode 100644 index 000000000000..396c8ca4d24d --- /dev/null +++ b/arch/riscv/boot/dts/canaan/k210_generic.dts @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +/dts-v1/; + +#include "k210.dtsi" + +#include +#include + +/ { + model = "Kendryte K210 generic"; + compatible = "canaan,kendryte-k210"; + + chosen { + bootargs = "earlycon console=ttySIF0"; + stdout-path = "serial0:115200n8"; + }; +}; + +&fpioa { + pinctrl-0 = <&jtag_pins>; + pinctrl-names = "default"; + status = "okay"; + + jtag_pins: jtag-pinmux { + pinmux = , + , + , + ; + }; + + uarths_pins: uarths-pinmux { + pinmux = , + ; + }; +}; + +&uarths0 { + pinctrl-0 = <&uarths_pins>; + pinctrl-names = "default"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts new file mode 100644 index 000000000000..0bcaf35045e7 --- /dev/null +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts @@ -0,0 +1,209 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +/dts-v1/; + +#include "k210.dtsi" + +#include +#include +#include + +/ { + model = "SiPeed MAIX BiT"; + compatible = "sipeed,maix-bit", "sipeed,maix-bitm", + "canaan,kendryte-k210"; + + chosen { + bootargs = "earlycon console=ttySIF0"; + stdout-path = "serial0:115200n8"; + }; + + gpio-leds { + compatible = "gpio-leds"; + + led0 { + color = ; + label = "green"; + gpios = <&gpio1_0 4 GPIO_ACTIVE_LOW>; + }; + + led1 { + color = ; + label = "red"; + gpios = <&gpio1_0 5 GPIO_ACTIVE_LOW>; + }; + + led2 { + color = ; + label = "blue"; + gpios = <&gpio1_0 6 GPIO_ACTIVE_LOW>; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + boot { + label = "BOOT"; + linux,code = ; + gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; + }; + }; +}; + +&fpioa { + pinctrl-names = "default"; + pinctrl-0 = <&jtag_pinctrl>; + status = "okay"; + + jtag_pinctrl: jtag-pinmux { + pinmux = , + , + , + ; + }; + + uarths_pinctrl: uarths-pinmux { + pinmux = , + ; + }; + + gpio_pinctrl: gpio-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; + + gpiohs_pinctrl: gpiohs-pinmux { + pinmux = , + , + , + , + , + , + , + , + , + , + ; + }; + + i2s0_pinctrl: i2s0-pinmux { + pinmux = , + , + ; + }; + + dvp_pinctrl: dvp-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; + + spi0_pinctrl: spi0-pinmux { + pinmux = , /* cs */ + , /* rst */ + , /* dc */ + ; /* wr */ + }; + + spi1_pinctrl: spi1-pinmux { + pinmux = , + , + , + ; /* cs */ + }; + + i2c1_pinctrl: i2c1-pinmux { + pinmux = , + ; + }; +}; + +&uarths0 { + pinctrl-0 = <&uarths_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio0 { + pinctrl-0 = <&gpiohs_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio1 { + pinctrl-0 = <&gpio_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2s0 { + #sound-dai-cells = <1>; + pinctrl-0 = <&i2s0_pinctrl>; + pinctrl-names = "default"; +}; + +&i2c1 { + pinctrl-0 = <&i2c1_pinctrl>; + pinctrl-names = "default"; + clock-frequency = <400000>; + status = "okay"; +}; + +&spi0 { + pinctrl-0 = <&spi0_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + + panel@0 { + compatible = "sitronix,st7789v"; + reg = <0>; + reset-gpios = <&gpio0 21 GPIO_ACTIVE_LOW>; + dc-gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>; + spi-max-frequency = <15000000>; + spi-cs-high; + status = "disabled"; + }; +}; + +&spi1 { + pinctrl-0 = <&spi1_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 13 GPIO_ACTIVE_LOW>; + status = "okay"; + + slot@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + voltage-ranges = <3300 3300>; + spi-max-frequency = <25000000>; + broken-cd; + }; +}; + +&spi3 { + spi-flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + m25p,fast-read; + broken-flash-reset; + }; +}; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts new file mode 100644 index 000000000000..ac8a03f5867a --- /dev/null +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts @@ -0,0 +1,211 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +/dts-v1/; + +#include "k210.dtsi" + +#include +#include +#include + +/ { + model = "SiPeed MAIX Dock"; + compatible = "sipeed,maix-dock-m1", "sipeed,maix-dock-m1w", + "canaan,kendryte-k210"; + + chosen { + bootargs = "earlycon console=ttySIF0"; + stdout-path = "serial0:115200n8"; + }; + + gpio-leds { + compatible = "gpio-leds"; + + /* + * Note: the board wiring drawing documents green on + * gpio #4, red on gpio #5 and blue on gpio #6. However, + * the board is actually wired differently as defined here. + */ + led0 { + color = ; + label = "blue"; + gpios = <&gpio1_0 4 GPIO_ACTIVE_LOW>; + }; + + led1 { + color = ; + label = "green"; + gpios = <&gpio1_0 5 GPIO_ACTIVE_LOW>; + }; + + led2 { + color = ; + label = "red"; + gpios = <&gpio1_0 6 GPIO_ACTIVE_LOW>; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + boot { + label = "BOOT"; + linux,code = ; + gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; + }; + }; +}; + +&fpioa { + pinctrl-0 = <&jtag_pinctrl>; + pinctrl-names = "default"; + status = "okay"; + + jtag_pinctrl: jtag-pinmux { + pinmux = , + , + , + ; + }; + + uarths_pinctrl: uarths-pinmux { + pinmux = , + ; + }; + + gpio_pinctrl: gpio-pinmux { + pinmux = , + , + , + , + , + ; + }; + + gpiohs_pinctrl: gpiohs-pinmux { + pinmux = , + , + , + , + , + , + , + , + , + , + ; + }; + + i2s0_pinctrl: i2s0-pinmux { + pinmux = , + , + ; + }; + + dvp_pinctrl: dvp-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; + + spi0_pinctrl: spi0-pinmux { + pinmux = , /* cs */ + , /* rst */ + , /* dc */ + ; /* wr */ + }; + + spi1_pinctrl: spi1-pinmux { + pinmux = , + , + , + ; /* cs */ + }; + + i2c1_pinctrl: i2c1-pinmux { + pinmux = , + ; + }; +}; + +&uarths0 { + pinctrl-0 = <&uarths_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio0 { + pinctrl-0 = <&gpiohs_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio1 { + pinctrl-0 = <&gpio_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2s0 { + #sound-dai-cells = <1>; + pinctrl-0 = <&i2s0_pinctrl>; + pinctrl-names = "default"; +}; + +&i2c1 { + pinctrl-0 = <&i2c1_pinctrl>; + pinctrl-names = "default"; + clock-frequency = <400000>; + status = "okay"; +}; + +&spi0 { + pinctrl-0 = <&spi0_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + + panel@0 { + compatible = "sitronix,st7789v"; + reg = <0>; + reset-gpios = <&gpio0 21 GPIO_ACTIVE_LOW>; + dc-gpios = <&gpio0 22 0>; + spi-max-frequency = <15000000>; + status = "disabled"; + }; +}; + +&spi1 { + pinctrl-0 = <&spi1_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 13 GPIO_ACTIVE_LOW>; + status = "okay"; + + slot@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + voltage-ranges = <3300 3300>; + spi-max-frequency = <25000000>; + broken-cd; + }; +}; + +&spi3 { + spi-flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + m25p,fast-read; + broken-flash-reset; + }; +}; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts new file mode 100644 index 000000000000..623998194bc1 --- /dev/null +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +/dts-v1/; + +#include "k210.dtsi" + +#include +#include +#include + +/ { + model = "SiPeed MAIX GO"; + compatible = "sipeed,maix-go", "canaan,kendryte-k210"; + + chosen { + bootargs = "earlycon console=ttySIF0"; + stdout-path = "serial0:115200n8"; + }; + + gpio-leds { + compatible = "gpio-leds"; + + led0 { + color = ; + label = "green"; + gpios = <&gpio1_0 4 GPIO_ACTIVE_LOW>; + }; + + led1 { + color = ; + label = "red"; + gpios = <&gpio1_0 5 GPIO_ACTIVE_LOW>; + }; + + led2 { + color = ; + label = "blue"; + gpios = <&gpio1_0 6 GPIO_ACTIVE_LOW>; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + up { + label = "UP"; + linux,code = ; + gpios = <&gpio1_0 7 GPIO_ACTIVE_LOW>; + }; + + press { + label = "PRESS"; + linux,code = ; + gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; + }; + + down { + label = "DOWN"; + linux,code = ; + gpios = <&gpio0 1 GPIO_ACTIVE_LOW>; + }; + }; +}; + +&fpioa { + pinctrl-0 = <&jtag_pinctrl>; + pinctrl-names = "default"; + status = "okay"; + + jtag_pinctrl: jtag-pinmux { + pinmux = , + , + , + ; + }; + + uarths_pinctrl: uarths-pinmux { + pinmux = , + ; + }; + + gpio_pinctrl: gpio-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; + + gpiohs_pinctrl: gpiohs-pinmux { + pinmux = , + , + , + , + , + , + , + , + , + , + ; + }; + + i2s0_pinctrl: i2s0-pinmux { + pinmux = , + , + ; + }; + + dvp_pinctrl: dvp-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; + + spi0_pinctrl: spi0-pinmux { + pinmux = , /* cs */ + , /* rst */ + , /* dc */ + ; /* wr */ + }; + + spi1_pinctrl: spi1-pinmux { + pinmux = , + , + , + ; /* cs */ + }; + + i2c1_pinctrl: i2c1-pinmux { + pinmux = , + ; + }; +}; + +&uarths0 { + pinctrl-0 = <&uarths_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio0 { + pinctrl-0 = <&gpiohs_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio1 { + pinctrl-0 = <&gpio_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2s0 { + #sound-dai-cells = <1>; + pinctrl-0 = <&i2s0_pinctrl>; + pinctrl-names = "default"; +}; + +&i2c1 { + pinctrl-0 = <&i2c1_pinctrl>; + pinctrl-names = "default"; + clock-frequency = <400000>; + status = "okay"; +}; + +&spi0 { + pinctrl-0 = <&spi0_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + + panel@0 { + compatible = "sitronix,st7789v"; + reg = <0>; + reset-gpios = <&gpio0 21 GPIO_ACTIVE_LOW>; + dc-gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>; + spi-max-frequency = <15000000>; + status = "disabled"; + }; +}; + +&spi1 { + pinctrl-0 = <&spi1_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 13 GPIO_ACTIVE_LOW>; + status = "okay"; + + slot@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + voltage-ranges = <3300 3300>; + spi-max-frequency = <25000000>; + broken-cd; + }; +}; + +&spi3 { + spi-flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + m25p,fast-read; + broken-flash-reset; + }; +}; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts new file mode 100644 index 000000000000..cf605ba0d67e --- /dev/null +++ b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts @@ -0,0 +1,184 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +/dts-v1/; + +#include "k210.dtsi" + +#include +#include + +/ { + model = "SiPeed MAIXDUINO"; + compatible = "sipeed,maixduino", "canaan,kendryte-k210"; + + chosen { + bootargs = "earlycon console=ttySIF0"; + stdout-path = "serial0:115200n8"; + }; + + gpio-keys { + compatible = "gpio-keys"; + + boot { + label = "BOOT"; + linux,code = ; + gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; + }; + }; + + vcc_3v3: regulator-3v3 { + compatible = "regulator-fixed"; + regulator-name = "3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; +}; + +&fpioa { + status = "okay"; + + uarths_pinctrl: uarths-pinmux { + pinmux = , /* Header "0" */ + ; /* Header "1" */ + }; + + gpio_pinctrl: gpio-pinmux { + pinmux = , + ; + }; + + gpiohs_pinctrl: gpiohs-pinmux { + pinmux = , /* BOOT */ + , /* Header "2" */ + , /* Header "3" */ + , /* Header "4" */ + , /* Header "5" */ + , /* Header "6" */ + , /* Header "7" */ + , /* Header "8" */ + , /* Header "9" */ + , /* Header "10" */ + , /* Header "11" */ + , /* Header "12" */ + ; /* Header "13" */ + }; + + i2s0_pinctrl: i2s0-pinmux { + pinmux = , + , + ; + }; + + spi1_pinctrl: spi1-pinmux { + pinmux = , + , + , + ; /* cs */ + }; + + i2c1_pinctrl: i2c1-pinmux { + pinmux = , /* Header "scl" */ + ; /* Header "sda" */ + }; + + i2s1_pinctrl: i2s1-pinmux { + pinmux = , + , + ; + }; + + spi0_pinctrl: spi0-pinmux { + pinmux = , /* cs */ + , /* rst */ + , /* dc */ + ; /* wr */ + }; + + dvp_pinctrl: dvp-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; +}; + +&uarths0 { + pinctrl-0 = <&uarths_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio0 { + pinctrl-0 = <&gpiohs_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio1 { + pinctrl-0 = <&gpio_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2s0 { + #sound-dai-cells = <1>; + pinctrl-0 = <&i2s0_pinctrl>; + pinctrl-names = "default"; +}; + +&i2c1 { + pinctrl-0 = <&i2c1_pinctrl>; + pinctrl-names = "default"; + clock-frequency = <400000>; + status = "okay"; +}; + +&spi0 { + pinctrl-0 = <&spi0_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + + panel@0 { + compatible = "sitronix,st7789v"; + reg = <0>; + reset-gpios = <&gpio0 21 GPIO_ACTIVE_LOW>; + dc-gpios = <&gpio0 22 0>; + spi-max-frequency = <15000000>; + power-supply = <&vcc_3v3>; + }; +}; + +&spi1 { + pinctrl-0 = <&spi1_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio1_0 2 GPIO_ACTIVE_LOW>; + status = "okay"; + + slot@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + voltage-ranges = <3300 3300>; + spi-max-frequency = <25000000>; + broken-cd; + }; +}; + +&spi3 { + spi-flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + m25p,fast-read; + broken-flash-reset; + }; +}; diff --git a/arch/riscv/boot/dts/kendryte/Makefile b/arch/riscv/boot/dts/kendryte/Makefile deleted file mode 100644 index 1a88e616f18e..000000000000 --- a/arch/riscv/boot/dts/kendryte/Makefile +++ /dev/null @@ -1,4 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -dtb-$(CONFIG_SOC_KENDRYTE_K210_DTB) += k210.dtb - -obj-$(CONFIG_SOC_KENDRYTE_K210_DTB_BUILTIN) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/riscv/boot/dts/kendryte/k210.dts b/arch/riscv/boot/dts/kendryte/k210.dts deleted file mode 100644 index 0d1f28fce6b2..000000000000 --- a/arch/riscv/boot/dts/kendryte/k210.dts +++ /dev/null @@ -1,23 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Copyright (C) 2020 Western Digital Corporation or its affiliates. - */ - -/dts-v1/; - -#include "k210.dtsi" - -/ { - model = "Kendryte K210 generic"; - compatible = "kendryte,k210"; - - chosen { - bootargs = "earlycon console=ttySIF0"; - stdout-path = "serial0"; - }; -}; - -&uarths0 { - status = "okay"; -}; - diff --git a/arch/riscv/boot/dts/kendryte/k210.dtsi b/arch/riscv/boot/dts/kendryte/k210.dtsi deleted file mode 100644 index d2d0ff645632..000000000000 --- a/arch/riscv/boot/dts/kendryte/k210.dtsi +++ /dev/null @@ -1,125 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Copyright (C) 2019 Sean Anderson - * Copyright (C) 2020 Western Digital Corporation or its affiliates. - */ -#include - -/ { - /* - * Although the K210 is a 64-bit CPU, the address bus is only 32-bits - * wide, and the upper half of all addresses is ignored. - */ - #address-cells = <1>; - #size-cells = <1>; - compatible = "kendryte,k210"; - - aliases { - serial0 = &uarths0; - }; - - /* - * The K210 has an sv39 MMU following the priviledge specification v1.9. - * Since this is a non-ratified draft specification, the kernel does not - * support it and the K210 support enabled only for the !MMU case. - * Be consistent with this by setting the CPUs MMU type to "none". - */ - cpus { - #address-cells = <1>; - #size-cells = <0>; - timebase-frequency = <7800000>; - cpu0: cpu@0 { - device_type = "cpu"; - reg = <0>; - compatible = "kendryte,k210", "sifive,rocket0", "riscv"; - riscv,isa = "rv64imafdc"; - mmu-type = "none"; - i-cache-size = <0x8000>; - i-cache-block-size = <64>; - d-cache-size = <0x8000>; - d-cache-block-size = <64>; - clocks = <&sysctl K210_CLK_CPU>; - clock-frequency = <390000000>; - cpu0_intc: interrupt-controller { - #interrupt-cells = <1>; - interrupt-controller; - compatible = "riscv,cpu-intc"; - }; - }; - cpu1: cpu@1 { - device_type = "cpu"; - reg = <1>; - compatible = "kendryte,k210", "sifive,rocket0", "riscv"; - riscv,isa = "rv64imafdc"; - mmu-type = "none"; - i-cache-size = <0x8000>; - i-cache-block-size = <64>; - d-cache-size = <0x8000>; - d-cache-block-size = <64>; - clocks = <&sysctl K210_CLK_CPU>; - clock-frequency = <390000000>; - cpu1_intc: interrupt-controller { - #interrupt-cells = <1>; - interrupt-controller; - compatible = "riscv,cpu-intc"; - }; - }; - }; - - sram: memory@80000000 { - device_type = "memory"; - reg = <0x80000000 0x400000>, - <0x80400000 0x200000>, - <0x80600000 0x200000>; - reg-names = "sram0", "sram1", "aisram"; - }; - - clocks { - in0: oscillator { - compatible = "fixed-clock"; - #clock-cells = <0>; - clock-frequency = <26000000>; - }; - }; - - soc { - #address-cells = <1>; - #size-cells = <1>; - compatible = "kendryte,k210-soc", "simple-bus"; - ranges; - interrupt-parent = <&plic0>; - - sysctl: sysctl@50440000 { - compatible = "kendryte,k210-sysctl", "simple-mfd"; - reg = <0x50440000 0x1000>; - #clock-cells = <1>; - }; - - clint0: clint@2000000 { - #interrupt-cells = <1>; - compatible = "riscv,clint0"; - reg = <0x2000000 0xC000>; - interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7 - &cpu1_intc 3 &cpu1_intc 7>; - clocks = <&sysctl K210_CLK_ACLK>; - }; - - plic0: interrupt-controller@c000000 { - #interrupt-cells = <1>; - interrupt-controller; - compatible = "kendryte,k210-plic0", "riscv,plic0"; - reg = <0xC000000 0x4000000>; - interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 0xffffffff>, - <&cpu1_intc 11>, <&cpu1_intc 0xffffffff>; - riscv,ndev = <65>; - riscv,max-priority = <7>; - }; - - uarths0: serial@38000000 { - compatible = "kendryte,k210-uarths", "sifive,uart0"; - reg = <0x38000000 0x1000>; - interrupts = <33>; - clocks = <&sysctl K210_CLK_CPU>; - }; - }; -}; diff --git a/arch/riscv/boot/dts/sifive/Makefile b/arch/riscv/boot/dts/sifive/Makefile index 6d6189e6e4af..74c47fe9fc22 100644 --- a/arch/riscv/boot/dts/sifive/Makefile +++ b/arch/riscv/boot/dts/sifive/Makefile @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -dtb-$(CONFIG_SOC_SIFIVE) += hifive-unleashed-a00.dtb +dtb-$(CONFIG_SOC_SIFIVE) += hifive-unleashed-a00.dtb \ + hifive-unmatched-a00.dtb diff --git a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi new file mode 100644 index 000000000000..eeb4f8c3e0e7 --- /dev/null +++ b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi @@ -0,0 +1,293 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2020 SiFive, Inc */ + +/dts-v1/; + +#include + +/ { + #address-cells = <2>; + #size-cells = <2>; + compatible = "sifive,fu740-c000", "sifive,fu740"; + + aliases { + serial0 = &uart0; + serial1 = &uart1; + ethernet0 = ð0; + }; + + chosen { + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + cpu0: cpu@0 { + compatible = "sifive,bullet0", "riscv"; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <16384>; + next-level-cache = <&ccache>; + reg = <0x0>; + riscv,isa = "rv64imac"; + status = "disabled"; + cpu0_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + cpu1: cpu@1 { + compatible = "sifive,bullet0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <40>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <40>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + reg = <0x1>; + riscv,isa = "rv64imafdc"; + tlb-split; + cpu1_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + cpu2: cpu@2 { + compatible = "sifive,bullet0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <40>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <40>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + reg = <0x2>; + riscv,isa = "rv64imafdc"; + tlb-split; + cpu2_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + cpu3: cpu@3 { + compatible = "sifive,bullet0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <40>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <40>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + reg = <0x3>; + riscv,isa = "rv64imafdc"; + tlb-split; + cpu3_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + cpu4: cpu@4 { + compatible = "sifive,bullet0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <40>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <40>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + reg = <0x4>; + riscv,isa = "rv64imafdc"; + tlb-split; + cpu4_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + }; + soc { + #address-cells = <2>; + #size-cells = <2>; + compatible = "simple-bus"; + ranges; + plic0: interrupt-controller@c000000 { + #interrupt-cells = <1>; + #address-cells = <0>; + compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0"; + reg = <0x0 0xc000000 0x0 0x4000000>; + riscv,ndev = <69>; + interrupt-controller; + interrupts-extended = < + &cpu0_intc 0xffffffff + &cpu1_intc 0xffffffff &cpu1_intc 9 + &cpu2_intc 0xffffffff &cpu2_intc 9 + &cpu3_intc 0xffffffff &cpu3_intc 9 + &cpu4_intc 0xffffffff &cpu4_intc 9>; + }; + prci: clock-controller@10000000 { + compatible = "sifive,fu740-c000-prci"; + reg = <0x0 0x10000000 0x0 0x1000>; + clocks = <&hfclk>, <&rtcclk>; + #clock-cells = <1>; + }; + uart0: serial@10010000 { + compatible = "sifive,fu740-c000-uart", "sifive,uart0"; + reg = <0x0 0x10010000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <39>; + clocks = <&prci PRCI_CLK_PCLK>; + status = "disabled"; + }; + uart1: serial@10011000 { + compatible = "sifive,fu740-c000-uart", "sifive,uart0"; + reg = <0x0 0x10011000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <40>; + clocks = <&prci PRCI_CLK_PCLK>; + status = "disabled"; + }; + i2c0: i2c@10030000 { + compatible = "sifive,fu740-c000-i2c", "sifive,i2c0"; + reg = <0x0 0x10030000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <52>; + clocks = <&prci PRCI_CLK_PCLK>; + reg-shift = <2>; + reg-io-width = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + i2c1: i2c@10031000 { + compatible = "sifive,fu740-c000-i2c", "sifive,i2c0"; + reg = <0x0 0x10031000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <53>; + clocks = <&prci PRCI_CLK_PCLK>; + reg-shift = <2>; + reg-io-width = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + qspi0: spi@10040000 { + compatible = "sifive,fu740-c000-spi", "sifive,spi0"; + reg = <0x0 0x10040000 0x0 0x1000>, + <0x0 0x20000000 0x0 0x10000000>; + interrupt-parent = <&plic0>; + interrupts = <41>; + clocks = <&prci PRCI_CLK_PCLK>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + qspi1: spi@10041000 { + compatible = "sifive,fu740-c000-spi", "sifive,spi0"; + reg = <0x0 0x10041000 0x0 0x1000>, + <0x0 0x30000000 0x0 0x10000000>; + interrupt-parent = <&plic0>; + interrupts = <42>; + clocks = <&prci PRCI_CLK_PCLK>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + spi0: spi@10050000 { + compatible = "sifive,fu740-c000-spi", "sifive,spi0"; + reg = <0x0 0x10050000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <43>; + clocks = <&prci PRCI_CLK_PCLK>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + eth0: ethernet@10090000 { + compatible = "sifive,fu540-c000-gem"; + interrupt-parent = <&plic0>; + interrupts = <55>; + reg = <0x0 0x10090000 0x0 0x2000>, + <0x0 0x100a0000 0x0 0x1000>; + local-mac-address = [00 00 00 00 00 00]; + clock-names = "pclk", "hclk"; + clocks = <&prci PRCI_CLK_GEMGXLPLL>, + <&prci PRCI_CLK_GEMGXLPLL>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + pwm0: pwm@10020000 { + compatible = "sifive,fu740-c000-pwm", "sifive,pwm0"; + reg = <0x0 0x10020000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <44>, <45>, <46>, <47>; + clocks = <&prci PRCI_CLK_PCLK>; + #pwm-cells = <3>; + status = "disabled"; + }; + pwm1: pwm@10021000 { + compatible = "sifive,fu740-c000-pwm", "sifive,pwm0"; + reg = <0x0 0x10021000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <48>, <49>, <50>, <51>; + clocks = <&prci PRCI_CLK_PCLK>; + #pwm-cells = <3>; + status = "disabled"; + }; + ccache: cache-controller@2010000 { + compatible = "sifive,fu740-c000-ccache", "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-sets = <2048>; + cache-size = <2097152>; + cache-unified; + interrupt-parent = <&plic0>; + interrupts = <19 20 21 22>; + reg = <0x0 0x2010000 0x0 0x1000>; + }; + gpio: gpio@10060000 { + compatible = "sifive,fu740-c000-gpio", "sifive,gpio0"; + interrupt-parent = <&plic0>; + interrupts = <23>, <24>, <25>, <26>, <27>, <28>, <29>, + <30>, <31>, <32>, <33>, <34>, <35>, <36>, + <37>, <38>; + reg = <0x0 0x10060000 0x0 0x1000>; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + clocks = <&prci PRCI_CLK_PCLK>; + status = "disabled"; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts new file mode 100644 index 000000000000..b1c3c596578f --- /dev/null +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -0,0 +1,253 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2020 SiFive, Inc */ + +#include "fu740-c000.dtsi" +#include + +/* Clock frequency (in Hz) of the PCB crystal for rtcclk */ +#define RTCCLK_FREQ 1000000 + +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "SiFive HiFive Unmatched A00"; + compatible = "sifive,hifive-unmatched-a00", "sifive,fu740-c000", + "sifive,fu740"; + + chosen { + stdout-path = "serial0"; + }; + + cpus { + timebase-frequency = ; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x2 0x00000000>; + }; + + soc { + }; + + hfclk: hfclk { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <26000000>; + clock-output-names = "hfclk"; + }; + + rtcclk: rtcclk { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = ; + clock-output-names = "rtcclk"; + }; +}; + +&uart0 { + status = "okay"; +}; + +&uart1 { + status = "okay"; +}; + +&i2c0 { + status = "okay"; + + temperature-sensor@4c { + compatible = "ti,tmp451"; + reg = <0x4c>; + interrupt-parent = <&gpio>; + interrupts = <6 IRQ_TYPE_LEVEL_LOW>; + }; + + pmic@58 { + compatible = "dlg,da9063"; + reg = <0x58>; + interrupt-parent = <&gpio>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + interrupt-controller; + + regulators { + vdd_bcore1: bcore1 { + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <900000>; + regulator-min-microamp = <5000000>; + regulator-max-microamp = <5000000>; + regulator-always-on; + }; + + vdd_bcore2: bcore2 { + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <900000>; + regulator-min-microamp = <5000000>; + regulator-max-microamp = <5000000>; + regulator-always-on; + }; + + vdd_bpro: bpro { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-min-microamp = <2500000>; + regulator-max-microamp = <2500000>; + regulator-always-on; + }; + + vdd_bperi: bperi { + regulator-min-microvolt = <1050000>; + regulator-max-microvolt = <1050000>; + regulator-min-microamp = <1500000>; + regulator-max-microamp = <1500000>; + regulator-always-on; + }; + + vdd_bmem: bmem { + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-min-microamp = <3000000>; + regulator-max-microamp = <3000000>; + regulator-always-on; + }; + + vdd_bio: bio { + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-min-microamp = <3000000>; + regulator-max-microamp = <3000000>; + regulator-always-on; + }; + + vdd_ldo1: ldo1 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-min-microamp = <100000>; + regulator-max-microamp = <100000>; + regulator-always-on; + }; + + vdd_ldo2: ldo2 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-min-microamp = <200000>; + regulator-max-microamp = <200000>; + regulator-always-on; + }; + + vdd_ldo3: ldo3 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-min-microamp = <200000>; + regulator-max-microamp = <200000>; + regulator-always-on; + }; + + vdd_ldo4: ldo4 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-min-microamp = <200000>; + regulator-max-microamp = <200000>; + regulator-always-on; + }; + + vdd_ldo5: ldo5 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-min-microamp = <100000>; + regulator-max-microamp = <100000>; + regulator-always-on; + }; + + vdd_ldo6: ldo6 { + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-min-microamp = <200000>; + regulator-max-microamp = <200000>; + regulator-always-on; + }; + + vdd_ldo7: ldo7 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-min-microamp = <200000>; + regulator-max-microamp = <200000>; + regulator-always-on; + }; + + vdd_ldo8: ldo8 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-min-microamp = <200000>; + regulator-max-microamp = <200000>; + regulator-always-on; + }; + + vdd_ld09: ldo9 { + regulator-min-microvolt = <1050000>; + regulator-max-microvolt = <1050000>; + regulator-min-microamp = <200000>; + regulator-max-microamp = <200000>; + }; + + vdd_ldo10: ldo10 { + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1000000>; + regulator-min-microamp = <300000>; + regulator-max-microamp = <300000>; + }; + + vdd_ldo11: ldo11 { + regulator-min-microvolt = <2500000>; + regulator-max-microvolt = <2500000>; + regulator-min-microamp = <300000>; + regulator-max-microamp = <300000>; + regulator-always-on; + }; + }; + }; +}; + +&qspi0 { + status = "okay"; + flash@0 { + compatible = "issi,is25wp256", "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + m25p,fast-read; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; + }; +}; + +&spi0 { + status = "okay"; + mmc@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + spi-max-frequency = <20000000>; + voltage-ranges = <3300 3300>; + disable-wp; + }; +}; + +ð0 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy0>; + phy0: ethernet-phy@0 { + reg = <0>; + }; +}; + +&pwm0 { + status = "okay"; +}; + +&pwm1 { + status = "okay"; +}; + +&gpio { + status = "okay"; +}; diff --git a/arch/riscv/configs/nommu_k210_defconfig b/arch/riscv/configs/nommu_k210_defconfig index cd1df62b13c7..b16a2a12c82a 100644 --- a/arch/riscv/configs/nommu_k210_defconfig +++ b/arch/riscv/configs/nommu_k210_defconfig @@ -1,17 +1,19 @@ # CONFIG_CPU_ISOLATION is not set -CONFIG_LOG_BUF_SHIFT=15 +CONFIG_LOG_BUF_SHIFT=13 CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT=12 CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_FORCE=y +# CONFIG_RD_GZIP is not set # CONFIG_RD_BZIP2 is not set # CONFIG_RD_LZMA is not set # CONFIG_RD_XZ is not set # CONFIG_RD_LZO is not set # CONFIG_RD_LZ4 is not set +# CONFIG_RD_ZSTD is not set CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_SYSFS_SYSCALL is not set # CONFIG_FHANDLE is not set # CONFIG_BASE_FULL is not set +# CONFIG_FUTEX is not set # CONFIG_EPOLL is not set # CONFIG_SIGNALFD is not set # CONFIG_TIMERFD is not set @@ -25,15 +27,17 @@ CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_COMPAT_BRK is not set CONFIG_SLOB=y -# CONFIG_SLAB_MERGE_DEFAULT is not set # CONFIG_MMU is not set -CONFIG_SOC_KENDRYTE=y +CONFIG_SOC_CANAAN=y +CONFIG_SOC_CANAAN_K210_DTB_SOURCE="k210_generic" CONFIG_MAXPHYSMEM_2GB=y CONFIG_SMP=y CONFIG_NR_CPUS=2 CONFIG_CMDLINE="earlycon console=ttySIF0" CONFIG_CMDLINE_FORCE=y -CONFIG_JUMP_LABEL=y +# CONFIG_SECCOMP is not set +# CONFIG_STACKPROTECTOR is not set +# CONFIG_GCC_PLUGINS is not set # CONFIG_BLOCK is not set CONFIG_BINFMT_FLAT=y # CONFIG_COREDUMP is not set @@ -41,23 +45,47 @@ CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FW_LOADER is not set # CONFIG_ALLOW_DEV_COREDUMP is not set -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set +# CONFIG_INPUT is not set # CONFIG_SERIO is not set +# CONFIG_VT is not set +# CONFIG_UNIX98_PTYS is not set # CONFIG_LEGACY_PTYS is not set # CONFIG_LDISC_AUTOLOAD is not set # CONFIG_HW_RANDOM is not set # CONFIG_DEVMEM is not set +CONFIG_I2C=y +# CONFIG_I2C_COMPAT is not set +CONFIG_I2C_CHARDEV=y +# CONFIG_I2C_HELPER_AUTO is not set +CONFIG_I2C_DESIGNWARE_PLATFORM=y +CONFIG_SPI=y +# CONFIG_SPI_MEM is not set +CONFIG_SPI_DESIGNWARE=y +CONFIG_SPI_DW_MMIO=y +# CONFIG_GPIO_CDEV_V1 is not set +CONFIG_GPIO_DWAPB=y +CONFIG_GPIO_SIFIVE=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set -# CONFIG_VGA_CONSOLE is not set -# CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y +CONFIG_LEDS_GPIO=y +CONFIG_LEDS_USER=y # CONFIG_VIRTIO_MENU is not set +# CONFIG_VHOST_MENU is not set +# CONFIG_SURFACE_PLATFORMS is not set +# CONFIG_FILE_LOCKING is not set # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set # CONFIG_MISC_FILESYSTEMS is not set CONFIG_LSM="[]" CONFIG_PRINTK_TIME=y +# CONFIG_SYMBOLIC_ERRNAME is not set +# CONFIG_DEBUG_BUGVERBOSE is not set +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set +# CONFIG_FRAME_POINTER is not set # CONFIG_DEBUG_MISC is not set CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set diff --git a/arch/riscv/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig new file mode 100644 index 000000000000..61f887f65419 --- /dev/null +++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig @@ -0,0 +1,92 @@ +# CONFIG_CPU_ISOLATION is not set +CONFIG_LOG_BUF_SHIFT=13 +CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT=12 +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +# CONFIG_SYSFS_SYSCALL is not set +# CONFIG_FHANDLE is not set +# CONFIG_BASE_FULL is not set +# CONFIG_FUTEX is not set +# CONFIG_EPOLL is not set +# CONFIG_SIGNALFD is not set +# CONFIG_TIMERFD is not set +# CONFIG_EVENTFD is not set +# CONFIG_AIO is not set +# CONFIG_IO_URING is not set +# CONFIG_ADVISE_SYSCALLS is not set +# CONFIG_MEMBARRIER is not set +# CONFIG_KALLSYMS is not set +CONFIG_EMBEDDED=y +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_SLOB=y +# CONFIG_MMU is not set +CONFIG_SOC_CANAAN=y +CONFIG_SOC_CANAAN_K210_DTB_SOURCE="k210_generic" +CONFIG_MAXPHYSMEM_2GB=y +CONFIG_SMP=y +CONFIG_NR_CPUS=2 +CONFIG_CMDLINE="earlycon console=ttySIF0 rootdelay=2 root=/dev/mmcblk0p1 ro" +CONFIG_CMDLINE_FORCE=y +# CONFIG_SECCOMP is not set +# CONFIG_STACKPROTECTOR is not set +# CONFIG_GCC_PLUGINS is not set +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_MQ_IOSCHED_DEADLINE is not set +# CONFIG_MQ_IOSCHED_KYBER is not set +CONFIG_BINFMT_FLAT=y +# CONFIG_COREDUMP is not set +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +# CONFIG_FW_LOADER is not set +# CONFIG_ALLOW_DEV_COREDUMP is not set +# CONFIG_BLK_DEV is not set +# CONFIG_INPUT is not set +# CONFIG_SERIO is not set +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_LDISC_AUTOLOAD is not set +# CONFIG_HW_RANDOM is not set +# CONFIG_DEVMEM is not set +CONFIG_I2C=y +CONFIG_I2C_CHARDEV=y +# CONFIG_I2C_HELPER_AUTO is not set +CONFIG_I2C_DESIGNWARE_PLATFORM=y +CONFIG_SPI=y +# CONFIG_SPI_MEM is not set +CONFIG_SPI_DESIGNWARE=y +CONFIG_SPI_DW_MMIO=y +# CONFIG_GPIO_CDEV_V1 is not set +CONFIG_GPIO_DWAPB=y +CONFIG_GPIO_SIFIVE=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +# CONFIG_HWMON is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_MMC=y +# CONFIG_PWRSEQ_EMMC is not set +# CONFIG_PWRSEQ_SIMPLE is not set +CONFIG_MMC_SPI=y +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y +CONFIG_LEDS_GPIO=y +CONFIG_LEDS_USER=y +# CONFIG_VIRTIO_MENU is not set +# CONFIG_VHOST_MENU is not set +# CONFIG_SURFACE_PLATFORMS is not set +CONFIG_EXT2_FS=y +# CONFIG_FILE_LOCKING is not set +# CONFIG_DNOTIFY is not set +# CONFIG_INOTIFY_USER is not set +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_LSM="[]" +CONFIG_PRINTK_TIME=y +# CONFIG_SYMBOLIC_ERRNAME is not set +# CONFIG_DEBUG_BUGVERBOSE is not set +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set +# CONFIG_FRAME_POINTER is not set +# CONFIG_DEBUG_MISC is not set +CONFIG_PANIC_ON_OOPS=y +# CONFIG_SCHED_DEBUG is not set +# CONFIG_RCU_TRACE is not set +# CONFIG_FTRACE is not set +# CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h index d6f1ec08d97b..d3804a2f9aad 100644 --- a/arch/riscv/include/asm/bug.h +++ b/arch/riscv/include/asm/bug.h @@ -85,6 +85,7 @@ do { \ struct pt_regs; struct task_struct; +void __show_regs(struct pt_regs *regs); void die(struct pt_regs *regs, const char *str); void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr); diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index cec462e198ce..caadfc1d7487 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -41,10 +41,16 @@ #define SATP_PPN _AC(0x003FFFFF, UL) #define SATP_MODE_32 _AC(0x80000000, UL) #define SATP_MODE SATP_MODE_32 +#define SATP_ASID_BITS 9 +#define SATP_ASID_SHIFT 22 +#define SATP_ASID_MASK _AC(0x1FF, UL) #else #define SATP_PPN _AC(0x00000FFFFFFFFFFF, UL) #define SATP_MODE_39 _AC(0x8000000000000000, UL) #define SATP_MODE SATP_MODE_39 +#define SATP_ASID_BITS 16 +#define SATP_ASID_SHIFT 44 +#define SATP_ASID_MASK _AC(0xFFFF, UL) #endif /* Exception cause high bit - is an interrupt if set */ diff --git a/arch/riscv/include/asm/kasan.h b/arch/riscv/include/asm/kasan.h index b04028c6218c..a2b3d9cdbc86 100644 --- a/arch/riscv/include/asm/kasan.h +++ b/arch/riscv/include/asm/kasan.h @@ -8,12 +8,28 @@ #ifdef CONFIG_KASAN +/* + * The following comment was copied from arm64: + * KASAN_SHADOW_START: beginning of the kernel virtual addresses. + * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/N of kernel virtual addresses, + * where N = (1 << KASAN_SHADOW_SCALE_SHIFT). + * + * KASAN_SHADOW_OFFSET: + * This value is used to map an address to the corresponding shadow + * address by the following formula: + * shadow_addr = (address >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET + * + * (1 << (64 - KASAN_SHADOW_SCALE_SHIFT)) shadow addresses that lie in range + * [KASAN_SHADOW_OFFSET, KASAN_SHADOW_END) cover all 64-bits of virtual + * addresses. So KASAN_SHADOW_OFFSET should satisfy the following equation: + * KASAN_SHADOW_OFFSET = KASAN_SHADOW_END - + * (1ULL << (64 - KASAN_SHADOW_SCALE_SHIFT)) + */ #define KASAN_SHADOW_SCALE_SHIFT 3 -#define KASAN_SHADOW_SIZE (UL(1) << (38 - KASAN_SHADOW_SCALE_SHIFT)) -#define KASAN_SHADOW_START KERN_VIRT_START /* 2^64 - 2^38 */ +#define KASAN_SHADOW_SIZE (UL(1) << ((CONFIG_VA_BITS - 1) - KASAN_SHADOW_SCALE_SHIFT)) +#define KASAN_SHADOW_START KERN_VIRT_START #define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE) - #define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << \ (64 - KASAN_SHADOW_SCALE_SHIFT))) diff --git a/arch/riscv/include/asm/kprobes.h b/arch/riscv/include/asm/kprobes.h index 56a98ea30731..4647d38018f6 100644 --- a/arch/riscv/include/asm/kprobes.h +++ b/arch/riscv/include/asm/kprobes.h @@ -11,4 +11,44 @@ #include +#ifdef CONFIG_KPROBES +#include +#include +#include + +#define __ARCH_WANT_KPROBES_INSN_SLOT +#define MAX_INSN_SIZE 2 + +#define flush_insn_slot(p) do { } while (0) +#define kretprobe_blacklist_size 0 + +#include + +struct prev_kprobe { + struct kprobe *kp; + unsigned int status; +}; + +/* Single step context for kprobe */ +struct kprobe_step_ctx { + unsigned long ss_pending; + unsigned long match_addr; +}; + +/* per-cpu kprobe control block */ +struct kprobe_ctlblk { + unsigned int kprobe_status; + unsigned long saved_status; + struct prev_kprobe prev_kprobe; + struct kprobe_step_ctx ss_ctx; +}; + +void arch_remove_kprobe(struct kprobe *p); +int kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr); +bool kprobe_breakpoint_handler(struct pt_regs *regs); +bool kprobe_single_step_handler(struct pt_regs *regs); +void kretprobe_trampoline(void); +void __kprobes *trampoline_probe_handler(struct pt_regs *regs); + +#endif /* CONFIG_KPROBES */ #endif /* _ASM_RISCV_KPROBES_H */ diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h index dabcf2cfb3dc..0099dc116168 100644 --- a/arch/riscv/include/asm/mmu.h +++ b/arch/riscv/include/asm/mmu.h @@ -12,6 +12,8 @@ typedef struct { #ifndef CONFIG_MMU unsigned long end_brk; +#else + atomic_long_t id; #endif void *vdso; #ifdef CONFIG_SMP diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h index 250defa06f3a..b0659413a080 100644 --- a/arch/riscv/include/asm/mmu_context.h +++ b/arch/riscv/include/asm/mmu_context.h @@ -23,6 +23,16 @@ static inline void activate_mm(struct mm_struct *prev, switch_mm(prev, next, NULL); } +#define init_new_context init_new_context +static inline int init_new_context(struct task_struct *tsk, + struct mm_struct *mm) +{ +#ifdef CONFIG_MMU + atomic_long_set(&mm->context.id, 0); +#endif + return 0; +} + #include #endif /* _ASM_RISCV_MMU_CONTEXT_H */ diff --git a/arch/riscv/include/asm/mmzone.h b/arch/riscv/include/asm/mmzone.h new file mode 100644 index 000000000000..fa17e01d9ab2 --- /dev/null +++ b/arch/riscv/include/asm/mmzone.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MMZONE_H +#define __ASM_MMZONE_H + +#ifdef CONFIG_NUMA + +#include + +extern struct pglist_data *node_data[]; +#define NODE_DATA(nid) (node_data[(nid)]) + +#endif /* CONFIG_NUMA */ +#endif /* __ASM_MMZONE_H */ diff --git a/arch/riscv/include/asm/numa.h b/arch/riscv/include/asm/numa.h new file mode 100644 index 000000000000..8c8cf4297cc3 --- /dev/null +++ b/arch/riscv/include/asm/numa.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_NUMA_H +#define __ASM_NUMA_H + +#include +#include + +#endif /* __ASM_NUMA_H */ diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 64a675c5c30a..adc9d26f3d75 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -97,9 +97,6 @@ extern unsigned long pfn_base; #define ARCH_PFN_OFFSET (PAGE_OFFSET >> PAGE_SHIFT) #endif /* CONFIG_MMU */ -extern unsigned long max_low_pfn; -extern unsigned long min_low_pfn; - #define __pa_to_va_nodebug(x) ((void *)((unsigned long) (x) + va_pa_offset)) #define __va_to_pa_nodebug(x) ((unsigned long)(x) - va_pa_offset) diff --git a/arch/riscv/include/asm/pci.h b/arch/riscv/include/asm/pci.h index 1c473a1bd986..658e112c3ce7 100644 --- a/arch/riscv/include/asm/pci.h +++ b/arch/riscv/include/asm/pci.h @@ -32,6 +32,20 @@ static inline int pci_proc_domain(struct pci_bus *bus) /* always show the domain in /proc */ return 1; } + +#ifdef CONFIG_NUMA + +static inline int pcibus_to_node(struct pci_bus *bus) +{ + return dev_to_node(&bus->dev); +} +#ifndef cpumask_of_pcibus +#define cpumask_of_pcibus(bus) (pcibus_to_node(bus) == -1 ? \ + cpu_all_mask : \ + cpumask_of_node(pcibus_to_node(bus))) +#endif +#endif /* CONFIG_NUMA */ + #endif /* CONFIG_PCI */ #endif /* _ASM_RISCV_PCI_H */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 251e1db088fa..ebf817c1bdf4 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -186,6 +186,11 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT); } +static inline pte_t pmd_pte(pmd_t pmd) +{ + return __pte(pmd_val(pmd)); +} + /* Yields the page frame number (PFN) of a page table entry */ static inline unsigned long pte_pfn(pte_t pte) { @@ -289,6 +294,21 @@ static inline pte_t pte_mkhuge(pte_t pte) return pte; } +#ifdef CONFIG_NUMA_BALANCING +/* + * See the comment in include/asm-generic/pgtable.h + */ +static inline int pte_protnone(pte_t pte) +{ + return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE)) == _PAGE_PROT_NONE; +} + +static inline int pmd_protnone(pmd_t pmd) +{ + return pte_protnone(pmd_pte(pmd)); +} +#endif + /* Modify page protection bits */ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { @@ -468,6 +488,7 @@ extern void *dtb_early_va; extern uintptr_t dtb_early_pa; void setup_bootmem(void); void paging_init(void); +void misc_mem_init(void); #define FIRST_USER_ADDRESS 0 diff --git a/arch/riscv/include/asm/probes.h b/arch/riscv/include/asm/probes.h new file mode 100644 index 000000000000..a787e6d537b9 --- /dev/null +++ b/arch/riscv/include/asm/probes.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_RISCV_PROBES_H +#define _ASM_RISCV_PROBES_H + +typedef u32 probe_opcode_t; +typedef bool (probes_handler_t) (u32 opcode, unsigned long addr, struct pt_regs *); + +/* architecture specific copy of original instruction */ +struct arch_probe_insn { + probe_opcode_t *insn; + probes_handler_t *handler; + /* restore address after simulation */ + unsigned long restore; +}; + +#ifdef CONFIG_KPROBES +typedef u32 kprobe_opcode_t; +struct arch_specific_insn { + struct arch_probe_insn api; +}; +#endif + +#endif /* _ASM_RISCV_PROBES_H */ diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index bdddcd5c1b71..3a240037bde2 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -34,6 +34,7 @@ struct thread_struct { unsigned long sp; /* Kernel mode stack */ unsigned long s[12]; /* s[0]: frame pointer */ struct __riscv_d_ext_state fstate; + unsigned long bad_cause; }; #define INIT_THREAD { \ diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h index ee49f80c9533..cb4abb639e8d 100644 --- a/arch/riscv/include/asm/ptrace.h +++ b/arch/riscv/include/asm/ptrace.h @@ -8,6 +8,7 @@ #include #include +#include #ifndef __ASSEMBLY__ @@ -60,6 +61,7 @@ struct pt_regs { #define user_mode(regs) (((regs)->status & SR_PP) == 0) +#define MAX_REG_OFFSET offsetof(struct pt_regs, orig_a0) /* Helpers for working with the instruction pointer */ static inline unsigned long instruction_pointer(struct pt_regs *regs) @@ -85,6 +87,12 @@ static inline void user_stack_pointer_set(struct pt_regs *regs, regs->sp = val; } +/* Valid only for Kernel mode traps. */ +static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) +{ + return regs->sp; +} + /* Helpers for working with the frame pointer */ static inline unsigned long frame_pointer(struct pt_regs *regs) { @@ -101,6 +109,33 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) return regs->a0; } +static inline void regs_set_return_value(struct pt_regs *regs, + unsigned long val) +{ + regs->a0 = val; +} + +extern int regs_query_register_offset(const char *name); +extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, + unsigned int n); + +/** + * regs_get_register() - get register value from its offset + * @regs: pt_regs from which register value is gotten + * @offset: offset of the register. + * + * regs_get_register returns the value of a register whose offset from @regs. + * The @offset is the offset of the register in struct pt_regs. + * If @offset is bigger than MAX_REG_OFFSET, this returns 0. + */ +static inline unsigned long regs_get_register(struct pt_regs *regs, + unsigned int offset) +{ + if (unlikely(offset > MAX_REG_OFFSET)) + return 0; + + return *(unsigned long *)((unsigned long)regs + offset); +} #endif /* __ASSEMBLY__ */ #endif /* _ASM_RISCV_PTRACE_H */ diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 653edb25d495..99895d9c3bdd 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -89,7 +89,7 @@ struct sbiret { long value; }; -int sbi_init(void); +void sbi_init(void); struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, unsigned long arg1, unsigned long arg2, unsigned long arg3, unsigned long arg4, @@ -100,13 +100,13 @@ int sbi_console_getchar(void); void sbi_set_timer(uint64_t stime_value); void sbi_shutdown(void); void sbi_clear_ipi(void); -void sbi_send_ipi(const unsigned long *hart_mask); -void sbi_remote_fence_i(const unsigned long *hart_mask); -void sbi_remote_sfence_vma(const unsigned long *hart_mask, +int sbi_send_ipi(const unsigned long *hart_mask); +int sbi_remote_fence_i(const unsigned long *hart_mask); +int sbi_remote_sfence_vma(const unsigned long *hart_mask, unsigned long start, unsigned long size); -void sbi_remote_sfence_vma_asid(const unsigned long *hart_mask, +int sbi_remote_sfence_vma_asid(const unsigned long *hart_mask, unsigned long start, unsigned long size, unsigned long asid); @@ -147,11 +147,7 @@ static inline unsigned long sbi_minor_version(void) int sbi_err_map_linux_errno(int err); #else /* CONFIG_RISCV_SBI */ -/* stubs for code that is only reachable under IS_ENABLED(CONFIG_RISCV_SBI): */ -void sbi_set_timer(uint64_t stime_value); -void sbi_clear_ipi(void); -void sbi_send_ipi(const unsigned long *hart_mask); -void sbi_remote_fence_i(const unsigned long *hart_mask); -void sbi_init(void); +static inline int sbi_remote_fence_i(const unsigned long *hart_mask) { return -1; } +static inline void sbi_init(void) {} #endif /* CONFIG_RISCV_SBI */ #endif /* _ASM_RISCV_SBI_H */ diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h index 8b80c80c7f1a..6887b3d9f371 100644 --- a/arch/riscv/include/asm/set_memory.h +++ b/arch/riscv/include/asm/set_memory.h @@ -22,7 +22,7 @@ static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; } static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; } static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } -static inline void protect_kernel_text_data(void) {}; +static inline void protect_kernel_text_data(void) {} static inline int set_memory_rw_nx(unsigned long addr, int numpages) { return 0; } #endif diff --git a/arch/riscv/include/asm/soc.h b/arch/riscv/include/asm/soc.h index 6c8363b1f327..f494066051a2 100644 --- a/arch/riscv/include/asm/soc.h +++ b/arch/riscv/include/asm/soc.h @@ -21,42 +21,4 @@ void soc_early_init(void); extern unsigned long __soc_early_init_table_start; extern unsigned long __soc_early_init_table_end; -/* - * Allows Linux to provide a device tree, which is necessary for SOCs that - * don't provide a useful one on their own. - */ -struct soc_builtin_dtb { - unsigned long vendor_id; - unsigned long arch_id; - unsigned long imp_id; - void *(*dtb_func)(void); -}; - -/* - * The argument name must specify a valid DTS file name without the dts - * extension. - */ -#define SOC_BUILTIN_DTB_DECLARE(name, vendor, arch, impl) \ - extern void *__dtb_##name##_begin; \ - \ - static __init __used \ - void *__soc_builtin_dtb_f__##name(void) \ - { \ - return (void *)&__dtb_##name##_begin; \ - } \ - \ - static const struct soc_builtin_dtb __soc_builtin_dtb__##name \ - __used __section("__soc_builtin_dtb_table") = \ - { \ - .vendor_id = vendor, \ - .arch_id = arch, \ - .imp_id = impl, \ - .dtb_func = __soc_builtin_dtb_f__##name, \ - } - -extern unsigned long __soc_builtin_dtb_table_start; -extern unsigned long __soc_builtin_dtb_table_end; - -void *soc_lookup_builtin_dtb(void); - #endif diff --git a/arch/riscv/include/asm/stackprotector.h b/arch/riscv/include/asm/stackprotector.h index 5962f8891f06..09093af46565 100644 --- a/arch/riscv/include/asm/stackprotector.h +++ b/arch/riscv/include/asm/stackprotector.h @@ -24,6 +24,7 @@ static __always_inline void boot_init_stack_canary(void) canary &= CANARY_MASK; current->stack_canary = canary; - __stack_chk_guard = current->stack_canary; + if (!IS_ENABLED(CONFIG_STACKPROTECTOR_PER_TASK)) + __stack_chk_guard = current->stack_canary; } #endif /* _ASM_RISCV_STACKPROTECTOR_H */ diff --git a/arch/riscv/include/asm/stacktrace.h b/arch/riscv/include/asm/stacktrace.h index 470a65c4ccdc..3450c1912afd 100644 --- a/arch/riscv/include/asm/stacktrace.h +++ b/arch/riscv/include/asm/stacktrace.h @@ -13,5 +13,7 @@ struct stackframe { extern void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(void *, unsigned long), void *arg); +extern void dump_backtrace(struct pt_regs *regs, struct task_struct *task, + const char *loglvl); #endif /* _ASM_RISCV_STACKTRACE_H */ diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 97bf5a1575d2..0e549a3089b3 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -75,6 +75,7 @@ struct thread_info { #define TIF_SYSCALL_AUDIT 7 /* syscall auditing */ #define TIF_SECCOMP 8 /* syscall secure computing */ #define TIF_NOTIFY_SIGNAL 9 /* signal notifications exist */ +#define TIF_UPROBE 10 /* uprobe breakpoint or singlestep */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) @@ -84,10 +85,11 @@ struct thread_info { #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) +#define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_WORK_MASK \ (_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED | \ - _TIF_NOTIFY_SIGNAL) + _TIF_NOTIFY_SIGNAL | _TIF_UPROBE) #define _TIF_SYSCALL_WORK \ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT | \ diff --git a/arch/riscv/include/asm/uprobes.h b/arch/riscv/include/asm/uprobes.h new file mode 100644 index 000000000000..f2183e00fdd2 --- /dev/null +++ b/arch/riscv/include/asm/uprobes.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ASM_RISCV_UPROBES_H +#define _ASM_RISCV_UPROBES_H + +#include +#include +#include + +#define MAX_UINSN_BYTES 8 + +#ifdef CONFIG_RISCV_ISA_C +#define UPROBE_SWBP_INSN __BUG_INSN_16 +#define UPROBE_SWBP_INSN_SIZE 2 +#else +#define UPROBE_SWBP_INSN __BUG_INSN_32 +#define UPROBE_SWBP_INSN_SIZE 4 +#endif +#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES + +typedef u32 uprobe_opcode_t; + +struct arch_uprobe_task { + unsigned long saved_cause; +}; + +struct arch_uprobe { + union { + u8 insn[MAX_UINSN_BYTES]; + u8 ixol[MAX_UINSN_BYTES]; + }; + struct arch_probe_insn api; + unsigned long insn_size; + bool simulate; +}; + +bool uprobe_breakpoint_handler(struct pt_regs *regs); +bool uprobe_single_step_handler(struct pt_regs *regs); + +#endif /* _ASM_RISCV_UPROBES_H */ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index f6caf4d9ca15..3dc0abde988a 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -4,8 +4,9 @@ # ifdef CONFIG_FTRACE -CFLAGS_REMOVE_ftrace.o = -pg -CFLAGS_REMOVE_patch.o = -pg +CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) endif extra-y += head.o @@ -29,6 +30,7 @@ obj-y += riscv_ksyms.o obj-y += stacktrace.o obj-y += cacheinfo.o obj-y += patch.o +obj-y += probes/ obj-$(CONFIG_MMU) += vdso.o vdso/ obj-$(CONFIG_RISCV_M_MODE) += traps_misaligned.o diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index b79ffa3561fd..9ef33346853c 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -68,6 +68,9 @@ void asm_offsets(void) OFFSET(TASK_THREAD_F30, task_struct, thread.fstate.f[30]); OFFSET(TASK_THREAD_F31, task_struct, thread.fstate.f[31]); OFFSET(TASK_THREAD_FCSR, task_struct, thread.fstate.fcsr); +#ifdef CONFIG_STACKPROTECTOR + OFFSET(TSK_STACK_CANARY, task_struct, stack_canary); +#endif DEFINE(PT_SIZE, sizeof(struct pt_regs)); OFFSET(PT_EPC, pt_regs, epc); diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 765b62434f30..7f1e5203de88 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -72,29 +72,56 @@ static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target, return 0; } +/* + * Put 5 instructions with 16 bytes at the front of function within + * patchable function entry nops' area. + * + * 0: REG_S ra, -SZREG(sp) + * 1: auipc ra, 0x? + * 2: jalr -?(ra) + * 3: REG_L ra, -SZREG(sp) + * + * So the opcodes is: + * 0: 0xfe113c23 (sd)/0xfe112e23 (sw) + * 1: 0x???????? -> auipc + * 2: 0x???????? -> jalr + * 3: 0xff813083 (ld)/0xffc12083 (lw) + */ +#if __riscv_xlen == 64 +#define INSN0 0xfe113c23 +#define INSN3 0xff813083 +#elif __riscv_xlen == 32 +#define INSN0 0xfe112e23 +#define INSN3 0xffc12083 +#endif + +#define FUNC_ENTRY_SIZE 16 +#define FUNC_ENTRY_JMP 4 + int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - int ret = ftrace_check_current_call(rec->ip, NULL); + unsigned int call[4] = {INSN0, 0, 0, INSN3}; + unsigned long target = addr; + unsigned long caller = rec->ip + FUNC_ENTRY_JMP; - if (ret) - return ret; + call[1] = to_auipc_insn((unsigned int)(target - caller)); + call[2] = to_jalr_insn((unsigned int)(target - caller)); - return __ftrace_modify_call(rec->ip, addr, true); + if (patch_text_nosync((void *)rec->ip, call, FUNC_ENTRY_SIZE)) + return -EPERM; + + return 0; } int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - unsigned int call[2]; - int ret; + unsigned int nops[4] = {NOP4, NOP4, NOP4, NOP4}; - make_call(rec->ip, addr, call); - ret = ftrace_check_current_call(rec->ip, call); + if (patch_text_nosync((void *)rec->ip, nops, FUNC_ENTRY_SIZE)) + return -EPERM; - if (ret) - return ret; - - return __ftrace_modify_call(rec->ip, addr, false); + return 0; } @@ -139,15 +166,16 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { unsigned int call[2]; + unsigned long caller = rec->ip + FUNC_ENTRY_JMP; int ret; - make_call(rec->ip, old_addr, call); - ret = ftrace_check_current_call(rec->ip, call); + make_call(caller, old_addr, call); + ret = ftrace_check_current_call(caller, call); if (ret) return ret; - return __ftrace_modify_call(rec->ip, addr, true); + return __ftrace_modify_call(caller, addr, true); } #endif @@ -176,53 +204,30 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); +extern void ftrace_graph_regs_call(void); int ftrace_enable_ftrace_graph_caller(void) { - unsigned int call[2]; - static int init_graph = 1; int ret; - make_call(&ftrace_graph_call, &ftrace_stub, call); - - /* - * When enabling graph tracer for the first time, ftrace_graph_call - * should contains a call to ftrace_stub. Once it has been disabled, - * the 8-bytes at the position becomes NOPs. - */ - if (init_graph) { - ret = ftrace_check_current_call((unsigned long)&ftrace_graph_call, - call); - init_graph = 0; - } else { - ret = ftrace_check_current_call((unsigned long)&ftrace_graph_call, - NULL); - } - + ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call, + (unsigned long)&prepare_ftrace_return, true); if (ret) return ret; - return __ftrace_modify_call((unsigned long)&ftrace_graph_call, + return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call, (unsigned long)&prepare_ftrace_return, true); } int ftrace_disable_ftrace_graph_caller(void) { - unsigned int call[2]; int ret; - make_call(&ftrace_graph_call, &prepare_ftrace_return, call); - - /* - * This is to make sure that ftrace_enable_ftrace_graph_caller - * did the right thing. - */ - ret = ftrace_check_current_call((unsigned long)&ftrace_graph_call, - call); - + ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call, + (unsigned long)&prepare_ftrace_return, false); if (ret) return ret; - return __ftrace_modify_call((unsigned long)&ftrace_graph_call, + return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call, (unsigned long)&prepare_ftrace_return, false); } #endif /* CONFIG_DYNAMIC_FTRACE */ diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 16e9941900c4..f5a9bad86e58 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -260,7 +260,11 @@ clear_bss_done: /* Initialize page tables and relocate to virtual addresses */ la sp, init_thread_union + THREAD_SIZE +#ifdef CONFIG_BUILTIN_DTB + la a0, __dtb_start +#else mv a0, s1 +#endif /* CONFIG_BUILTIN_DTB */ call setup_vm #ifdef CONFIG_MMU la a0, early_pg_dir diff --git a/arch/riscv/kernel/image-vars.h b/arch/riscv/kernel/image-vars.h index 8c212efb37a6..71a76a623257 100644 --- a/arch/riscv/kernel/image-vars.h +++ b/arch/riscv/kernel/image-vars.h @@ -3,7 +3,7 @@ * Copyright (C) 2020 Western Digital Corporation or its affiliates. * Linker script variables to be set after section resolution, as * ld.lld does not like variables assigned before SECTIONS is processed. - * Based on arch/arm64/kerne/image-vars.h + * Based on arch/arm64/kernel/image-vars.h */ #ifndef __RISCV_KERNEL_IMAGE_VARS_H #define __RISCV_KERNEL_IMAGE_VARS_H diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S index 35a6ed76cb8b..d171eca623b6 100644 --- a/arch/riscv/kernel/mcount-dyn.S +++ b/arch/riscv/kernel/mcount-dyn.S @@ -13,224 +13,186 @@ .text - .macro SAVE_ABI_STATE -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - addi sp, sp, -48 - sd s0, 32(sp) - sd ra, 40(sp) - addi s0, sp, 48 - sd t0, 24(sp) - sd t1, 16(sp) -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - sd t2, 8(sp) -#endif -#else - addi sp, sp, -16 - sd s0, 0(sp) - sd ra, 8(sp) - addi s0, sp, 16 -#endif +#define FENTRY_RA_OFFSET 12 +#define ABI_SIZE_ON_STACK 72 +#define ABI_A0 0 +#define ABI_A1 8 +#define ABI_A2 16 +#define ABI_A3 24 +#define ABI_A4 32 +#define ABI_A5 40 +#define ABI_A6 48 +#define ABI_A7 56 +#define ABI_RA 64 + + .macro SAVE_ABI + addi sp, sp, -SZREG + addi sp, sp, -ABI_SIZE_ON_STACK + + REG_S a0, ABI_A0(sp) + REG_S a1, ABI_A1(sp) + REG_S a2, ABI_A2(sp) + REG_S a3, ABI_A3(sp) + REG_S a4, ABI_A4(sp) + REG_S a5, ABI_A5(sp) + REG_S a6, ABI_A6(sp) + REG_S a7, ABI_A7(sp) + REG_S ra, ABI_RA(sp) .endm - .macro RESTORE_ABI_STATE -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - ld s0, 32(sp) - ld ra, 40(sp) - addi sp, sp, 48 -#else - ld ra, 8(sp) - ld s0, 0(sp) - addi sp, sp, 16 -#endif + .macro RESTORE_ABI + REG_L a0, ABI_A0(sp) + REG_L a1, ABI_A1(sp) + REG_L a2, ABI_A2(sp) + REG_L a3, ABI_A3(sp) + REG_L a4, ABI_A4(sp) + REG_L a5, ABI_A5(sp) + REG_L a6, ABI_A6(sp) + REG_L a7, ABI_A7(sp) + REG_L ra, ABI_RA(sp) + + addi sp, sp, ABI_SIZE_ON_STACK + addi sp, sp, SZREG .endm - .macro RESTORE_GRAPH_ARGS - ld a0, 24(sp) - ld a1, 16(sp) -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - ld a2, 8(sp) -#endif +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + .macro SAVE_ALL + addi sp, sp, -SZREG + addi sp, sp, -PT_SIZE_ON_STACK + + REG_S x1, PT_EPC(sp) + addi sp, sp, PT_SIZE_ON_STACK + REG_L x1, (sp) + addi sp, sp, -PT_SIZE_ON_STACK + REG_S x1, PT_RA(sp) + REG_L x1, PT_EPC(sp) + + REG_S x2, PT_SP(sp) + REG_S x3, PT_GP(sp) + REG_S x4, PT_TP(sp) + REG_S x5, PT_T0(sp) + REG_S x6, PT_T1(sp) + REG_S x7, PT_T2(sp) + REG_S x8, PT_S0(sp) + REG_S x9, PT_S1(sp) + REG_S x10, PT_A0(sp) + REG_S x11, PT_A1(sp) + REG_S x12, PT_A2(sp) + REG_S x13, PT_A3(sp) + REG_S x14, PT_A4(sp) + REG_S x15, PT_A5(sp) + REG_S x16, PT_A6(sp) + REG_S x17, PT_A7(sp) + REG_S x18, PT_S2(sp) + REG_S x19, PT_S3(sp) + REG_S x20, PT_S4(sp) + REG_S x21, PT_S5(sp) + REG_S x22, PT_S6(sp) + REG_S x23, PT_S7(sp) + REG_S x24, PT_S8(sp) + REG_S x25, PT_S9(sp) + REG_S x26, PT_S10(sp) + REG_S x27, PT_S11(sp) + REG_S x28, PT_T3(sp) + REG_S x29, PT_T4(sp) + REG_S x30, PT_T5(sp) + REG_S x31, PT_T6(sp) .endm -ENTRY(ftrace_graph_caller) - addi sp, sp, -16 - sd s0, 0(sp) - sd ra, 8(sp) - addi s0, sp, 16 -ftrace_graph_call: - .global ftrace_graph_call - /* - * Calling ftrace_enable/disable_ftrace_graph_caller would overwrite the - * call below. Check ftrace_modify_all_code for details. - */ - call ftrace_stub - ld ra, 8(sp) - ld s0, 0(sp) - addi sp, sp, 16 - ret -ENDPROC(ftrace_graph_caller) + .macro RESTORE_ALL + REG_L x1, PT_RA(sp) + addi sp, sp, PT_SIZE_ON_STACK + REG_S x1, (sp) + addi sp, sp, -PT_SIZE_ON_STACK + REG_L x1, PT_EPC(sp) + REG_L x2, PT_SP(sp) + REG_L x3, PT_GP(sp) + REG_L x4, PT_TP(sp) + REG_L x5, PT_T0(sp) + REG_L x6, PT_T1(sp) + REG_L x7, PT_T2(sp) + REG_L x8, PT_S0(sp) + REG_L x9, PT_S1(sp) + REG_L x10, PT_A0(sp) + REG_L x11, PT_A1(sp) + REG_L x12, PT_A2(sp) + REG_L x13, PT_A3(sp) + REG_L x14, PT_A4(sp) + REG_L x15, PT_A5(sp) + REG_L x16, PT_A6(sp) + REG_L x17, PT_A7(sp) + REG_L x18, PT_S2(sp) + REG_L x19, PT_S3(sp) + REG_L x20, PT_S4(sp) + REG_L x21, PT_S5(sp) + REG_L x22, PT_S6(sp) + REG_L x23, PT_S7(sp) + REG_L x24, PT_S8(sp) + REG_L x25, PT_S9(sp) + REG_L x26, PT_S10(sp) + REG_L x27, PT_S11(sp) + REG_L x28, PT_T3(sp) + REG_L x29, PT_T4(sp) + REG_L x30, PT_T5(sp) + REG_L x31, PT_T6(sp) + + addi sp, sp, PT_SIZE_ON_STACK + addi sp, sp, SZREG + .endm +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ ENTRY(ftrace_caller) - /* - * a0: the address in the caller when calling ftrace_caller - * a1: the caller's return address - * a2: the address of global variable function_trace_op - */ - ld a1, -8(s0) - addi a0, ra, -MCOUNT_INSN_SIZE - la t5, function_trace_op - ld a2, 0(t5) + SAVE_ABI -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* - * the graph tracer (specifically, prepare_ftrace_return) needs these - * arguments but for now the function tracer occupies the regs, so we - * save them in temporary regs to recover later. - */ - addi t0, s0, -8 - mv t1, a0 -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - ld t2, -16(s0) -#endif -#endif + addi a0, ra, -FENTRY_RA_OFFSET + la a1, function_trace_op + REG_L a2, 0(a1) + REG_L a1, ABI_SIZE_ON_STACK(sp) + mv a3, sp - SAVE_ABI_STATE ftrace_call: .global ftrace_call - /* - * For the dynamic ftrace to work, here we should reserve at least - * 8 bytes for a functional auipc-jalr pair. The following call - * serves this purpose. - * - * Calling ftrace_update_ftrace_func would overwrite the nops below. - * Check ftrace_modify_all_code for details. - */ call ftrace_stub #ifdef CONFIG_FUNCTION_GRAPH_TRACER - RESTORE_GRAPH_ARGS - call ftrace_graph_caller + addi a0, sp, ABI_SIZE_ON_STACK + REG_L a1, ABI_RA(sp) + addi a1, a1, -FENTRY_RA_OFFSET +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST + mv a2, s0 #endif - - RESTORE_ABI_STATE +ftrace_graph_call: + .global ftrace_graph_call + call ftrace_stub +#endif + RESTORE_ABI ret ENDPROC(ftrace_caller) #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS - .macro SAVE_ALL - addi sp, sp, -(PT_SIZE_ON_STACK+16) - sd s0, (PT_SIZE_ON_STACK)(sp) - sd ra, (PT_SIZE_ON_STACK+8)(sp) - addi s0, sp, (PT_SIZE_ON_STACK+16) - - sd x1, PT_RA(sp) - sd x2, PT_SP(sp) - sd x3, PT_GP(sp) - sd x4, PT_TP(sp) - sd x5, PT_T0(sp) - sd x6, PT_T1(sp) - sd x7, PT_T2(sp) - sd x8, PT_S0(sp) - sd x9, PT_S1(sp) - sd x10, PT_A0(sp) - sd x11, PT_A1(sp) - sd x12, PT_A2(sp) - sd x13, PT_A3(sp) - sd x14, PT_A4(sp) - sd x15, PT_A5(sp) - sd x16, PT_A6(sp) - sd x17, PT_A7(sp) - sd x18, PT_S2(sp) - sd x19, PT_S3(sp) - sd x20, PT_S4(sp) - sd x21, PT_S5(sp) - sd x22, PT_S6(sp) - sd x23, PT_S7(sp) - sd x24, PT_S8(sp) - sd x25, PT_S9(sp) - sd x26, PT_S10(sp) - sd x27, PT_S11(sp) - sd x28, PT_T3(sp) - sd x29, PT_T4(sp) - sd x30, PT_T5(sp) - sd x31, PT_T6(sp) - .endm - - .macro RESTORE_ALL - ld x1, PT_RA(sp) - ld x2, PT_SP(sp) - ld x3, PT_GP(sp) - ld x4, PT_TP(sp) - ld x5, PT_T0(sp) - ld x6, PT_T1(sp) - ld x7, PT_T2(sp) - ld x8, PT_S0(sp) - ld x9, PT_S1(sp) - ld x10, PT_A0(sp) - ld x11, PT_A1(sp) - ld x12, PT_A2(sp) - ld x13, PT_A3(sp) - ld x14, PT_A4(sp) - ld x15, PT_A5(sp) - ld x16, PT_A6(sp) - ld x17, PT_A7(sp) - ld x18, PT_S2(sp) - ld x19, PT_S3(sp) - ld x20, PT_S4(sp) - ld x21, PT_S5(sp) - ld x22, PT_S6(sp) - ld x23, PT_S7(sp) - ld x24, PT_S8(sp) - ld x25, PT_S9(sp) - ld x26, PT_S10(sp) - ld x27, PT_S11(sp) - ld x28, PT_T3(sp) - ld x29, PT_T4(sp) - ld x30, PT_T5(sp) - ld x31, PT_T6(sp) - - ld s0, (PT_SIZE_ON_STACK)(sp) - ld ra, (PT_SIZE_ON_STACK+8)(sp) - addi sp, sp, (PT_SIZE_ON_STACK+16) - .endm - - .macro RESTORE_GRAPH_REG_ARGS - ld a0, PT_T0(sp) - ld a1, PT_T1(sp) -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - ld a2, PT_T2(sp) -#endif - .endm - -/* - * Most of the contents are the same as ftrace_caller. - */ ENTRY(ftrace_regs_caller) - /* - * a3: the address of all registers in the stack - */ - ld a1, -8(s0) - addi a0, ra, -MCOUNT_INSN_SIZE - la t5, function_trace_op - ld a2, 0(t5) - addi a3, sp, -(PT_SIZE_ON_STACK+16) - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - addi t0, s0, -8 - mv t1, a0 -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - ld t2, -16(s0) -#endif -#endif SAVE_ALL + addi a0, ra, -FENTRY_RA_OFFSET + la a1, function_trace_op + REG_L a2, 0(a1) + REG_L a1, PT_SIZE_ON_STACK(sp) + mv a3, sp + ftrace_regs_call: .global ftrace_regs_call call ftrace_stub #ifdef CONFIG_FUNCTION_GRAPH_TRACER - RESTORE_GRAPH_REG_ARGS - call ftrace_graph_caller + addi a0, sp, PT_RA + REG_L a1, PT_EPC(sp) + addi a1, a1, -FENTRY_RA_OFFSET +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST + mv a2, s0 +#endif +ftrace_graph_regs_call: + .global ftrace_graph_regs_call + call ftrace_stub #endif RESTORE_ALL diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 3fe7a5296aa5..0b552873a577 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -20,7 +20,12 @@ struct patch_insn { }; #ifdef CONFIG_MMU -static void *patch_map(void *addr, int fixmap) +/* + * The fix_to_virt(, idx) needs a const value (not a dynamic variable of + * reg-a0) or BUILD_BUG_ON failed with "idx >= __end_of_fixed_addresses". + * So use '__always_inline' and 'const unsigned int fixmap' here. + */ +static __always_inline void *patch_map(void *addr, const unsigned int fixmap) { uintptr_t uintaddr = (uintptr_t) addr; struct page *page; @@ -37,7 +42,6 @@ static void *patch_map(void *addr, int fixmap) return (void *)set_fixmap_offset(fixmap, page_to_phys(page) + (uintaddr & ~PAGE_MASK)); } -NOKPROBE_SYMBOL(patch_map); static void patch_unmap(int fixmap) { diff --git a/arch/riscv/kernel/probes/Makefile b/arch/riscv/kernel/probes/Makefile new file mode 100644 index 000000000000..7f0840dcc31b --- /dev/null +++ b/arch/riscv/kernel/probes/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_KPROBES) += kprobes.o decode-insn.o simulate-insn.o +obj-$(CONFIG_KPROBES) += kprobes_trampoline.o +obj-$(CONFIG_KPROBES_ON_FTRACE) += ftrace.o +obj-$(CONFIG_UPROBES) += uprobes.o decode-insn.o simulate-insn.o +CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE) diff --git a/arch/riscv/kernel/probes/decode-insn.c b/arch/riscv/kernel/probes/decode-insn.c new file mode 100644 index 000000000000..0ed043acc882 --- /dev/null +++ b/arch/riscv/kernel/probes/decode-insn.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include +#include +#include +#include +#include + +#include "decode-insn.h" +#include "simulate-insn.h" + +/* Return: + * INSN_REJECTED If instruction is one not allowed to kprobe, + * INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot. + */ +enum probe_insn __kprobes +riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *api) +{ + probe_opcode_t insn = *addr; + + /* + * Reject instructions list: + */ + RISCV_INSN_REJECTED(system, insn); + RISCV_INSN_REJECTED(fence, insn); + + /* + * Simulate instructions list: + * TODO: the REJECTED ones below need to be implemented + */ +#ifdef CONFIG_RISCV_ISA_C + RISCV_INSN_REJECTED(c_j, insn); + RISCV_INSN_REJECTED(c_jr, insn); + RISCV_INSN_REJECTED(c_jal, insn); + RISCV_INSN_REJECTED(c_jalr, insn); + RISCV_INSN_REJECTED(c_beqz, insn); + RISCV_INSN_REJECTED(c_bnez, insn); + RISCV_INSN_REJECTED(c_ebreak, insn); +#endif + + RISCV_INSN_REJECTED(auipc, insn); + RISCV_INSN_REJECTED(branch, insn); + + RISCV_INSN_SET_SIMULATE(jal, insn); + RISCV_INSN_SET_SIMULATE(jalr, insn); + + return INSN_GOOD; +} diff --git a/arch/riscv/kernel/probes/decode-insn.h b/arch/riscv/kernel/probes/decode-insn.h new file mode 100644 index 000000000000..42269a7d676d --- /dev/null +++ b/arch/riscv/kernel/probes/decode-insn.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _RISCV_KERNEL_KPROBES_DECODE_INSN_H +#define _RISCV_KERNEL_KPROBES_DECODE_INSN_H + +#include +#include + +enum probe_insn { + INSN_REJECTED, + INSN_GOOD_NO_SLOT, + INSN_GOOD, +}; + +enum probe_insn __kprobes +riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *asi); + +#endif /* _RISCV_KERNEL_KPROBES_DECODE_INSN_H */ diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c new file mode 100644 index 000000000000..e6372490aa0b --- /dev/null +++ b/arch/riscv/kernel/probes/ftrace.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +/* Ftrace callback handler for kprobes -- called under preepmt disabed */ +void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *regs) +{ + struct kprobe *p; + struct kprobe_ctlblk *kcb; + + p = get_kprobe((kprobe_opcode_t *)ip); + if (unlikely(!p) || kprobe_disabled(p)) + return; + + kcb = get_kprobe_ctlblk(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(p); + } else { + unsigned long orig_ip = instruction_pointer(&(regs->regs)); + + instruction_pointer_set(&(regs->regs), ip); + + __this_cpu_write(current_kprobe, p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + if (!p->pre_handler || !p->pre_handler(p, &(regs->regs))) { + /* + * Emulate singlestep (and also recover regs->pc) + * as if there is a nop + */ + instruction_pointer_set(&(regs->regs), + (unsigned long)p->addr + MCOUNT_INSN_SIZE); + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, &(regs->regs), 0); + } + instruction_pointer_set(&(regs->regs), orig_ip); + } + + /* + * If pre_handler returns !0, it changes regs->pc. We have to + * skip emulating post_handler. + */ + __this_cpu_write(current_kprobe, NULL); + } +} +NOKPROBE_SYMBOL(kprobe_ftrace_handler); + +int arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + p->ainsn.api.insn = NULL; + return 0; +} diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c new file mode 100644 index 000000000000..a2ec18662fee --- /dev/null +++ b/arch/riscv/kernel/probes/kprobes.c @@ -0,0 +1,398 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "decode-insn.h" + +DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; +DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + +static void __kprobes +post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *); + +static void __kprobes arch_prepare_ss_slot(struct kprobe *p) +{ + unsigned long offset = GET_INSN_LENGTH(p->opcode); + + p->ainsn.api.restore = (unsigned long)p->addr + offset; + + patch_text(p->ainsn.api.insn, p->opcode); + patch_text((void *)((unsigned long)(p->ainsn.api.insn) + offset), + __BUG_INSN_32); +} + +static void __kprobes arch_prepare_simulate(struct kprobe *p) +{ + p->ainsn.api.restore = 0; +} + +static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + if (p->ainsn.api.handler) + p->ainsn.api.handler((u32)p->opcode, + (unsigned long)p->addr, regs); + + post_kprobe_handler(kcb, regs); +} + +int __kprobes arch_prepare_kprobe(struct kprobe *p) +{ + unsigned long probe_addr = (unsigned long)p->addr; + + if (probe_addr & 0x1) { + pr_warn("Address not aligned.\n"); + + return -EINVAL; + } + + /* copy instruction */ + p->opcode = *p->addr; + + /* decode instruction */ + switch (riscv_probe_decode_insn(p->addr, &p->ainsn.api)) { + case INSN_REJECTED: /* insn not supported */ + return -EINVAL; + + case INSN_GOOD_NO_SLOT: /* insn need simulation */ + p->ainsn.api.insn = NULL; + break; + + case INSN_GOOD: /* instruction uses slot */ + p->ainsn.api.insn = get_insn_slot(); + if (!p->ainsn.api.insn) + return -ENOMEM; + break; + } + + /* prepare the instruction */ + if (p->ainsn.api.insn) + arch_prepare_ss_slot(p); + else + arch_prepare_simulate(p); + + return 0; +} + +/* install breakpoint in text */ +void __kprobes arch_arm_kprobe(struct kprobe *p) +{ + if ((p->opcode & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) + patch_text(p->addr, __BUG_INSN_32); + else + patch_text(p->addr, __BUG_INSN_16); +} + +/* remove breakpoint from text */ +void __kprobes arch_disarm_kprobe(struct kprobe *p) +{ + patch_text(p->addr, p->opcode); +} + +void __kprobes arch_remove_kprobe(struct kprobe *p) +{ +} + +static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + kcb->prev_kprobe.kp = kprobe_running(); + kcb->prev_kprobe.status = kcb->kprobe_status; +} + +static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); + kcb->kprobe_status = kcb->prev_kprobe.status; +} + +static void __kprobes set_current_kprobe(struct kprobe *p) +{ + __this_cpu_write(current_kprobe, p); +} + +/* + * Interrupts need to be disabled before single-step mode is set, and not + * reenabled until after single-step mode ends. + * Without disabling interrupt on local CPU, there is a chance of + * interrupt occurrence in the period of exception return and start of + * out-of-line single-step, that result in wrongly single stepping + * into the interrupt handler. + */ +static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + kcb->saved_status = regs->status; + regs->status &= ~SR_SPIE; +} + +static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + regs->status = kcb->saved_status; +} + +static void __kprobes +set_ss_context(struct kprobe_ctlblk *kcb, unsigned long addr, struct kprobe *p) +{ + unsigned long offset = GET_INSN_LENGTH(p->opcode); + + kcb->ss_ctx.ss_pending = true; + kcb->ss_ctx.match_addr = addr + offset; +} + +static void __kprobes clear_ss_context(struct kprobe_ctlblk *kcb) +{ + kcb->ss_ctx.ss_pending = false; + kcb->ss_ctx.match_addr = 0; +} + +static void __kprobes setup_singlestep(struct kprobe *p, + struct pt_regs *regs, + struct kprobe_ctlblk *kcb, int reenter) +{ + unsigned long slot; + + if (reenter) { + save_previous_kprobe(kcb); + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_REENTER; + } else { + kcb->kprobe_status = KPROBE_HIT_SS; + } + + if (p->ainsn.api.insn) { + /* prepare for single stepping */ + slot = (unsigned long)p->ainsn.api.insn; + + set_ss_context(kcb, slot, p); /* mark pending ss */ + + /* IRQs and single stepping do not mix well. */ + kprobes_save_local_irqflag(kcb, regs); + + instruction_pointer_set(regs, slot); + } else { + /* insn simulation */ + arch_simulate_insn(p, regs); + } +} + +static int __kprobes reenter_kprobe(struct kprobe *p, + struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + switch (kcb->kprobe_status) { + case KPROBE_HIT_SSDONE: + case KPROBE_HIT_ACTIVE: + kprobes_inc_nmissed_count(p); + setup_singlestep(p, regs, kcb, 1); + break; + case KPROBE_HIT_SS: + case KPROBE_REENTER: + pr_warn("Unrecoverable kprobe detected.\n"); + dump_kprobe(p); + BUG(); + break; + default: + WARN_ON(1); + return 0; + } + + return 1; +} + +static void __kprobes +post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs) +{ + struct kprobe *cur = kprobe_running(); + + if (!cur) + return; + + /* return addr restore if non-branching insn */ + if (cur->ainsn.api.restore != 0) + regs->epc = cur->ainsn.api.restore; + + /* restore back original saved kprobe variables and continue */ + if (kcb->kprobe_status == KPROBE_REENTER) { + restore_previous_kprobe(kcb); + return; + } + + /* call post handler */ + kcb->kprobe_status = KPROBE_HIT_SSDONE; + if (cur->post_handler) { + /* post_handler can hit breakpoint and single step + * again, so we enable D-flag for recursive exception. + */ + cur->post_handler(cur, regs, 0); + } + + reset_current_kprobe(); +} + +int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + switch (kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the ip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + regs->epc = (unsigned long) cur->addr; + if (!instruction_pointer(regs)) + BUG(); + + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else + reset_current_kprobe(); + + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * We increment the nmissed count for accounting, + * we can also use npre/npostfault count for accounting + * these specific fault cases. + */ + kprobes_inc_nmissed_count(cur); + + /* + * We come here because instructions in the pre/post + * handler caused the page_fault, this could happen + * if handler tries to access user space by + * copy_from_user(), get_user() etc. Let the + * user-specified handler try to fix it first. + */ + if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) + return 1; + + /* + * In case the user-specified fault handler returned + * zero, try to fix up. + */ + if (fixup_exception(regs)) + return 1; + } + return 0; +} + +bool __kprobes +kprobe_breakpoint_handler(struct pt_regs *regs) +{ + struct kprobe *p, *cur_kprobe; + struct kprobe_ctlblk *kcb; + unsigned long addr = instruction_pointer(regs); + + kcb = get_kprobe_ctlblk(); + cur_kprobe = kprobe_running(); + + p = get_kprobe((kprobe_opcode_t *) addr); + + if (p) { + if (cur_kprobe) { + if (reenter_kprobe(p, regs, kcb)) + return true; + } else { + /* Probe hit */ + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + + /* + * If we have no pre-handler or it returned 0, we + * continue with normal processing. If we have a + * pre-handler and it returned non-zero, it will + * modify the execution path and no need to single + * stepping. Let's just reset current kprobe and exit. + * + * pre_handler can hit a breakpoint and can step thru + * before return. + */ + if (!p->pre_handler || !p->pre_handler(p, regs)) + setup_singlestep(p, regs, kcb, 0); + else + reset_current_kprobe(); + } + return true; + } + + /* + * The breakpoint instruction was removed right + * after we hit it. Another cpu has removed + * either a probepoint or a debugger breakpoint + * at this address. In either case, no further + * handling of this interrupt is appropriate. + * Return back to original instruction, and continue. + */ + return false; +} + +bool __kprobes +kprobe_single_step_handler(struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + if ((kcb->ss_ctx.ss_pending) + && (kcb->ss_ctx.match_addr == instruction_pointer(regs))) { + clear_ss_context(kcb); /* clear pending ss */ + + kprobes_restore_local_irqflag(kcb, regs); + + post_kprobe_handler(kcb, regs); + return true; + } + return false; +} + +/* + * Provide a blacklist of symbols identifying ranges which cannot be kprobed. + * This blacklist is exposed to userspace via debugfs (kprobes/blacklist). + */ +int __init arch_populate_kprobe_blacklist(void) +{ + int ret; + + ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start, + (unsigned long)__irqentry_text_end); + return ret; +} + +void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs) +{ + return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL); +} + +void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, + struct pt_regs *regs) +{ + ri->ret_addr = (kprobe_opcode_t *)regs->ra; + ri->fp = NULL; + regs->ra = (unsigned long) &kretprobe_trampoline; +} + +int __kprobes arch_trampoline_kprobe(struct kprobe *p) +{ + return 0; +} + +int __init arch_init_kprobes(void) +{ + return 0; +} diff --git a/arch/riscv/kernel/probes/kprobes_trampoline.S b/arch/riscv/kernel/probes/kprobes_trampoline.S new file mode 100644 index 000000000000..6e85d021e2a2 --- /dev/null +++ b/arch/riscv/kernel/probes/kprobes_trampoline.S @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Author: Patrick Stählin + */ +#include + +#include +#include + + .text + .altmacro + + .macro save_all_base_regs + REG_S x1, PT_RA(sp) + REG_S x3, PT_GP(sp) + REG_S x4, PT_TP(sp) + REG_S x5, PT_T0(sp) + REG_S x6, PT_T1(sp) + REG_S x7, PT_T2(sp) + REG_S x8, PT_S0(sp) + REG_S x9, PT_S1(sp) + REG_S x10, PT_A0(sp) + REG_S x11, PT_A1(sp) + REG_S x12, PT_A2(sp) + REG_S x13, PT_A3(sp) + REG_S x14, PT_A4(sp) + REG_S x15, PT_A5(sp) + REG_S x16, PT_A6(sp) + REG_S x17, PT_A7(sp) + REG_S x18, PT_S2(sp) + REG_S x19, PT_S3(sp) + REG_S x20, PT_S4(sp) + REG_S x21, PT_S5(sp) + REG_S x22, PT_S6(sp) + REG_S x23, PT_S7(sp) + REG_S x24, PT_S8(sp) + REG_S x25, PT_S9(sp) + REG_S x26, PT_S10(sp) + REG_S x27, PT_S11(sp) + REG_S x28, PT_T3(sp) + REG_S x29, PT_T4(sp) + REG_S x30, PT_T5(sp) + REG_S x31, PT_T6(sp) + .endm + + .macro restore_all_base_regs + REG_L x3, PT_GP(sp) + REG_L x4, PT_TP(sp) + REG_L x5, PT_T0(sp) + REG_L x6, PT_T1(sp) + REG_L x7, PT_T2(sp) + REG_L x8, PT_S0(sp) + REG_L x9, PT_S1(sp) + REG_L x10, PT_A0(sp) + REG_L x11, PT_A1(sp) + REG_L x12, PT_A2(sp) + REG_L x13, PT_A3(sp) + REG_L x14, PT_A4(sp) + REG_L x15, PT_A5(sp) + REG_L x16, PT_A6(sp) + REG_L x17, PT_A7(sp) + REG_L x18, PT_S2(sp) + REG_L x19, PT_S3(sp) + REG_L x20, PT_S4(sp) + REG_L x21, PT_S5(sp) + REG_L x22, PT_S6(sp) + REG_L x23, PT_S7(sp) + REG_L x24, PT_S8(sp) + REG_L x25, PT_S9(sp) + REG_L x26, PT_S10(sp) + REG_L x27, PT_S11(sp) + REG_L x28, PT_T3(sp) + REG_L x29, PT_T4(sp) + REG_L x30, PT_T5(sp) + REG_L x31, PT_T6(sp) + .endm + +ENTRY(kretprobe_trampoline) + addi sp, sp, -(PT_SIZE_ON_STACK) + save_all_base_regs + + move a0, sp /* pt_regs */ + + call trampoline_probe_handler + + /* use the result as the return-address */ + move ra, a0 + + restore_all_base_regs + addi sp, sp, PT_SIZE_ON_STACK + + ret +ENDPROC(kretprobe_trampoline) diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c new file mode 100644 index 000000000000..2519ce26377d --- /dev/null +++ b/arch/riscv/kernel/probes/simulate-insn.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include +#include +#include + +#include "decode-insn.h" +#include "simulate-insn.h" + +static inline bool rv_insn_reg_get_val(struct pt_regs *regs, u32 index, + unsigned long *ptr) +{ + if (index == 0) + *ptr = 0; + else if (index <= 31) + *ptr = *((unsigned long *)regs + index); + else + return false; + + return true; +} + +static inline bool rv_insn_reg_set_val(struct pt_regs *regs, u32 index, + unsigned long val) +{ + if (index == 0) + return false; + else if (index <= 31) + *((unsigned long *)regs + index) = val; + else + return false; + + return true; +} + +bool __kprobes simulate_jal(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * 31 30 21 20 19 12 11 7 6 0 + * imm [20] | imm[10:1] | imm[11] | imm[19:12] | rd | opcode + * 1 10 1 8 5 JAL/J + */ + bool ret; + u32 imm; + u32 index = (opcode >> 7) & 0x1f; + + ret = rv_insn_reg_set_val(regs, index, addr + 4); + if (!ret) + return ret; + + imm = ((opcode >> 21) & 0x3ff) << 1; + imm |= ((opcode >> 20) & 0x1) << 11; + imm |= ((opcode >> 12) & 0xff) << 12; + imm |= ((opcode >> 31) & 0x1) << 20; + + instruction_pointer_set(regs, addr + sign_extend32((imm), 20)); + + return ret; +} + +bool __kprobes simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * 31 20 19 15 14 12 11 7 6 0 + * offset[11:0] | rs1 | 010 | rd | opcode + * 12 5 3 5 JALR/JR + */ + bool ret; + unsigned long base_addr; + u32 imm = (opcode >> 20) & 0xfff; + u32 rd_index = (opcode >> 7) & 0x1f; + u32 rs1_index = (opcode >> 15) & 0x1f; + + ret = rv_insn_reg_set_val(regs, rd_index, addr + 4); + if (!ret) + return ret; + + ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr); + if (!ret) + return ret; + + instruction_pointer_set(regs, (base_addr + sign_extend32((imm), 11))&~1); + + return ret; +} diff --git a/arch/riscv/kernel/probes/simulate-insn.h b/arch/riscv/kernel/probes/simulate-insn.h new file mode 100644 index 000000000000..cb6ff7dccb92 --- /dev/null +++ b/arch/riscv/kernel/probes/simulate-insn.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _RISCV_KERNEL_PROBES_SIMULATE_INSN_H +#define _RISCV_KERNEL_PROBES_SIMULATE_INSN_H + +#define __RISCV_INSN_FUNCS(name, mask, val) \ +static __always_inline bool riscv_insn_is_##name(probe_opcode_t code) \ +{ \ + BUILD_BUG_ON(~(mask) & (val)); \ + return (code & (mask)) == (val); \ +} \ +bool simulate_##name(u32 opcode, unsigned long addr, \ + struct pt_regs *regs) + +#define RISCV_INSN_REJECTED(name, code) \ + do { \ + if (riscv_insn_is_##name(code)) { \ + return INSN_REJECTED; \ + } \ + } while (0) + +__RISCV_INSN_FUNCS(system, 0x7f, 0x73); +__RISCV_INSN_FUNCS(fence, 0x7f, 0x0f); + +#define RISCV_INSN_SET_SIMULATE(name, code) \ + do { \ + if (riscv_insn_is_##name(code)) { \ + api->handler = simulate_##name; \ + return INSN_GOOD_NO_SLOT; \ + } \ + } while (0) + +__RISCV_INSN_FUNCS(c_j, 0xe003, 0xa001); +__RISCV_INSN_FUNCS(c_jr, 0xf007, 0x8002); +__RISCV_INSN_FUNCS(c_jal, 0xe003, 0x2001); +__RISCV_INSN_FUNCS(c_jalr, 0xf007, 0x9002); +__RISCV_INSN_FUNCS(c_beqz, 0xe003, 0xc001); +__RISCV_INSN_FUNCS(c_bnez, 0xe003, 0xe001); +__RISCV_INSN_FUNCS(c_ebreak, 0xffff, 0x9002); + +__RISCV_INSN_FUNCS(auipc, 0x7f, 0x17); +__RISCV_INSN_FUNCS(branch, 0x7f, 0x63); + +__RISCV_INSN_FUNCS(jal, 0x7f, 0x6f); +__RISCV_INSN_FUNCS(jalr, 0x707f, 0x67); + +#endif /* _RISCV_KERNEL_PROBES_SIMULATE_INSN_H */ diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c new file mode 100644 index 000000000000..7a057b5f0adc --- /dev/null +++ b/arch/riscv/kernel/probes/uprobes.c @@ -0,0 +1,186 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include + +#include "decode-insn.h" + +#define UPROBE_TRAP_NR UINT_MAX + +bool is_swbp_insn(uprobe_opcode_t *insn) +{ +#ifdef CONFIG_RISCV_ISA_C + return (*insn & 0xffff) == UPROBE_SWBP_INSN; +#else + return *insn == UPROBE_SWBP_INSN; +#endif +} + +unsigned long uprobe_get_swbp_addr(struct pt_regs *regs) +{ + return instruction_pointer(regs); +} + +int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, + unsigned long addr) +{ + probe_opcode_t opcode; + + opcode = *(probe_opcode_t *)(&auprobe->insn[0]); + + auprobe->insn_size = GET_INSN_LENGTH(opcode); + + switch (riscv_probe_decode_insn(&opcode, &auprobe->api)) { + case INSN_REJECTED: + return -EINVAL; + + case INSN_GOOD_NO_SLOT: + auprobe->simulate = true; + break; + + case INSN_GOOD: + auprobe->simulate = false; + break; + + default: + return -EINVAL; + } + + return 0; +} + +int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + utask->autask.saved_cause = current->thread.bad_cause; + current->thread.bad_cause = UPROBE_TRAP_NR; + + instruction_pointer_set(regs, utask->xol_vaddr); + + regs->status &= ~SR_SPIE; + + return 0; +} + +int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + WARN_ON_ONCE(current->thread.bad_cause != UPROBE_TRAP_NR); + + instruction_pointer_set(regs, utask->vaddr + auprobe->insn_size); + + regs->status |= SR_SPIE; + + return 0; +} + +bool arch_uprobe_xol_was_trapped(struct task_struct *t) +{ + if (t->thread.bad_cause != UPROBE_TRAP_NR) + return true; + + return false; +} + +bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + probe_opcode_t insn; + unsigned long addr; + + if (!auprobe->simulate) + return false; + + insn = *(probe_opcode_t *)(&auprobe->insn[0]); + addr = instruction_pointer(regs); + + if (auprobe->api.handler) + auprobe->api.handler(insn, addr, regs); + + return true; +} + +void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + /* + * Task has received a fatal signal, so reset back to probbed + * address. + */ + instruction_pointer_set(regs, utask->vaddr); + + regs->status &= ~SR_SPIE; +} + +bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx, + struct pt_regs *regs) +{ + if (ctx == RP_CHECK_CHAIN_CALL) + return regs->sp <= ret->stack; + else + return regs->sp < ret->stack; +} + +unsigned long +arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, + struct pt_regs *regs) +{ + unsigned long ra; + + ra = regs->ra; + + regs->ra = trampoline_vaddr; + + return ra; +} + +int arch_uprobe_exception_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + return NOTIFY_DONE; +} + +bool uprobe_breakpoint_handler(struct pt_regs *regs) +{ + if (uprobe_pre_sstep_notifier(regs)) + return true; + + return false; +} + +bool uprobe_single_step_handler(struct pt_regs *regs) +{ + if (uprobe_post_sstep_notifier(regs)) + return true; + + return false; +} + +void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, + void *src, unsigned long len) +{ + /* Initialize the slot */ + void *kaddr = kmap_atomic(page); + void *dst = kaddr + (vaddr & ~PAGE_MASK); + + memcpy(dst, src, len); + + /* Add ebreak behind opcode to simulate singlestep */ + if (vaddr) { + dst += GET_INSN_LENGTH(*(probe_opcode_t *)src); + *(uprobe_opcode_t *)dst = __BUG_INSN_32; + } + + kunmap_atomic(kaddr); + + /* + * We probably need flush_icache_user_page() but it needs vma. + * This should work on most of architectures by default. If + * architecture needs to do something different it can define + * its own version of the function. + */ + flush_dcache_page(page); +} diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index dd5f985b1f40..19f4688f2f36 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -18,13 +18,14 @@ #include #include #include +#include #include #include #include register unsigned long gp_in_global __asm__("gp"); -#ifdef CONFIG_STACKPROTECTOR +#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) #include unsigned long __stack_chk_guard __read_mostly; EXPORT_SYMBOL(__stack_chk_guard); @@ -39,11 +40,16 @@ void arch_cpu_idle(void) raw_local_irq_enable(); } -void show_regs(struct pt_regs *regs) +void __show_regs(struct pt_regs *regs) { show_regs_print_info(KERN_DEFAULT); - pr_cont("epc: " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n", + if (!user_mode(regs)) { + pr_cont("epc : %pS\n", (void *)regs->epc); + pr_cont(" ra : %pS\n", (void *)regs->ra); + } + + pr_cont("epc : " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n", regs->epc, regs->ra, regs->sp); pr_cont(" gp : " REG_FMT " tp : " REG_FMT " t0 : " REG_FMT "\n", regs->gp, regs->tp, regs->t0); @@ -69,6 +75,12 @@ void show_regs(struct pt_regs *regs) pr_cont("status: " REG_FMT " badaddr: " REG_FMT " cause: " REG_FMT "\n", regs->status, regs->badaddr, regs->cause); } +void show_regs(struct pt_regs *regs) +{ + __show_regs(regs); + if (!user_mode(regs)) + dump_backtrace(regs, NULL, KERN_DEFAULT); +} void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 2d6395f5ad54..1a85305720e8 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -114,6 +114,105 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task) return &riscv_user_native_view; } +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} +#define REG_OFFSET_END {.name = NULL, .offset = 0} + +static const struct pt_regs_offset regoffset_table[] = { + REG_OFFSET_NAME(epc), + REG_OFFSET_NAME(ra), + REG_OFFSET_NAME(sp), + REG_OFFSET_NAME(gp), + REG_OFFSET_NAME(tp), + REG_OFFSET_NAME(t0), + REG_OFFSET_NAME(t1), + REG_OFFSET_NAME(t2), + REG_OFFSET_NAME(s0), + REG_OFFSET_NAME(s1), + REG_OFFSET_NAME(a0), + REG_OFFSET_NAME(a1), + REG_OFFSET_NAME(a2), + REG_OFFSET_NAME(a3), + REG_OFFSET_NAME(a4), + REG_OFFSET_NAME(a5), + REG_OFFSET_NAME(a6), + REG_OFFSET_NAME(a7), + REG_OFFSET_NAME(s2), + REG_OFFSET_NAME(s3), + REG_OFFSET_NAME(s4), + REG_OFFSET_NAME(s5), + REG_OFFSET_NAME(s6), + REG_OFFSET_NAME(s7), + REG_OFFSET_NAME(s8), + REG_OFFSET_NAME(s9), + REG_OFFSET_NAME(s10), + REG_OFFSET_NAME(s11), + REG_OFFSET_NAME(t3), + REG_OFFSET_NAME(t4), + REG_OFFSET_NAME(t5), + REG_OFFSET_NAME(t6), + REG_OFFSET_NAME(status), + REG_OFFSET_NAME(badaddr), + REG_OFFSET_NAME(cause), + REG_OFFSET_NAME(orig_a0), + REG_OFFSET_END, +}; + +/** + * regs_query_register_offset() - query register offset from its name + * @name: the name of a register + * + * regs_query_register_offset() returns the offset of a register in struct + * pt_regs from its name. If the name is invalid, this returns -EINVAL; + */ +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_offset *roff; + + for (roff = regoffset_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->offset; + return -EINVAL; +} + +/** + * regs_within_kernel_stack() - check the address in the stack + * @regs: pt_regs which contains kernel stack pointer. + * @addr: address which is checked. + * + * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). + * If @addr is within the kernel stack, it returns true. If not, returns false. + */ +static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) +{ + return (addr & ~(THREAD_SIZE - 1)) == + (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1)); +} + +/** + * regs_get_kernel_stack_nth() - get Nth entry of the stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which + * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * this returns 0. + */ +unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) +{ + unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return *addr; + else + return 0; +} + void ptrace_disable(struct task_struct *child) { clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index 226ccce0f9e0..f4a7db3d309e 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -351,7 +351,7 @@ static int __sbi_rfence_v02(int fid, const unsigned long *hart_mask, * sbi_set_timer() - Program the timer for next timer event. * @stime_value: The value after which next timer event should fire. * - * Return: None + * Return: None. */ void sbi_set_timer(uint64_t stime_value) { @@ -362,11 +362,11 @@ void sbi_set_timer(uint64_t stime_value) * sbi_send_ipi() - Send an IPI to any hart. * @hart_mask: A cpu mask containing all the target harts. * - * Return: None + * Return: 0 on success, appropriate linux error code otherwise. */ -void sbi_send_ipi(const unsigned long *hart_mask) +int sbi_send_ipi(const unsigned long *hart_mask) { - __sbi_send_ipi(hart_mask); + return __sbi_send_ipi(hart_mask); } EXPORT_SYMBOL(sbi_send_ipi); @@ -374,12 +374,12 @@ EXPORT_SYMBOL(sbi_send_ipi); * sbi_remote_fence_i() - Execute FENCE.I instruction on given remote harts. * @hart_mask: A cpu mask containing all the target harts. * - * Return: None + * Return: 0 on success, appropriate linux error code otherwise. */ -void sbi_remote_fence_i(const unsigned long *hart_mask) +int sbi_remote_fence_i(const unsigned long *hart_mask) { - __sbi_rfence(SBI_EXT_RFENCE_REMOTE_FENCE_I, - hart_mask, 0, 0, 0, 0); + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_FENCE_I, + hart_mask, 0, 0, 0, 0); } EXPORT_SYMBOL(sbi_remote_fence_i); @@ -390,14 +390,14 @@ EXPORT_SYMBOL(sbi_remote_fence_i); * @start: Start of the virtual address * @size: Total size of the virtual address range. * - * Return: None + * Return: 0 on success, appropriate linux error code otherwise. */ -void sbi_remote_sfence_vma(const unsigned long *hart_mask, +int sbi_remote_sfence_vma(const unsigned long *hart_mask, unsigned long start, unsigned long size) { - __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA, - hart_mask, start, size, 0, 0); + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA, + hart_mask, start, size, 0, 0); } EXPORT_SYMBOL(sbi_remote_sfence_vma); @@ -410,15 +410,15 @@ EXPORT_SYMBOL(sbi_remote_sfence_vma); * @size: Total size of the virtual address range. * @asid: The value of address space identifier (ASID). * - * Return: None + * Return: 0 on success, appropriate linux error code otherwise. */ -void sbi_remote_sfence_vma_asid(const unsigned long *hart_mask, +int sbi_remote_sfence_vma_asid(const unsigned long *hart_mask, unsigned long start, unsigned long size, unsigned long asid) { - __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID, - hart_mask, start, size, asid, 0); + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID, + hart_mask, start, size, asid, 0); } EXPORT_SYMBOL(sbi_remote_sfence_vma_asid); @@ -560,7 +560,7 @@ static struct riscv_ipi_ops sbi_ipi_ops = { .ipi_inject = sbi_send_cpumask_ipi }; -int __init sbi_init(void) +void __init sbi_init(void) { int ret; @@ -600,6 +600,4 @@ int __init sbi_init(void) } riscv_set_ipi_ops(&sbi_ipi_ops); - - return 0; } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index c7c0655dd45b..e85bacff1b50 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -216,8 +216,15 @@ static void __init init_resources(void) static void __init parse_dtb(void) { /* Early scan of device tree from init memory */ - if (early_init_dt_scan(dtb_early_va)) + if (early_init_dt_scan(dtb_early_va)) { + const char *name = of_flat_dt_get_machine_name(); + + if (name) { + pr_info("Machine model: %s\n", name); + dump_stack_set_arch_desc("%s (DT)", name); + } return; + } pr_err("No DTB passed to the kernel\n"); #ifdef CONFIG_CMDLINE_FORCE @@ -252,9 +259,9 @@ void __init setup_arch(char **cmdline_p) else pr_err("No DTB found in kernel mappings\n"); #endif + misc_mem_init(); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_init(); + sbi_init(); if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) protect_kernel_text_data(); @@ -275,13 +282,19 @@ void __init setup_arch(char **cmdline_p) static int __init topology_init(void) { - int i; + int i, ret; + + for_each_online_node(i) + register_one_node(i); for_each_possible_cpu(i) { struct cpu *cpu = &per_cpu(cpu_devices, i); cpu->hotpluggable = cpu_has_hotplug(i); - register_cpu(cpu, i); + ret = register_cpu(cpu, i); + if (unlikely(ret)) + pr_warn("Warning: %s: register_cpu %d failed (%d)\n", + __func__, i, ret); } return 0; diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 469aef8ed922..65942b3748b4 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -309,6 +309,9 @@ static void do_signal(struct pt_regs *regs) asmlinkage __visible void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) { + if (thread_info_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); + /* Handle pending signal delivery */ if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 96167d55ed98..5e276c25646f 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -45,13 +46,18 @@ void __init smp_prepare_cpus(unsigned int max_cpus) { int cpuid; int ret; + unsigned int curr_cpuid; + + curr_cpuid = smp_processor_id(); + numa_store_cpu_info(curr_cpuid); + numa_add_cpu(curr_cpuid); /* This covers non-smp usecase mandated by "nosmp" option */ if (max_cpus == 0) return; for_each_possible_cpu(cpuid) { - if (cpuid == smp_processor_id()) + if (cpuid == curr_cpuid) continue; if (cpu_ops[cpuid]->cpu_prepare) { ret = cpu_ops[cpuid]->cpu_prepare(cpuid); @@ -59,6 +65,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) continue; } set_cpu_present(cpuid, true); + numa_store_cpu_info(cpuid); } } @@ -79,6 +86,7 @@ void __init setup_smp(void) if (hart == cpuid_to_hartid_map(0)) { BUG_ON(found_boot_cpu); found_boot_cpu = 1; + early_map_cpu_to_node(0, of_node_to_nid(dn)); continue; } if (cpuid >= NR_CPUS) { @@ -88,6 +96,7 @@ void __init setup_smp(void) } cpuid_to_hartid_map(cpuid) = hart; + early_map_cpu_to_node(cpuid, of_node_to_nid(dn)); cpuid++; } @@ -153,6 +162,7 @@ asmlinkage __visible void smp_callin(void) current->active_mm = mm; notify_cpu_starting(curr_cpuid); + numa_add_cpu(curr_cpuid); update_siblings_masks(curr_cpuid); set_cpu_online(curr_cpuid, 1); diff --git a/arch/riscv/kernel/soc.c b/arch/riscv/kernel/soc.c index c7b0a73e382e..a0516172a33c 100644 --- a/arch/riscv/kernel/soc.c +++ b/arch/riscv/kernel/soc.c @@ -26,30 +26,3 @@ void __init soc_early_init(void) } } } - -static bool soc_builtin_dtb_match(unsigned long vendor_id, - unsigned long arch_id, unsigned long imp_id, - const struct soc_builtin_dtb *entry) -{ - return entry->vendor_id == vendor_id && - entry->arch_id == arch_id && - entry->imp_id == imp_id; -} - -void * __init soc_lookup_builtin_dtb(void) -{ - unsigned long vendor_id, arch_id, imp_id; - const struct soc_builtin_dtb *s; - - __asm__ ("csrr %0, mvendorid" : "=r"(vendor_id)); - __asm__ ("csrr %0, marchid" : "=r"(arch_id)); - __asm__ ("csrr %0, mimpid" : "=r"(imp_id)); - - for (s = (void *)&__soc_builtin_dtb_table_start; - (void *)s < (void *)&__soc_builtin_dtb_table_end; s++) { - if (soc_builtin_dtb_match(vendor_id, arch_id, imp_id, s)) - return s->dtb_func(); - } - - return NULL; -} diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index df5d2da7c40b..3f893c9d9d85 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -53,9 +53,15 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, /* Unwind stack frame */ frame = (struct stackframe *)fp - 1; sp = fp; - fp = frame->fp; - pc = ftrace_graph_ret_addr(current, NULL, frame->ra, - (unsigned long *)(fp - 8)); + if (regs && (regs->epc == pc) && (frame->fp & 0x7)) { + fp = frame->ra; + pc = regs->ra; + } else { + fp = frame->fp; + pc = ftrace_graph_ret_addr(current, NULL, frame->ra, + (unsigned long *)(fp - 8)); + } + } } @@ -100,10 +106,16 @@ static bool print_trace_address(void *arg, unsigned long pc) return true; } +void dump_backtrace(struct pt_regs *regs, struct task_struct *task, + const char *loglvl) +{ + pr_cont("%sCall Trace:\n", loglvl); + walk_stackframe(task, regs, print_trace_address, (void *)loglvl); +} + void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) { - pr_cont("Call Trace:\n"); - walk_stackframe(task, NULL, print_trace_address, (void *)loglvl); + dump_backtrace(NULL, task, loglvl); } static bool save_wchan(void *arg, unsigned long pc) diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index ad14f4466d92..3ed2c23601a0 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -12,10 +12,12 @@ #include #include #include +#include #include #include #include +#include #include #include #include @@ -66,7 +68,7 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) tsk->comm, task_pid_nr(tsk), signo, code, addr); print_vma_addr(KERN_CONT " in ", instruction_pointer(regs)); pr_cont("\n"); - show_regs(regs); + __show_regs(regs); } force_sig_fault(signo, code, (void __user *)addr); @@ -75,6 +77,8 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) static void do_trap_error(struct pt_regs *regs, int signo, int code, unsigned long addr, const char *str) { + current->thread.bad_cause = regs->cause; + if (user_mode(regs)) { do_trap(regs, signo, code, addr); } else { @@ -145,6 +149,22 @@ static inline unsigned long get_break_insn_length(unsigned long pc) asmlinkage __visible void do_trap_break(struct pt_regs *regs) { +#ifdef CONFIG_KPROBES + if (kprobe_single_step_handler(regs)) + return; + + if (kprobe_breakpoint_handler(regs)) + return; +#endif +#ifdef CONFIG_UPROBES + if (uprobe_single_step_handler(regs)) + return; + + if (uprobe_breakpoint_handler(regs)) + return; +#endif + current->thread.bad_cause = regs->cause; + if (user_mode(regs)) force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->epc); #ifdef CONFIG_KGDB diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 0cfd6da784f8..71a315e73cbe 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -32,9 +32,10 @@ CPPFLAGS_vdso.lds += -P -C -U$(ARCH) # Disable -pg to prevent insert call site CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os -# Disable gcov profiling for VDSO code +# Disable profiling and instrumentation for VDSO code GCOV_PROFILE := n KCOV_INSTRUMENT := n +KASAN_SANITIZE := n # Force dependency $(obj)/vdso.o: $(obj)/vdso.so diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index ac6171e9c19e..25d5c9664e57 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -5,3 +5,5 @@ lib-y += memset.o lib-y += memmove.o lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_64BIT) += tishift.o + +obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/riscv/lib/error-inject.c b/arch/riscv/lib/error-inject.c new file mode 100644 index 000000000000..d667ade2bc41 --- /dev/null +++ b/arch/riscv/lib/error-inject.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +void override_function_with_return(struct pt_regs *regs) +{ + instruction_pointer_set(regs, regs->ra); +} +NOKPROBE_SYMBOL(override_function_with_return); diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile index c0185e556ca5..7ebaef10ea1b 100644 --- a/arch/riscv/mm/Makefile +++ b/arch/riscv/mm/Makefile @@ -2,7 +2,8 @@ CFLAGS_init.o := -mcmodel=medany ifdef CONFIG_FTRACE -CFLAGS_REMOVE_init.o = -pg +CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_cacheflush.o = $(CC_FLAGS_FTRACE) endif KCOV_INSTRUMENT_init.o := n diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c index 613ec81a8979..68aa312fc352 100644 --- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -2,13 +2,273 @@ /* * Copyright (C) 2012 Regents of the University of California * Copyright (C) 2017 SiFive + * Copyright (C) 2021 Western Digital Corporation or its affiliates. */ +#include +#include #include +#include +#include +#include +#include #include #include #include +#ifdef CONFIG_MMU + +static DEFINE_STATIC_KEY_FALSE(use_asid_allocator); + +static unsigned long asid_bits; +static unsigned long num_asids; +static unsigned long asid_mask; + +static atomic_long_t current_version; + +static DEFINE_RAW_SPINLOCK(context_lock); +static cpumask_t context_tlb_flush_pending; +static unsigned long *context_asid_map; + +static DEFINE_PER_CPU(atomic_long_t, active_context); +static DEFINE_PER_CPU(unsigned long, reserved_context); + +static bool check_update_reserved_context(unsigned long cntx, + unsigned long newcntx) +{ + int cpu; + bool hit = false; + + /* + * Iterate over the set of reserved CONTEXT looking for a match. + * If we find one, then we can update our mm to use new CONTEXT + * (i.e. the same CONTEXT in the current_version) but we can't + * exit the loop early, since we need to ensure that all copies + * of the old CONTEXT are updated to reflect the mm. Failure to do + * so could result in us missing the reserved CONTEXT in a future + * version. + */ + for_each_possible_cpu(cpu) { + if (per_cpu(reserved_context, cpu) == cntx) { + hit = true; + per_cpu(reserved_context, cpu) = newcntx; + } + } + + return hit; +} + +static void __flush_context(void) +{ + int i; + unsigned long cntx; + + /* Must be called with context_lock held */ + lockdep_assert_held(&context_lock); + + /* Update the list of reserved ASIDs and the ASID bitmap. */ + bitmap_clear(context_asid_map, 0, num_asids); + + /* Mark already active ASIDs as used */ + for_each_possible_cpu(i) { + cntx = atomic_long_xchg_relaxed(&per_cpu(active_context, i), 0); + /* + * If this CPU has already been through a rollover, but + * hasn't run another task in the meantime, we must preserve + * its reserved CONTEXT, as this is the only trace we have of + * the process it is still running. + */ + if (cntx == 0) + cntx = per_cpu(reserved_context, i); + + __set_bit(cntx & asid_mask, context_asid_map); + per_cpu(reserved_context, i) = cntx; + } + + /* Mark ASID #0 as used because it is used at boot-time */ + __set_bit(0, context_asid_map); + + /* Queue a TLB invalidation for each CPU on next context-switch */ + cpumask_setall(&context_tlb_flush_pending); +} + +static unsigned long __new_context(struct mm_struct *mm) +{ + static u32 cur_idx = 1; + unsigned long cntx = atomic_long_read(&mm->context.id); + unsigned long asid, ver = atomic_long_read(¤t_version); + + /* Must be called with context_lock held */ + lockdep_assert_held(&context_lock); + + if (cntx != 0) { + unsigned long newcntx = ver | (cntx & asid_mask); + + /* + * If our current CONTEXT was active during a rollover, we + * can continue to use it and this was just a false alarm. + */ + if (check_update_reserved_context(cntx, newcntx)) + return newcntx; + + /* + * We had a valid CONTEXT in a previous life, so try to + * re-use it if possible. + */ + if (!__test_and_set_bit(cntx & asid_mask, context_asid_map)) + return newcntx; + } + + /* + * Allocate a free ASID. If we can't find one then increment + * current_version and flush all ASIDs. + */ + asid = find_next_zero_bit(context_asid_map, num_asids, cur_idx); + if (asid != num_asids) + goto set_asid; + + /* We're out of ASIDs, so increment current_version */ + ver = atomic_long_add_return_relaxed(num_asids, ¤t_version); + + /* Flush everything */ + __flush_context(); + + /* We have more ASIDs than CPUs, so this will always succeed */ + asid = find_next_zero_bit(context_asid_map, num_asids, 1); + +set_asid: + __set_bit(asid, context_asid_map); + cur_idx = asid; + return asid | ver; +} + +static void set_mm_asid(struct mm_struct *mm, unsigned int cpu) +{ + unsigned long flags; + bool need_flush_tlb = false; + unsigned long cntx, old_active_cntx; + + cntx = atomic_long_read(&mm->context.id); + + /* + * If our active_context is non-zero and the context matches the + * current_version, then we update the active_context entry with a + * relaxed cmpxchg. + * + * Following is how we handle racing with a concurrent rollover: + * + * - We get a zero back from the cmpxchg and end up waiting on the + * lock. Taking the lock synchronises with the rollover and so + * we are forced to see the updated verion. + * + * - We get a valid context back from the cmpxchg then we continue + * using old ASID because __flush_context() would have marked ASID + * of active_context as used and next context switch we will + * allocate new context. + */ + old_active_cntx = atomic_long_read(&per_cpu(active_context, cpu)); + if (old_active_cntx && + ((cntx & ~asid_mask) == atomic_long_read(¤t_version)) && + atomic_long_cmpxchg_relaxed(&per_cpu(active_context, cpu), + old_active_cntx, cntx)) + goto switch_mm_fast; + + raw_spin_lock_irqsave(&context_lock, flags); + + /* Check that our ASID belongs to the current_version. */ + cntx = atomic_long_read(&mm->context.id); + if ((cntx & ~asid_mask) != atomic_long_read(¤t_version)) { + cntx = __new_context(mm); + atomic_long_set(&mm->context.id, cntx); + } + + if (cpumask_test_and_clear_cpu(cpu, &context_tlb_flush_pending)) + need_flush_tlb = true; + + atomic_long_set(&per_cpu(active_context, cpu), cntx); + + raw_spin_unlock_irqrestore(&context_lock, flags); + +switch_mm_fast: + csr_write(CSR_SATP, virt_to_pfn(mm->pgd) | + ((cntx & asid_mask) << SATP_ASID_SHIFT) | + SATP_MODE); + + if (need_flush_tlb) + local_flush_tlb_all(); +} + +static void set_mm_noasid(struct mm_struct *mm) +{ + /* Switch the page table and blindly nuke entire local TLB */ + csr_write(CSR_SATP, virt_to_pfn(mm->pgd) | SATP_MODE); + local_flush_tlb_all(); +} + +static inline void set_mm(struct mm_struct *mm, unsigned int cpu) +{ + if (static_branch_unlikely(&use_asid_allocator)) + set_mm_asid(mm, cpu); + else + set_mm_noasid(mm); +} + +static int asids_init(void) +{ + unsigned long old; + + /* Figure-out number of ASID bits in HW */ + old = csr_read(CSR_SATP); + asid_bits = old | (SATP_ASID_MASK << SATP_ASID_SHIFT); + csr_write(CSR_SATP, asid_bits); + asid_bits = (csr_read(CSR_SATP) >> SATP_ASID_SHIFT) & SATP_ASID_MASK; + asid_bits = fls_long(asid_bits); + csr_write(CSR_SATP, old); + + /* + * In the process of determining number of ASID bits (above) + * we polluted the TLB of current HART so let's do TLB flushed + * to remove unwanted TLB enteries. + */ + local_flush_tlb_all(); + + /* Pre-compute ASID details */ + num_asids = 1 << asid_bits; + asid_mask = num_asids - 1; + + /* + * Use ASID allocator only if number of HW ASIDs are + * at-least twice more than CPUs + */ + if (num_asids > (2 * num_possible_cpus())) { + atomic_long_set(¤t_version, num_asids); + + context_asid_map = kcalloc(BITS_TO_LONGS(num_asids), + sizeof(*context_asid_map), GFP_KERNEL); + if (!context_asid_map) + panic("Failed to allocate bitmap for %lu ASIDs\n", + num_asids); + + __set_bit(0, context_asid_map); + + static_branch_enable(&use_asid_allocator); + + pr_info("ASID allocator using %lu bits (%lu entries)\n", + asid_bits, num_asids); + } else { + pr_info("ASID allocator disabled\n"); + } + + return 0; +} +early_initcall(asids_init); +#else +static inline void set_mm(struct mm_struct *mm, unsigned int cpu) +{ + /* Nothing to do here when there is no MMU */ +} +#endif + /* * When necessary, performs a deferred icache flush for the given MM context, * on the local CPU. RISC-V has no direct mechanism for instruction cache @@ -58,10 +318,7 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, cpumask_clear_cpu(cpu, mm_cpumask(prev)); cpumask_set_cpu(cpu, mm_cpumask(next)); -#ifdef CONFIG_MMU - csr_write(CSR_SATP, virt_to_pfn(next->pgd) | SATP_MODE); - local_flush_tlb_all(); -#endif + set_mm(next, cpu); flush_icache_deferred(next); } diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 3c8b9e433c67..8f17519208c7 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -13,14 +13,30 @@ #include #include #include +#include #include #include #include "../kernel/head.h" +static void die_kernel_fault(const char *msg, unsigned long addr, + struct pt_regs *regs) +{ + bust_spinlocks(1); + + pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n", msg, + addr); + + bust_spinlocks(0); + die(regs, "Oops"); + do_exit(SIGKILL); +} + static inline void no_context(struct pt_regs *regs, unsigned long addr) { + const char *msg; + /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs)) return; @@ -29,12 +45,8 @@ static inline void no_context(struct pt_regs *regs, unsigned long addr) * Oops. The kernel tried to access some bad page. We'll have to * terminate things with extreme prejudice. */ - bust_spinlocks(1); - pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n", - (addr < PAGE_SIZE) ? "NULL pointer dereference" : - "paging request", addr); - die(regs, "Oops"); - do_exit(SIGKILL); + msg = (addr < PAGE_SIZE) ? "NULL pointer dereference" : "paging request"; + die_kernel_fault(msg, addr, regs); } static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault) @@ -202,6 +214,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs) tsk = current; mm = tsk->mm; + if (kprobe_page_fault(regs, cause)) + return; + /* * Fault-in kernel-space virtual memory on-demand. * The 'reference' page table is init_mm.pgd. @@ -225,6 +240,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs) * in an atomic region, then we must not take the fault. */ if (unlikely(faulthandler_disabled() || !mm)) { + tsk->thread.bad_cause = cause; no_context(regs, addr); return; } @@ -232,6 +248,11 @@ asmlinkage void do_page_fault(struct pt_regs *regs) if (user_mode(regs)) flags |= FAULT_FLAG_USER; + if (!user_mode(regs) && addr < TASK_SIZE && + unlikely(!(regs->status & SR_SUM))) + die_kernel_fault("access to user memory without uaccess routines", + addr, regs); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); if (cause == EXC_STORE_PAGE_FAULT) @@ -242,16 +263,19 @@ asmlinkage void do_page_fault(struct pt_regs *regs) mmap_read_lock(mm); vma = find_vma(mm, addr); if (unlikely(!vma)) { + tsk->thread.bad_cause = cause; bad_area(regs, mm, code, addr); return; } if (likely(vma->vm_start <= addr)) goto good_area; if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { + tsk->thread.bad_cause = cause; bad_area(regs, mm, code, addr); return; } if (unlikely(expand_stack(vma, addr))) { + tsk->thread.bad_cause = cause; bad_area(regs, mm, code, addr); return; } @@ -264,6 +288,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs) code = SEGV_ACCERR; if (unlikely(access_error(cause, vma))) { + tsk->thread.bad_cause = cause; bad_area(regs, mm, code, addr); return; } @@ -297,6 +322,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs) mmap_read_unlock(mm); if (unlikely(fault & VM_FAULT_ERROR)) { + tsk->thread.bad_cause = cause; mm_fault_error(regs, addr, fault); return; } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index f9f9568d689e..9dfb8b2dffd6 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -21,6 +21,7 @@ #include #include #include +#include #include "../kernel/head.h" @@ -105,55 +106,6 @@ void __init mem_init(void) print_vm_layout(); } -#ifdef CONFIG_BLK_DEV_INITRD -static void __init setup_initrd(void) -{ - phys_addr_t start; - unsigned long size; - - /* Ignore the virtul address computed during device tree parsing */ - initrd_start = initrd_end = 0; - - if (!phys_initrd_size) - return; - /* - * Round the memory region to page boundaries as per free_initrd_mem() - * This allows us to detect whether the pages overlapping the initrd - * are in use, but more importantly, reserves the entire set of pages - * as we don't want these pages allocated for other purposes. - */ - start = round_down(phys_initrd_start, PAGE_SIZE); - size = phys_initrd_size + (phys_initrd_start - start); - size = round_up(size, PAGE_SIZE); - - if (!memblock_is_region_memory(start, size)) { - pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region", - (u64)start, size); - goto disable; - } - - if (memblock_is_region_reserved(start, size)) { - pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region\n", - (u64)start, size); - goto disable; - } - - memblock_reserve(start, size); - /* Now convert initrd to virtual addresses */ - initrd_start = (unsigned long)__va(phys_initrd_start); - initrd_end = initrd_start + phys_initrd_size; - initrd_below_start_ok = 1; - - pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n", - (void *)(initrd_start), size); - return; -disable: - pr_cont(" - disabling initrd\n"); - initrd_start = 0; - initrd_end = 0; -} -#endif /* CONFIG_BLK_DEV_INITRD */ - void __init setup_bootmem(void) { phys_addr_t mem_start = 0; @@ -198,20 +150,19 @@ void __init setup_bootmem(void) dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET); -#ifdef CONFIG_BLK_DEV_INITRD - setup_initrd(); -#endif /* CONFIG_BLK_DEV_INITRD */ - + reserve_initrd_mem(); /* - * Avoid using early_init_fdt_reserve_self() since __pa() does + * If DTB is built in, no need to reserve its memblock. + * Otherwise, do reserve it but avoid using + * early_init_fdt_reserve_self() since __pa() does * not work for DTB pointers that are fixmap addresses */ - memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); + if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) + memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); early_init_fdt_scan_reserved_mem(); dma_contiguous_reserve(dma32_phys_limit); memblock_allow_resize(); - memblock_dump_all(); } #ifdef CONFIG_MMU @@ -226,8 +177,6 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss; pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss; pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss; -#define MAX_EARLY_MAPPING_SIZE SZ_128M - pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) @@ -302,13 +251,7 @@ static void __init create_pte_mapping(pte_t *ptep, pmd_t trampoline_pmd[PTRS_PER_PMD] __page_aligned_bss; pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss; - -#if MAX_EARLY_MAPPING_SIZE < PGDIR_SIZE -#define NUM_EARLY_PMDS 1UL -#else -#define NUM_EARLY_PMDS (1UL + MAX_EARLY_MAPPING_SIZE / PGDIR_SIZE) -#endif -pmd_t early_pmd[PTRS_PER_PMD * NUM_EARLY_PMDS] __initdata __aligned(PAGE_SIZE); +pmd_t early_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE); pmd_t early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE); static pmd_t *__init get_pmd_virt_early(phys_addr_t pa) @@ -330,11 +273,9 @@ static pmd_t *get_pmd_virt_late(phys_addr_t pa) static phys_addr_t __init alloc_pmd_early(uintptr_t va) { - uintptr_t pmd_num; + BUG_ON((va - PAGE_OFFSET) >> PGDIR_SHIFT); - pmd_num = (va - PAGE_OFFSET) >> PGDIR_SHIFT; - BUG_ON(pmd_num >= NUM_EARLY_PMDS); - return (uintptr_t)&early_pmd[pmd_num * PTRS_PER_PMD]; + return (uintptr_t)early_pmd; } static phys_addr_t __init alloc_pmd_fixmap(uintptr_t va) @@ -452,7 +393,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) uintptr_t va, pa, end_va; uintptr_t load_pa = (uintptr_t)(&_start); uintptr_t load_sz = (uintptr_t)(&_end) - load_pa; - uintptr_t map_size = best_map_size(load_pa, MAX_EARLY_MAPPING_SIZE); + uintptr_t map_size; #ifndef __PAGETABLE_PMD_FOLDED pmd_t fix_bmap_spmd, fix_bmap_epmd; #endif @@ -464,12 +405,11 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) * Enforce boot alignment requirements of RV32 and * RV64 by only allowing PMD or PGD mappings. */ - BUG_ON(map_size == PAGE_SIZE); + map_size = PMD_SIZE; /* Sanity check alignment and size */ BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0); BUG_ON((load_pa % map_size) != 0); - BUG_ON(load_sz > MAX_EARLY_MAPPING_SIZE); pt_ops.alloc_pte = alloc_pte_early; pt_ops.get_pte_virt = get_pte_virt_early; @@ -511,6 +451,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) /* Setup early PMD for DTB */ create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, (uintptr_t)early_dtb_pmd, PGDIR_SIZE, PAGE_TABLE); +#ifndef CONFIG_BUILTIN_DTB /* Create two consecutive PMD mappings for FDT early scan */ pa = dtb_pa & ~(PMD_SIZE - 1); create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA, @@ -518,7 +459,11 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE, pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL); dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1)); +#else /* CONFIG_BUILTIN_DTB */ + dtb_early_va = __va(dtb_pa); +#endif /* CONFIG_BUILTIN_DTB */ #else +#ifndef CONFIG_BUILTIN_DTB /* Create two consecutive PGD mappings for FDT early scan */ pa = dtb_pa & ~(PGDIR_SIZE - 1); create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, @@ -526,6 +471,9 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA + PGDIR_SIZE, pa + PGDIR_SIZE, PGDIR_SIZE, PAGE_KERNEL); dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PGDIR_SIZE - 1)); +#else /* CONFIG_BUILTIN_DTB */ + dtb_early_va = __va(dtb_pa); +#endif /* CONFIG_BUILTIN_DTB */ #endif dtb_early_pa = dtb_pa; @@ -616,15 +564,7 @@ static void __init setup_vm_final(void) #else asmlinkage void __init setup_vm(uintptr_t dtb_pa) { -#ifdef CONFIG_BUILTIN_DTB - dtb_early_va = soc_lookup_builtin_dtb(); - if (!dtb_early_va) { - /* Fallback to first available DTS */ - dtb_early_va = (void *) __dtb_start; - } -#else dtb_early_va = (void *)dtb_pa; -#endif dtb_early_pa = dtb_pa; } @@ -665,9 +605,15 @@ void mark_rodata_ro(void) void __init paging_init(void) { setup_vm_final(); - sparse_init(); setup_zero_page(); +} + +void __init misc_mem_init(void) +{ + arch_numa_init(); + sparse_init(); zone_sizes_init(); + memblock_dump_all(); } #ifdef CONFIG_SPARSEMEM_VMEMMAP diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index a8a2ffd9114a..3fc18f469efb 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -9,6 +9,19 @@ #include #include #include +#include + +static __init void *early_alloc(size_t size, int node) +{ + void *ptr = memblock_alloc_try_nid(size, size, + __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, node); + + if (!ptr) + panic("%pS: Failed to allocate %zu bytes align=%zx nid=%d from=%llx\n", + __func__, size, size, node, (u64)__pa(MAX_DMA_ADDRESS)); + + return ptr; +} extern pgd_t early_pg_dir[PTRS_PER_PGD]; asmlinkage void __init kasan_early_init(void) @@ -47,40 +60,133 @@ asmlinkage void __init kasan_early_init(void) local_flush_tlb_all(); } -static void __init populate(void *start, void *end) +static void kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned long end) +{ + phys_addr_t phys_addr; + pte_t *ptep, *base_pte; + + if (pmd_none(*pmd)) + base_pte = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); + else + base_pte = (pte_t *)pmd_page_vaddr(*pmd); + + ptep = base_pte + pte_index(vaddr); + + do { + if (pte_none(*ptep)) { + phys_addr = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); + set_pte(ptep, pfn_pte(PFN_DOWN(phys_addr), PAGE_KERNEL)); + } + } while (ptep++, vaddr += PAGE_SIZE, vaddr != end); + + set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(base_pte)), PAGE_TABLE)); +} + +static void kasan_populate_pmd(pgd_t *pgd, unsigned long vaddr, unsigned long end) +{ + phys_addr_t phys_addr; + pmd_t *pmdp, *base_pmd; + unsigned long next; + + base_pmd = (pmd_t *)pgd_page_vaddr(*pgd); + if (base_pmd == lm_alias(kasan_early_shadow_pmd)) + base_pmd = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); + + pmdp = base_pmd + pmd_index(vaddr); + + do { + next = pmd_addr_end(vaddr, end); + + if (pmd_none(*pmdp) && IS_ALIGNED(vaddr, PMD_SIZE) && (next - vaddr) >= PMD_SIZE) { + phys_addr = memblock_phys_alloc(PMD_SIZE, PMD_SIZE); + if (phys_addr) { + set_pmd(pmdp, pfn_pmd(PFN_DOWN(phys_addr), PAGE_KERNEL)); + continue; + } + } + + kasan_populate_pte(pmdp, vaddr, next); + } while (pmdp++, vaddr = next, vaddr != end); + + /* + * Wait for the whole PGD to be populated before setting the PGD in + * the page table, otherwise, if we did set the PGD before populating + * it entirely, memblock could allocate a page at a physical address + * where KASAN is not populated yet and then we'd get a page fault. + */ + set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE)); +} + +static void kasan_populate_pgd(unsigned long vaddr, unsigned long end) +{ + phys_addr_t phys_addr; + pgd_t *pgdp = pgd_offset_k(vaddr); + unsigned long next; + + do { + next = pgd_addr_end(vaddr, end); + + /* + * pgdp can't be none since kasan_early_init initialized all KASAN + * shadow region with kasan_early_shadow_pmd: if this is stillthe case, + * that means we can try to allocate a hugepage as a replacement. + */ + if (pgd_page_vaddr(*pgdp) == (unsigned long)lm_alias(kasan_early_shadow_pmd) && + IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) { + phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE); + if (phys_addr) { + set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_KERNEL)); + continue; + } + } + + kasan_populate_pmd(pgdp, vaddr, next); + } while (pgdp++, vaddr = next, vaddr != end); +} + +static void __init kasan_populate(void *start, void *end) { - unsigned long i, offset; unsigned long vaddr = (unsigned long)start & PAGE_MASK; unsigned long vend = PAGE_ALIGN((unsigned long)end); - unsigned long n_pages = (vend - vaddr) / PAGE_SIZE; - unsigned long n_ptes = - ((n_pages + PTRS_PER_PTE) & -PTRS_PER_PTE) / PTRS_PER_PTE; - unsigned long n_pmds = - ((n_ptes + PTRS_PER_PMD) & -PTRS_PER_PMD) / PTRS_PER_PMD; - pte_t *pte = - memblock_alloc(n_ptes * PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); - pmd_t *pmd = - memblock_alloc(n_pmds * PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); - pgd_t *pgd = pgd_offset_k(vaddr); - - for (i = 0; i < n_pages; i++) { - phys_addr_t phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); - set_pte(&pte[i], pfn_pte(PHYS_PFN(phys), PAGE_KERNEL)); - } - - for (i = 0, offset = 0; i < n_ptes; i++, offset += PTRS_PER_PTE) - set_pmd(&pmd[i], - pfn_pmd(PFN_DOWN(__pa(&pte[offset])), - __pgprot(_PAGE_TABLE))); - - for (i = 0, offset = 0; i < n_pmds; i++, offset += PTRS_PER_PMD) - set_pgd(&pgd[i], - pfn_pgd(PFN_DOWN(__pa(&pmd[offset])), - __pgprot(_PAGE_TABLE))); + kasan_populate_pgd(vaddr, vend); local_flush_tlb_all(); - memset(start, 0, end - start); + memset(start, KASAN_SHADOW_INIT, end - start); +} + +void __init kasan_shallow_populate(void *start, void *end) +{ + unsigned long vaddr = (unsigned long)start & PAGE_MASK; + unsigned long vend = PAGE_ALIGN((unsigned long)end); + unsigned long pfn; + int index; + void *p; + pud_t *pud_dir, *pud_k; + pgd_t *pgd_dir, *pgd_k; + p4d_t *p4d_dir, *p4d_k; + + while (vaddr < vend) { + index = pgd_index(vaddr); + pfn = csr_read(CSR_SATP) & SATP_PPN; + pgd_dir = (pgd_t *)pfn_to_virt(pfn) + index; + pgd_k = init_mm.pgd + index; + pgd_dir = pgd_offset_k(vaddr); + set_pgd(pgd_dir, *pgd_k); + + p4d_dir = p4d_offset(pgd_dir, vaddr); + p4d_k = p4d_offset(pgd_k, vaddr); + + vaddr = (vaddr + PUD_SIZE) & PUD_MASK; + pud_dir = pud_offset(p4d_dir, vaddr); + pud_k = pud_offset(p4d_k, vaddr); + + if (pud_present(*pud_dir)) { + p = early_alloc(PAGE_SIZE, NUMA_NO_NODE); + pud_populate(&init_mm, pud_dir, p); + } + vaddr += PAGE_SIZE; + } } void __init kasan_init(void) @@ -90,7 +196,15 @@ void __init kasan_init(void) kasan_populate_early_shadow((void *)KASAN_SHADOW_START, (void *)kasan_mem_to_shadow((void *) - VMALLOC_END)); + VMEMMAP_END)); + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) + kasan_shallow_populate( + (void *)kasan_mem_to_shadow((void *)VMALLOC_START), + (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); + else + kasan_populate_early_shadow( + (void *)kasan_mem_to_shadow((void *)VMALLOC_START), + (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); for_each_mem_range(i, &_start, &_end) { void *start = (void *)__va(_start); @@ -99,7 +213,7 @@ void __init kasan_init(void) if (start >= end) break; - populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end)); + kasan_populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end)); }; for (i = 0; i < PTRS_PER_PTE; i++) @@ -108,6 +222,6 @@ void __init kasan_init(void) __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_ACCESSED))); - memset(kasan_early_shadow_page, 0, PAGE_SIZE); + memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE); init_task.kasan_depth = 0; } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 73a163065b95..0e76b2127dc6 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -297,6 +297,7 @@ int arch_add_memory(int nid, u64 start, u64 size, if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot)) return -EINVAL; + VM_BUG_ON(!mhp_range_allowed(start, size, true)); rc = vmem_add_mapping(start, size); if (rc) return rc; diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 01f3a5f58e64..82dbf9450105 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -4,6 +4,7 @@ * Author(s): Heiko Carstens */ +#include #include #include #include @@ -532,11 +533,22 @@ void vmem_remove_mapping(unsigned long start, unsigned long size) mutex_unlock(&vmem_mutex); } +struct range arch_get_mappable_range(void) +{ + struct range mhp_range; + + mhp_range.start = 0; + mhp_range.end = VMEM_MAX_PHYS - 1; + return mhp_range; +} + int vmem_add_mapping(unsigned long start, unsigned long size) { + struct range range = arch_get_mappable_range(); int ret; - if (start + size > VMEM_MAX_PHYS || + if (start < range.start || + start + size > range.end + 1 || start + size < start) return -ERANGE; diff --git a/arch/sh/kernel/syscalls/Makefile b/arch/sh/kernel/syscalls/Makefile index 659faefdcb1d..285aaba832d9 100644 --- a/arch/sh/kernel/syscalls/Makefile +++ b/arch/sh/kernel/syscalls/Makefile @@ -5,7 +5,7 @@ uapi := arch/$(SRCARCH)/include/generated/uapi/asm _dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') -syscall := $(srctree)/$(src)/syscall.tbl +syscall := $(src)/syscall.tbl syshdr := $(srctree)/$(src)/syscallhdr.sh systbl := $(srctree)/$(src)/syscalltbl.sh @@ -21,18 +21,19 @@ quiet_cmd_systbl = SYSTBL $@ '$(systbl_abi_$(basetarget))' \ '$(systbl_offset_$(basetarget))' -$(uapi)/unistd_32.h: $(syscall) $(syshdr) +$(uapi)/unistd_32.h: $(syscall) $(syshdr) FORCE $(call if_changed,syshdr) -$(kapi)/syscall_table.h: $(syscall) $(systbl) +$(kapi)/syscall_table.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) uapisyshdr-y += unistd_32.h kapisyshdr-y += syscall_table.h -targets += $(uapisyshdr-y) $(kapisyshdr-y) +uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) +kapisyshdr-y := $(addprefix $(kapi)/, $(kapisyshdr-y)) +targets += $(addprefix ../../../../, $(uapisyshdr-y) $(kapisyshdr-y)) PHONY += all -all: $(addprefix $(uapi)/,$(uapisyshdr-y)) -all: $(addprefix $(kapi)/,$(kapisyshdr-y)) +all: $(uapisyshdr-y) $(kapisyshdr-y) @: diff --git a/arch/sparc/kernel/syscalls/Makefile b/arch/sparc/kernel/syscalls/Makefile index c22a21c39f30..283f64407b07 100644 --- a/arch/sparc/kernel/syscalls/Makefile +++ b/arch/sparc/kernel/syscalls/Makefile @@ -5,7 +5,7 @@ uapi := arch/$(SRCARCH)/include/generated/uapi/asm _dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') -syscall := $(srctree)/$(src)/syscall.tbl +syscall := $(src)/syscall.tbl syshdr := $(srctree)/$(src)/syscallhdr.sh systbl := $(srctree)/$(src)/syscalltbl.sh @@ -22,24 +22,24 @@ quiet_cmd_systbl = SYSTBL $@ '$(systbl_offset_$(basetarget))' syshdr_abis_unistd_32 := common,32 -$(uapi)/unistd_32.h: $(syscall) $(syshdr) +$(uapi)/unistd_32.h: $(syscall) $(syshdr) FORCE $(call if_changed,syshdr) syshdr_abis_unistd_64 := common,64 -$(uapi)/unistd_64.h: $(syscall) $(syshdr) +$(uapi)/unistd_64.h: $(syscall) $(syshdr) FORCE $(call if_changed,syshdr) systbl_abis_syscall_table_32 := common,32 -$(kapi)/syscall_table_32.h: $(syscall) $(systbl) +$(kapi)/syscall_table_32.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) systbl_abis_syscall_table_64 := common,64 -$(kapi)/syscall_table_64.h: $(syscall) $(systbl) +$(kapi)/syscall_table_64.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) systbl_abis_syscall_table_c32 := common,32 systbl_abi_syscall_table_c32 := c32 -$(kapi)/syscall_table_c32.h: $(syscall) $(systbl) +$(kapi)/syscall_table_c32.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) uapisyshdr-y += unistd_32.h unistd_64.h @@ -47,9 +47,10 @@ kapisyshdr-y += syscall_table_32.h \ syscall_table_64.h \ syscall_table_c32.h -targets += $(uapisyshdr-y) $(kapisyshdr-y) +uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) +kapisyshdr-y := $(addprefix $(kapi)/, $(kapisyshdr-y)) +targets += $(addprefix ../../../../, $(uapisyshdr-y) $(kapisyshdr-y)) PHONY += all -all: $(addprefix $(uapi)/,$(uapisyshdr-y)) -all: $(addprefix $(kapi)/,$(kapisyshdr-y)) +all: $(uapisyshdr-y) $(kapisyshdr-y) @: diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cd4b9b1204a8..2792879d398e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -151,6 +151,7 @@ config X86 select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN if X86_64 select HAVE_ARCH_KASAN_VMALLOC if X86_64 + select HAVE_ARCH_KFENCE select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT diff --git a/arch/x86/entry/syscalls/Makefile b/arch/x86/entry/syscalls/Makefile index 6fb9b57ed5ba..d8c4f6c9eadc 100644 --- a/arch/x86/entry/syscalls/Makefile +++ b/arch/x86/entry/syscalls/Makefile @@ -6,8 +6,8 @@ uapi := arch/$(SRCARCH)/include/generated/uapi/asm _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \ $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') -syscall32 := $(srctree)/$(src)/syscall_32.tbl -syscall64 := $(srctree)/$(src)/syscall_64.tbl +syscall32 := $(src)/syscall_32.tbl +syscall64 := $(src)/syscall_64.tbl syshdr := $(srctree)/$(src)/syscallhdr.sh systbl := $(srctree)/$(src)/syscalltbl.sh @@ -21,37 +21,37 @@ quiet_cmd_systbl = SYSTBL $@ cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@ quiet_cmd_hypercalls = HYPERCALLS $@ - cmd_hypercalls = $(CONFIG_SHELL) '$<' $@ $(filter-out $<,$^) + cmd_hypercalls = $(CONFIG_SHELL) '$<' $@ $(filter-out $<, $(real-prereqs)) syshdr_abi_unistd_32 := i386 -$(uapi)/unistd_32.h: $(syscall32) $(syshdr) +$(uapi)/unistd_32.h: $(syscall32) $(syshdr) FORCE $(call if_changed,syshdr) syshdr_abi_unistd_32_ia32 := i386 syshdr_pfx_unistd_32_ia32 := ia32_ -$(out)/unistd_32_ia32.h: $(syscall32) $(syshdr) +$(out)/unistd_32_ia32.h: $(syscall32) $(syshdr) FORCE $(call if_changed,syshdr) syshdr_abi_unistd_x32 := common,x32 syshdr_offset_unistd_x32 := __X32_SYSCALL_BIT -$(uapi)/unistd_x32.h: $(syscall64) $(syshdr) +$(uapi)/unistd_x32.h: $(syscall64) $(syshdr) FORCE $(call if_changed,syshdr) syshdr_abi_unistd_64 := common,64 -$(uapi)/unistd_64.h: $(syscall64) $(syshdr) +$(uapi)/unistd_64.h: $(syscall64) $(syshdr) FORCE $(call if_changed,syshdr) syshdr_abi_unistd_64_x32 := x32 syshdr_pfx_unistd_64_x32 := x32_ -$(out)/unistd_64_x32.h: $(syscall64) $(syshdr) +$(out)/unistd_64_x32.h: $(syscall64) $(syshdr) FORCE $(call if_changed,syshdr) -$(out)/syscalls_32.h: $(syscall32) $(systbl) +$(out)/syscalls_32.h: $(syscall32) $(systbl) FORCE $(call if_changed,systbl) -$(out)/syscalls_64.h: $(syscall64) $(systbl) +$(out)/syscalls_64.h: $(syscall64) $(systbl) FORCE $(call if_changed,systbl) -$(out)/xen-hypercalls.h: $(srctree)/scripts/xen-hypercalls.sh +$(out)/xen-hypercalls.h: $(srctree)/scripts/xen-hypercalls.sh FORCE $(call if_changed,hypercalls) $(out)/xen-hypercalls.h: $(srctree)/include/xen/interface/xen*.h @@ -62,9 +62,10 @@ syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h unistd_64_x32.h syshdr-$(CONFIG_X86_64) += syscalls_64.h syshdr-$(CONFIG_XEN) += xen-hypercalls.h -targets += $(uapisyshdr-y) $(syshdr-y) +uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) +syshdr-y := $(addprefix $(out)/, $(syshdr-y)) +targets += $(addprefix ../../../../, $(uapisyshdr-y) $(syshdr-y)) PHONY += all -all: $(addprefix $(uapi)/,$(uapisyshdr-y)) -all: $(addprefix $(out)/,$(syshdr-y)) +all: $(uapisyshdr-y) $(syshdr-y) @: diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h new file mode 100644 index 000000000000..97bbb4a9083a --- /dev/null +++ b/arch/x86/include/asm/kfence.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * x86 KFENCE support. + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef _ASM_X86_KFENCE_H +#define _ASM_X86_KFENCE_H + +#include +#include + +#include +#include +#include +#include + +/* Force 4K pages for __kfence_pool. */ +static inline bool arch_kfence_init_pool(void) +{ + unsigned long addr; + + for (addr = (unsigned long)__kfence_pool; is_kfence_address((void *)addr); + addr += PAGE_SIZE) { + unsigned int level; + + if (!lookup_address(addr, &level)) + return false; + + if (level != PG_LEVEL_4K) + set_memory_4k(addr, 1); + } + + return true; +} + +/* Protect the given page and flush TLB. */ +static inline bool kfence_protect_page(unsigned long addr, bool protect) +{ + unsigned int level; + pte_t *pte = lookup_address(addr, &level); + + if (WARN_ON(!pte || level != PG_LEVEL_4K)) + return false; + + /* + * We need to avoid IPIs, as we may get KFENCE allocations or faults + * with interrupts disabled. Therefore, the below is best-effort, and + * does not flush TLBs on all CPUs. We can tolerate some inaccuracy; + * lazy fault handling takes care of faults after the page is PRESENT. + */ + + if (protect) + set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT)); + else + set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT)); + + /* Flush this CPU's TLB. */ + flush_tlb_one_kernel(addr); + return true; +} + +#endif /* _ASM_X86_KFENCE_H */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 355a2ab8fc09..323641097f63 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -93,11 +93,7 @@ KVM_X86_OP(check_intercept) KVM_X86_OP(handle_exit_irqoff) KVM_X86_OP_NULL(request_immediate_exit) KVM_X86_OP(sched_in) -KVM_X86_OP_NULL(slot_enable_log_dirty) -KVM_X86_OP_NULL(slot_disable_log_dirty) -KVM_X86_OP_NULL(flush_log_dirty) -KVM_X86_OP_NULL(enable_log_dirty_pt_masked) -KVM_X86_OP_NULL(cpu_dirty_log_size) +KVM_X86_OP_NULL(update_cpu_dirty_logging) KVM_X86_OP_NULL(pre_block) KVM_X86_OP_NULL(post_block) KVM_X86_OP_NULL(vcpu_blocking) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 84499aad01a4..0cf71ff2b2e5 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -89,6 +89,8 @@ KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_APF_READY KVM_ARCH_REQ(28) #define KVM_REQ_MSR_FILTER_CHANGED KVM_ARCH_REQ(29) +#define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \ + KVM_ARCH_REQ_FLAGS(30, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ @@ -1007,6 +1009,7 @@ struct kvm_arch { u32 bsp_vcpu_id; u64 disabled_quirks; + int cpu_dirty_logging_count; enum kvm_irqchip_mode irqchip_mode; u8 nr_reserved_ioapic_pins; @@ -1271,30 +1274,11 @@ struct kvm_x86_ops { void (*sched_in)(struct kvm_vcpu *kvm, int cpu); /* - * Arch-specific dirty logging hooks. These hooks are only supposed to - * be valid if the specific arch has hardware-accelerated dirty logging - * mechanism. Currently only for PML on VMX. - * - * - slot_enable_log_dirty: - * called when enabling log dirty mode for the slot. - * - slot_disable_log_dirty: - * called when disabling log dirty mode for the slot. - * also called when slot is created with log dirty disabled. - * - flush_log_dirty: - * called before reporting dirty_bitmap to userspace. - * - enable_log_dirty_pt_masked: - * called when reenabling log dirty for the GFNs in the mask after - * corresponding bits are cleared in slot->dirty_bitmap. + * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer. A zero + * value indicates CPU dirty logging is unsupported or disabled. */ - void (*slot_enable_log_dirty)(struct kvm *kvm, - struct kvm_memory_slot *slot); - void (*slot_disable_log_dirty)(struct kvm *kvm, - struct kvm_memory_slot *slot); - void (*flush_log_dirty)(struct kvm *kvm); - void (*enable_log_dirty_pt_masked)(struct kvm *kvm, - struct kvm_memory_slot *slot, - gfn_t offset, unsigned long mask); - int (*cpu_dirty_log_size)(void); + int cpu_dirty_log_size; + void (*update_cpu_dirty_logging)(struct kvm_vcpu *vcpu); /* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops; @@ -1437,11 +1421,6 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot); void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot); -void kvm_mmu_slot_set_dirty(struct kvm *kvm, - struct kvm_memory_slot *memslot); -void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, - struct kvm_memory_slot *slot, - gfn_t gfn_offset, unsigned long mask); void kvm_mmu_zap_all(struct kvm *kvm); void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); @@ -1613,7 +1592,6 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu); void kvm_update_dr7(struct kvm_vcpu *vcpu); int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); -int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); int kvm_mmu_load(struct kvm_vcpu *vcpu); void kvm_mmu_unload(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index c8f2592ccc99..6bd2f8b830e4 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -408,7 +408,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_7_0_EBX, F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | - F(BMI2) | F(ERMS) | 0 /*INVPCID*/ | F(RTM) | 0 /*MPX*/ | F(RDSEED) | + F(BMI2) | F(ERMS) | F(INVPCID) | F(RTM) | 0 /*MPX*/ | F(RDSEED) | F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) | F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) | F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | 0 /*INTEL_PT*/ diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index e507568cd55d..d75524bc8423 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1165,7 +1165,8 @@ static bool spte_wrprot_for_clear_dirty(u64 *sptep) * - W bit on ad-disabled SPTEs. * Returns true iff any D or W bits were cleared. */ -static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) +static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot) { u64 *sptep; struct rmap_iterator iter; @@ -1180,35 +1181,6 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) return flush; } -static bool spte_set_dirty(u64 *sptep) -{ - u64 spte = *sptep; - - rmap_printk("spte %p %llx\n", sptep, *sptep); - - /* - * Similar to the !kvm_x86_ops.slot_disable_log_dirty case, - * do not bother adding back write access to pages marked - * SPTE_AD_WRPROT_ONLY_MASK. - */ - spte |= shadow_dirty_mask; - - return mmu_spte_update(sptep, spte); -} - -static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) -{ - u64 *sptep; - struct rmap_iterator iter; - bool flush = false; - - for_each_rmap_spte(rmap_head, &iter, sptep) - if (spte_ad_enabled(*sptep)) - flush |= spte_set_dirty(sptep); - - return flush; -} - /** * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages * @kvm: kvm instance @@ -1248,9 +1220,9 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, * * Used for PML to re-log the dirty GPAs after userspace querying dirty_bitmap. */ -void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, - struct kvm_memory_slot *slot, - gfn_t gfn_offset, unsigned long mask) +static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn_offset, unsigned long mask) { struct kvm_rmap_head *rmap_head; @@ -1260,13 +1232,12 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, while (mask) { rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), PG_LEVEL_4K, slot); - __rmap_clear_dirty(kvm, rmap_head); + __rmap_clear_dirty(kvm, rmap_head, slot); /* clear the first set bit */ mask &= mask - 1; } } -EXPORT_SYMBOL_GPL(kvm_mmu_clear_dirty_pt_masked); /** * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected @@ -1282,20 +1253,15 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { - if (kvm_x86_ops.enable_log_dirty_pt_masked) - static_call(kvm_x86_enable_log_dirty_pt_masked)(kvm, slot, - gfn_offset, - mask); + if (kvm_x86_ops.cpu_dirty_log_size) + kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask); else kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } int kvm_cpu_dirty_log_size(void) { - if (kvm_x86_ops.cpu_dirty_log_size) - return static_call(kvm_x86_cpu_dirty_log_size)(); - - return 0; + return kvm_x86_ops.cpu_dirty_log_size; } bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, @@ -1325,7 +1291,8 @@ static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn); } -static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head) +static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot) { u64 *sptep; struct rmap_iterator iter; @@ -1345,7 +1312,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { - return kvm_zap_rmapp(kvm, rmap_head); + return kvm_zap_rmapp(kvm, rmap_head, slot); } static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, @@ -2499,7 +2466,21 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) return r; } -EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page); + +static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) +{ + gpa_t gpa; + int r; + + if (vcpu->arch.mmu->direct_map) + return 0; + + gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); + + r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); + + return r; +} static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { @@ -2753,11 +2734,18 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) if (sp->role.level > PG_LEVEL_4K) return; + /* + * If addresses are being invalidated, skip prefetching to avoid + * accidentally prefetching those addresses. + */ + if (unlikely(vcpu->kvm->mmu_notifier_count)) + return; + __direct_pte_prefetch(vcpu, sp, sptep); } -static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn, - kvm_pfn_t pfn, struct kvm_memory_slot *slot) +static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, + struct kvm_memory_slot *slot) { unsigned long hva; pte_t *pte; @@ -2776,19 +2764,36 @@ static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn, */ hva = __gfn_to_hva_memslot(slot, gfn); - pte = lookup_address_in_mm(vcpu->kvm->mm, hva, &level); + pte = lookup_address_in_mm(kvm->mm, hva, &level); if (unlikely(!pte)) return PG_LEVEL_4K; return level; } +int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, kvm_pfn_t pfn, int max_level) +{ + struct kvm_lpage_info *linfo; + + max_level = min(max_level, max_huge_page_level); + for ( ; max_level > PG_LEVEL_4K; max_level--) { + linfo = lpage_info_slot(gfn, slot, max_level); + if (!linfo->disallow_lpage) + break; + } + + if (max_level == PG_LEVEL_4K) + return PG_LEVEL_4K; + + return host_pfn_mapping_level(kvm, gfn, pfn, slot); +} + int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, int max_level, kvm_pfn_t *pfnp, bool huge_page_disallowed, int *req_level) { struct kvm_memory_slot *slot; - struct kvm_lpage_info *linfo; kvm_pfn_t pfn = *pfnp; kvm_pfn_t mask; int level; @@ -2805,17 +2810,7 @@ int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, if (!slot) return PG_LEVEL_4K; - max_level = min(max_level, max_huge_page_level); - for ( ; max_level > PG_LEVEL_4K; max_level--) { - linfo = lpage_info_slot(gfn, slot, max_level); - if (!linfo->disallow_lpage) - break; - } - - if (max_level == PG_LEVEL_4K) - return PG_LEVEL_4K; - - level = host_pfn_mapping_level(vcpu, gfn, pfn, slot); + level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, gfn, pfn, max_level); if (level == PG_LEVEL_4K) return level; @@ -3437,7 +3432,6 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); write_unlock(&vcpu->kvm->mmu_lock); } -EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots); static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) @@ -3653,8 +3647,8 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, - bool *writable) + gpa_t cr2_or_gpa, kvm_pfn_t *pfn, hva_t *hva, + bool write, bool *writable) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); bool async; @@ -3667,7 +3661,8 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, } async = false; - *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable); + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, + write, writable, hva); if (!async) return false; /* *pfn has correct page already */ @@ -3681,7 +3676,8 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return true; } - *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable); + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, + write, writable, hva); return false; } @@ -3694,6 +3690,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, gfn_t gfn = gpa >> PAGE_SHIFT; unsigned long mmu_seq; kvm_pfn_t pfn; + hva_t hva; int r; if (page_fault_handle_page_track(vcpu, error_code, gfn)) @@ -3712,7 +3709,8 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) + if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, &hva, + write, &map_writable)) return RET_PF_RETRY; if (handle_abnormal_pfn(vcpu, is_tdp ? 0 : gpa, gfn, pfn, ACC_ALL, &r)) @@ -3725,7 +3723,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, else write_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) + if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva)) goto out_unlock; r = make_mmu_pages_available(vcpu); if (r) @@ -5003,22 +5001,6 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, write_unlock(&vcpu->kvm->mmu_lock); } -int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) -{ - gpa_t gpa; - int r; - - if (vcpu->arch.mmu->direct_map) - return 0; - - gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); - - r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); - - return r; -} -EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); - int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { @@ -5117,7 +5099,6 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, mmu->invlpg(vcpu, gva, root_hpa); } } -EXPORT_SYMBOL_GPL(kvm_mmu_invalidate_gva); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { @@ -5157,7 +5138,6 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) * for them. */ } -EXPORT_SYMBOL_GPL(kvm_mmu_invpcid_gva); void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level, int tdp_huge_page_level) @@ -5182,7 +5162,8 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level, EXPORT_SYMBOL_GPL(kvm_configure_mmu); /* The return value indicates if tlb flush on all vcpus is needed. */ -typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); +typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot); /* The caller should hold mmu-lock before calling this function. */ static __always_inline bool @@ -5196,7 +5177,7 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn, end_gfn, &iterator) { if (iterator.rmap) - flush |= fn(kvm, iterator.rmap); + flush |= fn(kvm, iterator.rmap, memslot); if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { if (flush && lock_flush_tlb) { @@ -5229,22 +5210,6 @@ slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, lock_flush_tlb); } -static __always_inline bool -slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, bool lock_flush_tlb) -{ - return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K, - KVM_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); -} - -static __always_inline bool -slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, bool lock_flush_tlb) -{ - return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K + 1, - KVM_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); -} - static __always_inline bool slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) @@ -5485,7 +5450,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) } static bool slot_rmap_write_protect(struct kvm *kvm, - struct kvm_rmap_head *rmap_head) + struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot) { return __rmap_write_protect(kvm, rmap_head, false); } @@ -5519,7 +5485,8 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, } static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, - struct kvm_rmap_head *rmap_head) + struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot) { u64 *sptep; struct rmap_iterator iter; @@ -5540,8 +5507,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, * mapping if the indirect sp has level = 1. */ if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && - (kvm_is_zone_device_pfn(pfn) || - PageCompound(pfn_to_page(pfn)))) { + sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn, + pfn, PG_LEVEL_NUM)) { pte_list_remove(rmap_head, sptep); if (kvm_available_flush_tlb_with_range()) @@ -5561,12 +5528,13 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *memslot) { /* FIXME: const-ify all uses of struct kvm_memory_slot. */ + struct kvm_memory_slot *slot = (struct kvm_memory_slot *)memslot; + write_lock(&kvm->mmu_lock); - slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot, - kvm_mmu_zap_collapsible_spte, true); + slot_handle_leaf(kvm, slot, kvm_mmu_zap_collapsible_spte, true); if (is_tdp_mmu_enabled(kvm)) - kvm_tdp_mmu_zap_collapsible_sptes(kvm, memslot); + kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot); write_unlock(&kvm->mmu_lock); } @@ -5605,40 +5573,6 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, if (flush) kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } -EXPORT_SYMBOL_GPL(kvm_mmu_slot_leaf_clear_dirty); - -void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, - struct kvm_memory_slot *memslot) -{ - bool flush; - - write_lock(&kvm->mmu_lock); - flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect, - false); - if (is_tdp_mmu_enabled(kvm)) - flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_2M); - write_unlock(&kvm->mmu_lock); - - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); -} -EXPORT_SYMBOL_GPL(kvm_mmu_slot_largepage_remove_write_access); - -void kvm_mmu_slot_set_dirty(struct kvm *kvm, - struct kvm_memory_slot *memslot) -{ - bool flush; - - write_lock(&kvm->mmu_lock); - flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false); - if (is_tdp_mmu_enabled(kvm)) - flush |= kvm_tdp_mmu_slot_set_dirty(kvm, memslot); - write_unlock(&kvm->mmu_lock); - - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); -} -EXPORT_SYMBOL_GPL(kvm_mmu_slot_set_dirty); void kvm_mmu_zap_all(struct kvm *kvm) { diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 9e38d3c5daad..72b0928f2b2d 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -84,7 +84,10 @@ static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) * When using the EPT page-modification log, the GPAs in the log * would come from L2 rather than L1. Therefore, we need to rely * on write protection to record dirty pages. This also bypasses - * PML, since writes now result in a vmexit. + * PML, since writes now result in a vmexit. Note, this helper will + * tag SPTEs as needing write-protection even if PML is disabled or + * unsupported, but that's ok because the tag is consumed if and only + * if PML is enabled. Omit the PML check to save a few uops. */ return vcpu->arch.mmu == &vcpu->arch.guest_mmu; } @@ -138,6 +141,8 @@ enum { #define SET_SPTE_NEED_REMOTE_TLB_FLUSH BIT(1) #define SET_SPTE_SPURIOUS BIT(2) +int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, kvm_pfn_t pfn, int max_level); int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, int max_level, kvm_pfn_t *pfnp, bool huge_page_disallowed, int *req_level); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index d9f66cc459e8..55d7b473ac44 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -601,6 +601,13 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, if (sp->role.level > PG_LEVEL_4K) return; + /* + * If addresses are being invalidated, skip prefetching to avoid + * accidentally prefetching those addresses. + */ + if (unlikely(vcpu->kvm->mmu_notifier_count)) + return; + if (sp->role.direct) return __direct_pte_prefetch(vcpu, sp, sptep); @@ -790,6 +797,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, struct guest_walker walker; int r; kvm_pfn_t pfn; + hva_t hva; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; int max_level; @@ -840,8 +848,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, write_fault, - &map_writable)) + if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, &hva, + write_fault, &map_writable)) return RET_PF_RETRY; if (handle_abnormal_pfn(vcpu, addr, walker.gfn, pfn, walker.pte_access, &r)) @@ -869,7 +877,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) + if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva)) goto out_unlock; kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 71e100a5670f..c926c6b899a1 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1268,68 +1268,16 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, } } -/* - * Set the dirty status of all the SPTEs mapping GFNs in the memslot. This is - * only used for PML, and so will involve setting the dirty bit on each SPTE. - * Returns true if an SPTE has been changed and the TLBs need to be flushed. - */ -static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t start, gfn_t end) -{ - struct tdp_iter iter; - u64 new_spte; - bool spte_set = false; - - rcu_read_lock(); - - tdp_root_for_each_pte(iter, root, start, end) { - if (tdp_mmu_iter_cond_resched(kvm, &iter, false)) - continue; - - if (!is_shadow_present_pte(iter.old_spte) || - iter.old_spte & shadow_dirty_mask) - continue; - - new_spte = iter.old_spte | shadow_dirty_mask; - - tdp_mmu_set_spte(kvm, &iter, new_spte); - spte_set = true; - } - - rcu_read_unlock(); - return spte_set; -} - -/* - * Set the dirty status of all the SPTEs mapping GFNs in the memslot. This is - * only used for PML, and so will involve setting the dirty bit on each SPTE. - * Returns true if an SPTE has been changed and the TLBs need to be flushed. - */ -bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot) -{ - struct kvm_mmu_page *root; - int root_as_id; - bool spte_set = false; - - for_each_tdp_mmu_root_yield_safe(kvm, root) { - root_as_id = kvm_mmu_page_as_id(root); - if (root_as_id != slot->as_id) - continue; - - spte_set |= set_dirty_gfn_range(kvm, root, slot->base_gfn, - slot->base_gfn + slot->npages); - } - return spte_set; -} - /* * Clear leaf entries which could be replaced by large mappings, for * GFNs within the slot. */ static void zap_collapsible_spte_range(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t start, gfn_t end) + struct kvm_memory_slot *slot) { + gfn_t start = slot->base_gfn; + gfn_t end = start + slot->npages; struct tdp_iter iter; kvm_pfn_t pfn; bool spte_set = false; @@ -1348,7 +1296,8 @@ static void zap_collapsible_spte_range(struct kvm *kvm, pfn = spte_to_pfn(iter.old_spte); if (kvm_is_reserved_pfn(pfn) || - !PageTransCompoundMap(pfn_to_page(pfn))) + iter.level >= kvm_mmu_max_mapping_level(kvm, slot, iter.gfn, + pfn, PG_LEVEL_NUM)) continue; tdp_mmu_set_spte(kvm, &iter, 0); @@ -1366,7 +1315,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm, * be replaced by large mappings, for GFNs within the slot. */ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *slot) + struct kvm_memory_slot *slot) { struct kvm_mmu_page *root; int root_as_id; @@ -1376,8 +1325,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, if (root_as_id != slot->as_id) continue; - zap_collapsible_spte_range(kvm, root, slot->base_gfn, - slot->base_gfn + slot->npages); + zap_collapsible_spte_range(kvm, root, slot); } } diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index b4b65e3699b3..3b761c111bff 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -33,9 +33,8 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, unsigned long mask, bool wrprot); -bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *slot); + struct kvm_memory_slot *slot); bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index cc91738ab445..35891d9a1099 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -51,6 +51,23 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, nested_svm_vmexit(svm); } +static void svm_inject_page_fault_nested(struct kvm_vcpu *vcpu, struct x86_exception *fault) +{ + struct vcpu_svm *svm = to_svm(vcpu); + WARN_ON(!is_guest_mode(vcpu)); + + if (vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && + !svm->nested.nested_run_pending) { + svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = fault->error_code; + svm->vmcb->control.exit_info_2 = fault->address; + nested_svm_vmexit(svm); + } else { + kvm_inject_page_fault(vcpu, fault); + } +} + static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) { struct vcpu_svm *svm = to_svm(vcpu); @@ -436,16 +453,33 @@ int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb12_gpa, { int ret; + trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb12_gpa, + vmcb12->save.rip, + vmcb12->control.int_ctl, + vmcb12->control.event_inj, + vmcb12->control.nested_ctl); + + trace_kvm_nested_intercepts(vmcb12->control.intercepts[INTERCEPT_CR] & 0xffff, + vmcb12->control.intercepts[INTERCEPT_CR] >> 16, + vmcb12->control.intercepts[INTERCEPT_EXCEPTION], + vmcb12->control.intercepts[INTERCEPT_WORD3], + vmcb12->control.intercepts[INTERCEPT_WORD4], + vmcb12->control.intercepts[INTERCEPT_WORD5]); + + svm->nested.vmcb12_gpa = vmcb12_gpa; load_nested_vmcb_control(svm, &vmcb12->control); - nested_prepare_vmcb_save(svm, vmcb12); nested_prepare_vmcb_control(svm); + nested_prepare_vmcb_save(svm, vmcb12); ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3, nested_npt_enabled(svm)); if (ret) return ret; + if (!npt_enabled) + svm->vcpu.arch.mmu->inject_page_fault = svm_inject_page_fault_nested; + svm_set_gif(svm, true); return 0; @@ -489,18 +523,6 @@ int nested_svm_vmrun(struct vcpu_svm *svm) goto out; } - trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb12_gpa, - vmcb12->save.rip, - vmcb12->control.int_ctl, - vmcb12->control.event_inj, - vmcb12->control.nested_ctl); - - trace_kvm_nested_intercepts(vmcb12->control.intercepts[INTERCEPT_CR] & 0xffff, - vmcb12->control.intercepts[INTERCEPT_CR] >> 16, - vmcb12->control.intercepts[INTERCEPT_EXCEPTION], - vmcb12->control.intercepts[INTERCEPT_WORD3], - vmcb12->control.intercepts[INTERCEPT_WORD4], - vmcb12->control.intercepts[INTERCEPT_WORD5]); /* Clear internal status */ kvm_clear_exception_queue(&svm->vcpu); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index adb3619a3c16..c636021b066b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -926,9 +926,6 @@ static __init void svm_set_cpu_caps(void) if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) || boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); - - /* Enable INVPCID feature */ - kvm_cpu_cap_check_and_set(X86_FEATURE_INVPCID); } static __init int svm_hardware_setup(void) @@ -1103,12 +1100,12 @@ static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) static void svm_check_invpcid(struct vcpu_svm *svm) { /* - * Intercept INVPCID instruction only if shadow page table is - * enabled. Interception is not required with nested page table - * enabled. + * Intercept INVPCID if shadow paging is enabled to sync/free shadow + * roots, or if INVPCID is disabled in the guest to inject #UD. */ if (kvm_cpu_cap_has(X86_FEATURE_INVPCID)) { - if (!npt_enabled) + if (!npt_enabled || + !guest_cpuid_has(&svm->vcpu, X86_FEATURE_INVPCID)) svm_set_intercept(svm, INTERCEPT_INVPCID); else svm_clr_intercept(svm, INTERCEPT_INVPCID); @@ -2214,15 +2211,20 @@ static int emulate_svm_instr(struct kvm_vcpu *vcpu, int opcode) [SVM_INSTR_VMSAVE] = vmsave_interception, }; struct vcpu_svm *svm = to_svm(vcpu); + int ret; if (is_guest_mode(vcpu)) { svm->vmcb->control.exit_code = guest_mode_exit_codes[opcode]; svm->vmcb->control.exit_info_1 = 0; svm->vmcb->control.exit_info_2 = 0; - return nested_svm_vmexit(svm); - } else - return svm_instr_handlers[opcode](svm); + /* Returns '1' or -errno on failure, '0' on success. */ + ret = nested_svm_vmexit(svm); + if (ret) + return ret; + return 1; + } + return svm_instr_handlers[opcode](svm); } /* diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index b2f0b5e9cd63..bcca0b80e0d0 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2167,15 +2167,13 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); /* - * The PML address never changes, so it is constant in vmcs02. - * Conceptually we want to copy the PML index from vmcs01 here, - * and then back to vmcs01 on nested vmexit. But since we flush - * the log and reset GUEST_PML_INDEX on each vmexit, the PML - * index is also effectively constant in vmcs02. + * PML is emulated for L2, but never enabled in hardware as the MMU + * handles A/D emulation. Disabling PML for L2 also avoids having to + * deal with filtering out L2 GPAs from the buffer. */ if (enable_pml) { - vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + vmcs_write64(PML_ADDRESS, 0); + vmcs_write16(GUEST_PML_INDEX, -1); } if (cpu_has_vmx_encls_vmexit()) @@ -2210,7 +2208,7 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx, static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) { - u32 exec_control, vmcs12_exec_ctrl; + u32 exec_control; u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs) @@ -2284,11 +2282,11 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_ENABLE_VMFUNC); if (nested_cpu_has(vmcs12, - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) { - vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control & - ~SECONDARY_EXEC_ENABLE_PML; - exec_control |= vmcs12_exec_ctrl; - } + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) + exec_control |= vmcs12->secondary_vm_exec_control; + + /* PML is emulated and never enabled in hardware for L2. */ + exec_control &= ~SECONDARY_EXEC_ENABLE_PML; /* VMCS shadowing for L2 is emulated for now */ exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; @@ -4200,9 +4198,6 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &ignored)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL); - if (!enable_ept) - vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; - nested_vmx_transition_tlb_flush(vcpu, vmcs12, false); vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs); @@ -4495,6 +4490,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vmx_set_virtual_apic_mode(vcpu); } + if (vmx->nested.update_vmcs01_cpu_dirty_logging) { + vmx->nested.update_vmcs01_cpu_dirty_logging = false; + vmx_update_cpu_dirty_logging(vcpu); + } + /* Unpin physical memory we referred to in vmcs02 */ if (vmx->nested.apic_access_page) { kvm_release_page_clean(vmx->nested.apic_access_page); @@ -5793,7 +5793,10 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, case EXIT_REASON_PREEMPTION_TIMER: return true; case EXIT_REASON_PML_FULL: - /* We emulate PML support to L1. */ + /* + * PML is emulated for an L1 VMM and should never be enabled in + * vmcs02, always "handle" PML_FULL by exiting to userspace. + */ return true; case EXIT_REASON_VMFUNC: /* VM functions are emulated through L2->L0 vmexits. */ diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index d1df618cb7de..9efc1a6b8693 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -298,7 +298,7 @@ int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu) if (IS_ERR(event)) { pr_debug_ratelimited("%s: failed %ld\n", __func__, PTR_ERR(event)); - return -ENOENT; + return PTR_ERR(event); } lbr_desc->event = event; pmu->event_count++; @@ -320,7 +320,7 @@ static bool intel_pmu_handle_lbr_msrs_access(struct kvm_vcpu *vcpu, if (!intel_pmu_is_valid_lbr_msr(vcpu, index)) return false; - if (!lbr_desc->event && !intel_pmu_create_guest_lbr_event(vcpu)) + if (!lbr_desc->event && intel_pmu_create_guest_lbr_event(vcpu) < 0) goto dummy; /* diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e0a3a9be654b..50810d471462 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4277,7 +4277,12 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) */ exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; - if (!enable_pml) + /* + * PML is enabled/disabled when dirty logging of memsmlots changes, but + * it needs to be set here when dirty logging is already active, e.g. + * if this vCPU was created after dirty logging was enabled. + */ + if (!vcpu->kvm->arch.cpu_dirty_logging_count) exec_control &= ~SECONDARY_EXEC_ENABLE_PML; if (cpu_has_vmx_xsaves()) { @@ -4295,18 +4300,8 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) } vmx_adjust_sec_exec_feature(vmx, &exec_control, rdtscp, RDTSCP); - - /* - * Expose INVPCID if and only if PCID is also exposed to the guest. - * INVPCID takes a #UD when it's disabled in the VMCS, but a #GP or #PF - * if CR4.PCIDE=0. Enumerating CPUID.INVPCID=1 would lead to incorrect - * behavior from the guest perspective (it would expect #GP or #PF). - */ - if (!guest_cpuid_has(vcpu, X86_FEATURE_PCID)) - guest_cpuid_clear(vcpu, X86_FEATURE_INVPCID); vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID); - vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND); vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdseed, RDSEED); @@ -5776,24 +5771,6 @@ static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); } -/* - * Flush all vcpus' PML buffer and update logged GPAs to dirty_bitmap. - * Called before reporting dirty_bitmap to userspace. - */ -static void kvm_flush_pml_buffers(struct kvm *kvm) -{ - int i; - struct kvm_vcpu *vcpu; - /* - * We only need to kick vcpu out of guest mode here, as PML buffer - * is flushed at beginning of all VMEXITs, and it's obvious that only - * vcpus running in guest are possible to have unflushed GPAs in PML - * buffer. - */ - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_kick(vcpu); -} - static void vmx_dump_sel(char *name, uint32_t sel) { pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", @@ -5976,9 +5953,10 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before * querying dirty_bitmap, we only need to kick all vcpus out of guest * mode as if vcpus is in root mode, the PML buffer must has been - * flushed already. + * flushed already. Note, PML is never enabled in hardware while + * running L2. */ - if (enable_pml) + if (enable_pml && !is_guest_mode(vcpu)) vmx_flush_pml_buffer(vcpu); /* @@ -5994,6 +5972,13 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return handle_invalid_guest_state(vcpu); if (is_guest_mode(vcpu)) { + /* + * PML is never enabled when running L2, bail immediately if a + * PML full exit occurs as something is horribly wrong. + */ + if (exit_reason.basic == EXIT_REASON_PML_FULL) + goto unexpected_vmexit; + /* * The host physical addresses of some pages of guest memory * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC @@ -6851,13 +6836,15 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY)) kvm_machine_check(); + if (likely(!vmx->exit_reason.failed_vmentry)) + vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); + trace_kvm_exit(vmx->exit_reason.full, vcpu, KVM_ISA_VMX); if (unlikely(vmx->exit_reason.failed_vmentry)) return EXIT_FASTPATH_NONE; vmx->loaded_vmcs->launched = 1; - vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); @@ -7330,8 +7317,8 @@ static __init void vmx_set_cpu_caps(void) /* CPUID 0x7 */ if (kvm_mpx_supported()) kvm_cpu_cap_check_and_set(X86_FEATURE_MPX); - if (cpu_has_vmx_invpcid()) - kvm_cpu_cap_check_and_set(X86_FEATURE_INVPCID); + if (!cpu_has_vmx_invpcid()) + kvm_cpu_cap_clear(X86_FEATURE_INVPCID); if (vmx_pt_mode_is_host_guest()) kvm_cpu_cap_check_and_set(X86_FEATURE_INTEL_PT); @@ -7509,30 +7496,24 @@ static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) shrink_ple_window(vcpu); } -static void vmx_slot_enable_log_dirty(struct kvm *kvm, - struct kvm_memory_slot *slot) +void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) { - if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) - kvm_mmu_slot_leaf_clear_dirty(kvm, slot); - kvm_mmu_slot_largepage_remove_write_access(kvm, slot); -} + struct vcpu_vmx *vmx = to_vmx(vcpu); -static void vmx_slot_disable_log_dirty(struct kvm *kvm, - struct kvm_memory_slot *slot) -{ - kvm_mmu_slot_set_dirty(kvm, slot); -} + if (is_guest_mode(vcpu)) { + vmx->nested.update_vmcs01_cpu_dirty_logging = true; + return; + } -static void vmx_flush_log_dirty(struct kvm *kvm) -{ - kvm_flush_pml_buffers(kvm); -} - -static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, - struct kvm_memory_slot *memslot, - gfn_t offset, unsigned long mask) -{ - kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); + /* + * Note, cpu_dirty_logging_count can be changed concurrent with this + * code, but in that case another update request will be made and so + * the guest will never run with a stale PML value. + */ + if (vcpu->kvm->arch.cpu_dirty_logging_count) + secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_ENABLE_PML); + else + secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML); } static int vmx_pre_block(struct kvm_vcpu *vcpu) @@ -7642,11 +7623,6 @@ static bool vmx_check_apicv_inhibit_reasons(ulong bit) return supported & BIT(bit); } -static int vmx_cpu_dirty_log_size(void) -{ - return enable_pml ? PML_ENTITY_NUM : 0; -} - static struct kvm_x86_ops vmx_x86_ops __initdata = { .hardware_unsetup = hardware_unsetup, @@ -7746,10 +7722,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .sched_in = vmx_sched_in, - .slot_enable_log_dirty = vmx_slot_enable_log_dirty, - .slot_disable_log_dirty = vmx_slot_disable_log_dirty, - .flush_log_dirty = vmx_flush_log_dirty, - .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, + .cpu_dirty_log_size = PML_ENTITY_NUM, + .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging, .pre_block = vmx_pre_block, .post_block = vmx_post_block, @@ -7777,7 +7751,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .msr_filter_changed = vmx_msr_filter_changed, .complete_emulated_msr = kvm_complete_insn_gp, - .cpu_dirty_log_size = vmx_cpu_dirty_log_size, .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, }; @@ -7894,13 +7867,8 @@ static __init int hardware_setup(void) if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml()) enable_pml = 0; - if (!enable_pml) { - vmx_x86_ops.slot_enable_log_dirty = NULL; - vmx_x86_ops.slot_disable_log_dirty = NULL; - vmx_x86_ops.flush_log_dirty = NULL; - vmx_x86_ops.enable_log_dirty_pt_masked = NULL; - vmx_x86_ops.cpu_dirty_log_size = NULL; - } + if (!enable_pml) + vmx_x86_ops.cpu_dirty_log_size = 0; if (!cpu_has_vmx_preemption_timer()) enable_preemption_timer = false; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 12c53d05a902..89da5e1251f1 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -165,6 +165,7 @@ struct nested_vmx { bool change_vmcs01_virtual_apic_mode; bool reload_vmcs01_apic_access_page; + bool update_vmcs01_cpu_dirty_logging; /* * Enlightened VMCS has been enabled. It does not mean that L1 has to @@ -393,6 +394,7 @@ int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr); void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu); void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool value); +void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); static inline u8 vmx_get_rvi(void) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 884e5b3838c7..3712bb5245eb 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5215,10 +5215,18 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { + /* - * Flush potentially hardware-cached dirty pages to dirty_bitmap. + * Flush all CPUs' dirty log buffers to the dirty_bitmap. Called + * before reporting dirty_bitmap to userspace. KVM flushes the buffers + * on all VM-Exits, thus we only need to kick running vCPUs to force a + * VM-Exit. */ - static_call_cond(kvm_x86_flush_log_dirty)(kvm); + struct kvm_vcpu *vcpu; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_vcpu_kick(vcpu); } int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, @@ -8980,6 +8988,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_check_async_pf_completion(vcpu); if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu)) static_call(kvm_x86_msr_filter_changed)(vcpu); + + if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu)) + static_call(kvm_x86_update_cpu_dirty_logging)(vcpu); } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win || @@ -10748,75 +10759,96 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, return 0; } + +static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable) +{ + struct kvm_arch *ka = &kvm->arch; + + if (!kvm_x86_ops.cpu_dirty_log_size) + return; + + if ((enable && ++ka->cpu_dirty_logging_count == 1) || + (!enable && --ka->cpu_dirty_logging_count == 0)) + kvm_make_all_cpus_request(kvm, KVM_REQ_UPDATE_CPU_DIRTY_LOGGING); + + WARN_ON_ONCE(ka->cpu_dirty_logging_count < 0); +} + static void kvm_mmu_slot_apply_flags(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { + bool log_dirty_pages = new->flags & KVM_MEM_LOG_DIRTY_PAGES; + /* - * Nothing to do for RO slots or CREATE/MOVE/DELETE of a slot. - * See comments below. + * Update CPU dirty logging if dirty logging is being toggled. This + * applies to all operations. + */ + if ((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES) + kvm_mmu_update_cpu_dirty_logging(kvm, log_dirty_pages); + + /* + * Nothing more to do for RO slots (which can't be dirtied and can't be + * made writable) or CREATE/MOVE/DELETE of a slot. + * + * For a memslot with dirty logging disabled: + * CREATE: No dirty mappings will already exist. + * MOVE/DELETE: The old mappings will already have been cleaned up by + * kvm_arch_flush_shadow_memslot() + * + * For a memslot with dirty logging enabled: + * CREATE: No shadow pages exist, thus nothing to write-protect + * and no dirty bits to clear. + * MOVE/DELETE: The old mappings will already have been cleaned up by + * kvm_arch_flush_shadow_memslot(). */ if ((change != KVM_MR_FLAGS_ONLY) || (new->flags & KVM_MEM_READONLY)) return; /* - * Dirty logging tracks sptes in 4k granularity, meaning that large - * sptes have to be split. If live migration is successful, the guest - * in the source machine will be destroyed and large sptes will be - * created in the destination. However, if the guest continues to run - * in the source machine (for example if live migration fails), small - * sptes will remain around and cause bad performance. - * - * Scan sptes if dirty logging has been stopped, dropping those - * which can be collapsed into a single large-page spte. Later - * page faults will create the large-page sptes. - * - * There is no need to do this in any of the following cases: - * CREATE: No dirty mappings will already exist. - * MOVE/DELETE: The old mappings will already have been cleaned up by - * kvm_arch_flush_shadow_memslot() + * READONLY and non-flags changes were filtered out above, and the only + * other flag is LOG_DIRTY_PAGES, i.e. something is wrong if dirty + * logging isn't being toggled on or off. */ - if ((old->flags & KVM_MEM_LOG_DIRTY_PAGES) && - !(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) + if (WARN_ON_ONCE(!((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES))) + return; + + if (!log_dirty_pages) { + /* + * Dirty logging tracks sptes in 4k granularity, meaning that + * large sptes have to be split. If live migration succeeds, + * the guest in the source machine will be destroyed and large + * sptes will be created in the destination. However, if the + * guest continues to run in the source machine (for example if + * live migration fails), small sptes will remain around and + * cause bad performance. + * + * Scan sptes if dirty logging has been stopped, dropping those + * which can be collapsed into a single large-page spte. Later + * page faults will create the large-page sptes. + */ kvm_mmu_zap_collapsible_sptes(kvm, new); + } else { + /* By default, write-protect everything to log writes. */ + int level = PG_LEVEL_4K; - /* - * Enable or disable dirty logging for the slot. - * - * For KVM_MR_DELETE and KVM_MR_MOVE, the shadow pages of the old - * slot have been zapped so no dirty logging updates are needed for - * the old slot. - * For KVM_MR_CREATE and KVM_MR_MOVE, once the new slot is visible - * any mappings that might be created in it will consume the - * properties of the new slot and do not need to be updated here. - * - * When PML is enabled, the kvm_x86_ops dirty logging hooks are - * called to enable/disable dirty logging. - * - * When disabling dirty logging with PML enabled, the D-bit is set - * for sptes in the slot in order to prevent unnecessary GPA - * logging in the PML buffer (and potential PML buffer full VMEXIT). - * This guarantees leaving PML enabled for the guest's lifetime - * won't have any additional overhead from PML when the guest is - * running with dirty logging disabled. - * - * When enabling dirty logging, large sptes are write-protected - * so they can be split on first write. New large sptes cannot - * be created for this slot until the end of the logging. - * See the comments in fast_page_fault(). - * For small sptes, nothing is done if the dirty log is in the - * initial-all-set state. Otherwise, depending on whether pml - * is enabled the D-bit or the W-bit will be cleared. - */ - if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { - if (kvm_x86_ops.slot_enable_log_dirty) { - static_call(kvm_x86_slot_enable_log_dirty)(kvm, new); - } else { - int level = - kvm_dirty_log_manual_protect_and_init_set(kvm) ? - PG_LEVEL_2M : PG_LEVEL_4K; + if (kvm_x86_ops.cpu_dirty_log_size) { + /* + * Clear all dirty bits, unless pages are treated as + * dirty from the get-go. + */ + if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) + kvm_mmu_slot_leaf_clear_dirty(kvm, new); + /* + * Write-protect large pages on write so that dirty + * logging happens at 4k granularity. No need to + * write-protect small SPTEs since write accesses are + * logged by the CPU via dirty bits. + */ + level = PG_LEVEL_2M; + } else if (kvm_dirty_log_manual_protect_and_init_set(kvm)) { /* * If we're with initial-all-set, we don't need * to write protect any small page because @@ -10825,10 +10857,9 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * so that the page split can happen lazily on * the first write to the huge page. */ - kvm_mmu_slot_remove_write_access(kvm, new, level); + level = PG_LEVEL_2M; } - } else { - static_call_cond(kvm_x86_slot_disable_log_dirty)(kvm, new); + kvm_mmu_slot_remove_write_access(kvm, new, level); } } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 525197381baa..a73347e2cdfc 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -9,6 +9,7 @@ #include /* oops_begin/end, ... */ #include /* search_exception_tables */ #include /* max_low_pfn */ +#include /* kfence_handle_page_fault */ #include /* NOKPROBE_SYMBOL, ... */ #include /* kmmio_handler, ... */ #include /* perf_sw_event */ @@ -680,6 +681,11 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code, if (IS_ENABLED(CONFIG_EFI)) efi_crash_gracefully_on_page_fault(address); + /* Only not-present faults should be handled by KFENCE. */ + if (!(error_code & X86_PF_PROT) && + kfence_handle_page_fault(address, error_code & X86_PF_WRITE, regs)) + return; + oops: /* * Oops. The kernel tried to access some bad page. We'll have to diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 8f665c352bf0..ca311aaa67b8 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -1164,12 +1164,14 @@ static void *memtype_seq_start(struct seq_file *seq, loff_t *pos) static void *memtype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { + kfree(v); ++*pos; return memtype_get_idx(*pos); } static void memtype_seq_stop(struct seq_file *seq, void *v) { + kfree(v); } static int memtype_seq_show(struct seq_file *seq, void *v) @@ -1181,8 +1183,6 @@ static int memtype_seq_show(struct seq_file *seq, void *v) entry_print->end, cattr_name(entry_print->type)); - kfree(entry_print); - return 0; } diff --git a/arch/xtensa/kernel/syscalls/Makefile b/arch/xtensa/kernel/syscalls/Makefile index 659faefdcb1d..285aaba832d9 100644 --- a/arch/xtensa/kernel/syscalls/Makefile +++ b/arch/xtensa/kernel/syscalls/Makefile @@ -5,7 +5,7 @@ uapi := arch/$(SRCARCH)/include/generated/uapi/asm _dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') -syscall := $(srctree)/$(src)/syscall.tbl +syscall := $(src)/syscall.tbl syshdr := $(srctree)/$(src)/syscallhdr.sh systbl := $(srctree)/$(src)/syscalltbl.sh @@ -21,18 +21,19 @@ quiet_cmd_systbl = SYSTBL $@ '$(systbl_abi_$(basetarget))' \ '$(systbl_offset_$(basetarget))' -$(uapi)/unistd_32.h: $(syscall) $(syshdr) +$(uapi)/unistd_32.h: $(syscall) $(syshdr) FORCE $(call if_changed,syshdr) -$(kapi)/syscall_table.h: $(syscall) $(systbl) +$(kapi)/syscall_table.h: $(syscall) $(systbl) FORCE $(call if_changed,systbl) uapisyshdr-y += unistd_32.h kapisyshdr-y += syscall_table.h -targets += $(uapisyshdr-y) $(kapisyshdr-y) +uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) +kapisyshdr-y := $(addprefix $(kapi)/, $(kapisyshdr-y)) +targets += $(addprefix ../../../../, $(uapisyshdr-y) $(kapisyshdr-y)) PHONY += all -all: $(addprefix $(uapi)/,$(uapisyshdr-y)) -all: $(addprefix $(kapi)/,$(kapisyshdr-y)) +all: $(uapisyshdr-y) $(kapisyshdr-y) @: diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index fc06945d3f99..eedec61e3476 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -87,6 +87,14 @@ config ACPI_SPCR_TABLE This table provides information about the configuration of the earlycon console. +config ACPI_FPDT + bool "ACPI Firmware Performance Data Table (FPDT) support" + depends on X86_64 + help + Enable support for the Firmware Performance Data Table (FPDT). + This table provides information on the timing of the system + boot, S3 suspend and S3 resume firmware code paths. + config ACPI_LPIT bool depends on X86_64 @@ -327,21 +335,7 @@ config ACPI_THERMAL the module will be called thermal. config ACPI_PLATFORM_PROFILE - tristate "ACPI Platform Profile Driver" - default m - help - This driver adds support for platform-profiles on platforms that - support it. - - Platform-profiles can be used to control the platform behaviour. For - example whether to operate in a lower power mode, in a higher - power performance mode or between the two. - - This driver provides the sysfs interface and is used as the registration - point for platform specific drivers. - - Which profiles are supported is determined on a per-platform basis and - should be obtained from the platform specific driver. + tristate config ACPI_CUSTOM_DSDT_FILE string "Custom DSDT Table file to include" diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 52b627c7f977..700b41adf2db 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -57,6 +57,7 @@ acpi-$(CONFIG_X86) += x86/utils.o acpi-$(CONFIG_X86) += x86/s2idle.o acpi-$(CONFIG_DEBUG_FS) += debugfs.o acpi-y += acpi_lpat.o +acpi-$(CONFIG_ACPI_FPDT) += acpi_fpdt.o acpi-$(CONFIG_ACPI_LPIT) += acpi_lpit.o acpi-$(CONFIG_ACPI_GENERIC_GSI) += irq.o acpi-$(CONFIG_ACPI_WATCHDOG) += acpi_watchdog.o diff --git a/drivers/acpi/acpi_fpdt.c b/drivers/acpi/acpi_fpdt.c new file mode 100644 index 000000000000..a89a806a7a2a --- /dev/null +++ b/drivers/acpi/acpi_fpdt.c @@ -0,0 +1,264 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * FPDT support for exporting boot and suspend/resume performance data + * + * Copyright (C) 2021 Intel Corporation. All rights reserved. + */ + +#define pr_fmt(fmt) "ACPI FPDT: " fmt + +#include + +/* + * FPDT contains ACPI table header and a number of fpdt_subtable_entries. + * Each fpdt_subtable_entry points to a subtable: FBPT or S3PT. + * Each FPDT subtable (FBPT/S3PT) is composed of a fpdt_subtable_header + * and a number of fpdt performance records. + * Each FPDT performance record is composed of a fpdt_record_header and + * performance data fields, for boot or suspend or resume phase. + */ +enum fpdt_subtable_type { + SUBTABLE_FBPT, + SUBTABLE_S3PT, +}; + +struct fpdt_subtable_entry { + u16 type; /* refer to enum fpdt_subtable_type */ + u8 length; + u8 revision; + u32 reserved; + u64 address; /* physical address of the S3PT/FBPT table */ +}; + +struct fpdt_subtable_header { + u32 signature; + u32 length; +}; + +enum fpdt_record_type { + RECORD_S3_RESUME, + RECORD_S3_SUSPEND, + RECORD_BOOT, +}; + +struct fpdt_record_header { + u16 type; /* refer to enum fpdt_record_type */ + u8 length; + u8 revision; +}; + +struct resume_performance_record { + struct fpdt_record_header header; + u32 resume_count; + u64 resume_prev; + u64 resume_avg; +} __attribute__((packed)); + +struct boot_performance_record { + struct fpdt_record_header header; + u32 reserved; + u64 firmware_start; + u64 bootloader_load; + u64 bootloader_launch; + u64 exitbootservice_start; + u64 exitbootservice_end; +} __attribute__((packed)); + +struct suspend_performance_record { + struct fpdt_record_header header; + u64 suspend_start; + u64 suspend_end; +} __attribute__((packed)); + + +static struct resume_performance_record *record_resume; +static struct suspend_performance_record *record_suspend; +static struct boot_performance_record *record_boot; + +#define FPDT_ATTR(phase, name) \ +static ssize_t name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf) \ +{ \ + return sprintf(buf, "%llu\n", record_##phase->name); \ +} \ +static struct kobj_attribute name##_attr = \ +__ATTR(name##_ns, 0444, name##_show, NULL) + +FPDT_ATTR(resume, resume_prev); +FPDT_ATTR(resume, resume_avg); +FPDT_ATTR(suspend, suspend_start); +FPDT_ATTR(suspend, suspend_end); +FPDT_ATTR(boot, firmware_start); +FPDT_ATTR(boot, bootloader_load); +FPDT_ATTR(boot, bootloader_launch); +FPDT_ATTR(boot, exitbootservice_start); +FPDT_ATTR(boot, exitbootservice_end); + +static ssize_t resume_count_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", record_resume->resume_count); +} + +static struct kobj_attribute resume_count_attr = +__ATTR_RO(resume_count); + +static struct attribute *resume_attrs[] = { + &resume_count_attr.attr, + &resume_prev_attr.attr, + &resume_avg_attr.attr, + NULL +}; + +static const struct attribute_group resume_attr_group = { + .attrs = resume_attrs, + .name = "resume", +}; + +static struct attribute *suspend_attrs[] = { + &suspend_start_attr.attr, + &suspend_end_attr.attr, + NULL +}; + +static const struct attribute_group suspend_attr_group = { + .attrs = suspend_attrs, + .name = "suspend", +}; + +static struct attribute *boot_attrs[] = { + &firmware_start_attr.attr, + &bootloader_load_attr.attr, + &bootloader_launch_attr.attr, + &exitbootservice_start_attr.attr, + &exitbootservice_end_attr.attr, + NULL +}; + +static const struct attribute_group boot_attr_group = { + .attrs = boot_attrs, + .name = "boot", +}; + +static struct kobject *fpdt_kobj; + +static int fpdt_process_subtable(u64 address, u32 subtable_type) +{ + struct fpdt_subtable_header *subtable_header; + struct fpdt_record_header *record_header; + char *signature = (subtable_type == SUBTABLE_FBPT ? "FBPT" : "S3PT"); + u32 length, offset; + int result; + + subtable_header = acpi_os_map_memory(address, sizeof(*subtable_header)); + if (!subtable_header) + return -ENOMEM; + + if (strncmp((char *)&subtable_header->signature, signature, 4)) { + pr_info(FW_BUG "subtable signature and type mismatch!\n"); + return -EINVAL; + } + + length = subtable_header->length; + acpi_os_unmap_memory(subtable_header, sizeof(*subtable_header)); + + subtable_header = acpi_os_map_memory(address, length); + if (!subtable_header) + return -ENOMEM; + + offset = sizeof(*subtable_header); + while (offset < length) { + record_header = (void *)subtable_header + offset; + offset += record_header->length; + + switch (record_header->type) { + case RECORD_S3_RESUME: + if (subtable_type != SUBTABLE_S3PT) { + pr_err(FW_BUG "Invalid record %d for subtable %s\n", + record_header->type, signature); + return -EINVAL; + } + if (record_resume) { + pr_err("Duplicate resume performance record found.\n"); + continue; + } + record_resume = (struct resume_performance_record *)record_header; + result = sysfs_create_group(fpdt_kobj, &resume_attr_group); + if (result) + return result; + break; + case RECORD_S3_SUSPEND: + if (subtable_type != SUBTABLE_S3PT) { + pr_err(FW_BUG "Invalid %d for subtable %s\n", + record_header->type, signature); + continue; + } + if (record_suspend) { + pr_err("Duplicate suspend performance record found.\n"); + continue; + } + record_suspend = (struct suspend_performance_record *)record_header; + result = sysfs_create_group(fpdt_kobj, &suspend_attr_group); + if (result) + return result; + break; + case RECORD_BOOT: + if (subtable_type != SUBTABLE_FBPT) { + pr_err(FW_BUG "Invalid %d for subtable %s\n", + record_header->type, signature); + return -EINVAL; + } + if (record_boot) { + pr_err("Duplicate boot performance record found.\n"); + continue; + } + record_boot = (struct boot_performance_record *)record_header; + result = sysfs_create_group(fpdt_kobj, &boot_attr_group); + if (result) + return result; + break; + + default: + pr_err(FW_BUG "Invalid record %d found.\n", record_header->type); + return -EINVAL; + } + } + return 0; +} + +static int __init acpi_init_fpdt(void) +{ + acpi_status status; + struct acpi_table_header *header; + struct fpdt_subtable_entry *subtable; + u32 offset = sizeof(*header); + + status = acpi_get_table(ACPI_SIG_FPDT, 0, &header); + + if (ACPI_FAILURE(status)) + return 0; + + fpdt_kobj = kobject_create_and_add("fpdt", acpi_kobj); + if (!fpdt_kobj) + return -ENOMEM; + + while (offset < header->length) { + subtable = (void *)header + offset; + switch (subtable->type) { + case SUBTABLE_FBPT: + case SUBTABLE_S3PT: + fpdt_process_subtable(subtable->address, + subtable->type); + break; + default: + pr_info(FW_BUG "Invalid subtable type %d found.\n", + subtable->type); + break; + } + offset += sizeof(*subtable); + } + return 0; +} + +fs_initcall(acpi_init_fpdt); diff --git a/drivers/acpi/platform_profile.c b/drivers/acpi/platform_profile.c index 4a59c5993bde..dd2fbf38e414 100644 --- a/drivers/acpi/platform_profile.c +++ b/drivers/acpi/platform_profile.c @@ -17,6 +17,7 @@ static const char * const profile_names[] = { [PLATFORM_PROFILE_COOL] = "cool", [PLATFORM_PROFILE_QUIET] = "quiet", [PLATFORM_PROFILE_BALANCED] = "balanced", + [PLATFORM_PROFILE_BALANCED_PERFORMANCE] = "balanced-performance", [PLATFORM_PROFILE_PERFORMANCE] = "performance", }; static_assert(ARRAY_SIZE(profile_names) == PLATFORM_PROFILE_LAST); diff --git a/drivers/auxdisplay/cfag12864b.c b/drivers/auxdisplay/cfag12864b.c index 7eebae7e322c..fd430e6866a1 100644 --- a/drivers/auxdisplay/cfag12864b.c +++ b/drivers/auxdisplay/cfag12864b.c @@ -5,7 +5,7 @@ * Description: cfag12864b LCD driver * Depends: ks0108 * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-31 */ @@ -376,5 +376,5 @@ module_init(cfag12864b_init); module_exit(cfag12864b_exit); MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Miguel Ojeda Sandonis "); +MODULE_AUTHOR("Miguel Ojeda "); MODULE_DESCRIPTION("cfag12864b LCD driver"); diff --git a/drivers/auxdisplay/cfag12864bfb.c b/drivers/auxdisplay/cfag12864bfb.c index 2002291ab338..d66821adf453 100644 --- a/drivers/auxdisplay/cfag12864bfb.c +++ b/drivers/auxdisplay/cfag12864bfb.c @@ -5,7 +5,7 @@ * Description: cfag12864b LCD framebuffer driver * Depends: cfag12864b * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-31 */ @@ -171,5 +171,5 @@ module_init(cfag12864bfb_init); module_exit(cfag12864bfb_exit); MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Miguel Ojeda Sandonis "); +MODULE_AUTHOR("Miguel Ojeda "); MODULE_DESCRIPTION("cfag12864b LCD framebuffer driver"); diff --git a/drivers/auxdisplay/ks0108.c b/drivers/auxdisplay/ks0108.c index abfe3fa9e6f4..03c95ad4216c 100644 --- a/drivers/auxdisplay/ks0108.c +++ b/drivers/auxdisplay/ks0108.c @@ -5,7 +5,7 @@ * Description: ks0108 LCD Controller driver * Depends: parport * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-31 */ @@ -182,6 +182,6 @@ module_init(ks0108_init); module_exit(ks0108_exit); MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Miguel Ojeda Sandonis "); +MODULE_AUTHOR("Miguel Ojeda "); MODULE_DESCRIPTION("ks0108 LCD Controller driver"); diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 324aa03fed3c..ffcbe2bc460e 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -213,4 +213,10 @@ config GENERIC_ARCH_TOPOLOGY appropriate scaling, sysfs interface for reading capacity values at runtime. +config GENERIC_ARCH_NUMA + bool + help + Enable support for generic NUMA implementation. Currently, RISC-V + and ARM64 use it. + endmenu diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 5e7bf9669a81..8b93a7f291ec 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -24,6 +24,7 @@ obj-$(CONFIG_PINCTRL) += pinctrl.o obj-$(CONFIG_DEV_COREDUMP) += devcoredump.o obj-$(CONFIG_GENERIC_MSI_IRQ_DOMAIN) += platform-msi.o obj-$(CONFIG_GENERIC_ARCH_TOPOLOGY) += arch_topology.o +obj-$(CONFIG_GENERIC_ARCH_NUMA) += arch_numa.o obj-y += test/ diff --git a/arch/arm64/mm/numa.c b/drivers/base/arch_numa.c similarity index 93% rename from arch/arm64/mm/numa.c rename to drivers/base/arch_numa.c index a8303bc6b62a..4cc4e117727d 100644 --- a/arch/arm64/mm/numa.c +++ b/drivers/base/arch_numa.c @@ -13,7 +13,6 @@ #include #include -#include #include struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; @@ -356,11 +355,12 @@ static int __init numa_register_nodes(void) /* Check that valid nid is set to memblks */ for_each_mem_region(mblk) { int mblk_nid = memblock_get_region_node(mblk); + phys_addr_t start = mblk->base; + phys_addr_t end = mblk->base + mblk->size - 1; if (mblk_nid == NUMA_NO_NODE || mblk_nid >= MAX_NUMNODES) { - pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n", - mblk_nid, mblk->base, - mblk->base + mblk->size - 1); + pr_warn("Warning: invalid memblk node %d [mem %pap-%pap]\n", + mblk_nid, &start, &end); return -EINVAL; } } @@ -428,14 +428,14 @@ static int __init numa_init(int (*init_func)(void)) static int __init dummy_numa_init(void) { phys_addr_t start = memblock_start_of_DRAM(); - phys_addr_t end = memblock_end_of_DRAM(); + phys_addr_t end = memblock_end_of_DRAM() - 1; int ret; if (numa_off) pr_info("NUMA disabled\n"); /* Forced off on command line. */ - pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n", start, end - 1); + pr_info("Faking a node at [mem %pap-%pap]\n", &start, &end); - ret = numa_add_memblk(0, start, end); + ret = numa_add_memblk(0, start, end + 1); if (ret) { pr_err("NUMA init failed\n"); return ret; @@ -445,16 +445,36 @@ static int __init dummy_numa_init(void) return 0; } +#ifdef CONFIG_ACPI_NUMA +static int __init arch_acpi_numa_init(void) +{ + int ret; + + ret = acpi_numa_init(); + if (ret) { + pr_info("Failed to initialise from firmware\n"); + return ret; + } + + return srat_disabled() ? -EINVAL : 0; +} +#else +static int __init arch_acpi_numa_init(void) +{ + return -EOPNOTSUPP; +} +#endif + /** - * arm64_numa_init() - Initialize NUMA + * arch_numa_init() - Initialize NUMA * * Try each configured NUMA initialization method until one succeeds. The * last fallback is dummy single node config encompassing whole memory. */ -void __init arm64_numa_init(void) +void __init arch_numa_init(void) { if (!numa_off) { - if (!acpi_disabled && !numa_init(arm64_acpi_numa_init)) + if (!acpi_disabled && !numa_init(arch_acpi_numa_init)) return; if (acpi_disabled && !numa_init(of_numa_init)) return; diff --git a/drivers/base/memory.c b/drivers/base/memory.c index eef4ffb6122c..f35298425575 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -35,7 +35,7 @@ static const char *const online_type_to_str[] = { [MMOP_ONLINE_MOVABLE] = "online_movable", }; -int memhp_online_type_from_str(const char *str) +int mhp_online_type_from_str(const char *str) { int i; @@ -253,7 +253,7 @@ static int memory_subsys_offline(struct device *dev) static ssize_t state_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - const int online_type = memhp_online_type_from_str(buf); + const int online_type = mhp_online_type_from_str(buf); struct memory_block *mem = to_memory_block(dev); int ret; @@ -290,20 +290,20 @@ static ssize_t state_store(struct device *dev, struct device_attribute *attr, } /* - * phys_device is a bad name for this. What I really want - * is a way to differentiate between memory ranges that - * are part of physical devices that constitute - * a complete removable unit or fru. - * i.e. do these ranges belong to the same physical device, - * s.t. if I offline all of these sections I can then - * remove the physical device? + * Legacy interface that we cannot remove: s390x exposes the storage increment + * covered by a memory block, allowing for identifying which memory blocks + * comprise a storage increment. Since a memory block spans complete + * storage increments nowadays, this interface is basically unused. Other + * archs never exposed != 0. */ static ssize_t phys_device_show(struct device *dev, struct device_attribute *attr, char *buf) { struct memory_block *mem = to_memory_block(dev); + unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); - return sysfs_emit(buf, "%d\n", mem->phys_device); + return sysfs_emit(buf, "%d\n", + arch_get_memory_phys_device(start_pfn)); } #ifdef CONFIG_MEMORY_HOTREMOVE @@ -387,19 +387,19 @@ static ssize_t auto_online_blocks_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", - online_type_to_str[memhp_default_online_type]); + online_type_to_str[mhp_default_online_type]); } static ssize_t auto_online_blocks_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - const int online_type = memhp_online_type_from_str(buf); + const int online_type = mhp_online_type_from_str(buf); if (online_type < 0) return -EINVAL; - memhp_default_online_type = online_type; + mhp_default_online_type = online_type; return count; } @@ -488,11 +488,7 @@ static DEVICE_ATTR_WO(soft_offline_page); static DEVICE_ATTR_WO(hard_offline_page); #endif -/* - * Note that phys_device is optional. It is here to allow for - * differentiation between which *physical* devices each - * section belongs to... - */ +/* See phys_device_show(). */ int __weak arch_get_memory_phys_device(unsigned long start_pfn) { return 0; @@ -574,7 +570,6 @@ int register_memory(struct memory_block *memory) static int init_memory_block(unsigned long block_id, unsigned long state) { struct memory_block *mem; - unsigned long start_pfn; int ret = 0; mem = find_memory_block_by_id(block_id); @@ -588,8 +583,6 @@ static int init_memory_block(unsigned long block_id, unsigned long state) mem->start_section_nr = block_id * sections_per_block; mem->state = state; - start_pfn = section_nr_to_pfn(mem->start_section_nr); - mem->phys_device = arch_get_memory_phys_device(start_pfn); mem->nid = NUMA_NO_NODE; ret = register_memory(mem); diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 2779e85795a7..fd236158f32d 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -66,6 +66,12 @@ config AMIGA_Z2RAM To compile this driver as a module, choose M here: the module will be called z2ram. +config N64CART + bool "N64 cart support" + depends on MACH_NINTENDO64 + help + Support for the N64 cart. + config CDROM tristate select BLK_SCSI_REQUEST diff --git a/drivers/block/Makefile b/drivers/block/Makefile index b501b8728fb9..e3e3f1c79a82 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_PS3_DISK) += ps3disk.o obj-$(CONFIG_PS3_VRAM) += ps3vram.o obj-$(CONFIG_ATARI_FLOPPY) += ataflop.o obj-$(CONFIG_AMIGA_Z2RAM) += z2ram.o +obj-$(CONFIG_N64CART) += n64cart.o obj-$(CONFIG_BLK_DEV_RAM) += brd.o obj-$(CONFIG_BLK_DEV_LOOP) += loop.o obj-$(CONFIG_XILINX_SYSACE) += xsysace.o diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c new file mode 100644 index 000000000000..47bdf324e962 --- /dev/null +++ b/drivers/block/n64cart.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Support for the N64 cart. + * + * Copyright (c) 2021 Lauri Kasanen + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include +#include +#include +#include +#include +#include + +enum { + PI_DRAM_REG = 0, + PI_CART_REG, + PI_READ_REG, + PI_WRITE_REG, + PI_STATUS_REG, +}; + +#define PI_STATUS_DMA_BUSY (1 << 0) +#define PI_STATUS_IO_BUSY (1 << 1) + +#define CART_DOMAIN 0x10000000 +#define CART_MAX 0x1FFFFFFF + +#define MIN_ALIGNMENT 8 + +static u32 __iomem *reg_base; + +static unsigned int start; +module_param(start, uint, 0); +MODULE_PARM_DESC(start, "Start address of the cart block data"); + +static unsigned int size; +module_param(size, uint, 0); +MODULE_PARM_DESC(size, "Size of the cart block data, in bytes"); + +static void n64cart_write_reg(const u8 reg, const u32 value) +{ + writel(value, reg_base + reg); +} + +static u32 n64cart_read_reg(const u8 reg) +{ + return readl(reg_base + reg); +} + +static void n64cart_wait_dma(void) +{ + while (n64cart_read_reg(PI_STATUS_REG) & + (PI_STATUS_DMA_BUSY | PI_STATUS_IO_BUSY)) + cpu_relax(); +} + +/* + * Process a single bvec of a bio. + */ +static bool n64cart_do_bvec(struct device *dev, struct bio_vec *bv, u32 pos) +{ + dma_addr_t dma_addr; + const u32 bstart = pos + start; + + /* Alignment check */ + WARN_ON_ONCE((bv->bv_offset & (MIN_ALIGNMENT - 1)) || + (bv->bv_len & (MIN_ALIGNMENT - 1))); + + dma_addr = dma_map_bvec(dev, bv, DMA_FROM_DEVICE, 0); + if (dma_mapping_error(dev, dma_addr)) + return false; + + n64cart_wait_dma(); + + n64cart_write_reg(PI_DRAM_REG, dma_addr + bv->bv_offset); + n64cart_write_reg(PI_CART_REG, (bstart | CART_DOMAIN) & CART_MAX); + n64cart_write_reg(PI_WRITE_REG, bv->bv_len - 1); + + n64cart_wait_dma(); + + dma_unmap_page(dev, dma_addr, bv->bv_len, DMA_FROM_DEVICE); + return true; +} + +static blk_qc_t n64cart_submit_bio(struct bio *bio) +{ + struct bio_vec bvec; + struct bvec_iter iter; + struct device *dev = bio->bi_disk->private_data; + u32 pos = bio->bi_iter.bi_sector << SECTOR_SHIFT; + + bio_for_each_segment(bvec, bio, iter) { + if (!n64cart_do_bvec(dev, &bvec, pos)) + goto io_error; + pos += bvec.bv_len; + } + + bio_endio(bio); + return BLK_QC_T_NONE; +io_error: + bio_io_error(bio); + return BLK_QC_T_NONE; +} + +static const struct block_device_operations n64cart_fops = { + .owner = THIS_MODULE, + .submit_bio = n64cart_submit_bio, +}; + +/* + * The target device is embedded and RAM-constrained. We save RAM + * by initializing in __init code that gets dropped late in boot. + * For the same reason there is no module or unloading support. + */ +static int __init n64cart_probe(struct platform_device *pdev) +{ + struct gendisk *disk; + + if (!start || !size) { + pr_err("start or size not specified\n"); + return -ENODEV; + } + + if (size & 4095) { + pr_err("size must be a multiple of 4K\n"); + return -ENODEV; + } + + reg_base = devm_platform_ioremap_resource(pdev, 0); + if (!reg_base) + return -EINVAL; + + disk = alloc_disk(0); + if (!disk) + return -ENOMEM; + + disk->queue = blk_alloc_queue(NUMA_NO_NODE); + if (!disk->queue) + return -ENOMEM; + + disk->first_minor = 0; + disk->flags = GENHD_FL_NO_PART_SCAN | GENHD_FL_EXT_DEVT; + disk->fops = &n64cart_fops; + disk->private_data = &pdev->dev; + strcpy(disk->disk_name, "n64cart"); + + set_capacity(disk, size >> SECTOR_SHIFT); + set_disk_ro(disk, 1); + + blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); + blk_queue_physical_block_size(disk->queue, 4096); + blk_queue_logical_block_size(disk->queue, 4096); + + add_disk(disk); + + pr_info("n64cart: %u kb disk\n", size / 1024); + + return 0; +} + +static struct platform_driver n64cart_driver = { + .driver = { + .name = "n64cart", + }, +}; + +static int __init n64cart_init(void) +{ + return platform_driver_probe(&n64cart_driver, n64cart_probe); +} + +module_init(n64cart_init); + +MODULE_AUTHOR("Lauri Kasanen "); +MODULE_DESCRIPTION("Driver for the N64 cart"); +MODULE_LICENSE("GPL"); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 37c409f3cd83..fdfe8887332d 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -707,6 +707,7 @@ static int virtblk_probe(struct virtio_device *vdev) u32 v, blk_size, max_size, sg_elems, opt_io_size; u16 min_io_size; u8 physical_block_exp, alignment_offset; + unsigned int queue_depth; if (!vdev->config->get) { dev_err(&vdev->dev, "%s failure: config access disabled\n", @@ -758,16 +759,18 @@ static int virtblk_probe(struct virtio_device *vdev) } /* Default queue sizing is to fill the ring. */ - if (!virtblk_queue_depth) { - virtblk_queue_depth = vblk->vqs[0].vq->num_free; + if (likely(!virtblk_queue_depth)) { + queue_depth = vblk->vqs[0].vq->num_free; /* ... but without indirect descs, we use 2 descs per req */ if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC)) - virtblk_queue_depth /= 2; + queue_depth /= 2; + } else { + queue_depth = virtblk_queue_depth; } memset(&vblk->tag_set, 0, sizeof(vblk->tag_set)); vblk->tag_set.ops = &virtio_mq_ops; - vblk->tag_set.queue_depth = virtblk_queue_depth; + vblk->tag_set.queue_depth = queue_depth; vblk->tag_set.numa_node = NUMA_NO_NODE; vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; vblk->tag_set.cmd_size = diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index d7018543842e..a711a2e2a794 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1081,7 +1081,7 @@ static ssize_t mm_stat_show(struct device *dev, zram->limit_pages << PAGE_SHIFT, max_used << PAGE_SHIFT, (u64)atomic64_read(&zram->stats.same_pages), - pool_stats.pages_compacted, + atomic_long_read(&pool_stats.pages_compacted), (u64)atomic64_read(&zram->stats.huge_pages), (u64)atomic64_read(&zram->stats.huge_pages_since)); up_read(&zram->init_lock); diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 4b47170dbe2e..a588d56502d4 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -369,6 +369,13 @@ config COMMON_CLK_FIXED_MMIO help Support for Memory Mapped IO Fixed clocks +config COMMON_CLK_K210 + bool "Clock driver for the Canaan Kendryte K210 SoC" + depends on OF && RISCV && SOC_CANAAN + default SOC_CANAAN + help + Support for the Canaan Kendryte K210 RISC-V SoC clocks. + source "drivers/clk/actions/Kconfig" source "drivers/clk/analogbits/Kconfig" source "drivers/clk/baikal-t1/Kconfig" diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index 71c1fa24b5f0..b22ae4f81e0b 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -36,6 +36,7 @@ obj-$(CONFIG_COMMON_CLK_ASPEED) += clk-aspeed.o obj-$(CONFIG_MACH_ASPEED_G6) += clk-ast2600.o obj-$(CONFIG_ARCH_HIGHBANK) += clk-highbank.o obj-$(CONFIG_CLK_HSDK) += clk-hsdk-pll.o +obj-$(CONFIG_COMMON_CLK_K210) += clk-k210.o obj-$(CONFIG_COMMON_CLK_LOCHNAGAR) += clk-lochnagar.o obj-$(CONFIG_COMMON_CLK_MAX77686) += clk-max77686.o obj-$(CONFIG_COMMON_CLK_MAX9485) += clk-max9485.o diff --git a/drivers/clk/clk-k210.c b/drivers/clk/clk-k210.c new file mode 100644 index 000000000000..6c84abf5b2e3 --- /dev/null +++ b/drivers/clk/clk-k210.c @@ -0,0 +1,1007 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (c) 2019 Western Digital Corporation or its affiliates. + */ +#define pr_fmt(fmt) "k210-clk: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +struct k210_sysclk; + +struct k210_clk { + int id; + struct k210_sysclk *ksc; + struct clk_hw hw; +}; + +struct k210_clk_cfg { + const char *name; + u8 gate_reg; + u8 gate_bit; + u8 div_reg; + u8 div_shift; + u8 div_width; + u8 div_type; + u8 mux_reg; + u8 mux_bit; +}; + +enum k210_clk_div_type { + K210_DIV_NONE, + K210_DIV_ONE_BASED, + K210_DIV_DOUBLE_ONE_BASED, + K210_DIV_POWER_OF_TWO, +}; + +#define K210_GATE(_reg, _bit) \ + .gate_reg = (_reg), \ + .gate_bit = (_bit) + +#define K210_DIV(_reg, _shift, _width, _type) \ + .div_reg = (_reg), \ + .div_shift = (_shift), \ + .div_width = (_width), \ + .div_type = (_type) + +#define K210_MUX(_reg, _bit) \ + .mux_reg = (_reg), \ + .mux_bit = (_bit) + +static struct k210_clk_cfg k210_clk_cfgs[K210_NUM_CLKS] = { + /* Gated clocks, no mux, no divider */ + [K210_CLK_CPU] = { + .name = "cpu", + K210_GATE(K210_SYSCTL_EN_CENT, 0) + }, + [K210_CLK_DMA] = { + .name = "dma", + K210_GATE(K210_SYSCTL_EN_PERI, 1) + }, + [K210_CLK_FFT] = { + .name = "fft", + K210_GATE(K210_SYSCTL_EN_PERI, 4) + }, + [K210_CLK_GPIO] = { + .name = "gpio", + K210_GATE(K210_SYSCTL_EN_PERI, 5) + }, + [K210_CLK_UART1] = { + .name = "uart1", + K210_GATE(K210_SYSCTL_EN_PERI, 16) + }, + [K210_CLK_UART2] = { + .name = "uart2", + K210_GATE(K210_SYSCTL_EN_PERI, 17) + }, + [K210_CLK_UART3] = { + .name = "uart3", + K210_GATE(K210_SYSCTL_EN_PERI, 18) + }, + [K210_CLK_FPIOA] = { + .name = "fpioa", + K210_GATE(K210_SYSCTL_EN_PERI, 20) + }, + [K210_CLK_SHA] = { + .name = "sha", + K210_GATE(K210_SYSCTL_EN_PERI, 26) + }, + [K210_CLK_AES] = { + .name = "aes", + K210_GATE(K210_SYSCTL_EN_PERI, 19) + }, + [K210_CLK_OTP] = { + .name = "otp", + K210_GATE(K210_SYSCTL_EN_PERI, 27) + }, + [K210_CLK_RTC] = { + .name = "rtc", + K210_GATE(K210_SYSCTL_EN_PERI, 29) + }, + + /* Gated divider clocks */ + [K210_CLK_SRAM0] = { + .name = "sram0", + K210_GATE(K210_SYSCTL_EN_CENT, 1), + K210_DIV(K210_SYSCTL_THR0, 0, 4, K210_DIV_ONE_BASED) + }, + [K210_CLK_SRAM1] = { + .name = "sram1", + K210_GATE(K210_SYSCTL_EN_CENT, 2), + K210_DIV(K210_SYSCTL_THR0, 4, 4, K210_DIV_ONE_BASED) + }, + [K210_CLK_ROM] = { + .name = "rom", + K210_GATE(K210_SYSCTL_EN_PERI, 0), + K210_DIV(K210_SYSCTL_THR0, 16, 4, K210_DIV_ONE_BASED) + }, + [K210_CLK_DVP] = { + .name = "dvp", + K210_GATE(K210_SYSCTL_EN_PERI, 3), + K210_DIV(K210_SYSCTL_THR0, 12, 4, K210_DIV_ONE_BASED) + }, + [K210_CLK_APB0] = { + .name = "apb0", + K210_GATE(K210_SYSCTL_EN_CENT, 3), + K210_DIV(K210_SYSCTL_SEL0, 3, 3, K210_DIV_ONE_BASED) + }, + [K210_CLK_APB1] = { + .name = "apb1", + K210_GATE(K210_SYSCTL_EN_CENT, 4), + K210_DIV(K210_SYSCTL_SEL0, 6, 3, K210_DIV_ONE_BASED) + }, + [K210_CLK_APB2] = { + .name = "apb2", + K210_GATE(K210_SYSCTL_EN_CENT, 5), + K210_DIV(K210_SYSCTL_SEL0, 9, 3, K210_DIV_ONE_BASED) + }, + [K210_CLK_AI] = { + .name = "ai", + K210_GATE(K210_SYSCTL_EN_PERI, 2), + K210_DIV(K210_SYSCTL_THR0, 8, 4, K210_DIV_ONE_BASED) + }, + [K210_CLK_SPI0] = { + .name = "spi0", + K210_GATE(K210_SYSCTL_EN_PERI, 6), + K210_DIV(K210_SYSCTL_THR1, 0, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_SPI1] = { + .name = "spi1", + K210_GATE(K210_SYSCTL_EN_PERI, 7), + K210_DIV(K210_SYSCTL_THR1, 8, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_SPI2] = { + .name = "spi2", + K210_GATE(K210_SYSCTL_EN_PERI, 8), + K210_DIV(K210_SYSCTL_THR1, 16, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2C0] = { + .name = "i2c0", + K210_GATE(K210_SYSCTL_EN_PERI, 13), + K210_DIV(K210_SYSCTL_THR5, 8, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2C1] = { + .name = "i2c1", + K210_GATE(K210_SYSCTL_EN_PERI, 14), + K210_DIV(K210_SYSCTL_THR5, 16, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2C2] = { + .name = "i2c2", + K210_GATE(K210_SYSCTL_EN_PERI, 15), + K210_DIV(K210_SYSCTL_THR5, 24, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_WDT0] = { + .name = "wdt0", + K210_GATE(K210_SYSCTL_EN_PERI, 24), + K210_DIV(K210_SYSCTL_THR6, 0, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_WDT1] = { + .name = "wdt1", + K210_GATE(K210_SYSCTL_EN_PERI, 25), + K210_DIV(K210_SYSCTL_THR6, 8, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2S0] = { + .name = "i2s0", + K210_GATE(K210_SYSCTL_EN_PERI, 10), + K210_DIV(K210_SYSCTL_THR3, 0, 16, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2S1] = { + .name = "i2s1", + K210_GATE(K210_SYSCTL_EN_PERI, 11), + K210_DIV(K210_SYSCTL_THR3, 16, 16, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2S2] = { + .name = "i2s2", + K210_GATE(K210_SYSCTL_EN_PERI, 12), + K210_DIV(K210_SYSCTL_THR4, 0, 16, K210_DIV_DOUBLE_ONE_BASED) + }, + + /* Divider clocks, no gate, no mux */ + [K210_CLK_I2S0_M] = { + .name = "i2s0_m", + K210_DIV(K210_SYSCTL_THR4, 16, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2S1_M] = { + .name = "i2s1_m", + K210_DIV(K210_SYSCTL_THR4, 24, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + [K210_CLK_I2S2_M] = { + .name = "i2s2_m", + K210_DIV(K210_SYSCTL_THR4, 0, 8, K210_DIV_DOUBLE_ONE_BASED) + }, + + /* Muxed gated divider clocks */ + [K210_CLK_SPI3] = { + .name = "spi3", + K210_GATE(K210_SYSCTL_EN_PERI, 9), + K210_DIV(K210_SYSCTL_THR1, 24, 8, K210_DIV_DOUBLE_ONE_BASED), + K210_MUX(K210_SYSCTL_SEL0, 12) + }, + [K210_CLK_TIMER0] = { + .name = "timer0", + K210_GATE(K210_SYSCTL_EN_PERI, 21), + K210_DIV(K210_SYSCTL_THR2, 0, 8, K210_DIV_DOUBLE_ONE_BASED), + K210_MUX(K210_SYSCTL_SEL0, 13) + }, + [K210_CLK_TIMER1] = { + .name = "timer1", + K210_GATE(K210_SYSCTL_EN_PERI, 22), + K210_DIV(K210_SYSCTL_THR2, 8, 8, K210_DIV_DOUBLE_ONE_BASED), + K210_MUX(K210_SYSCTL_SEL0, 14) + }, + [K210_CLK_TIMER2] = { + .name = "timer2", + K210_GATE(K210_SYSCTL_EN_PERI, 23), + K210_DIV(K210_SYSCTL_THR2, 16, 8, K210_DIV_DOUBLE_ONE_BASED), + K210_MUX(K210_SYSCTL_SEL0, 15) + }, +}; + +/* + * PLL control register bits. + */ +#define K210_PLL_CLKR GENMASK(3, 0) +#define K210_PLL_CLKF GENMASK(9, 4) +#define K210_PLL_CLKOD GENMASK(13, 10) +#define K210_PLL_BWADJ GENMASK(19, 14) +#define K210_PLL_RESET (1 << 20) +#define K210_PLL_PWRD (1 << 21) +#define K210_PLL_INTFB (1 << 22) +#define K210_PLL_BYPASS (1 << 23) +#define K210_PLL_TEST (1 << 24) +#define K210_PLL_EN (1 << 25) +#define K210_PLL_SEL GENMASK(27, 26) /* PLL2 only */ + +/* + * PLL lock register bits. + */ +#define K210_PLL_LOCK 0 +#define K210_PLL_CLEAR_SLIP 2 +#define K210_PLL_TEST_OUT 3 + +/* + * Clock selector register bits. + */ +#define K210_ACLK_SEL BIT(0) +#define K210_ACLK_DIV GENMASK(2, 1) + +/* + * PLLs. + */ +enum k210_pll_id { + K210_PLL0, K210_PLL1, K210_PLL2, K210_PLL_NUM +}; + +struct k210_pll { + enum k210_pll_id id; + struct k210_sysclk *ksc; + void __iomem *base; + void __iomem *reg; + void __iomem *lock; + u8 lock_shift; + u8 lock_width; + struct clk_hw hw; +}; +#define to_k210_pll(_hw) container_of(_hw, struct k210_pll, hw) + +/* + * PLLs configuration: by default PLL0 runs at 780 MHz and PLL1 at 299 MHz. + * The first 2 SRAM banks depend on ACLK/CPU clock which is by default PLL0 + * rate divided by 2. Set PLL1 to 390 MHz so that the third SRAM bank has the + * same clock as the first 2. + */ +struct k210_pll_cfg { + u32 reg; + u8 lock_shift; + u8 lock_width; + u32 r; + u32 f; + u32 od; + u32 bwadj; +}; + +static struct k210_pll_cfg k210_plls_cfg[] = { + { K210_SYSCTL_PLL0, 0, 2, 0, 59, 1, 59 }, /* 780 MHz */ + { K210_SYSCTL_PLL1, 8, 1, 0, 59, 3, 59 }, /* 390 MHz */ + { K210_SYSCTL_PLL2, 16, 1, 0, 22, 1, 22 }, /* 299 MHz */ +}; + +/** + * struct k210_sysclk - sysclk driver data + * @regs: system controller registers start address + * @clk_lock: clock setting spinlock + * @plls: SoC PLLs descriptors + * @aclk: ACLK clock + * @clks: All other clocks + */ +struct k210_sysclk { + void __iomem *regs; + spinlock_t clk_lock; + struct k210_pll plls[K210_PLL_NUM]; + struct clk_hw aclk; + struct k210_clk clks[K210_NUM_CLKS]; +}; + +#define to_k210_sysclk(_hw) container_of(_hw, struct k210_sysclk, aclk) + +/* + * Set ACLK parent selector: 0 for IN0, 1 for PLL0. + */ +static void k210_aclk_set_selector(void __iomem *regs, u8 sel) +{ + u32 reg = readl(regs + K210_SYSCTL_SEL0); + + if (sel) + reg |= K210_ACLK_SEL; + else + reg &= K210_ACLK_SEL; + writel(reg, regs + K210_SYSCTL_SEL0); +} + +static void k210_init_pll(void __iomem *regs, enum k210_pll_id pllid, + struct k210_pll *pll) +{ + pll->id = pllid; + pll->reg = regs + k210_plls_cfg[pllid].reg; + pll->lock = regs + K210_SYSCTL_PLL_LOCK; + pll->lock_shift = k210_plls_cfg[pllid].lock_shift; + pll->lock_width = k210_plls_cfg[pllid].lock_width; +} + +static void k210_pll_wait_for_lock(struct k210_pll *pll) +{ + u32 reg, mask = GENMASK(pll->lock_shift + pll->lock_width - 1, + pll->lock_shift); + + while (true) { + reg = readl(pll->lock); + if ((reg & mask) == mask) + break; + + reg |= BIT(pll->lock_shift + K210_PLL_CLEAR_SLIP); + writel(reg, pll->lock); + } +} + +static bool k210_pll_hw_is_enabled(struct k210_pll *pll) +{ + u32 reg = readl(pll->reg); + u32 mask = K210_PLL_PWRD | K210_PLL_EN; + + if (reg & K210_PLL_RESET) + return false; + + return (reg & mask) == mask; +} + +static void k210_pll_enable_hw(void __iomem *regs, struct k210_pll *pll) +{ + struct k210_pll_cfg *pll_cfg = &k210_plls_cfg[pll->id]; + u32 reg; + + if (k210_pll_hw_is_enabled(pll)) + return; + + /* + * For PLL0, we need to re-parent ACLK to IN0 to keep the CPU cores and + * SRAM running. + */ + if (pll->id == K210_PLL0) + k210_aclk_set_selector(regs, 0); + + /* Set PLL factors */ + reg = readl(pll->reg); + reg &= ~GENMASK(19, 0); + reg |= FIELD_PREP(K210_PLL_CLKR, pll_cfg->r); + reg |= FIELD_PREP(K210_PLL_CLKF, pll_cfg->f); + reg |= FIELD_PREP(K210_PLL_CLKOD, pll_cfg->od); + reg |= FIELD_PREP(K210_PLL_BWADJ, pll_cfg->bwadj); + reg |= K210_PLL_PWRD; + writel(reg, pll->reg); + + /* + * Reset the PLL: ensure reset is low before asserting it. + * The magic NOPs come from the Kendryte reference SDK. + */ + reg &= ~K210_PLL_RESET; + writel(reg, pll->reg); + reg |= K210_PLL_RESET; + writel(reg, pll->reg); + nop(); + nop(); + reg &= ~K210_PLL_RESET; + writel(reg, pll->reg); + + k210_pll_wait_for_lock(pll); + + reg &= ~K210_PLL_BYPASS; + reg |= K210_PLL_EN; + writel(reg, pll->reg); + + if (pll->id == K210_PLL0) + k210_aclk_set_selector(regs, 1); +} + +static int k210_pll_enable(struct clk_hw *hw) +{ + struct k210_pll *pll = to_k210_pll(hw); + struct k210_sysclk *ksc = pll->ksc; + unsigned long flags; + + spin_lock_irqsave(&ksc->clk_lock, flags); + + k210_pll_enable_hw(ksc->regs, pll); + + spin_unlock_irqrestore(&ksc->clk_lock, flags); + + return 0; +} + +static void k210_pll_disable(struct clk_hw *hw) +{ + struct k210_pll *pll = to_k210_pll(hw); + struct k210_sysclk *ksc = pll->ksc; + unsigned long flags; + u32 reg; + + /* + * Bypassing before powering off is important so child clocks do not + * stop working. This is especially important for pll0, the indirect + * parent of the cpu clock. + */ + spin_lock_irqsave(&ksc->clk_lock, flags); + reg = readl(pll->reg); + reg |= K210_PLL_BYPASS; + writel(reg, pll->reg); + + reg &= ~K210_PLL_PWRD; + reg &= ~K210_PLL_EN; + writel(reg, pll->reg); + spin_unlock_irqrestore(&ksc->clk_lock, flags); +} + +static int k210_pll_is_enabled(struct clk_hw *hw) +{ + return k210_pll_hw_is_enabled(to_k210_pll(hw)); +} + +static unsigned long k210_pll_get_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct k210_pll *pll = to_k210_pll(hw); + u32 reg = readl(pll->reg); + u32 r, f, od; + + if (reg & K210_PLL_BYPASS) + return parent_rate; + + if (!(reg & K210_PLL_PWRD)) + return 0; + + r = FIELD_GET(K210_PLL_CLKR, reg) + 1; + f = FIELD_GET(K210_PLL_CLKF, reg) + 1; + od = FIELD_GET(K210_PLL_CLKOD, reg) + 1; + + return (u64)parent_rate * f / (r * od); +} + +static const struct clk_ops k210_pll_ops = { + .enable = k210_pll_enable, + .disable = k210_pll_disable, + .is_enabled = k210_pll_is_enabled, + .recalc_rate = k210_pll_get_rate, +}; + +static int k210_pll2_set_parent(struct clk_hw *hw, u8 index) +{ + struct k210_pll *pll = to_k210_pll(hw); + struct k210_sysclk *ksc = pll->ksc; + unsigned long flags; + u32 reg; + + spin_lock_irqsave(&ksc->clk_lock, flags); + + reg = readl(pll->reg); + reg &= ~K210_PLL_SEL; + reg |= FIELD_PREP(K210_PLL_SEL, index); + writel(reg, pll->reg); + + spin_unlock_irqrestore(&ksc->clk_lock, flags); + + return 0; +} + +static u8 k210_pll2_get_parent(struct clk_hw *hw) +{ + struct k210_pll *pll = to_k210_pll(hw); + u32 reg = readl(pll->reg); + + return FIELD_GET(K210_PLL_SEL, reg); +} + +static const struct clk_ops k210_pll2_ops = { + .enable = k210_pll_enable, + .disable = k210_pll_disable, + .is_enabled = k210_pll_is_enabled, + .recalc_rate = k210_pll_get_rate, + .set_parent = k210_pll2_set_parent, + .get_parent = k210_pll2_get_parent, +}; + +static int __init k210_register_pll(struct device_node *np, + struct k210_sysclk *ksc, + enum k210_pll_id pllid, const char *name, + int num_parents, const struct clk_ops *ops) +{ + struct k210_pll *pll = &ksc->plls[pllid]; + struct clk_init_data init = {}; + const struct clk_parent_data parent_data[] = { + { /* .index = 0 for in0 */ }, + { .hw = &ksc->plls[K210_PLL0].hw }, + { .hw = &ksc->plls[K210_PLL1].hw }, + }; + + init.name = name; + init.parent_data = parent_data; + init.num_parents = num_parents; + init.ops = ops; + + pll->hw.init = &init; + pll->ksc = ksc; + + return of_clk_hw_register(np, &pll->hw); +} + +static int __init k210_register_plls(struct device_node *np, + struct k210_sysclk *ksc) +{ + int i, ret; + + for (i = 0; i < K210_PLL_NUM; i++) + k210_init_pll(ksc->regs, i, &ksc->plls[i]); + + /* PLL0 and PLL1 only have IN0 as parent */ + ret = k210_register_pll(np, ksc, K210_PLL0, "pll0", 1, &k210_pll_ops); + if (ret) { + pr_err("%pOFP: register PLL0 failed\n", np); + return ret; + } + ret = k210_register_pll(np, ksc, K210_PLL1, "pll1", 1, &k210_pll_ops); + if (ret) { + pr_err("%pOFP: register PLL1 failed\n", np); + return ret; + } + + /* PLL2 has IN0, PLL0 and PLL1 as parents */ + ret = k210_register_pll(np, ksc, K210_PLL2, "pll2", 3, &k210_pll2_ops); + if (ret) { + pr_err("%pOFP: register PLL2 failed\n", np); + return ret; + } + + return 0; +} + +static int k210_aclk_set_parent(struct clk_hw *hw, u8 index) +{ + struct k210_sysclk *ksc = to_k210_sysclk(hw); + unsigned long flags; + + spin_lock_irqsave(&ksc->clk_lock, flags); + + k210_aclk_set_selector(ksc->regs, index); + + spin_unlock_irqrestore(&ksc->clk_lock, flags); + + return 0; +} + +static u8 k210_aclk_get_parent(struct clk_hw *hw) +{ + struct k210_sysclk *ksc = to_k210_sysclk(hw); + u32 sel; + + sel = readl(ksc->regs + K210_SYSCTL_SEL0) & K210_ACLK_SEL; + + return sel ? 1 : 0; +} + +static unsigned long k210_aclk_get_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct k210_sysclk *ksc = to_k210_sysclk(hw); + u32 reg = readl(ksc->regs + K210_SYSCTL_SEL0); + unsigned int shift; + + if (!(reg & 0x1)) + return parent_rate; + + shift = FIELD_GET(K210_ACLK_DIV, reg); + + return parent_rate / (2UL << shift); +} + +static const struct clk_ops k210_aclk_ops = { + .set_parent = k210_aclk_set_parent, + .get_parent = k210_aclk_get_parent, + .recalc_rate = k210_aclk_get_rate, +}; + +/* + * ACLK has IN0 and PLL0 as parents. + */ +static int __init k210_register_aclk(struct device_node *np, + struct k210_sysclk *ksc) +{ + struct clk_init_data init = {}; + const struct clk_parent_data parent_data[] = { + { /* .index = 0 for in0 */ }, + { .hw = &ksc->plls[K210_PLL0].hw }, + }; + int ret; + + init.name = "aclk"; + init.parent_data = parent_data; + init.num_parents = 2; + init.ops = &k210_aclk_ops; + ksc->aclk.init = &init; + + ret = of_clk_hw_register(np, &ksc->aclk); + if (ret) { + pr_err("%pOFP: register aclk failed\n", np); + return ret; + } + + return 0; +} + +#define to_k210_clk(_hw) container_of(_hw, struct k210_clk, hw) + +static int k210_clk_enable(struct clk_hw *hw) +{ + struct k210_clk *kclk = to_k210_clk(hw); + struct k210_sysclk *ksc = kclk->ksc; + struct k210_clk_cfg *cfg = &k210_clk_cfgs[kclk->id]; + unsigned long flags; + u32 reg; + + if (!cfg->gate_reg) + return 0; + + spin_lock_irqsave(&ksc->clk_lock, flags); + reg = readl(ksc->regs + cfg->gate_reg); + reg |= BIT(cfg->gate_bit); + writel(reg, ksc->regs + cfg->gate_reg); + spin_unlock_irqrestore(&ksc->clk_lock, flags); + + return 0; +} + +static void k210_clk_disable(struct clk_hw *hw) +{ + struct k210_clk *kclk = to_k210_clk(hw); + struct k210_sysclk *ksc = kclk->ksc; + struct k210_clk_cfg *cfg = &k210_clk_cfgs[kclk->id]; + unsigned long flags; + u32 reg; + + if (!cfg->gate_reg) + return; + + spin_lock_irqsave(&ksc->clk_lock, flags); + reg = readl(ksc->regs + cfg->gate_reg); + reg &= ~BIT(cfg->gate_bit); + writel(reg, ksc->regs + cfg->gate_reg); + spin_unlock_irqrestore(&ksc->clk_lock, flags); +} + +static int k210_clk_set_parent(struct clk_hw *hw, u8 index) +{ + struct k210_clk *kclk = to_k210_clk(hw); + struct k210_sysclk *ksc = kclk->ksc; + struct k210_clk_cfg *cfg = &k210_clk_cfgs[kclk->id]; + unsigned long flags; + u32 reg; + + spin_lock_irqsave(&ksc->clk_lock, flags); + reg = readl(ksc->regs + cfg->mux_reg); + if (index) + reg |= BIT(cfg->mux_bit); + else + reg &= ~BIT(cfg->mux_bit); + spin_unlock_irqrestore(&ksc->clk_lock, flags); + + return 0; +} + +static u8 k210_clk_get_parent(struct clk_hw *hw) +{ + struct k210_clk *kclk = to_k210_clk(hw); + struct k210_sysclk *ksc = kclk->ksc; + struct k210_clk_cfg *cfg = &k210_clk_cfgs[kclk->id]; + unsigned long flags; + u32 reg, idx; + + spin_lock_irqsave(&ksc->clk_lock, flags); + reg = readl(ksc->regs + cfg->mux_reg); + idx = (reg & BIT(cfg->mux_bit)) ? 1 : 0; + spin_unlock_irqrestore(&ksc->clk_lock, flags); + + return idx; +} + +static unsigned long k210_clk_get_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct k210_clk *kclk = to_k210_clk(hw); + struct k210_sysclk *ksc = kclk->ksc; + struct k210_clk_cfg *cfg = &k210_clk_cfgs[kclk->id]; + u32 reg, div_val; + + if (!cfg->div_reg) + return parent_rate; + + reg = readl(ksc->regs + cfg->div_reg); + div_val = (reg >> cfg->div_shift) & GENMASK(cfg->div_width - 1, 0); + + switch (cfg->div_type) { + case K210_DIV_ONE_BASED: + return parent_rate / (div_val + 1); + case K210_DIV_DOUBLE_ONE_BASED: + return parent_rate / ((div_val + 1) * 2); + case K210_DIV_POWER_OF_TWO: + return parent_rate / (2UL << div_val); + case K210_DIV_NONE: + default: + return 0; + } +} + +static const struct clk_ops k210_clk_mux_ops = { + .enable = k210_clk_enable, + .disable = k210_clk_disable, + .set_parent = k210_clk_set_parent, + .get_parent = k210_clk_get_parent, + .recalc_rate = k210_clk_get_rate, +}; + +static const struct clk_ops k210_clk_ops = { + .enable = k210_clk_enable, + .disable = k210_clk_disable, + .recalc_rate = k210_clk_get_rate, +}; + +static void __init k210_register_clk(struct device_node *np, + struct k210_sysclk *ksc, int id, + const struct clk_parent_data *parent_data, + int num_parents, unsigned long flags) +{ + struct k210_clk *kclk = &ksc->clks[id]; + struct clk_init_data init = {}; + int ret; + + init.name = k210_clk_cfgs[id].name; + init.flags = flags; + init.parent_data = parent_data; + init.num_parents = num_parents; + if (num_parents > 1) + init.ops = &k210_clk_mux_ops; + else + init.ops = &k210_clk_ops; + + kclk->id = id; + kclk->ksc = ksc; + kclk->hw.init = &init; + + ret = of_clk_hw_register(np, &kclk->hw); + if (ret) { + pr_err("%pOFP: register clock %s failed\n", + np, k210_clk_cfgs[id].name); + kclk->id = -1; + } +} + +/* + * All muxed clocks have IN0 and PLL0 as parents. + */ +static inline void __init k210_register_mux_clk(struct device_node *np, + struct k210_sysclk *ksc, int id) +{ + const struct clk_parent_data parent_data[2] = { + { /* .index = 0 for in0 */ }, + { .hw = &ksc->plls[K210_PLL0].hw } + }; + + k210_register_clk(np, ksc, id, parent_data, 2, 0); +} + +static inline void __init k210_register_in0_child(struct device_node *np, + struct k210_sysclk *ksc, int id) +{ + const struct clk_parent_data parent_data = { + /* .index = 0 for in0 */ + }; + + k210_register_clk(np, ksc, id, &parent_data, 1, 0); +} + +static inline void __init k210_register_pll_child(struct device_node *np, + struct k210_sysclk *ksc, int id, + enum k210_pll_id pllid, + unsigned long flags) +{ + const struct clk_parent_data parent_data = { + .hw = &ksc->plls[pllid].hw, + }; + + k210_register_clk(np, ksc, id, &parent_data, 1, flags); +} + +static inline void __init k210_register_aclk_child(struct device_node *np, + struct k210_sysclk *ksc, int id, + unsigned long flags) +{ + const struct clk_parent_data parent_data = { + .hw = &ksc->aclk, + }; + + k210_register_clk(np, ksc, id, &parent_data, 1, flags); +} + +static inline void __init k210_register_clk_child(struct device_node *np, + struct k210_sysclk *ksc, int id, + int parent_id) +{ + const struct clk_parent_data parent_data = { + .hw = &ksc->clks[parent_id].hw, + }; + + k210_register_clk(np, ksc, id, &parent_data, 1, 0); +} + +static struct clk_hw *k210_clk_hw_onecell_get(struct of_phandle_args *clkspec, + void *data) +{ + struct k210_sysclk *ksc = data; + unsigned int idx = clkspec->args[0]; + + if (idx >= K210_NUM_CLKS) + return ERR_PTR(-EINVAL); + + return &ksc->clks[idx].hw; +} + +static void __init k210_clk_init(struct device_node *np) +{ + struct device_node *sysctl_np; + struct k210_sysclk *ksc; + int i, ret; + + ksc = kzalloc(sizeof(*ksc), GFP_KERNEL); + if (!ksc) + return; + + spin_lock_init(&ksc->clk_lock); + sysctl_np = of_get_parent(np); + ksc->regs = of_iomap(sysctl_np, 0); + of_node_put(sysctl_np); + if (!ksc->regs) { + pr_err("%pOFP: failed to map registers\n", np); + return; + } + + ret = k210_register_plls(np, ksc); + if (ret) + return; + + ret = k210_register_aclk(np, ksc); + if (ret) + return; + + /* + * Critical clocks: there are no consumers of the SRAM clocks, + * including the AI clock for the third SRAM bank. The CPU clock + * is only referenced by the uarths serial device and so would be + * disabled if the serial console is disabled to switch to another + * console. Mark all these clocks as critical so that they are never + * disabled by the core clock management. + */ + k210_register_aclk_child(np, ksc, K210_CLK_CPU, CLK_IS_CRITICAL); + k210_register_aclk_child(np, ksc, K210_CLK_SRAM0, CLK_IS_CRITICAL); + k210_register_aclk_child(np, ksc, K210_CLK_SRAM1, CLK_IS_CRITICAL); + k210_register_pll_child(np, ksc, K210_CLK_AI, K210_PLL1, + CLK_IS_CRITICAL); + + /* Clocks with aclk as source */ + k210_register_aclk_child(np, ksc, K210_CLK_DMA, 0); + k210_register_aclk_child(np, ksc, K210_CLK_FFT, 0); + k210_register_aclk_child(np, ksc, K210_CLK_ROM, 0); + k210_register_aclk_child(np, ksc, K210_CLK_DVP, 0); + k210_register_aclk_child(np, ksc, K210_CLK_APB0, 0); + k210_register_aclk_child(np, ksc, K210_CLK_APB1, 0); + k210_register_aclk_child(np, ksc, K210_CLK_APB2, 0); + + /* Clocks with PLL0 as source */ + k210_register_pll_child(np, ksc, K210_CLK_SPI0, K210_PLL0, 0); + k210_register_pll_child(np, ksc, K210_CLK_SPI1, K210_PLL0, 0); + k210_register_pll_child(np, ksc, K210_CLK_SPI2, K210_PLL0, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2C0, K210_PLL0, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2C1, K210_PLL0, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2C2, K210_PLL0, 0); + + /* Clocks with PLL2 as source */ + k210_register_pll_child(np, ksc, K210_CLK_I2S0, K210_PLL2, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2S1, K210_PLL2, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2S2, K210_PLL2, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2S0_M, K210_PLL2, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2S1_M, K210_PLL2, 0); + k210_register_pll_child(np, ksc, K210_CLK_I2S2_M, K210_PLL2, 0); + + /* Clocks with IN0 as source */ + k210_register_in0_child(np, ksc, K210_CLK_WDT0); + k210_register_in0_child(np, ksc, K210_CLK_WDT1); + k210_register_in0_child(np, ksc, K210_CLK_RTC); + + /* Clocks with APB0 as source */ + k210_register_clk_child(np, ksc, K210_CLK_GPIO, K210_CLK_APB0); + k210_register_clk_child(np, ksc, K210_CLK_UART1, K210_CLK_APB0); + k210_register_clk_child(np, ksc, K210_CLK_UART2, K210_CLK_APB0); + k210_register_clk_child(np, ksc, K210_CLK_UART3, K210_CLK_APB0); + k210_register_clk_child(np, ksc, K210_CLK_FPIOA, K210_CLK_APB0); + k210_register_clk_child(np, ksc, K210_CLK_SHA, K210_CLK_APB0); + + /* Clocks with APB1 as source */ + k210_register_clk_child(np, ksc, K210_CLK_AES, K210_CLK_APB1); + k210_register_clk_child(np, ksc, K210_CLK_OTP, K210_CLK_APB1); + + /* Mux clocks with in0 or pll0 as source */ + k210_register_mux_clk(np, ksc, K210_CLK_SPI3); + k210_register_mux_clk(np, ksc, K210_CLK_TIMER0); + k210_register_mux_clk(np, ksc, K210_CLK_TIMER1); + k210_register_mux_clk(np, ksc, K210_CLK_TIMER2); + + /* Check for registration errors */ + for (i = 0; i < K210_NUM_CLKS; i++) { + if (ksc->clks[i].id != i) + return; + } + + ret = of_clk_add_hw_provider(np, k210_clk_hw_onecell_get, ksc); + if (ret) { + pr_err("%pOFP: add clock provider failed %d\n", np, ret); + return; + } + + pr_info("%pOFP: CPU running at %lu MHz\n", + np, clk_hw_get_rate(&ksc->clks[K210_CLK_CPU].hw) / 1000000); +} + +CLK_OF_DECLARE(k210_clk, "canaan,k210-clk", k210_clk_init); + +/* + * Enable PLL1 to be able to use the AI SRAM. + */ +void __init k210_clk_early_init(void __iomem *regs) +{ + struct k210_pll pll1; + + /* Make sure ACLK selector is set to PLL0 */ + k210_aclk_set_selector(regs, 1); + + /* Startup PLL1 to enable the aisram bank for general memory use */ + k210_init_pll(regs, K210_PLL1, &pll1); + k210_pll_enable_hw(regs, &pll1); +} diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 7475e09b0680..d64fc03929be 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -311,6 +311,83 @@ void __dma_fence_might_wait(void) #endif +/** + * dma_fence_signal_timestamp_locked - signal completion of a fence + * @fence: the fence to signal + * @timestamp: fence signal timestamp in kernel's CLOCK_MONOTONIC time domain + * + * Signal completion for software callbacks on a fence, this will unblock + * dma_fence_wait() calls and run all the callbacks added with + * dma_fence_add_callback(). Can be called multiple times, but since a fence + * can only go from the unsignaled to the signaled state and not back, it will + * only be effective the first time. Set the timestamp provided as the fence + * signal timestamp. + * + * Unlike dma_fence_signal_timestamp(), this function must be called with + * &dma_fence.lock held. + * + * Returns 0 on success and a negative error value when @fence has been + * signalled already. + */ +int dma_fence_signal_timestamp_locked(struct dma_fence *fence, + ktime_t timestamp) +{ + struct dma_fence_cb *cur, *tmp; + struct list_head cb_list; + + lockdep_assert_held(fence->lock); + + if (unlikely(test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, + &fence->flags))) + return -EINVAL; + + /* Stash the cb_list before replacing it with the timestamp */ + list_replace(&fence->cb_list, &cb_list); + + fence->timestamp = timestamp; + set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags); + trace_dma_fence_signaled(fence); + + list_for_each_entry_safe(cur, tmp, &cb_list, node) { + INIT_LIST_HEAD(&cur->node); + cur->func(fence, cur); + } + + return 0; +} +EXPORT_SYMBOL(dma_fence_signal_timestamp_locked); + +/** + * dma_fence_signal_timestamp - signal completion of a fence + * @fence: the fence to signal + * @timestamp: fence signal timestamp in kernel's CLOCK_MONOTONIC time domain + * + * Signal completion for software callbacks on a fence, this will unblock + * dma_fence_wait() calls and run all the callbacks added with + * dma_fence_add_callback(). Can be called multiple times, but since a fence + * can only go from the unsignaled to the signaled state and not back, it will + * only be effective the first time. Set the timestamp provided as the fence + * signal timestamp. + * + * Returns 0 on success and a negative error value when @fence has been + * signalled already. + */ +int dma_fence_signal_timestamp(struct dma_fence *fence, ktime_t timestamp) +{ + unsigned long flags; + int ret; + + if (!fence) + return -EINVAL; + + spin_lock_irqsave(fence->lock, flags); + ret = dma_fence_signal_timestamp_locked(fence, timestamp); + spin_unlock_irqrestore(fence->lock, flags); + + return ret; +} +EXPORT_SYMBOL(dma_fence_signal_timestamp); + /** * dma_fence_signal_locked - signal completion of a fence * @fence: the fence to signal @@ -329,28 +406,7 @@ void __dma_fence_might_wait(void) */ int dma_fence_signal_locked(struct dma_fence *fence) { - struct dma_fence_cb *cur, *tmp; - struct list_head cb_list; - - lockdep_assert_held(fence->lock); - - if (unlikely(test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, - &fence->flags))) - return -EINVAL; - - /* Stash the cb_list before replacing it with the timestamp */ - list_replace(&fence->cb_list, &cb_list); - - fence->timestamp = ktime_get(); - set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags); - trace_dma_fence_signaled(fence); - - list_for_each_entry_safe(cur, tmp, &cb_list, node) { - INIT_LIST_HEAD(&cur->node); - cur->func(fence, cur); - } - - return 0; + return dma_fence_signal_timestamp_locked(fence, ktime_get()); } EXPORT_SYMBOL(dma_fence_signal_locked); @@ -379,7 +435,7 @@ int dma_fence_signal(struct dma_fence *fence) tmp = dma_fence_begin_signalling(); spin_lock_irqsave(fence->lock, flags); - ret = dma_fence_signal_locked(fence); + ret = dma_fence_signal_timestamp_locked(fence, ktime_get()); spin_unlock_irqrestore(fence->lock, flags); dma_fence_end_signalling(tmp); diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c index 40b06f4ac03f..5d64eccd21d6 100644 --- a/drivers/dma-buf/heaps/cma_heap.c +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -348,7 +348,6 @@ static struct dma_buf *cma_heap_allocate(struct dma_heap *heap, ret = PTR_ERR(dmabuf); goto free_pages; } - return dmabuf; free_pages: diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c index 70533d51a244..76f4d636f974 100644 --- a/drivers/dma-buf/heaps/system_heap.c +++ b/drivers/dma-buf/heaps/system_heap.c @@ -388,8 +388,10 @@ static struct dma_buf *system_heap_do_allocate(struct dma_heap *heap, * Avoid trying to allocate memory if the process * has been killed by SIGKILL */ - if (fatal_signal_pending(current)) + if (fatal_signal_pending(current)) { + ret = -EINTR; goto free_buffer; + } page = alloc_largest_available(size_remaining, max_order); if (!page) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 86452f4f3c82..b6879d97c9c9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1008,6 +1008,12 @@ struct amdgpu_device { bool in_suspend; bool in_hibernate; + /* + * The combination flag in_poweroff_reboot_com used to identify the poweroff + * and reboot opt in the s0i3 system-wide suspend. + */ + bool in_poweroff_reboot_com; + atomic_t in_gpu_reset; enum pp_mp1_state mp1_state; struct rw_semaphore reset_sem; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 7052dc35d278..6447cd6ca5a8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2678,7 +2678,8 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev) { int i, r; - if (!amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) { + if (adev->in_poweroff_reboot_com || + !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) { amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); } @@ -3741,7 +3742,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) amdgpu_fence_driver_suspend(adev); - if (!amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) + if (adev->in_poweroff_reboot_com || + !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) r = amdgpu_device_ip_suspend_phase2(adev); else amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 03c529630c21..4575192d9b08 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1270,7 +1270,9 @@ amdgpu_pci_shutdown(struct pci_dev *pdev) */ if (!amdgpu_passthrough(adev)) adev->mp1_state = PP_MP1_STATE_UNLOAD; + adev->in_poweroff_reboot_com = true; amdgpu_device_ip_suspend(adev); + adev->in_poweroff_reboot_com = false; adev->mp1_state = PP_MP1_STATE_NONE; } @@ -1312,8 +1314,13 @@ static int amdgpu_pmops_thaw(struct device *dev) static int amdgpu_pmops_poweroff(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + int r; - return amdgpu_device_suspend(drm_dev, true); + adev->in_poweroff_reboot_com = true; + r = amdgpu_device_suspend(drm_dev, true); + adev->in_poweroff_reboot_com = false; + return r; } static int amdgpu_pmops_restore(struct device *dev) 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 94cd5ddd67ef..3e1fd1e7d09f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -937,7 +937,49 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_ } #endif +#if defined(CONFIG_DRM_AMD_DC_DCN) +static void event_mall_stutter(struct work_struct *work) +{ + struct vblank_workqueue *vblank_work = container_of(work, struct vblank_workqueue, mall_work); + struct amdgpu_display_manager *dm = vblank_work->dm; + + mutex_lock(&dm->dc_lock); + + if (vblank_work->enable) + dm->active_vblank_irq_count++; + else + dm->active_vblank_irq_count--; + + + dc_allow_idle_optimizations( + dm->dc, dm->active_vblank_irq_count == 0 ? true : false); + + DRM_DEBUG_DRIVER("Allow idle optimizations (MALL): %d\n", dm->active_vblank_irq_count == 0); + + + mutex_unlock(&dm->dc_lock); +} + +static struct vblank_workqueue *vblank_create_workqueue(struct amdgpu_device *adev, struct dc *dc) +{ + + int max_caps = dc->caps.max_links; + struct vblank_workqueue *vblank_work; + int i = 0; + + vblank_work = kcalloc(max_caps, sizeof(*vblank_work), GFP_KERNEL); + if (ZERO_OR_NULL_PTR(vblank_work)) { + kfree(vblank_work); + return NULL; + } + + for (i = 0; i < max_caps; i++) + INIT_WORK(&vblank_work[i].mall_work, event_mall_stutter); + + return vblank_work; +} +#endif static int amdgpu_dm_init(struct amdgpu_device *adev) { struct dc_init_data init_data; @@ -957,6 +999,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) mutex_init(&adev->dm.dc_lock); mutex_init(&adev->dm.audio_lock); +#if defined(CONFIG_DRM_AMD_DC_DCN) + spin_lock_init(&adev->dm.vblank_lock); +#endif if(amdgpu_dm_irq_init(adev)) { DRM_ERROR("amdgpu: failed to initialize DM IRQ support.\n"); @@ -1071,6 +1116,17 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) amdgpu_dm_init_color_mod(); +#if defined(CONFIG_DRM_AMD_DC_DCN) + if (adev->dm.dc->caps.max_links > 0) { + adev->dm.vblank_workqueue = vblank_create_workqueue(adev, adev->dm.dc); + + if (!adev->dm.vblank_workqueue) + DRM_ERROR("amdgpu: failed to initialize vblank_workqueue.\n"); + else + DRM_DEBUG_DRIVER("amdgpu: vblank_workqueue init done %p.\n", adev->dm.vblank_workqueue); + } +#endif + #ifdef CONFIG_DRM_AMD_DC_HDCP 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); @@ -1936,7 +1992,7 @@ static void dm_gpureset_commit_state(struct dc_state *dc_state, dc_commit_updates_for_stream( dm->dc, bundle->surface_updates, dc_state->stream_status->plane_count, - dc_state->streams[k], &bundle->stream_update); + dc_state->streams[k], &bundle->stream_update, dc_state); } cleanup: @@ -1967,7 +2023,8 @@ static void dm_set_dpms_off(struct dc_link *link) stream_update.stream = stream_state; dc_commit_updates_for_stream(stream_state->ctx->dc, NULL, 0, - stream_state, &stream_update); + stream_state, &stream_update, + stream_state->ctx->dc->current_state); mutex_unlock(&adev->dm.dc_lock); } @@ -5374,7 +5431,10 @@ static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); struct amdgpu_device *adev = drm_to_adev(crtc->dev); struct dm_crtc_state *acrtc_state = to_dm_crtc_state(crtc->state); +#if defined(CONFIG_DRM_AMD_DC_DCN) struct amdgpu_display_manager *dm = &adev->dm; + unsigned long flags; +#endif int rc = 0; if (enable) { @@ -5397,22 +5457,15 @@ static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable) if (amdgpu_in_reset(adev)) return 0; - mutex_lock(&dm->dc_lock); - - if (enable) - dm->active_vblank_irq_count++; - else - dm->active_vblank_irq_count--; - #if defined(CONFIG_DRM_AMD_DC_DCN) - dc_allow_idle_optimizations( - adev->dm.dc, dm->active_vblank_irq_count == 0 ? true : false); - - DRM_DEBUG_DRIVER("Allow idle optimizations (MALL): %d\n", dm->active_vblank_irq_count == 0); + spin_lock_irqsave(&dm->vblank_lock, flags); + dm->vblank_workqueue->dm = dm; + dm->vblank_workqueue->otg_inst = acrtc->otg_inst; + dm->vblank_workqueue->enable = enable; + spin_unlock_irqrestore(&dm->vblank_lock, flags); + schedule_work(&dm->vblank_workqueue->mall_work); #endif - mutex_unlock(&dm->dc_lock); - return 0; } @@ -7663,7 +7716,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, struct drm_crtc *pcrtc, bool wait_for_vblank) { - int i; + uint32_t i; uint64_t timestamp_ns; struct drm_plane *plane; struct drm_plane_state *old_plane_state, *new_plane_state; @@ -7704,7 +7757,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, amdgpu_dm_commit_cursors(state); /* update planes when needed */ - for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) { + for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { struct drm_crtc *crtc = new_plane_state->crtc; struct drm_crtc_state *new_crtc_state; struct drm_framebuffer *fb = new_plane_state->fb; @@ -7927,7 +7980,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, bundle->surface_updates, planes_count, acrtc_state->stream, - &bundle->stream_update); + &bundle->stream_update, + dc_state); /** * Enable or disable the interrupts on the backend. @@ -8263,13 +8317,13 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) struct dm_connector_state *dm_new_con_state = to_dm_connector_state(new_con_state); struct dm_connector_state *dm_old_con_state = to_dm_connector_state(old_con_state); struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc); - struct dc_surface_update surface_updates[MAX_SURFACES]; + struct dc_surface_update dummy_updates[MAX_SURFACES]; struct dc_stream_update stream_update; struct dc_info_packet hdr_packet; struct dc_stream_status *status = NULL; bool abm_changed, hdr_changed, scaling_changed; - memset(&surface_updates, 0, sizeof(surface_updates)); + memset(&dummy_updates, 0, sizeof(dummy_updates)); memset(&stream_update, 0, sizeof(stream_update)); if (acrtc) { @@ -8326,15 +8380,16 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) * To fix this, DC should permit updating only stream properties. */ for (j = 0; j < status->plane_count; j++) - surface_updates[j].surface = status->plane_states[j]; + dummy_updates[j].surface = status->plane_states[0]; mutex_lock(&dm->dc_lock); dc_commit_updates_for_stream(dm->dc, - surface_updates, + dummy_updates, status->plane_count, dm_new_crtc_state->stream, - &stream_update); + &stream_update, + dc_state); mutex_unlock(&dm->dc_lock); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index f72930c36c22..8bfe901cf237 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -92,6 +92,20 @@ struct dm_compressor_info { uint64_t gpu_addr; }; +/** + * struct vblank_workqueue - Works to be executed in a separate thread during vblank + * @mall_work: work for mall stutter + * @dm: amdgpu display manager device + * @otg_inst: otg instance of which vblank is being set + * @enable: true if enable vblank + */ +struct vblank_workqueue { + struct work_struct mall_work; + struct amdgpu_display_manager *dm; + int otg_inst; + bool enable; +}; + /** * struct amdgpu_dm_backlight_caps - Information about backlight * @@ -243,6 +257,15 @@ struct amdgpu_display_manager { */ struct mutex audio_lock; + /** + * @vblank_work_lock: + * + * Guards access to deferred vblank work state. + */ +#if defined(CONFIG_DRM_AMD_DC_DCN) + spinlock_t vblank_lock; +#endif + /** * @audio_component: * @@ -321,6 +344,10 @@ struct amdgpu_display_manager { struct hdcp_workqueue *hdcp_workqueue; #endif +#if defined(CONFIG_DRM_AMD_DC_DCN) + struct vblank_workqueue *vblank_workqueue; +#endif + struct drm_atomic_state *cached_state; struct dc_state *cached_dc_state; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index c9aede2f783d..8f8a13c7cf73 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2697,7 +2697,8 @@ void dc_commit_updates_for_stream(struct dc *dc, struct dc_surface_update *srf_updates, int surface_count, struct dc_stream_state *stream, - struct dc_stream_update *stream_update) + struct dc_stream_update *stream_update, + struct dc_state *state) { const struct dc_stream_status *stream_status; enum surface_update_type update_type; @@ -2716,12 +2717,6 @@ void dc_commit_updates_for_stream(struct dc *dc, if (update_type >= UPDATE_TYPE_FULL) { - struct dc_plane_state *new_planes[MAX_SURFACES]; - - memset(new_planes, 0, sizeof(new_planes)); - - for (i = 0; i < surface_count; i++) - new_planes[i] = srf_updates[i].surface; /* initialize scratch memory for building context */ context = dc_create_state(dc); @@ -2730,21 +2725,15 @@ void dc_commit_updates_for_stream(struct dc *dc, return; } - dc_resource_state_copy_construct( - dc->current_state, context); + dc_resource_state_copy_construct(state, context); - /*remove old surfaces from context */ - if (!dc_rem_all_planes_for_stream(dc, stream, context)) { - DC_ERROR("Failed to remove streams for new validate context!\n"); - return; + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i]; + struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + + if (new_pipe->plane_state && new_pipe->plane_state != old_pipe->plane_state) + new_pipe->plane_state->force_full_update = true; } - - /* add surface to context */ - if (!dc_add_all_planes_for_stream(dc, stream, new_planes, surface_count, context)) { - DC_ERROR("Failed to add streams for new validate context!\n"); - return; - } - } diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index a4f7ec888c67..80b67b860091 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -294,7 +294,8 @@ void dc_commit_updates_for_stream(struct dc *dc, struct dc_surface_update *srf_updates, int surface_count, struct dc_stream_state *stream, - struct dc_stream_update *stream_update); + struct dc_stream_update *stream_update, + struct dc_state *state); /* * Log the current stream state. */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c index 59024653430c..e4701825b5a0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c @@ -480,7 +480,6 @@ unsigned int dcn10_get_dig_frontend(struct link_encoder *enc) break; default: // invalid source select DIG - ASSERT(false); result = ENGINE_ID_UNKNOWN; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index 9620fb8a27dc..06dc1e2e8383 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -539,6 +539,8 @@ void dcn30_init_hw(struct dc *dc) fe = dc->links[i]->link_enc->funcs->get_dig_frontend( dc->links[i]->link_enc); + if (fe == ENGINE_ID_UNKNOWN) + continue; for (j = 0; j < dc->res_pool->stream_enc_count; j++) { if (fe == dc->res_pool->stream_enc[j]->id) { diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c index 1b971265418b..0e0f494fbb5e 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c @@ -168,6 +168,11 @@ static const struct irq_source_info_funcs vblank_irq_info_funcs = { .ack = NULL }; +static const struct irq_source_info_funcs vupdate_no_lock_irq_info_funcs = { + .set = NULL, + .ack = NULL +}; + #undef BASE_INNER #define BASE_INNER(seg) DMU_BASE__INST0_SEG ## seg @@ -230,6 +235,17 @@ static const struct irq_source_info_funcs vblank_irq_info_funcs = { .funcs = &vblank_irq_info_funcs\ } +/* vupdate_no_lock_int_entry maps to DC_IRQ_SOURCE_VUPDATEx, to match semantic + * of DCE's DC_IRQ_SOURCE_VUPDATEx. + */ +#define vupdate_no_lock_int_entry(reg_num)\ + [DC_IRQ_SOURCE_VUPDATE1 + reg_num] = {\ + IRQ_REG_ENTRY(OTG, reg_num,\ + OTG_GLOBAL_SYNC_STATUS, VUPDATE_NO_LOCK_INT_EN,\ + OTG_GLOBAL_SYNC_STATUS, VUPDATE_NO_LOCK_EVENT_CLEAR),\ + .funcs = &vupdate_no_lock_irq_info_funcs\ + } + #define vblank_int_entry(reg_num)\ [DC_IRQ_SOURCE_VBLANK1 + reg_num] = {\ IRQ_REG_ENTRY(OTG, reg_num,\ @@ -338,6 +354,12 @@ irq_source_info_dcn21[DAL_IRQ_SOURCES_NUMBER] = { vupdate_int_entry(3), vupdate_int_entry(4), vupdate_int_entry(5), + vupdate_no_lock_int_entry(0), + vupdate_no_lock_int_entry(1), + vupdate_no_lock_int_entry(2), + vupdate_no_lock_int_entry(3), + vupdate_no_lock_int_entry(4), + vupdate_no_lock_int_entry(5), vblank_int_entry(0), vblank_int_entry(1), vblank_int_entry(2), diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index bb620fdd4cd2..bcedd4d92e35 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -762,7 +762,7 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev) structure_size = sizeof(struct gpu_metrics_v2_0); break; default: - break; + return; } #undef METRICS_VERSION diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 6b116bfd747c..7efbccffc2ea 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -774,6 +774,72 @@ void drm_event_cancel_free(struct drm_device *dev, } EXPORT_SYMBOL(drm_event_cancel_free); +/** + * drm_send_event_helper - send DRM event to file descriptor + * @dev: DRM device + * @e: DRM event to deliver + * @timestamp: timestamp to set for the fence event in kernel's CLOCK_MONOTONIC + * time domain + * + * This helper function sends the event @e, initialized with + * drm_event_reserve_init(), to its associated userspace DRM file. + * The timestamp variant of dma_fence_signal is used when the caller + * sends a valid timestamp. + */ +void drm_send_event_helper(struct drm_device *dev, + struct drm_pending_event *e, ktime_t timestamp) +{ + assert_spin_locked(&dev->event_lock); + + if (e->completion) { + complete_all(e->completion); + e->completion_release(e->completion); + e->completion = NULL; + } + + if (e->fence) { + if (timestamp) + dma_fence_signal_timestamp(e->fence, timestamp); + else + dma_fence_signal(e->fence); + dma_fence_put(e->fence); + } + + if (!e->file_priv) { + kfree(e); + return; + } + + list_del(&e->pending_link); + list_add_tail(&e->link, + &e->file_priv->event_list); + wake_up_interruptible_poll(&e->file_priv->event_wait, + EPOLLIN | EPOLLRDNORM); +} + +/** + * drm_send_event_timestamp_locked - send DRM event to file descriptor + * @dev: DRM device + * @e: DRM event to deliver + * @timestamp: timestamp to set for the fence event in kernel's CLOCK_MONOTONIC + * time domain + * + * This function sends the event @e, initialized with drm_event_reserve_init(), + * to its associated userspace DRM file. Callers must already hold + * &drm_device.event_lock. + * + * Note that the core will take care of unlinking and disarming events when the + * corresponding DRM file is closed. Drivers need not worry about whether the + * DRM file for this event still exists and can call this function upon + * completion of the asynchronous work unconditionally. + */ +void drm_send_event_timestamp_locked(struct drm_device *dev, + struct drm_pending_event *e, ktime_t timestamp) +{ + drm_send_event_helper(dev, e, timestamp); +} +EXPORT_SYMBOL(drm_send_event_timestamp_locked); + /** * drm_send_event_locked - send DRM event to file descriptor * @dev: DRM device @@ -790,29 +856,7 @@ EXPORT_SYMBOL(drm_event_cancel_free); */ void drm_send_event_locked(struct drm_device *dev, struct drm_pending_event *e) { - assert_spin_locked(&dev->event_lock); - - if (e->completion) { - complete_all(e->completion); - e->completion_release(e->completion); - e->completion = NULL; - } - - if (e->fence) { - dma_fence_signal(e->fence); - dma_fence_put(e->fence); - } - - if (!e->file_priv) { - kfree(e); - return; - } - - list_del(&e->pending_link); - list_add_tail(&e->link, - &e->file_priv->event_list); - wake_up_interruptible_poll(&e->file_priv->event_wait, - EPOLLIN | EPOLLRDNORM); + drm_send_event_helper(dev, e, 0); } EXPORT_SYMBOL(drm_send_event_locked); @@ -836,7 +880,7 @@ void drm_send_event(struct drm_device *dev, struct drm_pending_event *e) unsigned long irqflags; spin_lock_irqsave(&dev->event_lock, irqflags); - drm_send_event_locked(dev, e); + drm_send_event_helper(dev, e, 0); spin_unlock_irqrestore(&dev->event_lock, irqflags); } EXPORT_SYMBOL(drm_send_event); diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c index 30912d8f82a5..893165eeddf3 100644 --- a/drivers/gpu/drm/drm_vblank.c +++ b/drivers/gpu/drm/drm_vblank.c @@ -1006,7 +1006,14 @@ static void send_vblank_event(struct drm_device *dev, break; } trace_drm_vblank_event_delivered(e->base.file_priv, e->pipe, seq); - drm_send_event_locked(dev, &e->base); + /* + * Use the same timestamp for any associated fence signal to avoid + * mismatch in timestamps for vsync & fence events triggered by the + * same HW event. Frameworks like SurfaceFlinger in Android expects the + * retire-fence timestamp to match exactly with HW vsync as it uses it + * for its software vsync modeling. + */ + drm_send_event_timestamp_locked(dev, &e->base, now); } /** diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 32bd1fdffffe..2385a7505f5d 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -21,7 +21,6 @@ subdir-ccflags-y += $(call cc-disable-warning, unused-but-set-variable) subdir-ccflags-y += $(call cc-disable-warning, sign-compare) subdir-ccflags-y += $(call cc-disable-warning, sometimes-uninitialized) subdir-ccflags-y += $(call cc-disable-warning, initializer-overrides) -subdir-ccflags-y += $(call cc-disable-warning, uninitialized) subdir-ccflags-y += $(call cc-disable-warning, frame-address) subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror @@ -298,7 +297,7 @@ obj-$(CONFIG_DRM_I915_GVT_KVMGT) += gvt/kvmgt.o no-header-test := \ display/intel_vbt_defs.h -extra-$(CONFIG_DRM_I915_WERROR) += \ +always-$(CONFIG_DRM_I915_WERROR) += \ $(patsubst %.h,%.hdrtest, $(filter-out $(no-header-test), \ $(shell cd $(srctree)/$(src) && find * -name '*.h'))) diff --git a/drivers/gpu/drm/i915/display/intel_crtc.c b/drivers/gpu/drm/i915/display/intel_crtc.c index 57b0a3ebe908..8e77ca7ddf11 100644 --- a/drivers/gpu/drm/i915/display/intel_crtc.c +++ b/drivers/gpu/drm/i915/display/intel_crtc.c @@ -109,7 +109,6 @@ void intel_crtc_state_reset(struct intel_crtc_state *crtc_state, crtc_state->cpu_transcoder = INVALID_TRANSCODER; crtc_state->master_transcoder = INVALID_TRANSCODER; crtc_state->hsw_workaround_pipe = INVALID_PIPE; - crtc_state->output_format = INTEL_OUTPUT_FORMAT_INVALID; crtc_state->scaler_state.scaler_id = -1; crtc_state->mst_master_transcoder = INVALID_TRANSCODER; } diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 7ea1e5b487b6..8d7aaa68c6f6 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -10211,7 +10211,6 @@ static void snprintf_output_types(char *buf, size_t len, } static const char * const output_format_str[] = { - [INTEL_OUTPUT_FORMAT_INVALID] = "Invalid", [INTEL_OUTPUT_FORMAT_RGB] = "RGB", [INTEL_OUTPUT_FORMAT_YCBCR420] = "YCBCR4:2:0", [INTEL_OUTPUT_FORMAT_YCBCR444] = "YCBCR4:4:4", @@ -10220,7 +10219,7 @@ static const char * const output_format_str[] = { static const char *output_formats(enum intel_output_format format) { if (format >= ARRAY_SIZE(output_format_str)) - format = INTEL_OUTPUT_FORMAT_INVALID; + return "invalid"; return output_format_str[format]; } diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 39397748b4b0..184ecbbcec99 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -830,7 +830,6 @@ struct intel_crtc_wm_state { }; enum intel_output_format { - INTEL_OUTPUT_FORMAT_INVALID, INTEL_OUTPUT_FORMAT_RGB, INTEL_OUTPUT_FORMAT_YCBCR420, INTEL_OUTPUT_FORMAT_YCBCR444, diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index d54ea0e4681d..fef1e857cefc 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -41,6 +41,7 @@ #include "gt/intel_lrc.h" #include "gt/intel_ring.h" #include "gt/intel_gt_requests.h" +#include "gt/shmem_utils.h" #include "gvt.h" #include "i915_pvinfo.h" #include "trace.h" @@ -3094,71 +3095,28 @@ int intel_gvt_scan_and_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) */ void intel_gvt_update_reg_whitelist(struct intel_vgpu *vgpu) { + const unsigned long start = LRC_STATE_PN * PAGE_SIZE; struct intel_gvt *gvt = vgpu->gvt; - struct drm_i915_private *dev_priv = gvt->gt->i915; struct intel_engine_cs *engine; enum intel_engine_id id; - const unsigned long start = LRC_STATE_PN * PAGE_SIZE; - struct i915_request *rq; - struct intel_vgpu_submission *s = &vgpu->submission; - struct i915_request *requests[I915_NUM_ENGINES] = {}; - bool is_ctx_pinned[I915_NUM_ENGINES] = {}; - int ret = 0; if (gvt->is_reg_whitelist_updated) return; - for_each_engine(engine, &dev_priv->gt, id) { - ret = intel_context_pin(s->shadow[id]); - if (ret) { - gvt_vgpu_err("fail to pin shadow ctx\n"); - goto out; - } - is_ctx_pinned[id] = true; - - rq = i915_request_create(s->shadow[id]); - if (IS_ERR(rq)) { - gvt_vgpu_err("fail to alloc default request\n"); - ret = -EIO; - goto out; - } - requests[id] = i915_request_get(rq); - i915_request_add(rq); - } - - if (intel_gt_wait_for_idle(&dev_priv->gt, - I915_GEM_IDLE_TIMEOUT) == -ETIME) { - ret = -EIO; - goto out; - } - /* scan init ctx to update cmd accessible list */ - for_each_engine(engine, &dev_priv->gt, id) { - int size = engine->context_size - PAGE_SIZE; - void *vaddr; + for_each_engine(engine, gvt->gt, id) { struct parser_exec_state s; - struct drm_i915_gem_object *obj; - struct i915_request *rq; + void *vaddr; + int ret; - rq = requests[id]; - GEM_BUG_ON(!i915_request_completed(rq)); - GEM_BUG_ON(!intel_context_is_pinned(rq->context)); - obj = rq->context->state->obj; + if (!engine->default_state) + continue; - if (!obj) { - ret = -EIO; - goto out; - } - - i915_gem_object_set_cache_coherency(obj, - I915_CACHE_LLC); - - vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB); + vaddr = shmem_pin_map(engine->default_state); if (IS_ERR(vaddr)) { - gvt_err("failed to pin init ctx obj, ring=%d, err=%lx\n", - id, PTR_ERR(vaddr)); - ret = PTR_ERR(vaddr); - goto out; + gvt_err("failed to map %s->default state, err:%zd\n", + engine->name, PTR_ERR(vaddr)); + return; } s.buf_type = RING_BUFFER_CTX; @@ -3166,9 +3124,9 @@ void intel_gvt_update_reg_whitelist(struct intel_vgpu *vgpu) s.vgpu = vgpu; s.engine = engine; s.ring_start = 0; - s.ring_size = size; + s.ring_size = engine->context_size - start; s.ring_head = 0; - s.ring_tail = size; + s.ring_tail = s.ring_size; s.rb_va = vaddr + start; s.workload = NULL; s.is_ctx_wa = false; @@ -3176,29 +3134,18 @@ void intel_gvt_update_reg_whitelist(struct intel_vgpu *vgpu) /* skipping the first RING_CTX_SIZE(0x50) dwords */ ret = ip_gma_set(&s, RING_CTX_SIZE); - if (ret) { - i915_gem_object_unpin_map(obj); - goto out; + if (ret == 0) { + ret = command_scan(&s, 0, s.ring_size, 0, s.ring_size); + if (ret) + gvt_err("Scan init ctx error\n"); } - ret = command_scan(&s, 0, size, 0, size); + shmem_unpin_map(engine->default_state, vaddr); if (ret) - gvt_err("Scan init ctx error\n"); - - i915_gem_object_unpin_map(obj); + return; } -out: - if (!ret) - gvt->is_reg_whitelist_updated = true; - - for (id = 0; id < I915_NUM_ENGINES ; id++) { - if (requests[id]) - i915_request_put(requests[id]); - - if (is_ctx_pinned[id]) - intel_context_unpin(s->shadow[id]); - } + gvt->is_reg_whitelist_updated = true; } int intel_gvt_scan_engine_context(struct intel_vgpu_workload *workload) diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c index 158873f269b1..c8dcda6d4f0d 100644 --- a/drivers/gpu/drm/i915/gvt/execlist.c +++ b/drivers/gpu/drm/i915/gvt/execlist.c @@ -522,12 +522,11 @@ static void init_vgpu_execlist(struct intel_vgpu *vgpu, static void clean_execlist(struct intel_vgpu *vgpu, intel_engine_mask_t engine_mask) { - struct drm_i915_private *dev_priv = vgpu->gvt->gt->i915; - struct intel_engine_cs *engine; struct intel_vgpu_submission *s = &vgpu->submission; + struct intel_engine_cs *engine; intel_engine_mask_t tmp; - for_each_engine_masked(engine, &dev_priv->gt, engine_mask, tmp) { + for_each_engine_masked(engine, vgpu->gvt->gt, engine_mask, tmp) { kfree(s->ring_scan_buffer[engine->id]); s->ring_scan_buffer[engine->id] = NULL; s->ring_scan_buffer_size[engine->id] = 0; @@ -537,11 +536,10 @@ static void clean_execlist(struct intel_vgpu *vgpu, static void reset_execlist(struct intel_vgpu *vgpu, intel_engine_mask_t engine_mask) { - struct drm_i915_private *dev_priv = vgpu->gvt->gt->i915; struct intel_engine_cs *engine; intel_engine_mask_t tmp; - for_each_engine_masked(engine, &dev_priv->gt, engine_mask, tmp) + for_each_engine_masked(engine, vgpu->gvt->gt, engine_mask, tmp) init_vgpu_execlist(vgpu, engine); } diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 43f31c2eab14..fc735692f21f 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -412,7 +412,9 @@ static void release_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) if (!wa_ctx->indirect_ctx.obj) return; + i915_gem_object_lock(wa_ctx->indirect_ctx.obj, NULL); i915_gem_object_unpin_map(wa_ctx->indirect_ctx.obj); + i915_gem_object_unlock(wa_ctx->indirect_ctx.obj); i915_gem_object_put(wa_ctx->indirect_ctx.obj); wa_ctx->indirect_ctx.obj = NULL; @@ -520,6 +522,7 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload) struct intel_gvt *gvt = workload->vgpu->gvt; const int gmadr_bytes = gvt->device_info.gmadr_bytes_in_cmd; struct intel_vgpu_shadow_bb *bb; + struct i915_gem_ww_ctx ww; int ret; list_for_each_entry(bb, &workload->shadow_bb, list) { @@ -544,10 +547,19 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload) * directly */ if (!bb->ppgtt) { - bb->vma = i915_gem_object_ggtt_pin(bb->obj, - NULL, 0, 0, 0); + i915_gem_ww_ctx_init(&ww, false); +retry: + i915_gem_object_lock(bb->obj, &ww); + + bb->vma = i915_gem_object_ggtt_pin_ww(bb->obj, &ww, + NULL, 0, 0, 0); if (IS_ERR(bb->vma)) { ret = PTR_ERR(bb->vma); + if (ret == -EDEADLK) { + ret = i915_gem_ww_ctx_backoff(&ww); + if (!ret) + goto retry; + } goto err; } @@ -561,13 +573,15 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload) 0); if (ret) goto err; - } - /* No one is going to touch shadow bb from now on. */ - i915_gem_object_flush_map(bb->obj); + /* No one is going to touch shadow bb from now on. */ + i915_gem_object_flush_map(bb->obj); + i915_gem_object_unlock(bb->obj); + } } return 0; err: + i915_gem_ww_ctx_fini(&ww); release_shadow_batch_buffer(workload); return ret; } @@ -594,14 +608,29 @@ static int prepare_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) unsigned char *per_ctx_va = (unsigned char *)wa_ctx->indirect_ctx.shadow_va + wa_ctx->indirect_ctx.size; + struct i915_gem_ww_ctx ww; + int ret; if (wa_ctx->indirect_ctx.size == 0) return 0; - vma = i915_gem_object_ggtt_pin(wa_ctx->indirect_ctx.obj, NULL, - 0, CACHELINE_BYTES, 0); - if (IS_ERR(vma)) - return PTR_ERR(vma); + i915_gem_ww_ctx_init(&ww, false); +retry: + i915_gem_object_lock(wa_ctx->indirect_ctx.obj, &ww); + + vma = i915_gem_object_ggtt_pin_ww(wa_ctx->indirect_ctx.obj, &ww, NULL, + 0, CACHELINE_BYTES, 0); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + if (ret == -EDEADLK) { + ret = i915_gem_ww_ctx_backoff(&ww); + if (!ret) + goto retry; + } + return ret; + } + + i915_gem_object_unlock(wa_ctx->indirect_ctx.obj); /* FIXME: we are not tracking our pinned VMA leaving it * up to the core to fix up the stray pin_count upon @@ -635,12 +664,14 @@ static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload) list_for_each_entry_safe(bb, pos, &workload->shadow_bb, list) { if (bb->obj) { + i915_gem_object_lock(bb->obj, NULL); if (bb->va && !IS_ERR(bb->va)) i915_gem_object_unpin_map(bb->obj); if (bb->vma && !IS_ERR(bb->vma)) i915_vma_unpin(bb->vma); + i915_gem_object_unlock(bb->obj); i915_gem_object_put(bb->obj); } list_del(&bb->list); @@ -1015,13 +1046,12 @@ void intel_vgpu_clean_workloads(struct intel_vgpu *vgpu, intel_engine_mask_t engine_mask) { struct intel_vgpu_submission *s = &vgpu->submission; - struct drm_i915_private *dev_priv = vgpu->gvt->gt->i915; struct intel_engine_cs *engine; struct intel_vgpu_workload *pos, *n; intel_engine_mask_t tmp; /* free the unsubmited workloads in the queues. */ - for_each_engine_masked(engine, &dev_priv->gt, engine_mask, tmp) { + for_each_engine_masked(engine, vgpu->gvt->gt, engine_mask, tmp) { list_for_each_entry_safe(pos, n, &s->workload_q_head[engine->id], list) { list_del_init(&pos->list); diff --git a/drivers/gpu/drm/msm/adreno/a5xx.xml.h b/drivers/gpu/drm/msm/adreno/a5xx.xml.h index 346cc6ff3a36..7b9fcfe95c04 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx.xml.h +++ b/drivers/gpu/drm/msm/adreno/a5xx.xml.h @@ -2367,6 +2367,8 @@ static inline uint32_t A5XX_VSC_RESOLVE_CNTL_Y(uint32_t val) #define REG_A5XX_UCHE_ADDR_MODE_CNTL 0x00000e80 +#define REG_A5XX_UCHE_MODE_CNTL 0x00000e81 + #define REG_A5XX_UCHE_SVM_CNTL 0x00000e82 #define REG_A5XX_UCHE_WRITE_THRU_BASE_LO 0x00000e87 diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index a5af223eaf50..7e553d3efeb2 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -222,7 +222,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) a5xx_preempt_trigger(gpu); } -static const struct { +static const struct adreno_five_hwcg_regs { u32 offset; u32 value; } a5xx_hwcg[] = { @@ -318,16 +318,124 @@ static const struct { {REG_A5XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000}, {REG_A5XX_RBBM_CLOCK_DELAY_GPC, 0x00000200}, {REG_A5XX_RBBM_CLOCK_DELAY_VFD, 0x00002222} +}, a50x_hwcg[] = { + {REG_A5XX_RBBM_CLOCK_CNTL_SP0, 0x02222222}, + {REG_A5XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220}, + {REG_A5XX_RBBM_CLOCK_HYST_SP0, 0x0000F3CF}, + {REG_A5XX_RBBM_CLOCK_DELAY_SP0, 0x00000080}, + {REG_A5XX_RBBM_CLOCK_CNTL_TP0, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL3_TP0, 0x00002222}, + {REG_A5XX_RBBM_CLOCK_HYST_TP0, 0x77777777}, + {REG_A5XX_RBBM_CLOCK_HYST2_TP0, 0x77777777}, + {REG_A5XX_RBBM_CLOCK_HYST3_TP0, 0x00007777}, + {REG_A5XX_RBBM_CLOCK_DELAY_TP0, 0x11111111}, + {REG_A5XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111}, + {REG_A5XX_RBBM_CLOCK_DELAY3_TP0, 0x00001111}, + {REG_A5XX_RBBM_CLOCK_CNTL2_UCHE, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL3_UCHE, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL4_UCHE, 0x00222222}, + {REG_A5XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_HYST_UCHE, 0x00FFFFF4}, + {REG_A5XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002}, + {REG_A5XX_RBBM_CLOCK_CNTL_RB0, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL2_RB0, 0x00222222}, + {REG_A5XX_RBBM_CLOCK_CNTL_CCU0, 0x00022220}, + {REG_A5XX_RBBM_CLOCK_CNTL_RAC, 0x05522222}, + {REG_A5XX_RBBM_CLOCK_CNTL2_RAC, 0x00505555}, + {REG_A5XX_RBBM_CLOCK_HYST_RB_CCU0, 0x04040404}, + {REG_A5XX_RBBM_CLOCK_HYST_RAC, 0x07444044}, + {REG_A5XX_RBBM_CLOCK_DELAY_RB_CCU_L1_0, 0x00000002}, + {REG_A5XX_RBBM_CLOCK_DELAY_RAC, 0x00010011}, + {REG_A5XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222}, + {REG_A5XX_RBBM_CLOCK_MODE_GPC, 0x02222222}, + {REG_A5XX_RBBM_CLOCK_MODE_VFD, 0x00002222}, + {REG_A5XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000}, + {REG_A5XX_RBBM_CLOCK_HYST_GPC, 0x04104004}, + {REG_A5XX_RBBM_CLOCK_HYST_VFD, 0x00000000}, + {REG_A5XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000}, + {REG_A5XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000}, + {REG_A5XX_RBBM_CLOCK_DELAY_GPC, 0x00000200}, + {REG_A5XX_RBBM_CLOCK_DELAY_VFD, 0x00002222}, +}, a512_hwcg[] = { + {REG_A5XX_RBBM_CLOCK_CNTL_SP0, 0x02222222}, + {REG_A5XX_RBBM_CLOCK_CNTL_SP1, 0x02222222}, + {REG_A5XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220}, + {REG_A5XX_RBBM_CLOCK_CNTL2_SP1, 0x02222220}, + {REG_A5XX_RBBM_CLOCK_HYST_SP0, 0x0000F3CF}, + {REG_A5XX_RBBM_CLOCK_HYST_SP1, 0x0000F3CF}, + {REG_A5XX_RBBM_CLOCK_DELAY_SP0, 0x00000080}, + {REG_A5XX_RBBM_CLOCK_DELAY_SP1, 0x00000080}, + {REG_A5XX_RBBM_CLOCK_CNTL_TP0, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL_TP1, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL2_TP1, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL3_TP0, 0x00002222}, + {REG_A5XX_RBBM_CLOCK_CNTL3_TP1, 0x00002222}, + {REG_A5XX_RBBM_CLOCK_HYST_TP0, 0x77777777}, + {REG_A5XX_RBBM_CLOCK_HYST_TP1, 0x77777777}, + {REG_A5XX_RBBM_CLOCK_HYST2_TP0, 0x77777777}, + {REG_A5XX_RBBM_CLOCK_HYST2_TP1, 0x77777777}, + {REG_A5XX_RBBM_CLOCK_HYST3_TP0, 0x00007777}, + {REG_A5XX_RBBM_CLOCK_HYST3_TP1, 0x00007777}, + {REG_A5XX_RBBM_CLOCK_DELAY_TP0, 0x11111111}, + {REG_A5XX_RBBM_CLOCK_DELAY_TP1, 0x11111111}, + {REG_A5XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111}, + {REG_A5XX_RBBM_CLOCK_DELAY2_TP1, 0x11111111}, + {REG_A5XX_RBBM_CLOCK_DELAY3_TP0, 0x00001111}, + {REG_A5XX_RBBM_CLOCK_DELAY3_TP1, 0x00001111}, + {REG_A5XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL2_UCHE, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL3_UCHE, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL4_UCHE, 0x00222222}, + {REG_A5XX_RBBM_CLOCK_HYST_UCHE, 0x00444444}, + {REG_A5XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002}, + {REG_A5XX_RBBM_CLOCK_CNTL_RB0, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL_RB1, 0x22222222}, + {REG_A5XX_RBBM_CLOCK_CNTL2_RB0, 0x00222222}, + {REG_A5XX_RBBM_CLOCK_CNTL2_RB1, 0x00222222}, + {REG_A5XX_RBBM_CLOCK_CNTL_CCU0, 0x00022220}, + {REG_A5XX_RBBM_CLOCK_CNTL_CCU1, 0x00022220}, + {REG_A5XX_RBBM_CLOCK_CNTL_RAC, 0x05522222}, + {REG_A5XX_RBBM_CLOCK_CNTL2_RAC, 0x00505555}, + {REG_A5XX_RBBM_CLOCK_HYST_RB_CCU0, 0x04040404}, + {REG_A5XX_RBBM_CLOCK_HYST_RB_CCU1, 0x04040404}, + {REG_A5XX_RBBM_CLOCK_HYST_RAC, 0x07444044}, + {REG_A5XX_RBBM_CLOCK_DELAY_RB_CCU_L1_0, 0x00000002}, + {REG_A5XX_RBBM_CLOCK_DELAY_RB_CCU_L1_1, 0x00000002}, + {REG_A5XX_RBBM_CLOCK_DELAY_RAC, 0x00010011}, + {REG_A5XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222}, + {REG_A5XX_RBBM_CLOCK_MODE_GPC, 0x02222222}, + {REG_A5XX_RBBM_CLOCK_MODE_VFD, 0x00002222}, + {REG_A5XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000}, + {REG_A5XX_RBBM_CLOCK_HYST_GPC, 0x04104004}, + {REG_A5XX_RBBM_CLOCK_HYST_VFD, 0x00000000}, + {REG_A5XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000}, + {REG_A5XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000}, + {REG_A5XX_RBBM_CLOCK_DELAY_GPC, 0x00000200}, + {REG_A5XX_RBBM_CLOCK_DELAY_VFD, 0x00002222}, }; void a5xx_set_hwcg(struct msm_gpu *gpu, bool state) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); - unsigned int i; + const struct adreno_five_hwcg_regs *regs; + unsigned int i, sz; - for (i = 0; i < ARRAY_SIZE(a5xx_hwcg); i++) - gpu_write(gpu, a5xx_hwcg[i].offset, - state ? a5xx_hwcg[i].value : 0); + if (adreno_is_a508(adreno_gpu)) { + regs = a50x_hwcg; + sz = ARRAY_SIZE(a50x_hwcg); + } else if (adreno_is_a509(adreno_gpu) || adreno_is_a512(adreno_gpu)) { + regs = a512_hwcg; + sz = ARRAY_SIZE(a512_hwcg); + } else { + regs = a5xx_hwcg; + sz = ARRAY_SIZE(a5xx_hwcg); + } + + for (i = 0; i < sz; i++) + gpu_write(gpu, regs[i].offset, + state ? regs[i].value : 0); if (adreno_is_a540(adreno_gpu)) { gpu_write(gpu, REG_A5XX_RBBM_CLOCK_DELAY_GPMU, state ? 0x00000770 : 0); @@ -538,11 +646,13 @@ static int a5xx_hw_init(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); + u32 regbit; int ret; gpu_write(gpu, REG_A5XX_VBIF_ROUND_ROBIN_QOS_ARB, 0x00000003); - if (adreno_is_a540(adreno_gpu)) + if (adreno_is_a509(adreno_gpu) || adreno_is_a512(adreno_gpu) || + adreno_is_a540(adreno_gpu)) gpu_write(gpu, REG_A5XX_VBIF_GATE_OFF_WRREQ_EN, 0x00000009); /* Make all blocks contribute to the GPU BUSY perf counter */ @@ -604,29 +714,48 @@ static int a5xx_hw_init(struct msm_gpu *gpu) 0x00100000 + adreno_gpu->gmem - 1); gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MAX_HI, 0x00000000); - if (adreno_is_a510(adreno_gpu)) { + if (adreno_is_a508(adreno_gpu) || adreno_is_a510(adreno_gpu)) { gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x20); - gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x20); + if (adreno_is_a508(adreno_gpu)) + gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x400); + else + gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x20); gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x40000030); gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x20100D0A); - gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, - (0x200 << 11 | 0x200 << 22)); } else { gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x40); if (adreno_is_a530(adreno_gpu)) gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x40); - if (adreno_is_a540(adreno_gpu)) + else gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x400); gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x80000060); gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x40201B16); + } + + if (adreno_is_a508(adreno_gpu)) + gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, + (0x100 << 11 | 0x100 << 22)); + else if (adreno_is_a509(adreno_gpu) || adreno_is_a510(adreno_gpu) || + adreno_is_a512(adreno_gpu)) + gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, + (0x200 << 11 | 0x200 << 22)); + else gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, (0x400 << 11 | 0x300 << 22)); - } if (adreno_gpu->info->quirks & ADRENO_QUIRK_TWO_PASS_USE_WFI) gpu_rmw(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0, (1 << 8)); - gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0xc0200100); + /* + * Disable the RB sampler datapath DP2 clock gating optimization + * for 1-SP GPUs, as it is enabled by default. + */ + if (adreno_is_a508(adreno_gpu) || adreno_is_a509(adreno_gpu) || + adreno_is_a512(adreno_gpu)) + gpu_rmw(gpu, REG_A5XX_RB_DBG_ECO_CNTL, 0, (1 << 9)); + + /* Disable UCHE global filter as SP can invalidate/flush independently */ + gpu_write(gpu, REG_A5XX_UCHE_MODE_CNTL, BIT(29)); /* Enable USE_RETENTION_FLOPS */ gpu_write(gpu, REG_A5XX_CP_CHICKEN_DBG, 0x02000000); @@ -653,10 +782,20 @@ static int a5xx_hw_init(struct msm_gpu *gpu) gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL2, 0x0000003F); /* Set the highest bank bit */ - gpu_write(gpu, REG_A5XX_TPL1_MODE_CNTL, 2 << 7); - gpu_write(gpu, REG_A5XX_RB_MODE_CNTL, 2 << 1); if (adreno_is_a540(adreno_gpu)) - gpu_write(gpu, REG_A5XX_UCHE_DBG_ECO_CNTL_2, 2); + regbit = 2; + else + regbit = 1; + + gpu_write(gpu, REG_A5XX_TPL1_MODE_CNTL, regbit << 7); + gpu_write(gpu, REG_A5XX_RB_MODE_CNTL, regbit << 1); + + if (adreno_is_a509(adreno_gpu) || adreno_is_a512(adreno_gpu) || + adreno_is_a540(adreno_gpu)) + gpu_write(gpu, REG_A5XX_UCHE_DBG_ECO_CNTL_2, regbit); + + /* Disable All flat shading optimization (ALLFLATOPTDIS) */ + gpu_rmw(gpu, REG_A5XX_VPC_DBG_ECO_CNTL, 0, (1 << 10)); /* Protect registers from the CP */ gpu_write(gpu, REG_A5XX_CP_PROTECT_CNTL, 0x00000007); @@ -688,12 +827,14 @@ static int a5xx_hw_init(struct msm_gpu *gpu) /* VPC */ gpu_write(gpu, REG_A5XX_CP_PROTECT(14), ADRENO_PROTECT_RW(0xE68, 8)); - gpu_write(gpu, REG_A5XX_CP_PROTECT(15), ADRENO_PROTECT_RW(0xE70, 4)); + gpu_write(gpu, REG_A5XX_CP_PROTECT(15), ADRENO_PROTECT_RW(0xE70, 16)); /* UCHE */ gpu_write(gpu, REG_A5XX_CP_PROTECT(16), ADRENO_PROTECT_RW(0xE80, 16)); - if (adreno_is_a530(adreno_gpu) || adreno_is_a510(adreno_gpu)) + if (adreno_is_a508(adreno_gpu) || adreno_is_a509(adreno_gpu) || + adreno_is_a510(adreno_gpu) || adreno_is_a512(adreno_gpu) || + adreno_is_a530(adreno_gpu)) gpu_write(gpu, REG_A5XX_CP_PROTECT(17), ADRENO_PROTECT_RW(0x10000, 0x8000)); @@ -735,7 +876,8 @@ static int a5xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; - if (!adreno_is_a510(adreno_gpu)) + if (!(adreno_is_a508(adreno_gpu) || adreno_is_a509(adreno_gpu) || + adreno_is_a510(adreno_gpu) || adreno_is_a512(adreno_gpu))) a5xx_gpmu_ucode_init(gpu); ret = a5xx_ucode_init(gpu); @@ -1168,7 +1310,8 @@ static int a5xx_pm_resume(struct msm_gpu *gpu) if (ret) return ret; - if (adreno_is_a510(adreno_gpu)) { + /* Adreno 508, 509, 510, 512 needs manual RBBM sus/res control */ + if (!(adreno_is_a530(adreno_gpu) || adreno_is_a540(adreno_gpu))) { /* Halt the sp_input_clk at HM level */ gpu_write(gpu, REG_A5XX_RBBM_CLOCK_CNTL, 0x00000055); a5xx_set_hwcg(gpu, true); @@ -1210,8 +1353,8 @@ static int a5xx_pm_suspend(struct msm_gpu *gpu) u32 mask = 0xf; int i, ret; - /* A510 has 3 XIN ports in VBIF */ - if (adreno_is_a510(adreno_gpu)) + /* A508, A510 have 3 XIN ports in VBIF */ + if (adreno_is_a508(adreno_gpu) || adreno_is_a510(adreno_gpu)) mask = 0x7; /* Clear the VBIF pipe before shutting down */ @@ -1223,10 +1366,12 @@ static int a5xx_pm_suspend(struct msm_gpu *gpu) /* * Reset the VBIF before power collapse to avoid issue with FIFO - * entries + * entries on Adreno A510 and A530 (the others will tend to lock up) */ - gpu_write(gpu, REG_A5XX_RBBM_BLOCK_SW_RESET_CMD, 0x003C0000); - gpu_write(gpu, REG_A5XX_RBBM_BLOCK_SW_RESET_CMD, 0x00000000); + if (adreno_is_a510(adreno_gpu) || adreno_is_a530(adreno_gpu)) { + gpu_write(gpu, REG_A5XX_RBBM_BLOCK_SW_RESET_CMD, 0x003C0000); + gpu_write(gpu, REG_A5XX_RBBM_BLOCK_SW_RESET_CMD, 0x00000000); + } ret = msm_gpu_pm_suspend(gpu); if (ret) diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c index f176a6f3eff6..5ccc9da455a1 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_power.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c @@ -298,7 +298,7 @@ int a5xx_power_init(struct msm_gpu *gpu) int ret; /* Not all A5xx chips have a GPMU */ - if (adreno_is_a510(adreno_gpu)) + if (!(adreno_is_a530(adreno_gpu) || adreno_is_a540(adreno_gpu))) return 0; /* Set up the limits management */ @@ -330,7 +330,7 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu) unsigned int *data, *ptr, *cmds; unsigned int cmds_size; - if (adreno_is_a510(adreno_gpu)) + if (!(adreno_is_a530(adreno_gpu) || adreno_is_a540(adreno_gpu))) return; if (a5xx_gpu->gpmu_bo) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 05e0ef58fe32..71c917f909af 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -245,37 +245,66 @@ static int a6xx_gmu_hfi_start(struct a6xx_gmu *gmu) return ret; } +struct a6xx_gmu_oob_bits { + int set, ack, set_new, ack_new; + const char *name; +}; + +/* These are the interrupt / ack bits for each OOB request that are set + * in a6xx_gmu_set_oob and a6xx_clear_oob + */ +static const struct a6xx_gmu_oob_bits a6xx_gmu_oob_bits[] = { + [GMU_OOB_GPU_SET] = { + .name = "GPU_SET", + .set = 16, + .ack = 24, + .set_new = 30, + .ack_new = 31, + }, + + [GMU_OOB_PERFCOUNTER_SET] = { + .name = "PERFCOUNTER", + .set = 17, + .ack = 25, + .set_new = 28, + .ack_new = 30, + }, + + [GMU_OOB_BOOT_SLUMBER] = { + .name = "BOOT_SLUMBER", + .set = 22, + .ack = 30, + }, + + [GMU_OOB_DCVS_SET] = { + .name = "GPU_DCVS", + .set = 23, + .ack = 31, + }, +}; + /* Trigger a OOB (out of band) request to the GMU */ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) { int ret; u32 val; int request, ack; - const char *name; - switch (state) { - case GMU_OOB_GPU_SET: - if (gmu->legacy) { - request = GMU_OOB_GPU_SET_REQUEST; - ack = GMU_OOB_GPU_SET_ACK; - } else { - request = GMU_OOB_GPU_SET_REQUEST_NEW; - ack = GMU_OOB_GPU_SET_ACK_NEW; - } - name = "GPU_SET"; - break; - case GMU_OOB_BOOT_SLUMBER: - request = GMU_OOB_BOOT_SLUMBER_REQUEST; - ack = GMU_OOB_BOOT_SLUMBER_ACK; - name = "BOOT_SLUMBER"; - break; - case GMU_OOB_DCVS_SET: - request = GMU_OOB_DCVS_REQUEST; - ack = GMU_OOB_DCVS_ACK; - name = "GPU_DCVS"; - break; - default: + if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits)) return -EINVAL; + + if (gmu->legacy) { + request = a6xx_gmu_oob_bits[state].set; + ack = a6xx_gmu_oob_bits[state].ack; + } else { + request = a6xx_gmu_oob_bits[state].set_new; + ack = a6xx_gmu_oob_bits[state].ack_new; + if (!request || !ack) { + DRM_DEV_ERROR(gmu->dev, + "Invalid non-legacy GMU request %s\n", + a6xx_gmu_oob_bits[state].name); + return -EINVAL; + } } /* Trigger the equested OOB operation */ @@ -288,7 +317,7 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) if (ret) DRM_DEV_ERROR(gmu->dev, "Timeout waiting for GMU OOB set %s: 0x%x\n", - name, + a6xx_gmu_oob_bits[state].name, gmu_read(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO)); /* Clear the acknowledge interrupt */ @@ -300,27 +329,17 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) /* Clear a pending OOB state in the GMU */ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) { - if (!gmu->legacy) { - WARN_ON(state != GMU_OOB_GPU_SET); - gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, - 1 << GMU_OOB_GPU_SET_CLEAR_NEW); - return; - } + int bit; - switch (state) { - case GMU_OOB_GPU_SET: - gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, - 1 << GMU_OOB_GPU_SET_CLEAR); - break; - case GMU_OOB_BOOT_SLUMBER: - gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, - 1 << GMU_OOB_BOOT_SLUMBER_CLEAR); - break; - case GMU_OOB_DCVS_SET: - gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, - 1 << GMU_OOB_DCVS_CLEAR); - break; - } + if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits)) + return; + + if (gmu->legacy) + bit = a6xx_gmu_oob_bits[state].ack; + else + bit = a6xx_gmu_oob_bits[state].ack_new; + + gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, bit); } /* Enable CPU control of SPTP power power collapse */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h index c6d2bced8e5d..71dfa60070cc 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h @@ -153,44 +153,27 @@ static inline void gmu_write_rscc(struct a6xx_gmu *gmu, u32 offset, u32 value) */ enum a6xx_gmu_oob_state { + /* + * Let the GMU know that a boot or slumber operation has started. The value in + * REG_A6XX_GMU_BOOT_SLUMBER_OPTION lets the GMU know which operation we are + * doing + */ GMU_OOB_BOOT_SLUMBER = 0, + /* + * Let the GMU know to not turn off any GPU registers while the CPU is in a + * critical section + */ GMU_OOB_GPU_SET, + /* + * Set a new power level for the GPU when the CPU is doing frequency scaling + */ GMU_OOB_DCVS_SET, + /* + * Used to keep the GPU on for CPU-side reads of performance counters. + */ + GMU_OOB_PERFCOUNTER_SET, }; -/* These are the interrupt / ack bits for each OOB request that are set - * in a6xx_gmu_set_oob and a6xx_clear_oob - */ - -/* - * Let the GMU know that a boot or slumber operation has started. The value in - * REG_A6XX_GMU_BOOT_SLUMBER_OPTION lets the GMU know which operation we are - * doing - */ -#define GMU_OOB_BOOT_SLUMBER_REQUEST 22 -#define GMU_OOB_BOOT_SLUMBER_ACK 30 -#define GMU_OOB_BOOT_SLUMBER_CLEAR 30 - -/* - * Set a new power level for the GPU when the CPU is doing frequency scaling - */ -#define GMU_OOB_DCVS_REQUEST 23 -#define GMU_OOB_DCVS_ACK 31 -#define GMU_OOB_DCVS_CLEAR 31 - -/* - * Let the GMU know to not turn off any GPU registers while the CPU is in a - * critical section - */ -#define GMU_OOB_GPU_SET_REQUEST 16 -#define GMU_OOB_GPU_SET_ACK 24 -#define GMU_OOB_GPU_SET_CLEAR 24 - -#define GMU_OOB_GPU_SET_REQUEST_NEW 30 -#define GMU_OOB_GPU_SET_ACK_NEW 31 -#define GMU_OOB_GPU_SET_CLEAR_NEW 31 - - void a6xx_hfi_init(struct a6xx_gmu *gmu); int a6xx_hfi_start(struct a6xx_gmu *gmu, int boot_state); void a6xx_hfi_stop(struct a6xx_gmu *gmu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 130661898546..ba8e9d3cf0fe 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -10,6 +10,7 @@ #include #include +#include #include #define GPU_PAS_ID 13 @@ -1117,7 +1118,7 @@ static void a6xx_llc_slices_init(struct platform_device *pdev, a6xx_gpu->llc_slice = llcc_slice_getd(LLCC_GPU); a6xx_gpu->htw_llc_slice = llcc_slice_getd(LLCC_GPUHTW); - if (IS_ERR(a6xx_gpu->llc_slice) && IS_ERR(a6xx_gpu->htw_llc_slice)) + if (IS_ERR_OR_NULL(a6xx_gpu->llc_slice) && IS_ERR_OR_NULL(a6xx_gpu->htw_llc_slice)) a6xx_gpu->llc_mmio = ERR_PTR(-EINVAL); } @@ -1169,14 +1170,18 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + static DEFINE_MUTEX(perfcounter_oob); + + mutex_lock(&perfcounter_oob); /* Force the GPU power on so we can read this register */ - a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); *value = gpu_read64(gpu, REG_A6XX_RBBM_PERFCTR_CP_0_LO, REG_A6XX_RBBM_PERFCTR_CP_0_HI); - a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); + mutex_unlock(&perfcounter_oob); return 0; } @@ -1208,6 +1213,10 @@ static void a6xx_destroy(struct msm_gpu *gpu) a6xx_gmu_remove(a6xx_gpu); adreno_gpu_cleanup(adreno_gpu); + + if (a6xx_gpu->opp_table) + dev_pm_opp_put_supported_hw(a6xx_gpu->opp_table); + kfree(a6xx_gpu); } @@ -1239,6 +1248,50 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu) return (unsigned long)busy_time; } +static struct msm_gem_address_space * +a6xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct iommu_domain *iommu; + struct msm_mmu *mmu; + struct msm_gem_address_space *aspace; + u64 start, size; + + iommu = iommu_domain_alloc(&platform_bus_type); + if (!iommu) + return NULL; + + /* + * This allows GPU to set the bus attributes required to use system + * cache on behalf of the iommu page table walker. + */ + if (!IS_ERR_OR_NULL(a6xx_gpu->htw_llc_slice)) + adreno_set_llc_attributes(iommu); + + mmu = msm_iommu_new(&pdev->dev, iommu); + if (IS_ERR(mmu)) { + iommu_domain_free(iommu); + return ERR_CAST(mmu); + } + + /* + * Use the aperture start or SZ_16M, whichever is greater. This will + * ensure that we align with the allocated pagetable range while still + * allowing room in the lower 32 bits for GMEM and whatnot + */ + start = max_t(u64, SZ_16M, iommu->geometry.aperture_start); + size = iommu->geometry.aperture_end - start + 1; + + aspace = msm_gem_address_space_create(mmu, "gpu", + start & GENMASK_ULL(48, 0), size); + + if (IS_ERR(aspace) && !IS_ERR(mmu)) + mmu->funcs->destroy(mmu); + + return aspace; +} + static struct msm_gem_address_space * a6xx_create_private_address_space(struct msm_gpu *gpu) { @@ -1264,6 +1317,78 @@ static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return ring->memptrs->rptr = gpu_read(gpu, REG_A6XX_CP_RB_RPTR); } +static u32 a618_get_speed_bin(u32 fuse) +{ + if (fuse == 0) + return 0; + else if (fuse == 169) + return 1; + else if (fuse == 174) + return 2; + + return UINT_MAX; +} + +static u32 fuse_to_supp_hw(struct device *dev, u32 revn, u32 fuse) +{ + u32 val = UINT_MAX; + + if (revn == 618) + val = a618_get_speed_bin(fuse); + + if (val == UINT_MAX) { + DRM_DEV_ERROR(dev, + "missing support for speed-bin: %u. Some OPPs may not be supported by hardware", + fuse); + return UINT_MAX; + } + + return (1 << val); +} + +static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu, + u32 revn) +{ + struct opp_table *opp_table; + struct nvmem_cell *cell; + u32 supp_hw = UINT_MAX; + void *buf; + + cell = nvmem_cell_get(dev, "speed_bin"); + /* + * -ENOENT means that the platform doesn't support speedbin which is + * fine + */ + if (PTR_ERR(cell) == -ENOENT) + return 0; + else if (IS_ERR(cell)) { + DRM_DEV_ERROR(dev, + "failed to read speed-bin. Some OPPs may not be supported by hardware"); + goto done; + } + + buf = nvmem_cell_read(cell, NULL); + if (IS_ERR(buf)) { + nvmem_cell_put(cell); + DRM_DEV_ERROR(dev, + "failed to read speed-bin. Some OPPs may not be supported by hardware"); + goto done; + } + + supp_hw = fuse_to_supp_hw(dev, revn, *((u32 *) buf)); + + kfree(buf); + nvmem_cell_put(cell); + +done: + opp_table = dev_pm_opp_set_supported_hw(dev, &supp_hw, 1); + if (IS_ERR(opp_table)) + return PTR_ERR(opp_table); + + a6xx_gpu->opp_table = opp_table; + return 0; +} + static const struct adreno_gpu_funcs funcs = { .base = { .get_param = adreno_get_param, @@ -1285,7 +1410,7 @@ static const struct adreno_gpu_funcs funcs = { .gpu_state_get = a6xx_gpu_state_get, .gpu_state_put = a6xx_gpu_state_put, #endif - .create_address_space = adreno_iommu_create_address_space, + .create_address_space = a6xx_create_address_space, .create_private_address_space = a6xx_create_private_address_space, .get_rptr = a6xx_get_rptr, }, @@ -1325,6 +1450,12 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) a6xx_llc_slices_init(pdev, a6xx_gpu); + ret = a6xx_set_supported_hw(&pdev->dev, a6xx_gpu, info->revn); + if (ret) { + a6xx_destroy(&(a6xx_gpu->base.base)); + return ERR_PTR(ret); + } + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) { a6xx_destroy(&(a6xx_gpu->base.base)); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index e793d329e77b..ce0610c5256f 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -33,6 +33,8 @@ struct a6xx_gpu { void *llc_slice; void *htw_llc_slice; bool have_mmu500; + + struct opp_table *opp_table; }; #define to_a6xx_gpu(x) container_of(x, struct a6xx_gpu, base) diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 12e75ba360f9..600d445fabe8 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -133,6 +133,41 @@ static const struct adreno_info gpulist[] = { .gmem = (SZ_1M + SZ_512K), .inactive_period = DRM_MSM_INACTIVE_PERIOD, .init = a4xx_gpu_init, + }, { + .rev = ADRENO_REV(5, 0, 8, ANY_ID), + .revn = 508, + .name = "A508", + .fw = { + [ADRENO_FW_PM4] = "a530_pm4.fw", + [ADRENO_FW_PFP] = "a530_pfp.fw", + }, + .gmem = (SZ_128K + SZ_8K), + /* + * Increase inactive period to 250 to avoid bouncing + * the GDSC which appears to make it grumpy + */ + .inactive_period = 250, + .quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE, + .init = a5xx_gpu_init, + .zapfw = "a508_zap.mdt", + }, { + .rev = ADRENO_REV(5, 0, 9, ANY_ID), + .revn = 509, + .name = "A509", + .fw = { + [ADRENO_FW_PM4] = "a530_pm4.fw", + [ADRENO_FW_PFP] = "a530_pfp.fw", + }, + .gmem = (SZ_256K + SZ_16K), + /* + * Increase inactive period to 250 to avoid bouncing + * the GDSC which appears to make it grumpy + */ + .inactive_period = 250, + .quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE, + .init = a5xx_gpu_init, + /* Adreno 509 uses the same ZAP as 512 */ + .zapfw = "a512_zap.mdt", }, { .rev = ADRENO_REV(5, 1, 0, ANY_ID), .revn = 510, @@ -148,6 +183,23 @@ static const struct adreno_info gpulist[] = { */ .inactive_period = 250, .init = a5xx_gpu_init, + }, { + .rev = ADRENO_REV(5, 1, 2, ANY_ID), + .revn = 512, + .name = "A512", + .fw = { + [ADRENO_FW_PM4] = "a530_pm4.fw", + [ADRENO_FW_PFP] = "a530_pfp.fw", + }, + .gmem = (SZ_256K + SZ_16K), + /* + * Increase inactive period to 250 to avoid bouncing + * the GDSC which appears to make it grumpy + */ + .inactive_period = 250, + .quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE, + .init = a5xx_gpu_init, + .zapfw = "a512_zap.mdt", }, { .rev = ADRENO_REV(5, 3, 0, 2), .revn = 530, @@ -168,7 +220,7 @@ static const struct adreno_info gpulist[] = { .init = a5xx_gpu_init, .zapfw = "a530_zap.mdt", }, { - .rev = ADRENO_REV(5, 4, 0, 2), + .rev = ADRENO_REV(5, 4, 0, ANY_ID), .revn = 540, .name = "A540", .fw = { diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index f09175698827..0f184c3dd9d9 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -186,11 +186,18 @@ int adreno_zap_shader_load(struct msm_gpu *gpu, u32 pasid) return zap_shader_load_mdt(gpu, adreno_gpu->info->zapfw, pasid); } +void adreno_set_llc_attributes(struct iommu_domain *iommu) +{ + struct io_pgtable_domain_attr pgtbl_cfg; + + pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_ARM_OUTER_WBWA; + iommu_domain_set_attr(iommu, DOMAIN_ATTR_IO_PGTABLE_CFG, &pgtbl_cfg); +} + struct msm_gem_address_space * adreno_iommu_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev) { - struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct iommu_domain *iommu; struct msm_mmu *mmu; struct msm_gem_address_space *aspace; @@ -200,20 +207,6 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu, if (!iommu) return NULL; - - if (adreno_is_a6xx(adreno_gpu)) { - struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); - struct io_pgtable_domain_attr pgtbl_cfg; - /* - * This allows GPU to set the bus attributes required to use system - * cache on behalf of the iommu page table walker. - */ - if (!IS_ERR(a6xx_gpu->htw_llc_slice)) { - pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_ARM_OUTER_WBWA; - iommu_domain_set_attr(iommu, DOMAIN_ATTR_IO_PGTABLE_CFG, &pgtbl_cfg); - } - } - mmu = msm_iommu_new(&pdev->dev, iommu); if (IS_ERR(mmu)) { iommu_domain_free(iommu); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index b3d9a333591b..ccac275aa7a2 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -197,11 +197,26 @@ static inline int adreno_is_a430(struct adreno_gpu *gpu) return gpu->revn == 430; } +static inline int adreno_is_a508(struct adreno_gpu *gpu) +{ + return gpu->revn == 508; +} + +static inline int adreno_is_a509(struct adreno_gpu *gpu) +{ + return gpu->revn == 509; +} + static inline int adreno_is_a510(struct adreno_gpu *gpu) { return gpu->revn == 510; } +static inline int adreno_is_a512(struct adreno_gpu *gpu) +{ + return gpu->revn == 512; +} + static inline int adreno_is_a530(struct adreno_gpu *gpu) { return gpu->revn == 530; @@ -212,11 +227,6 @@ static inline int adreno_is_a540(struct adreno_gpu *gpu) return gpu->revn == 540; } -static inline bool adreno_is_a6xx(struct adreno_gpu *gpu) -{ - return ((gpu->revn < 700 && gpu->revn > 599)); -} - static inline int adreno_is_a618(struct adreno_gpu *gpu) { return gpu->revn == 618; @@ -278,6 +288,8 @@ struct msm_gem_address_space * adreno_iommu_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev); +void adreno_set_llc_attributes(struct iommu_domain *iommu); + /* * For a5xx and a6xx targets load the zap shader that is used to pull the GPU * out of secure mode diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c index 5a056c1191df..b2be39b9144e 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c @@ -4,8 +4,10 @@ */ #define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ +#include #include "dpu_encoder_phys.h" #include "dpu_hw_interrupts.h" +#include "dpu_hw_pingpong.h" #include "dpu_core_irq.h" #include "dpu_formats.h" #include "dpu_trace.h" @@ -35,6 +37,8 @@ #define DPU_ENC_WR_PTR_START_TIMEOUT_US 20000 +#define DPU_ENC_MAX_POLL_TIMEOUT_US 2000 + static bool dpu_encoder_phys_cmd_is_master(struct dpu_encoder_phys *phys_enc) { return (phys_enc->split_role != ENC_ROLE_SLAVE) ? true : false; @@ -368,15 +372,12 @@ static void dpu_encoder_phys_cmd_tearcheck_config( tc_cfg.vsync_count = vsync_hz / (mode->vtotal * drm_mode_vrefresh(mode)); - /* enable external TE after kickoff to avoid premature autorefresh */ - tc_cfg.hw_vsync_mode = 0; - /* - * By setting sync_cfg_height to near max register value, we essentially - * disable dpu hw generated TE signal, since hw TE will arrive first. - * Only caveat is if due to error, we hit wrap-around. + * Set the sync_cfg_height to twice vtotal so that if we lose a + * TE event coming from the display TE pin we won't stall immediately */ - tc_cfg.sync_cfg_height = 0xFFF0; + tc_cfg.hw_vsync_mode = 1; + tc_cfg.sync_cfg_height = mode->vtotal * 2; tc_cfg.vsync_init_val = mode->vdisplay; tc_cfg.sync_threshold_start = DEFAULT_TEARCHECK_SYNC_THRESH_START; tc_cfg.sync_threshold_continue = DEFAULT_TEARCHECK_SYNC_THRESH_CONTINUE; @@ -580,6 +581,69 @@ static void dpu_encoder_phys_cmd_prepare_for_kickoff( atomic_read(&phys_enc->pending_kickoff_cnt)); } +static bool dpu_encoder_phys_cmd_is_ongoing_pptx( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_hw_pp_vsync_info info; + + if (!phys_enc) + return false; + + phys_enc->hw_pp->ops.get_vsync_info(phys_enc->hw_pp, &info); + if (info.wr_ptr_line_count > 0 && + info.wr_ptr_line_count < phys_enc->cached_mode.vdisplay) + return true; + + return false; +} + +static void dpu_encoder_phys_cmd_prepare_commit( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_cmd *cmd_enc = + to_dpu_encoder_phys_cmd(phys_enc); + int trial = 0; + + if (!phys_enc) + return; + if (!phys_enc->hw_pp) + return; + if (!dpu_encoder_phys_cmd_is_master(phys_enc)) + return; + + /* If autorefresh is already disabled, we have nothing to do */ + if (!phys_enc->hw_pp->ops.get_autorefresh(phys_enc->hw_pp, NULL)) + return; + + /* + * If autorefresh is enabled, disable it and make sure it is safe to + * proceed with current frame commit/push. Sequence fallowed is, + * 1. Disable TE + * 2. Disable autorefresh config + * 4. Poll for frame transfer ongoing to be false + * 5. Enable TE back + */ + _dpu_encoder_phys_cmd_connect_te(phys_enc, false); + phys_enc->hw_pp->ops.setup_autorefresh(phys_enc->hw_pp, 0, false); + + do { + udelay(DPU_ENC_MAX_POLL_TIMEOUT_US); + if ((trial * DPU_ENC_MAX_POLL_TIMEOUT_US) + > (KICKOFF_TIMEOUT_MS * USEC_PER_MSEC)) { + DPU_ERROR_CMDENC(cmd_enc, + "disable autorefresh failed\n"); + break; + } + + trial++; + } while (dpu_encoder_phys_cmd_is_ongoing_pptx(phys_enc)); + + _dpu_encoder_phys_cmd_connect_te(phys_enc, true); + + DPU_DEBUG_CMDENC(to_dpu_encoder_phys_cmd(phys_enc), + "disabled autorefresh\n"); +} + static int _dpu_encoder_phys_cmd_wait_for_ctl_start( struct dpu_encoder_phys *phys_enc) { @@ -621,20 +685,15 @@ static int dpu_encoder_phys_cmd_wait_for_tx_complete( static int dpu_encoder_phys_cmd_wait_for_commit_done( struct dpu_encoder_phys *phys_enc) { - int rc = 0; struct dpu_encoder_phys_cmd *cmd_enc; cmd_enc = to_dpu_encoder_phys_cmd(phys_enc); /* only required for master controller */ - if (dpu_encoder_phys_cmd_is_master(phys_enc)) - rc = _dpu_encoder_phys_cmd_wait_for_ctl_start(phys_enc); + if (!dpu_encoder_phys_cmd_is_master(phys_enc)) + return 0; - /* required for both controllers */ - if (!rc && cmd_enc->serialize_wait4pp) - dpu_encoder_phys_cmd_prepare_for_kickoff(phys_enc); - - return rc; + return _dpu_encoder_phys_cmd_wait_for_ctl_start(phys_enc); } static int dpu_encoder_phys_cmd_wait_for_vblank( @@ -681,6 +740,7 @@ static void dpu_encoder_phys_cmd_trigger_start( static void dpu_encoder_phys_cmd_init_ops( struct dpu_encoder_phys_ops *ops) { + ops->prepare_commit = dpu_encoder_phys_cmd_prepare_commit; ops->is_master = dpu_encoder_phys_cmd_is_master; ops->mode_set = dpu_encoder_phys_cmd_mode_set; ops->mode_fixup = dpu_encoder_phys_cmd_mode_fixup; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 90393fe9e59c..189f3533525c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -12,14 +12,17 @@ #define VIG_MASK \ (BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) |\ - BIT(DPU_SSPP_CSC_10BIT) | BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_QOS_8LVL) |\ + BIT(DPU_SSPP_CSC_10BIT) | BIT(DPU_SSPP_CDP) |\ BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_EXCL_RECT)) #define VIG_SDM845_MASK \ - (VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED3)) + (VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED3)) #define VIG_SC7180_MASK \ - (VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED4)) + (VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED4)) + +#define VIG_SM8250_MASK \ + (VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED3LITE)) #define DMA_SDM845_MASK \ (BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) | BIT(DPU_SSPP_QOS_8LVL) |\ @@ -185,7 +188,7 @@ static const struct dpu_caps sm8150_dpu_caps = { static const struct dpu_caps sm8250_dpu_caps = { .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .max_mixer_blendstages = 0xb, - .qseed_type = DPU_SSPP_SCALER_QSEED3, /* TODO: qseed3 lite */ + .qseed_type = DPU_SSPP_SCALER_QSEED3LITE, .smart_dma_rev = DPU_SSPP_SMART_DMA_V2, /* TODO: v2.5 */ .ubwc_version = DPU_HW_UBWC_VER_40, .has_src_split = true, @@ -444,6 +447,34 @@ static const struct dpu_sspp_cfg sc7180_sspp[] = { sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), }; +static const struct dpu_sspp_sub_blks sm8250_vig_sblk_0 = + _VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED3LITE); +static const struct dpu_sspp_sub_blks sm8250_vig_sblk_1 = + _VIG_SBLK("1", 6, DPU_SSPP_SCALER_QSEED3LITE); +static const struct dpu_sspp_sub_blks sm8250_vig_sblk_2 = + _VIG_SBLK("2", 7, DPU_SSPP_SCALER_QSEED3LITE); +static const struct dpu_sspp_sub_blks sm8250_vig_sblk_3 = + _VIG_SBLK("3", 8, DPU_SSPP_SCALER_QSEED3LITE); + +static const struct dpu_sspp_cfg sm8250_sspp[] = { + SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SM8250_MASK, + sm8250_vig_sblk_0, 0, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0), + SSPP_BLK("sspp_1", SSPP_VIG1, 0x6000, VIG_SM8250_MASK, + sm8250_vig_sblk_1, 4, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG1), + SSPP_BLK("sspp_2", SSPP_VIG2, 0x8000, VIG_SM8250_MASK, + sm8250_vig_sblk_2, 8, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG2), + SSPP_BLK("sspp_3", SSPP_VIG3, 0xa000, VIG_SM8250_MASK, + sm8250_vig_sblk_3, 12, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG3), + SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000, DMA_SDM845_MASK, + sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0), + SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000, DMA_SDM845_MASK, + sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1), + SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000, DMA_CURSOR_SDM845_MASK, + sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0), + SSPP_BLK("sspp_11", SSPP_DMA3, 0x2a000, DMA_CURSOR_SDM845_MASK, + sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), +}; + /************************************************************* * MIXER sub blocks config *************************************************************/ @@ -532,23 +563,28 @@ static const struct dpu_dspp_sub_blks sm8150_dspp_sblk = { .len = 0x90, .version = 0x40000}, }; -#define DSPP_BLK(_name, _id, _base, _sblk) \ +#define DSPP_BLK(_name, _id, _base, _mask, _sblk) \ {\ .name = _name, .id = _id, \ .base = _base, .len = 0x1800, \ - .features = DSPP_SC7180_MASK, \ + .features = _mask, \ .sblk = _sblk \ } static const struct dpu_dspp_cfg sc7180_dspp[] = { - DSPP_BLK("dspp_0", DSPP_0, 0x54000, &sc7180_dspp_sblk), + DSPP_BLK("dspp_0", DSPP_0, 0x54000, DSPP_SC7180_MASK, + &sc7180_dspp_sblk), }; static const struct dpu_dspp_cfg sm8150_dspp[] = { - DSPP_BLK("dspp_0", DSPP_0, 0x54000, &sm8150_dspp_sblk), - DSPP_BLK("dspp_1", DSPP_1, 0x56000, &sm8150_dspp_sblk), - DSPP_BLK("dspp_2", DSPP_2, 0x58000, &sm8150_dspp_sblk), - DSPP_BLK("dspp_3", DSPP_3, 0x5a000, &sm8150_dspp_sblk), + DSPP_BLK("dspp_0", DSPP_0, 0x54000, DSPP_SC7180_MASK, + &sm8150_dspp_sblk), + DSPP_BLK("dspp_1", DSPP_1, 0x56000, DSPP_SC7180_MASK, + &sm8150_dspp_sblk), + DSPP_BLK("dspp_2", DSPP_2, 0x58000, DSPP_SC7180_MASK, + &sm8150_dspp_sblk), + DSPP_BLK("dspp_3", DSPP_3, 0x5a000, DSPP_SC7180_MASK, + &sm8150_dspp_sblk), }; /************************************************************* @@ -624,33 +660,33 @@ static const struct dpu_merge_3d_cfg sm8150_merge_3d[] = { /************************************************************* * INTF sub blocks config *************************************************************/ -#define INTF_BLK(_name, _id, _base, _type, _ctrl_id, _features) \ +#define INTF_BLK(_name, _id, _base, _type, _ctrl_id, _progfetch, _features) \ {\ .name = _name, .id = _id, \ .base = _base, .len = 0x280, \ .features = _features, \ .type = _type, \ .controller_id = _ctrl_id, \ - .prog_fetch_lines_worst_case = 24 \ + .prog_fetch_lines_worst_case = _progfetch \ } static const struct dpu_intf_cfg sdm845_intf[] = { - INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, INTF_SDM845_MASK), - INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, INTF_SDM845_MASK), - INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, INTF_SDM845_MASK), - INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1, INTF_SDM845_MASK), + INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, 24, INTF_SDM845_MASK), + INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SDM845_MASK), + INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, 24, INTF_SDM845_MASK), + INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1, 24, INTF_SDM845_MASK), }; static const struct dpu_intf_cfg sc7180_intf[] = { - INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, INTF_SC7180_MASK), - INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, INTF_SC7180_MASK), + INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, 24, INTF_SC7180_MASK), + INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SC7180_MASK), }; static const struct dpu_intf_cfg sm8150_intf[] = { - INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, INTF_SC7180_MASK), - INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, INTF_SC7180_MASK), - INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, INTF_SC7180_MASK), - INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1, INTF_SC7180_MASK), + INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, 24, INTF_SC7180_MASK), + INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SC7180_MASK), + INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, 24, INTF_SC7180_MASK), + INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1, 24, INTF_SC7180_MASK), }; /************************************************************* @@ -969,9 +1005,8 @@ static void sm8250_cfg_init(struct dpu_mdss_cfg *dpu_cfg) .mdp = sm8250_mdp, .ctl_count = ARRAY_SIZE(sm8150_ctl), .ctl = sm8150_ctl, - /* TODO: sspp qseed version differs from 845 */ - .sspp_count = ARRAY_SIZE(sdm845_sspp), - .sspp = sdm845_sspp, + .sspp_count = ARRAY_SIZE(sm8250_sspp), + .sspp = sm8250_sspp, .mixer_count = ARRAY_SIZE(sm8150_lm), .mixer = sm8150_lm, .dspp_count = ARRAY_SIZE(sm8150_dspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h index eaef99db2d2f..ea4647d21a20 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -95,6 +95,7 @@ enum { * @DPU_SSPP_SRC Src and fetch part of the pipes, * @DPU_SSPP_SCALER_QSEED2, QSEED2 algorithm support * @DPU_SSPP_SCALER_QSEED3, QSEED3 alogorithm support + * @DPU_SSPP_SCALER_QSEED3LITE, QSEED3 Lite alogorithm support * @DPU_SSPP_SCALER_QSEED4, QSEED4 algorithm support * @DPU_SSPP_SCALER_RGB, RGB Scaler, supported by RGB pipes * @DPU_SSPP_CSC, Support of Color space converion @@ -114,6 +115,7 @@ enum { DPU_SSPP_SRC = 0x1, DPU_SSPP_SCALER_QSEED2, DPU_SSPP_SCALER_QSEED3, + DPU_SSPP_SCALER_QSEED3LITE, DPU_SSPP_SCALER_QSEED4, DPU_SSPP_SCALER_RGB, DPU_SSPP_CSC, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c index bea4ab5c58c5..245a7a62b5c6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c @@ -23,6 +23,7 @@ #define PP_WR_PTR_IRQ 0x024 #define PP_OUT_LINE_COUNT 0x028 #define PP_LINE_COUNT 0x02C +#define PP_AUTOREFRESH_CONFIG 0x030 #define PP_FBC_MODE 0x034 #define PP_FBC_BUDGET_CTL 0x038 @@ -120,6 +121,29 @@ static int dpu_hw_pp_setup_te_config(struct dpu_hw_pingpong *pp, return 0; } +static void dpu_hw_pp_setup_autorefresh_config(struct dpu_hw_pingpong *pp, + u32 frame_count, bool enable) +{ + DPU_REG_WRITE(&pp->hw, PP_AUTOREFRESH_CONFIG, + enable ? (BIT(31) | frame_count) : 0); +} + +/* + * dpu_hw_pp_get_autorefresh_config - Get autorefresh config from HW + * @pp: DPU pingpong structure + * @frame_count: Used to return the current frame count from hw + * + * Returns: True if autorefresh enabled, false if disabled. + */ +static bool dpu_hw_pp_get_autorefresh_config(struct dpu_hw_pingpong *pp, + u32 *frame_count) +{ + u32 val = DPU_REG_READ(&pp->hw, PP_AUTOREFRESH_CONFIG); + if (frame_count != NULL) + *frame_count = val & 0xffff; + return !!((val & BIT(31)) >> 31); +} + static int dpu_hw_pp_poll_timeout_wr_ptr(struct dpu_hw_pingpong *pp, u32 timeout_us) { @@ -228,6 +252,8 @@ static void _setup_pingpong_ops(struct dpu_hw_pingpong *c, c->ops.enable_tearcheck = dpu_hw_pp_enable_te; c->ops.connect_external_te = dpu_hw_pp_connect_external_te; c->ops.get_vsync_info = dpu_hw_pp_get_vsync_info; + c->ops.setup_autorefresh = dpu_hw_pp_setup_autorefresh_config; + c->ops.get_autorefresh = dpu_hw_pp_get_autorefresh_config; c->ops.poll_timeout_wr_ptr = dpu_hw_pp_poll_timeout_wr_ptr; c->ops.get_line_count = dpu_hw_pp_get_line_count; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h index 6902b9b95c8e..845b9ce80e31 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h @@ -63,6 +63,8 @@ struct dpu_hw_dither_cfg { * @setup_tearcheck : program tear check values * @enable_tearcheck : enables tear check * @get_vsync_info : retries timing info of the panel + * @setup_autorefresh : configure and enable the autorefresh config + * @get_autorefresh : retrieve autorefresh config from hardware * @setup_dither : function to program the dither hw block * @get_line_count: obtain current vertical line counter */ @@ -94,6 +96,18 @@ struct dpu_hw_pingpong_ops { int (*get_vsync_info)(struct dpu_hw_pingpong *pp, struct dpu_hw_pp_vsync_info *info); + /** + * configure and enable the autorefresh config + */ + void (*setup_autorefresh)(struct dpu_hw_pingpong *pp, + u32 frame_count, bool enable); + + /** + * retrieve autorefresh config from hardware + */ + bool (*get_autorefresh)(struct dpu_hw_pingpong *pp, + u32 *frame_count); + /** * poll until write pointer transmission starts * @Return: 0 on success, -ETIMEDOUT on timeout diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c index 2c2ca5335aa8..34d81aa16041 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c @@ -673,6 +673,7 @@ static void _setup_layer_ops(struct dpu_hw_pipe *c, c->ops.setup_multirect = dpu_hw_sspp_setup_multirect; if (test_bit(DPU_SSPP_SCALER_QSEED3, &features) || + test_bit(DPU_SSPP_SCALER_QSEED3LITE, &features) || test_bit(DPU_SSPP_SCALER_QSEED4, &features)) { c->ops.setup_scaler = _dpu_hw_sspp_setup_scaler3; c->ops.get_scaler_ver = _dpu_hw_sspp_get_scaler3_ver; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h index 85b018a9b03c..fdfd4b46e2c6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h @@ -28,6 +28,7 @@ struct dpu_hw_pipe; #define DPU_SSPP_SCALER ((1UL << DPU_SSPP_SCALER_RGB) | \ (1UL << DPU_SSPP_SCALER_QSEED2) | \ (1UL << DPU_SSPP_SCALER_QSEED3) | \ + (1UL << DPU_SSPP_SCALER_QSEED3LITE) | \ (1UL << DPU_SSPP_SCALER_QSEED4)) /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c index 84e9875994a8..f94584c982cd 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c @@ -59,6 +59,19 @@ static u32 dpu_hw_util_log_mask = DPU_DBG_MASK_NONE; #define QSEED3_SEP_LUT_SIZE \ (QSEED3_LUT_SIZE * QSEED3_SEPARABLE_LUTS * sizeof(u32)) +/* DPU_SCALER_QSEED3LITE */ +#define QSEED3LITE_COEF_LUT_Y_SEP_BIT 4 +#define QSEED3LITE_COEF_LUT_UV_SEP_BIT 5 +#define QSEED3LITE_COEF_LUT_CTRL 0x4C +#define QSEED3LITE_COEF_LUT_SWAP_BIT 0 +#define QSEED3LITE_DIR_FILTER_WEIGHT 0x60 +#define QSEED3LITE_FILTERS 2 +#define QSEED3LITE_SEPARABLE_LUTS 10 +#define QSEED3LITE_LUT_SIZE 33 +#define QSEED3LITE_SEP_LUT_SIZE \ + (QSEED3LITE_LUT_SIZE * QSEED3LITE_SEPARABLE_LUTS * sizeof(u32)) + + void dpu_reg_write(struct dpu_hw_blk_reg_map *c, u32 reg_off, u32 val, @@ -156,6 +169,57 @@ static void _dpu_hw_setup_scaler3_lut(struct dpu_hw_blk_reg_map *c, } +static void _dpu_hw_setup_scaler3lite_lut(struct dpu_hw_blk_reg_map *c, + struct dpu_hw_scaler3_cfg *scaler3_cfg, u32 offset) +{ + int j, filter; + int config_lut = 0x0; + unsigned long lut_flags; + u32 lut_addr, lut_offset; + u32 *lut[QSEED3LITE_FILTERS] = {NULL, NULL}; + static const uint32_t off_tbl[QSEED3_FILTERS] = { 0x000, 0x200 }; + + DPU_REG_WRITE(c, QSEED3LITE_DIR_FILTER_WEIGHT + offset, scaler3_cfg->dir_weight); + + if (!scaler3_cfg->sep_lut) + return; + + lut_flags = (unsigned long) scaler3_cfg->lut_flag; + if (test_bit(QSEED3_COEF_LUT_Y_SEP_BIT, &lut_flags) && + (scaler3_cfg->y_rgb_sep_lut_idx < QSEED3LITE_SEPARABLE_LUTS) && + (scaler3_cfg->sep_len == QSEED3LITE_SEP_LUT_SIZE)) { + lut[0] = scaler3_cfg->sep_lut + + scaler3_cfg->y_rgb_sep_lut_idx * QSEED3LITE_LUT_SIZE; + config_lut = 1; + } + if (test_bit(QSEED3_COEF_LUT_UV_SEP_BIT, &lut_flags) && + (scaler3_cfg->uv_sep_lut_idx < QSEED3LITE_SEPARABLE_LUTS) && + (scaler3_cfg->sep_len == QSEED3LITE_SEP_LUT_SIZE)) { + lut[1] = scaler3_cfg->sep_lut + + scaler3_cfg->uv_sep_lut_idx * QSEED3LITE_LUT_SIZE; + config_lut = 1; + } + + if (config_lut) { + for (filter = 0; filter < QSEED3LITE_FILTERS; filter++) { + if (!lut[filter]) + continue; + lut_offset = 0; + lut_addr = QSEED3_COEF_LUT + offset + off_tbl[filter]; + for (j = 0; j < QSEED3LITE_LUT_SIZE; j++) { + DPU_REG_WRITE(c, + lut_addr, + (lut[filter])[lut_offset++]); + lut_addr += 4; + } + } + } + + if (test_bit(QSEED3_COEF_LUT_SWAP_BIT, &lut_flags)) + DPU_REG_WRITE(c, QSEED3_COEF_LUT_CTRL + offset, BIT(0)); + +} + static void _dpu_hw_setup_scaler3_de(struct dpu_hw_blk_reg_map *c, struct dpu_hw_scaler3_de_cfg *de_cfg, u32 offset) { @@ -242,9 +306,12 @@ void dpu_hw_setup_scaler3(struct dpu_hw_blk_reg_map *c, op_mode |= BIT(8); } - if (scaler3_cfg->lut_flag) - _dpu_hw_setup_scaler3_lut(c, scaler3_cfg, - scaler_offset); + if (scaler3_cfg->lut_flag) { + if (scaler_version < 0x2004) + _dpu_hw_setup_scaler3_lut(c, scaler3_cfg, scaler_offset); + else + _dpu_hw_setup_scaler3lite_lut(c, scaler3_cfg, scaler_offset); + } if (scaler_version == 0x1002) { phase_init = diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h index 234eb7d65753..ff3cffde84cd 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h @@ -97,6 +97,7 @@ struct dpu_hw_scaler3_de_cfg { * @ cir_lut: pointer to circular filter LUT * @ sep_lut: pointer to separable filter LUT * @ de: detail enhancer configuration + * @ dir_weight: Directional weight */ struct dpu_hw_scaler3_cfg { u32 enable; @@ -137,6 +138,8 @@ struct dpu_hw_scaler3_cfg { * Detail enhancer settings */ struct dpu_hw_scaler3_de_cfg de; + + u32 dir_weight; }; /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c index cf867f3f7c36..b757054e1c23 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c @@ -30,7 +30,7 @@ #define VBIF_XIN_HALT_CTRL0 0x0200 #define VBIF_XIN_HALT_CTRL1 0x0204 #define VBIF_XINL_QOS_RP_REMAP_000 0x0550 -#define VBIF_XINL_QOS_LVL_REMAP_000 0x0590 +#define VBIF_XINL_QOS_LVL_REMAP_000(v) (v < DPU_HW_VER_400 ? 0x570 : 0x0590) static void dpu_hw_clear_errors(struct dpu_hw_vbif *vbif, u32 *pnd_errors, u32 *src_errors) @@ -156,18 +156,19 @@ static void dpu_hw_set_qos_remap(struct dpu_hw_vbif *vbif, u32 xin_id, u32 level, u32 remap_level) { struct dpu_hw_blk_reg_map *c; - u32 reg_val, reg_val_lvl, mask, reg_high, reg_shift; + u32 reg_lvl, reg_val, reg_val_lvl, mask, reg_high, reg_shift; if (!vbif) return; c = &vbif->hw; + reg_lvl = VBIF_XINL_QOS_LVL_REMAP_000(c->hwversion); reg_high = ((xin_id & 0x8) >> 3) * 4 + (level * 8); reg_shift = (xin_id & 0x7) * 4; reg_val = DPU_REG_READ(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high); - reg_val_lvl = DPU_REG_READ(c, VBIF_XINL_QOS_LVL_REMAP_000 + reg_high); + reg_val_lvl = DPU_REG_READ(c, reg_lvl + reg_high); mask = 0x7 << reg_shift; @@ -178,7 +179,7 @@ static void dpu_hw_set_qos_remap(struct dpu_hw_vbif *vbif, reg_val_lvl |= (remap_level << reg_shift) & mask; DPU_REG_WRITE(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high, reg_val); - DPU_REG_WRITE(c, VBIF_XINL_QOS_LVL_REMAP_000 + reg_high, reg_val_lvl); + DPU_REG_WRITE(c, reg_lvl + reg_high, reg_val_lvl); } static void dpu_hw_set_write_gather_en(struct dpu_hw_vbif *vbif, u32 xin_id) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 374b0e8471e6..5a8e3e1fc48c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -749,7 +749,7 @@ static void _dpu_kms_set_encoder_mode(struct msm_kms *kms, case DRM_MODE_ENCODER_TMDS: info.num_of_h_tiles = 1; break; - }; + } rc = dpu_encoder_setup(encoder->dev, encoder, &info); if (rc) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index bc0231a50132..f898a8f67b7f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -1465,6 +1465,7 @@ static int _dpu_plane_init_debugfs(struct drm_plane *plane) pdpu->debugfs_root, &pdpu->debugfs_src); if (cfg->features & BIT(DPU_SSPP_SCALER_QSEED3) || + cfg->features & BIT(DPU_SSPP_SCALER_QSEED3LITE) || cfg->features & BIT(DPU_SSPP_SCALER_QSEED2) || cfg->features & BIT(DPU_SSPP_SCALER_QSEED4)) { dpu_debugfs_setup_regset32(&pdpu->debugfs_scaler, diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c index df10c1ac7591..94ce62a26daf 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c @@ -177,7 +177,7 @@ static const struct mdp5_cfg_hw msm8x74v2_config = { [3] = INTF_HDMI, }, }, - .max_clk = 200000000, + .max_clk = 320000000, }; static const struct mdp5_cfg_hw apq8084_config = { diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c index 0c8f9f88301f..f5d71b274079 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c @@ -1180,7 +1180,7 @@ static void mdp5_crtc_pp_done_irq(struct mdp_irq *irq, uint32_t irqstatus) struct mdp5_crtc *mdp5_crtc = container_of(irq, struct mdp5_crtc, pp_done); - complete(&mdp5_crtc->pp_completion); + complete_all(&mdp5_crtc->pp_completion); } static void mdp5_crtc_wait_for_pp_done(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c index 19b35ae3e927..1c6e1d2b947c 100644 --- a/drivers/gpu/drm/msm/dp/dp_aux.c +++ b/drivers/gpu/drm/msm/dp/dp_aux.c @@ -336,7 +336,6 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux, ssize_t ret; int const aux_cmd_native_max = 16; int const aux_cmd_i2c_max = 128; - int const retry_count = 5; struct dp_aux_private *aux = container_of(dp_aux, struct dp_aux_private, dp_aux); @@ -378,12 +377,6 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux, ret = dp_aux_cmd_fifo_tx(aux, msg); if (ret < 0) { - if (aux->native) { - aux->retry_cnt++; - if (!(aux->retry_cnt % retry_count)) - dp_catalog_aux_update_cfg(aux->catalog); - dp_catalog_aux_reset(aux->catalog); - } usleep_range(400, 500); /* at least 400us to next try */ goto unlock_exit; } diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.c b/drivers/gpu/drm/msm/dp/dp_catalog.c index 44f0c57798d0..b1a9b1b98f5f 100644 --- a/drivers/gpu/drm/msm/dp/dp_catalog.c +++ b/drivers/gpu/drm/msm/dp/dp_catalog.c @@ -190,6 +190,18 @@ int dp_catalog_aux_clear_hw_interrupts(struct dp_catalog *dp_catalog) return 0; } +/** + * dp_catalog_aux_reset() - reset AUX controller + * + * @aux: DP catalog structure + * + * return: void + * + * This function reset AUX controller + * + * NOTE: reset AUX controller will also clear any pending HPD related interrupts + * + */ void dp_catalog_aux_reset(struct dp_catalog *dp_catalog) { u32 aux_ctrl; @@ -483,6 +495,18 @@ int dp_catalog_ctrl_set_pattern(struct dp_catalog *dp_catalog, return 0; } +/** + * dp_catalog_ctrl_reset() - reset DP controller + * + * @dp_catalog: DP catalog structure + * + * return: void + * + * This function reset the DP controller + * + * NOTE: reset DP controller will also clear any pending HPD related interrupts + * + */ void dp_catalog_ctrl_reset(struct dp_catalog *dp_catalog) { u32 sw_reset; diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index 36b39c381b3f..1390f3547fde 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -631,7 +631,7 @@ static void _dp_ctrl_calc_tu(struct dp_tu_calc_input *in, tu = kzalloc(sizeof(*tu), GFP_KERNEL); if (!tu) - return + return; dp_panel_update_tu_timings(in, tu); @@ -1158,7 +1158,7 @@ static int dp_ctrl_link_rate_down_shift(struct dp_ctrl_private *ctrl) default: ret = -EINVAL; break; - }; + } if (!ret) DRM_DEBUG_DP("new rate=0x%x\n", ctrl->link->link_params.rate); @@ -1296,7 +1296,6 @@ static int dp_ctrl_setup_main_link(struct dp_ctrl_private *ctrl, * transitioned to PUSH_IDLE. In order to start transmitting * a link training pattern, we have to first do soft reset. */ - dp_catalog_ctrl_reset(ctrl->catalog); ret = dp_ctrl_link_train(ctrl, cr, training_step); @@ -1365,7 +1364,7 @@ static int dp_ctrl_enable_stream_clocks(struct dp_ctrl_private *ctrl) return ret; } -int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip) +int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip, bool reset) { struct dp_ctrl_private *ctrl; struct dp_io *dp_io; @@ -1382,6 +1381,9 @@ int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip) ctrl->dp_ctrl.orientation = flip; + if (reset) + dp_catalog_ctrl_reset(ctrl->catalog); + dp_catalog_ctrl_phy_reset(ctrl->catalog); phy_init(phy); dp_catalog_ctrl_enable_irq(ctrl->catalog, true); @@ -1496,7 +1498,6 @@ static int dp_ctrl_link_maintenance(struct dp_ctrl_private *ctrl) int training_step = DP_TRAINING_NONE; dp_ctrl_push_idle(&ctrl->dp_ctrl); - dp_catalog_ctrl_reset(ctrl->catalog); ctrl->dp_ctrl.pixel_rate = ctrl->panel->dp_mode.drm_mode.clock; @@ -1785,14 +1786,14 @@ int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl) * Set up transfer unit values and set controller state to send * video. */ + reinit_completion(&ctrl->video_comp); + dp_ctrl_configure_source_params(ctrl); dp_catalog_ctrl_config_msa(ctrl->catalog, ctrl->link->link_params.rate, ctrl->dp_ctrl.pixel_rate, dp_ctrl_use_fixed_nvid(ctrl)); - reinit_completion(&ctrl->video_comp); - dp_ctrl_setup_tr_unit(ctrl); dp_catalog_ctrl_state_ctrl(ctrl->catalog, DP_STATE_CTRL_SEND_VIDEO); diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.h b/drivers/gpu/drm/msm/dp/dp_ctrl.h index f60ba93c8678..a836bd358447 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.h +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.h @@ -19,7 +19,7 @@ struct dp_ctrl { u32 pixel_rate; }; -int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip); +int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip, bool reset); void dp_ctrl_host_deinit(struct dp_ctrl *dp_ctrl); int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl); int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl); diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 3bc7ed21de28..5a39da6e1eaf 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -350,7 +350,7 @@ static int dp_display_process_hpd_high(struct dp_display_private *dp) return rc; } -static void dp_display_host_init(struct dp_display_private *dp) +static void dp_display_host_init(struct dp_display_private *dp, int reset) { bool flip = false; @@ -365,7 +365,7 @@ static void dp_display_host_init(struct dp_display_private *dp) dp_display_set_encoder_mode(dp); dp_power_init(dp->power, flip); - dp_ctrl_host_init(dp->ctrl, flip); + dp_ctrl_host_init(dp->ctrl, flip, reset); dp_aux_init(dp->aux); dp->core_initialized = true; } @@ -403,7 +403,7 @@ static int dp_display_usbpd_configure_cb(struct device *dev) goto end; } - dp_display_host_init(dp); + dp_display_host_init(dp, false); /* * set sink to normal operation mode -- D0 @@ -651,8 +651,8 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data) dp_add_event(dp, EV_DISCONNECT_PENDING_TIMEOUT, 0, DP_TIMEOUT_5_SECOND); /* signal the disconnect event early to ensure proper teardown */ - dp_display_handle_plugged_change(g_dp_display, false); reinit_completion(&dp->audio_comp); + dp_display_handle_plugged_change(g_dp_display, false); dp_catalog_hpd_config_intr(dp->catalog, DP_DP_HPD_PLUG_INT_MASK | DP_DP_IRQ_HPD_INT_MASK, true); @@ -700,6 +700,13 @@ static int dp_irq_hpd_handle(struct dp_display_private *dp, u32 data) return 0; } + if (state == ST_CONNECT_PENDING || state == ST_DISCONNECT_PENDING) { + /* wait until ST_CONNECTED */ + dp_add_event(dp, EV_IRQ_HPD_INT, 0, 1); /* delay = 1 */ + mutex_unlock(&dp->event_mutex); + return 0; + } + ret = dp_display_usbpd_attention_cb(&dp->pdev->dev); if (ret == -ECONNRESET) { /* cable unplugged */ dp->core_initialized = false; @@ -890,6 +897,9 @@ static int dp_display_disable(struct dp_display_private *dp, u32 data) /* wait only if audio was enabled */ if (dp_display->audio_enabled) { + /* signal the disconnect event */ + reinit_completion(&dp->audio_comp); + dp_display_handle_plugged_change(dp_display, false); if (!wait_for_completion_timeout(&dp->audio_comp, HZ * 5)) DRM_ERROR("audio comp timeout\n"); @@ -1002,7 +1012,7 @@ int dp_display_get_test_bpp(struct msm_dp *dp) static void dp_display_config_hpd(struct dp_display_private *dp) { - dp_display_host_init(dp); + dp_display_host_init(dp, true); dp_catalog_ctrl_hpd_config(dp->catalog); /* Enable interrupt first time @@ -1256,7 +1266,7 @@ static int dp_pm_resume(struct device *dev) dp->hpd_state = ST_DISCONNECTED; /* turn on dp ctrl/phy */ - dp_display_host_init(dp); + dp_display_host_init(dp, true); dp_catalog_ctrl_hpd_config(dp->catalog); @@ -1439,7 +1449,7 @@ int msm_dp_display_enable(struct msm_dp *dp, struct drm_encoder *encoder) state = dp_display->hpd_state; if (state == ST_DISPLAY_OFF) - dp_display_host_init(dp_display); + dp_display_host_init(dp_display, true); dp_display_enable(dp_display, 0); diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index d1780bcac8cc..9cc816663668 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -409,7 +409,6 @@ int dp_panel_timing_cfg(struct dp_panel *dp_panel) int dp_panel_init_panel_info(struct dp_panel *dp_panel) { - int rc = 0; struct drm_display_mode *drm_mode; drm_mode = &dp_panel->dp_mode.drm_mode; @@ -436,7 +435,7 @@ int dp_panel_init_panel_info(struct dp_panel *dp_panel) min_t(u32, dp_panel->dp_mode.bpp, 30)); DRM_DEBUG_DP("updated bpp = %d\n", dp_panel->dp_mode.bpp); - return rc; + return 0; } struct dp_panel *dp_panel_get(struct dp_panel_in *in) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c index 1afb7c579dbb..eca86bf448f7 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c @@ -139,7 +139,7 @@ const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs = { .disable = dsi_20nm_phy_disable, .init = msm_dsi_phy_init_common, }, - .io_start = { 0xfd998300, 0xfd9a0300 }, + .io_start = { 0xfd998500, 0xfd9a0500 }, .num_dsi_phy = 2, }; diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c index e4e9bf04b736..de3b802ccd3d 100644 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c @@ -172,9 +172,7 @@ static void dsi_pll_calc_dec_frac(struct dsi_pll_10nm *pll) multiplier = 1 << config->frac_bits; dec_multiple = div_u64(pll_freq * multiplier, divider); - div_u64_rem(dec_multiple, multiplier, &frac); - - dec = div_u64(dec_multiple, multiplier); + dec = div_u64_rem(dec_multiple, multiplier, &frac); if (pll_freq <= 1900000000UL) regs->pll_prop_gain_rate = 8; @@ -306,7 +304,8 @@ static void dsi_pll_commit(struct dsi_pll_10nm *pll) reg->frac_div_start_mid); pll_write(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_HIGH_1, reg->frac_div_start_high); - pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCKDET_RATE_1, 0x40); + pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCKDET_RATE_1, + reg->pll_lockdet_rate); pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCK_DELAY, 0x06); pll_write(base + REG_DSI_10nm_PHY_PLL_CMODE, 0x10); pll_write(base + REG_DSI_10nm_PHY_PLL_CLOCK_INVERTERS, @@ -345,6 +344,7 @@ static int dsi_pll_10nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, static int dsi_pll_10nm_lock_status(struct dsi_pll_10nm *pll) { + struct device *dev = &pll->pdev->dev; int rc; u32 status = 0; u32 const delay_us = 100; @@ -357,8 +357,8 @@ static int dsi_pll_10nm_lock_status(struct dsi_pll_10nm *pll) delay_us, timeout_us); if (rc) - pr_err("DSI PLL(%d) lock failed, status=0x%08x\n", - pll->id, status); + DRM_DEV_ERROR(dev, "DSI PLL(%d) lock failed, status=0x%08x\n", + pll->id, status); return rc; } @@ -405,6 +405,7 @@ static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw) { struct msm_dsi_pll *pll = hw_clk_to_pll(hw); struct dsi_pll_10nm *pll_10nm = to_pll_10nm(pll); + struct device *dev = &pll_10nm->pdev->dev; int rc; dsi_pll_enable_pll_bias(pll_10nm); @@ -413,7 +414,7 @@ static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw) rc = dsi_pll_10nm_vco_set_rate(hw,pll_10nm->vco_current_rate, 0); if (rc) { - pr_err("vco_set_rate failed, rc=%d\n", rc); + DRM_DEV_ERROR(dev, "vco_set_rate failed, rc=%d\n", rc); return rc; } @@ -430,7 +431,7 @@ static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw) /* Check for PLL lock */ rc = dsi_pll_10nm_lock_status(pll_10nm); if (rc) { - pr_err("PLL(%d) lock failed\n", pll_10nm->id); + DRM_DEV_ERROR(dev, "PLL(%d) lock failed\n", pll_10nm->id); goto error; } @@ -483,6 +484,7 @@ static unsigned long dsi_pll_10nm_vco_recalc_rate(struct clk_hw *hw, { struct msm_dsi_pll *pll = hw_clk_to_pll(hw); struct dsi_pll_10nm *pll_10nm = to_pll_10nm(pll); + struct dsi_pll_config *config = &pll_10nm->pll_configuration; void __iomem *base = pll_10nm->mmio; u64 ref_clk = pll_10nm->vco_ref_clk_rate; u64 vco_rate = 0x0; @@ -503,9 +505,8 @@ static unsigned long dsi_pll_10nm_vco_recalc_rate(struct clk_hw *hw, /* * TODO: * 1. Assumes prescaler is disabled - * 2. Multiplier is 2^18. it should be 2^(num_of_frac_bits) */ - multiplier = 1 << 18; + multiplier = 1 << config->frac_bits; pll_freq = dec * (ref_clk * 2); tmp64 = (ref_clk * 2 * frac); pll_freq += div_u64(tmp64, multiplier); diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 108c405e03dd..94525ac76d4e 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -788,9 +788,10 @@ static int msm_ioctl_gem_info_iova(struct drm_device *dev, struct drm_file *file, struct drm_gem_object *obj, uint64_t *iova) { + struct msm_drm_private *priv = dev->dev_private; struct msm_file_private *ctx = file->driver_priv; - if (!ctx->aspace) + if (!priv->gpu) return -EINVAL; /* diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index a588b0388d27..f091c1e164fa 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -987,8 +987,7 @@ void msm_gem_free_object(struct drm_gem_object *obj) /* Don't drop the pages for imported dmabuf, as they are not * ours, just free the array we allocated: */ - if (msm_obj->pages) - kvfree(msm_obj->pages); + kvfree(msm_obj->pages); put_iova_vmas(obj); diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index d04c349d8112..5480852bdeda 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -198,6 +198,8 @@ static int submit_lookup_cmds(struct msm_gem_submit *submit, submit->cmd[i].idx = submit_cmd.submit_idx; submit->cmd[i].nr_relocs = submit_cmd.nr_relocs; + userptr = u64_to_user_ptr(submit_cmd.relocs); + sz = array_size(submit_cmd.nr_relocs, sizeof(struct drm_msm_gem_submit_reloc)); /* check for overflow: */ diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h index d8151a89e163..4735251a394d 100644 --- a/drivers/gpu/drm/msm/msm_kms.h +++ b/drivers/gpu/drm/msm/msm_kms.h @@ -157,6 +157,7 @@ struct msm_kms { * from the crtc's pending_timer close to end of the frame: */ struct mutex commit_lock[MAX_CRTCS]; + struct lock_class_key commit_lock_keys[MAX_CRTCS]; unsigned pending_crtc_mask; struct msm_pending_timer pending_timers[MAX_CRTCS]; }; @@ -166,8 +167,11 @@ static inline int msm_kms_init(struct msm_kms *kms, { unsigned i, ret; - for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++) - mutex_init(&kms->commit_lock[i]); + for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++) { + lockdep_register_key(&kms->commit_lock_keys[i]); + __mutex_init(&kms->commit_lock[i], "&kms->commit_lock[i]", + &kms->commit_lock_keys[i]); + } kms->funcs = funcs; diff --git a/drivers/gpu/drm/panel/panel-elida-kd35t133.c b/drivers/gpu/drm/panel/panel-elida-kd35t133.c index bc36aa3c1123..fe5ac3ef9018 100644 --- a/drivers/gpu/drm/panel/panel-elida-kd35t133.c +++ b/drivers/gpu/drm/panel/panel-elida-kd35t133.c @@ -265,7 +265,8 @@ static int kd35t133_probe(struct mipi_dsi_device *dsi) dsi->lanes = 1; dsi->format = MIPI_DSI_FMT_RGB888; dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST | - MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_EOT_PACKET; + MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_EOT_PACKET | + MIPI_DSI_CLOCK_NON_CONTINUOUS; drm_panel_init(&ctx->panel, &dsi->dev, &kd35t133_funcs, DRM_MODE_CONNECTOR_DSI); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h index 4a2099cb582e..857d97cdc67c 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h @@ -17,9 +17,20 @@ #define NUM_YUV2YUV_COEFFICIENTS 12 +/* AFBC supports a number of configurable modes. Relevant to us is block size + * (16x16 or 32x8), storage modifiers (SPARSE, SPLIT), and the YUV-like + * colourspace transform (YTR). 16x16 SPARSE mode is always used. SPLIT mode + * could be enabled via the hreg_block_split register, but is not currently + * handled. The colourspace transform is implicitly always assumed by the + * decoder, so consumers must use this transform as well. + * + * Failure to match modifiers will cause errors displaying AFBC buffers + * produced by conformant AFBC producers, including Mesa. + */ #define ROCKCHIP_AFBC_MOD \ DRM_FORMAT_MOD_ARM_AFBC( \ AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 | AFBC_FORMAT_MOD_SPARSE \ + | AFBC_FORMAT_MOD_YTR \ ) enum vop_data_format { diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index b65f4b12f986..20a25660b35b 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -959,8 +959,10 @@ static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo, return ret; /* move to the bounce domain */ ret = ttm_bo_handle_move_mem(bo, &hop_mem, false, ctx, NULL); - if (ret) + if (ret) { + ttm_resource_free(bo, &hop_mem); return ret; + } return 0; } @@ -991,18 +993,19 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo, * stop and the driver will be called to make * the second hop. */ -bounce: ret = ttm_bo_mem_space(bo, placement, &mem, ctx); if (ret) return ret; +bounce: ret = ttm_bo_handle_move_mem(bo, &mem, false, ctx, &hop); if (ret == -EMULTIHOP) { ret = ttm_bo_bounce_temp_buffer(bo, &mem, ctx, &hop); if (ret) - return ret; + goto out; /* try and move to final place now. */ goto bounce; } +out: if (ret) ttm_resource_free(bo, &mem); return ret; diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 8c471823a5af..2f776d78e3c1 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -726,7 +726,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, nid = memory_add_physaddr_to_nid(PFN_PHYS(start_pfn)); ret = add_memory(nid, PFN_PHYS((start_pfn)), - (HA_CHUNK << PAGE_SHIFT), MEMHP_MERGE_RESOURCE); + (HA_CHUNK << PAGE_SHIFT), MHP_MERGE_RESOURCE); if (ret) { pr_err("hot_add memory failed error is %d\n", ret); diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 6c1d8b69a465..b6742b4231bf 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -934,4 +934,7 @@ source "drivers/leds/flash/Kconfig" comment "LED Triggers" source "drivers/leds/trigger/Kconfig" +comment "LED Blink" +source "drivers/leds/blink/Kconfig" + endif # NEW_LEDS diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile index 156c0b4e60d9..2a698df9da57 100644 --- a/drivers/leds/Makefile +++ b/drivers/leds/Makefile @@ -108,3 +108,6 @@ obj-$(CONFIG_LEDS_CLASS_FLASH) += flash/ # LED Triggers obj-$(CONFIG_LEDS_TRIGGERS) += trigger/ + +# LED Blink +obj-$(CONFIG_LEDS_BLINK) += blink/ diff --git a/drivers/leds/blink/Kconfig b/drivers/leds/blink/Kconfig new file mode 100644 index 000000000000..265b53476a80 --- /dev/null +++ b/drivers/leds/blink/Kconfig @@ -0,0 +1,20 @@ +menuconfig LEDS_BLINK + bool "LED Blink support" + depends on LEDS_CLASS + help + This option enables blink support for the leds class. + If unsure, say Y. + +if LEDS_BLINK + +config LEDS_BLINK_LGM + tristate "LED support for Intel LGM SoC series" + depends on LEDS_CLASS + depends on MFD_SYSCON + depends on OF + help + Parallel to serial conversion, which is also called SSO controller, + can drive external shift register for LED outputs. + This enables LED support for Serial Shift Output controller(SSO). + +endif # LEDS_BLINK diff --git a/drivers/leds/blink/Makefile b/drivers/leds/blink/Makefile new file mode 100644 index 000000000000..2fa6c7b7b67e --- /dev/null +++ b/drivers/leds/blink/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_LEDS_BLINK_LGM) += leds-lgm-sso.o diff --git a/drivers/leds/blink/leds-lgm-sso.c b/drivers/leds/blink/leds-lgm-sso.c new file mode 100644 index 000000000000..7d5c9ca007d6 --- /dev/null +++ b/drivers/leds/blink/leds-lgm-sso.c @@ -0,0 +1,888 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Lightning Mountain SoC LED Serial Shift Output Controller driver + * + * Copyright (c) 2020 Intel Corporation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define SSO_DEV_NAME "lgm-sso" + +#define LED_BLINK_H8_0 0x0 +#define LED_BLINK_H8_1 0x4 +#define GET_FREQ_OFFSET(pin, src) (((pin) * 6) + ((src) * 2)) +#define GET_SRC_OFFSET(pinc) (((pin) * 6) + 4) + +#define DUTY_CYCLE(x) (0x8 + ((x) * 4)) +#define SSO_CON0 0x2B0 +#define SSO_CON0_RZFL BIT(26) +#define SSO_CON0_BLINK_R BIT(30) +#define SSO_CON0_SWU BIT(31) + +#define SSO_CON1 0x2B4 +#define SSO_CON1_FCDSC GENMASK(21, 20) /* Fixed Divider Shift Clock */ +#define SSO_CON1_FPID GENMASK(24, 23) +#define SSO_CON1_GPTD GENMASK(26, 25) +#define SSO_CON1_US GENMASK(31, 30) + +#define SSO_CPU 0x2B8 +#define SSO_CON2 0x2C4 +#define SSO_CON3 0x2C8 + +/* Driver MACRO */ +#define MAX_PIN_NUM_PER_BANK SZ_32 +#define MAX_GROUP_NUM SZ_4 +#define PINS_PER_GROUP SZ_8 +#define FPID_FREQ_RANK_MAX SZ_4 +#define SSO_LED_MAX_NUM SZ_32 +#define MAX_FREQ_RANK 10 +#define DEF_GPTC_CLK_RATE 200000000 +#define SSO_DEF_BRIGHTNESS LED_HALF +#define DATA_CLK_EDGE 0 /* 0-rising, 1-falling */ + +static const u32 freq_div_tbl[] = {4000, 2000, 1000, 800}; +static const int freq_tbl[] = {2, 4, 8, 10, 50000, 100000, 200000, 250000}; +static const int shift_clk_freq_tbl[] = {25000000, 12500000, 6250000, 3125000}; + +/* + * Update Source to update the SOUTs + * SW - Software has to update the SWU bit + * GPTC - General Purpose timer is used as clock source + * FPID - Divided FSC clock (FPID) is used as clock source + */ +enum { + US_SW = 0, + US_GPTC = 1, + US_FPID = 2 +}; + +enum { + MAX_FPID_FREQ_RANK = 5, /* 1 to 4 */ + MAX_GPTC_FREQ_RANK = 9, /* 5 to 8 */ + MAX_GPTC_HS_FREQ_RANK = 10, /* 9 to 10 */ +}; + +enum { + LED_GRP0_PIN_MAX = 24, + LED_GRP1_PIN_MAX = 29, + LED_GRP2_PIN_MAX = 32, +}; + +enum { + LED_GRP0_0_23, + LED_GRP1_24_28, + LED_GRP2_29_31, + LED_GROUP_MAX, +}; + +enum { + CLK_SRC_FPID = 0, + CLK_SRC_GPTC = 1, + CLK_SRC_GPTC_HS = 2, +}; + +struct sso_led_priv; + +struct sso_led_desc { + const char *name; + const char *default_trigger; + unsigned int brightness; + unsigned int blink_rate; + unsigned int retain_state_suspended:1; + unsigned int retain_state_shutdown:1; + unsigned int panic_indicator:1; + unsigned int hw_blink:1; + unsigned int hw_trig:1; + unsigned int blinking:1; + int freq_idx; + u32 pin; +}; + +struct sso_led { + struct list_head list; + struct led_classdev cdev; + struct gpio_desc *gpiod; + struct sso_led_desc desc; + struct sso_led_priv *priv; +}; + +struct sso_gpio { + struct gpio_chip chip; + int shift_clk_freq; + int edge; + int freq; + u32 pins; + u32 alloc_bitmap; +}; + +struct sso_led_priv { + struct regmap *mmap; + struct device *dev; + struct platform_device *pdev; + struct clk *gclk; + struct clk *fpid_clk; + u32 fpid_clkrate; + u32 gptc_clkrate; + u32 freq[MAX_FREQ_RANK]; + struct list_head led_list; + struct sso_gpio gpio; +}; + +static int sso_get_blink_rate_idx(struct sso_led_priv *priv, u32 rate) +{ + int i; + + for (i = 0; i < MAX_FREQ_RANK; i++) { + if (rate <= priv->freq[i]) + return i; + } + + return -1; +} + +static unsigned int sso_led_pin_to_group(u32 pin) +{ + if (pin < LED_GRP0_PIN_MAX) + return LED_GRP0_0_23; + else if (pin < LED_GRP1_PIN_MAX) + return LED_GRP1_24_28; + else + return LED_GRP2_29_31; +} + +static u32 sso_led_get_freq_src(int freq_idx) +{ + if (freq_idx < MAX_FPID_FREQ_RANK) + return CLK_SRC_FPID; + else if (freq_idx < MAX_GPTC_FREQ_RANK) + return CLK_SRC_GPTC; + else + return CLK_SRC_GPTC_HS; +} + +static u32 sso_led_pin_blink_off(u32 pin, unsigned int group) +{ + if (group == LED_GRP2_29_31) + return pin - LED_GRP1_PIN_MAX; + else if (group == LED_GRP1_24_28) + return pin - LED_GRP0_PIN_MAX; + else /* led 0 - 23 in led 32 location */ + return SSO_LED_MAX_NUM - LED_GRP1_PIN_MAX; +} + +static struct sso_led +*cdev_to_sso_led_data(struct led_classdev *led_cdev) +{ + return container_of(led_cdev, struct sso_led, cdev); +} + +static void sso_led_freq_set(struct sso_led_priv *priv, u32 pin, int freq_idx) +{ + u32 reg, off, freq_src, val_freq; + u32 low, high, val; + unsigned int group; + + if (!freq_idx) + return; + + group = sso_led_pin_to_group(pin); + freq_src = sso_led_get_freq_src(freq_idx); + off = sso_led_pin_blink_off(pin, group); + + if (group == LED_GRP0_0_23) + return; + else if (group == LED_GRP1_24_28) + reg = LED_BLINK_H8_0; + else + reg = LED_BLINK_H8_1; + + if (freq_src == CLK_SRC_FPID) + val_freq = freq_idx - 1; + else if (freq_src == CLK_SRC_GPTC) + val_freq = freq_idx - MAX_FPID_FREQ_RANK; + + /* set blink rate idx */ + if (freq_src != CLK_SRC_GPTC_HS) { + low = GET_FREQ_OFFSET(off, freq_src); + high = low + 2; + val = val_freq << high; + regmap_update_bits(priv->mmap, reg, GENMASK(high, low), val); + } + + /* select clock source */ + low = GET_SRC_OFFSET(off); + high = low + 2; + val = freq_src << high; + regmap_update_bits(priv->mmap, reg, GENMASK(high, low), val); +} + +static void sso_led_brightness_set(struct led_classdev *led_cdev, + enum led_brightness brightness) +{ + struct sso_led_priv *priv; + struct sso_led_desc *desc; + struct sso_led *led; + int val; + + led = cdev_to_sso_led_data(led_cdev); + priv = led->priv; + desc = &led->desc; + + desc->brightness = brightness; + regmap_write(priv->mmap, DUTY_CYCLE(desc->pin), brightness); + + if (brightness == LED_OFF) + val = 0; + else + val = 1; + + /* HW blink off */ + if (desc->hw_blink && !val && desc->blinking) { + desc->blinking = 0; + regmap_update_bits(priv->mmap, SSO_CON2, BIT(desc->pin), 0); + } else if (desc->hw_blink && val && !desc->blinking) { + desc->blinking = 1; + regmap_update_bits(priv->mmap, SSO_CON2, BIT(desc->pin), + 1 << desc->pin); + } + + if (!desc->hw_trig && led->gpiod) + gpiod_set_value(led->gpiod, val); +} + +static enum led_brightness sso_led_brightness_get(struct led_classdev *led_cdev) +{ + struct sso_led *led = cdev_to_sso_led_data(led_cdev); + + return (enum led_brightness)led->desc.brightness; +} + +static int +delay_to_freq_idx(struct sso_led *led, unsigned long *delay_on, + unsigned long *delay_off) +{ + struct sso_led_priv *priv = led->priv; + unsigned long delay; + int freq_idx; + u32 freq; + + if (!*delay_on && !*delay_off) { + *delay_on = *delay_off = (1000 / priv->freq[0]) / 2; + return 0; + } + + delay = *delay_on + *delay_off; + freq = 1000 / delay; + + freq_idx = sso_get_blink_rate_idx(priv, freq); + if (freq_idx == -1) + freq_idx = MAX_FREQ_RANK - 1; + + delay = 1000 / priv->freq[freq_idx]; + *delay_on = *delay_off = delay / 2; + + if (!*delay_on) + *delay_on = *delay_off = 1; + + return freq_idx; +} + +static int +sso_led_blink_set(struct led_classdev *led_cdev, unsigned long *delay_on, + unsigned long *delay_off) +{ + struct sso_led_priv *priv; + struct sso_led *led; + int freq_idx; + + led = cdev_to_sso_led_data(led_cdev); + priv = led->priv; + freq_idx = delay_to_freq_idx(led, delay_on, delay_off); + + sso_led_freq_set(priv, led->desc.pin, freq_idx); + regmap_update_bits(priv->mmap, SSO_CON2, BIT(led->desc.pin), + 1 << led->desc.pin); + led->desc.freq_idx = freq_idx; + led->desc.blink_rate = priv->freq[freq_idx]; + led->desc.blinking = 1; + + return 1; +} + +static void sso_led_hw_cfg(struct sso_led_priv *priv, struct sso_led *led) +{ + struct sso_led_desc *desc = &led->desc; + + /* set freq */ + if (desc->hw_blink) { + sso_led_freq_set(priv, desc->pin, desc->freq_idx); + regmap_update_bits(priv->mmap, SSO_CON2, BIT(desc->pin), + 1 << desc->pin); + } + + if (desc->hw_trig) + regmap_update_bits(priv->mmap, SSO_CON3, BIT(desc->pin), + 1 << desc->pin); + + /* set brightness */ + regmap_write(priv->mmap, DUTY_CYCLE(desc->pin), desc->brightness); + + /* enable output */ + if (!desc->hw_trig && desc->brightness) + gpiod_set_value(led->gpiod, 1); +} + +static int sso_create_led(struct sso_led_priv *priv, struct sso_led *led, + struct fwnode_handle *child) +{ + struct sso_led_desc *desc = &led->desc; + struct led_init_data init_data; + int err; + + init_data.fwnode = child; + init_data.devicename = SSO_DEV_NAME; + init_data.default_label = ":"; + + led->cdev.default_trigger = desc->default_trigger; + led->cdev.brightness_set = sso_led_brightness_set; + led->cdev.brightness_get = sso_led_brightness_get; + led->cdev.brightness = desc->brightness; + led->cdev.max_brightness = LED_FULL; + + if (desc->retain_state_shutdown) + led->cdev.flags |= LED_RETAIN_AT_SHUTDOWN; + if (desc->retain_state_suspended) + led->cdev.flags |= LED_CORE_SUSPENDRESUME; + if (desc->panic_indicator) + led->cdev.flags |= LED_PANIC_INDICATOR; + + if (desc->hw_blink) + led->cdev.blink_set = sso_led_blink_set; + + sso_led_hw_cfg(priv, led); + + err = devm_led_classdev_register_ext(priv->dev, &led->cdev, &init_data); + if (err) + return err; + + list_add(&led->list, &priv->led_list); + + return 0; +} + +static void sso_init_freq(struct sso_led_priv *priv) +{ + int i; + + priv->freq[0] = 0; + for (i = 1; i < MAX_FREQ_RANK; i++) { + if (i < MAX_FPID_FREQ_RANK) { + priv->freq[i] = priv->fpid_clkrate / freq_div_tbl[i - 1]; + } else if (i < MAX_GPTC_FREQ_RANK) { + priv->freq[i] = priv->gptc_clkrate / + freq_div_tbl[i - MAX_FPID_FREQ_RANK]; + } else if (i < MAX_GPTC_HS_FREQ_RANK) { + priv->freq[i] = priv->gptc_clkrate; + } + } +} + +static int sso_gpio_request(struct gpio_chip *chip, unsigned int offset) +{ + struct sso_led_priv *priv = gpiochip_get_data(chip); + + if (priv->gpio.alloc_bitmap & BIT(offset)) + return -EINVAL; + + priv->gpio.alloc_bitmap |= BIT(offset); + regmap_write(priv->mmap, DUTY_CYCLE(offset), 0xFF); + + return 0; +} + +static void sso_gpio_free(struct gpio_chip *chip, unsigned int offset) +{ + struct sso_led_priv *priv = gpiochip_get_data(chip); + + priv->gpio.alloc_bitmap &= ~BIT(offset); + regmap_write(priv->mmap, DUTY_CYCLE(offset), 0x0); +} + +static int sso_gpio_get_dir(struct gpio_chip *chip, unsigned int offset) +{ + return GPIOF_DIR_OUT; +} + +static int +sso_gpio_dir_out(struct gpio_chip *chip, unsigned int offset, int value) +{ + struct sso_led_priv *priv = gpiochip_get_data(chip); + bool bit = !!value; + + regmap_update_bits(priv->mmap, SSO_CPU, BIT(offset), bit << offset); + if (!priv->gpio.freq) + regmap_update_bits(priv->mmap, SSO_CON0, SSO_CON0_SWU, + SSO_CON0_SWU); + + return 0; +} + +static int sso_gpio_get(struct gpio_chip *chip, unsigned int offset) +{ + struct sso_led_priv *priv = gpiochip_get_data(chip); + u32 reg_val; + + regmap_read(priv->mmap, SSO_CPU, ®_val); + + return !!(reg_val & BIT(offset)); +} + +static void sso_gpio_set(struct gpio_chip *chip, unsigned int offset, int value) +{ + struct sso_led_priv *priv = gpiochip_get_data(chip); + + regmap_update_bits(priv->mmap, SSO_CPU, BIT(offset), value << offset); + if (!priv->gpio.freq) + regmap_update_bits(priv->mmap, SSO_CON0, SSO_CON0_SWU, + SSO_CON0_SWU); +} + +static int sso_gpio_gc_init(struct device *dev, struct sso_led_priv *priv) +{ + struct gpio_chip *gc = &priv->gpio.chip; + + gc->request = sso_gpio_request; + gc->free = sso_gpio_free; + gc->get_direction = sso_gpio_get_dir; + gc->direction_output = sso_gpio_dir_out; + gc->get = sso_gpio_get; + gc->set = sso_gpio_set; + + gc->label = "lgm-sso"; + gc->base = -1; + /* To exclude pins from control, use "gpio-reserved-ranges" */ + gc->ngpio = priv->gpio.pins; + gc->parent = dev; + gc->owner = THIS_MODULE; + gc->of_node = dev->of_node; + + return devm_gpiochip_add_data(dev, gc, priv); +} + +static int sso_gpio_get_freq_idx(int freq) +{ + int idx; + + for (idx = 0; idx < ARRAY_SIZE(freq_tbl); idx++) { + if (freq <= freq_tbl[idx]) + return idx; + } + + return -1; +} + +static void sso_register_shift_clk(struct sso_led_priv *priv) +{ + int idx, size = ARRAY_SIZE(shift_clk_freq_tbl); + u32 val = 0; + + for (idx = 0; idx < size; idx++) { + if (shift_clk_freq_tbl[idx] <= priv->gpio.shift_clk_freq) { + val = idx; + break; + } + } + + if (idx == size) + dev_warn(priv->dev, "%s: Invalid freq %d\n", + __func__, priv->gpio.shift_clk_freq); + + regmap_update_bits(priv->mmap, SSO_CON1, SSO_CON1_FCDSC, + FIELD_PREP(SSO_CON1_FCDSC, val)); +} + +static int sso_gpio_freq_set(struct sso_led_priv *priv) +{ + int freq_idx; + u32 val; + + freq_idx = sso_gpio_get_freq_idx(priv->gpio.freq); + if (freq_idx == -1) + freq_idx = ARRAY_SIZE(freq_tbl) - 1; + + val = freq_idx % FPID_FREQ_RANK_MAX; + + if (!priv->gpio.freq) { + regmap_update_bits(priv->mmap, SSO_CON0, SSO_CON0_BLINK_R, 0); + regmap_update_bits(priv->mmap, SSO_CON1, SSO_CON1_US, + FIELD_PREP(SSO_CON1_US, US_SW)); + } else if (freq_idx < FPID_FREQ_RANK_MAX) { + regmap_update_bits(priv->mmap, SSO_CON0, SSO_CON0_BLINK_R, + SSO_CON0_BLINK_R); + regmap_update_bits(priv->mmap, SSO_CON1, SSO_CON1_US, + FIELD_PREP(SSO_CON1_US, US_FPID)); + regmap_update_bits(priv->mmap, SSO_CON1, SSO_CON1_FPID, + FIELD_PREP(SSO_CON1_FPID, val)); + } else { + regmap_update_bits(priv->mmap, SSO_CON0, SSO_CON0_BLINK_R, + SSO_CON0_BLINK_R); + regmap_update_bits(priv->mmap, SSO_CON1, SSO_CON1_US, + FIELD_PREP(SSO_CON1_US, US_GPTC)); + regmap_update_bits(priv->mmap, SSO_CON1, SSO_CON1_GPTD, + FIELD_PREP(SSO_CON1_GPTD, val)); + } + + return 0; +} + +static int sso_gpio_hw_init(struct sso_led_priv *priv) +{ + u32 activate; + int i, err; + + /* Clear all duty cycles */ + for (i = 0; i < priv->gpio.pins; i++) { + err = regmap_write(priv->mmap, DUTY_CYCLE(i), 0); + if (err) + return err; + } + + /* 4 groups for total 32 pins */ + for (i = 1; i <= MAX_GROUP_NUM; i++) { + activate = !!(i * PINS_PER_GROUP <= priv->gpio.pins || + priv->gpio.pins > (i - 1) * PINS_PER_GROUP); + err = regmap_update_bits(priv->mmap, SSO_CON1, BIT(i - 1), + activate << (i - 1)); + if (err) + return err; + } + + /* NO HW directly controlled pin by default */ + err = regmap_write(priv->mmap, SSO_CON3, 0); + if (err) + return err; + + /* NO BLINK for all pins */ + err = regmap_write(priv->mmap, SSO_CON2, 0); + if (err) + return err; + + /* OUTPUT 0 by default */ + err = regmap_write(priv->mmap, SSO_CPU, 0); + if (err) + return err; + + /* update edge */ + err = regmap_update_bits(priv->mmap, SSO_CON0, SSO_CON0_RZFL, + FIELD_PREP(SSO_CON0_RZFL, priv->gpio.edge)); + if (err) + return err; + + /* Set GPIO update rate */ + sso_gpio_freq_set(priv); + + /* Register shift clock */ + sso_register_shift_clk(priv); + + return 0; +} + +static void sso_led_shutdown(struct sso_led *led) +{ + struct sso_led_priv *priv = led->priv; + + /* unregister led */ + devm_led_classdev_unregister(priv->dev, &led->cdev); + + /* clear HW control bit */ + if (led->desc.hw_trig) + regmap_update_bits(priv->mmap, SSO_CON3, BIT(led->desc.pin), 0); + + if (led->gpiod) + devm_gpiod_put(priv->dev, led->gpiod); + + led->priv = NULL; +} + +static int +__sso_led_dt_parse(struct sso_led_priv *priv, struct fwnode_handle *fw_ssoled) +{ + struct fwnode_handle *fwnode_child; + struct device *dev = priv->dev; + struct sso_led_desc *desc; + struct sso_led *led; + struct list_head *p; + const char *tmp; + u32 prop; + int ret; + + fwnode_for_each_child_node(fw_ssoled, fwnode_child) { + led = devm_kzalloc(dev, sizeof(*led), GFP_KERNEL); + if (!led) + return -ENOMEM; + + INIT_LIST_HEAD(&led->list); + led->priv = priv; + desc = &led->desc; + + led->gpiod = devm_fwnode_get_gpiod_from_child(dev, NULL, + fwnode_child, + GPIOD_ASIS, NULL); + if (IS_ERR(led->gpiod)) { + dev_err(dev, "led: get gpio fail!\n"); + goto __dt_err; + } + + fwnode_property_read_string(fwnode_child, + "linux,default-trigger", + &desc->default_trigger); + + if (fwnode_property_present(fwnode_child, + "retain-state-suspended")) + desc->retain_state_suspended = 1; + + if (fwnode_property_present(fwnode_child, + "retain-state-shutdown")) + desc->retain_state_shutdown = 1; + + if (fwnode_property_present(fwnode_child, "panic-indicator")) + desc->panic_indicator = 1; + + ret = fwnode_property_read_u32(fwnode_child, "reg", &prop); + if (ret != 0 || prop >= SSO_LED_MAX_NUM) { + dev_err(dev, "invalid LED pin:%u\n", prop); + goto __dt_err; + } + desc->pin = prop; + + if (fwnode_property_present(fwnode_child, "intel,sso-hw-blink")) + desc->hw_blink = 1; + + desc->hw_trig = fwnode_property_read_bool(fwnode_child, + "intel,sso-hw-trigger"); + if (desc->hw_trig) { + desc->default_trigger = NULL; + desc->retain_state_shutdown = 0; + desc->retain_state_suspended = 0; + desc->panic_indicator = 0; + desc->hw_blink = 0; + } + + if (fwnode_property_read_u32(fwnode_child, + "intel,sso-blink-rate-hz", &prop)) { + /* default first freq rate */ + desc->freq_idx = 0; + desc->blink_rate = priv->freq[desc->freq_idx]; + } else { + desc->freq_idx = sso_get_blink_rate_idx(priv, prop); + if (desc->freq_idx == -1) + desc->freq_idx = MAX_FREQ_RANK - 1; + + desc->blink_rate = priv->freq[desc->freq_idx]; + } + + if (!fwnode_property_read_string(fwnode_child, "default-state", &tmp)) { + if (!strcmp(tmp, "on")) + desc->brightness = LED_FULL; + } + + if (sso_create_led(priv, led, fwnode_child)) + goto __dt_err; + } + fwnode_handle_put(fw_ssoled); + + return 0; +__dt_err: + fwnode_handle_put(fw_ssoled); + /* unregister leds */ + list_for_each(p, &priv->led_list) { + led = list_entry(p, struct sso_led, list); + sso_led_shutdown(led); + } + + return -EINVAL; +} + +static int sso_led_dt_parse(struct sso_led_priv *priv) +{ + struct fwnode_handle *fwnode = dev_fwnode(priv->dev); + struct fwnode_handle *fw_ssoled; + struct device *dev = priv->dev; + int count; + int ret; + + count = device_get_child_node_count(dev); + if (!count) + return 0; + + fw_ssoled = fwnode_get_named_child_node(fwnode, "ssoled"); + if (fw_ssoled) { + ret = __sso_led_dt_parse(priv, fw_ssoled); + if (ret) + return ret; + } + + return 0; +} + +static int sso_probe_gpios(struct sso_led_priv *priv) +{ + struct device *dev = priv->dev; + int ret; + + if (device_property_read_u32(dev, "ngpios", &priv->gpio.pins)) + priv->gpio.pins = MAX_PIN_NUM_PER_BANK; + + if (priv->gpio.pins > MAX_PIN_NUM_PER_BANK) + return -EINVAL; + + if (device_property_read_u32(dev, "intel,sso-update-rate-hz", + &priv->gpio.freq)) + priv->gpio.freq = 0; + + priv->gpio.edge = DATA_CLK_EDGE; + priv->gpio.shift_clk_freq = -1; + + ret = sso_gpio_hw_init(priv); + if (ret) + return ret; + + return sso_gpio_gc_init(dev, priv); +} + +static void sso_clk_disable(void *data) +{ + struct sso_led_priv *priv = data; + + clk_disable_unprepare(priv->fpid_clk); + clk_disable_unprepare(priv->gclk); +} + +static int intel_sso_led_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct sso_led_priv *priv; + int ret; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->pdev = pdev; + priv->dev = dev; + + /* gate clock */ + priv->gclk = devm_clk_get(dev, "sso"); + if (IS_ERR(priv->gclk)) { + dev_err(dev, "get sso gate clock failed!\n"); + return PTR_ERR(priv->gclk); + } + + ret = clk_prepare_enable(priv->gclk); + if (ret) { + dev_err(dev, "Failed to prepate/enable sso gate clock!\n"); + return ret; + } + + priv->fpid_clk = devm_clk_get(dev, "fpid"); + if (IS_ERR(priv->fpid_clk)) { + dev_err(dev, "Failed to get fpid clock!\n"); + return PTR_ERR(priv->fpid_clk); + } + + ret = clk_prepare_enable(priv->fpid_clk); + if (ret) { + dev_err(dev, "Failed to prepare/enable fpid clock!\n"); + return ret; + } + priv->fpid_clkrate = clk_get_rate(priv->fpid_clk); + + ret = devm_add_action_or_reset(dev, sso_clk_disable, priv); + if (ret) { + dev_err(dev, "Failed to devm_add_action_or_reset, %d\n", ret); + return ret; + } + + priv->mmap = syscon_node_to_regmap(dev->of_node); + if (IS_ERR(priv->mmap)) { + dev_err(dev, "Failed to map iomem!\n"); + return PTR_ERR(priv->mmap); + } + + ret = sso_probe_gpios(priv); + if (ret) { + regmap_exit(priv->mmap); + return ret; + } + + INIT_LIST_HEAD(&priv->led_list); + + platform_set_drvdata(pdev, priv); + sso_init_freq(priv); + + priv->gptc_clkrate = DEF_GPTC_CLK_RATE; + + ret = sso_led_dt_parse(priv); + if (ret) { + regmap_exit(priv->mmap); + return ret; + } + dev_info(priv->dev, "sso LED init success!\n"); + + return 0; +} + +static int intel_sso_led_remove(struct platform_device *pdev) +{ + struct sso_led_priv *priv; + struct list_head *pos, *n; + struct sso_led *led; + + priv = platform_get_drvdata(pdev); + + list_for_each_safe(pos, n, &priv->led_list) { + list_del(pos); + led = list_entry(pos, struct sso_led, list); + sso_led_shutdown(led); + } + + clk_disable_unprepare(priv->fpid_clk); + clk_disable_unprepare(priv->gclk); + regmap_exit(priv->mmap); + + return 0; +} + +static const struct of_device_id of_sso_led_match[] = { + { .compatible = "intel,lgm-ssoled" }, + {} +}; + +MODULE_DEVICE_TABLE(of, of_sso_led_match); + +static struct platform_driver intel_sso_led_driver = { + .probe = intel_sso_led_probe, + .remove = intel_sso_led_remove, + .driver = { + .name = "lgm-ssoled", + .of_match_table = of_match_ptr(of_sso_led_match), + }, +}; + +module_platform_driver(intel_sso_led_driver); + +MODULE_DESCRIPTION("Intel SSO LED/GPIO driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 131ca83f5fb3..2e495ff67856 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -145,8 +145,7 @@ static void led_remove_brightness_hw_changed(struct led_classdev *led_cdev) device_remove_file(led_cdev->dev, &dev_attr_brightness_hw_changed); } -void led_classdev_notify_brightness_hw_changed(struct led_classdev *led_cdev, - enum led_brightness brightness) +void led_classdev_notify_brightness_hw_changed(struct led_classdev *led_cdev, unsigned int brightness) { if (WARN_ON(!led_cdev->brightness_hw_changed_kn)) return; diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c index c4e780bdb385..8eb8054ef9c6 100644 --- a/drivers/leds/led-core.c +++ b/drivers/leds/led-core.c @@ -39,8 +39,7 @@ const char * const led_colors[LED_COLOR_ID_MAX] = { }; EXPORT_SYMBOL_GPL(led_colors); -static int __led_set_brightness(struct led_classdev *led_cdev, - enum led_brightness value) +static int __led_set_brightness(struct led_classdev *led_cdev, unsigned int value) { if (!led_cdev->brightness_set) return -ENOTSUPP; @@ -50,8 +49,7 @@ static int __led_set_brightness(struct led_classdev *led_cdev, return 0; } -static int __led_set_brightness_blocking(struct led_classdev *led_cdev, - enum led_brightness value) +static int __led_set_brightness_blocking(struct led_classdev *led_cdev, unsigned int value) { if (!led_cdev->brightness_set_blocking) return -ENOTSUPP; @@ -240,8 +238,7 @@ void led_stop_software_blink(struct led_classdev *led_cdev) } EXPORT_SYMBOL_GPL(led_stop_software_blink); -void led_set_brightness(struct led_classdev *led_cdev, - enum led_brightness brightness) +void led_set_brightness(struct led_classdev *led_cdev, unsigned int brightness) { /* * If software blink is active, delay brightness setting @@ -253,7 +250,7 @@ void led_set_brightness(struct led_classdev *led_cdev, * work queue task to avoid problems in case we are called * from hard irq context. */ - if (brightness == LED_OFF) { + if (!brightness) { set_bit(LED_BLINK_DISABLE, &led_cdev->work_flags); schedule_work(&led_cdev->set_brightness_work); } else { @@ -268,8 +265,7 @@ void led_set_brightness(struct led_classdev *led_cdev, } EXPORT_SYMBOL_GPL(led_set_brightness); -void led_set_brightness_nopm(struct led_classdev *led_cdev, - enum led_brightness value) +void led_set_brightness_nopm(struct led_classdev *led_cdev, unsigned int value) { /* Use brightness_set op if available, it is guaranteed not to sleep */ if (!__led_set_brightness(led_cdev, value)) @@ -281,8 +277,7 @@ void led_set_brightness_nopm(struct led_classdev *led_cdev, } EXPORT_SYMBOL_GPL(led_set_brightness_nopm); -void led_set_brightness_nosleep(struct led_classdev *led_cdev, - enum led_brightness value) +void led_set_brightness_nosleep(struct led_classdev *led_cdev, unsigned int value) { led_cdev->brightness = min(value, led_cdev->max_brightness); @@ -293,8 +288,7 @@ void led_set_brightness_nosleep(struct led_classdev *led_cdev, } EXPORT_SYMBOL_GPL(led_set_brightness_nosleep); -int led_set_brightness_sync(struct led_classdev *led_cdev, - enum led_brightness value) +int led_set_brightness_sync(struct led_classdev *led_cdev, unsigned int value) { if (led_cdev->blink_delay_on || led_cdev->blink_delay_off) return -EBUSY; diff --git a/drivers/leds/leds-apu.c b/drivers/leds/leds-apu.c index 7fd557aceff6..c409b80c236d 100644 --- a/drivers/leds/leds-apu.c +++ b/drivers/leds/leds-apu.c @@ -83,6 +83,7 @@ static const struct apu_led_profile apu1_led_profile[] = { }; static const struct dmi_system_id apu_led_dmi_table[] __initconst = { + /* PC Engines APU with factory bios "SageBios_PCEngines_APU-45" */ { .ident = "apu", .matches = { @@ -90,6 +91,14 @@ static const struct dmi_system_id apu_led_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "APU") } }, + /* PC Engines APU with "Mainline" bios >= 4.6.8 */ + { + .ident = "apu", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "PC Engines"), + DMI_MATCH(DMI_PRODUCT_NAME, "apu1") + } + }, {} }; MODULE_DEVICE_TABLE(dmi, apu_led_dmi_table); @@ -173,7 +182,7 @@ static int __init apu_led_init(void) int err; if (!(dmi_match(DMI_SYS_VENDOR, "PC Engines") && - dmi_match(DMI_PRODUCT_NAME, "APU"))) { + (dmi_match(DMI_PRODUCT_NAME, "APU") || dmi_match(DMI_PRODUCT_NAME, "apu1")))) { pr_err("No PC Engines APUv1 board detected. For APUv2,3 support, enable CONFIG_PCENGINES_APU2\n"); return -ENODEV; } diff --git a/drivers/leds/leds-blinkm.c b/drivers/leds/leds-blinkm.c index e11fe1788242..b4e1fdff4186 100644 --- a/drivers/leds/leds-blinkm.c +++ b/drivers/leds/leds-blinkm.c @@ -192,13 +192,13 @@ static int store_color_common(struct device *dev, const char *buf, int color) return 0; } -static ssize_t show_red(struct device *dev, struct device_attribute *attr, +static ssize_t red_show(struct device *dev, struct device_attribute *attr, char *buf) { return show_color_common(dev, buf, RED); } -static ssize_t store_red(struct device *dev, struct device_attribute *attr, +static ssize_t red_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int ret; @@ -209,15 +209,15 @@ static ssize_t store_red(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(red, S_IRUGO | S_IWUSR, show_red, store_red); +static DEVICE_ATTR_RW(red); -static ssize_t show_green(struct device *dev, struct device_attribute *attr, +static ssize_t green_show(struct device *dev, struct device_attribute *attr, char *buf) { return show_color_common(dev, buf, GREEN); } -static ssize_t store_green(struct device *dev, struct device_attribute *attr, +static ssize_t green_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -229,15 +229,15 @@ static ssize_t store_green(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(green, S_IRUGO | S_IWUSR, show_green, store_green); +static DEVICE_ATTR_RW(green); -static ssize_t show_blue(struct device *dev, struct device_attribute *attr, +static ssize_t blue_show(struct device *dev, struct device_attribute *attr, char *buf) { return show_color_common(dev, buf, BLUE); } -static ssize_t store_blue(struct device *dev, struct device_attribute *attr, +static ssize_t blue_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int ret; @@ -248,16 +248,16 @@ static ssize_t store_blue(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(blue, S_IRUGO | S_IWUSR, show_blue, store_blue); +static DEVICE_ATTR_RW(blue); -static ssize_t show_test(struct device *dev, struct device_attribute *attr, +static ssize_t test_show(struct device *dev, struct device_attribute *attr, char *buf) { return scnprintf(buf, PAGE_SIZE, "#Write into test to start test sequence!#\n"); } -static ssize_t store_test(struct device *dev, struct device_attribute *attr, +static ssize_t test_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -273,7 +273,7 @@ static ssize_t store_test(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(test, S_IRUGO | S_IWUSR, show_test, store_test); +static DEVICE_ATTR_RW(test); /* TODO: HSB, fade, timeadj, script ... */ diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c index 93f5b1b60fde..b5d5e22d2d1e 100644 --- a/drivers/leds/leds-gpio.c +++ b/drivers/leds/leds-gpio.c @@ -96,7 +96,8 @@ static int create_gpio_led(const struct gpio_led *template, } else { state = (template->default_state == LEDS_GPIO_DEFSTATE_ON); } - led_dat->cdev.brightness = state ? LED_FULL : LED_OFF; + led_dat->cdev.brightness = state; + led_dat->cdev.max_brightness = 1; if (!template->retain_state_suspended) led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME; if (template->panic_indicator) diff --git a/drivers/leds/leds-lm3530.c b/drivers/leds/leds-lm3530.c index 2f8362f6bf75..2db455efd4b1 100644 --- a/drivers/leds/leds-lm3530.c +++ b/drivers/leds/leds-lm3530.c @@ -346,8 +346,8 @@ static void lm3530_brightness_set(struct led_classdev *led_cdev, } } -static ssize_t lm3530_mode_get(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t mode_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct led_classdev *led_cdev = dev_get_drvdata(dev); struct lm3530_data *drvdata; @@ -365,8 +365,8 @@ static ssize_t lm3530_mode_get(struct device *dev, return len; } -static ssize_t lm3530_mode_set(struct device *dev, struct device_attribute - *attr, const char *buf, size_t size) +static ssize_t mode_store(struct device *dev, struct device_attribute + *attr, const char *buf, size_t size) { struct led_classdev *led_cdev = dev_get_drvdata(dev); struct lm3530_data *drvdata; @@ -397,7 +397,7 @@ static ssize_t lm3530_mode_set(struct device *dev, struct device_attribute return sizeof(drvdata->mode); } -static DEVICE_ATTR(mode, 0644, lm3530_mode_get, lm3530_mode_set); +static DEVICE_ATTR_RW(mode); static struct attribute *lm3530_attrs[] = { &dev_attr_mode.attr, diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c index 9dd205870525..43d5970d96aa 100644 --- a/drivers/leds/leds-lm3533.c +++ b/drivers/leds/leds-lm3533.c @@ -608,7 +608,7 @@ static struct attribute *lm3533_led_attributes[] = { static umode_t lm3533_led_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct led_classdev *led_cdev = dev_get_drvdata(dev); struct lm3533_led *led = to_lm3533_led(led_cdev); umode_t mode = attr->mode; diff --git a/drivers/leds/leds-lm355x.c b/drivers/leds/leds-lm355x.c index 1505521249b5..2d3e11845ba5 100644 --- a/drivers/leds/leds-lm355x.c +++ b/drivers/leds/leds-lm355x.c @@ -349,9 +349,9 @@ static int lm355x_indicator_brightness_set(struct led_classdev *cdev, } /* indicator pattern only for lm3556*/ -static ssize_t lm3556_indicator_pattern_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t size) +static ssize_t pattern_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) { ssize_t ret; struct led_classdev *led_cdev = dev_get_drvdata(dev); @@ -381,7 +381,7 @@ static ssize_t lm3556_indicator_pattern_store(struct device *dev, return ret; } -static DEVICE_ATTR(pattern, S_IWUSR, NULL, lm3556_indicator_pattern_store); +static DEVICE_ATTR_WO(pattern); static struct attribute *lm355x_indicator_attrs[] = { &dev_attr_pattern.attr, diff --git a/drivers/leds/leds-lm3642.c b/drivers/leds/leds-lm3642.c index 62c14872caf7..8007b82985a8 100644 --- a/drivers/leds/leds-lm3642.c +++ b/drivers/leds/leds-lm3642.c @@ -165,9 +165,9 @@ static int lm3642_control(struct lm3642_chip_data *chip, /* torch */ /* torch pin config for lm3642 */ -static ssize_t lm3642_torch_pin_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t size) +static ssize_t torch_pin_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) { ssize_t ret; struct led_classdev *led_cdev = dev_get_drvdata(dev); @@ -193,7 +193,7 @@ static ssize_t lm3642_torch_pin_store(struct device *dev, return size; } -static DEVICE_ATTR(torch_pin, S_IWUSR, NULL, lm3642_torch_pin_store); +static DEVICE_ATTR_WO(torch_pin); static int lm3642_torch_brightness_set(struct led_classdev *cdev, enum led_brightness brightness) @@ -212,9 +212,9 @@ static int lm3642_torch_brightness_set(struct led_classdev *cdev, /* flash */ /* strobe pin config for lm3642*/ -static ssize_t lm3642_strobe_pin_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t size) +static ssize_t strobe_pin_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) { ssize_t ret; struct led_classdev *led_cdev = dev_get_drvdata(dev); @@ -240,7 +240,7 @@ static ssize_t lm3642_strobe_pin_store(struct device *dev, return size; } -static DEVICE_ATTR(strobe_pin, S_IWUSR, NULL, lm3642_strobe_pin_store); +static DEVICE_ATTR_WO(strobe_pin); static int lm3642_strobe_brightness_set(struct led_classdev *cdev, enum led_brightness brightness) diff --git a/drivers/leds/leds-lp50xx.c b/drivers/leds/leds-lp50xx.c index f13117eed976..06230614fdc5 100644 --- a/drivers/leds/leds-lp50xx.c +++ b/drivers/leds/leds-lp50xx.c @@ -6,10 +6,9 @@ #include #include #include +#include #include #include -#include -#include #include #include #include @@ -322,7 +321,7 @@ static int lp50xx_brightness_set(struct led_classdev *cdev, ret = regmap_write(led->priv->regmap, reg_val, brightness); if (ret) { - dev_err(&led->priv->client->dev, + dev_err(led->priv->dev, "Cannot write brightness value %d\n", ret); goto out; } @@ -338,7 +337,7 @@ static int lp50xx_brightness_set(struct led_classdev *cdev, ret = regmap_write(led->priv->regmap, reg_val, mc_dev->subled_info[i].intensity); if (ret) { - dev_err(&led->priv->client->dev, + dev_err(led->priv->dev, "Cannot write intensity value %d\n", ret); goto out; } @@ -360,8 +359,8 @@ static int lp50xx_set_banks(struct lp50xx *priv, u32 led_banks[]) bank_enable_mask |= (1 << led_banks[i]); } - led_config_lo = (u8)(bank_enable_mask & 0xff); - led_config_hi = (u8)(bank_enable_mask >> 8) & 0xff; + led_config_lo = bank_enable_mask; + led_config_hi = bank_enable_mask >> 8; ret = regmap_write(priv->regmap, LP50XX_LED_CFG0, led_config_lo); if (ret) @@ -382,11 +381,9 @@ static int lp50xx_enable_disable(struct lp50xx *priv, int enable_disable) { int ret; - if (priv->enable_gpio) { - ret = gpiod_direction_output(priv->enable_gpio, enable_disable); - if (ret) - return ret; - } + ret = gpiod_direction_output(priv->enable_gpio, enable_disable); + if (ret) + return ret; if (enable_disable) return regmap_write(priv->regmap, LP50XX_DEV_CFG0, LP50XX_CHIP_EN); @@ -404,7 +401,7 @@ static int lp50xx_probe_leds(struct fwnode_handle *child, struct lp50xx *priv, if (num_leds > 1) { if (num_leds > priv->chip_info->max_modules) { - dev_err(&priv->client->dev, "reg property is invalid\n"); + dev_err(priv->dev, "reg property is invalid\n"); return -EINVAL; } @@ -412,13 +409,13 @@ static int lp50xx_probe_leds(struct fwnode_handle *child, struct lp50xx *priv, ret = fwnode_property_read_u32_array(child, "reg", led_banks, num_leds); if (ret) { - dev_err(&priv->client->dev, "reg property is missing\n"); + dev_err(priv->dev, "reg property is missing\n"); return ret; } ret = lp50xx_set_banks(priv, led_banks); if (ret) { - dev_err(&priv->client->dev, "Cannot setup banked LEDs\n"); + dev_err(priv->dev, "Cannot setup banked LEDs\n"); return ret; } @@ -426,12 +423,12 @@ static int lp50xx_probe_leds(struct fwnode_handle *child, struct lp50xx *priv, } else { ret = fwnode_property_read_u32(child, "reg", &led_number); if (ret) { - dev_err(&priv->client->dev, "led reg property missing\n"); + dev_err(priv->dev, "led reg property missing\n"); return ret; } if (led_number > priv->chip_info->num_leds) { - dev_err(&priv->client->dev, "led-sources property is invalid\n"); + dev_err(priv->dev, "led-sources property is invalid\n"); return -EINVAL; } @@ -455,12 +452,9 @@ static int lp50xx_probe_dt(struct lp50xx *priv) int i = 0; priv->enable_gpio = devm_gpiod_get_optional(priv->dev, "enable", GPIOD_OUT_LOW); - if (IS_ERR(priv->enable_gpio)) { - ret = PTR_ERR(priv->enable_gpio); - dev_err(&priv->client->dev, "Failed to get enable gpio: %d\n", - ret); - return ret; - } + if (IS_ERR(priv->enable_gpio)) + return dev_err_probe(priv->dev, PTR_ERR(priv->enable_gpio), + "Failed to get enable GPIO\n"); priv->regulator = devm_regulator_get(priv->dev, "vled"); if (IS_ERR(priv->regulator)) @@ -470,7 +464,7 @@ static int lp50xx_probe_dt(struct lp50xx *priv) led = &priv->leds[i]; ret = fwnode_property_count_u32(child, "reg"); if (ret < 0) { - dev_err(&priv->client->dev, "reg property is invalid\n"); + dev_err(priv->dev, "reg property is invalid\n"); goto child_out; } @@ -510,12 +504,11 @@ static int lp50xx_probe_dt(struct lp50xx *priv) led_cdev = &led->mc_cdev.led_cdev; led_cdev->brightness_set_blocking = lp50xx_brightness_set; - ret = devm_led_classdev_multicolor_register_ext(&priv->client->dev, + ret = devm_led_classdev_multicolor_register_ext(priv->dev, &led->mc_cdev, &init_data); if (ret) { - dev_err(&priv->client->dev, "led register err: %d\n", - ret); + dev_err(priv->dev, "led register err: %d\n", ret); goto child_out; } i++; @@ -529,8 +522,7 @@ static int lp50xx_probe_dt(struct lp50xx *priv) return ret; } -static int lp50xx_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int lp50xx_probe(struct i2c_client *client) { struct lp50xx *led; int count; @@ -550,7 +542,7 @@ static int lp50xx_probe(struct i2c_client *client, mutex_init(&led->lock); led->client = client; led->dev = &client->dev; - led->chip_info = &lp50xx_chip_info_tbl[id->driver_data]; + led->chip_info = device_get_match_data(&client->dev); i2c_set_clientdata(client, led); led->regmap = devm_regmap_init_i2c(client, led->chip_info->lp50xx_regmap_config); @@ -579,15 +571,14 @@ static int lp50xx_remove(struct i2c_client *client) ret = lp50xx_enable_disable(led, 0); if (ret) { - dev_err(&led->client->dev, "Failed to disable chip\n"); + dev_err(led->dev, "Failed to disable chip\n"); return ret; } if (led->regulator) { ret = regulator_disable(led->regulator); if (ret) - dev_err(&led->client->dev, - "Failed to disable regulator\n"); + dev_err(led->dev, "Failed to disable regulator\n"); } mutex_destroy(&led->lock); @@ -596,24 +587,24 @@ static int lp50xx_remove(struct i2c_client *client) } static const struct i2c_device_id lp50xx_id[] = { - { "lp5009", LP5009 }, - { "lp5012", LP5012 }, - { "lp5018", LP5018 }, - { "lp5024", LP5024 }, - { "lp5030", LP5030 }, - { "lp5036", LP5036 }, + { "lp5009", (kernel_ulong_t)&lp50xx_chip_info_tbl[LP5009] }, + { "lp5012", (kernel_ulong_t)&lp50xx_chip_info_tbl[LP5012] }, + { "lp5018", (kernel_ulong_t)&lp50xx_chip_info_tbl[LP5018] }, + { "lp5024", (kernel_ulong_t)&lp50xx_chip_info_tbl[LP5024] }, + { "lp5030", (kernel_ulong_t)&lp50xx_chip_info_tbl[LP5030] }, + { "lp5036", (kernel_ulong_t)&lp50xx_chip_info_tbl[LP5036] }, { } }; MODULE_DEVICE_TABLE(i2c, lp50xx_id); static const struct of_device_id of_lp50xx_leds_match[] = { - { .compatible = "ti,lp5009", .data = (void *)LP5009 }, - { .compatible = "ti,lp5012", .data = (void *)LP5012 }, - { .compatible = "ti,lp5018", .data = (void *)LP5018 }, - { .compatible = "ti,lp5024", .data = (void *)LP5024 }, - { .compatible = "ti,lp5030", .data = (void *)LP5030 }, - { .compatible = "ti,lp5036", .data = (void *)LP5036 }, - {}, + { .compatible = "ti,lp5009", .data = &lp50xx_chip_info_tbl[LP5009] }, + { .compatible = "ti,lp5012", .data = &lp50xx_chip_info_tbl[LP5012] }, + { .compatible = "ti,lp5018", .data = &lp50xx_chip_info_tbl[LP5018] }, + { .compatible = "ti,lp5024", .data = &lp50xx_chip_info_tbl[LP5024] }, + { .compatible = "ti,lp5030", .data = &lp50xx_chip_info_tbl[LP5030] }, + { .compatible = "ti,lp5036", .data = &lp50xx_chip_info_tbl[LP5036] }, + {} }; MODULE_DEVICE_TABLE(of, of_lp50xx_leds_match); @@ -622,7 +613,7 @@ static struct i2c_driver lp50xx_driver = { .name = "lp50xx", .of_match_table = of_lp50xx_leds_match, }, - .probe = lp50xx_probe, + .probe_new = lp50xx_probe, .remove = lp50xx_remove, .id_table = lp50xx_id, }; diff --git a/drivers/leds/leds-max8997.c b/drivers/leds/leds-max8997.c index 512a11d142d0..c0bddb33888d 100644 --- a/drivers/leds/leds-max8997.c +++ b/drivers/leds/leds-max8997.c @@ -160,8 +160,8 @@ static void max8997_led_brightness_set(struct led_classdev *led_cdev, } } -static ssize_t max8997_led_show_mode(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t mode_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct led_classdev *led_cdev = dev_get_drvdata(dev); struct max8997_led *led = @@ -193,9 +193,9 @@ static ssize_t max8997_led_show_mode(struct device *dev, return ret; } -static ssize_t max8997_led_store_mode(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t size) +static ssize_t mode_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) { struct led_classdev *led_cdev = dev_get_drvdata(dev); struct max8997_led *led = @@ -222,7 +222,7 @@ static ssize_t max8997_led_store_mode(struct device *dev, return size; } -static DEVICE_ATTR(mode, 0644, max8997_led_show_mode, max8997_led_store_mode); +static DEVICE_ATTR_RW(mode); static struct attribute *max8997_attrs[] = { &dev_attr_mode.attr, diff --git a/drivers/leds/leds-netxbig.c b/drivers/leds/leds-netxbig.c index 68fbf0b66fad..77213b79f84d 100644 --- a/drivers/leds/leds-netxbig.c +++ b/drivers/leds/leds-netxbig.c @@ -204,9 +204,9 @@ static void netxbig_led_set(struct led_classdev *led_cdev, spin_unlock_irqrestore(&led_dat->lock, flags); } -static ssize_t netxbig_led_sata_store(struct device *dev, - struct device_attribute *attr, - const char *buff, size_t count) +static ssize_t sata_store(struct device *dev, + struct device_attribute *attr, + const char *buff, size_t count) { struct led_classdev *led_cdev = dev_get_drvdata(dev); struct netxbig_led_data *led_dat = @@ -255,8 +255,8 @@ static ssize_t netxbig_led_sata_store(struct device *dev, return ret; } -static ssize_t netxbig_led_sata_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t sata_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct led_classdev *led_cdev = dev_get_drvdata(dev); struct netxbig_led_data *led_dat = @@ -265,7 +265,7 @@ static ssize_t netxbig_led_sata_show(struct device *dev, return sprintf(buf, "%d\n", led_dat->sata); } -static DEVICE_ATTR(sata, 0644, netxbig_led_sata_show, netxbig_led_sata_store); +static DEVICE_ATTR_RW(sata); static struct attribute *netxbig_led_attrs[] = { &dev_attr_sata.attr, diff --git a/drivers/leds/leds-ss4200.c b/drivers/leds/leds-ss4200.c index 245de443fe9c..fcaa34706b6c 100644 --- a/drivers/leds/leds-ss4200.c +++ b/drivers/leds/leds-ss4200.c @@ -441,8 +441,8 @@ static void set_power_light_amber_noblink(void) nasgpio_led_set_brightness(&amber->led_cdev, LED_FULL); } -static ssize_t nas_led_blink_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t blink_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct led_classdev *led = dev_get_drvdata(dev); int blinking = 0; @@ -451,9 +451,9 @@ static ssize_t nas_led_blink_show(struct device *dev, return sprintf(buf, "%u\n", blinking); } -static ssize_t nas_led_blink_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t size) +static ssize_t blink_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) { int ret; struct led_classdev *led = dev_get_drvdata(dev); @@ -468,7 +468,7 @@ static ssize_t nas_led_blink_store(struct device *dev, return size; } -static DEVICE_ATTR(blink, 0644, nas_led_blink_show, nas_led_blink_store); +static DEVICE_ATTR_RW(blink); static struct attribute *nasgpio_led_attrs[] = { &dev_attr_blink.attr, @@ -478,7 +478,6 @@ ATTRIBUTE_GROUPS(nasgpio_led); static int register_nasgpio_led(int led_nr) { - int ret; struct nasgpio_led *nas_led = &nasgpio_leds[led_nr]; struct led_classdev *led = get_classdev_for_led_nr(led_nr); @@ -489,11 +488,8 @@ static int register_nasgpio_led(int led_nr) led->brightness_set = nasgpio_led_set_brightness; led->blink_set = nasgpio_led_set_blink; led->groups = nasgpio_led_groups; - ret = led_classdev_register(&nas_gpio_pci_dev->dev, led); - if (ret) - return ret; - return 0; + return led_classdev_register(&nas_gpio_pci_dev->dev, led); } static void unregister_nasgpio_led(int led_nr) diff --git a/drivers/leds/leds-wm831x-status.c b/drivers/leds/leds-wm831x-status.c index 67f4235cb28a..c48b80574f02 100644 --- a/drivers/leds/leds-wm831x-status.c +++ b/drivers/leds/leds-wm831x-status.c @@ -155,8 +155,8 @@ static const char * const led_src_texts[] = { "soft", }; -static ssize_t wm831x_status_src_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t src_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct led_classdev *led_cdev = dev_get_drvdata(dev); struct wm831x_status *led = to_wm831x_status(led_cdev); @@ -178,9 +178,9 @@ static ssize_t wm831x_status_src_show(struct device *dev, return ret; } -static ssize_t wm831x_status_src_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t size) +static ssize_t src_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) { struct led_classdev *led_cdev = dev_get_drvdata(dev); struct wm831x_status *led = to_wm831x_status(led_cdev); @@ -197,7 +197,7 @@ static ssize_t wm831x_status_src_store(struct device *dev, return size; } -static DEVICE_ATTR(src, 0644, wm831x_status_src_show, wm831x_status_src_store); +static DEVICE_ATTR_RW(src); static struct attribute *wm831x_status_attrs[] = { &dev_attr_src.attr, diff --git a/drivers/leds/leds.h b/drivers/leds/leds.h index 2d9eb48bbed9..345062ccabda 100644 --- a/drivers/leds/leds.h +++ b/drivers/leds/leds.h @@ -19,10 +19,8 @@ static inline int led_get_brightness(struct led_classdev *led_cdev) void led_init_core(struct led_classdev *led_cdev); void led_stop_software_blink(struct led_classdev *led_cdev); -void led_set_brightness_nopm(struct led_classdev *led_cdev, - enum led_brightness value); -void led_set_brightness_nosleep(struct led_classdev *led_cdev, - enum led_brightness value); +void led_set_brightness_nopm(struct led_classdev *led_cdev, unsigned int value); +void led_set_brightness_nosleep(struct led_classdev *led_cdev, unsigned int value); ssize_t led_trigger_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t pos, size_t count); diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 45d12b0e9a2f..b09bed554f26 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -88,7 +88,7 @@ config WIREGUARD select CRYPTO_CURVE25519_X86 if X86 && 64BIT select ARM_CRYPTO if ARM select ARM64_CRYPTO if ARM64 - select CRYPTO_CHACHA20_NEON if (ARM || ARM64) && KERNEL_MODE_NEON + select CRYPTO_CHACHA20_NEON if ARM || (ARM64 && KERNEL_MODE_NEON) select CRYPTO_POLY1305_NEON if ARM64 && KERNEL_MODE_NEON select CRYPTO_POLY1305_ARM if ARM select CRYPTO_BLAKE2S_ARM if ARM diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index d9281ae853f8..311d8564d611 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -239,6 +239,7 @@ void can_setup(struct net_device *dev) struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, unsigned int txqs, unsigned int rxqs) { + struct can_ml_priv *can_ml; struct net_device *dev; struct can_priv *priv; int size; @@ -270,7 +271,8 @@ struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, priv = netdev_priv(dev); priv->dev = dev; - dev->ml_priv = (void *)priv + ALIGN(sizeof_priv, NETDEV_ALIGN); + can_ml = (void *)priv + ALIGN(sizeof_priv, NETDEV_ALIGN); + can_set_ml_priv(dev, can_ml); if (echo_skb_max) { priv->echo_skb_max = echo_skb_max; diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index a1bd1be09548..30c8d53c9745 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -516,6 +516,7 @@ static struct slcan *slc_alloc(void) int i; char name[IFNAMSIZ]; struct net_device *dev = NULL; + struct can_ml_priv *can_ml; struct slcan *sl; int size; @@ -538,7 +539,8 @@ static struct slcan *slc_alloc(void) dev->base_addr = i; sl = netdev_priv(dev); - dev->ml_priv = (void *)sl + ALIGN(sizeof(*sl), NETDEV_ALIGN); + can_ml = (void *)sl + ALIGN(sizeof(*sl), NETDEV_ALIGN); + can_set_ml_priv(dev, can_ml); /* Initialize channel control data */ sl->magic = SLCAN_MAGIC; diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c index 39ca14b0585d..067705e2850b 100644 --- a/drivers/net/can/vcan.c +++ b/drivers/net/can/vcan.c @@ -153,7 +153,7 @@ static void vcan_setup(struct net_device *dev) dev->addr_len = 0; dev->tx_queue_len = 0; dev->flags = IFF_NOARP; - dev->ml_priv = netdev_priv(dev); + can_set_ml_priv(dev, netdev_priv(dev)); /* set flags according to driver capabilities */ if (echo) diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index f9a524c5f6d6..8861a7d875e7 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -141,6 +141,8 @@ static const struct net_device_ops vxcan_netdev_ops = { static void vxcan_setup(struct net_device *dev) { + struct can_ml_priv *can_ml; + dev->type = ARPHRD_CAN; dev->mtu = CANFD_MTU; dev->hard_header_len = 0; @@ -149,7 +151,9 @@ static void vxcan_setup(struct net_device *dev) dev->flags = (IFF_NOARP|IFF_ECHO); dev->netdev_ops = &vxcan_netdev_ops; dev->needs_free_netdev = true; - dev->ml_priv = netdev_priv(dev) + ALIGN(sizeof(struct vxcan_priv), NETDEV_ALIGN); + + can_ml = netdev_priv(dev) + ALIGN(sizeof(struct vxcan_priv), NETDEV_ALIGN); + can_set_ml_priv(dev, can_ml); } /* forward declaration for rtnl_create_link() */ diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index ae86ded1e2a1..a162499bcafc 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -543,6 +543,19 @@ static void b53_port_set_mcast_flood(struct b53_device *dev, int port, b53_write16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, mc); } +static void b53_port_set_learning(struct b53_device *dev, int port, + bool learning) +{ + u16 reg; + + b53_read16(dev, B53_CTRL_PAGE, B53_DIS_LEARNING, ®); + if (learning) + reg &= ~BIT(port); + else + reg |= BIT(port); + b53_write16(dev, B53_CTRL_PAGE, B53_DIS_LEARNING, reg); +} + int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) { struct b53_device *dev = ds->priv; @@ -557,6 +570,7 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) b53_port_set_ucast_flood(dev, port, true); b53_port_set_mcast_flood(dev, port, true); + b53_port_set_learning(dev, port, false); if (dev->ops->irq_enable) ret = dev->ops->irq_enable(dev, port); @@ -691,6 +705,7 @@ static void b53_enable_cpu_port(struct b53_device *dev, int port) b53_port_set_ucast_flood(dev, port, true); b53_port_set_mcast_flood(dev, port, true); + b53_port_set_learning(dev, port, false); } static void b53_enable_mib(struct b53_device *dev) @@ -1953,19 +1968,20 @@ void b53_br_fast_age(struct dsa_switch *ds, int port) } EXPORT_SYMBOL(b53_br_fast_age); -static int b53_br_flags_pre(struct dsa_switch *ds, int port, - struct switchdev_brport_flags flags, - struct netlink_ext_ack *extack) +int b53_br_flags_pre(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) { - if (flags.mask & ~(BR_FLOOD | BR_MCAST_FLOOD)) + if (flags.mask & ~(BR_FLOOD | BR_MCAST_FLOOD | BR_LEARNING)) return -EINVAL; return 0; } +EXPORT_SYMBOL(b53_br_flags_pre); -static int b53_br_flags(struct dsa_switch *ds, int port, - struct switchdev_brport_flags flags, - struct netlink_ext_ack *extack) +int b53_br_flags(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) { if (flags.mask & BR_FLOOD) b53_port_set_ucast_flood(ds->priv, port, @@ -1973,17 +1989,22 @@ static int b53_br_flags(struct dsa_switch *ds, int port, if (flags.mask & BR_MCAST_FLOOD) b53_port_set_mcast_flood(ds->priv, port, !!(flags.val & BR_MCAST_FLOOD)); + if (flags.mask & BR_LEARNING) + b53_port_set_learning(ds->priv, port, + !!(flags.val & BR_LEARNING)); return 0; } +EXPORT_SYMBOL(b53_br_flags); -static int b53_set_mrouter(struct dsa_switch *ds, int port, bool mrouter, - struct netlink_ext_ack *extack) +int b53_set_mrouter(struct dsa_switch *ds, int port, bool mrouter, + struct netlink_ext_ack *extack) { b53_port_set_mcast_flood(ds->priv, port, mrouter); return 0; } +EXPORT_SYMBOL(b53_set_mrouter); static bool b53_possible_cpu_port(struct dsa_switch *ds, int port) { diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index faf983fbca82..8419bb7f4505 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -326,6 +326,14 @@ int b53_br_join(struct dsa_switch *ds, int port, struct net_device *bridge); void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *bridge); void b53_br_set_stp_state(struct dsa_switch *ds, int port, u8 state); void b53_br_fast_age(struct dsa_switch *ds, int port); +int b53_br_flags_pre(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); +int b53_br_flags(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); +int b53_set_mrouter(struct dsa_switch *ds, int port, bool mrouter, + struct netlink_ext_ack *extack); int b53_setup_devlink_resources(struct dsa_switch *ds); void b53_port_event(struct dsa_switch *ds, int port); void b53_phylink_validate(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h index c90985c294a2..b2c539a42154 100644 --- a/drivers/net/dsa/b53/b53_regs.h +++ b/drivers/net/dsa/b53/b53_regs.h @@ -115,6 +115,7 @@ #define B53_UC_FLOOD_MASK 0x32 #define B53_MC_FLOOD_MASK 0x34 #define B53_IPMC_FLOOD_MASK 0x36 +#define B53_DIS_LEARNING 0x3c /* * Override Ports 0-7 State on devices with xMII interfaces (8 bit) diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 1857aa9aa84a..5ee8103b8e9c 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -223,23 +223,10 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port, reg &= ~P_TXQ_PSM_VDD(port); core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL); - /* Enable learning */ - reg = core_readl(priv, CORE_DIS_LEARN); - reg &= ~BIT(port); - core_writel(priv, reg, CORE_DIS_LEARN); - /* Enable Broadcom tags for that port if requested */ - if (priv->brcm_tag_mask & BIT(port)) { + if (priv->brcm_tag_mask & BIT(port)) b53_brcm_hdr_setup(ds, port); - /* Disable learning on ASP port */ - if (port == 7) { - reg = core_readl(priv, CORE_DIS_LEARN); - reg |= BIT(port); - core_writel(priv, reg, CORE_DIS_LEARN); - } - } - /* Configure Traffic Class to QoS mapping, allow each priority to map * to a different queue number */ @@ -1117,7 +1104,10 @@ static const struct dsa_switch_ops bcm_sf2_ops = { .set_mac_eee = b53_set_mac_eee, .port_bridge_join = b53_br_join, .port_bridge_leave = b53_br_leave, + .port_pre_bridge_flags = b53_br_flags_pre, + .port_bridge_flags = b53_br_flags, .port_stp_state_set = b53_br_set_stp_state, + .port_set_mrouter = b53_set_mrouter, .port_fast_age = b53_br_fast_age, .port_vlan_filtering = b53_vlan_filtering, .port_vlan_add = b53_vlan_add, diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c index 139b7b4fbd0d..a8efb7fac395 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.c +++ b/drivers/net/dsa/sja1105/sja1105_static_config.c @@ -85,7 +85,7 @@ u32 sja1105_crc32(const void *buf, size_t len) /* seed */ crc = ~0; for (i = 0; i < len; i += 4) { - sja1105_unpack((void *)buf + i, &word, 31, 0, 4); + sja1105_unpack(buf + i, &word, 31, 0, 4); crc = crc32_le(crc, (u8 *)&word, 4); } return ~crc; diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index dd5c8a9038bb..a60ce9030581 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -223,8 +223,6 @@ #define AG71XX_REG_RX_SM 0x01b0 #define AG71XX_REG_TX_SM 0x01b4 -#define ETH_SWITCH_HEADER_LEN 2 - #define AG71XX_DEFAULT_MSG_ENABLE \ (NETIF_MSG_DRV \ | NETIF_MSG_PROBE \ @@ -933,7 +931,7 @@ static void ag71xx_hw_setup(struct ag71xx *ag) static unsigned int ag71xx_max_frame_len(unsigned int mtu) { - return ETH_SWITCH_HEADER_LEN + ETH_HLEN + VLAN_HLEN + mtu + ETH_FCS_LEN; + return ETH_HLEN + VLAN_HLEN + mtu + ETH_FCS_LEN; } static void ag71xx_hw_set_macaddr(struct ag71xx *ag, unsigned char *mac) diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c index 9be33dc98072..0b70e9e0ddad 100644 --- a/drivers/net/ethernet/broadcom/bcm4908_enet.c +++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c @@ -570,6 +570,7 @@ static int bcm4908_enet_poll(struct napi_struct *napi, int weight) if (len < ETH_ZLEN || (ctl & (DMA_CTL_STATUS_SOP | DMA_CTL_STATUS_EOP)) != (DMA_CTL_STATUS_SOP | DMA_CTL_STATUS_EOP)) { + kfree_skb(slot.skb); enet->netdev->stats.rx_dropped++; break; } @@ -582,6 +583,8 @@ static int bcm4908_enet_poll(struct napi_struct *napi, int weight) enet->netdev->stats.rx_packets++; enet->netdev->stats.rx_bytes += len; + + handled++; } if (handled < weight) { diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index fd8767213165..977f097fc7bf 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1192,7 +1192,6 @@ static int bcm_enet_stop(struct net_device *dev) kdev = &priv->pdev->dev; netif_stop_queue(dev); - netdev_reset_queue(dev); napi_disable(&priv->napi); if (priv->has_phy) phy_stop(dev->phydev); @@ -1231,6 +1230,9 @@ static int bcm_enet_stop(struct net_device *dev) if (priv->has_phy) phy_disconnect(dev->phydev); + /* reset BQL after forced tx reclaim to prevent kernel panic */ + netdev_reset_queue(dev); + return 0; } @@ -2343,7 +2345,6 @@ static int bcm_enetsw_stop(struct net_device *dev) del_timer_sync(&priv->swphy_poll); netif_stop_queue(dev); - netdev_reset_queue(dev); napi_disable(&priv->napi); del_timer_sync(&priv->rx_timeout); @@ -2371,6 +2372,9 @@ static int bcm_enetsw_stop(struct net_device *dev) free_irq(priv->irq_tx, dev); free_irq(priv->irq_rx, dev); + /* reset BQL after forced tx reclaim to prevent kernel panic */ + netdev_reset_queue(dev); + return 0; } diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index ccfe52a50a66..720dc99bd1fc 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2670,7 +2670,6 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, u32 hash; u64 ns; - np = container_of(&portal, struct dpaa_napi_portal, p); dpaa_fq = container_of(fq, struct dpaa_fq, fq_base); fd_status = be32_to_cpu(fd->status); fd_format = qm_fd_get_format(fd); @@ -2685,6 +2684,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, percpu_priv = this_cpu_ptr(priv->percpu_priv); percpu_stats = &percpu_priv->stats; + np = &percpu_priv->np; if (unlikely(dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi))) return qman_cb_dqrr_stop; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 1c0e4beb56e7..118a4bd3f877 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1172,12 +1172,25 @@ static int ibmvnic_open(struct net_device *netdev) struct ibmvnic_adapter *adapter = netdev_priv(netdev); int rc; - /* If device failover is pending, just set device state and return. - * Device operation will be handled by reset routine. + ASSERT_RTNL(); + + /* If device failover is pending or we are about to reset, just set + * device state and return. Device operation will be handled by reset + * routine. + * + * It should be safe to overwrite the adapter->state here. Since + * we hold the rtnl, either the reset has not actually started or + * the rtnl got dropped during the set_link_state() in do_reset(). + * In the former case, no one else is changing the state (again we + * have the rtnl) and in the latter case, do_reset() will detect and + * honor our setting below. */ - if (adapter->failover_pending) { + if (adapter->failover_pending || (test_bit(0, &adapter->resetting))) { + netdev_dbg(netdev, "[S:%d FOP:%d] Resetting, deferring open\n", + adapter->state, adapter->failover_pending); adapter->state = VNIC_OPEN; - return 0; + rc = 0; + goto out; } if (adapter->state != VNIC_CLOSED) { @@ -1196,10 +1209,12 @@ static int ibmvnic_open(struct net_device *netdev) rc = __ibmvnic_open(netdev); out: - /* If open fails due to a pending failover, set device state and - * return. Device operation will be handled by reset routine. + /* If open failed and there is a pending failover or in-progress reset, + * set device state and return. Device operation will be handled by + * reset routine. See also comments above regarding rtnl. */ - if (rc && adapter->failover_pending) { + if (rc && + (adapter->failover_pending || (test_bit(0, &adapter->resetting)))) { adapter->state = VNIC_OPEN; rc = 0; } @@ -1928,6 +1943,14 @@ static int do_reset(struct ibmvnic_adapter *adapter, if (rwi->reset_reason == VNIC_RESET_FAILOVER) adapter->failover_pending = false; + /* read the state and check (again) after getting rtnl */ + reset_state = adapter->state; + + if (reset_state == VNIC_REMOVING || reset_state == VNIC_REMOVED) { + rc = -EBUSY; + goto out; + } + netif_carrier_off(netdev); old_num_rx_queues = adapter->req_rx_queues; @@ -1958,11 +1981,27 @@ static int do_reset(struct ibmvnic_adapter *adapter, if (rc) goto out; + if (adapter->state == VNIC_OPEN) { + /* When we dropped rtnl, ibmvnic_open() got + * it and noticed that we are resetting and + * set the adapter state to OPEN. Update our + * new "target" state, and resume the reset + * from VNIC_CLOSING state. + */ + netdev_dbg(netdev, + "Open changed state from %d, updating.\n", + reset_state); + reset_state = VNIC_OPEN; + adapter->state = VNIC_CLOSING; + } + if (adapter->state != VNIC_CLOSING) { + /* If someone else changed the adapter state + * when we dropped the rtnl, fail the reset + */ rc = -1; goto out; } - adapter->state = VNIC_CLOSED; } } @@ -2106,6 +2145,14 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter, netdev_dbg(adapter->netdev, "Hard resetting driver (%d)\n", rwi->reset_reason); + /* read the state and check (again) after getting rtnl */ + reset_state = adapter->state; + + if (reset_state == VNIC_REMOVING || reset_state == VNIC_REMOVED) { + rc = -EBUSY; + goto out; + } + netif_carrier_off(netdev); adapter->reset_reason = rwi->reset_reason; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index a8a2b5f683a2..c70dec65a572 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -5083,7 +5083,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) enum i40e_admin_queue_err adq_err; struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - bool is_reset_needed; + u32 reset_needed = 0; i40e_status status; u32 i, j; @@ -5128,9 +5128,11 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) flags_complete: changed_flags = orig_flags ^ new_flags; - is_reset_needed = !!(changed_flags & (I40E_FLAG_VEB_STATS_ENABLED | - I40E_FLAG_LEGACY_RX | I40E_FLAG_SOURCE_PRUNING_DISABLED | - I40E_FLAG_DISABLE_FW_LLDP)); + if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) + reset_needed = I40E_PF_RESET_AND_REBUILD_FLAG; + if (changed_flags & (I40E_FLAG_VEB_STATS_ENABLED | + I40E_FLAG_LEGACY_RX | I40E_FLAG_SOURCE_PRUNING_DISABLED)) + reset_needed = BIT(__I40E_PF_RESET_REQUESTED); /* Before we finalize any flag changes, we need to perform some * checks to ensure that the changes are supported and safe. @@ -5252,7 +5254,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) case I40E_AQ_RC_EEXIST: dev_warn(&pf->pdev->dev, "FW LLDP agent is already running\n"); - is_reset_needed = false; + reset_needed = 0; break; case I40E_AQ_RC_EPERM: dev_warn(&pf->pdev->dev, @@ -5281,8 +5283,8 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) /* Issue reset to cause things to take effect, as additional bits * are added we will need to create a mask of bits requiring reset */ - if (is_reset_needed) - i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true); + if (reset_needed) + i40e_do_reset(pf, reset_needed, true); return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 8bb8eb65add9..353deae139f9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2616,7 +2616,7 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) return; if (!test_and_clear_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state)) return; - if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) { + if (test_bit(__I40E_VF_DISABLE, pf->state)) { set_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state); return; } @@ -2634,7 +2634,6 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) } } } - clear_bit(__I40E_VF_DISABLE, pf->state); } /** @@ -5937,7 +5936,7 @@ static int i40e_add_channel(struct i40e_pf *pf, u16 uplink_seid, ch->enabled_tc = !i40e_is_channel_macvlan(ch) && enabled_tc; ch->seid = ctxt.seid; ch->vsi_number = ctxt.vsi_number; - ch->stat_counter_idx = cpu_to_le16(ctxt.info.stat_counter_idx); + ch->stat_counter_idx = le16_to_cpu(ctxt.info.stat_counter_idx); /* copy just the sections touched not the entire info * since not all sections are valid as returned by @@ -7977,8 +7976,8 @@ static inline void i40e_set_cld_element(struct i40e_cloud_filter *filter, struct i40e_aqc_cloud_filters_element_data *cld) { - int i, j; u32 ipa; + int i; memset(cld, 0, sizeof(*cld)); ether_addr_copy(cld->outer_mac, filter->dst_mac); @@ -7989,14 +7988,14 @@ i40e_set_cld_element(struct i40e_cloud_filter *filter, if (filter->n_proto == ETH_P_IPV6) { #define IPV6_MAX_INDEX (ARRAY_SIZE(filter->dst_ipv6) - 1) - for (i = 0, j = 0; i < ARRAY_SIZE(filter->dst_ipv6); - i++, j += 2) { + for (i = 0; i < ARRAY_SIZE(filter->dst_ipv6); i++) { ipa = be32_to_cpu(filter->dst_ipv6[IPV6_MAX_INDEX - i]); - ipa = cpu_to_le32(ipa); - memcpy(&cld->ipaddr.raw_v6.data[j], &ipa, sizeof(ipa)); + + *(__le32 *)&cld->ipaddr.raw_v6.data[i * 2] = cpu_to_le32(ipa); } } else { ipa = be32_to_cpu(filter->dst_ipv4); + memcpy(&cld->ipaddr.v4.data, &ipa, sizeof(ipa)); } @@ -8044,6 +8043,8 @@ int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, if (filter->flags >= ARRAY_SIZE(flag_table)) return I40E_ERR_CONFIG; + memset(&cld_filter, 0, sizeof(cld_filter)); + /* copy element needed to add cloud filter from filter */ i40e_set_cld_element(filter, &cld_filter); @@ -8107,10 +8108,13 @@ int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, return -EOPNOTSUPP; /* adding filter using src_port/src_ip is not supported at this stage */ - if (filter->src_port || filter->src_ipv4 || + if (filter->src_port || + (filter->src_ipv4 && filter->n_proto != ETH_P_IPV6) || !ipv6_addr_any(&filter->ip.v6.src_ip6)) return -EOPNOTSUPP; + memset(&cld_filter, 0, sizeof(cld_filter)); + /* copy element needed to add cloud filter from filter */ i40e_set_cld_element(filter, &cld_filter.element); @@ -8134,7 +8138,7 @@ int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT); } - } else if (filter->dst_ipv4 || + } else if ((filter->dst_ipv4 && filter->n_proto != ETH_P_IPV6) || !ipv6_addr_any(&filter->ip.v6.dst_ip6)) { cld_filter.element.flags = cpu_to_le16(I40E_AQC_ADD_CLOUD_FILTER_IP_PORT); @@ -8928,11 +8932,6 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) dev_dbg(&pf->pdev->dev, "PFR requested\n"); i40e_handle_reset_warning(pf, lock_acquired); - dev_info(&pf->pdev->dev, - pf->flags & I40E_FLAG_DISABLE_FW_LLDP ? - "FW LLDP is disabled\n" : - "FW LLDP is enabled\n"); - } else if (reset_flags & I40E_PF_RESET_AND_REBUILD_FLAG) { /* Request a PF Reset * @@ -8940,6 +8939,10 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) */ i40e_prep_for_reset(pf); i40e_reset_and_rebuild(pf, true, lock_acquired); + dev_info(&pf->pdev->dev, + pf->flags & I40E_FLAG_DISABLE_FW_LLDP ? + "FW LLDP is disabled\n" : + "FW LLDP is enabled\n"); } else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) { int v; @@ -10462,7 +10465,6 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) int old_recovery_mode_bit = test_bit(__I40E_RECOVERY_MODE, pf->state); struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; struct i40e_hw *hw = &pf->hw; - u8 set_fc_aq_fail = 0; i40e_status ret; u32 val; int v; @@ -10605,13 +10607,6 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) i40e_stat_str(&pf->hw, ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); - /* make sure our flow control settings are restored */ - ret = i40e_set_fc(&pf->hw, &set_fc_aq_fail, true); - if (ret) - dev_dbg(&pf->pdev->dev, "setting flow control: ret = %s last_status = %s\n", - i40e_stat_str(&pf->hw, ret), - i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); - /* Rebuild the VSIs and VEBs that existed before reset. * They are still in our local switch element arrays, so only * need to rebuild the switch model in the HW. @@ -12191,6 +12186,8 @@ i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf) struct i40e_aqc_configure_partition_bw_data bw_data; i40e_status status; + memset(&bw_data, 0, sizeof(bw_data)); + /* Set the valid bit for this PF */ bw_data.pf_valid_bits = cpu_to_le16(BIT(pf->hw.pf_id)); bw_data.max_bw[pf->hw.pf_id] = pf->max_bw & I40E_ALT_BW_VALUE_MASK; @@ -15198,7 +15195,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) int err; u32 val; u32 i; - u8 set_fc_aq_fail; err = pci_enable_device_mem(pdev); if (err) @@ -15537,24 +15533,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } INIT_LIST_HEAD(&pf->vsi[pf->lan_vsi]->ch_list); - /* Make sure flow control is set according to current settings */ - err = i40e_set_fc(hw, &set_fc_aq_fail, true); - if (set_fc_aq_fail & I40E_SET_FC_AQ_FAIL_GET) - dev_dbg(&pf->pdev->dev, - "Set fc with err %s aq_err %s on get_phy_cap\n", - i40e_stat_str(hw, err), - i40e_aq_str(hw, hw->aq.asq_last_status)); - if (set_fc_aq_fail & I40E_SET_FC_AQ_FAIL_SET) - dev_dbg(&pf->pdev->dev, - "Set fc with err %s aq_err %s on set_phy_config\n", - i40e_stat_str(hw, err), - i40e_aq_str(hw, hw->aq.asq_last_status)); - if (set_fc_aq_fail & I40E_SET_FC_AQ_FAIL_UPDATE) - dev_dbg(&pf->pdev->dev, - "Set fc with err %s aq_err %s on get_link_info\n", - i40e_stat_str(hw, err), - i40e_aq_str(hw, hw->aq.asq_last_status)); - /* if FDIR VSI was set up, start it now */ for (i = 0; i < pf->num_alloc_vsi; i++) { if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) { @@ -15611,6 +15589,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) { dev_info(&pdev->dev, "setup of misc vector failed: %d\n", err); + i40e_cloud_filter_exit(pf); + i40e_fdir_teardown(pf); goto err_vsis; } } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index f6f1af94cca0..627794b31e33 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1948,7 +1948,7 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring, skb_record_rx_queue(skb, rx_ring->queue_index); if (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) { - u16 vlan_tag = rx_desc->wb.qword0.lo_dword.l2tag1; + __le16 vlan_tag = rx_desc->wb.qword0.lo_dword.l2tag1; __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), le16_to_cpu(vlan_tag)); @@ -3223,13 +3223,16 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, l4_proto = ip.v4->protocol; } else if (*tx_flags & I40E_TX_FLAGS_IPV6) { + int ret; + tunnel |= I40E_TX_CTX_EXT_IP_IPV6; exthdr = ip.hdr + sizeof(*ip.v6); l4_proto = ip.v6->nexthdr; - if (l4.hdr != exthdr) - ipv6_skip_exthdr(skb, exthdr - skb->data, - &l4_proto, &frag_off); + ret = ipv6_skip_exthdr(skb, exthdr - skb->data, + &l4_proto, &frag_off); + if (ret < 0) + return -1; } /* define outer transport */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 4f11f7bf75d1..fc32c5019b0f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -453,7 +453,7 @@ static void i40e_set_rs_bit(struct i40e_ring *xdp_ring) struct i40e_tx_desc *tx_desc; tx_desc = I40E_TX_DESC(xdp_ring, ntu); - tx_desc->cmd_type_offset_bsz |= (I40E_TX_DESC_CMD_RS << I40E_TXD_QW1_CMD_SHIFT); + tx_desc->cmd_type_offset_bsz |= cpu_to_le64(I40E_TX_DESC_CMD_RS << I40E_TXD_QW1_CMD_SHIFT); } /** diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index dae8280ce17c..357706444dd5 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -454,9 +454,7 @@ struct ice_pf { struct ice_hw_port_stats stats_prev; struct ice_hw hw; u8 stat_prev_loaded:1; /* has previous stats been loaded */ -#ifdef CONFIG_DCB u16 dcbx_cap; -#endif /* CONFIG_DCB */ u32 tx_timeout_count; unsigned long tx_timeout_last_recovery; u32 tx_timeout_recovery_level; diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index fcfefad00d1c..468a63f7eff9 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -134,7 +134,7 @@ ice_dcbnl_getnumtcs(struct net_device *dev, int __always_unused tcid, u8 *num) if (!test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags)) return -EINVAL; - *num = IEEE_8021QAZ_MAX_TCS; + *num = pf->hw.func_caps.common_cap.maxtc; return 0; } @@ -159,6 +159,10 @@ static u8 ice_dcbnl_setdcbx(struct net_device *netdev, u8 mode) struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_qos_cfg *qos_cfg; + /* if FW LLDP agent is running, DCBNL not allowed to change mode */ + if (test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) + return ICE_DCB_NO_HW_CHG; + /* No support for LLD_MANAGED modes or CEE+IEEE */ if ((mode & DCB_CAP_DCBX_LLD_MANAGED) || ((mode & DCB_CAP_DCBX_VER_IEEE) && (mode & DCB_CAP_DCBX_VER_CEE)) || diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 5636c9b23896..2dcfa685b763 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -8,6 +8,7 @@ #include "ice_fltr.h" #include "ice_lib.h" #include "ice_dcb_lib.h" +#include struct ice_stats { char stat_string[ETH_GSTRING_LEN]; @@ -1238,6 +1239,9 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) status = ice_init_pf_dcb(pf, true); if (status) dev_warn(dev, "Fail to init DCB\n"); + + pf->dcbx_cap &= ~DCB_CAP_DCBX_LLD_MANAGED; + pf->dcbx_cap |= DCB_CAP_DCBX_HOST; } else { enum ice_status status; bool dcbx_agent_status; @@ -1280,6 +1284,9 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) if (status) dev_dbg(dev, "Fail to enable MIB change events\n"); + pf->dcbx_cap &= ~DCB_CAP_DCBX_HOST; + pf->dcbx_cap |= DCB_CAP_DCBX_LLD_MANAGED; + ice_nway_reset(netdev); } } @@ -3321,6 +3328,18 @@ ice_get_channels(struct net_device *dev, struct ethtool_channels *ch) ch->max_other = ch->other_count; } +/** + * ice_get_valid_rss_size - return valid number of RSS queues + * @hw: pointer to the HW structure + * @new_size: requested RSS queues + */ +static int ice_get_valid_rss_size(struct ice_hw *hw, int new_size) +{ + struct ice_hw_common_caps *caps = &hw->func_caps.common_cap; + + return min_t(int, new_size, BIT(caps->rss_table_entry_width)); +} + /** * ice_vsi_set_dflt_rss_lut - set default RSS LUT with requested RSS size * @vsi: VSI to reconfigure RSS LUT on @@ -3348,14 +3367,10 @@ static int ice_vsi_set_dflt_rss_lut(struct ice_vsi *vsi, int req_rss_size) return -ENOMEM; /* set RSS LUT parameters */ - if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { + if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) vsi->rss_size = 1; - } else { - struct ice_hw_common_caps *caps = &hw->func_caps.common_cap; - - vsi->rss_size = min_t(int, req_rss_size, - BIT(caps->rss_table_entry_width)); - } + else + vsi->rss_size = ice_get_valid_rss_size(hw, req_rss_size); /* create/set RSS LUT */ ice_fill_rss_lut(lut, vsi->rss_table_size, vsi->rss_size); @@ -3434,9 +3449,12 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) ice_vsi_recfg_qs(vsi, new_rx, new_tx); - if (new_rx && !netif_is_rxfh_configured(dev)) + if (!netif_is_rxfh_configured(dev)) return ice_vsi_set_dflt_rss_lut(vsi, new_rx); + /* Update rss_size due to change in Rx queues */ + vsi->rss_size = ice_get_valid_rss_size(&pf->hw, new_rx); + return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index bf5fd812ea0e..1f38a8d0c525 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -1918,6 +1918,29 @@ static int ice_vc_get_ver_msg(struct ice_vf *vf, u8 *msg) sizeof(struct virtchnl_version_info)); } +/** + * ice_vc_get_max_frame_size - get max frame size allowed for VF + * @vf: VF used to determine max frame size + * + * Max frame size is determined based on the current port's max frame size and + * whether a port VLAN is configured on this VF. The VF is not aware whether + * it's in a port VLAN so the PF needs to account for this in max frame size + * checks and sending the max frame size to the VF. + */ +static u16 ice_vc_get_max_frame_size(struct ice_vf *vf) +{ + struct ice_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx]; + struct ice_port_info *pi = vsi->port_info; + u16 max_frame_size; + + max_frame_size = pi->phy.link_info.max_frame_size; + + if (vf->port_vlan_info) + max_frame_size -= VLAN_HLEN; + + return max_frame_size; +} + /** * ice_vc_get_vf_res_msg * @vf: pointer to the VF info @@ -2000,6 +2023,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->max_vectors = pf->num_msix_per_vf; vfres->rss_key_size = ICE_VSIQF_HKEY_ARRAY_SIZE; vfres->rss_lut_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + vfres->max_mtu = ice_vc_get_max_frame_size(vf); vfres->vsi_res[0].vsi_id = vf->lan_vsi_num; vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV; @@ -2420,7 +2444,7 @@ static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) } if (!test_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, pf->flags)) { - bool set_dflt_vsi = !!(info->flags & FLAG_VF_UNICAST_PROMISC); + bool set_dflt_vsi = alluni || allmulti; if (set_dflt_vsi && !ice_is_dflt_vsi_in_use(pf->first_sw)) /* only attempt to set the default forwarding VSI if @@ -2998,6 +3022,8 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) /* copy Rx queue info from VF into VSI */ if (qpi->rxq.ring_len > 0) { + u16 max_frame_size = ice_vc_get_max_frame_size(vf); + num_rxq++; vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr; vsi->rx_rings[i]->count = qpi->rxq.ring_len; @@ -3010,7 +3036,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) } vsi->rx_buf_len = qpi->rxq.databuffer_size; vsi->rx_rings[i]->rx_buf_len = vsi->rx_buf_len; - if (qpi->rxq.max_pkt_size >= (16 * 1024) || + if (qpi->rxq.max_pkt_size > max_frame_size || qpi->rxq.max_pkt_size < 64) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; @@ -3018,6 +3044,11 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) } vsi->max_frame = qpi->rxq.max_pkt_size; + /* add space for the port VLAN since the VF driver is not + * expected to account for it in the MTU calculation + */ + if (vf->port_vlan_info) + vsi->max_frame += VLAN_HLEN; } /* VF can request to configure less than allocated queues or default diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 0507369bb54d..1767c60056c5 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4699,9 +4699,10 @@ static void mvpp2_irqs_deinit(struct mvpp2_port *port) } } -static bool mvpp22_rss_is_supported(void) +static bool mvpp22_rss_is_supported(struct mvpp2_port *port) { - return queue_mode == MVPP2_QDIST_MULTI_MODE; + return (queue_mode == MVPP2_QDIST_MULTI_MODE) && + !(port->flags & MVPP2_F_LOOPBACK); } static int mvpp2_open(struct net_device *dev) @@ -5513,7 +5514,7 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev, struct mvpp2_port *port = netdev_priv(dev); int ret = 0, i, loc = 0; - if (!mvpp22_rss_is_supported()) + if (!mvpp22_rss_is_supported(port)) return -EOPNOTSUPP; switch (info->cmd) { @@ -5548,7 +5549,7 @@ static int mvpp2_ethtool_set_rxnfc(struct net_device *dev, struct mvpp2_port *port = netdev_priv(dev); int ret = 0; - if (!mvpp22_rss_is_supported()) + if (!mvpp22_rss_is_supported(port)) return -EOPNOTSUPP; switch (info->cmd) { @@ -5569,7 +5570,9 @@ static int mvpp2_ethtool_set_rxnfc(struct net_device *dev, static u32 mvpp2_ethtool_get_rxfh_indir_size(struct net_device *dev) { - return mvpp22_rss_is_supported() ? MVPP22_RSS_TABLE_ENTRIES : 0; + struct mvpp2_port *port = netdev_priv(dev); + + return mvpp22_rss_is_supported(port) ? MVPP22_RSS_TABLE_ENTRIES : 0; } static int mvpp2_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, @@ -5578,7 +5581,7 @@ static int mvpp2_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, struct mvpp2_port *port = netdev_priv(dev); int ret = 0; - if (!mvpp22_rss_is_supported()) + if (!mvpp22_rss_is_supported(port)) return -EOPNOTSUPP; if (indir) @@ -5596,7 +5599,7 @@ static int mvpp2_ethtool_set_rxfh(struct net_device *dev, const u32 *indir, struct mvpp2_port *port = netdev_priv(dev); int ret = 0; - if (!mvpp22_rss_is_supported()) + if (!mvpp22_rss_is_supported(port)) return -EOPNOTSUPP; if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_CRC32) @@ -5617,7 +5620,7 @@ static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir, struct mvpp2_port *port = netdev_priv(dev); int ret = 0; - if (!mvpp22_rss_is_supported()) + if (!mvpp22_rss_is_supported(port)) return -EOPNOTSUPP; if (rss_context >= MVPP22_N_RSS_TABLES) return -EINVAL; @@ -5639,7 +5642,7 @@ static int mvpp2_ethtool_set_rxfh_context(struct net_device *dev, struct mvpp2_port *port = netdev_priv(dev); int ret; - if (!mvpp22_rss_is_supported()) + if (!mvpp22_rss_is_supported(port)) return -EOPNOTSUPP; if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_CRC32) @@ -5956,7 +5959,7 @@ static int mvpp2_port_init(struct mvpp2_port *port) mvpp2_cls_oversize_rxq_set(port); mvpp2_cls_port_config(port); - if (mvpp22_rss_is_supported()) + if (mvpp22_rss_is_supported(port)) mvpp22_port_rss_init(port); /* Provide an initial Rx packet size */ @@ -6861,7 +6864,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev->hw_features |= features | NETIF_F_RXCSUM | NETIF_F_GRO | NETIF_F_HW_VLAN_CTAG_FILTER; - if (mvpp22_rss_is_supported()) { + if (mvpp22_rss_is_supported(port)) { dev->hw_features |= NETIF_F_RXHASH; dev->features |= NETIF_F_NTUPLE; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 094124b695dc..aa2ca8780b9c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -473,7 +473,7 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp, u16 pcifunc; int ret, lf; - cmd_buf = memdup_user(buffer, count); + cmd_buf = memdup_user(buffer, count + 1); if (IS_ERR(cmd_buf)) return -ENOMEM; diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index ebe1406c6e64..dbec8e187a68 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4806,12 +4806,11 @@ static struct net_device *sky2_init_netdev(struct sky2_hw *hw, unsigned port, if (!is_valid_ether_addr(dev->dev_addr)) { struct sockaddr sa = { AF_UNSPEC }; - netdev_warn(dev, - "Invalid MAC address, defaulting to random\n"); + dev_warn(&hw->pdev->dev, "Invalid MAC address, defaulting to random\n"); eth_hw_addr_random(dev); memcpy(sa.sa_data, dev->dev_addr, ETH_ALEN); if (sky2_set_mac_address(dev, &sa)) - netdev_warn(dev, "Failed to set MAC address.\n"); + dev_warn(&hw->pdev->dev, "Failed to set MAC address.\n"); } return dev; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 394f43add85c..a99e71bc7b3c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -4986,6 +4986,7 @@ static int mlx4_do_mirror_rule(struct mlx4_dev *dev, struct res_fs_rule *fs_rule if (!fs_rule->mirr_mbox) { mlx4_err(dev, "rule mirroring mailbox is null\n"); + mlx4_free_cmd_mailbox(dev, mailbox); return -EINVAL; } memcpy(mailbox->buf, fs_rule->mirr_mbox, fs_rule->mirr_mbox_size); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 2f2c352f301e..c568896cfb23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -237,8 +237,8 @@ static void mlx5_set_driver_version(struct mlx5_core_dev *dev) remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); snprintf(string + strlen(string), remaining_size, "%u.%u.%u", - (u8)((LINUX_VERSION_CODE >> 16) & 0xff), (u8)((LINUX_VERSION_CODE >> 8) & 0xff), - (u16)(LINUX_VERSION_CODE & 0xffff)); + LINUX_VERSION_MAJOR, LINUX_VERSION_PATCHLEVEL, + LINUX_VERSION_SUBLEVEL); /*Send the command*/ MLX5_SET(set_driver_version_in, in, opcode, diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 0a20dae32184..f704da3f214c 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2285,14 +2285,14 @@ static void r8168dp_hw_jumbo_disable(struct rtl8169_private *tp) static void r8168e_hw_jumbo_enable(struct rtl8169_private *tp) { - RTL_W8(tp, MaxTxPacketSize, 0x3f); + RTL_W8(tp, MaxTxPacketSize, 0x24); RTL_W8(tp, Config3, RTL_R8(tp, Config3) | Jumbo_En0); RTL_W8(tp, Config4, RTL_R8(tp, Config4) | 0x01); } static void r8168e_hw_jumbo_disable(struct rtl8169_private *tp) { - RTL_W8(tp, MaxTxPacketSize, 0x0c); + RTL_W8(tp, MaxTxPacketSize, 0x3f); RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Jumbo_En0); RTL_W8(tp, Config4, RTL_R8(tp, Config4) & ~0x01); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c index b7a0c57dfbfb..d23be45a64e5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c @@ -218,6 +218,7 @@ static int visconti_eth_dwmac_probe(struct platform_device *pdev) goto remove_config; } + spin_lock_init(&dwmac->lock); dwmac->reg = stmmac_res.addr; plat_dat->bsp_priv = dwmac; plat_dat->fix_mac_speed = visconti_eth_fix_mac_speed; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 56985542e202..44bb133c3000 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -316,6 +316,32 @@ static int tc_setup_cbs(struct stmmac_priv *priv, if (!priv->dma_cap.av) return -EOPNOTSUPP; + /* Port Transmit Rate and Speed Divider */ + switch (priv->speed) { + case SPEED_10000: + ptr = 32; + speed_div = 10000000; + break; + case SPEED_5000: + ptr = 32; + speed_div = 5000000; + break; + case SPEED_2500: + ptr = 8; + speed_div = 2500000; + break; + case SPEED_1000: + ptr = 8; + speed_div = 1000000; + break; + case SPEED_100: + ptr = 4; + speed_div = 100000; + break; + default: + return -EOPNOTSUPP; + } + mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use; if (mode_to_use == MTL_QUEUE_DCB && qopt->enable) { ret = stmmac_dma_qmode(priv, priv->ioaddr, queue, MTL_QUEUE_AVB); @@ -332,10 +358,6 @@ static int tc_setup_cbs(struct stmmac_priv *priv, priv->plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; } - /* Port Transmit Rate and Speed Divider */ - ptr = (priv->speed == SPEED_100) ? 4 : 8; - speed_div = (priv->speed == SPEED_100) ? 100000 : 1000000; - /* Final adjustments for HW */ value = div_s64(qopt->idleslope * 1024ll * ptr, speed_div); priv->plat->tx_queues_cfg[queue].idle_slope = value & GENMASK(31, 0); diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 9a70f05baf6e..39c00f050fbd 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -543,7 +543,6 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) && mtu < ntohs(iph->tot_len)) { netdev_dbg(dev, "packet too big, fragmentation needed\n"); - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); goto err_rt; diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c index 3e431737c1ba..a00a667454a9 100644 --- a/drivers/net/phy/icplus.c +++ b/drivers/net/phy/icplus.c @@ -239,7 +239,7 @@ static int ip101a_g_config_intr_pin(struct phy_device *phydev) oldpage = phy_select_page(phydev, IP101G_DEFAULT_PAGE); if (oldpage < 0) - return oldpage; + goto out; /* configure the RXER/INTR_32 pin of the 32-pin IP101GR if needed: */ switch (priv->sel_intr32) { @@ -314,7 +314,7 @@ static int ip101a_g_read_status(struct phy_device *phydev) oldpage = phy_select_page(phydev, IP101G_DEFAULT_PAGE); if (oldpage < 0) - return oldpage; + goto out; ret = __phy_read(phydev, IP10XX_SPEC_CTRL_STATUS); if (ret < 0) @@ -349,7 +349,8 @@ static int ip101a_g_read_status(struct phy_device *phydev) static int ip101a_g_config_mdix(struct phy_device *phydev) { u16 ctrl = 0, ctrl2 = 0; - int oldpage, ret; + int oldpage; + int ret = 0; switch (phydev->mdix_ctrl) { case ETH_TP_MDI: @@ -367,7 +368,7 @@ static int ip101a_g_config_mdix(struct phy_device *phydev) oldpage = phy_select_page(phydev, IP101G_DEFAULT_PAGE); if (oldpage < 0) - return oldpage; + goto out; ret = __phy_modify(phydev, IP10XX_SPEC_CTRL_STATUS, IP101A_G_AUTO_MDIX_DIS, ctrl); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 7ec6f70d6a82..a14a00328fa3 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -1303,6 +1303,7 @@ static struct phy_driver ksphy_driver[] = { .driver_data = &ksz8081_type, .probe = kszphy_probe, .config_init = ksz8081_config_init, + .soft_reset = genphy_soft_reset, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, .get_sset_count = kszphy_get_sset_count, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 6c3d8c2abd38..17a050521b86 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1318,6 +1318,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x1255, 4)}, {QMI_FIXED_INTF(0x19d2, 0x1256, 4)}, {QMI_FIXED_INTF(0x19d2, 0x1270, 5)}, /* ZTE MF667 */ + {QMI_FIXED_INTF(0x19d2, 0x1275, 3)}, /* ZTE P685M */ {QMI_FIXED_INTF(0x19d2, 0x1401, 2)}, {QMI_FIXED_INTF(0x19d2, 0x1402, 2)}, /* ZTE MF60 */ {QMI_FIXED_INTF(0x19d2, 0x1424, 2)}, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 2d7cc63bef89..b246817f3405 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -2632,21 +2632,24 @@ static inline u8 rtl8152_get_speed(struct r8152 *tp) return ocp_read_byte(tp, MCU_TYPE_PLA, PLA_PHYSTATUS); } -static void rtl_set_eee_plus(struct r8152 *tp) +static void rtl_eee_plus_en(struct r8152 *tp, bool enable) { u32 ocp_data; - u8 speed; - speed = rtl8152_get_speed(tp); - if (speed & _10bps) { - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EEEP_CR); + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EEEP_CR); + if (enable) ocp_data |= EEEP_CR_EEEP_TX; - ocp_write_word(tp, MCU_TYPE_PLA, PLA_EEEP_CR, ocp_data); - } else { - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EEEP_CR); + else ocp_data &= ~EEEP_CR_EEEP_TX; - ocp_write_word(tp, MCU_TYPE_PLA, PLA_EEEP_CR, ocp_data); - } + ocp_write_word(tp, MCU_TYPE_PLA, PLA_EEEP_CR, ocp_data); +} + +static void rtl_set_eee_plus(struct r8152 *tp) +{ + if (rtl8152_get_speed(tp) & _10bps) + rtl_eee_plus_en(tp, true); + else + rtl_eee_plus_en(tp, false); } static void rxdy_gated_en(struct r8152 *tp, bool enable) @@ -3150,10 +3153,22 @@ static void r8153b_ups_flags(struct r8152 *tp) ocp_write_dword(tp, MCU_TYPE_USB, USB_UPS_FLAGS, ups_flags); } -static void r8153b_green_en(struct r8152 *tp, bool enable) +static void rtl_green_en(struct r8152 *tp, bool enable) { u16 data; + data = sram_read(tp, SRAM_GREEN_CFG); + if (enable) + data |= GREEN_ETH_EN; + else + data &= ~GREEN_ETH_EN; + sram_write(tp, SRAM_GREEN_CFG, data); + + tp->ups_info.green = enable; +} + +static void r8153b_green_en(struct r8152 *tp, bool enable) +{ if (enable) { sram_write(tp, 0x8045, 0); /* 10M abiq&ldvbias */ sram_write(tp, 0x804d, 0x1222); /* 100M short abiq&ldvbias */ @@ -3164,11 +3179,7 @@ static void r8153b_green_en(struct r8152 *tp, bool enable) sram_write(tp, 0x805d, 0x2444); /* 1000M short abiq&ldvbias */ } - data = sram_read(tp, SRAM_GREEN_CFG); - data |= GREEN_ETH_EN; - sram_write(tp, SRAM_GREEN_CFG, data); - - tp->ups_info.green = enable; + rtl_green_en(tp, true); } static u16 r8153_phy_status(struct r8152 *tp, u16 desired) @@ -3360,7 +3371,7 @@ static void rtl8153b_runtime_enable(struct r8152 *tp, bool enable) r8153b_ups_en(tp, false); r8153_queue_wake(tp, false); rtl_runtime_suspend_enable(tp, false); - if (tp->udev->speed != USB_SPEED_HIGH) + if (tp->udev->speed >= USB_SPEED_SUPER) r8153b_u1u2en(tp, true); } } @@ -5056,7 +5067,7 @@ static void rtl8153b_up(struct r8152 *tp) r8153_aldps_en(tp, true); - if (tp->udev->speed != USB_SPEED_HIGH) + if (tp->udev->speed >= USB_SPEED_SUPER) r8153b_u1u2en(tp, true); } @@ -5572,8 +5583,9 @@ static void r8153b_init(struct r8152 *tp) ocp_data |= POLL_LINK_CHG; ocp_write_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS, ocp_data); - if (tp->udev->speed != USB_SPEED_HIGH) + if (tp->udev->speed >= USB_SPEED_SUPER) r8153b_u1u2en(tp, true); + usb_enable_lpm(tp->udev); /* MAC clock speed down */ @@ -5756,6 +5768,9 @@ static int rtl8152_runtime_suspend(struct r8152 *tp) struct net_device *netdev = tp->netdev; int ret = 0; + if (!tp->rtl_ops.autosuspend_en) + return -EBUSY; + set_bit(SELECTIVE_SUSPEND, &tp->flags); smp_mb__after_atomic(); @@ -6155,6 +6170,11 @@ rtl_ethtool_get_eee(struct net_device *net, struct ethtool_eee *edata) struct r8152 *tp = netdev_priv(net); int ret; + if (!tp->rtl_ops.eee_get) { + ret = -EOPNOTSUPP; + goto out; + } + ret = usb_autopm_get_interface(tp->intf); if (ret < 0) goto out; @@ -6177,6 +6197,11 @@ rtl_ethtool_set_eee(struct net_device *net, struct ethtool_eee *edata) struct r8152 *tp = netdev_priv(net); int ret; + if (!tp->rtl_ops.eee_set) { + ret = -EOPNOTSUPP; + goto out; + } + ret = usb_autopm_get_interface(tp->intf); if (ret < 0) goto out; @@ -6576,7 +6601,7 @@ static int rtl_ops_init(struct r8152 *tp) default: ret = -ENODEV; - netif_err(tp, probe, tp->netdev, "Unknown Device\n"); + dev_err(&tp->intf->dev, "Unknown Device\n"); break; } @@ -6833,7 +6858,7 @@ static int rtl8152_probe(struct usb_interface *intf, ret = register_netdev(netdev); if (ret != 0) { - netif_err(tp, probe, netdev, "couldn't register the device\n"); + dev_err(&intf->dev, "couldn't register the device\n"); goto out1; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index a8e1584747b5..7a1ba8735138 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -729,6 +729,7 @@ static struct sk_buff *receive_small(struct net_device *dev, fallthrough; case XDP_ABORTED: trace_xdp_exception(vi->dev, xdp_prog, act); + goto err_xdp; case XDP_DROP: goto err_xdp; } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 3929e437382b..666dd201c3d5 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -4721,7 +4721,6 @@ static void vxlan_destroy_tunnels(struct net *net, struct list_head *head) struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan, *next; struct net_device *dev, *aux; - unsigned int h; for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &vxlan_link_ops) @@ -4735,14 +4734,13 @@ static void vxlan_destroy_tunnels(struct net *net, struct list_head *head) unregister_netdevice_queue(vxlan->dev, head); } - for (h = 0; h < PORT_HASH_SIZE; ++h) - WARN_ON_ONCE(!hlist_empty(&vn->sock_list[h])); } static void __net_exit vxlan_exit_batch_net(struct list_head *net_list) { struct net *net; LIST_HEAD(list); + unsigned int h; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { @@ -4755,6 +4753,13 @@ static void __net_exit vxlan_exit_batch_net(struct list_head *net_list) unregister_netdevice_many(&list); rtnl_unlock(); + + list_for_each_entry(net, net_list, exit_list) { + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + + for (h = 0; h < PORT_HASH_SIZE; ++h) + WARN_ON_ONCE(!hlist_empty(&vn->sock_list[h])); + } } static struct pernet_operations vxlan_net_ops = { diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index a3ed49cd95c3..551ddaaaf540 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -138,7 +138,7 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) else if (skb->protocol == htons(ETH_P_IPV6)) net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n", dev->name, &ipv6_hdr(skb)->daddr); - goto err; + goto err_icmp; } family = READ_ONCE(peer->endpoint.addr.sa_family); @@ -157,7 +157,7 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) } else { struct sk_buff *segs = skb_gso_segment(skb, 0); - if (unlikely(IS_ERR(segs))) { + if (IS_ERR(segs)) { ret = PTR_ERR(segs); goto err_peer; } @@ -201,12 +201,13 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) err_peer: wg_peer_put(peer); -err: - ++dev->stats.tx_errors; +err_icmp: if (skb->protocol == htons(ETH_P_IP)) icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); else if (skb->protocol == htons(ETH_P_IPV6)) icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); +err: + ++dev->stats.tx_errors; kfree_skb(skb); return ret; } @@ -234,8 +235,8 @@ static void wg_destruct(struct net_device *dev) destroy_workqueue(wg->handshake_receive_wq); destroy_workqueue(wg->handshake_send_wq); destroy_workqueue(wg->packet_crypt_wq); - wg_packet_queue_free(&wg->decrypt_queue, true); - wg_packet_queue_free(&wg->encrypt_queue, true); + wg_packet_queue_free(&wg->decrypt_queue); + wg_packet_queue_free(&wg->encrypt_queue); rcu_barrier(); /* Wait for all the peers to be actually freed. */ wg_ratelimiter_uninit(); memzero_explicit(&wg->static_identity, sizeof(wg->static_identity)); @@ -337,12 +338,12 @@ static int wg_newlink(struct net *src_net, struct net_device *dev, goto err_destroy_handshake_send; ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker, - true, MAX_QUEUED_PACKETS); + MAX_QUEUED_PACKETS); if (ret < 0) goto err_destroy_packet_crypt; ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker, - true, MAX_QUEUED_PACKETS); + MAX_QUEUED_PACKETS); if (ret < 0) goto err_free_encrypt_queue; @@ -367,9 +368,9 @@ static int wg_newlink(struct net *src_net, struct net_device *dev, err_uninit_ratelimiter: wg_ratelimiter_uninit(); err_free_decrypt_queue: - wg_packet_queue_free(&wg->decrypt_queue, true); + wg_packet_queue_free(&wg->decrypt_queue); err_free_encrypt_queue: - wg_packet_queue_free(&wg->encrypt_queue, true); + wg_packet_queue_free(&wg->encrypt_queue); err_destroy_packet_crypt: destroy_workqueue(wg->packet_crypt_wq); err_destroy_handshake_send: diff --git a/drivers/net/wireguard/device.h b/drivers/net/wireguard/device.h index 4d0144e16947..854bc3d97150 100644 --- a/drivers/net/wireguard/device.h +++ b/drivers/net/wireguard/device.h @@ -27,13 +27,14 @@ struct multicore_worker { struct crypt_queue { struct ptr_ring ring; - union { - struct { - struct multicore_worker __percpu *worker; - int last_cpu; - }; - struct work_struct work; - }; + struct multicore_worker __percpu *worker; + int last_cpu; +}; + +struct prev_queue { + struct sk_buff *head, *tail, *peeked; + struct { struct sk_buff *next, *prev; } empty; // Match first 2 members of struct sk_buff. + atomic_t count; }; struct wg_device { diff --git a/drivers/net/wireguard/peer.c b/drivers/net/wireguard/peer.c index b3b6370e6b95..cd5cb0292cb6 100644 --- a/drivers/net/wireguard/peer.c +++ b/drivers/net/wireguard/peer.c @@ -32,27 +32,22 @@ struct wg_peer *wg_peer_create(struct wg_device *wg, peer = kzalloc(sizeof(*peer), GFP_KERNEL); if (unlikely(!peer)) return ERR_PTR(ret); - peer->device = wg; + if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL)) + goto err; + peer->device = wg; wg_noise_handshake_init(&peer->handshake, &wg->static_identity, public_key, preshared_key, peer); - if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL)) - goto err_1; - if (wg_packet_queue_init(&peer->tx_queue, wg_packet_tx_worker, false, - MAX_QUEUED_PACKETS)) - goto err_2; - if (wg_packet_queue_init(&peer->rx_queue, NULL, false, - MAX_QUEUED_PACKETS)) - goto err_3; - peer->internal_id = atomic64_inc_return(&peer_counter); peer->serial_work_cpu = nr_cpumask_bits; wg_cookie_init(&peer->latest_cookie); wg_timers_init(peer); wg_cookie_checker_precompute_peer_keys(peer); spin_lock_init(&peer->keypairs.keypair_update_lock); - INIT_WORK(&peer->transmit_handshake_work, - wg_packet_handshake_send_worker); + INIT_WORK(&peer->transmit_handshake_work, wg_packet_handshake_send_worker); + INIT_WORK(&peer->transmit_packet_work, wg_packet_tx_worker); + wg_prev_queue_init(&peer->tx_queue); + wg_prev_queue_init(&peer->rx_queue); rwlock_init(&peer->endpoint_lock); kref_init(&peer->refcount); skb_queue_head_init(&peer->staged_packet_queue); @@ -68,11 +63,7 @@ struct wg_peer *wg_peer_create(struct wg_device *wg, pr_debug("%s: Peer %llu created\n", wg->dev->name, peer->internal_id); return peer; -err_3: - wg_packet_queue_free(&peer->tx_queue, false); -err_2: - dst_cache_destroy(&peer->endpoint_cache); -err_1: +err: kfree(peer); return ERR_PTR(ret); } @@ -197,8 +188,7 @@ static void rcu_release(struct rcu_head *rcu) struct wg_peer *peer = container_of(rcu, struct wg_peer, rcu); dst_cache_destroy(&peer->endpoint_cache); - wg_packet_queue_free(&peer->rx_queue, false); - wg_packet_queue_free(&peer->tx_queue, false); + WARN_ON(wg_prev_queue_peek(&peer->tx_queue) || wg_prev_queue_peek(&peer->rx_queue)); /* The final zeroing takes care of clearing any remaining handshake key * material and other potentially sensitive information. diff --git a/drivers/net/wireguard/peer.h b/drivers/net/wireguard/peer.h index 23af40922997..8d53b687a1d1 100644 --- a/drivers/net/wireguard/peer.h +++ b/drivers/net/wireguard/peer.h @@ -36,16 +36,17 @@ struct endpoint { struct wg_peer { struct wg_device *device; - struct crypt_queue tx_queue, rx_queue; + struct prev_queue tx_queue, rx_queue; struct sk_buff_head staged_packet_queue; int serial_work_cpu; + bool is_dead; struct noise_keypairs keypairs; struct endpoint endpoint; struct dst_cache endpoint_cache; rwlock_t endpoint_lock; struct noise_handshake handshake; atomic64_t last_sent_handshake; - struct work_struct transmit_handshake_work, clear_peer_work; + struct work_struct transmit_handshake_work, clear_peer_work, transmit_packet_work; struct cookie latest_cookie; struct hlist_node pubkey_hash; u64 rx_bytes, tx_bytes; @@ -61,9 +62,8 @@ struct wg_peer { struct rcu_head rcu; struct list_head peer_list; struct list_head allowedips_list; - u64 internal_id; struct napi_struct napi; - bool is_dead; + u64 internal_id; }; struct wg_peer *wg_peer_create(struct wg_device *wg, diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c index 71b8e80b58e1..48e7b982a307 100644 --- a/drivers/net/wireguard/queueing.c +++ b/drivers/net/wireguard/queueing.c @@ -9,8 +9,7 @@ struct multicore_worker __percpu * wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr) { int cpu; - struct multicore_worker __percpu *worker = - alloc_percpu(struct multicore_worker); + struct multicore_worker __percpu *worker = alloc_percpu(struct multicore_worker); if (!worker) return NULL; @@ -23,7 +22,7 @@ wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr) } int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, - bool multicore, unsigned int len) + unsigned int len) { int ret; @@ -31,25 +30,78 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL); if (ret) return ret; - if (function) { - if (multicore) { - queue->worker = wg_packet_percpu_multicore_worker_alloc( - function, queue); - if (!queue->worker) { - ptr_ring_cleanup(&queue->ring, NULL); - return -ENOMEM; - } - } else { - INIT_WORK(&queue->work, function); - } + queue->worker = wg_packet_percpu_multicore_worker_alloc(function, queue); + if (!queue->worker) { + ptr_ring_cleanup(&queue->ring, NULL); + return -ENOMEM; } return 0; } -void wg_packet_queue_free(struct crypt_queue *queue, bool multicore) +void wg_packet_queue_free(struct crypt_queue *queue) { - if (multicore) - free_percpu(queue->worker); + free_percpu(queue->worker); WARN_ON(!__ptr_ring_empty(&queue->ring)); ptr_ring_cleanup(&queue->ring, NULL); } + +#define NEXT(skb) ((skb)->prev) +#define STUB(queue) ((struct sk_buff *)&queue->empty) + +void wg_prev_queue_init(struct prev_queue *queue) +{ + NEXT(STUB(queue)) = NULL; + queue->head = queue->tail = STUB(queue); + queue->peeked = NULL; + atomic_set(&queue->count, 0); + BUILD_BUG_ON( + offsetof(struct sk_buff, next) != offsetof(struct prev_queue, empty.next) - + offsetof(struct prev_queue, empty) || + offsetof(struct sk_buff, prev) != offsetof(struct prev_queue, empty.prev) - + offsetof(struct prev_queue, empty)); +} + +static void __wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb) +{ + WRITE_ONCE(NEXT(skb), NULL); + WRITE_ONCE(NEXT(xchg_release(&queue->head, skb)), skb); +} + +bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb) +{ + if (!atomic_add_unless(&queue->count, 1, MAX_QUEUED_PACKETS)) + return false; + __wg_prev_queue_enqueue(queue, skb); + return true; +} + +struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue) +{ + struct sk_buff *tail = queue->tail, *next = smp_load_acquire(&NEXT(tail)); + + if (tail == STUB(queue)) { + if (!next) + return NULL; + queue->tail = next; + tail = next; + next = smp_load_acquire(&NEXT(next)); + } + if (next) { + queue->tail = next; + atomic_dec(&queue->count); + return tail; + } + if (tail != READ_ONCE(queue->head)) + return NULL; + __wg_prev_queue_enqueue(queue, STUB(queue)); + next = smp_load_acquire(&NEXT(tail)); + if (next) { + queue->tail = next; + atomic_dec(&queue->count); + return tail; + } + return NULL; +} + +#undef NEXT +#undef STUB diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h index dfb674e03076..4ef2944a68bc 100644 --- a/drivers/net/wireguard/queueing.h +++ b/drivers/net/wireguard/queueing.h @@ -17,12 +17,13 @@ struct wg_device; struct wg_peer; struct multicore_worker; struct crypt_queue; +struct prev_queue; struct sk_buff; /* queueing.c APIs: */ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, - bool multicore, unsigned int len); -void wg_packet_queue_free(struct crypt_queue *queue, bool multicore); + unsigned int len); +void wg_packet_queue_free(struct crypt_queue *queue); struct multicore_worker __percpu * wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr); @@ -135,8 +136,31 @@ static inline int wg_cpumask_next_online(int *next) return cpu; } +void wg_prev_queue_init(struct prev_queue *queue); + +/* Multi producer */ +bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb); + +/* Single consumer */ +struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue); + +/* Single consumer */ +static inline struct sk_buff *wg_prev_queue_peek(struct prev_queue *queue) +{ + if (queue->peeked) + return queue->peeked; + queue->peeked = wg_prev_queue_dequeue(queue); + return queue->peeked; +} + +/* Single consumer */ +static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue) +{ + queue->peeked = NULL; +} + static inline int wg_queue_enqueue_per_device_and_peer( - struct crypt_queue *device_queue, struct crypt_queue *peer_queue, + struct crypt_queue *device_queue, struct prev_queue *peer_queue, struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu) { int cpu; @@ -145,8 +169,9 @@ static inline int wg_queue_enqueue_per_device_and_peer( /* We first queue this up for the peer ingestion, but the consumer * will wait for the state to change to CRYPTED or DEAD before. */ - if (unlikely(ptr_ring_produce_bh(&peer_queue->ring, skb))) + if (unlikely(!wg_prev_queue_enqueue(peer_queue, skb))) return -ENOSPC; + /* Then we queue it up in the device queue, which consumes the * packet as soon as it can. */ @@ -157,9 +182,7 @@ static inline int wg_queue_enqueue_per_device_and_peer( return 0; } -static inline void wg_queue_enqueue_per_peer(struct crypt_queue *queue, - struct sk_buff *skb, - enum packet_state state) +static inline void wg_queue_enqueue_per_peer_tx(struct sk_buff *skb, enum packet_state state) { /* We take a reference, because as soon as we call atomic_set, the * peer can be freed from below us. @@ -167,14 +190,12 @@ static inline void wg_queue_enqueue_per_peer(struct crypt_queue *queue, struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb)); atomic_set_release(&PACKET_CB(skb)->state, state); - queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, - peer->internal_id), - peer->device->packet_crypt_wq, &queue->work); + queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, peer->internal_id), + peer->device->packet_crypt_wq, &peer->transmit_packet_work); wg_peer_put(peer); } -static inline void wg_queue_enqueue_per_peer_napi(struct sk_buff *skb, - enum packet_state state) +static inline void wg_queue_enqueue_per_peer_rx(struct sk_buff *skb, enum packet_state state) { /* We take a reference, because as soon as we call atomic_set, the * peer can be freed from below us. diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 2c9551ea6dc7..7dc84bcca261 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -444,7 +444,6 @@ static void wg_packet_consume_data_done(struct wg_peer *peer, int wg_packet_rx_poll(struct napi_struct *napi, int budget) { struct wg_peer *peer = container_of(napi, struct wg_peer, napi); - struct crypt_queue *queue = &peer->rx_queue; struct noise_keypair *keypair; struct endpoint endpoint; enum packet_state state; @@ -455,11 +454,10 @@ int wg_packet_rx_poll(struct napi_struct *napi, int budget) if (unlikely(budget <= 0)) return 0; - while ((skb = __ptr_ring_peek(&queue->ring)) != NULL && + while ((skb = wg_prev_queue_peek(&peer->rx_queue)) != NULL && (state = atomic_read_acquire(&PACKET_CB(skb)->state)) != PACKET_STATE_UNCRYPTED) { - __ptr_ring_discard_one(&queue->ring); - peer = PACKET_PEER(skb); + wg_prev_queue_drop_peeked(&peer->rx_queue); keypair = PACKET_CB(skb)->keypair; free = true; @@ -508,7 +506,7 @@ void wg_packet_decrypt_worker(struct work_struct *work) enum packet_state state = likely(decrypt_packet(skb, PACKET_CB(skb)->keypair)) ? PACKET_STATE_CRYPTED : PACKET_STATE_DEAD; - wg_queue_enqueue_per_peer_napi(skb, state); + wg_queue_enqueue_per_peer_rx(skb, state); if (need_resched()) cond_resched(); } @@ -531,12 +529,10 @@ static void wg_packet_consume_data(struct wg_device *wg, struct sk_buff *skb) if (unlikely(READ_ONCE(peer->is_dead))) goto err; - ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, - &peer->rx_queue, skb, - wg->packet_crypt_wq, - &wg->decrypt_queue.last_cpu); + ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, &peer->rx_queue, skb, + wg->packet_crypt_wq, &wg->decrypt_queue.last_cpu); if (unlikely(ret == -EPIPE)) - wg_queue_enqueue_per_peer_napi(skb, PACKET_STATE_DEAD); + wg_queue_enqueue_per_peer_rx(skb, PACKET_STATE_DEAD); if (likely(!ret || ret == -EPIPE)) { rcu_read_unlock_bh(); return; diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index f74b9341ab0f..5368f7c35b4b 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -239,8 +239,7 @@ void wg_packet_send_keepalive(struct wg_peer *peer) wg_packet_send_staged_packets(peer); } -static void wg_packet_create_data_done(struct sk_buff *first, - struct wg_peer *peer) +static void wg_packet_create_data_done(struct wg_peer *peer, struct sk_buff *first) { struct sk_buff *skb, *next; bool is_keepalive, data_sent = false; @@ -262,22 +261,19 @@ static void wg_packet_create_data_done(struct sk_buff *first, void wg_packet_tx_worker(struct work_struct *work) { - struct crypt_queue *queue = container_of(work, struct crypt_queue, - work); + struct wg_peer *peer = container_of(work, struct wg_peer, transmit_packet_work); struct noise_keypair *keypair; enum packet_state state; struct sk_buff *first; - struct wg_peer *peer; - while ((first = __ptr_ring_peek(&queue->ring)) != NULL && + while ((first = wg_prev_queue_peek(&peer->tx_queue)) != NULL && (state = atomic_read_acquire(&PACKET_CB(first)->state)) != PACKET_STATE_UNCRYPTED) { - __ptr_ring_discard_one(&queue->ring); - peer = PACKET_PEER(first); + wg_prev_queue_drop_peeked(&peer->tx_queue); keypair = PACKET_CB(first)->keypair; if (likely(state == PACKET_STATE_CRYPTED)) - wg_packet_create_data_done(first, peer); + wg_packet_create_data_done(peer, first); else kfree_skb_list(first); @@ -306,16 +302,14 @@ void wg_packet_encrypt_worker(struct work_struct *work) break; } } - wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first, - state); + wg_queue_enqueue_per_peer_tx(first, state); if (need_resched()) cond_resched(); } } -static void wg_packet_create_data(struct sk_buff *first) +static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first) { - struct wg_peer *peer = PACKET_PEER(first); struct wg_device *wg = peer->device; int ret = -EINVAL; @@ -323,13 +317,10 @@ static void wg_packet_create_data(struct sk_buff *first) if (unlikely(READ_ONCE(peer->is_dead))) goto err; - ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, - &peer->tx_queue, first, - wg->packet_crypt_wq, - &wg->encrypt_queue.last_cpu); + ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first, + wg->packet_crypt_wq, &wg->encrypt_queue.last_cpu); if (unlikely(ret == -EPIPE)) - wg_queue_enqueue_per_peer(&peer->tx_queue, first, - PACKET_STATE_DEAD); + wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD); err: rcu_read_unlock_bh(); if (likely(!ret || ret == -EPIPE)) @@ -393,7 +384,7 @@ void wg_packet_send_staged_packets(struct wg_peer *peer) packets.prev->next = NULL; wg_peer_get(keypair->entry.peer); PACKET_CB(packets.next)->keypair = keypair; - wg_packet_create_data(packets.next); + wg_packet_create_data(peer, packets.next); return; out_invalid: diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c index 410b318e57fb..d9ad850daa79 100644 --- a/drivers/net/wireguard/socket.c +++ b/drivers/net/wireguard/socket.c @@ -53,7 +53,7 @@ static int send4(struct wg_device *wg, struct sk_buff *skb, if (unlikely(!inet_confirm_addr(sock_net(sock), NULL, 0, fl.saddr, RT_SCOPE_HOST))) { endpoint->src4.s_addr = 0; - *(__force __be32 *)&endpoint->src_if4 = 0; + endpoint->src_if4 = 0; fl.saddr = 0; if (cache) dst_cache_reset(cache); @@ -63,7 +63,7 @@ static int send4(struct wg_device *wg, struct sk_buff *skb, PTR_ERR(rt) == -EINVAL) || (!IS_ERR(rt) && rt->dst.dev->ifindex != endpoint->src_if4)))) { endpoint->src4.s_addr = 0; - *(__force __be32 *)&endpoint->src_if4 = 0; + endpoint->src_if4 = 0; fl.saddr = 0; if (cache) dst_cache_reset(cache); @@ -71,7 +71,7 @@ static int send4(struct wg_device *wg, struct sk_buff *skb, ip_rt_put(rt); rt = ip_route_output_flow(sock_net(sock), &fl, sock); } - if (unlikely(IS_ERR(rt))) { + if (IS_ERR(rt)) { ret = PTR_ERR(rt); net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); @@ -138,7 +138,7 @@ static int send6(struct wg_device *wg, struct sk_buff *skb, } dst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(sock), sock, &fl, NULL); - if (unlikely(IS_ERR(dst))) { + if (IS_ERR(dst)) { ret = PTR_ERR(dst); net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); diff --git a/drivers/pcmcia/cistpl.c b/drivers/pcmcia/cistpl.c index cf109d9a1112..e6939103991b 100644 --- a/drivers/pcmcia/cistpl.c +++ b/drivers/pcmcia/cistpl.c @@ -1554,7 +1554,7 @@ static ssize_t pccard_show_cis(struct file *filp, struct kobject *kobj, if (off + count > size) count = size - off; - s = to_socket(container_of(kobj, struct device, kobj)); + s = to_socket(kobj_to_dev(kobj)); if (!(s->state & SOCKET_PRESENT)) return -ENODEV; @@ -1581,7 +1581,7 @@ static ssize_t pccard_store_cis(struct file *filp, struct kobject *kobj, if (error) return error; - s = to_socket(container_of(kobj, struct device, kobj)); + s = to_socket(kobj_to_dev(kobj)); if (off) return -EINVAL; diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index 03c62e1cb395..b7675cce0027 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -370,6 +370,19 @@ config PINCTRL_MICROCHIP_SGPIO connect control signals from SFP modules and to act as an LED controller. +config PINCTRL_K210 + bool "Pinctrl driver for the Canaan Kendryte K210 SoC" + depends on RISCV && SOC_CANAAN && OF + select GENERIC_PINMUX_FUNCTIONS + select GENERIC_PINCONF + select GPIOLIB + select OF_GPIO + select REGMAP_MMIO + default SOC_CANAAN + help + Add support for the Canaan Kendryte K210 RISC-V SOC Field + Programmable IO Array (FPIOA) controller. + source "drivers/pinctrl/actions/Kconfig" source "drivers/pinctrl/aspeed/Kconfig" source "drivers/pinctrl/bcm/Kconfig" diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile index efc96f25c8db..8bf459c32a76 100644 --- a/drivers/pinctrl/Makefile +++ b/drivers/pinctrl/Makefile @@ -45,6 +45,7 @@ obj-$(CONFIG_PINCTRL_RK805) += pinctrl-rk805.o obj-$(CONFIG_PINCTRL_OCELOT) += pinctrl-ocelot.o obj-$(CONFIG_PINCTRL_MICROCHIP_SGPIO) += pinctrl-microchip-sgpio.o obj-$(CONFIG_PINCTRL_EQUILIBRIUM) += pinctrl-equilibrium.o +obj-$(CONFIG_PINCTRL_K210) += pinctrl-k210.o obj-y += actions/ obj-$(CONFIG_ARCH_ASPEED) += aspeed/ diff --git a/drivers/pinctrl/pinctrl-k210.c b/drivers/pinctrl/pinctrl-k210.c new file mode 100644 index 000000000000..8a733cf77ba0 --- /dev/null +++ b/drivers/pinctrl/pinctrl-k210.c @@ -0,0 +1,985 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2020 Sean Anderson + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "core.h" +#include "pinconf.h" +#include "pinctrl-utils.h" + +/* + * The K210 only implements 8 drive levels, even though + * there is register space for 16 + */ +#define K210_PC_DRIVE_MASK GENMASK(11, 8) +#define K210_PC_DRIVE_SHIFT 8 +#define K210_PC_DRIVE_0 (0 << K210_PC_DRIVE_SHIFT) +#define K210_PC_DRIVE_1 (1 << K210_PC_DRIVE_SHIFT) +#define K210_PC_DRIVE_2 (2 << K210_PC_DRIVE_SHIFT) +#define K210_PC_DRIVE_3 (3 << K210_PC_DRIVE_SHIFT) +#define K210_PC_DRIVE_4 (4 << K210_PC_DRIVE_SHIFT) +#define K210_PC_DRIVE_5 (5 << K210_PC_DRIVE_SHIFT) +#define K210_PC_DRIVE_6 (6 << K210_PC_DRIVE_SHIFT) +#define K210_PC_DRIVE_7 (7 << K210_PC_DRIVE_SHIFT) +#define K210_PC_DRIVE_MAX 7 +#define K210_PC_MODE_MASK GENMASK(23, 12) + +/* + * output enabled == PC_OE & (PC_OE_INV ^ FUNCTION_OE) + * where FUNCTION_OE is a physical signal from the function. + */ +#define K210_PC_OE BIT(12) /* Output Enable */ +#define K210_PC_OE_INV BIT(13) /* INVert Output Enable */ +#define K210_PC_DO_OE BIT(14) /* set Data Out to Output Enable sig */ +#define K210_PC_DO_INV BIT(15) /* INVert final Data Output */ +#define K210_PC_PU BIT(16) /* Pull Up */ +#define K210_PC_PD BIT(17) /* Pull Down */ +/* Strong pull up not implemented on K210 */ +#define K210_PC_SL BIT(19) /* reduce SLew rate */ +/* Same semantics as OE above */ +#define K210_PC_IE BIT(20) /* Input Enable */ +#define K210_PC_IE_INV BIT(21) /* INVert Input Enable */ +#define K210_PC_DI_INV BIT(22) /* INVert Data Input */ +#define K210_PC_ST BIT(23) /* Schmitt Trigger */ +#define K210_PC_DI BIT(31) /* raw Data Input */ + +#define K210_PC_BIAS_MASK (K210_PC_PU & K210_PC_PD) + +#define K210_PC_MODE_IN (K210_PC_IE | K210_PC_ST) +#define K210_PC_MODE_OUT (K210_PC_DRIVE_7 | K210_PC_OE) +#define K210_PC_MODE_I2C (K210_PC_MODE_IN | K210_PC_SL | \ + K210_PC_OE | K210_PC_PU) +#define K210_PC_MODE_SCCB (K210_PC_MODE_I2C | \ + K210_PC_OE_INV | K210_PC_IE_INV) +#define K210_PC_MODE_SPI (K210_PC_MODE_IN | K210_PC_IE_INV | \ + K210_PC_MODE_OUT | K210_PC_OE_INV) +#define K210_PC_MODE_GPIO (K210_PC_MODE_IN | K210_PC_MODE_OUT) + +#define K210_PG_FUNC GENMASK(7, 0) +#define K210_PG_DO BIT(8) +#define K210_PG_PIN GENMASK(22, 16) + +/* + * struct k210_fpioa: Kendryte K210 FPIOA memory mapped registers + * @pins: 48 32-bits IO pin registers + * @tie_en: 256 (one per function) input tie enable bits + * @tie_val: 256 (one per function) input tie value bits + */ +struct k210_fpioa { + u32 pins[48]; + u32 tie_en[8]; + u32 tie_val[8]; +}; + +struct k210_fpioa_data { + + struct device *dev; + struct pinctrl_dev *pctl; + + struct k210_fpioa __iomem *fpioa; + struct regmap *sysctl_map; + u32 power_offset; + struct clk *clk; + struct clk *pclk; +}; + +#define K210_PIN_NAME(i) ("IO_" #i) +#define K210_PIN(i) [(i)] = PINCTRL_PIN((i), K210_PIN_NAME(i)) + +static const struct pinctrl_pin_desc k210_pins[] = { + K210_PIN(0), K210_PIN(1), K210_PIN(2), + K210_PIN(3), K210_PIN(4), K210_PIN(5), + K210_PIN(6), K210_PIN(7), K210_PIN(8), + K210_PIN(9), K210_PIN(10), K210_PIN(11), + K210_PIN(12), K210_PIN(13), K210_PIN(14), + K210_PIN(15), K210_PIN(16), K210_PIN(17), + K210_PIN(18), K210_PIN(19), K210_PIN(20), + K210_PIN(21), K210_PIN(22), K210_PIN(23), + K210_PIN(24), K210_PIN(25), K210_PIN(26), + K210_PIN(27), K210_PIN(28), K210_PIN(29), + K210_PIN(30), K210_PIN(31), K210_PIN(32), + K210_PIN(33), K210_PIN(34), K210_PIN(35), + K210_PIN(36), K210_PIN(37), K210_PIN(38), + K210_PIN(39), K210_PIN(40), K210_PIN(41), + K210_PIN(42), K210_PIN(43), K210_PIN(44), + K210_PIN(45), K210_PIN(46), K210_PIN(47) +}; + +#define K210_NPINS ARRAY_SIZE(k210_pins) + +/* + * Pin groups: each of the 48 programmable pins is a group. + * To this are added 8 power domain groups, which for the purposes of + * the pin subsystem, contain no pins. The power domain groups only exist + * to set the power level. The id should never be used (since there are + * no pins 48-55). + */ +static const char *const k210_group_names[] = { + /* The first 48 groups are for pins, one each */ + K210_PIN_NAME(0), K210_PIN_NAME(1), K210_PIN_NAME(2), + K210_PIN_NAME(3), K210_PIN_NAME(4), K210_PIN_NAME(5), + K210_PIN_NAME(6), K210_PIN_NAME(7), K210_PIN_NAME(8), + K210_PIN_NAME(9), K210_PIN_NAME(10), K210_PIN_NAME(11), + K210_PIN_NAME(12), K210_PIN_NAME(13), K210_PIN_NAME(14), + K210_PIN_NAME(15), K210_PIN_NAME(16), K210_PIN_NAME(17), + K210_PIN_NAME(18), K210_PIN_NAME(19), K210_PIN_NAME(20), + K210_PIN_NAME(21), K210_PIN_NAME(22), K210_PIN_NAME(23), + K210_PIN_NAME(24), K210_PIN_NAME(25), K210_PIN_NAME(26), + K210_PIN_NAME(27), K210_PIN_NAME(28), K210_PIN_NAME(29), + K210_PIN_NAME(30), K210_PIN_NAME(31), K210_PIN_NAME(32), + K210_PIN_NAME(33), K210_PIN_NAME(34), K210_PIN_NAME(35), + K210_PIN_NAME(36), K210_PIN_NAME(37), K210_PIN_NAME(38), + K210_PIN_NAME(39), K210_PIN_NAME(40), K210_PIN_NAME(41), + K210_PIN_NAME(42), K210_PIN_NAME(43), K210_PIN_NAME(44), + K210_PIN_NAME(45), K210_PIN_NAME(46), K210_PIN_NAME(47), + [48] = "A0", [49] = "A1", [50] = "A2", + [51] = "B3", [52] = "B4", [53] = "B5", + [54] = "C6", [55] = "C7" +}; + +#define K210_NGROUPS ARRAY_SIZE(k210_group_names) + +enum k210_pinctrl_mode_id { + K210_PC_DEFAULT_DISABLED, + K210_PC_DEFAULT_IN, + K210_PC_DEFAULT_IN_TIE, + K210_PC_DEFAULT_OUT, + K210_PC_DEFAULT_I2C, + K210_PC_DEFAULT_SCCB, + K210_PC_DEFAULT_SPI, + K210_PC_DEFAULT_GPIO, + K210_PC_DEFAULT_INT13, +}; + +#define K210_PC_DEFAULT(mode) \ + [K210_PC_DEFAULT_##mode] = K210_PC_MODE_##mode + +static const u32 k210_pinconf_mode_id_to_mode[] = { + [K210_PC_DEFAULT_DISABLED] = 0, + K210_PC_DEFAULT(IN), + [K210_PC_DEFAULT_IN_TIE] = K210_PC_MODE_IN, + K210_PC_DEFAULT(OUT), + K210_PC_DEFAULT(I2C), + K210_PC_DEFAULT(SCCB), + K210_PC_DEFAULT(SPI), + K210_PC_DEFAULT(GPIO), + [K210_PC_DEFAULT_INT13] = K210_PC_MODE_IN | K210_PC_PU, +}; + +#undef DEFAULT + +/* + * Pin functions configuration information. + */ +struct k210_pcf_info { + char name[15]; + u8 mode_id; +}; + +#define K210_FUNC(id, mode) \ + [K210_PCF_##id] = { \ + .name = #id, \ + .mode_id = K210_PC_DEFAULT_##mode \ + } + +static const struct k210_pcf_info k210_pcf_infos[] = { + K210_FUNC(JTAG_TCLK, IN), + K210_FUNC(JTAG_TDI, IN), + K210_FUNC(JTAG_TMS, IN), + K210_FUNC(JTAG_TDO, OUT), + K210_FUNC(SPI0_D0, SPI), + K210_FUNC(SPI0_D1, SPI), + K210_FUNC(SPI0_D2, SPI), + K210_FUNC(SPI0_D3, SPI), + K210_FUNC(SPI0_D4, SPI), + K210_FUNC(SPI0_D5, SPI), + K210_FUNC(SPI0_D6, SPI), + K210_FUNC(SPI0_D7, SPI), + K210_FUNC(SPI0_SS0, OUT), + K210_FUNC(SPI0_SS1, OUT), + K210_FUNC(SPI0_SS2, OUT), + K210_FUNC(SPI0_SS3, OUT), + K210_FUNC(SPI0_ARB, IN_TIE), + K210_FUNC(SPI0_SCLK, OUT), + K210_FUNC(UARTHS_RX, IN), + K210_FUNC(UARTHS_TX, OUT), + K210_FUNC(RESV6, IN), + K210_FUNC(RESV7, IN), + K210_FUNC(CLK_SPI1, OUT), + K210_FUNC(CLK_I2C1, OUT), + K210_FUNC(GPIOHS0, GPIO), + K210_FUNC(GPIOHS1, GPIO), + K210_FUNC(GPIOHS2, GPIO), + K210_FUNC(GPIOHS3, GPIO), + K210_FUNC(GPIOHS4, GPIO), + K210_FUNC(GPIOHS5, GPIO), + K210_FUNC(GPIOHS6, GPIO), + K210_FUNC(GPIOHS7, GPIO), + K210_FUNC(GPIOHS8, GPIO), + K210_FUNC(GPIOHS9, GPIO), + K210_FUNC(GPIOHS10, GPIO), + K210_FUNC(GPIOHS11, GPIO), + K210_FUNC(GPIOHS12, GPIO), + K210_FUNC(GPIOHS13, GPIO), + K210_FUNC(GPIOHS14, GPIO), + K210_FUNC(GPIOHS15, GPIO), + K210_FUNC(GPIOHS16, GPIO), + K210_FUNC(GPIOHS17, GPIO), + K210_FUNC(GPIOHS18, GPIO), + K210_FUNC(GPIOHS19, GPIO), + K210_FUNC(GPIOHS20, GPIO), + K210_FUNC(GPIOHS21, GPIO), + K210_FUNC(GPIOHS22, GPIO), + K210_FUNC(GPIOHS23, GPIO), + K210_FUNC(GPIOHS24, GPIO), + K210_FUNC(GPIOHS25, GPIO), + K210_FUNC(GPIOHS26, GPIO), + K210_FUNC(GPIOHS27, GPIO), + K210_FUNC(GPIOHS28, GPIO), + K210_FUNC(GPIOHS29, GPIO), + K210_FUNC(GPIOHS30, GPIO), + K210_FUNC(GPIOHS31, GPIO), + K210_FUNC(GPIO0, GPIO), + K210_FUNC(GPIO1, GPIO), + K210_FUNC(GPIO2, GPIO), + K210_FUNC(GPIO3, GPIO), + K210_FUNC(GPIO4, GPIO), + K210_FUNC(GPIO5, GPIO), + K210_FUNC(GPIO6, GPIO), + K210_FUNC(GPIO7, GPIO), + K210_FUNC(UART1_RX, IN), + K210_FUNC(UART1_TX, OUT), + K210_FUNC(UART2_RX, IN), + K210_FUNC(UART2_TX, OUT), + K210_FUNC(UART3_RX, IN), + K210_FUNC(UART3_TX, OUT), + K210_FUNC(SPI1_D0, SPI), + K210_FUNC(SPI1_D1, SPI), + K210_FUNC(SPI1_D2, SPI), + K210_FUNC(SPI1_D3, SPI), + K210_FUNC(SPI1_D4, SPI), + K210_FUNC(SPI1_D5, SPI), + K210_FUNC(SPI1_D6, SPI), + K210_FUNC(SPI1_D7, SPI), + K210_FUNC(SPI1_SS0, OUT), + K210_FUNC(SPI1_SS1, OUT), + K210_FUNC(SPI1_SS2, OUT), + K210_FUNC(SPI1_SS3, OUT), + K210_FUNC(SPI1_ARB, IN_TIE), + K210_FUNC(SPI1_SCLK, OUT), + K210_FUNC(SPI2_D0, SPI), + K210_FUNC(SPI2_SS, IN), + K210_FUNC(SPI2_SCLK, IN), + K210_FUNC(I2S0_MCLK, OUT), + K210_FUNC(I2S0_SCLK, OUT), + K210_FUNC(I2S0_WS, OUT), + K210_FUNC(I2S0_IN_D0, IN), + K210_FUNC(I2S0_IN_D1, IN), + K210_FUNC(I2S0_IN_D2, IN), + K210_FUNC(I2S0_IN_D3, IN), + K210_FUNC(I2S0_OUT_D0, OUT), + K210_FUNC(I2S0_OUT_D1, OUT), + K210_FUNC(I2S0_OUT_D2, OUT), + K210_FUNC(I2S0_OUT_D3, OUT), + K210_FUNC(I2S1_MCLK, OUT), + K210_FUNC(I2S1_SCLK, OUT), + K210_FUNC(I2S1_WS, OUT), + K210_FUNC(I2S1_IN_D0, IN), + K210_FUNC(I2S1_IN_D1, IN), + K210_FUNC(I2S1_IN_D2, IN), + K210_FUNC(I2S1_IN_D3, IN), + K210_FUNC(I2S1_OUT_D0, OUT), + K210_FUNC(I2S1_OUT_D1, OUT), + K210_FUNC(I2S1_OUT_D2, OUT), + K210_FUNC(I2S1_OUT_D3, OUT), + K210_FUNC(I2S2_MCLK, OUT), + K210_FUNC(I2S2_SCLK, OUT), + K210_FUNC(I2S2_WS, OUT), + K210_FUNC(I2S2_IN_D0, IN), + K210_FUNC(I2S2_IN_D1, IN), + K210_FUNC(I2S2_IN_D2, IN), + K210_FUNC(I2S2_IN_D3, IN), + K210_FUNC(I2S2_OUT_D0, OUT), + K210_FUNC(I2S2_OUT_D1, OUT), + K210_FUNC(I2S2_OUT_D2, OUT), + K210_FUNC(I2S2_OUT_D3, OUT), + K210_FUNC(RESV0, DISABLED), + K210_FUNC(RESV1, DISABLED), + K210_FUNC(RESV2, DISABLED), + K210_FUNC(RESV3, DISABLED), + K210_FUNC(RESV4, DISABLED), + K210_FUNC(RESV5, DISABLED), + K210_FUNC(I2C0_SCLK, I2C), + K210_FUNC(I2C0_SDA, I2C), + K210_FUNC(I2C1_SCLK, I2C), + K210_FUNC(I2C1_SDA, I2C), + K210_FUNC(I2C2_SCLK, I2C), + K210_FUNC(I2C2_SDA, I2C), + K210_FUNC(DVP_XCLK, OUT), + K210_FUNC(DVP_RST, OUT), + K210_FUNC(DVP_PWDN, OUT), + K210_FUNC(DVP_VSYNC, IN), + K210_FUNC(DVP_HSYNC, IN), + K210_FUNC(DVP_PCLK, IN), + K210_FUNC(DVP_D0, IN), + K210_FUNC(DVP_D1, IN), + K210_FUNC(DVP_D2, IN), + K210_FUNC(DVP_D3, IN), + K210_FUNC(DVP_D4, IN), + K210_FUNC(DVP_D5, IN), + K210_FUNC(DVP_D6, IN), + K210_FUNC(DVP_D7, IN), + K210_FUNC(SCCB_SCLK, SCCB), + K210_FUNC(SCCB_SDA, SCCB), + K210_FUNC(UART1_CTS, IN), + K210_FUNC(UART1_DSR, IN), + K210_FUNC(UART1_DCD, IN), + K210_FUNC(UART1_RI, IN), + K210_FUNC(UART1_SIR_IN, IN), + K210_FUNC(UART1_DTR, OUT), + K210_FUNC(UART1_RTS, OUT), + K210_FUNC(UART1_OUT2, OUT), + K210_FUNC(UART1_OUT1, OUT), + K210_FUNC(UART1_SIR_OUT, OUT), + K210_FUNC(UART1_BAUD, OUT), + K210_FUNC(UART1_RE, OUT), + K210_FUNC(UART1_DE, OUT), + K210_FUNC(UART1_RS485_EN, OUT), + K210_FUNC(UART2_CTS, IN), + K210_FUNC(UART2_DSR, IN), + K210_FUNC(UART2_DCD, IN), + K210_FUNC(UART2_RI, IN), + K210_FUNC(UART2_SIR_IN, IN), + K210_FUNC(UART2_DTR, OUT), + K210_FUNC(UART2_RTS, OUT), + K210_FUNC(UART2_OUT2, OUT), + K210_FUNC(UART2_OUT1, OUT), + K210_FUNC(UART2_SIR_OUT, OUT), + K210_FUNC(UART2_BAUD, OUT), + K210_FUNC(UART2_RE, OUT), + K210_FUNC(UART2_DE, OUT), + K210_FUNC(UART2_RS485_EN, OUT), + K210_FUNC(UART3_CTS, IN), + K210_FUNC(UART3_DSR, IN), + K210_FUNC(UART3_DCD, IN), + K210_FUNC(UART3_RI, IN), + K210_FUNC(UART3_SIR_IN, IN), + K210_FUNC(UART3_DTR, OUT), + K210_FUNC(UART3_RTS, OUT), + K210_FUNC(UART3_OUT2, OUT), + K210_FUNC(UART3_OUT1, OUT), + K210_FUNC(UART3_SIR_OUT, OUT), + K210_FUNC(UART3_BAUD, OUT), + K210_FUNC(UART3_RE, OUT), + K210_FUNC(UART3_DE, OUT), + K210_FUNC(UART3_RS485_EN, OUT), + K210_FUNC(TIMER0_TOGGLE1, OUT), + K210_FUNC(TIMER0_TOGGLE2, OUT), + K210_FUNC(TIMER0_TOGGLE3, OUT), + K210_FUNC(TIMER0_TOGGLE4, OUT), + K210_FUNC(TIMER1_TOGGLE1, OUT), + K210_FUNC(TIMER1_TOGGLE2, OUT), + K210_FUNC(TIMER1_TOGGLE3, OUT), + K210_FUNC(TIMER1_TOGGLE4, OUT), + K210_FUNC(TIMER2_TOGGLE1, OUT), + K210_FUNC(TIMER2_TOGGLE2, OUT), + K210_FUNC(TIMER2_TOGGLE3, OUT), + K210_FUNC(TIMER2_TOGGLE4, OUT), + K210_FUNC(CLK_SPI2, OUT), + K210_FUNC(CLK_I2C2, OUT), + K210_FUNC(INTERNAL0, OUT), + K210_FUNC(INTERNAL1, OUT), + K210_FUNC(INTERNAL2, OUT), + K210_FUNC(INTERNAL3, OUT), + K210_FUNC(INTERNAL4, OUT), + K210_FUNC(INTERNAL5, OUT), + K210_FUNC(INTERNAL6, OUT), + K210_FUNC(INTERNAL7, OUT), + K210_FUNC(INTERNAL8, OUT), + K210_FUNC(INTERNAL9, IN), + K210_FUNC(INTERNAL10, IN), + K210_FUNC(INTERNAL11, IN), + K210_FUNC(INTERNAL12, IN), + K210_FUNC(INTERNAL13, INT13), + K210_FUNC(INTERNAL14, I2C), + K210_FUNC(INTERNAL15, IN), + K210_FUNC(INTERNAL16, IN), + K210_FUNC(INTERNAL17, IN), + K210_FUNC(CONSTANT, DISABLED), + K210_FUNC(INTERNAL18, IN), + K210_FUNC(DEBUG0, OUT), + K210_FUNC(DEBUG1, OUT), + K210_FUNC(DEBUG2, OUT), + K210_FUNC(DEBUG3, OUT), + K210_FUNC(DEBUG4, OUT), + K210_FUNC(DEBUG5, OUT), + K210_FUNC(DEBUG6, OUT), + K210_FUNC(DEBUG7, OUT), + K210_FUNC(DEBUG8, OUT), + K210_FUNC(DEBUG9, OUT), + K210_FUNC(DEBUG10, OUT), + K210_FUNC(DEBUG11, OUT), + K210_FUNC(DEBUG12, OUT), + K210_FUNC(DEBUG13, OUT), + K210_FUNC(DEBUG14, OUT), + K210_FUNC(DEBUG15, OUT), + K210_FUNC(DEBUG16, OUT), + K210_FUNC(DEBUG17, OUT), + K210_FUNC(DEBUG18, OUT), + K210_FUNC(DEBUG19, OUT), + K210_FUNC(DEBUG20, OUT), + K210_FUNC(DEBUG21, OUT), + K210_FUNC(DEBUG22, OUT), + K210_FUNC(DEBUG23, OUT), + K210_FUNC(DEBUG24, OUT), + K210_FUNC(DEBUG25, OUT), + K210_FUNC(DEBUG26, OUT), + K210_FUNC(DEBUG27, OUT), + K210_FUNC(DEBUG28, OUT), + K210_FUNC(DEBUG29, OUT), + K210_FUNC(DEBUG30, OUT), + K210_FUNC(DEBUG31, OUT), +}; + +#define PIN_CONFIG_OUTPUT_INVERT (PIN_CONFIG_END + 1) +#define PIN_CONFIG_INPUT_INVERT (PIN_CONFIG_END + 2) + +static const struct pinconf_generic_params k210_pinconf_custom_params[] = { + { "output-polarity-invert", PIN_CONFIG_OUTPUT_INVERT, 1 }, + { "input-polarity-invert", PIN_CONFIG_INPUT_INVERT, 1 }, +}; + +/* + * Max drive strength in uA. + */ +static const int k210_pinconf_drive_strength[] = { + [0] = 11200, + [1] = 16800, + [2] = 22300, + [3] = 27800, + [4] = 33300, + [5] = 38700, + [6] = 44100, + [7] = 49500, +}; + +static int k210_pinconf_get_drive(unsigned int max_strength_ua) +{ + int i; + + for (i = K210_PC_DRIVE_MAX; i; i--) { + if (k210_pinconf_drive_strength[i] <= max_strength_ua) + return i; + } + + return -EINVAL; +} + +static void k210_pinmux_set_pin_function(struct pinctrl_dev *pctldev, + u32 pin, u32 func) +{ + struct k210_fpioa_data *pdata = pinctrl_dev_get_drvdata(pctldev); + const struct k210_pcf_info *info = &k210_pcf_infos[func]; + u32 mode = k210_pinconf_mode_id_to_mode[info->mode_id]; + u32 val = func | mode; + + dev_dbg(pdata->dev, "set pin %u function %s (%u) -> 0x%08x\n", + pin, info->name, func, val); + + writel(val, &pdata->fpioa->pins[pin]); +} + +static int k210_pinconf_set_param(struct pinctrl_dev *pctldev, + unsigned int pin, + unsigned int param, unsigned int arg) +{ + struct k210_fpioa_data *pdata = pinctrl_dev_get_drvdata(pctldev); + u32 val = readl(&pdata->fpioa->pins[pin]); + int drive; + + dev_dbg(pdata->dev, "set pin %u param %u, arg 0x%x\n", + pin, param, arg); + + switch (param) { + case PIN_CONFIG_BIAS_DISABLE: + val &= ~K210_PC_BIAS_MASK; + break; + case PIN_CONFIG_BIAS_PULL_DOWN: + if (!arg) + return -EINVAL; + val |= K210_PC_PD; + break; + case PIN_CONFIG_BIAS_PULL_UP: + if (!arg) + return -EINVAL; + val |= K210_PC_PD; + break; + case PIN_CONFIG_DRIVE_STRENGTH: + arg *= 1000; + fallthrough; + case PIN_CONFIG_DRIVE_STRENGTH_UA: + drive = k210_pinconf_get_drive(arg); + if (drive < 0) + return drive; + val &= ~K210_PC_DRIVE_MASK; + val |= FIELD_PREP(K210_PC_DRIVE_MASK, drive); + break; + case PIN_CONFIG_INPUT_ENABLE: + if (arg) + val |= K210_PC_IE; + else + val &= ~K210_PC_IE; + break; + case PIN_CONFIG_INPUT_SCHMITT_ENABLE: + if (arg) + val |= K210_PC_ST; + else + val &= ~K210_PC_ST; + break; + case PIN_CONFIG_OUTPUT: + k210_pinmux_set_pin_function(pctldev, pin, K210_PCF_CONSTANT); + val = readl(&pdata->fpioa->pins[pin]); + val |= K210_PC_MODE_OUT; + if (!arg) + val |= K210_PC_DO_INV; + break; + case PIN_CONFIG_OUTPUT_ENABLE: + if (arg) + val |= K210_PC_OE; + else + val &= ~K210_PC_OE; + break; + case PIN_CONFIG_SLEW_RATE: + if (arg) + val |= K210_PC_SL; + else + val &= ~K210_PC_SL; + break; + case PIN_CONFIG_OUTPUT_INVERT: + if (arg) + val |= K210_PC_DO_INV; + else + val &= ~K210_PC_DO_INV; + break; + case PIN_CONFIG_INPUT_INVERT: + if (arg) + val |= K210_PC_DI_INV; + else + val &= ~K210_PC_DI_INV; + break; + default: + return -EINVAL; + } + + writel(val, &pdata->fpioa->pins[pin]); + + return 0; +} + +static int k210_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, + unsigned long *configs, unsigned int num_configs) +{ + unsigned int param, arg; + int i, ret; + + if (WARN_ON(pin >= K210_NPINS)) + return -EINVAL; + + for (i = 0; i < num_configs; i++) { + param = pinconf_to_config_param(configs[i]); + arg = pinconf_to_config_argument(configs[i]); + ret = k210_pinconf_set_param(pctldev, pin, param, arg); + if (ret) + return ret; + } + + return 0; +} + +static void k210_pinconf_dbg_show(struct pinctrl_dev *pctldev, + struct seq_file *s, unsigned int pin) +{ + struct k210_fpioa_data *pdata = pinctrl_dev_get_drvdata(pctldev); + + seq_printf(s, "%#x", readl(&pdata->fpioa->pins[pin])); +} + +static int k210_pinconf_group_set(struct pinctrl_dev *pctldev, + unsigned int selector, unsigned long *configs, + unsigned int num_configs) +{ + struct k210_fpioa_data *pdata = pinctrl_dev_get_drvdata(pctldev); + unsigned int param, arg; + u32 bit; + int i; + + /* Pins should be configured with pinmux, not groups*/ + if (selector < K210_NPINS) + return -EINVAL; + + /* Otherwise it's a power domain */ + for (i = 0; i < num_configs; i++) { + param = pinconf_to_config_param(configs[i]); + if (param != PIN_CONFIG_POWER_SOURCE) + return -EINVAL; + + arg = pinconf_to_config_argument(configs[i]); + bit = BIT(selector - K210_NPINS); + regmap_update_bits(pdata->sysctl_map, + pdata->power_offset, + bit, arg ? bit : 0); + } + + return 0; +} + +static void k210_pinconf_group_dbg_show(struct pinctrl_dev *pctldev, + struct seq_file *s, + unsigned int selector) +{ + struct k210_fpioa_data *pdata = pinctrl_dev_get_drvdata(pctldev); + int ret; + u32 val; + + if (selector < K210_NPINS) + return k210_pinconf_dbg_show(pctldev, s, selector); + + ret = regmap_read(pdata->sysctl_map, pdata->power_offset, &val); + if (ret) { + dev_err(pdata->dev, "Failed to read power reg\n"); + return; + } + + seq_printf(s, "%s: %s V", k210_group_names[selector], + val & BIT(selector - K210_NPINS) ? "1.8" : "3.3"); +} + +static const struct pinconf_ops k210_pinconf_ops = { + .is_generic = true, + .pin_config_set = k210_pinconf_set, + .pin_config_group_set = k210_pinconf_group_set, + .pin_config_dbg_show = k210_pinconf_dbg_show, + .pin_config_group_dbg_show = k210_pinconf_group_dbg_show, +}; + +static int k210_pinmux_get_function_count(struct pinctrl_dev *pctldev) +{ + return ARRAY_SIZE(k210_pcf_infos); +} + +static const char *k210_pinmux_get_function_name(struct pinctrl_dev *pctldev, + unsigned int selector) +{ + return k210_pcf_infos[selector].name; +} + +static int k210_pinmux_get_function_groups(struct pinctrl_dev *pctldev, + unsigned int selector, + const char * const **groups, + unsigned int * const num_groups) +{ + /* Any function can be mapped to any pin */ + *groups = k210_group_names; + *num_groups = K210_NPINS; + + return 0; +} + +static int k210_pinmux_set_mux(struct pinctrl_dev *pctldev, + unsigned int function, + unsigned int group) +{ + /* Can't mux power domains */ + if (group >= K210_NPINS) + return -EINVAL; + + k210_pinmux_set_pin_function(pctldev, group, function); + + return 0; +} + +static const struct pinmux_ops k210_pinmux_ops = { + .get_functions_count = k210_pinmux_get_function_count, + .get_function_name = k210_pinmux_get_function_name, + .get_function_groups = k210_pinmux_get_function_groups, + .set_mux = k210_pinmux_set_mux, + .strict = true, +}; + +static int k210_pinctrl_get_groups_count(struct pinctrl_dev *pctldev) +{ + return K210_NGROUPS; +} + +static const char *k210_pinctrl_get_group_name(struct pinctrl_dev *pctldev, + unsigned int group) +{ + return k210_group_names[group]; +} + +static int k210_pinctrl_get_group_pins(struct pinctrl_dev *pctldev, + unsigned int group, + const unsigned int **pins, + unsigned int *npins) +{ + if (group >= K210_NPINS) { + *pins = NULL; + *npins = 0; + return 0; + } + + *pins = &k210_pins[group].number; + *npins = 1; + + return 0; +} + +static void k210_pinctrl_pin_dbg_show(struct pinctrl_dev *pctldev, + struct seq_file *s, unsigned int offset) +{ + seq_printf(s, "%s", dev_name(pctldev->dev)); +} + +static int k210_pinctrl_dt_subnode_to_map(struct pinctrl_dev *pctldev, + struct device_node *np, + struct pinctrl_map **map, + unsigned int *reserved_maps, + unsigned int *num_maps) +{ + struct property *prop; + const __be32 *p; + int ret, pinmux_groups; + u32 pinmux_group; + unsigned long *configs = NULL; + unsigned int num_configs = 0; + unsigned int reserve = 0; + + ret = of_property_count_strings(np, "groups"); + if (!ret) + return pinconf_generic_dt_subnode_to_map(pctldev, np, map, + reserved_maps, num_maps, + PIN_MAP_TYPE_CONFIGS_GROUP); + + pinmux_groups = of_property_count_u32_elems(np, "pinmux"); + if (pinmux_groups <= 0) { + /* Ignore this node */ + return 0; + } + + ret = pinconf_generic_parse_dt_config(np, pctldev, &configs, + &num_configs); + if (ret < 0) { + dev_err(pctldev->dev, "%pOF: could not parse node property\n", + np); + return ret; + } + + reserve = pinmux_groups * (1 + num_configs); + ret = pinctrl_utils_reserve_map(pctldev, map, reserved_maps, num_maps, + reserve); + if (ret < 0) + goto exit; + + of_property_for_each_u32(np, "pinmux", prop, p, pinmux_group) { + const char *group_name, *func_name; + u32 pin = FIELD_GET(K210_PG_PIN, pinmux_group); + u32 func = FIELD_GET(K210_PG_FUNC, pinmux_group); + + if (pin >= K210_NPINS) { + ret = -EINVAL; + goto exit; + } + + group_name = k210_group_names[pin]; + func_name = k210_pcf_infos[func].name; + + dev_dbg(pctldev->dev, "Pinmux %s: pin %u func %s\n", + np->name, pin, func_name); + + ret = pinctrl_utils_add_map_mux(pctldev, map, reserved_maps, + num_maps, group_name, + func_name); + if (ret < 0) { + dev_err(pctldev->dev, "%pOF add mux map failed %d\n", + np, ret); + goto exit; + } + + if (num_configs) { + ret = pinctrl_utils_add_map_configs(pctldev, map, + reserved_maps, num_maps, group_name, + configs, num_configs, + PIN_MAP_TYPE_CONFIGS_PIN); + if (ret < 0) { + dev_err(pctldev->dev, + "%pOF add configs map failed %d\n", + np, ret); + goto exit; + } + } + } + + ret = 0; + +exit: + kfree(configs); + return ret; +} + +static int k210_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev, + struct device_node *np_config, + struct pinctrl_map **map, + unsigned int *num_maps) +{ + unsigned int reserved_maps; + struct device_node *np; + int ret; + + reserved_maps = 0; + *map = NULL; + *num_maps = 0; + + ret = k210_pinctrl_dt_subnode_to_map(pctldev, np_config, map, + &reserved_maps, num_maps); + if (ret < 0) + goto err; + + for_each_available_child_of_node(np_config, np) { + ret = k210_pinctrl_dt_subnode_to_map(pctldev, np, map, + &reserved_maps, num_maps); + if (ret < 0) + goto err; + } + return 0; + +err: + pinctrl_utils_free_map(pctldev, *map, *num_maps); + return ret; +} + + +static const struct pinctrl_ops k210_pinctrl_ops = { + .get_groups_count = k210_pinctrl_get_groups_count, + .get_group_name = k210_pinctrl_get_group_name, + .get_group_pins = k210_pinctrl_get_group_pins, + .pin_dbg_show = k210_pinctrl_pin_dbg_show, + .dt_node_to_map = k210_pinctrl_dt_node_to_map, + .dt_free_map = pinconf_generic_dt_free_map, +}; + +static struct pinctrl_desc k210_pinctrl_desc = { + .name = "k210-pinctrl", + .pins = k210_pins, + .npins = K210_NPINS, + .pctlops = &k210_pinctrl_ops, + .pmxops = &k210_pinmux_ops, + .confops = &k210_pinconf_ops, + .custom_params = k210_pinconf_custom_params, + .num_custom_params = ARRAY_SIZE(k210_pinconf_custom_params), +}; + +static void k210_fpioa_init_ties(struct k210_fpioa_data *pdata) +{ + struct k210_fpioa __iomem *fpioa = pdata->fpioa; + u32 val; + int i, j; + + dev_dbg(pdata->dev, "Init pin ties\n"); + + /* Init pin functions input ties */ + for (i = 0; i < ARRAY_SIZE(fpioa->tie_en); i++) { + val = 0; + for (j = 0; j < 32; j++) { + if (k210_pcf_infos[i * 32 + j].mode_id == + K210_PC_DEFAULT_IN_TIE) { + dev_dbg(pdata->dev, + "tie_en function %d (%s)\n", + i * 32 + j, + k210_pcf_infos[i * 32 + j].name); + val |= BIT(j); + } + } + + /* Set value before enable */ + writel(val, &fpioa->tie_val[i]); + writel(val, &fpioa->tie_en[i]); + } +} + +static int k210_fpioa_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct k210_fpioa_data *pdata; + int ret; + + dev_info(dev, "K210 FPIOA pin controller\n"); + + pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return -ENOMEM; + + pdata->dev = dev; + platform_set_drvdata(pdev, pdata); + + pdata->fpioa = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(pdata->fpioa)) + return PTR_ERR(pdata->fpioa); + + pdata->clk = devm_clk_get(dev, "ref"); + if (IS_ERR(pdata->clk)) + return PTR_ERR(pdata->clk); + + ret = clk_prepare_enable(pdata->clk); + if (ret) + return ret; + + pdata->pclk = devm_clk_get_optional(dev, "pclk"); + if (!IS_ERR(pdata->pclk)) + clk_prepare_enable(pdata->pclk); + + pdata->sysctl_map = + syscon_regmap_lookup_by_phandle_args(np, + "canaan,k210-sysctl-power", + 1, &pdata->power_offset); + if (IS_ERR(pdata->sysctl_map)) + return PTR_ERR(pdata->sysctl_map); + + k210_fpioa_init_ties(pdata); + + pdata->pctl = pinctrl_register(&k210_pinctrl_desc, dev, (void *)pdata); + if (IS_ERR(pdata->pctl)) + return PTR_ERR(pdata->pctl); + + return 0; +} + +static const struct of_device_id k210_fpioa_dt_ids[] = { + { .compatible = "canaan,k210-fpioa" }, + { /* sentinel */ }, +}; + +static struct platform_driver k210_fpioa_driver = { + .probe = k210_fpioa_probe, + .driver = { + .name = "k210-fpioa", + .of_match_table = k210_fpioa_dt_ids, + }, +}; +builtin_platform_driver(k210_fpioa_driver); diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 56353e8c792a..ad4e630e73e2 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -450,7 +450,7 @@ config IDEAPAD_LAPTOP depends on BACKLIGHT_CLASS_DEVICE depends on ACPI_VIDEO || ACPI_VIDEO = n depends on ACPI_WMI || ACPI_WMI = n - depends on ACPI_PLATFORM_PROFILE + select ACPI_PLATFORM_PROFILE select INPUT_SPARSEKMAP select NEW_LEDS select LEDS_CLASS @@ -484,7 +484,7 @@ config THINKPAD_ACPI depends on RFKILL || RFKILL = n depends on ACPI_VIDEO || ACPI_VIDEO = n depends on BACKLIGHT_CLASS_DEVICE - depends on ACPI_PLATFORM_PROFILE + select ACPI_PLATFORM_PROFILE select HWMON select NVRAM select NEW_LEDS diff --git a/drivers/pwm/Kconfig b/drivers/pwm/Kconfig index 0937e1c047ac..9a4f66ae8070 100644 --- a/drivers/pwm/Kconfig +++ b/drivers/pwm/Kconfig @@ -611,14 +611,4 @@ config PWM_VT8500 To compile this driver as a module, choose M here: the module will be called pwm-vt8500. -config PWM_ZX - tristate "ZTE ZX PWM support" - depends on ARCH_ZX || COMPILE_TEST - depends on HAS_IOMEM - help - Generic PWM framework driver for ZTE ZX family SoCs. - - To compile this driver as a module, choose M here: the module - will be called pwm-zx. - endif diff --git a/drivers/pwm/Makefile b/drivers/pwm/Makefile index 18b89d7fd092..6374d3b1d6f3 100644 --- a/drivers/pwm/Makefile +++ b/drivers/pwm/Makefile @@ -57,4 +57,3 @@ obj-$(CONFIG_PWM_TIEHRPWM) += pwm-tiehrpwm.o obj-$(CONFIG_PWM_TWL) += pwm-twl.o obj-$(CONFIG_PWM_TWL_LED) += pwm-twl-led.o obj-$(CONFIG_PWM_VT8500) += pwm-vt8500.o -obj-$(CONFIG_PWM_ZX) += pwm-zx.o diff --git a/drivers/pwm/pwm-iqs620a.c b/drivers/pwm/pwm-iqs620a.c index 5ede8255926e..957b972c458b 100644 --- a/drivers/pwm/pwm-iqs620a.c +++ b/drivers/pwm/pwm-iqs620a.c @@ -37,16 +37,34 @@ struct iqs620_pwm_private { struct pwm_chip chip; struct notifier_block notifier; struct mutex lock; - bool out_en; - u8 duty_val; + unsigned int duty_scale; }; +static int iqs620_pwm_init(struct iqs620_pwm_private *iqs620_pwm, + unsigned int duty_scale) +{ + struct iqs62x_core *iqs62x = iqs620_pwm->iqs62x; + int ret; + + if (!duty_scale) + return regmap_update_bits(iqs62x->regmap, IQS620_PWR_SETTINGS, + IQS620_PWR_SETTINGS_PWM_OUT, 0); + + ret = regmap_write(iqs62x->regmap, IQS620_PWM_DUTY_CYCLE, + duty_scale - 1); + if (ret) + return ret; + + return regmap_update_bits(iqs62x->regmap, IQS620_PWR_SETTINGS, + IQS620_PWR_SETTINGS_PWM_OUT, 0xff); +} + static int iqs620_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, const struct pwm_state *state) { struct iqs620_pwm_private *iqs620_pwm; - struct iqs62x_core *iqs62x; - u64 duty_scale; + unsigned int duty_cycle; + unsigned int duty_scale; int ret; if (state->polarity != PWM_POLARITY_NORMAL) @@ -56,7 +74,6 @@ static int iqs620_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, return -EINVAL; iqs620_pwm = container_of(chip, struct iqs620_pwm_private, chip); - iqs62x = iqs620_pwm->iqs62x; /* * The duty cycle generated by the device is calculated as follows: @@ -70,38 +87,18 @@ static int iqs620_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, * For lower duty cycles (e.g. 0), the PWM output is simply disabled to * allow an external pull-down resistor to hold the GPIO3/LTX pin low. */ - duty_scale = div_u64(state->duty_cycle * 256, IQS620_PWM_PERIOD_NS); + duty_cycle = min_t(u64, state->duty_cycle, IQS620_PWM_PERIOD_NS); + duty_scale = duty_cycle * 256 / IQS620_PWM_PERIOD_NS; + + if (!state->enabled) + duty_scale = 0; mutex_lock(&iqs620_pwm->lock); - if (!state->enabled || !duty_scale) { - ret = regmap_update_bits(iqs62x->regmap, IQS620_PWR_SETTINGS, - IQS620_PWR_SETTINGS_PWM_OUT, 0); - if (ret) - goto err_mutex; - } + ret = iqs620_pwm_init(iqs620_pwm, duty_scale); + if (!ret) + iqs620_pwm->duty_scale = duty_scale; - if (duty_scale) { - u8 duty_val = min_t(u64, duty_scale - 1, 0xff); - - ret = regmap_write(iqs62x->regmap, IQS620_PWM_DUTY_CYCLE, - duty_val); - if (ret) - goto err_mutex; - - iqs620_pwm->duty_val = duty_val; - } - - if (state->enabled && duty_scale) { - ret = regmap_update_bits(iqs62x->regmap, IQS620_PWR_SETTINGS, - IQS620_PWR_SETTINGS_PWM_OUT, 0xff); - if (ret) - goto err_mutex; - } - - iqs620_pwm->out_en = state->enabled; - -err_mutex: mutex_unlock(&iqs620_pwm->lock); return ret; @@ -119,12 +116,11 @@ static void iqs620_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, /* * Since the device cannot generate a 0% duty cycle, requests to do so * cause subsequent calls to iqs620_pwm_get_state to report the output - * as disabled with duty cycle equal to that which was in use prior to - * the request. This is not ideal, but is the best compromise based on + * as disabled. This is not ideal, but is the best compromise based on * the capabilities of the device. */ - state->enabled = iqs620_pwm->out_en; - state->duty_cycle = DIV_ROUND_UP((iqs620_pwm->duty_val + 1) * + state->enabled = iqs620_pwm->duty_scale > 0; + state->duty_cycle = DIV_ROUND_UP(iqs620_pwm->duty_scale * IQS620_PWM_PERIOD_NS, 256); mutex_unlock(&iqs620_pwm->lock); @@ -136,7 +132,6 @@ static int iqs620_pwm_notifier(struct notifier_block *notifier, unsigned long event_flags, void *context) { struct iqs620_pwm_private *iqs620_pwm; - struct iqs62x_core *iqs62x; int ret; if (!(event_flags & BIT(IQS62X_EVENT_SYS_RESET))) @@ -144,7 +139,6 @@ static int iqs620_pwm_notifier(struct notifier_block *notifier, iqs620_pwm = container_of(notifier, struct iqs620_pwm_private, notifier); - iqs62x = iqs620_pwm->iqs62x; mutex_lock(&iqs620_pwm->lock); @@ -153,16 +147,8 @@ static int iqs620_pwm_notifier(struct notifier_block *notifier, * of a device reset, so nothing else is printed here unless there is * an additional failure. */ - ret = regmap_write(iqs62x->regmap, IQS620_PWM_DUTY_CYCLE, - iqs620_pwm->duty_val); - if (ret) - goto err_mutex; + ret = iqs620_pwm_init(iqs620_pwm, iqs620_pwm->duty_scale); - ret = regmap_update_bits(iqs62x->regmap, IQS620_PWR_SETTINGS, - IQS620_PWR_SETTINGS_PWM_OUT, - iqs620_pwm->out_en ? 0xff : 0); - -err_mutex: mutex_unlock(&iqs620_pwm->lock); if (ret) { @@ -209,12 +195,14 @@ static int iqs620_pwm_probe(struct platform_device *pdev) ret = regmap_read(iqs62x->regmap, IQS620_PWR_SETTINGS, &val); if (ret) return ret; - iqs620_pwm->out_en = val & IQS620_PWR_SETTINGS_PWM_OUT; - ret = regmap_read(iqs62x->regmap, IQS620_PWM_DUTY_CYCLE, &val); - if (ret) - return ret; - iqs620_pwm->duty_val = val; + if (val & IQS620_PWR_SETTINGS_PWM_OUT) { + ret = regmap_read(iqs62x->regmap, IQS620_PWM_DUTY_CYCLE, &val); + if (ret) + return ret; + + iqs620_pwm->duty_scale = val + 1; + } iqs620_pwm->chip.dev = &pdev->dev; iqs620_pwm->chip.ops = &iqs620_pwm_ops; diff --git a/drivers/pwm/pwm-lpc18xx-sct.c b/drivers/pwm/pwm-lpc18xx-sct.c index dc5133bec3e7..7ef40243eb6c 100644 --- a/drivers/pwm/pwm-lpc18xx-sct.c +++ b/drivers/pwm/pwm-lpc18xx-sct.c @@ -289,7 +289,7 @@ static int lpc18xx_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm) dev_err(lpc18xx_pwm->dev, "maximum number of simultaneous channels reached\n"); return -EBUSY; - }; + } set_bit(event, &lpc18xx_pwm->event_map); lpc18xx_data->duty_event = event; diff --git a/drivers/pwm/pwm-rockchip.c b/drivers/pwm/pwm-rockchip.c index 389a5e140412..6ad7d0a50aed 100644 --- a/drivers/pwm/pwm-rockchip.c +++ b/drivers/pwm/pwm-rockchip.c @@ -72,6 +72,10 @@ static void rockchip_pwm_get_state(struct pwm_chip *chip, if (ret) return; + ret = clk_enable(pc->clk); + if (ret) + return; + clk_rate = clk_get_rate(pc->clk); tmp = readl_relaxed(pc->base + pc->data->regs.period); @@ -90,6 +94,7 @@ static void rockchip_pwm_get_state(struct pwm_chip *chip, else state->polarity = PWM_POLARITY_NORMAL; + clk_disable(pc->clk); clk_disable(pc->pclk); } @@ -189,6 +194,10 @@ static int rockchip_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, if (ret) return ret; + ret = clk_enable(pc->clk); + if (ret) + return ret; + pwm_get_state(pwm, &curstate); enabled = curstate.enabled; @@ -208,6 +217,7 @@ static int rockchip_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, } out: + clk_disable(pc->clk); clk_disable(pc->pclk); return ret; @@ -288,6 +298,7 @@ static int rockchip_pwm_probe(struct platform_device *pdev) const struct of_device_id *id; struct rockchip_pwm_chip *pc; u32 enable_conf, ctrl; + bool enabled; int ret, count; id = of_match_device(rockchip_pwm_dt_ids, &pdev->dev); @@ -307,7 +318,7 @@ static int rockchip_pwm_probe(struct platform_device *pdev) pc->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(pc->clk)) return dev_err_probe(&pdev->dev, PTR_ERR(pc->clk), - "Can't get bus clk\n"); + "Can't get PWM clk\n"); } count = of_count_phandle_with_args(pdev->dev.of_node, @@ -326,13 +337,13 @@ static int rockchip_pwm_probe(struct platform_device *pdev) ret = clk_prepare_enable(pc->clk); if (ret) { - dev_err(&pdev->dev, "Can't prepare enable bus clk: %d\n", ret); + dev_err(&pdev->dev, "Can't prepare enable PWM clk: %d\n", ret); return ret; } - ret = clk_prepare(pc->pclk); + ret = clk_prepare_enable(pc->pclk); if (ret) { - dev_err(&pdev->dev, "Can't prepare APB clk: %d\n", ret); + dev_err(&pdev->dev, "Can't prepare enable APB clk: %d\n", ret); goto err_clk; } @@ -349,23 +360,26 @@ static int rockchip_pwm_probe(struct platform_device *pdev) pc->chip.of_pwm_n_cells = 3; } + enable_conf = pc->data->enable_conf; + ctrl = readl_relaxed(pc->base + pc->data->regs.ctrl); + enabled = (ctrl & enable_conf) == enable_conf; + ret = pwmchip_add(&pc->chip); if (ret < 0) { - clk_unprepare(pc->clk); dev_err(&pdev->dev, "pwmchip_add() failed: %d\n", ret); goto err_pclk; } /* Keep the PWM clk enabled if the PWM appears to be up and running. */ - enable_conf = pc->data->enable_conf; - ctrl = readl_relaxed(pc->base + pc->data->regs.ctrl); - if ((ctrl & enable_conf) != enable_conf) + if (!enabled) clk_disable(pc->clk); + clk_disable(pc->pclk); + return 0; err_pclk: - clk_unprepare(pc->pclk); + clk_disable_unprepare(pc->pclk); err_clk: clk_disable_unprepare(pc->clk); diff --git a/drivers/pwm/pwm-zx.c b/drivers/pwm/pwm-zx.c deleted file mode 100644 index 34e91195ce98..000000000000 --- a/drivers/pwm/pwm-zx.c +++ /dev/null @@ -1,278 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2017 Sanechips Technology Co., Ltd. - * Copyright 2017 Linaro Ltd. - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#define ZX_PWM_MODE 0x0 -#define ZX_PWM_CLKDIV_SHIFT 2 -#define ZX_PWM_CLKDIV_MASK GENMASK(11, 2) -#define ZX_PWM_CLKDIV(x) (((x) << ZX_PWM_CLKDIV_SHIFT) & \ - ZX_PWM_CLKDIV_MASK) -#define ZX_PWM_POLAR BIT(1) -#define ZX_PWM_EN BIT(0) -#define ZX_PWM_PERIOD 0x4 -#define ZX_PWM_DUTY 0x8 - -#define ZX_PWM_CLKDIV_MAX 1023 -#define ZX_PWM_PERIOD_MAX 65535 - -struct zx_pwm_chip { - struct pwm_chip chip; - struct clk *pclk; - struct clk *wclk; - void __iomem *base; -}; - -static inline struct zx_pwm_chip *to_zx_pwm_chip(struct pwm_chip *chip) -{ - return container_of(chip, struct zx_pwm_chip, chip); -} - -static inline u32 zx_pwm_readl(struct zx_pwm_chip *zpc, unsigned int hwpwm, - unsigned int offset) -{ - return readl(zpc->base + (hwpwm + 1) * 0x10 + offset); -} - -static inline void zx_pwm_writel(struct zx_pwm_chip *zpc, unsigned int hwpwm, - unsigned int offset, u32 value) -{ - writel(value, zpc->base + (hwpwm + 1) * 0x10 + offset); -} - -static void zx_pwm_set_mask(struct zx_pwm_chip *zpc, unsigned int hwpwm, - unsigned int offset, u32 mask, u32 value) -{ - u32 data; - - data = zx_pwm_readl(zpc, hwpwm, offset); - data &= ~mask; - data |= value & mask; - zx_pwm_writel(zpc, hwpwm, offset, data); -} - -static void zx_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, - struct pwm_state *state) -{ - struct zx_pwm_chip *zpc = to_zx_pwm_chip(chip); - unsigned long rate; - unsigned int div; - u32 value; - u64 tmp; - - value = zx_pwm_readl(zpc, pwm->hwpwm, ZX_PWM_MODE); - - if (value & ZX_PWM_POLAR) - state->polarity = PWM_POLARITY_NORMAL; - else - state->polarity = PWM_POLARITY_INVERSED; - - if (value & ZX_PWM_EN) - state->enabled = true; - else - state->enabled = false; - - div = (value & ZX_PWM_CLKDIV_MASK) >> ZX_PWM_CLKDIV_SHIFT; - rate = clk_get_rate(zpc->wclk); - - tmp = zx_pwm_readl(zpc, pwm->hwpwm, ZX_PWM_PERIOD); - tmp *= div * NSEC_PER_SEC; - state->period = DIV_ROUND_CLOSEST_ULL(tmp, rate); - - tmp = zx_pwm_readl(zpc, pwm->hwpwm, ZX_PWM_DUTY); - tmp *= div * NSEC_PER_SEC; - state->duty_cycle = DIV_ROUND_CLOSEST_ULL(tmp, rate); -} - -static int zx_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, - unsigned int duty_ns, unsigned int period_ns) -{ - struct zx_pwm_chip *zpc = to_zx_pwm_chip(chip); - unsigned int period_cycles, duty_cycles; - unsigned long long c; - unsigned int div = 1; - unsigned long rate; - - /* Find out the best divider */ - rate = clk_get_rate(zpc->wclk); - - while (1) { - c = rate / div; - c = c * period_ns; - do_div(c, NSEC_PER_SEC); - - if (c < ZX_PWM_PERIOD_MAX) - break; - - div++; - - if (div > ZX_PWM_CLKDIV_MAX) - return -ERANGE; - } - - /* Calculate duty cycles */ - period_cycles = c; - c *= duty_ns; - do_div(c, period_ns); - duty_cycles = c; - - /* - * If the PWM is being enabled, we have to temporarily disable it - * before configuring the registers. - */ - if (pwm_is_enabled(pwm)) - zx_pwm_set_mask(zpc, pwm->hwpwm, ZX_PWM_MODE, ZX_PWM_EN, 0); - - /* Set up registers */ - zx_pwm_set_mask(zpc, pwm->hwpwm, ZX_PWM_MODE, ZX_PWM_CLKDIV_MASK, - ZX_PWM_CLKDIV(div)); - zx_pwm_writel(zpc, pwm->hwpwm, ZX_PWM_PERIOD, period_cycles); - zx_pwm_writel(zpc, pwm->hwpwm, ZX_PWM_DUTY, duty_cycles); - - /* Re-enable the PWM if needed */ - if (pwm_is_enabled(pwm)) - zx_pwm_set_mask(zpc, pwm->hwpwm, ZX_PWM_MODE, - ZX_PWM_EN, ZX_PWM_EN); - - return 0; -} - -static int zx_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, - const struct pwm_state *state) -{ - struct zx_pwm_chip *zpc = to_zx_pwm_chip(chip); - struct pwm_state cstate; - int ret; - - pwm_get_state(pwm, &cstate); - - if (state->polarity != cstate.polarity) - zx_pwm_set_mask(zpc, pwm->hwpwm, ZX_PWM_MODE, ZX_PWM_POLAR, - (state->polarity == PWM_POLARITY_INVERSED) ? - 0 : ZX_PWM_POLAR); - - if (state->period != cstate.period || - state->duty_cycle != cstate.duty_cycle) { - ret = zx_pwm_config(chip, pwm, state->duty_cycle, - state->period); - if (ret) - return ret; - } - - if (state->enabled != cstate.enabled) { - if (state->enabled) { - ret = clk_prepare_enable(zpc->wclk); - if (ret) - return ret; - - zx_pwm_set_mask(zpc, pwm->hwpwm, ZX_PWM_MODE, - ZX_PWM_EN, ZX_PWM_EN); - } else { - zx_pwm_set_mask(zpc, pwm->hwpwm, ZX_PWM_MODE, - ZX_PWM_EN, 0); - clk_disable_unprepare(zpc->wclk); - } - } - - return 0; -} - -static const struct pwm_ops zx_pwm_ops = { - .apply = zx_pwm_apply, - .get_state = zx_pwm_get_state, - .owner = THIS_MODULE, -}; - -static int zx_pwm_probe(struct platform_device *pdev) -{ - struct zx_pwm_chip *zpc; - unsigned int i; - int ret; - - zpc = devm_kzalloc(&pdev->dev, sizeof(*zpc), GFP_KERNEL); - if (!zpc) - return -ENOMEM; - - zpc->base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(zpc->base)) - return PTR_ERR(zpc->base); - - zpc->pclk = devm_clk_get(&pdev->dev, "pclk"); - if (IS_ERR(zpc->pclk)) - return PTR_ERR(zpc->pclk); - - zpc->wclk = devm_clk_get(&pdev->dev, "wclk"); - if (IS_ERR(zpc->wclk)) - return PTR_ERR(zpc->wclk); - - ret = clk_prepare_enable(zpc->pclk); - if (ret) - return ret; - - zpc->chip.dev = &pdev->dev; - zpc->chip.ops = &zx_pwm_ops; - zpc->chip.base = -1; - zpc->chip.npwm = 4; - zpc->chip.of_xlate = of_pwm_xlate_with_flags; - zpc->chip.of_pwm_n_cells = 3; - - /* - * PWM devices may be enabled by firmware, and let's disable all of - * them initially to save power. - */ - for (i = 0; i < zpc->chip.npwm; i++) - zx_pwm_set_mask(zpc, i, ZX_PWM_MODE, ZX_PWM_EN, 0); - - ret = pwmchip_add(&zpc->chip); - if (ret < 0) { - dev_err(&pdev->dev, "failed to add PWM chip: %d\n", ret); - clk_disable_unprepare(zpc->pclk); - return ret; - } - - platform_set_drvdata(pdev, zpc); - - return 0; -} - -static int zx_pwm_remove(struct platform_device *pdev) -{ - struct zx_pwm_chip *zpc = platform_get_drvdata(pdev); - int ret; - - ret = pwmchip_remove(&zpc->chip); - clk_disable_unprepare(zpc->pclk); - - return ret; -} - -static const struct of_device_id zx_pwm_dt_ids[] = { - { .compatible = "zte,zx296718-pwm", }, - { /* sentinel */ } -}; -MODULE_DEVICE_TABLE(of, zx_pwm_dt_ids); - -static struct platform_driver zx_pwm_driver = { - .driver = { - .name = "zx-pwm", - .of_match_table = zx_pwm_dt_ids, - }, - .probe = zx_pwm_probe, - .remove = zx_pwm_remove, -}; -module_platform_driver(zx_pwm_driver); - -MODULE_ALIAS("platform:zx-pwm"); -MODULE_AUTHOR("Shawn Guo "); -MODULE_DESCRIPTION("ZTE ZX PWM Driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig index 8ac5627564f0..4171c6f76385 100644 --- a/drivers/reset/Kconfig +++ b/drivers/reset/Kconfig @@ -89,6 +89,16 @@ config RESET_INTEL_GW Say Y to control the reset signals provided by reset controller. Otherwise, say N. +config RESET_K210 + bool "Reset controller driver for Canaan Kendryte K210 SoC" + depends on (SOC_CANAAN || COMPILE_TEST) && OF + select MFD_SYSCON + default SOC_CANAAN + help + Support for the Canaan Kendryte K210 RISC-V SoC reset controller. + Say Y if you want to control reset signals provided by this + controller. + config RESET_LANTIQ bool "Lantiq XWAY Reset Driver" if COMPILE_TEST default SOC_TYPE_XWAY diff --git a/drivers/reset/Makefile b/drivers/reset/Makefile index 1054123fd187..65a118a91b27 100644 --- a/drivers/reset/Makefile +++ b/drivers/reset/Makefile @@ -13,6 +13,7 @@ obj-$(CONFIG_RESET_BRCMSTB_RESCAL) += reset-brcmstb-rescal.o obj-$(CONFIG_RESET_HSDK) += reset-hsdk.o obj-$(CONFIG_RESET_IMX7) += reset-imx7.o obj-$(CONFIG_RESET_INTEL_GW) += reset-intel-gw.o +obj-$(CONFIG_RESET_K210) += reset-k210.o obj-$(CONFIG_RESET_LANTIQ) += reset-lantiq.o obj-$(CONFIG_RESET_LPC18XX) += reset-lpc18xx.o obj-$(CONFIG_RESET_MESON) += reset-meson.o diff --git a/drivers/reset/reset-k210.c b/drivers/reset/reset-k210.c new file mode 100644 index 000000000000..1b6e03522b40 --- /dev/null +++ b/drivers/reset/reset-k210.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define K210_RST_MASK 0x27FFFFFF + +struct k210_rst { + struct regmap *map; + struct reset_controller_dev rcdev; +}; + +static inline struct k210_rst * +to_k210_rst(struct reset_controller_dev *rcdev) +{ + return container_of(rcdev, struct k210_rst, rcdev); +} + +static inline int k210_rst_assert(struct reset_controller_dev *rcdev, + unsigned long id) +{ + struct k210_rst *ksr = to_k210_rst(rcdev); + + return regmap_update_bits(ksr->map, K210_SYSCTL_PERI_RESET, BIT(id), 1); +} + +static inline int k210_rst_deassert(struct reset_controller_dev *rcdev, + unsigned long id) +{ + struct k210_rst *ksr = to_k210_rst(rcdev); + + return regmap_update_bits(ksr->map, K210_SYSCTL_PERI_RESET, BIT(id), 0); +} + +static int k210_rst_reset(struct reset_controller_dev *rcdev, + unsigned long id) +{ + int ret; + + ret = k210_rst_assert(rcdev, id); + if (ret == 0) { + udelay(10); + ret = k210_rst_deassert(rcdev, id); + } + + return ret; +} + +static int k210_rst_status(struct reset_controller_dev *rcdev, + unsigned long id) +{ + struct k210_rst *ksr = to_k210_rst(rcdev); + u32 reg, bit = BIT(id); + int ret; + + ret = regmap_read(ksr->map, K210_SYSCTL_PERI_RESET, ®); + if (ret) + return ret; + + return reg & bit; +} + +static int k210_rst_xlate(struct reset_controller_dev *rcdev, + const struct of_phandle_args *reset_spec) +{ + unsigned long id = reset_spec->args[0]; + + if (!(BIT(id) & K210_RST_MASK)) + return -EINVAL; + + return id; +} + +static const struct reset_control_ops k210_rst_ops = { + .assert = k210_rst_assert, + .deassert = k210_rst_deassert, + .reset = k210_rst_reset, + .status = k210_rst_status, +}; + +static int k210_rst_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *parent_np = of_get_parent(dev->of_node); + struct k210_rst *ksr; + + dev_info(dev, "K210 reset controller\n"); + + ksr = devm_kzalloc(dev, sizeof(*ksr), GFP_KERNEL); + if (!ksr) + return -ENOMEM; + + ksr->map = syscon_node_to_regmap(parent_np); + of_node_put(parent_np); + if (IS_ERR(ksr->map)) + return PTR_ERR(ksr->map); + + ksr->rcdev.owner = THIS_MODULE; + ksr->rcdev.dev = dev; + ksr->rcdev.of_node = dev->of_node; + ksr->rcdev.ops = &k210_rst_ops; + ksr->rcdev.nr_resets = fls(K210_RST_MASK); + ksr->rcdev.of_reset_n_cells = 1; + ksr->rcdev.of_xlate = k210_rst_xlate; + + return devm_reset_controller_register(dev, &ksr->rcdev); +} + +static const struct of_device_id k210_rst_dt_ids[] = { + { .compatible = "canaan,k210-rst" }, + { /* sentinel */ }, +}; + +static struct platform_driver k210_rst_driver = { + .probe = k210_rst_probe, + .driver = { + .name = "k210-rst", + .of_match_table = k210_rst_dt_ids, + }, +}; +builtin_platform_driver(k210_rst_driver); diff --git a/drivers/soc/Kconfig b/drivers/soc/Kconfig index f357c6c659d2..e8a30c4c5aec 100644 --- a/drivers/soc/Kconfig +++ b/drivers/soc/Kconfig @@ -6,6 +6,7 @@ source "drivers/soc/amlogic/Kconfig" source "drivers/soc/aspeed/Kconfig" source "drivers/soc/atmel/Kconfig" source "drivers/soc/bcm/Kconfig" +source "drivers/soc/canaan/Kconfig" source "drivers/soc/fsl/Kconfig" source "drivers/soc/imx/Kconfig" source "drivers/soc/ixp4xx/Kconfig" @@ -22,6 +23,5 @@ source "drivers/soc/ti/Kconfig" source "drivers/soc/ux500/Kconfig" source "drivers/soc/versatile/Kconfig" source "drivers/soc/xilinx/Kconfig" -source "drivers/soc/kendryte/Kconfig" endmenu diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile index 9bceb12b291d..f678e4d9e585 100644 --- a/drivers/soc/Makefile +++ b/drivers/soc/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_ARCH_ACTIONS) += actions/ obj-y += aspeed/ obj-$(CONFIG_ARCH_AT91) += atmel/ obj-y += bcm/ +obj-$(CONFIG_SOC_CANAAN) += canaan/ obj-$(CONFIG_ARCH_DOVE) += dove/ obj-$(CONFIG_MACH_DOVE) += dove/ obj-y += fsl/ @@ -28,4 +29,3 @@ obj-y += ti/ obj-$(CONFIG_ARCH_U8500) += ux500/ obj-$(CONFIG_PLAT_VERSATILE) += versatile/ obj-y += xilinx/ -obj-$(CONFIG_SOC_KENDRYTE) += kendryte/ diff --git a/drivers/soc/canaan/Kconfig b/drivers/soc/canaan/Kconfig new file mode 100644 index 000000000000..8179b69518b4 --- /dev/null +++ b/drivers/soc/canaan/Kconfig @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 + +config SOC_K210_SYSCTL + bool "Canaan Kendryte K210 SoC system controller" + depends on RISCV && SOC_CANAAN && OF + default SOC_CANAAN + select PM + select SIMPLE_PM_BUS + select SYSCON + select MFD_SYSCON + help + Canaan Kendryte K210 SoC system controller driver. diff --git a/drivers/soc/canaan/Makefile b/drivers/soc/canaan/Makefile new file mode 100644 index 000000000000..570280ad7967 --- /dev/null +++ b/drivers/soc/canaan/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_SOC_K210_SYSCTL) += k210-sysctl.o diff --git a/drivers/soc/canaan/k210-sysctl.c b/drivers/soc/canaan/k210-sysctl.c new file mode 100644 index 000000000000..27a346c406bc --- /dev/null +++ b/drivers/soc/canaan/k210-sysctl.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2019 Christoph Hellwig. + * Copyright (c) 2019 Western Digital Corporation or its affiliates. + */ +#include +#include +#include +#include +#include + +#include + +static int k210_sysctl_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct clk *pclk; + int ret; + + dev_info(dev, "K210 system controller\n"); + + /* Get power bus clock */ + pclk = devm_clk_get(dev, NULL); + if (IS_ERR(pclk)) + return dev_err_probe(dev, PTR_ERR(pclk), + "Get bus clock failed\n"); + + ret = clk_prepare_enable(pclk); + if (ret) { + dev_err(dev, "Enable bus clock failed\n"); + return ret; + } + + /* Populate children */ + ret = devm_of_platform_populate(dev); + if (ret) + dev_err(dev, "Populate platform failed %d\n", ret); + + return ret; +} + +static const struct of_device_id k210_sysctl_of_match[] = { + { .compatible = "canaan,k210-sysctl", }, + { /* sentinel */ }, +}; + +static struct platform_driver k210_sysctl_driver = { + .driver = { + .name = "k210-sysctl", + .of_match_table = k210_sysctl_of_match, + }, + .probe = k210_sysctl_probe, +}; +builtin_platform_driver(k210_sysctl_driver); + +/* + * System controller registers base address and size. + */ +#define K210_SYSCTL_BASE_ADDR 0x50440000ULL +#define K210_SYSCTL_BASE_SIZE 0x1000 + +/* + * This needs to be called very early during initialization, given that + * PLL1 needs to be enabled to be able to use all SRAM. + */ +static void __init k210_soc_early_init(const void *fdt) +{ + void __iomem *sysctl_base; + + sysctl_base = ioremap(K210_SYSCTL_BASE_ADDR, K210_SYSCTL_BASE_SIZE); + if (!sysctl_base) + panic("k210-sysctl: ioremap failed"); + + k210_clk_early_init(sysctl_base); + + iounmap(sysctl_base); +} +SOC_EARLY_INIT_DECLARE(k210_soc, "canaan,kendryte-k210", k210_soc_early_init); diff --git a/drivers/soc/kendryte/Kconfig b/drivers/soc/kendryte/Kconfig deleted file mode 100644 index 49785b1b0217..000000000000 --- a/drivers/soc/kendryte/Kconfig +++ /dev/null @@ -1,14 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -if SOC_KENDRYTE - -config K210_SYSCTL - bool "Kendryte K210 system controller" - default y - depends on RISCV - help - Enables controlling the K210 various clocks and to enable - general purpose use of the extra 2MB of SRAM normally - reserved for the AI engine. - -endif diff --git a/drivers/soc/kendryte/Makefile b/drivers/soc/kendryte/Makefile deleted file mode 100644 index 002d9ce95c0d..000000000000 --- a/drivers/soc/kendryte/Makefile +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -obj-$(CONFIG_K210_SYSCTL) += k210-sysctl.o diff --git a/drivers/soc/kendryte/k210-sysctl.c b/drivers/soc/kendryte/k210-sysctl.c deleted file mode 100644 index 707019223dd8..000000000000 --- a/drivers/soc/kendryte/k210-sysctl.c +++ /dev/null @@ -1,260 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (c) 2019 Christoph Hellwig. - * Copyright (c) 2019 Western Digital Corporation or its affiliates. - */ -#include -#include -#include -#include -#include -#include -#include -#include - -#define K210_SYSCTL_CLK0_FREQ 26000000UL - -/* Registers base address */ -#define K210_SYSCTL_SYSCTL_BASE_ADDR 0x50440000ULL - -/* Registers */ -#define K210_SYSCTL_PLL0 0x08 -#define K210_SYSCTL_PLL1 0x0c -/* clkr: 4bits, clkf1: 6bits, clkod: 4bits, bwadj: 4bits */ -#define PLL_RESET (1 << 20) -#define PLL_PWR (1 << 21) -#define PLL_INTFB (1 << 22) -#define PLL_BYPASS (1 << 23) -#define PLL_TEST (1 << 24) -#define PLL_OUT_EN (1 << 25) -#define PLL_TEST_EN (1 << 26) -#define K210_SYSCTL_PLL_LOCK 0x18 -#define PLL0_LOCK1 (1 << 0) -#define PLL0_LOCK2 (1 << 1) -#define PLL0_SLIP_CLEAR (1 << 2) -#define PLL0_TEST_CLK_OUT (1 << 3) -#define PLL1_LOCK1 (1 << 8) -#define PLL1_LOCK2 (1 << 9) -#define PLL1_SLIP_CLEAR (1 << 10) -#define PLL1_TEST_CLK_OUT (1 << 11) -#define PLL2_LOCK1 (1 << 16) -#define PLL2_LOCK2 (1 << 16) -#define PLL2_SLIP_CLEAR (1 << 18) -#define PLL2_TEST_CLK_OUT (1 << 19) -#define K210_SYSCTL_CLKSEL0 0x20 -#define CLKSEL_ACLK (1 << 0) -#define K210_SYSCTL_CLKEN_CENT 0x28 -#define CLKEN_CPU (1 << 0) -#define CLKEN_SRAM0 (1 << 1) -#define CLKEN_SRAM1 (1 << 2) -#define CLKEN_APB0 (1 << 3) -#define CLKEN_APB1 (1 << 4) -#define CLKEN_APB2 (1 << 5) -#define K210_SYSCTL_CLKEN_PERI 0x2c -#define CLKEN_ROM (1 << 0) -#define CLKEN_DMA (1 << 1) -#define CLKEN_AI (1 << 2) -#define CLKEN_DVP (1 << 3) -#define CLKEN_FFT (1 << 4) -#define CLKEN_GPIO (1 << 5) -#define CLKEN_SPI0 (1 << 6) -#define CLKEN_SPI1 (1 << 7) -#define CLKEN_SPI2 (1 << 8) -#define CLKEN_SPI3 (1 << 9) -#define CLKEN_I2S0 (1 << 10) -#define CLKEN_I2S1 (1 << 11) -#define CLKEN_I2S2 (1 << 12) -#define CLKEN_I2C0 (1 << 13) -#define CLKEN_I2C1 (1 << 14) -#define CLKEN_I2C2 (1 << 15) -#define CLKEN_UART1 (1 << 16) -#define CLKEN_UART2 (1 << 17) -#define CLKEN_UART3 (1 << 18) -#define CLKEN_AES (1 << 19) -#define CLKEN_FPIO (1 << 20) -#define CLKEN_TIMER0 (1 << 21) -#define CLKEN_TIMER1 (1 << 22) -#define CLKEN_TIMER2 (1 << 23) -#define CLKEN_WDT0 (1 << 24) -#define CLKEN_WDT1 (1 << 25) -#define CLKEN_SHA (1 << 26) -#define CLKEN_OTP (1 << 27) -#define CLKEN_RTC (1 << 29) - -struct k210_sysctl { - void __iomem *regs; - struct clk_hw hw; -}; - -static void k210_set_bits(u32 val, void __iomem *reg) -{ - writel(readl(reg) | val, reg); -} - -static void k210_clear_bits(u32 val, void __iomem *reg) -{ - writel(readl(reg) & ~val, reg); -} - -static void k210_pll1_enable(void __iomem *regs) -{ - u32 val; - - val = readl(regs + K210_SYSCTL_PLL1); - val &= ~GENMASK(19, 0); /* clkr1 = 0 */ - val |= FIELD_PREP(GENMASK(9, 4), 0x3B); /* clkf1 = 59 */ - val |= FIELD_PREP(GENMASK(13, 10), 0x3); /* clkod1 = 3 */ - val |= FIELD_PREP(GENMASK(19, 14), 0x3B); /* bwadj1 = 59 */ - writel(val, regs + K210_SYSCTL_PLL1); - - k210_clear_bits(PLL_BYPASS, regs + K210_SYSCTL_PLL1); - k210_set_bits(PLL_PWR, regs + K210_SYSCTL_PLL1); - - /* - * Reset the pll. The magic NOPs come from the Kendryte reference SDK. - */ - k210_clear_bits(PLL_RESET, regs + K210_SYSCTL_PLL1); - k210_set_bits(PLL_RESET, regs + K210_SYSCTL_PLL1); - nop(); - nop(); - k210_clear_bits(PLL_RESET, regs + K210_SYSCTL_PLL1); - - for (;;) { - val = readl(regs + K210_SYSCTL_PLL_LOCK); - if (val & PLL1_LOCK2) - break; - writel(val | PLL1_SLIP_CLEAR, regs + K210_SYSCTL_PLL_LOCK); - } - - k210_set_bits(PLL_OUT_EN, regs + K210_SYSCTL_PLL1); -} - -static unsigned long k210_sysctl_clk_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct k210_sysctl *s = container_of(hw, struct k210_sysctl, hw); - u32 clksel0, pll0; - u64 pll0_freq, clkr0, clkf0, clkod0; - - /* - * If the clock selector is not set, use the base frequency. - * Otherwise, use PLL0 frequency with a frequency divisor. - */ - clksel0 = readl(s->regs + K210_SYSCTL_CLKSEL0); - if (!(clksel0 & CLKSEL_ACLK)) - return K210_SYSCTL_CLK0_FREQ; - - /* - * Get PLL0 frequency: - * freq = base frequency * clkf0 / (clkr0 * clkod0) - */ - pll0 = readl(s->regs + K210_SYSCTL_PLL0); - clkr0 = 1 + FIELD_GET(GENMASK(3, 0), pll0); - clkf0 = 1 + FIELD_GET(GENMASK(9, 4), pll0); - clkod0 = 1 + FIELD_GET(GENMASK(13, 10), pll0); - pll0_freq = clkf0 * K210_SYSCTL_CLK0_FREQ / (clkr0 * clkod0); - - /* Get the frequency divisor from the clock selector */ - return pll0_freq / (2ULL << FIELD_GET(0x00000006, clksel0)); -} - -static const struct clk_ops k210_sysctl_clk_ops = { - .recalc_rate = k210_sysctl_clk_recalc_rate, -}; - -static const struct clk_init_data k210_clk_init_data = { - .name = "k210-sysctl-pll1", - .ops = &k210_sysctl_clk_ops, -}; - -static int k210_sysctl_probe(struct platform_device *pdev) -{ - struct k210_sysctl *s; - int error; - - pr_info("Kendryte K210 SoC sysctl\n"); - - s = devm_kzalloc(&pdev->dev, sizeof(*s), GFP_KERNEL); - if (!s) - return -ENOMEM; - - s->regs = devm_ioremap_resource(&pdev->dev, - platform_get_resource(pdev, IORESOURCE_MEM, 0)); - if (IS_ERR(s->regs)) - return PTR_ERR(s->regs); - - s->hw.init = &k210_clk_init_data; - error = devm_clk_hw_register(&pdev->dev, &s->hw); - if (error) { - dev_err(&pdev->dev, "failed to register clk"); - return error; - } - - error = devm_of_clk_add_hw_provider(&pdev->dev, of_clk_hw_simple_get, - &s->hw); - if (error) { - dev_err(&pdev->dev, "adding clk provider failed\n"); - return error; - } - - return 0; -} - -static const struct of_device_id k210_sysctl_of_match[] = { - { .compatible = "kendryte,k210-sysctl", }, - {} -}; - -static struct platform_driver k210_sysctl_driver = { - .driver = { - .name = "k210-sysctl", - .of_match_table = k210_sysctl_of_match, - }, - .probe = k210_sysctl_probe, -}; - -static int __init k210_sysctl_init(void) -{ - return platform_driver_register(&k210_sysctl_driver); -} -core_initcall(k210_sysctl_init); - -/* - * This needs to be called very early during initialization, given that - * PLL1 needs to be enabled to be able to use all SRAM. - */ -static void __init k210_soc_early_init(const void *fdt) -{ - void __iomem *regs; - - regs = ioremap(K210_SYSCTL_SYSCTL_BASE_ADDR, 0x1000); - if (!regs) - panic("K210 sysctl ioremap"); - - /* Enable PLL1 to make the KPU SRAM useable */ - k210_pll1_enable(regs); - - k210_set_bits(PLL_OUT_EN, regs + K210_SYSCTL_PLL0); - - k210_set_bits(CLKEN_CPU | CLKEN_SRAM0 | CLKEN_SRAM1, - regs + K210_SYSCTL_CLKEN_CENT); - k210_set_bits(CLKEN_ROM | CLKEN_TIMER0 | CLKEN_RTC, - regs + K210_SYSCTL_CLKEN_PERI); - - k210_set_bits(CLKSEL_ACLK, regs + K210_SYSCTL_CLKSEL0); - - iounmap(regs); -} -SOC_EARLY_INIT_DECLARE(generic_k210, "kendryte,k210", k210_soc_early_init); - -#ifdef CONFIG_SOC_KENDRYTE_K210_DTB_BUILTIN -/* - * Generic entry for the default k210.dtb embedded DTB for boards with: - * - Vendor ID: 0x4B5 - * - Arch ID: 0xE59889E6A5A04149 (= "Canaan AI" in UTF-8 encoded Chinese) - * - Impl ID: 0x4D41495832303030 (= "MAIX2000") - * These values are reported by the SiPEED MAXDUINO, SiPEED MAIX GO and - * SiPEED Dan dock boards. - */ -SOC_BUILTIN_DTB_DECLARE(k210, 0x4B5, 0xE59889E6A5A04149, 0x4D41495832303030); -#endif diff --git a/drivers/soc/sifive/sifive_l2_cache.c b/drivers/soc/sifive/sifive_l2_cache.c index 44d7e1951da3..59640a1d0b28 100644 --- a/drivers/soc/sifive/sifive_l2_cache.c +++ b/drivers/soc/sifive/sifive_l2_cache.c @@ -17,6 +17,10 @@ #define SIFIVE_L2_DIRECCFIX_HIGH 0x104 #define SIFIVE_L2_DIRECCFIX_COUNT 0x108 +#define SIFIVE_L2_DIRECCFAIL_LOW 0x120 +#define SIFIVE_L2_DIRECCFAIL_HIGH 0x124 +#define SIFIVE_L2_DIRECCFAIL_COUNT 0x128 + #define SIFIVE_L2_DATECCFIX_LOW 0x140 #define SIFIVE_L2_DATECCFIX_HIGH 0x144 #define SIFIVE_L2_DATECCFIX_COUNT 0x148 @@ -29,7 +33,7 @@ #define SIFIVE_L2_WAYENABLE 0x08 #define SIFIVE_L2_ECCINJECTERR 0x40 -#define SIFIVE_L2_MAX_ECCINTR 3 +#define SIFIVE_L2_MAX_ECCINTR 4 static void __iomem *l2_base; static int g_irq[SIFIVE_L2_MAX_ECCINTR]; @@ -39,6 +43,7 @@ enum { DIR_CORR = 0, DATA_CORR, DATA_UNCORR, + DIR_UNCORR, }; #ifdef CONFIG_DEBUG_FS @@ -93,6 +98,7 @@ static void l2_config_read(void) static const struct of_device_id sifive_l2_ids[] = { { .compatible = "sifive,fu540-c000-ccache" }, + { .compatible = "sifive,fu740-c000-ccache" }, { /* end of table */ }, }; @@ -155,6 +161,15 @@ static irqreturn_t l2_int_handler(int irq, void *device) atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_CE, "DirECCFix"); } + if (irq == g_irq[DIR_UNCORR]) { + add_h = readl(l2_base + SIFIVE_L2_DIRECCFAIL_HIGH); + add_l = readl(l2_base + SIFIVE_L2_DIRECCFAIL_LOW); + /* Reading this register clears the DirFail interrupt sig */ + readl(l2_base + SIFIVE_L2_DIRECCFAIL_COUNT); + atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_UE, + "DirECCFail"); + panic("L2CACHE: DirFail @ 0x%08X.%08X\n", add_h, add_l); + } if (irq == g_irq[DATA_CORR]) { add_h = readl(l2_base + SIFIVE_L2_DATECCFIX_HIGH); add_l = readl(l2_base + SIFIVE_L2_DATECCFIX_LOW); @@ -181,7 +196,7 @@ static int __init sifive_l2_init(void) { struct device_node *np; struct resource res; - int i, rc; + int i, rc, intr_num; np = of_find_matching_node(NULL, sifive_l2_ids); if (!np) @@ -194,7 +209,13 @@ static int __init sifive_l2_init(void) if (!l2_base) return -ENOMEM; - for (i = 0; i < SIFIVE_L2_MAX_ECCINTR; i++) { + intr_num = of_property_count_u32_elems(np, "interrupts"); + if (!intr_num) { + pr_err("L2CACHE: no interrupts property\n"); + return -ENODEV; + } + + for (i = 0; i < intr_num; i++) { g_irq[i] = irq_of_parse_and_map(np, i); rc = request_irq(g_irq[i], l2_int_handler, 0, "l2_ecc", NULL); if (rc) { diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index ad5a0f405a75..3f0381344221 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -111,8 +111,8 @@ DECLARE_WAIT_QUEUE_HEAD(usb_kill_urb_queue); */ /*-------------------------------------------------------------------------*/ -#define KERNEL_REL bin2bcd(((LINUX_VERSION_CODE >> 16) & 0x0ff)) -#define KERNEL_VER bin2bcd(((LINUX_VERSION_CODE >> 8) & 0x0ff)) +#define KERNEL_REL bin2bcd(LINUX_VERSION_MAJOR) +#define KERNEL_VER bin2bcd(LINUX_VERSION_PATCHLEVEL) /* usb 3.1 root hub device descriptor */ static const u8 usb31_rh_dev_descriptor[18] = { diff --git a/drivers/usb/gadget/udc/aspeed-vhub/hub.c b/drivers/usb/gadget/udc/aspeed-vhub/hub.c index bfd8e77788e2..5c7dea5e0ff1 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/hub.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/hub.c @@ -46,8 +46,8 @@ * - Make vid/did overridable * - make it look like usb1 if usb1 mode forced */ -#define KERNEL_REL bin2bcd(((LINUX_VERSION_CODE >> 16) & 0x0ff)) -#define KERNEL_VER bin2bcd(((LINUX_VERSION_CODE >> 8) & 0x0ff)) +#define KERNEL_REL bin2bcd(LINUX_VERSION_MAJOR) +#define KERNEL_VER bin2bcd(LINUX_VERSION_PATCHLEVEL) enum { AST_VHUB_STR_INDEX_MAX = 4, diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index 92a6396f8a73..ffd1e098bfd2 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only menuconfig VDPA tristate "vDPA drivers" + depends on NET help Enable this module to support vDPA device that uses a datapath which complies with virtio specifications with diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index fa1af301cf55..7c8bbfcf6c3e 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -432,7 +432,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, dev, &ifc_vdpa_ops, - IFCVF_MAX_QUEUE_PAIRS * 2); + IFCVF_MAX_QUEUE_PAIRS * 2, NULL); if (adapter == NULL) { IFCVF_ERR(pdev, "Failed to allocate vDPA structure"); return -ENOMEM; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index b5fe6d2ad22f..10e9b09932eb 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1820,7 +1820,7 @@ static void mlx5_vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); - if (offset + len < sizeof(struct virtio_net_config)) + if (offset + len <= sizeof(struct virtio_net_config)) memcpy(buf, (u8 *)&ndev->config + offset, len); } @@ -1982,7 +1982,7 @@ static int mlx5v_probe(struct auxiliary_device *adev, max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS); ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, - 2 * mlx5_vdpa_max_qps(max_vqs)); + 2 * mlx5_vdpa_max_qps(max_vqs), NULL); if (IS_ERR(ndev)) return PTR_ERR(ndev); diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index c0825650c055..da67f07e24fd 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -11,9 +11,17 @@ #include #include #include +#include +#include +#include +static LIST_HEAD(mdev_head); +/* A global mutex that protects vdpa management device and device level operations. */ +static DEFINE_MUTEX(vdpa_dev_mutex); static DEFINE_IDA(vdpa_index_ida); +static struct genl_family vdpa_nl_family; + static int vdpa_dev_probe(struct device *d) { struct vdpa_device *vdev = dev_to_vdpa(d); @@ -63,6 +71,7 @@ static void vdpa_release_dev(struct device *d) * @config: the bus operations that is supported by this device * @nvqs: number of virtqueues supported by this device * @size: size of the parent structure that contains private data + * @name: name of the vdpa device; optional. * * Driver should use vdpa_alloc_device() wrapper macro instead of * using this directly. @@ -72,8 +81,7 @@ static void vdpa_release_dev(struct device *d) */ struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, - int nvqs, - size_t size) + int nvqs, size_t size, const char *name) { struct vdpa_device *vdev; int err = -EINVAL; @@ -101,7 +109,10 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, vdev->features_valid = false; vdev->nvqs = nvqs; - err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index); + if (name) + err = dev_set_name(&vdev->dev, "%s", name); + else + err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index); if (err) goto err_name; @@ -118,6 +129,44 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, } EXPORT_SYMBOL_GPL(__vdpa_alloc_device); +static int vdpa_name_match(struct device *dev, const void *data) +{ + struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev); + + return (strcmp(dev_name(&vdev->dev), data) == 0); +} + +static int __vdpa_register_device(struct vdpa_device *vdev) +{ + struct device *dev; + + lockdep_assert_held(&vdpa_dev_mutex); + dev = bus_find_device(&vdpa_bus, NULL, dev_name(&vdev->dev), vdpa_name_match); + if (dev) { + put_device(dev); + return -EEXIST; + } + return device_add(&vdev->dev); +} + +/** + * _vdpa_register_device - register a vDPA device with vdpa lock held + * Caller must have a succeed call of vdpa_alloc_device() before. + * Caller must invoke this routine in the management device dev_add() + * callback after setting up valid mgmtdev for this vdpa device. + * @vdev: the vdpa device to be registered to vDPA bus + * + * Returns an error when fail to add device to vDPA bus + */ +int _vdpa_register_device(struct vdpa_device *vdev) +{ + if (!vdev->mdev) + return -EINVAL; + + return __vdpa_register_device(vdev); +} +EXPORT_SYMBOL_GPL(_vdpa_register_device); + /** * vdpa_register_device - register a vDPA device * Callers must have a succeed call of vdpa_alloc_device() before. @@ -127,17 +176,38 @@ EXPORT_SYMBOL_GPL(__vdpa_alloc_device); */ int vdpa_register_device(struct vdpa_device *vdev) { - return device_add(&vdev->dev); + int err; + + mutex_lock(&vdpa_dev_mutex); + err = __vdpa_register_device(vdev); + mutex_unlock(&vdpa_dev_mutex); + return err; } EXPORT_SYMBOL_GPL(vdpa_register_device); +/** + * _vdpa_unregister_device - unregister a vDPA device + * Caller must invoke this routine as part of management device dev_del() + * callback. + * @vdev: the vdpa device to be unregisted from vDPA bus + */ +void _vdpa_unregister_device(struct vdpa_device *vdev) +{ + lockdep_assert_held(&vdpa_dev_mutex); + WARN_ON(!vdev->mdev); + device_unregister(&vdev->dev); +} +EXPORT_SYMBOL_GPL(_vdpa_unregister_device); + /** * vdpa_unregister_device - unregister a vDPA device * @vdev: the vdpa device to be unregisted from vDPA bus */ void vdpa_unregister_device(struct vdpa_device *vdev) { + mutex_lock(&vdpa_dev_mutex); device_unregister(&vdev->dev); + mutex_unlock(&vdpa_dev_mutex); } EXPORT_SYMBOL_GPL(vdpa_unregister_device); @@ -167,13 +237,436 @@ void vdpa_unregister_driver(struct vdpa_driver *drv) } EXPORT_SYMBOL_GPL(vdpa_unregister_driver); +/** + * vdpa_mgmtdev_register - register a vdpa management device + * + * @mdev: Pointer to vdpa management device + * vdpa_mgmtdev_register() register a vdpa management device which supports + * vdpa device management. + */ +int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev) +{ + if (!mdev->device || !mdev->ops || !mdev->ops->dev_add || !mdev->ops->dev_del) + return -EINVAL; + + INIT_LIST_HEAD(&mdev->list); + mutex_lock(&vdpa_dev_mutex); + list_add_tail(&mdev->list, &mdev_head); + mutex_unlock(&vdpa_dev_mutex); + return 0; +} +EXPORT_SYMBOL_GPL(vdpa_mgmtdev_register); + +static int vdpa_match_remove(struct device *dev, void *data) +{ + struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev); + struct vdpa_mgmt_dev *mdev = vdev->mdev; + + if (mdev == data) + mdev->ops->dev_del(mdev, vdev); + return 0; +} + +void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev) +{ + mutex_lock(&vdpa_dev_mutex); + + list_del(&mdev->list); + + /* Filter out all the entries belong to this management device and delete it. */ + bus_for_each_dev(&vdpa_bus, NULL, mdev, vdpa_match_remove); + + mutex_unlock(&vdpa_dev_mutex); +} +EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister); + +static bool mgmtdev_handle_match(const struct vdpa_mgmt_dev *mdev, + const char *busname, const char *devname) +{ + /* Bus name is optional for simulated management device, so ignore the + * device with bus if bus attribute is provided. + */ + if ((busname && !mdev->device->bus) || (!busname && mdev->device->bus)) + return false; + + if (!busname && strcmp(dev_name(mdev->device), devname) == 0) + return true; + + if (busname && (strcmp(mdev->device->bus->name, busname) == 0) && + (strcmp(dev_name(mdev->device), devname) == 0)) + return true; + + return false; +} + +static struct vdpa_mgmt_dev *vdpa_mgmtdev_get_from_attr(struct nlattr **attrs) +{ + struct vdpa_mgmt_dev *mdev; + const char *busname = NULL; + const char *devname; + + if (!attrs[VDPA_ATTR_MGMTDEV_DEV_NAME]) + return ERR_PTR(-EINVAL); + devname = nla_data(attrs[VDPA_ATTR_MGMTDEV_DEV_NAME]); + if (attrs[VDPA_ATTR_MGMTDEV_BUS_NAME]) + busname = nla_data(attrs[VDPA_ATTR_MGMTDEV_BUS_NAME]); + + list_for_each_entry(mdev, &mdev_head, list) { + if (mgmtdev_handle_match(mdev, busname, devname)) + return mdev; + } + return ERR_PTR(-ENODEV); +} + +static int vdpa_nl_mgmtdev_handle_fill(struct sk_buff *msg, const struct vdpa_mgmt_dev *mdev) +{ + if (mdev->device->bus && + nla_put_string(msg, VDPA_ATTR_MGMTDEV_BUS_NAME, mdev->device->bus->name)) + return -EMSGSIZE; + if (nla_put_string(msg, VDPA_ATTR_MGMTDEV_DEV_NAME, dev_name(mdev->device))) + return -EMSGSIZE; + return 0; +} + +static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *msg, + u32 portid, u32 seq, int flags) +{ + u64 supported_classes = 0; + void *hdr; + int i = 0; + int err; + + hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, VDPA_CMD_MGMTDEV_NEW); + if (!hdr) + return -EMSGSIZE; + err = vdpa_nl_mgmtdev_handle_fill(msg, mdev); + if (err) + goto msg_err; + + while (mdev->id_table[i].device) { + supported_classes |= BIT(mdev->id_table[i].device); + i++; + } + + if (nla_put_u64_64bit(msg, VDPA_ATTR_MGMTDEV_SUPPORTED_CLASSES, + supported_classes, VDPA_ATTR_UNSPEC)) { + err = -EMSGSIZE; + goto msg_err; + } + + genlmsg_end(msg, hdr); + return 0; + +msg_err: + genlmsg_cancel(msg, hdr); + return err; +} + +static int vdpa_nl_cmd_mgmtdev_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_mgmt_dev *mdev; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&vdpa_dev_mutex); + mdev = vdpa_mgmtdev_get_from_attr(info->attrs); + if (IS_ERR(mdev)) { + mutex_unlock(&vdpa_dev_mutex); + NL_SET_ERR_MSG_MOD(info->extack, "Fail to find the specified mgmt device"); + err = PTR_ERR(mdev); + goto out; + } + + err = vdpa_mgmtdev_fill(mdev, msg, info->snd_portid, info->snd_seq, 0); + mutex_unlock(&vdpa_dev_mutex); + if (err) + goto out; + err = genlmsg_reply(msg, info); + return err; + +out: + nlmsg_free(msg); + return err; +} + +static int +vdpa_nl_cmd_mgmtdev_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct vdpa_mgmt_dev *mdev; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&vdpa_dev_mutex); + list_for_each_entry(mdev, &mdev_head, list) { + if (idx < start) { + idx++; + continue; + } + err = vdpa_mgmtdev_fill(mdev, msg, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); + if (err) + goto out; + idx++; + } +out: + mutex_unlock(&vdpa_dev_mutex); + cb->args[0] = idx; + return msg->len; +} + +static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_mgmt_dev *mdev; + const char *name; + int err = 0; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + + name = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + + mutex_lock(&vdpa_dev_mutex); + mdev = vdpa_mgmtdev_get_from_attr(info->attrs); + if (IS_ERR(mdev)) { + NL_SET_ERR_MSG_MOD(info->extack, "Fail to find the specified management device"); + err = PTR_ERR(mdev); + goto err; + } + + err = mdev->ops->dev_add(mdev, name); +err: + mutex_unlock(&vdpa_dev_mutex); + return err; +} + +static int vdpa_nl_cmd_dev_del_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_mgmt_dev *mdev; + struct vdpa_device *vdev; + struct device *dev; + const char *name; + int err = 0; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + name = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + + mutex_lock(&vdpa_dev_mutex); + dev = bus_find_device(&vdpa_bus, NULL, name, vdpa_name_match); + if (!dev) { + NL_SET_ERR_MSG_MOD(info->extack, "device not found"); + err = -ENODEV; + goto dev_err; + } + vdev = container_of(dev, struct vdpa_device, dev); + if (!vdev->mdev) { + NL_SET_ERR_MSG_MOD(info->extack, "Only user created device can be deleted by user"); + err = -EINVAL; + goto mdev_err; + } + mdev = vdev->mdev; + mdev->ops->dev_del(mdev, vdev); +mdev_err: + put_device(dev); +dev_err: + mutex_unlock(&vdpa_dev_mutex); + return err; +} + +static int +vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq, + int flags, struct netlink_ext_ack *extack) +{ + u16 max_vq_size; + u32 device_id; + u32 vendor_id; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, VDPA_CMD_DEV_NEW); + if (!hdr) + return -EMSGSIZE; + + err = vdpa_nl_mgmtdev_handle_fill(msg, vdev->mdev); + if (err) + goto msg_err; + + device_id = vdev->config->get_device_id(vdev); + vendor_id = vdev->config->get_vendor_id(vdev); + max_vq_size = vdev->config->get_vq_num_max(vdev); + + err = -EMSGSIZE; + if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) + goto msg_err; + if (nla_put_u32(msg, VDPA_ATTR_DEV_ID, device_id)) + goto msg_err; + if (nla_put_u32(msg, VDPA_ATTR_DEV_VENDOR_ID, vendor_id)) + goto msg_err; + if (nla_put_u32(msg, VDPA_ATTR_DEV_MAX_VQS, vdev->nvqs)) + goto msg_err; + if (nla_put_u16(msg, VDPA_ATTR_DEV_MAX_VQ_SIZE, max_vq_size)) + goto msg_err; + + genlmsg_end(msg, hdr); + return 0; + +msg_err: + genlmsg_cancel(msg, hdr); + return err; +} + +static int vdpa_nl_cmd_dev_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_device *vdev; + struct sk_buff *msg; + const char *devname; + struct device *dev; + int err; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + devname = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&vdpa_dev_mutex); + dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match); + if (!dev) { + NL_SET_ERR_MSG_MOD(info->extack, "device not found"); + err = -ENODEV; + goto err; + } + vdev = container_of(dev, struct vdpa_device, dev); + if (!vdev->mdev) { + err = -EINVAL; + goto mdev_err; + } + err = vdpa_dev_fill(vdev, msg, info->snd_portid, info->snd_seq, 0, info->extack); + if (!err) + err = genlmsg_reply(msg, info); +mdev_err: + put_device(dev); +err: + mutex_unlock(&vdpa_dev_mutex); + if (err) + nlmsg_free(msg); + return err; +} + +struct vdpa_dev_dump_info { + struct sk_buff *msg; + struct netlink_callback *cb; + int start_idx; + int idx; +}; + +static int vdpa_dev_dump(struct device *dev, void *data) +{ + struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev); + struct vdpa_dev_dump_info *info = data; + int err; + + if (!vdev->mdev) + return 0; + if (info->idx < info->start_idx) { + info->idx++; + return 0; + } + err = vdpa_dev_fill(vdev, info->msg, NETLINK_CB(info->cb->skb).portid, + info->cb->nlh->nlmsg_seq, NLM_F_MULTI, info->cb->extack); + if (err) + return err; + + info->idx++; + return 0; +} + +static int vdpa_nl_cmd_dev_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct vdpa_dev_dump_info info; + + info.msg = msg; + info.cb = cb; + info.start_idx = cb->args[0]; + info.idx = 0; + + mutex_lock(&vdpa_dev_mutex); + bus_for_each_dev(&vdpa_bus, NULL, &info, vdpa_dev_dump); + mutex_unlock(&vdpa_dev_mutex); + cb->args[0] = info.idx; + return msg->len; +} + +static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { + [VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING }, + [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, + [VDPA_ATTR_DEV_NAME] = { .type = NLA_STRING }, +}; + +static const struct genl_ops vdpa_nl_ops[] = { + { + .cmd = VDPA_CMD_MGMTDEV_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_mgmtdev_get_doit, + .dumpit = vdpa_nl_cmd_mgmtdev_get_dumpit, + }, + { + .cmd = VDPA_CMD_DEV_NEW, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_add_set_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = VDPA_CMD_DEV_DEL, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_del_set_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = VDPA_CMD_DEV_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_get_doit, + .dumpit = vdpa_nl_cmd_dev_get_dumpit, + }, +}; + +static struct genl_family vdpa_nl_family __ro_after_init = { + .name = VDPA_GENL_NAME, + .version = VDPA_GENL_VERSION, + .maxattr = VDPA_ATTR_MAX, + .policy = vdpa_nl_policy, + .netnsok = false, + .module = THIS_MODULE, + .ops = vdpa_nl_ops, + .n_ops = ARRAY_SIZE(vdpa_nl_ops), +}; + static int vdpa_init(void) { - return bus_register(&vdpa_bus); + int err; + + err = bus_register(&vdpa_bus); + if (err) + return err; + err = genl_register_family(&vdpa_nl_family); + if (err) + goto err; + return 0; + +err: + bus_unregister(&vdpa_bus); + return err; } static void __exit vdpa_exit(void) { + genl_unregister_family(&vdpa_nl_family); bus_unregister(&vdpa_bus); ida_destroy(&vdpa_index_ida); } diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index b3fcc67bfdf0..d5942842432d 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -235,7 +235,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr) ops = &vdpasim_config_ops; vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, - dev_attr->nvqs); + dev_attr->nvqs, dev_attr->name); if (!vdpasim) goto err_alloc; @@ -249,6 +249,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr) if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))) goto err_iommu; set_dma_ops(dev, &vdpasim_dma_ops); + vdpasim->vdpa.mdev = dev_attr->mgmt_dev; vdpasim->config = kzalloc(dev_attr->config_size, GFP_KERNEL); if (!vdpasim->config) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h index b02142293d5b..6d75444f9948 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.h +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h @@ -33,6 +33,8 @@ struct vdpasim_virtqueue { }; struct vdpasim_dev_attr { + struct vdpa_mgmt_dev *mgmt_dev; + const char *name; u64 supported_features; size_t config_size; size_t buffer_size; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index c10b6981fdab..d344c5b7c914 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -33,9 +33,7 @@ static char *macaddr; module_param(macaddr, charp, 0); MODULE_PARM_DESC(macaddr, "Ethernet MAC address"); -u8 macaddr_buf[ETH_ALEN]; - -static struct vdpasim *vdpasim_net_dev; +static u8 macaddr_buf[ETH_ALEN]; static void vdpasim_net_work(struct work_struct *work) { @@ -120,21 +118,23 @@ static void vdpasim_net_get_config(struct vdpasim *vdpasim, void *config) memcpy(net_config->mac, macaddr_buf, ETH_ALEN); } -static int __init vdpasim_net_init(void) +static void vdpasim_net_mgmtdev_release(struct device *dev) +{ +} + +static struct device vdpasim_net_mgmtdev = { + .init_name = "vdpasim_net", + .release = vdpasim_net_mgmtdev_release, +}; + +static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name) { struct vdpasim_dev_attr dev_attr = {}; + struct vdpasim *simdev; int ret; - if (macaddr) { - mac_pton(macaddr, macaddr_buf); - if (!is_valid_ether_addr(macaddr_buf)) { - ret = -EADDRNOTAVAIL; - goto out; - } - } else { - eth_random_addr(macaddr_buf); - } - + dev_attr.mgmt_dev = mdev; + dev_attr.name = name; dev_attr.id = VIRTIO_ID_NET; dev_attr.supported_features = VDPASIM_NET_FEATURES; dev_attr.nvqs = VDPASIM_NET_VQ_NUM; @@ -143,29 +143,75 @@ static int __init vdpasim_net_init(void) dev_attr.work_fn = vdpasim_net_work; dev_attr.buffer_size = PAGE_SIZE; - vdpasim_net_dev = vdpasim_create(&dev_attr); - if (IS_ERR(vdpasim_net_dev)) { - ret = PTR_ERR(vdpasim_net_dev); - goto out; - } + simdev = vdpasim_create(&dev_attr); + if (IS_ERR(simdev)) + return PTR_ERR(simdev); - ret = vdpa_register_device(&vdpasim_net_dev->vdpa); + ret = _vdpa_register_device(&simdev->vdpa); if (ret) - goto put_dev; + goto reg_err; return 0; -put_dev: - put_device(&vdpasim_net_dev->vdpa.dev); -out: +reg_err: + put_device(&simdev->vdpa.dev); + return ret; +} + +static void vdpasim_net_dev_del(struct vdpa_mgmt_dev *mdev, + struct vdpa_device *dev) +{ + struct vdpasim *simdev = container_of(dev, struct vdpasim, vdpa); + + _vdpa_unregister_device(&simdev->vdpa); +} + +static const struct vdpa_mgmtdev_ops vdpasim_net_mgmtdev_ops = { + .dev_add = vdpasim_net_dev_add, + .dev_del = vdpasim_net_dev_del +}; + +static struct virtio_device_id id_table[] = { + { VIRTIO_ID_NET, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; + +static struct vdpa_mgmt_dev mgmt_dev = { + .device = &vdpasim_net_mgmtdev, + .id_table = id_table, + .ops = &vdpasim_net_mgmtdev_ops, +}; + +static int __init vdpasim_net_init(void) +{ + int ret; + + if (macaddr) { + mac_pton(macaddr, macaddr_buf); + if (!is_valid_ether_addr(macaddr_buf)) + return -EADDRNOTAVAIL; + } else { + eth_random_addr(macaddr_buf); + } + + ret = device_register(&vdpasim_net_mgmtdev); + if (ret) + return ret; + + ret = vdpa_mgmtdev_register(&mgmt_dev); + if (ret) + goto parent_err; + return 0; + +parent_err: + device_unregister(&vdpasim_net_mgmtdev); return ret; } static void __exit vdpasim_net_exit(void) { - struct vdpa_device *vdpa = &vdpasim_net_dev->vdpa; - - vdpa_unregister_device(vdpa); + vdpa_mgmtdev_unregister(&mgmt_dev); + device_unregister(&vdpasim_net_mgmtdev); } module_init(vdpasim_net_init); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 4ce9f00ae10e..5de21ad4bd05 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1814,12 +1814,9 @@ static int vhost_scsi_open(struct inode *inode, struct file *f) struct vhost_virtqueue **vqs; int r = -ENOMEM, i; - vs = kzalloc(sizeof(*vs), GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL); - if (!vs) { - vs = vzalloc(sizeof(*vs)); - if (!vs) - goto err_vs; - } + vs = kvzalloc(sizeof(*vs), GFP_KERNEL); + if (!vs) + goto err_vs; vqs = kmalloc_array(VHOST_SCSI_MAX_VQ, sizeof(*vqs), GFP_KERNEL); if (!vqs) diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index 83c8e809955a..e946903a86c2 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -175,6 +175,15 @@ u32 aty_ld_lcd(int index, const struct atyfb_par *par) return aty_ld_le32(LCD_DATA, par); } } +#else /* defined(CONFIG_PMAC_BACKLIGHT) || defined(CONFIG_FB_ATY_BACKLIGHT) \ + defined(CONFIG_FB_ATY_GENERIC_LCD) */ +void aty_st_lcd(int index, u32 val, const struct atyfb_par *par) +{ } + +u32 aty_ld_lcd(int index, const struct atyfb_par *par) +{ + return 0; +} #endif /* defined(CONFIG_PMAC_BACKLIGHT) || defined (CONFIG_FB_ATY_GENERIC_LCD) */ #ifdef CONFIG_FB_ATY_GENERIC_LCD diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 3ef55447d160..d9b8c06392ee 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -12,6 +12,14 @@ config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS This option is selected if the architecture may need to enforce VIRTIO_F_ACCESS_PLATFORM +config VIRTIO_PCI_LIB + tristate + help + Modern PCI device implementation. This module implements the + basic probe and control for devices which are based on modern + PCI device with possible vendor specific extensions. Any + module that selects this module must depend on PCI. + menuconfig VIRTIO_MENU bool "Virtio drivers" default y @@ -21,6 +29,7 @@ if VIRTIO_MENU config VIRTIO_PCI tristate "PCI driver for virtio devices" depends on PCI + select VIRTIO_PCI_LIB select VIRTIO help This driver provides support for virtio based paravirtual device diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile index 591e6f72aa54..699bbea0465f 100644 --- a/drivers/virtio/Makefile +++ b/drivers/virtio/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o +obj-$(CONFIG_VIRTIO_PCI_LIB) += virtio_pci_modern_dev.o obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c index 427d58c771cb..2e51018a467b 100644 --- a/drivers/virtio/virtio_input.c +++ b/drivers/virtio/virtio_input.c @@ -8,6 +8,7 @@ #include #include +#include struct virtio_input { struct virtio_device *vdev; @@ -65,6 +66,21 @@ static int virtinput_send_status(struct virtio_input *vi, unsigned long flags; int rc; + /* + * Since 29cc309d8bf1 (HID: hid-multitouch: forward MSC_TIMESTAMP), + * EV_MSC/MSC_TIMESTAMP is added to each before EV_SYN event. + * EV_MSC is configured as INPUT_PASS_TO_ALL. + * In case of touch device: + * BE pass EV_MSC/MSC_TIMESTAMP to FE on receiving event from evdev. + * FE pass EV_MSC/MSC_TIMESTAMP back to BE. + * BE writes EV_MSC/MSC_TIMESTAMP to evdev due to INPUT_PASS_TO_ALL. + * BE receives extra EV_MSC/MSC_TIMESTAMP and pass to FE. + * >>> Each new frame becomes larger and larger. + * Disable EV_MSC/MSC_TIMESTAMP forwarding for MT. + */ + if (vi->idev->mt && type == EV_MSC && code == MSC_TIMESTAMP) + return 0; + stsbuf = kzalloc(sizeof(*stsbuf), GFP_ATOMIC); if (!stsbuf) return -ENOMEM; @@ -214,7 +230,7 @@ static int virtinput_probe(struct virtio_device *vdev) struct virtio_input *vi; unsigned long flags; size_t size; - int abs, err; + int abs, err, nslots; if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) return -ENODEV; @@ -299,6 +315,13 @@ static int virtinput_probe(struct virtio_device *vdev) continue; virtinput_cfg_abs(vi, abs); } + + if (test_bit(ABS_MT_SLOT, vi->idev->absbit)) { + nslots = input_abs_get_max(vi->idev, ABS_MT_SLOT) + 1; + err = input_mt_init_slots(vi->idev, nslots, 0); + if (err) + goto err_mt_init_slots; + } } virtio_device_ready(vdev); @@ -314,6 +337,7 @@ static int virtinput_probe(struct virtio_device *vdev) spin_lock_irqsave(&vi->lock, flags); vi->ready = false; spin_unlock_irqrestore(&vi->lock, flags); +err_mt_init_slots: input_free_device(vi->idev); err_input_alloc: vdev->config->del_vqs(vdev); diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 9fc9ec4a25f5..10ec60d81e84 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -623,7 +623,7 @@ static int virtio_mem_add_memory(struct virtio_mem *vm, uint64_t addr, /* Memory might get onlined immediately. */ atomic64_add(size, &vm->offline_size); rc = add_memory_driver_managed(vm->nid, addr, size, vm->resource_name, - MEMHP_MERGE_RESOURCE); + MHP_MERGE_RESOURCE); if (rc) { atomic64_sub(size, &vm->offline_size); dev_warn(&vm->vdev->dev, "adding memory failed: %d\n", rc); @@ -2222,7 +2222,7 @@ static int virtio_mem_unplug_pending_mb(struct virtio_mem *vm) */ static void virtio_mem_refresh_config(struct virtio_mem *vm) { - const uint64_t phys_limit = 1UL << MAX_PHYSMEM_BITS; + const struct range pluggable_range = mhp_get_pluggable_range(true); uint64_t new_plugged_size, usable_region_size, end_addr; /* the plugged_size is just a reflection of what _we_ did previously */ @@ -2234,15 +2234,25 @@ static void virtio_mem_refresh_config(struct virtio_mem *vm) /* calculate the last usable memory block id */ virtio_cread_le(vm->vdev, struct virtio_mem_config, usable_region_size, &usable_region_size); - end_addr = vm->addr + usable_region_size; - end_addr = min(end_addr, phys_limit); + end_addr = min(vm->addr + usable_region_size - 1, + pluggable_range.end); - if (vm->in_sbm) - vm->sbm.last_usable_mb_id = - virtio_mem_phys_to_mb_id(end_addr) - 1; - else - vm->bbm.last_usable_bb_id = - virtio_mem_phys_to_bb_id(vm, end_addr) - 1; + if (vm->in_sbm) { + vm->sbm.last_usable_mb_id = virtio_mem_phys_to_mb_id(end_addr); + if (!IS_ALIGNED(end_addr + 1, memory_block_size_bytes())) + vm->sbm.last_usable_mb_id--; + } else { + vm->bbm.last_usable_bb_id = virtio_mem_phys_to_bb_id(vm, + end_addr); + if (!IS_ALIGNED(end_addr + 1, vm->bbm.bb_size)) + vm->bbm.last_usable_bb_id--; + } + /* + * If we cannot plug any of our device memory (e.g., nothing in the + * usable region is addressable), the last usable memory block id will + * be smaller than the first usable memory block id. We'll stop + * attempting to add memory with -ENOSPC from our main loop. + */ /* see if there is a request to change the size */ virtio_cread_le(vm->vdev, struct virtio_mem_config, requested_size, @@ -2364,7 +2374,7 @@ static int virtio_mem_init_vq(struct virtio_mem *vm) static int virtio_mem_init(struct virtio_mem *vm) { - const uint64_t phys_limit = 1UL << MAX_PHYSMEM_BITS; + const struct range pluggable_range = mhp_get_pluggable_range(true); uint64_t sb_size, addr; uint16_t node_id; @@ -2405,9 +2415,10 @@ static int virtio_mem_init(struct virtio_mem *vm) if (!IS_ALIGNED(vm->addr + vm->region_size, memory_block_size_bytes())) dev_warn(&vm->vdev->dev, "The alignment of the physical end address can make some memory unusable.\n"); - if (vm->addr + vm->region_size > phys_limit) + if (vm->addr < pluggable_range.start || + vm->addr + vm->region_size - 1 > pluggable_range.end) dev_warn(&vm->vdev->dev, - "Some memory is not addressable. This can make some memory unusable.\n"); + "Some device memory is not addressable/pluggable. This can make some memory unusable.\n"); /* * We want subblocks to span at least MAX_ORDER_NR_PAGES and @@ -2429,7 +2440,8 @@ static int virtio_mem_init(struct virtio_mem *vm) vm->sbm.sb_size; /* Round up to the next full memory block */ - addr = vm->addr + memory_block_size_bytes() - 1; + addr = max_t(uint64_t, vm->addr, pluggable_range.start) + + memory_block_size_bytes() - 1; vm->sbm.first_mb_id = virtio_mem_phys_to_mb_id(addr); vm->sbm.next_mb_id = vm->sbm.first_mb_id; } else { @@ -2450,7 +2462,8 @@ static int virtio_mem_init(struct virtio_mem *vm) } /* Round up to the next aligned big block */ - addr = vm->addr + vm->bbm.bb_size - 1; + addr = max_t(uint64_t, vm->addr, pluggable_range.start) + + vm->bbm.bb_size - 1; vm->bbm.first_bb_id = virtio_mem_phys_to_bb_id(vm, addr); vm->bbm.next_bb_id = vm->bbm.first_bb_id; } @@ -2577,7 +2590,7 @@ static int virtio_mem_probe(struct virtio_device *vdev) * actually in use (e.g., trying to reload the driver). */ if (vm->plugged_size) { - vm->unplug_all_required = 1; + vm->unplug_all_required = true; dev_info(&vm->vdev->dev, "unplugging all memory is required\n"); } diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 238383ff1064..a286d22b6551 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -126,7 +126,7 @@ static int vm_finalize_features(struct virtio_device *vdev) /* Give virtio_ring a chance to accept features. */ vring_transport_features(vdev); - /* Make sure there is are no mixed devices */ + /* Make sure there are no mixed devices */ if (vm_dev->version == 2 && !__virtio_test_bit(vdev, VIRTIO_F_VERSION_1)) { dev_err(&vdev->dev, "New virtio-mmio devices (version 2) must provide VIRTIO_F_VERSION_1 feature!\n"); diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index b2f0eb4067cb..beec047a8f8d 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -43,31 +44,12 @@ struct virtio_pci_vq_info { struct virtio_pci_device { struct virtio_device vdev; struct pci_dev *pci_dev; + struct virtio_pci_modern_device mdev; /* In legacy mode, these two point to within ->legacy. */ /* Where to read and clear interrupt */ u8 __iomem *isr; - /* Modern only fields */ - /* The IO mapping for the PCI config space (non-legacy mode) */ - struct virtio_pci_common_cfg __iomem *common; - /* Device-specific data (non-legacy mode) */ - void __iomem *device; - /* Base of vq notifications (non-legacy mode). */ - void __iomem *notify_base; - - /* So we can sanity-check accesses. */ - size_t notify_len; - size_t device_len; - - /* Capability for when we need to map notifications per-vq. */ - int notify_map_cap; - - /* Multiply queue_notify_off by this value. (non-legacy mode). */ - u32 notify_offset_multiplier; - - int modern_bars; - /* Legacy only field */ /* the IO mapping for the PCI config space */ void __iomem *ioaddr; diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 3d6ae5a5e252..fbd4ebc00eb6 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -19,136 +19,11 @@ #define VIRTIO_RING_NO_LEGACY #include "virtio_pci_common.h" -/* - * Type-safe wrappers for io accesses. - * Use these to enforce at compile time the following spec requirement: - * - * The driver MUST access each field using the “natural” access - * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses - * for 16-bit fields and 8-bit accesses for 8-bit fields. - */ -static inline u8 vp_ioread8(const u8 __iomem *addr) -{ - return ioread8(addr); -} -static inline u16 vp_ioread16 (const __le16 __iomem *addr) -{ - return ioread16(addr); -} - -static inline u32 vp_ioread32(const __le32 __iomem *addr) -{ - return ioread32(addr); -} - -static inline void vp_iowrite8(u8 value, u8 __iomem *addr) -{ - iowrite8(value, addr); -} - -static inline void vp_iowrite16(u16 value, __le16 __iomem *addr) -{ - iowrite16(value, addr); -} - -static inline void vp_iowrite32(u32 value, __le32 __iomem *addr) -{ - iowrite32(value, addr); -} - -static void vp_iowrite64_twopart(u64 val, - __le32 __iomem *lo, __le32 __iomem *hi) -{ - vp_iowrite32((u32)val, lo); - vp_iowrite32(val >> 32, hi); -} - -static void __iomem *map_capability(struct pci_dev *dev, int off, - size_t minlen, - u32 align, - u32 start, u32 size, - size_t *len) -{ - u8 bar; - u32 offset, length; - void __iomem *p; - - pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap, - bar), - &bar); - pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset), - &offset); - pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length), - &length); - - if (length <= start) { - dev_err(&dev->dev, - "virtio_pci: bad capability len %u (>%u expected)\n", - length, start); - return NULL; - } - - if (length - start < minlen) { - dev_err(&dev->dev, - "virtio_pci: bad capability len %u (>=%zu expected)\n", - length, minlen); - return NULL; - } - - length -= start; - - if (start + offset < offset) { - dev_err(&dev->dev, - "virtio_pci: map wrap-around %u+%u\n", - start, offset); - return NULL; - } - - offset += start; - - if (offset & (align - 1)) { - dev_err(&dev->dev, - "virtio_pci: offset %u not aligned to %u\n", - offset, align); - return NULL; - } - - if (length > size) - length = size; - - if (len) - *len = length; - - if (minlen + offset < minlen || - minlen + offset > pci_resource_len(dev, bar)) { - dev_err(&dev->dev, - "virtio_pci: map virtio %zu@%u " - "out of range on bar %i length %lu\n", - minlen, offset, - bar, (unsigned long)pci_resource_len(dev, bar)); - return NULL; - } - - p = pci_iomap_range(dev, bar, offset, length); - if (!p) - dev_err(&dev->dev, - "virtio_pci: unable to map virtio %u@%u on bar %i\n", - length, offset, bar); - return p; -} - -/* virtio config->get_features() implementation */ static u64 vp_get_features(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - u64 features; - vp_iowrite32(0, &vp_dev->common->device_feature_select); - features = vp_ioread32(&vp_dev->common->device_feature); - vp_iowrite32(1, &vp_dev->common->device_feature_select); - features |= ((u64)vp_ioread32(&vp_dev->common->device_feature) << 32); - - return features; + return vp_modern_get_features(&vp_dev->mdev); } static void vp_transport_features(struct virtio_device *vdev, u64 features) @@ -179,10 +54,7 @@ static int vp_finalize_features(struct virtio_device *vdev) return -EINVAL; } - vp_iowrite32(0, &vp_dev->common->guest_feature_select); - vp_iowrite32((u32)vdev->features, &vp_dev->common->guest_feature); - vp_iowrite32(1, &vp_dev->common->guest_feature_select); - vp_iowrite32(vdev->features >> 32, &vp_dev->common->guest_feature); + vp_modern_set_features(&vp_dev->mdev, vdev->features); return 0; } @@ -192,29 +64,31 @@ static void vp_get(struct virtio_device *vdev, unsigned offset, void *buf, unsigned len) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_modern_device *mdev = &vp_dev->mdev; + void __iomem *device = mdev->device; u8 b; __le16 w; __le32 l; - BUG_ON(offset + len > vp_dev->device_len); + BUG_ON(offset + len > mdev->device_len); switch (len) { case 1: - b = ioread8(vp_dev->device + offset); + b = ioread8(device + offset); memcpy(buf, &b, sizeof b); break; case 2: - w = cpu_to_le16(ioread16(vp_dev->device + offset)); + w = cpu_to_le16(ioread16(device + offset)); memcpy(buf, &w, sizeof w); break; case 4: - l = cpu_to_le32(ioread32(vp_dev->device + offset)); + l = cpu_to_le32(ioread32(device + offset)); memcpy(buf, &l, sizeof l); break; case 8: - l = cpu_to_le32(ioread32(vp_dev->device + offset)); + l = cpu_to_le32(ioread32(device + offset)); memcpy(buf, &l, sizeof l); - l = cpu_to_le32(ioread32(vp_dev->device + offset + sizeof l)); + l = cpu_to_le32(ioread32(device + offset + sizeof l)); memcpy(buf + sizeof l, &l, sizeof l); break; default: @@ -228,30 +102,32 @@ static void vp_set(struct virtio_device *vdev, unsigned offset, const void *buf, unsigned len) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_modern_device *mdev = &vp_dev->mdev; + void __iomem *device = mdev->device; u8 b; __le16 w; __le32 l; - BUG_ON(offset + len > vp_dev->device_len); + BUG_ON(offset + len > mdev->device_len); switch (len) { case 1: memcpy(&b, buf, sizeof b); - iowrite8(b, vp_dev->device + offset); + iowrite8(b, device + offset); break; case 2: memcpy(&w, buf, sizeof w); - iowrite16(le16_to_cpu(w), vp_dev->device + offset); + iowrite16(le16_to_cpu(w), device + offset); break; case 4: memcpy(&l, buf, sizeof l); - iowrite32(le32_to_cpu(l), vp_dev->device + offset); + iowrite32(le32_to_cpu(l), device + offset); break; case 8: memcpy(&l, buf, sizeof l); - iowrite32(le32_to_cpu(l), vp_dev->device + offset); + iowrite32(le32_to_cpu(l), device + offset); memcpy(&l, buf + sizeof l, sizeof l); - iowrite32(le32_to_cpu(l), vp_dev->device + offset + sizeof l); + iowrite32(le32_to_cpu(l), device + offset + sizeof l); break; default: BUG(); @@ -261,35 +137,40 @@ static void vp_set(struct virtio_device *vdev, unsigned offset, static u32 vp_generation(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - return vp_ioread8(&vp_dev->common->config_generation); + + return vp_modern_generation(&vp_dev->mdev); } /* config->{get,set}_status() implementations */ static u8 vp_get_status(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - return vp_ioread8(&vp_dev->common->device_status); + + return vp_modern_get_status(&vp_dev->mdev); } static void vp_set_status(struct virtio_device *vdev, u8 status) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); + /* We should never be setting status to 0. */ BUG_ON(status == 0); - vp_iowrite8(status, &vp_dev->common->device_status); + vp_modern_set_status(&vp_dev->mdev, status); } static void vp_reset(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_modern_device *mdev = &vp_dev->mdev; + /* 0 status means a reset. */ - vp_iowrite8(0, &vp_dev->common->device_status); + vp_modern_set_status(mdev, 0); /* After writing 0 to device_status, the driver MUST wait for a read of * device_status to return 0 before reinitializing the device. * This will flush out the status write, and flush in device writes, * including MSI-X interrupts, if any. */ - while (vp_ioread8(&vp_dev->common->device_status)) + while (vp_modern_get_status(mdev)) msleep(1); /* Flush pending VQ/configuration callbacks. */ vp_synchronize_vectors(vdev); @@ -297,11 +178,7 @@ static void vp_reset(struct virtio_device *vdev) static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) { - /* Setup the vector used for configuration events */ - vp_iowrite16(vector, &vp_dev->common->msix_config); - /* Verify we had enough resources to assign the vector */ - /* Will also flush the write out to device */ - return vp_ioread16(&vp_dev->common->msix_config); + return vp_modern_config_vector(&vp_dev->mdev, vector); } static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, @@ -312,20 +189,18 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, bool ctx, u16 msix_vec) { - struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common; + + struct virtio_pci_modern_device *mdev = &vp_dev->mdev; struct virtqueue *vq; u16 num, off; int err; - if (index >= vp_ioread16(&cfg->num_queues)) + if (index >= vp_modern_get_num_queues(mdev)) return ERR_PTR(-ENOENT); - /* Select the queue we're interested in */ - vp_iowrite16(index, &cfg->queue_select); - /* Check if queue is either not available or already active. */ - num = vp_ioread16(&cfg->queue_size); - if (!num || vp_ioread16(&cfg->queue_enable)) + num = vp_modern_get_queue_size(mdev, index); + if (!num || vp_modern_get_queue_enable(mdev, index)) return ERR_PTR(-ENOENT); if (num & (num - 1)) { @@ -334,7 +209,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, } /* get offset of notification word for this vq */ - off = vp_ioread16(&cfg->queue_notify_off); + off = vp_modern_get_queue_notify_off(mdev, index); info->msix_vector = msix_vec; @@ -347,33 +222,30 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, return ERR_PTR(-ENOMEM); /* activate the queue */ - vp_iowrite16(virtqueue_get_vring_size(vq), &cfg->queue_size); - vp_iowrite64_twopart(virtqueue_get_desc_addr(vq), - &cfg->queue_desc_lo, &cfg->queue_desc_hi); - vp_iowrite64_twopart(virtqueue_get_avail_addr(vq), - &cfg->queue_avail_lo, &cfg->queue_avail_hi); - vp_iowrite64_twopart(virtqueue_get_used_addr(vq), - &cfg->queue_used_lo, &cfg->queue_used_hi); + vp_modern_set_queue_size(mdev, index, virtqueue_get_vring_size(vq)); + vp_modern_queue_address(mdev, index, virtqueue_get_desc_addr(vq), + virtqueue_get_avail_addr(vq), + virtqueue_get_used_addr(vq)); - if (vp_dev->notify_base) { + if (mdev->notify_base) { /* offset should not wrap */ - if ((u64)off * vp_dev->notify_offset_multiplier + 2 - > vp_dev->notify_len) { - dev_warn(&vp_dev->pci_dev->dev, + if ((u64)off * mdev->notify_offset_multiplier + 2 + > mdev->notify_len) { + dev_warn(&mdev->pci_dev->dev, "bad notification offset %u (x %u) " "for queue %u > %zd", - off, vp_dev->notify_offset_multiplier, - index, vp_dev->notify_len); + off, mdev->notify_offset_multiplier, + index, mdev->notify_len); err = -EINVAL; goto err_map_notify; } - vq->priv = (void __force *)vp_dev->notify_base + - off * vp_dev->notify_offset_multiplier; + vq->priv = (void __force *)mdev->notify_base + + off * mdev->notify_offset_multiplier; } else { - vq->priv = (void __force *)map_capability(vp_dev->pci_dev, - vp_dev->notify_map_cap, 2, 2, - off * vp_dev->notify_offset_multiplier, 2, - NULL); + vq->priv = (void __force *)vp_modern_map_capability(mdev, + mdev->notify_map_cap, 2, 2, + off * mdev->notify_offset_multiplier, 2, + NULL); } if (!vq->priv) { @@ -382,8 +254,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, } if (msix_vec != VIRTIO_MSI_NO_VECTOR) { - vp_iowrite16(msix_vec, &cfg->queue_msix_vector); - msix_vec = vp_ioread16(&cfg->queue_msix_vector); + msix_vec = vp_modern_queue_vector(mdev, index, msix_vec); if (msix_vec == VIRTIO_MSI_NO_VECTOR) { err = -EBUSY; goto err_assign_vector; @@ -393,8 +264,8 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, return vq; err_assign_vector: - if (!vp_dev->notify_base) - pci_iounmap(vp_dev->pci_dev, (void __iomem __force *)vq->priv); + if (!mdev->notify_base) + pci_iounmap(mdev->pci_dev, (void __iomem __force *)vq->priv); err_map_notify: vring_del_virtqueue(vq); return ERR_PTR(err); @@ -416,10 +287,8 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs, /* Select and activate all queues. Has to be done last: once we do * this, there's no way to go back except reset. */ - list_for_each_entry(vq, &vdev->vqs, list) { - vp_iowrite16(vq->index, &vp_dev->common->queue_select); - vp_iowrite16(1, &vp_dev->common->queue_enable); - } + list_for_each_entry(vq, &vdev->vqs, list) + vp_modern_set_queue_enable(&vp_dev->mdev, vq->index, true); return 0; } @@ -428,18 +297,14 @@ static void del_vq(struct virtio_pci_vq_info *info) { struct virtqueue *vq = info->vq; struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); + struct virtio_pci_modern_device *mdev = &vp_dev->mdev; - vp_iowrite16(vq->index, &vp_dev->common->queue_select); + if (vp_dev->msix_enabled) + vp_modern_queue_vector(mdev, vq->index, + VIRTIO_MSI_NO_VECTOR); - if (vp_dev->msix_enabled) { - vp_iowrite16(VIRTIO_MSI_NO_VECTOR, - &vp_dev->common->queue_msix_vector); - /* Flush the write out to device */ - vp_ioread16(&vp_dev->common->queue_msix_vector); - } - - if (!vp_dev->notify_base) - pci_iounmap(vp_dev->pci_dev, (void __force __iomem *)vq->priv); + if (!mdev->notify_base) + pci_iounmap(mdev->pci_dev, (void __force __iomem *)vq->priv); vring_del_virtqueue(vq); } @@ -571,261 +436,36 @@ static const struct virtio_config_ops virtio_pci_config_ops = { .get_shm_region = vp_get_shm_region, }; -/** - * virtio_pci_find_capability - walk capabilities to find device info. - * @dev: the pci device - * @cfg_type: the VIRTIO_PCI_CAP_* value we seek - * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO. - * @bars: the bitmask of BARs - * - * Returns offset of the capability, or 0. - */ -static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type, - u32 ioresource_types, int *bars) -{ - int pos; - - for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR); - pos > 0; - pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) { - u8 type, bar; - pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap, - cfg_type), - &type); - pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap, - bar), - &bar); - - /* Ignore structures with reserved BAR values */ - if (bar > 0x5) - continue; - - if (type == cfg_type) { - if (pci_resource_len(dev, bar) && - pci_resource_flags(dev, bar) & ioresource_types) { - *bars |= (1 << bar); - return pos; - } - } - } - return 0; -} - -/* This is part of the ABI. Don't screw with it. */ -static inline void check_offsets(void) -{ - /* Note: disk space was harmed in compilation of this function. */ - BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR != - offsetof(struct virtio_pci_cap, cap_vndr)); - BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT != - offsetof(struct virtio_pci_cap, cap_next)); - BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN != - offsetof(struct virtio_pci_cap, cap_len)); - BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE != - offsetof(struct virtio_pci_cap, cfg_type)); - BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR != - offsetof(struct virtio_pci_cap, bar)); - BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET != - offsetof(struct virtio_pci_cap, offset)); - BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH != - offsetof(struct virtio_pci_cap, length)); - BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT != - offsetof(struct virtio_pci_notify_cap, - notify_off_multiplier)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT != - offsetof(struct virtio_pci_common_cfg, - device_feature_select)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF != - offsetof(struct virtio_pci_common_cfg, device_feature)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT != - offsetof(struct virtio_pci_common_cfg, - guest_feature_select)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF != - offsetof(struct virtio_pci_common_cfg, guest_feature)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX != - offsetof(struct virtio_pci_common_cfg, msix_config)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ != - offsetof(struct virtio_pci_common_cfg, num_queues)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS != - offsetof(struct virtio_pci_common_cfg, device_status)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION != - offsetof(struct virtio_pci_common_cfg, config_generation)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT != - offsetof(struct virtio_pci_common_cfg, queue_select)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE != - offsetof(struct virtio_pci_common_cfg, queue_size)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX != - offsetof(struct virtio_pci_common_cfg, queue_msix_vector)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE != - offsetof(struct virtio_pci_common_cfg, queue_enable)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF != - offsetof(struct virtio_pci_common_cfg, queue_notify_off)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO != - offsetof(struct virtio_pci_common_cfg, queue_desc_lo)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI != - offsetof(struct virtio_pci_common_cfg, queue_desc_hi)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO != - offsetof(struct virtio_pci_common_cfg, queue_avail_lo)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI != - offsetof(struct virtio_pci_common_cfg, queue_avail_hi)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO != - offsetof(struct virtio_pci_common_cfg, queue_used_lo)); - BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI != - offsetof(struct virtio_pci_common_cfg, queue_used_hi)); -} - /* the PCI probing function */ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) { + struct virtio_pci_modern_device *mdev = &vp_dev->mdev; struct pci_dev *pci_dev = vp_dev->pci_dev; - int err, common, isr, notify, device; - u32 notify_length; - u32 notify_offset; + int err; - check_offsets(); + mdev->pci_dev = pci_dev; - /* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */ - if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f) - return -ENODEV; - - if (pci_dev->device < 0x1040) { - /* Transitional devices: use the PCI subsystem device id as - * virtio device id, same as legacy driver always did. - */ - vp_dev->vdev.id.device = pci_dev->subsystem_device; - } else { - /* Modern devices: simply use PCI device id, but start from 0x1040. */ - vp_dev->vdev.id.device = pci_dev->device - 0x1040; - } - vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor; - - /* check for a common config: if not, use legacy mode (bar 0). */ - common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG, - IORESOURCE_IO | IORESOURCE_MEM, - &vp_dev->modern_bars); - if (!common) { - dev_info(&pci_dev->dev, - "virtio_pci: leaving for legacy driver\n"); - return -ENODEV; - } - - /* If common is there, these should be too... */ - isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG, - IORESOURCE_IO | IORESOURCE_MEM, - &vp_dev->modern_bars); - notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG, - IORESOURCE_IO | IORESOURCE_MEM, - &vp_dev->modern_bars); - if (!isr || !notify) { - dev_err(&pci_dev->dev, - "virtio_pci: missing capabilities %i/%i/%i\n", - common, isr, notify); - return -EINVAL; - } - - err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64)); - if (err) - err = dma_set_mask_and_coherent(&pci_dev->dev, - DMA_BIT_MASK(32)); - if (err) - dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n"); - - /* Device capability is only mandatory for devices that have - * device-specific configuration. - */ - device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG, - IORESOURCE_IO | IORESOURCE_MEM, - &vp_dev->modern_bars); - - err = pci_request_selected_regions(pci_dev, vp_dev->modern_bars, - "virtio-pci-modern"); + err = vp_modern_probe(mdev); if (err) return err; - err = -EINVAL; - vp_dev->common = map_capability(pci_dev, common, - sizeof(struct virtio_pci_common_cfg), 4, - 0, sizeof(struct virtio_pci_common_cfg), - NULL); - if (!vp_dev->common) - goto err_map_common; - vp_dev->isr = map_capability(pci_dev, isr, sizeof(u8), 1, - 0, 1, - NULL); - if (!vp_dev->isr) - goto err_map_isr; - - /* Read notify_off_multiplier from config space. */ - pci_read_config_dword(pci_dev, - notify + offsetof(struct virtio_pci_notify_cap, - notify_off_multiplier), - &vp_dev->notify_offset_multiplier); - /* Read notify length and offset from config space. */ - pci_read_config_dword(pci_dev, - notify + offsetof(struct virtio_pci_notify_cap, - cap.length), - ¬ify_length); - - pci_read_config_dword(pci_dev, - notify + offsetof(struct virtio_pci_notify_cap, - cap.offset), - ¬ify_offset); - - /* We don't know how many VQs we'll map, ahead of the time. - * If notify length is small, map it all now. - * Otherwise, map each VQ individually later. - */ - if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) { - vp_dev->notify_base = map_capability(pci_dev, notify, 2, 2, - 0, notify_length, - &vp_dev->notify_len); - if (!vp_dev->notify_base) - goto err_map_notify; - } else { - vp_dev->notify_map_cap = notify; - } - - /* Again, we don't know how much we should map, but PAGE_SIZE - * is more than enough for all existing devices. - */ - if (device) { - vp_dev->device = map_capability(pci_dev, device, 0, 4, - 0, PAGE_SIZE, - &vp_dev->device_len); - if (!vp_dev->device) - goto err_map_device; - + if (mdev->device) vp_dev->vdev.config = &virtio_pci_config_ops; - } else { + else vp_dev->vdev.config = &virtio_pci_config_nodev_ops; - } vp_dev->config_vector = vp_config_vector; vp_dev->setup_vq = setup_vq; vp_dev->del_vq = del_vq; + vp_dev->isr = mdev->isr; + vp_dev->vdev.id = mdev->id; return 0; - -err_map_device: - if (vp_dev->notify_base) - pci_iounmap(pci_dev, vp_dev->notify_base); -err_map_notify: - pci_iounmap(pci_dev, vp_dev->isr); -err_map_isr: - pci_iounmap(pci_dev, vp_dev->common); -err_map_common: - return err; } void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev) { - struct pci_dev *pci_dev = vp_dev->pci_dev; + struct virtio_pci_modern_device *mdev = &vp_dev->mdev; - if (vp_dev->device) - pci_iounmap(pci_dev, vp_dev->device); - if (vp_dev->notify_base) - pci_iounmap(pci_dev, vp_dev->notify_base); - pci_iounmap(pci_dev, vp_dev->isr); - pci_iounmap(pci_dev, vp_dev->common); - pci_release_selected_regions(pci_dev, vp_dev->modern_bars); + vp_modern_remove(mdev); } diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c new file mode 100644 index 000000000000..cbd667496bb1 --- /dev/null +++ b/drivers/virtio/virtio_pci_modern_dev.c @@ -0,0 +1,599 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include +#include +#include + +/* + * vp_modern_map_capability - map a part of virtio pci capability + * @mdev: the modern virtio-pci device + * @off: offset of the capability + * @minlen: minimal length of the capability + * @align: align requirement + * @start: start from the capability + * @size: map size + * @len: the length that is actually mapped + * + * Returns the io address of for the part of the capability + */ +void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off, + size_t minlen, + u32 align, + u32 start, u32 size, + size_t *len) +{ + struct pci_dev *dev = mdev->pci_dev; + u8 bar; + u32 offset, length; + void __iomem *p; + + pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap, + bar), + &bar); + pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset), + &offset); + pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length), + &length); + + if (length <= start) { + dev_err(&dev->dev, + "virtio_pci: bad capability len %u (>%u expected)\n", + length, start); + return NULL; + } + + if (length - start < minlen) { + dev_err(&dev->dev, + "virtio_pci: bad capability len %u (>=%zu expected)\n", + length, minlen); + return NULL; + } + + length -= start; + + if (start + offset < offset) { + dev_err(&dev->dev, + "virtio_pci: map wrap-around %u+%u\n", + start, offset); + return NULL; + } + + offset += start; + + if (offset & (align - 1)) { + dev_err(&dev->dev, + "virtio_pci: offset %u not aligned to %u\n", + offset, align); + return NULL; + } + + if (length > size) + length = size; + + if (len) + *len = length; + + if (minlen + offset < minlen || + minlen + offset > pci_resource_len(dev, bar)) { + dev_err(&dev->dev, + "virtio_pci: map virtio %zu@%u " + "out of range on bar %i length %lu\n", + minlen, offset, + bar, (unsigned long)pci_resource_len(dev, bar)); + return NULL; + } + + p = pci_iomap_range(dev, bar, offset, length); + if (!p) + dev_err(&dev->dev, + "virtio_pci: unable to map virtio %u@%u on bar %i\n", + length, offset, bar); + return p; +} +EXPORT_SYMBOL_GPL(vp_modern_map_capability); + +/** + * virtio_pci_find_capability - walk capabilities to find device info. + * @dev: the pci device + * @cfg_type: the VIRTIO_PCI_CAP_* value we seek + * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO. + * @bars: the bitmask of BARs + * + * Returns offset of the capability, or 0. + */ +static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type, + u32 ioresource_types, int *bars) +{ + int pos; + + for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR); + pos > 0; + pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) { + u8 type, bar; + pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap, + cfg_type), + &type); + pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap, + bar), + &bar); + + /* Ignore structures with reserved BAR values */ + if (bar > 0x5) + continue; + + if (type == cfg_type) { + if (pci_resource_len(dev, bar) && + pci_resource_flags(dev, bar) & ioresource_types) { + *bars |= (1 << bar); + return pos; + } + } + } + return 0; +} + +/* This is part of the ABI. Don't screw with it. */ +static inline void check_offsets(void) +{ + /* Note: disk space was harmed in compilation of this function. */ + BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR != + offsetof(struct virtio_pci_cap, cap_vndr)); + BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT != + offsetof(struct virtio_pci_cap, cap_next)); + BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN != + offsetof(struct virtio_pci_cap, cap_len)); + BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE != + offsetof(struct virtio_pci_cap, cfg_type)); + BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR != + offsetof(struct virtio_pci_cap, bar)); + BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET != + offsetof(struct virtio_pci_cap, offset)); + BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH != + offsetof(struct virtio_pci_cap, length)); + BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT != + offsetof(struct virtio_pci_notify_cap, + notify_off_multiplier)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT != + offsetof(struct virtio_pci_common_cfg, + device_feature_select)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF != + offsetof(struct virtio_pci_common_cfg, device_feature)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT != + offsetof(struct virtio_pci_common_cfg, + guest_feature_select)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF != + offsetof(struct virtio_pci_common_cfg, guest_feature)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX != + offsetof(struct virtio_pci_common_cfg, msix_config)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ != + offsetof(struct virtio_pci_common_cfg, num_queues)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS != + offsetof(struct virtio_pci_common_cfg, device_status)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION != + offsetof(struct virtio_pci_common_cfg, config_generation)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT != + offsetof(struct virtio_pci_common_cfg, queue_select)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE != + offsetof(struct virtio_pci_common_cfg, queue_size)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX != + offsetof(struct virtio_pci_common_cfg, queue_msix_vector)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE != + offsetof(struct virtio_pci_common_cfg, queue_enable)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF != + offsetof(struct virtio_pci_common_cfg, queue_notify_off)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO != + offsetof(struct virtio_pci_common_cfg, queue_desc_lo)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI != + offsetof(struct virtio_pci_common_cfg, queue_desc_hi)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO != + offsetof(struct virtio_pci_common_cfg, queue_avail_lo)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI != + offsetof(struct virtio_pci_common_cfg, queue_avail_hi)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO != + offsetof(struct virtio_pci_common_cfg, queue_used_lo)); + BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI != + offsetof(struct virtio_pci_common_cfg, queue_used_hi)); +} + +/* + * vp_modern_probe: probe the modern virtio pci device, note that the + * caller is required to enable PCI device before calling this function. + * @mdev: the modern virtio-pci device + * + * Return 0 on succeed otherwise fail + */ +int vp_modern_probe(struct virtio_pci_modern_device *mdev) +{ + struct pci_dev *pci_dev = mdev->pci_dev; + int err, common, isr, notify, device; + u32 notify_length; + u32 notify_offset; + + check_offsets(); + + mdev->pci_dev = pci_dev; + + /* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */ + if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f) + return -ENODEV; + + if (pci_dev->device < 0x1040) { + /* Transitional devices: use the PCI subsystem device id as + * virtio device id, same as legacy driver always did. + */ + mdev->id.device = pci_dev->subsystem_device; + } else { + /* Modern devices: simply use PCI device id, but start from 0x1040. */ + mdev->id.device = pci_dev->device - 0x1040; + } + mdev->id.vendor = pci_dev->subsystem_vendor; + + /* check for a common config: if not, use legacy mode (bar 0). */ + common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG, + IORESOURCE_IO | IORESOURCE_MEM, + &mdev->modern_bars); + if (!common) { + dev_info(&pci_dev->dev, + "virtio_pci: leaving for legacy driver\n"); + return -ENODEV; + } + + /* If common is there, these should be too... */ + isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG, + IORESOURCE_IO | IORESOURCE_MEM, + &mdev->modern_bars); + notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG, + IORESOURCE_IO | IORESOURCE_MEM, + &mdev->modern_bars); + if (!isr || !notify) { + dev_err(&pci_dev->dev, + "virtio_pci: missing capabilities %i/%i/%i\n", + common, isr, notify); + return -EINVAL; + } + + err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64)); + if (err) + err = dma_set_mask_and_coherent(&pci_dev->dev, + DMA_BIT_MASK(32)); + if (err) + dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n"); + + /* Device capability is only mandatory for devices that have + * device-specific configuration. + */ + device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG, + IORESOURCE_IO | IORESOURCE_MEM, + &mdev->modern_bars); + + err = pci_request_selected_regions(pci_dev, mdev->modern_bars, + "virtio-pci-modern"); + if (err) + return err; + + err = -EINVAL; + mdev->common = vp_modern_map_capability(mdev, common, + sizeof(struct virtio_pci_common_cfg), 4, + 0, sizeof(struct virtio_pci_common_cfg), + NULL); + if (!mdev->common) + goto err_map_common; + mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1, + 0, 1, + NULL); + if (!mdev->isr) + goto err_map_isr; + + /* Read notify_off_multiplier from config space. */ + pci_read_config_dword(pci_dev, + notify + offsetof(struct virtio_pci_notify_cap, + notify_off_multiplier), + &mdev->notify_offset_multiplier); + /* Read notify length and offset from config space. */ + pci_read_config_dword(pci_dev, + notify + offsetof(struct virtio_pci_notify_cap, + cap.length), + ¬ify_length); + + pci_read_config_dword(pci_dev, + notify + offsetof(struct virtio_pci_notify_cap, + cap.offset), + ¬ify_offset); + + /* We don't know how many VQs we'll map, ahead of the time. + * If notify length is small, map it all now. + * Otherwise, map each VQ individually later. + */ + if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) { + mdev->notify_base = vp_modern_map_capability(mdev, notify, + 2, 2, + 0, notify_length, + &mdev->notify_len); + if (!mdev->notify_base) + goto err_map_notify; + } else { + mdev->notify_map_cap = notify; + } + + /* Again, we don't know how much we should map, but PAGE_SIZE + * is more than enough for all existing devices. + */ + if (device) { + mdev->device = vp_modern_map_capability(mdev, device, 0, 4, + 0, PAGE_SIZE, + &mdev->device_len); + if (!mdev->device) + goto err_map_device; + } + + return 0; + +err_map_device: + if (mdev->notify_base) + pci_iounmap(pci_dev, mdev->notify_base); +err_map_notify: + pci_iounmap(pci_dev, mdev->isr); +err_map_isr: + pci_iounmap(pci_dev, mdev->common); +err_map_common: + return err; +} +EXPORT_SYMBOL_GPL(vp_modern_probe); + +/* + * vp_modern_probe: remove and cleanup the modern virtio pci device + * @mdev: the modern virtio-pci device + */ +void vp_modern_remove(struct virtio_pci_modern_device *mdev) +{ + struct pci_dev *pci_dev = mdev->pci_dev; + + if (mdev->device) + pci_iounmap(pci_dev, mdev->device); + if (mdev->notify_base) + pci_iounmap(pci_dev, mdev->notify_base); + pci_iounmap(pci_dev, mdev->isr); + pci_iounmap(pci_dev, mdev->common); + pci_release_selected_regions(pci_dev, mdev->modern_bars); +} +EXPORT_SYMBOL_GPL(vp_modern_remove); + +/* + * vp_modern_get_features - get features from device + * @mdev: the modern virtio-pci device + * + * Returns the features read from the device + */ +u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + u64 features; + + vp_iowrite32(0, &cfg->device_feature_select); + features = vp_ioread32(&cfg->device_feature); + vp_iowrite32(1, &cfg->device_feature_select); + features |= ((u64)vp_ioread32(&cfg->device_feature) << 32); + + return features; +} +EXPORT_SYMBOL_GPL(vp_modern_get_features); + +/* + * vp_modern_set_features - set features to device + * @mdev: the modern virtio-pci device + * @features: the features set to device + */ +void vp_modern_set_features(struct virtio_pci_modern_device *mdev, + u64 features) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + vp_iowrite32(0, &cfg->guest_feature_select); + vp_iowrite32((u32)features, &cfg->guest_feature); + vp_iowrite32(1, &cfg->guest_feature_select); + vp_iowrite32(features >> 32, &cfg->guest_feature); +} +EXPORT_SYMBOL_GPL(vp_modern_set_features); + +/* + * vp_modern_generation - get the device genreation + * @mdev: the modern virtio-pci device + * + * Returns the genreation read from device + */ +u32 vp_modern_generation(struct virtio_pci_modern_device *mdev) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + return vp_ioread8(&cfg->config_generation); +} +EXPORT_SYMBOL_GPL(vp_modern_generation); + +/* + * vp_modern_get_status - get the device status + * @mdev: the modern virtio-pci device + * + * Returns the status read from device + */ +u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + return vp_ioread8(&cfg->device_status); +} +EXPORT_SYMBOL_GPL(vp_modern_get_status); + +/* + * vp_modern_set_status - set status to device + * @mdev: the modern virtio-pci device + * @status: the status set to device + */ +void vp_modern_set_status(struct virtio_pci_modern_device *mdev, + u8 status) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + vp_iowrite8(status, &cfg->device_status); +} +EXPORT_SYMBOL_GPL(vp_modern_set_status); + +/* + * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue + * @mdev: the modern virtio-pci device + * @index: queue index + * @vector: the config vector + * + * Returns the config vector read from the device + */ +u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev, + u16 index, u16 vector) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + vp_iowrite16(index, &cfg->queue_select); + vp_iowrite16(vector, &cfg->queue_msix_vector); + /* Flush the write out to device */ + return vp_ioread16(&cfg->queue_msix_vector); +} +EXPORT_SYMBOL_GPL(vp_modern_queue_vector); + +/* + * vp_modern_config_vector - set the vector for config interrupt + * @mdev: the modern virtio-pci device + * @vector: the config vector + * + * Returns the config vector read from the device + */ +u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev, + u16 vector) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + /* Setup the vector used for configuration events */ + vp_iowrite16(vector, &cfg->msix_config); + /* Verify we had enough resources to assign the vector */ + /* Will also flush the write out to device */ + return vp_ioread16(&cfg->msix_config); +} +EXPORT_SYMBOL_GPL(vp_modern_config_vector); + +/* + * vp_modern_queue_address - set the virtqueue address + * @mdev: the modern virtio-pci device + * @index: the queue index + * @desc_addr: address of the descriptor area + * @driver_addr: address of the driver area + * @device_addr: address of the device area + */ +void vp_modern_queue_address(struct virtio_pci_modern_device *mdev, + u16 index, u64 desc_addr, u64 driver_addr, + u64 device_addr) +{ + struct virtio_pci_common_cfg __iomem *cfg = mdev->common; + + vp_iowrite16(index, &cfg->queue_select); + + vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo, + &cfg->queue_desc_hi); + vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo, + &cfg->queue_avail_hi); + vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo, + &cfg->queue_used_hi); +} +EXPORT_SYMBOL_GPL(vp_modern_queue_address); + +/* + * vp_modern_set_queue_enable - enable a virtqueue + * @mdev: the modern virtio-pci device + * @index: the queue index + * @enable: whether the virtqueue is enable or not + */ +void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev, + u16 index, bool enable) +{ + vp_iowrite16(index, &mdev->common->queue_select); + vp_iowrite16(enable, &mdev->common->queue_enable); +} +EXPORT_SYMBOL_GPL(vp_modern_set_queue_enable); + +/* + * vp_modern_get_queue_enable - enable a virtqueue + * @mdev: the modern virtio-pci device + * @index: the queue index + * + * Returns whether a virtqueue is enabled or not + */ +bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev, + u16 index) +{ + vp_iowrite16(index, &mdev->common->queue_select); + + return vp_ioread16(&mdev->common->queue_enable); +} +EXPORT_SYMBOL_GPL(vp_modern_get_queue_enable); + +/* + * vp_modern_set_queue_size - set size for a virtqueue + * @mdev: the modern virtio-pci device + * @index: the queue index + * @size: the size of the virtqueue + */ +void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev, + u16 index, u16 size) +{ + vp_iowrite16(index, &mdev->common->queue_select); + vp_iowrite16(size, &mdev->common->queue_size); + +} +EXPORT_SYMBOL_GPL(vp_modern_set_queue_size); + +/* + * vp_modern_get_queue_size - get size for a virtqueue + * @mdev: the modern virtio-pci device + * @index: the queue index + * + * Returns the size of the virtqueue + */ +u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev, + u16 index) +{ + vp_iowrite16(index, &mdev->common->queue_select); + + return vp_ioread16(&mdev->common->queue_size); + +} +EXPORT_SYMBOL_GPL(vp_modern_get_queue_size); + +/* + * vp_modern_get_num_queues - get the number of virtqueues + * @mdev: the modern virtio-pci device + * + * Returns the number of virtqueues + */ +u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev) +{ + return vp_ioread16(&mdev->common->num_queues); +} +EXPORT_SYMBOL_GPL(vp_modern_get_num_queues); + +/* + * vp_modern_get_queue_notify_off - get notification offset for a virtqueue + * @mdev: the modern virtio-pci device + * @index: the queue index + * + * Returns the notification offset for a virtqueue + */ +u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev, + u16 index) +{ + vp_iowrite16(index, &mdev->common->queue_select); + + return vp_ioread16(&mdev->common->queue_notify_off); +} +EXPORT_SYMBOL_GPL(vp_modern_get_queue_notify_off); + +MODULE_VERSION("0.1"); +MODULE_DESCRIPTION("Modern Virtio PCI Device"); +MODULE_AUTHOR("Jason Wang "); +MODULE_LICENSE("GPL"); diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index 4a9ddb44b2a7..e28acf482e0c 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -225,9 +225,8 @@ static void virtio_vdpa_del_vq(struct virtqueue *vq) list_del(&info->node); spin_unlock_irqrestore(&vd_dev->lock, flags); - /* Select and deactivate the queue */ + /* Select and deactivate the queue (best effort) */ ops->set_vq_ready(vdpa, index, 0); - WARN_ON(ops->get_vq_ready(vdpa, index)); vring_del_virtqueue(vq); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index b57b2067ecbf..671c71245a7b 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -331,7 +331,7 @@ static enum bp_state reserve_additional_memory(void) mutex_unlock(&balloon_mutex); /* add_memory_resource() requires the device_hotplug lock */ lock_device_hotplug(); - rc = add_memory_resource(nid, resource, MEMHP_MERGE_RESOURCE); + rc = add_memory_resource(nid, resource, MHP_MERGE_RESOURCE); unlock_device_hotplug(); mutex_lock(&balloon_mutex); diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index b249f2d6b0cc..adb7260e94b2 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -323,6 +323,8 @@ static int xen_irq_info_evtchn_setup(unsigned irq, ret = xen_irq_info_common_setup(info, irq, IRQT_EVTCHN, evtchn, 0); info->u.interdomain = dev; + if (dev) + atomic_inc(&dev->event_channels); return ret; } @@ -568,18 +570,28 @@ static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious) return; if (spurious) { + struct xenbus_device *dev = info->u.interdomain; + unsigned int threshold = 1; + + if (dev && dev->spurious_threshold) + threshold = dev->spurious_threshold; + if ((1 << info->spurious_cnt) < (HZ << 2)) { if (info->spurious_cnt != 0xFF) info->spurious_cnt++; } - if (info->spurious_cnt > 1) { - delay = 1 << (info->spurious_cnt - 2); + if (info->spurious_cnt > threshold) { + delay = 1 << (info->spurious_cnt - 1 - threshold); if (delay > HZ) delay = HZ; if (!info->eoi_time) info->eoi_cpu = smp_processor_id(); info->eoi_time = get_jiffies_64() + delay; + if (dev) + atomic_add(delay, &dev->jiffies_eoi_delayed); } + if (dev) + atomic_inc(&dev->spurious_events); } else { info->spurious_cnt = 0; } @@ -908,6 +920,7 @@ static void __unbind_from_irq(unsigned int irq) if (VALID_EVTCHN(evtchn)) { unsigned int cpu = cpu_from_irq(irq); + struct xenbus_device *dev; xen_evtchn_close(evtchn); @@ -918,6 +931,11 @@ static void __unbind_from_irq(unsigned int irq) case IRQT_IPI: per_cpu(ipi_to_irq, cpu)[ipi_from_irq(irq)] = -1; break; + case IRQT_EVTCHN: + dev = info->u.interdomain; + if (dev) + atomic_dec(&dev->event_channels); + break; default: break; } @@ -1581,6 +1599,7 @@ void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl) { int irq; struct irq_info *info; + struct xenbus_device *dev; irq = get_evtchn_to_irq(port); if (irq == -1) @@ -1610,6 +1629,10 @@ void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl) info = info_for_irq(irq); + dev = (info->type == IRQT_EVTCHN) ? info->u.interdomain : NULL; + if (dev) + atomic_inc(&dev->events); + if (ctrl->defer_eoi) { info->eoi_cpu = smp_processor_id(); info->irq_epoch = __this_cpu_read(irq_epoch); diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c index a7a85719a8c8..c99415a70051 100644 --- a/drivers/xen/evtchn.c +++ b/drivers/xen/evtchn.c @@ -162,6 +162,7 @@ static irqreturn_t evtchn_interrupt(int irq, void *data) { struct user_evtchn *evtchn = data; struct per_user_data *u = evtchn->user; + unsigned int prod, cons; WARN(!evtchn->enabled, "Interrupt for port %u, but apparently not enabled; per-user %p\n", @@ -171,10 +172,14 @@ static irqreturn_t evtchn_interrupt(int irq, void *data) spin_lock(&u->ring_prod_lock); - if ((u->ring_prod - u->ring_cons) < u->ring_size) { - *evtchn_ring_entry(u, u->ring_prod) = evtchn->port; - wmb(); /* Ensure ring contents visible */ - if (u->ring_cons == u->ring_prod++) { + prod = READ_ONCE(u->ring_prod); + cons = READ_ONCE(u->ring_cons); + + if ((prod - cons) < u->ring_size) { + *evtchn_ring_entry(u, prod) = evtchn->port; + smp_wmb(); /* Ensure ring contents visible */ + WRITE_ONCE(u->ring_prod, prod + 1); + if (cons == prod) { wake_up_interruptible(&u->evtchn_wait); kill_fasync(&u->evtchn_async_queue, SIGIO, POLL_IN); @@ -210,8 +215,8 @@ static ssize_t evtchn_read(struct file *file, char __user *buf, if (u->ring_overflow) goto unlock_out; - c = u->ring_cons; - p = u->ring_prod; + c = READ_ONCE(u->ring_cons); + p = READ_ONCE(u->ring_prod); if (c != p) break; @@ -221,7 +226,7 @@ static ssize_t evtchn_read(struct file *file, char __user *buf, return -EAGAIN; rc = wait_event_interruptible(u->evtchn_wait, - u->ring_cons != u->ring_prod); + READ_ONCE(u->ring_cons) != READ_ONCE(u->ring_prod)); if (rc) return rc; } @@ -245,13 +250,13 @@ static ssize_t evtchn_read(struct file *file, char __user *buf, } rc = -EFAULT; - rmb(); /* Ensure that we see the port before we copy it. */ + smp_rmb(); /* Ensure that we see the port before we copy it. */ if (copy_to_user(buf, evtchn_ring_entry(u, c), bytes1) || ((bytes2 != 0) && copy_to_user(&buf[bytes1], &u->ring[0], bytes2))) goto unlock_out; - u->ring_cons += (bytes1 + bytes2) / sizeof(evtchn_port_t); + WRITE_ONCE(u->ring_cons, c + (bytes1 + bytes2) / sizeof(evtchn_port_t)); rc = bytes1 + bytes2; unlock_out: @@ -552,7 +557,9 @@ static long evtchn_ioctl(struct file *file, /* Initialise the ring to empty. Clear errors. */ mutex_lock(&u->ring_cons_mutex); spin_lock_irq(&u->ring_prod_lock); - u->ring_cons = u->ring_prod = u->ring_overflow = 0; + WRITE_ONCE(u->ring_cons, 0); + WRITE_ONCE(u->ring_prod, 0); + u->ring_overflow = 0; spin_unlock_irq(&u->ring_prod_lock); mutex_unlock(&u->ring_cons_mutex); rc = 0; @@ -595,7 +602,7 @@ static __poll_t evtchn_poll(struct file *file, poll_table *wait) struct per_user_data *u = file->private_data; poll_wait(file, &u->evtchn_wait, wait); - if (u->ring_cons != u->ring_prod) + if (READ_ONCE(u->ring_cons) != READ_ONCE(u->ring_prod)) mask |= EPOLLIN | EPOLLRDNORM; if (u->ring_overflow) mask = EPOLLERR; diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c index ce8ffb595a46..df7cab870be5 100644 --- a/drivers/xen/xen-acpi-processor.c +++ b/drivers/xen/xen-acpi-processor.c @@ -3,7 +3,8 @@ * Copyright 2012 by Oracle Inc * Author: Konrad Rzeszutek Wilk * - * This code borrows ideas from https://lkml.org/lkml/2011/11/30/249 + * This code borrows ideas from + * https://lore.kernel.org/lkml/1322673664-14642-6-git-send-email-konrad.wilk@oracle.com * so many thanks go to Kevin Tian * and Yu Ke . */ diff --git a/drivers/xen/xen-front-pgdir-shbuf.c b/drivers/xen/xen-front-pgdir-shbuf.c index 48a658dc7ccf..81b6e13fa5ec 100644 --- a/drivers/xen/xen-front-pgdir-shbuf.c +++ b/drivers/xen/xen-front-pgdir-shbuf.c @@ -305,11 +305,18 @@ static int backend_map(struct xen_front_pgdir_shbuf *buf) /* Save handles even if error, so we can unmap. */ for (cur_page = 0; cur_page < buf->num_pages; cur_page++) { - buf->backend_map_handles[cur_page] = map_ops[cur_page].handle; - if (unlikely(map_ops[cur_page].status != GNTST_okay)) + if (likely(map_ops[cur_page].status == GNTST_okay)) { + buf->backend_map_handles[cur_page] = + map_ops[cur_page].handle; + } else { + buf->backend_map_handles[cur_page] = + INVALID_GRANT_HANDLE; + if (!ret) + ret = -ENXIO; dev_err(&buf->xb_dev->dev, "Failed to map page %d: %d\n", cur_page, map_ops[cur_page].status); + } } if (ret) { diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 8a75092bb148..97f0d234482d 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -206,6 +206,65 @@ void xenbus_otherend_changed(struct xenbus_watch *watch, } EXPORT_SYMBOL_GPL(xenbus_otherend_changed); +#define XENBUS_SHOW_STAT(name) \ +static ssize_t show_##name(struct device *_dev, \ + struct device_attribute *attr, \ + char *buf) \ +{ \ + struct xenbus_device *dev = to_xenbus_device(_dev); \ + \ + return sprintf(buf, "%d\n", atomic_read(&dev->name)); \ +} \ +static DEVICE_ATTR(name, 0444, show_##name, NULL) + +XENBUS_SHOW_STAT(event_channels); +XENBUS_SHOW_STAT(events); +XENBUS_SHOW_STAT(spurious_events); +XENBUS_SHOW_STAT(jiffies_eoi_delayed); + +static ssize_t show_spurious_threshold(struct device *_dev, + struct device_attribute *attr, + char *buf) +{ + struct xenbus_device *dev = to_xenbus_device(_dev); + + return sprintf(buf, "%d\n", dev->spurious_threshold); +} + +static ssize_t set_spurious_threshold(struct device *_dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct xenbus_device *dev = to_xenbus_device(_dev); + unsigned int val; + ssize_t ret; + + ret = kstrtouint(buf, 0, &val); + if (ret) + return ret; + + dev->spurious_threshold = val; + + return count; +} + +static DEVICE_ATTR(spurious_threshold, 0644, show_spurious_threshold, + set_spurious_threshold); + +static struct attribute *xenbus_attrs[] = { + &dev_attr_event_channels.attr, + &dev_attr_events.attr, + &dev_attr_spurious_events.attr, + &dev_attr_jiffies_eoi_delayed.attr, + &dev_attr_spurious_threshold.attr, + NULL +}; + +static const struct attribute_group xenbus_group = { + .name = "xenbus", + .attrs = xenbus_attrs, +}; + int xenbus_dev_probe(struct device *_dev) { struct xenbus_device *dev = to_xenbus_device(_dev); @@ -253,6 +312,11 @@ int xenbus_dev_probe(struct device *_dev) return err; } + dev->spurious_threshold = 1; + if (sysfs_create_group(&dev->dev.kobj, &xenbus_group)) + dev_warn(&dev->dev, "sysfs_create_group on %s failed.\n", + dev->nodename); + return 0; fail_put: module_put(drv->driver.owner); @@ -269,6 +333,8 @@ int xenbus_dev_remove(struct device *_dev) DPRINTK("%s", dev->nodename); + sysfs_remove_group(&dev->dev.kobj, &xenbus_group); + free_otherend_watch(dev); if (drv->remove) { diff --git a/fs/coredump.c b/fs/coredump.c index ae778937a1ff..1c0fdc1aa70b 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -897,10 +897,10 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start, */ page = get_dump_page(addr); if (page) { - void *kaddr = kmap(page); + void *kaddr = kmap_local_page(page); stop = !dump_emit(cprm, kaddr, PAGE_SIZE); - kunmap(page); + kunmap_local(kaddr); put_page(page); } else { stop = !dump_skip(cprm, PAGE_SIZE); diff --git a/fs/ext4/.kunitconfig b/fs/ext4/.kunitconfig new file mode 100644 index 000000000000..bf51da7cd9fc --- /dev/null +++ b/fs/ext4/.kunitconfig @@ -0,0 +1,3 @@ +CONFIG_KUNIT=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_KUNIT_TESTS=y diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 619dd35ddd48..86699c8cab28 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -103,8 +103,7 @@ config EXT4_DEBUG config EXT4_KUNIT_TESTS tristate "KUnit tests for ext4" if !KUNIT_ALL_TESTS - select EXT4_FS - depends on KUNIT + depends on EXT4_FS && KUNIT default KUNIT_ALL_TESTS help This builds the ext4 KUnit tests. diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 3960b7ec3ab7..77c7c8a54da7 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4382,8 +4382,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, { struct inode *inode = file_inode(file); handle_t *handle; - int ret = 0; - int ret2 = 0, ret3 = 0; + int ret, ret2 = 0, ret3 = 0; int retries = 0; int depth = 0; struct ext4_map_blocks map; @@ -4408,7 +4407,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, depth = ext_depth(inode); retry: - while (ret >= 0 && len) { + while (len) { /* * Recalculate credits when extent tree depth changes. */ @@ -4430,9 +4429,13 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, inode->i_ino, map.m_lblk, map.m_len, ret); ext4_mark_inode_dirty(handle, inode); - ret2 = ext4_journal_stop(handle); + ext4_journal_stop(handle); break; } + /* + * allow a full retry cycle for any remaining allocations + */ + retries = 0; map.m_lblk += ret; map.m_len = len = len - ret; epos = (loff_t)map.m_lblk << inode->i_blkbits; @@ -4450,11 +4453,8 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, if (unlikely(ret2)) break; } - if (ret == -ENOSPC && - ext4_should_retry_alloc(inode->i_sb, &retries)) { - ret = 0; + if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; - } return ret > 0 ? ret2 : ret; } diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 6e8208acfc62..6c4f19b0a556 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -915,13 +915,11 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal) struct super_block *sb = (struct super_block *)(journal->j_private); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *ei; - struct list_head *pos; int ret = 0; spin_lock(&sbi->s_fc_lock); 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); + list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING); while (atomic_read(&ei->i_fc_updates)) { DEFINE_WAIT(wait); @@ -978,17 +976,15 @@ __releases(&sbi->s_fc_lock) { struct super_block *sb = (struct super_block *)(journal->j_private); struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_fc_dentry_update *fc_dentry; + struct ext4_fc_dentry_update *fc_dentry, *fc_dentry_n; struct inode *inode; - struct list_head *pos, *n, *fcd_pos, *fcd_n; - struct ext4_inode_info *ei; + struct ext4_inode_info *ei, *ei_n; int ret; if (list_empty(&sbi->s_fc_dentry_q[FC_Q_MAIN])) return 0; - list_for_each_safe(fcd_pos, fcd_n, &sbi->s_fc_dentry_q[FC_Q_MAIN]) { - fc_dentry = list_entry(fcd_pos, struct ext4_fc_dentry_update, - fcd_list); + list_for_each_entry_safe(fc_dentry, fc_dentry_n, + &sbi->s_fc_dentry_q[FC_Q_MAIN], fcd_list) { if (fc_dentry->fcd_op != EXT4_FC_TAG_CREAT) { spin_unlock(&sbi->s_fc_lock); if (!ext4_fc_add_dentry_tlv( @@ -1004,8 +1000,8 @@ __releases(&sbi->s_fc_lock) } inode = NULL; - list_for_each_safe(pos, n, &sbi->s_fc_q[FC_Q_MAIN]) { - ei = list_entry(pos, struct ext4_inode_info, i_fc_list); + list_for_each_entry_safe(ei, ei_n, &sbi->s_fc_q[FC_Q_MAIN], + i_fc_list) { if (ei->vfs_inode.i_ino == fc_dentry->fcd_ino) { inode = &ei->vfs_inode; break; @@ -1057,7 +1053,6 @@ static int ext4_fc_perform_commit(journal_t *journal) struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *iter; struct ext4_fc_head head; - struct list_head *pos; struct inode *inode; struct blk_plug plug; int ret = 0; @@ -1099,8 +1094,7 @@ static int ext4_fc_perform_commit(journal_t *journal) goto out; } - list_for_each(pos, &sbi->s_fc_q[FC_Q_MAIN]) { - iter = list_entry(pos, struct ext4_inode_info, i_fc_list); + list_for_each_entry(iter, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { inode = &iter->vfs_inode; if (!ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) continue; @@ -1226,9 +1220,8 @@ static void ext4_fc_cleanup(journal_t *journal, int full) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_inode_info *iter; + struct ext4_inode_info *iter, *iter_n; struct ext4_fc_dentry_update *fc_dentry; - struct list_head *pos, *n; if (full && sbi->s_fc_bh) sbi->s_fc_bh = NULL; @@ -1236,8 +1229,8 @@ static void ext4_fc_cleanup(journal_t *journal, int full) jbd2_fc_release_bufs(journal); spin_lock(&sbi->s_fc_lock); - list_for_each_safe(pos, n, &sbi->s_fc_q[FC_Q_MAIN]) { - iter = list_entry(pos, struct ext4_inode_info, i_fc_list); + list_for_each_entry_safe(iter, iter_n, &sbi->s_fc_q[FC_Q_MAIN], + i_fc_list) { list_del_init(&iter->i_fc_list); ext4_clear_inode_state(&iter->vfs_inode, EXT4_STATE_FC_COMMITTING); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 47e28b3927ed..8d4339b85b98 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -738,6 +738,29 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir, (space/bcount)*100/blocksize); return (struct stats) { names, space, bcount}; } + +/* + * Linear search cross check + */ +static inline void htree_rep_invariant_check(struct dx_entry *at, + struct dx_entry *target, + u32 hash, unsigned int n) +{ + while (n--) { + dxtrace(printk(KERN_CONT ",")); + if (dx_get_hash(++at) > hash) { + at--; + break; + } + } + ASSERT(at == target - 1); +} +#else /* DX_DEBUG */ +static inline void htree_rep_invariant_check(struct dx_entry *at, + struct dx_entry *target, + u32 hash, unsigned int n) +{ +} #endif /* DX_DEBUG */ /* @@ -850,20 +873,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, p = m + 1; } - if (0) { // linear search cross check - unsigned n = count - 1; - at = entries; - while (n--) - { - dxtrace(printk(KERN_CONT ",")); - if (dx_get_hash(++at) > hash) - { - at--; - break; - } - } - ASSERT(at == p - 1); - } + htree_rep_invariant_check(entries, p, hash, count - 1); at = p - 1; dxtrace(printk(KERN_CONT " %x->%u\n", @@ -2509,11 +2519,10 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, (frame - 1)->bh); if (err) goto journal_error; - if (restart) { - err = ext4_handle_dirty_dx_node(handle, dir, - frame->bh); + err = ext4_handle_dirty_dx_node(handle, dir, + frame->bh); + if (err) goto journal_error; - } } else { struct dx_root *dxroot; memcpy((char *) entries2, (char *) entries, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 36c9faf2c8cf..312c7c03f401 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -59,7 +59,7 @@ #include static struct ext4_lazy_init *ext4_li_info; -static struct mutex ext4_li_mtx; +static DEFINE_MUTEX(ext4_li_mtx); static struct ratelimit_state ext4_mount_msg_ratelimit; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, @@ -4869,7 +4869,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) set_task_ioprio(sbi->s_journal->j_task, journal_ioprio); - sbi->s_journal->j_commit_callback = ext4_journal_commit_callback; sbi->s_journal->j_submit_inode_data_buffers = ext4_journal_submit_inode_data_buffers; sbi->s_journal->j_finish_inode_data_buffers = @@ -4981,6 +4980,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount5; } + /* + * We can only set up the journal commit callback once + * mballoc is initialized + */ + if (sbi->s_journal) + sbi->s_journal->j_commit_callback = + ext4_journal_commit_callback; + block = ext4_count_free_clusters(sb); ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, block)); @@ -6661,7 +6668,6 @@ static int __init ext4_init_fs(void) ratelimit_state_init(&ext4_mount_msg_ratelimit, 30 * HZ, 64); ext4_li_info = NULL; - mutex_init(&ext4_li_mtx); /* Build-time check for flags consistency */ ext4_check_flag_values(); diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c index 107ee80c3568..dab1b02eba5b 100644 --- a/fs/iomap/seek.c +++ b/fs/iomap/seek.c @@ -10,122 +10,17 @@ #include #include -/* - * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff. - * Returns true if found and updates @lastoff to the offset in file. - */ -static bool -page_seek_hole_data(struct inode *inode, struct page *page, loff_t *lastoff, - int whence) -{ - const struct address_space_operations *ops = inode->i_mapping->a_ops; - unsigned int bsize = i_blocksize(inode), off; - bool seek_data = whence == SEEK_DATA; - loff_t poff = page_offset(page); - - if (WARN_ON_ONCE(*lastoff >= poff + PAGE_SIZE)) - return false; - - if (*lastoff < poff) { - /* - * Last offset smaller than the start of the page means we found - * a hole: - */ - if (whence == SEEK_HOLE) - return true; - *lastoff = poff; - } - - /* - * Just check the page unless we can and should check block ranges: - */ - if (bsize == PAGE_SIZE || !ops->is_partially_uptodate) - return PageUptodate(page) == seek_data; - - lock_page(page); - if (unlikely(page->mapping != inode->i_mapping)) - goto out_unlock_not_found; - - for (off = 0; off < PAGE_SIZE; off += bsize) { - if (offset_in_page(*lastoff) >= off + bsize) - continue; - if (ops->is_partially_uptodate(page, off, bsize) == seek_data) { - unlock_page(page); - return true; - } - *lastoff = poff + off + bsize; - } - -out_unlock_not_found: - unlock_page(page); - return false; -} - -/* - * Seek for SEEK_DATA / SEEK_HOLE in the page cache. - * - * Within unwritten extents, the page cache determines which parts are holes - * and which are data: uptodate buffer heads count as data; everything else - * counts as a hole. - * - * Returns the resulting offset on successs, and -ENOENT otherwise. - */ static loff_t -page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length, - int whence) -{ - pgoff_t index = offset >> PAGE_SHIFT; - pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE); - loff_t lastoff = offset; - struct pagevec pvec; - - if (length <= 0) - return -ENOENT; - - pagevec_init(&pvec); - - do { - unsigned nr_pages, i; - - nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, &index, - end - 1); - if (nr_pages == 0) - break; - - for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; - - if (page_seek_hole_data(inode, page, &lastoff, whence)) - goto check_range; - lastoff = page_offset(page) + PAGE_SIZE; - } - pagevec_release(&pvec); - } while (index < end); - - /* When no page at lastoff and we are not done, we found a hole. */ - if (whence != SEEK_HOLE) - goto not_found; - -check_range: - if (lastoff < offset + length) - goto out; -not_found: - lastoff = -ENOENT; -out: - pagevec_release(&pvec); - return lastoff; -} - - -static loff_t -iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length, +iomap_seek_hole_actor(struct inode *inode, loff_t start, loff_t length, void *data, struct iomap *iomap, struct iomap *srcmap) { + loff_t offset = start; + switch (iomap->type) { case IOMAP_UNWRITTEN: - offset = page_cache_seek_hole_data(inode, offset, length, - SEEK_HOLE); - if (offset < 0) + offset = mapping_seek_hole_data(inode->i_mapping, start, + start + length, SEEK_HOLE); + if (offset == start + length) return length; fallthrough; case IOMAP_HOLE: @@ -164,15 +59,17 @@ iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops) EXPORT_SYMBOL_GPL(iomap_seek_hole); static loff_t -iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length, +iomap_seek_data_actor(struct inode *inode, loff_t start, loff_t length, void *data, struct iomap *iomap, struct iomap *srcmap) { + loff_t offset = start; + switch (iomap->type) { case IOMAP_HOLE: return length; case IOMAP_UNWRITTEN: - offset = page_cache_seek_hole_data(inode, offset, length, - SEEK_DATA); + offset = mapping_seek_hole_data(inode->i_mapping, start, + start + length, SEEK_DATA); if (offset < 0) return length; fallthrough; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 63940a7a70be..16ad5050e046 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -89,7 +89,7 @@ nfs_file_release(struct inode *inode, struct file *filp) EXPORT_SYMBOL_GPL(nfs_file_release); /** - * nfs_revalidate_size - Revalidate the file size + * nfs_revalidate_file_size - Revalidate the file size * @inode: pointer to inode struct * @filp: pointer to struct file * @@ -606,8 +606,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - unsigned long written = 0; - ssize_t result; + unsigned int mntflags = NFS_SERVER(inode)->flags; + ssize_t result, written; errseq_t since; int error; @@ -626,13 +626,13 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) /* * O_APPEND implies that we must revalidate the file length. */ - if (iocb->ki_flags & IOCB_APPEND) { + if (iocb->ki_flags & IOCB_APPEND || iocb->ki_pos > i_size_read(inode)) { result = nfs_revalidate_file_size(inode, file); if (result) goto out; } - if (iocb->ki_pos > i_size_read(inode)) - nfs_revalidate_mapping(inode, file->f_mapping); + + nfs_clear_invalid_mapping(file->f_mapping); since = filemap_sample_wb_err(file->f_mapping); nfs_start_io_write(inode); @@ -648,6 +648,21 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) written = result; iocb->ki_pos += written; + + if (mntflags & NFS_MOUNT_WRITE_EAGER) { + result = filemap_fdatawrite_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); + if (result < 0) + goto out; + } + if (mntflags & NFS_MOUNT_WRITE_WAIT) { + result = filemap_fdatawait_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); + if (result < 0) + goto out; + } result = generic_write_sync(iocb, written); if (result < 0) goto out; diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index 06894bcdea2d..971a9251c1d9 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -82,6 +82,7 @@ enum nfs_param { Opt_v, Opt_vers, Opt_wsize, + Opt_write, }; enum { @@ -113,6 +114,19 @@ static const struct constant_table nfs_param_enums_lookupcache[] = { {} }; +enum { + Opt_write_lazy, + Opt_write_eager, + Opt_write_wait, +}; + +static const struct constant_table nfs_param_enums_write[] = { + { "lazy", Opt_write_lazy }, + { "eager", Opt_write_eager }, + { "wait", Opt_write_wait }, + {} +}; + static const struct fs_parameter_spec nfs_fs_parameters[] = { fsparam_flag_no("ac", Opt_ac), fsparam_u32 ("acdirmax", Opt_acdirmax), @@ -171,6 +185,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = { fsparam_flag ("v4.1", Opt_v), fsparam_flag ("v4.2", Opt_v), fsparam_string("vers", Opt_vers), + fsparam_enum ("write", Opt_write, nfs_param_enums_write), fsparam_u32 ("wsize", Opt_wsize), {} }; @@ -770,6 +785,24 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, goto out_invalid_value; } break; + case Opt_write: + switch (result.uint_32) { + case Opt_write_lazy: + ctx->flags &= + ~(NFS_MOUNT_WRITE_EAGER | NFS_MOUNT_WRITE_WAIT); + break; + case Opt_write_eager: + ctx->flags |= NFS_MOUNT_WRITE_EAGER; + ctx->flags &= ~NFS_MOUNT_WRITE_WAIT; + break; + case Opt_write_wait: + ctx->flags |= + NFS_MOUNT_WRITE_EAGER | NFS_MOUNT_WRITE_WAIT; + break; + default: + goto out_invalid_value; + } + break; /* * Special options @@ -1479,6 +1512,8 @@ static int nfs_init_fs_context(struct fs_context *fc) ctx->selected_flavor = RPC_AUTH_MAXFLAVOR; ctx->minorversion = 0; ctx->need_mount = true; + + fc->s_iflags |= SB_I_STABLE_WRITES; } fc->fs_private = ctx; fc->ops = &nfs_fs_context_ops; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index a60df88efc40..c4c021c6ebbd 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -390,10 +390,6 @@ static void nfs_readpage_from_fscache_complete(struct page *page, if (!error) { SetPageUptodate(page); unlock_page(page); - } else { - error = nfs_readpage_async(context, page->mapping->host, page); - if (error) - unlock_page(page); } } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 447e95974386..749bbea14d99 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -195,6 +195,18 @@ bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags) } EXPORT_SYMBOL_GPL(nfs_check_cache_invalid); +#ifdef CONFIG_NFS_V4_2 +static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi) +{ + return nfsi->xattr_cache != NULL; +} +#else +static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi) +{ + return false; +} +#endif + static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) { struct nfs_inode *nfsi = NFS_I(inode); @@ -209,6 +221,8 @@ static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) | NFS_INO_INVALID_XATTR); } + if (!nfs_has_xattr_cache(nfsi)) + flags &= ~NFS_INO_INVALID_XATTR; if (inode->i_mapping->nrpages == 0) flags &= ~(NFS_INO_INVALID_DATA|NFS_INO_DATA_INVAL_DEFER); nfsi->cache_validity |= flags; @@ -1258,6 +1272,63 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map return 0; } +/** + * nfs_clear_invalid_mapping - Conditionally clear a mapping + * @mapping: pointer to mapping + * + * If the NFS_INO_INVALID_DATA inode flag is set, clear the mapping. + */ +int nfs_clear_invalid_mapping(struct address_space *mapping) +{ + struct inode *inode = mapping->host; + struct nfs_inode *nfsi = NFS_I(inode); + unsigned long *bitlock = &nfsi->flags; + int ret = 0; + + /* + * We must clear NFS_INO_INVALID_DATA first to ensure that + * invalidations that come in while we're shooting down the mappings + * are respected. But, that leaves a race window where one revalidator + * can clear the flag, and then another checks it before the mapping + * gets invalidated. Fix that by serializing access to this part of + * the function. + * + * At the same time, we need to allow other tasks to see whether we + * might be in the middle of invalidating the pages, so we only set + * the bit lock here if it looks like we're going to be doing that. + */ + for (;;) { + ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING, + nfs_wait_bit_killable, TASK_KILLABLE); + if (ret) + goto out; + spin_lock(&inode->i_lock); + if (test_bit(NFS_INO_INVALIDATING, bitlock)) { + spin_unlock(&inode->i_lock); + continue; + } + if (nfsi->cache_validity & NFS_INO_INVALID_DATA) + break; + spin_unlock(&inode->i_lock); + goto out; + } + + set_bit(NFS_INO_INVALIDATING, bitlock); + smp_wmb(); + nfsi->cache_validity &= + ~(NFS_INO_INVALID_DATA | NFS_INO_DATA_INVAL_DEFER); + spin_unlock(&inode->i_lock); + trace_nfs_invalidate_mapping_enter(inode); + ret = nfs_invalidate_mapping(inode, mapping); + trace_nfs_invalidate_mapping_exit(inode, ret); + + clear_bit_unlock(NFS_INO_INVALIDATING, bitlock); + smp_mb__after_atomic(); + wake_up_bit(bitlock, NFS_INO_INVALIDATING); +out: + return ret; +} + bool nfs_mapping_need_revalidate_inode(struct inode *inode) { return nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE) || @@ -1290,65 +1361,19 @@ int nfs_revalidate_mapping_rcu(struct inode *inode) * @inode: pointer to host inode * @mapping: pointer to mapping */ -int nfs_revalidate_mapping(struct inode *inode, - struct address_space *mapping) +int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) { - struct nfs_inode *nfsi = NFS_I(inode); - unsigned long *bitlock = &nfsi->flags; - int ret = 0; - /* swapfiles are not supposed to be shared. */ if (IS_SWAPFILE(inode)) - goto out; + return 0; if (nfs_mapping_need_revalidate_inode(inode)) { - ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); + int ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); if (ret < 0) - goto out; + return ret; } - /* - * We must clear NFS_INO_INVALID_DATA first to ensure that - * invalidations that come in while we're shooting down the mappings - * are respected. But, that leaves a race window where one revalidator - * can clear the flag, and then another checks it before the mapping - * gets invalidated. Fix that by serializing access to this part of - * the function. - * - * At the same time, we need to allow other tasks to see whether we - * might be in the middle of invalidating the pages, so we only set - * the bit lock here if it looks like we're going to be doing that. - */ - for (;;) { - ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING, - nfs_wait_bit_killable, TASK_KILLABLE); - if (ret) - goto out; - spin_lock(&inode->i_lock); - if (test_bit(NFS_INO_INVALIDATING, bitlock)) { - spin_unlock(&inode->i_lock); - continue; - } - if (nfsi->cache_validity & NFS_INO_INVALID_DATA) - break; - spin_unlock(&inode->i_lock); - goto out; - } - - set_bit(NFS_INO_INVALIDATING, bitlock); - smp_wmb(); - nfsi->cache_validity &= ~(NFS_INO_INVALID_DATA| - NFS_INO_DATA_INVAL_DEFER); - spin_unlock(&inode->i_lock); - trace_nfs_invalidate_mapping_enter(inode); - ret = nfs_invalidate_mapping(inode, mapping); - trace_nfs_invalidate_mapping_exit(inode, ret); - - clear_bit_unlock(NFS_INO_INVALIDATING, bitlock); - smp_mb__after_atomic(); - wake_up_bit(bitlock, NFS_INO_INVALIDATING); -out: - return ret; + return nfs_clear_invalid_mapping(mapping); } static bool nfs_file_has_writers(struct nfs_inode *nfsi) diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 5604e807fc01..bb386a691e69 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -111,6 +111,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type) fallthrough; case -ENOTSUPP: status = -EOPNOTSUPP; + goto getout; default: goto getout; } diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 86acffe7335c..889a9f4c0310 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -609,6 +609,7 @@ int nfs40_walk_client_list(struct nfs_client *new, * changed. Schedule recovery! */ nfs4_schedule_path_down_recovery(pos); + goto out; default: goto out; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a07530cf673d..74bc5120013d 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -71,10 +71,6 @@ #include "nfs4trace.h" -#ifdef CONFIG_NFS_V4_2 -#include "nfs42.h" -#endif /* CONFIG_NFS_V4_2 */ - #define NFSDBG_FACILITY NFSDBG_PROC #define NFS4_BITMASK_SZ 3 @@ -2231,6 +2227,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct default: printk(KERN_ERR "NFS: %s: unhandled error " "%d.\n", __func__, err); + fallthrough; case 0: case -ENOENT: case -EAGAIN: @@ -5438,15 +5435,16 @@ static void nfs4_bitmask_adjust(__u32 *bitmask, struct inode *inode, if (cache_validity & NFS_INO_INVALID_ATIME) bitmask[1] |= FATTR4_WORD1_TIME_ACCESS; - if (cache_validity & NFS_INO_INVALID_ACCESS) - bitmask[0] |= FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | - FATTR4_WORD1_OWNER_GROUP; - if (cache_validity & NFS_INO_INVALID_ACL) - bitmask[0] |= FATTR4_WORD0_ACL; - if (cache_validity & NFS_INO_INVALID_LABEL) + if (cache_validity & NFS_INO_INVALID_OTHER) + bitmask[1] |= FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | + FATTR4_WORD1_OWNER_GROUP | + FATTR4_WORD1_NUMLINKS; + if (label && label->len && cache_validity & NFS_INO_INVALID_LABEL) bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL; - if (cache_validity & NFS_INO_INVALID_CTIME) + if (cache_validity & NFS_INO_INVALID_CHANGE) bitmask[0] |= FATTR4_WORD0_CHANGE; + if (cache_validity & NFS_INO_INVALID_CTIME) + bitmask[1] |= FATTR4_WORD1_TIME_METADATA; if (cache_validity & NFS_INO_INVALID_MTIME) bitmask[1] |= FATTR4_WORD1_TIME_MODIFY; if (cache_validity & NFS_INO_INVALID_SIZE) @@ -9708,6 +9706,7 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata) case -NFS4ERR_BADLAYOUT: /* no layout */ case -NFS4ERR_GRACE: /* loca_recalim always false */ task->tk_status = 0; + break; case 0: break; default: diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 4bf10792cb5b..3a51351bdc6a 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1125,6 +1125,7 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid) " sequence-id error on an" " unconfirmed sequence %p!\n", seqid->sequence); + return; case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_BAD_STATEID: diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index af64b4e6fd1f..102b66e0bdef 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2875,6 +2875,7 @@ pnfs_do_write(struct nfs_pageio_descriptor *desc, switch (trypnfs) { case PNFS_NOT_ATTEMPTED: pnfs_write_through_mds(desc, hdr); + break; case PNFS_ATTEMPTED: break; case PNFS_TRY_AGAIN: @@ -3019,6 +3020,7 @@ pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) switch (trypnfs) { case PNFS_NOT_ATTEMPTED: pnfs_read_through_mds(desc, hdr); + break; case PNFS_ATTEMPTED: break; case PNFS_TRY_AGAIN: diff --git a/fs/nfs/read.c b/fs/nfs/read.c index eb854f1f86e2..d2b6dce1f99f 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -74,6 +74,24 @@ void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, } EXPORT_SYMBOL_GPL(nfs_pageio_init_read); +static void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio, + struct inode *inode) +{ + struct nfs_pgio_mirror *pgm; + unsigned long npages; + + nfs_pageio_complete(pgio); + + /* It doesn't make sense to do mirrored reads! */ + WARN_ON_ONCE(pgio->pg_mirror_count != 1); + + pgm = &pgio->pg_mirrors[0]; + NFS_I(inode)->read_io += pgm->pg_bytes_written; + npages = (pgm->pg_bytes_written + PAGE_SIZE - 1) >> PAGE_SHIFT; + nfs_add_stats(inode, NFSIOS_READPAGES, npages); +} + + void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) { struct nfs_pgio_mirror *mirror; @@ -114,41 +132,10 @@ static void nfs_readpage_release(struct nfs_page *req, int error) nfs_release_request(req); } -int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, - struct page *page) -{ - struct nfs_page *new; - unsigned int len; +struct nfs_readdesc { struct nfs_pageio_descriptor pgio; - struct nfs_pgio_mirror *pgm; - - len = nfs_page_length(page); - if (len == 0) - return nfs_return_empty_page(page); - new = nfs_create_request(ctx, page, 0, len); - if (IS_ERR(new)) { - unlock_page(page); - return PTR_ERR(new); - } - if (len < PAGE_SIZE) - zero_user_segment(page, len, PAGE_SIZE); - - nfs_pageio_init_read(&pgio, inode, false, - &nfs_async_read_completion_ops); - if (!nfs_pageio_add_request(&pgio, new)) { - nfs_list_remove_request(new); - nfs_readpage_release(new, pgio.pg_error); - } - nfs_pageio_complete(&pgio); - - /* It doesn't make sense to do mirrored reads! */ - WARN_ON_ONCE(pgio.pg_mirror_count != 1); - - pgm = &pgio.pg_mirrors[0]; - NFS_I(inode)->read_io += pgm->pg_bytes_written; - - return pgio.pg_error < 0 ? pgio.pg_error : 0; -} + struct nfs_open_context *ctx; +}; static void nfs_page_group_set_uptodate(struct nfs_page *req) { @@ -171,8 +158,7 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr) if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) { /* note: regions of the page not covered by a - * request are zeroed in nfs_readpage_async / - * readpage_async_filler */ + * request are zeroed in readpage_async_filler */ if (bytes > hdr->good_bytes) { /* nothing in this request was good, so zero * the full extent of the request */ @@ -304,78 +290,10 @@ static void nfs_readpage_result(struct rpc_task *task, nfs_readpage_retry(task, hdr); } -/* - * Read a page over NFS. - * We read the page synchronously in the following case: - * - The error flag is set for this page. This happens only when a - * previous async read operation failed. - */ -int nfs_readpage(struct file *file, struct page *page) -{ - struct nfs_open_context *ctx; - struct inode *inode = page_file_mapping(page)->host; - int error; - - dprintk("NFS: nfs_readpage (%p %ld@%lu)\n", - page, PAGE_SIZE, page_index(page)); - nfs_inc_stats(inode, NFSIOS_VFSREADPAGE); - nfs_add_stats(inode, NFSIOS_READPAGES, 1); - - /* - * Try to flush any pending writes to the file.. - * - * NOTE! Because we own the page lock, there cannot - * be any new pending writes generated at this point - * for this page (other pages can be written to). - */ - error = nfs_wb_page(inode, page); - if (error) - goto out_unlock; - if (PageUptodate(page)) - goto out_unlock; - - error = -ESTALE; - if (NFS_STALE(inode)) - goto out_unlock; - - if (file == NULL) { - error = -EBADF; - ctx = nfs_find_open_context(inode, NULL, FMODE_READ); - if (ctx == NULL) - goto out_unlock; - } else - ctx = get_nfs_open_context(nfs_file_open_context(file)); - - if (!IS_SYNC(inode)) { - error = nfs_readpage_from_fscache(ctx, inode, page); - if (error == 0) - goto out; - } - - xchg(&ctx->error, 0); - error = nfs_readpage_async(ctx, inode, page); - if (!error) { - error = wait_on_page_locked_killable(page); - if (!PageUptodate(page) && !error) - error = xchg(&ctx->error, 0); - } -out: - put_nfs_open_context(ctx); - return error; -out_unlock: - unlock_page(page); - return error; -} - -struct nfs_readdesc { - struct nfs_pageio_descriptor *pgio; - struct nfs_open_context *ctx; -}; - static int readpage_async_filler(void *data, struct page *page) { - struct nfs_readdesc *desc = (struct nfs_readdesc *)data; + struct nfs_readdesc *desc = data; struct nfs_page *new; unsigned int len; int error; @@ -390,9 +308,9 @@ readpage_async_filler(void *data, struct page *page) if (len < PAGE_SIZE) zero_user_segment(page, len, PAGE_SIZE); - if (!nfs_pageio_add_request(desc->pgio, new)) { + if (!nfs_pageio_add_request(&desc->pgio, new)) { nfs_list_remove_request(new); - error = desc->pgio->pg_error; + error = desc->pgio.pg_error; nfs_readpage_release(new, error); goto out; } @@ -404,17 +322,82 @@ readpage_async_filler(void *data, struct page *page) return error; } -int nfs_readpages(struct file *filp, struct address_space *mapping, +/* + * Read a page over NFS. + * We read the page synchronously in the following case: + * - The error flag is set for this page. This happens only when a + * previous async read operation failed. + */ +int nfs_readpage(struct file *file, struct page *page) +{ + struct nfs_readdesc desc; + struct inode *inode = page_file_mapping(page)->host; + int ret; + + dprintk("NFS: nfs_readpage (%p %ld@%lu)\n", + page, PAGE_SIZE, page_index(page)); + nfs_inc_stats(inode, NFSIOS_VFSREADPAGE); + + /* + * Try to flush any pending writes to the file.. + * + * NOTE! Because we own the page lock, there cannot + * be any new pending writes generated at this point + * for this page (other pages can be written to). + */ + ret = nfs_wb_page(inode, page); + if (ret) + goto out_unlock; + if (PageUptodate(page)) + goto out_unlock; + + ret = -ESTALE; + if (NFS_STALE(inode)) + goto out_unlock; + + if (file == NULL) { + ret = -EBADF; + desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ); + if (desc.ctx == NULL) + goto out_unlock; + } else + desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); + + if (!IS_SYNC(inode)) { + ret = nfs_readpage_from_fscache(desc.ctx, inode, page); + if (ret == 0) + goto out; + } + + xchg(&desc.ctx->error, 0); + nfs_pageio_init_read(&desc.pgio, inode, false, + &nfs_async_read_completion_ops); + + ret = readpage_async_filler(&desc, page); + + if (!ret) + nfs_pageio_complete_read(&desc.pgio, inode); + + ret = desc.pgio.pg_error < 0 ? desc.pgio.pg_error : 0; + if (!ret) { + ret = wait_on_page_locked_killable(page); + if (!PageUptodate(page) && !ret) + ret = xchg(&desc.ctx->error, 0); + } +out: + put_nfs_open_context(desc.ctx); + return ret; +out_unlock: + unlock_page(page); + return ret; +} + +int nfs_readpages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { - struct nfs_pageio_descriptor pgio; - struct nfs_pgio_mirror *pgm; - struct nfs_readdesc desc = { - .pgio = &pgio, - }; + struct nfs_readdesc desc; struct inode *inode = mapping->host; - unsigned long npages; - int ret = -ESTALE; + int ret; dprintk("NFS: nfs_readpages (%s/%Lu %d)\n", inode->i_sb->s_id, @@ -422,15 +405,17 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, nr_pages); nfs_inc_stats(inode, NFSIOS_VFSREADPAGES); + ret = -ESTALE; if (NFS_STALE(inode)) goto out; - if (filp == NULL) { + if (file == NULL) { + ret = -EBADF; desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ); if (desc.ctx == NULL) - return -EBADF; + goto out; } else - desc.ctx = get_nfs_open_context(nfs_file_open_context(filp)); + desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); /* attempt to read as many of the pages as possible from the cache * - this returns -ENOBUFS immediately if the cookie is negative @@ -440,20 +425,13 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) goto read_complete; /* all pages were read */ - nfs_pageio_init_read(&pgio, inode, false, + nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); - nfs_pageio_complete(&pgio); - /* It doesn't make sense to do mirrored reads! */ - WARN_ON_ONCE(pgio.pg_mirror_count != 1); + nfs_pageio_complete_read(&desc.pgio, inode); - pgm = &pgio.pg_mirrors[0]; - NFS_I(inode)->read_io += pgm->pg_bytes_written; - npages = (pgm->pg_bytes_written + PAGE_SIZE - 1) >> - PAGE_SHIFT; - nfs_add_stats(inode, NFSIOS_READPAGES, npages); read_complete: put_nfs_open_context(desc.ctx); out: diff --git a/fs/nfs/super.c b/fs/nfs/super.c index c7a924580eec..94885c6f8f54 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -523,6 +523,13 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, seq_puts(m, ",local_lock=flock"); else seq_puts(m, ",local_lock=posix"); + + if (nfss->flags & NFS_MOUNT_WRITE_EAGER) { + if (nfss->flags & NFS_MOUNT_WRITE_WAIT) + seq_puts(m, ",write=wait"); + else + seq_puts(m, ",write=eager"); + } } /* diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 639c34fec04a..82bdcb982186 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -712,16 +712,23 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; struct nfs_pageio_descriptor pgio; - struct nfs_io_completion *ioc; + struct nfs_io_completion *ioc = NULL; + unsigned int mntflags = NFS_SERVER(inode)->flags; + int priority = 0; int err; nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); - ioc = nfs_io_completion_alloc(GFP_KERNEL); - if (ioc) - nfs_io_completion_init(ioc, nfs_io_completion_commit, inode); + if (!(mntflags & NFS_MOUNT_WRITE_EAGER) || wbc->for_kupdate || + wbc->for_background || wbc->for_sync || wbc->for_reclaim) { + ioc = nfs_io_completion_alloc(GFP_KERNEL); + if (ioc) + nfs_io_completion_init(ioc, nfs_io_completion_commit, + inode); + priority = wb_priority(wbc); + } - nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false, + nfs_pageio_init_write(&pgio, inode, priority, false, &nfs_async_write_completion_ops); pgio.pg_io_completion = ioc; err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio); @@ -1278,19 +1285,21 @@ bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode) * the PageUptodate() flag. In this case, we will need to turn off * write optimisations that depend on the page contents being correct. */ -static bool nfs_write_pageuptodate(struct page *page, struct inode *inode) +static bool nfs_write_pageuptodate(struct page *page, struct inode *inode, + unsigned int pagelen) { struct nfs_inode *nfsi = NFS_I(inode); if (nfs_have_delegated_attributes(inode)) goto out; - if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) + if (nfsi->cache_validity & + (NFS_INO_REVAL_PAGECACHE | NFS_INO_INVALID_SIZE)) return false; smp_rmb(); - if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags)) + if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags) && pagelen != 0) return false; out: - if (nfsi->cache_validity & NFS_INO_INVALID_DATA) + if (nfsi->cache_validity & NFS_INO_INVALID_DATA && pagelen != 0) return false; return PageUptodate(page) != 0; } @@ -1310,7 +1319,8 @@ is_whole_file_wrlock(struct file_lock *fl) * If the file is opened for synchronous writes then we can just skip the rest * of the checks. */ -static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode) +static int nfs_can_extend_write(struct file *file, struct page *page, + struct inode *inode, unsigned int pagelen) { int ret; struct file_lock_context *flctx = inode->i_flctx; @@ -1318,7 +1328,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino if (file->f_flags & O_DSYNC) return 0; - if (!nfs_write_pageuptodate(page, inode)) + if (!nfs_write_pageuptodate(page, inode, pagelen)) return 0; if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) return 1; @@ -1356,6 +1366,7 @@ int nfs_updatepage(struct file *file, struct page *page, struct nfs_open_context *ctx = nfs_file_open_context(file); struct address_space *mapping = page_file_mapping(page); struct inode *inode = mapping->host; + unsigned int pagelen = nfs_page_length(page); int status = 0; nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE); @@ -1366,8 +1377,8 @@ int nfs_updatepage(struct file *file, struct page *page, if (!count) goto out; - if (nfs_can_extend_write(file, page, inode)) { - count = max(count + offset, nfs_page_length(page)); + if (nfs_can_extend_write(file, page, inode, pagelen)) { + count = max(count + offset, pagelen); offset = 0; } diff --git a/fs/proc/base.c b/fs/proc/base.c index 5c9b86b09c14..5d9c52d9d380 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -67,7 +67,6 @@ #include #include #include -#include #include #include #include @@ -387,19 +386,17 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long wchan; - char symname[KSYM_NAME_LEN]; - if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) - goto print0; + if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) + wchan = get_wchan(task); + else + wchan = 0; - wchan = get_wchan(task); - if (wchan && !lookup_symbol_name(wchan, symname)) { - seq_puts(m, symname); - return 0; - } + if (wchan) + seq_printf(m, "%ps", (void *) wchan); + else + seq_putc(m, '0'); -print0: - seq_putc(m, '0'); return 0; } #endif /* CONFIG_KALLSYMS */ diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 656ba24c317d..984e42f8cb11 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -571,7 +571,7 @@ static ssize_t proc_sys_call_handler(struct kiocb *iocb, struct iov_iter *iter, error = -ENOMEM; if (count >= KMALLOC_MAX_SIZE) goto out; - kbuf = kzalloc(count + 1, GFP_KERNEL); + kbuf = kvzalloc(count + 1, GFP_KERNEL); if (!kbuf) goto out; @@ -600,7 +600,7 @@ static ssize_t proc_sys_call_handler(struct kiocb *iocb, struct iov_iter *iter, error = count; out_free_buf: - kfree(kbuf); + kvfree(kbuf); out: sysctl_head_finish(head); diff --git a/include/asm-generic/numa.h b/include/asm-generic/numa.h new file mode 100644 index 000000000000..1a3ad6d29833 --- /dev/null +++ b/include/asm-generic/numa.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_GENERIC_NUMA_H +#define __ASM_GENERIC_NUMA_H + +#ifdef CONFIG_NUMA + +#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2) + +int __node_distance(int from, int to); +#define node_distance(a, b) __node_distance(a, b) + +extern nodemask_t numa_nodes_parsed __initdata; + +extern bool numa_off; + +/* Mappings between node number and cpus on that node. */ +extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; +void numa_clear_node(unsigned int cpu); + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +const struct cpumask *cpumask_of_node(int node); +#else +/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ +static inline const struct cpumask *cpumask_of_node(int node) +{ + if (node == NUMA_NO_NODE) + return cpu_all_mask; + + return node_to_cpumask_map[node]; +} +#endif + +void __init arch_numa_init(void); +int __init numa_add_memblk(int nodeid, u64 start, u64 end); +void __init numa_set_distance(int from, int to, int distance); +void __init numa_free_distance(void); +void __init early_map_cpu_to_node(unsigned int cpu, int nid); +void numa_store_cpu_info(unsigned int cpu); +void numa_add_cpu(unsigned int cpu); +void numa_remove_cpu(unsigned int cpu); + +#else /* CONFIG_NUMA */ + +static inline void numa_store_cpu_info(unsigned int cpu) { } +static inline void numa_add_cpu(unsigned int cpu) { } +static inline void numa_remove_cpu(unsigned int cpu) { } +static inline void arch_numa_init(void) { } +static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { } + +#endif /* CONFIG_NUMA */ + +#endif /* __ASM_GENERIC_NUMA_H */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index c54adce8f6f6..0331d5d49551 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -98,7 +98,7 @@ */ #if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) #define TEXT_MAIN .text .text.[0-9a-zA-Z_]* -#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliteral* .data.$__unnamed_* .data.$Lubsan_* +#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliteral* .data.$__unnamed_* .data.$L* #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]* #define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* .rodata..L* #define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..compoundliteral* @@ -803,8 +803,13 @@ /* DWARF 4 */ \ .debug_types 0 : { *(.debug_types) } \ /* DWARF 5 */ \ + .debug_addr 0 : { *(.debug_addr) } \ + .debug_line_str 0 : { *(.debug_line_str) } \ + .debug_loclists 0 : { *(.debug_loclists) } \ .debug_macro 0 : { *(.debug_macro) } \ - .debug_addr 0 : { *(.debug_addr) } + .debug_names 0 : { *(.debug_names) } \ + .debug_rnglists 0 : { *(.debug_rnglists) } \ + .debug_str_offsets 0 : { *(.debug_str_offsets) } /* Stabs debugging sections. */ #define STABS_DEBUG \ @@ -963,12 +968,13 @@ #endif /* - * Clang's -fsanitize=kernel-address and -fsanitize=thread produce - * unwanted sections (.eh_frame and .init_array.*), but - * CONFIG_CONSTRUCTORS wants to keep any .init_array.* sections. + * Clang's -fprofile-arcs, -fsanitize=kernel-address, and + * -fsanitize=thread produce unwanted sections (.eh_frame + * and .init_array.*), but CONFIG_CONSTRUCTORS wants to + * keep any .init_array.* sections. * https://bugs.llvm.org/show_bug.cgi?id=46478 */ -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN) +#if defined(CONFIG_GCOV_KERNEL) || defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN) # ifdef CONFIG_CONSTRUCTORS # define SANITIZER_DISCARDS \ *(.eh_frame) diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h index 716990bace10..b81b3bfb08c8 100644 --- a/include/drm/drm_file.h +++ b/include/drm/drm_file.h @@ -399,6 +399,9 @@ void drm_event_cancel_free(struct drm_device *dev, struct drm_pending_event *p); void drm_send_event_locked(struct drm_device *dev, struct drm_pending_event *e); void drm_send_event(struct drm_device *dev, struct drm_pending_event *e); +void drm_send_event_timestamp_locked(struct drm_device *dev, + struct drm_pending_event *e, + ktime_t timestamp); struct file *mock_drm_getfile(struct drm_minor *minor, unsigned int flags); diff --git a/include/dt-bindings/clock/k210-clk.h b/include/dt-bindings/clock/k210-clk.h index a48176ad3c23..b2de702cbf75 100644 --- a/include/dt-bindings/clock/k210-clk.h +++ b/include/dt-bindings/clock/k210-clk.h @@ -9,7 +9,6 @@ /* * Kendryte K210 SoC clock identifiers (arbitrary values). */ -#define K210_CLK_ACLK 0 #define K210_CLK_CPU 0 #define K210_CLK_SRAM0 1 #define K210_CLK_SRAM1 2 diff --git a/include/dt-bindings/pinctrl/k210-fpioa.h b/include/dt-bindings/pinctrl/k210-fpioa.h new file mode 100644 index 000000000000..314285eab3a1 --- /dev/null +++ b/include/dt-bindings/pinctrl/k210-fpioa.h @@ -0,0 +1,276 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2020 Sean Anderson + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ +#ifndef PINCTRL_K210_FPIOA_H +#define PINCTRL_K210_FPIOA_H + +/* + * Full list of FPIOA functions from + * kendryte-standalone-sdk/lib/drivers/include/fpioa.h + */ +#define K210_PCF_MASK GENMASK(7, 0) +#define K210_PCF_JTAG_TCLK 0 /* JTAG Test Clock */ +#define K210_PCF_JTAG_TDI 1 /* JTAG Test Data In */ +#define K210_PCF_JTAG_TMS 2 /* JTAG Test Mode Select */ +#define K210_PCF_JTAG_TDO 3 /* JTAG Test Data Out */ +#define K210_PCF_SPI0_D0 4 /* SPI0 Data 0 */ +#define K210_PCF_SPI0_D1 5 /* SPI0 Data 1 */ +#define K210_PCF_SPI0_D2 6 /* SPI0 Data 2 */ +#define K210_PCF_SPI0_D3 7 /* SPI0 Data 3 */ +#define K210_PCF_SPI0_D4 8 /* SPI0 Data 4 */ +#define K210_PCF_SPI0_D5 9 /* SPI0 Data 5 */ +#define K210_PCF_SPI0_D6 10 /* SPI0 Data 6 */ +#define K210_PCF_SPI0_D7 11 /* SPI0 Data 7 */ +#define K210_PCF_SPI0_SS0 12 /* SPI0 Chip Select 0 */ +#define K210_PCF_SPI0_SS1 13 /* SPI0 Chip Select 1 */ +#define K210_PCF_SPI0_SS2 14 /* SPI0 Chip Select 2 */ +#define K210_PCF_SPI0_SS3 15 /* SPI0 Chip Select 3 */ +#define K210_PCF_SPI0_ARB 16 /* SPI0 Arbitration */ +#define K210_PCF_SPI0_SCLK 17 /* SPI0 Serial Clock */ +#define K210_PCF_UARTHS_RX 18 /* UART High speed Receiver */ +#define K210_PCF_UARTHS_TX 19 /* UART High speed Transmitter */ +#define K210_PCF_RESV6 20 /* Reserved function */ +#define K210_PCF_RESV7 21 /* Reserved function */ +#define K210_PCF_CLK_SPI1 22 /* Clock SPI1 */ +#define K210_PCF_CLK_I2C1 23 /* Clock I2C1 */ +#define K210_PCF_GPIOHS0 24 /* GPIO High speed 0 */ +#define K210_PCF_GPIOHS1 25 /* GPIO High speed 1 */ +#define K210_PCF_GPIOHS2 26 /* GPIO High speed 2 */ +#define K210_PCF_GPIOHS3 27 /* GPIO High speed 3 */ +#define K210_PCF_GPIOHS4 28 /* GPIO High speed 4 */ +#define K210_PCF_GPIOHS5 29 /* GPIO High speed 5 */ +#define K210_PCF_GPIOHS6 30 /* GPIO High speed 6 */ +#define K210_PCF_GPIOHS7 31 /* GPIO High speed 7 */ +#define K210_PCF_GPIOHS8 32 /* GPIO High speed 8 */ +#define K210_PCF_GPIOHS9 33 /* GPIO High speed 9 */ +#define K210_PCF_GPIOHS10 34 /* GPIO High speed 10 */ +#define K210_PCF_GPIOHS11 35 /* GPIO High speed 11 */ +#define K210_PCF_GPIOHS12 36 /* GPIO High speed 12 */ +#define K210_PCF_GPIOHS13 37 /* GPIO High speed 13 */ +#define K210_PCF_GPIOHS14 38 /* GPIO High speed 14 */ +#define K210_PCF_GPIOHS15 39 /* GPIO High speed 15 */ +#define K210_PCF_GPIOHS16 40 /* GPIO High speed 16 */ +#define K210_PCF_GPIOHS17 41 /* GPIO High speed 17 */ +#define K210_PCF_GPIOHS18 42 /* GPIO High speed 18 */ +#define K210_PCF_GPIOHS19 43 /* GPIO High speed 19 */ +#define K210_PCF_GPIOHS20 44 /* GPIO High speed 20 */ +#define K210_PCF_GPIOHS21 45 /* GPIO High speed 21 */ +#define K210_PCF_GPIOHS22 46 /* GPIO High speed 22 */ +#define K210_PCF_GPIOHS23 47 /* GPIO High speed 23 */ +#define K210_PCF_GPIOHS24 48 /* GPIO High speed 24 */ +#define K210_PCF_GPIOHS25 49 /* GPIO High speed 25 */ +#define K210_PCF_GPIOHS26 50 /* GPIO High speed 26 */ +#define K210_PCF_GPIOHS27 51 /* GPIO High speed 27 */ +#define K210_PCF_GPIOHS28 52 /* GPIO High speed 28 */ +#define K210_PCF_GPIOHS29 53 /* GPIO High speed 29 */ +#define K210_PCF_GPIOHS30 54 /* GPIO High speed 30 */ +#define K210_PCF_GPIOHS31 55 /* GPIO High speed 31 */ +#define K210_PCF_GPIO0 56 /* GPIO pin 0 */ +#define K210_PCF_GPIO1 57 /* GPIO pin 1 */ +#define K210_PCF_GPIO2 58 /* GPIO pin 2 */ +#define K210_PCF_GPIO3 59 /* GPIO pin 3 */ +#define K210_PCF_GPIO4 60 /* GPIO pin 4 */ +#define K210_PCF_GPIO5 61 /* GPIO pin 5 */ +#define K210_PCF_GPIO6 62 /* GPIO pin 6 */ +#define K210_PCF_GPIO7 63 /* GPIO pin 7 */ +#define K210_PCF_UART1_RX 64 /* UART1 Receiver */ +#define K210_PCF_UART1_TX 65 /* UART1 Transmitter */ +#define K210_PCF_UART2_RX 66 /* UART2 Receiver */ +#define K210_PCF_UART2_TX 67 /* UART2 Transmitter */ +#define K210_PCF_UART3_RX 68 /* UART3 Receiver */ +#define K210_PCF_UART3_TX 69 /* UART3 Transmitter */ +#define K210_PCF_SPI1_D0 70 /* SPI1 Data 0 */ +#define K210_PCF_SPI1_D1 71 /* SPI1 Data 1 */ +#define K210_PCF_SPI1_D2 72 /* SPI1 Data 2 */ +#define K210_PCF_SPI1_D3 73 /* SPI1 Data 3 */ +#define K210_PCF_SPI1_D4 74 /* SPI1 Data 4 */ +#define K210_PCF_SPI1_D5 75 /* SPI1 Data 5 */ +#define K210_PCF_SPI1_D6 76 /* SPI1 Data 6 */ +#define K210_PCF_SPI1_D7 77 /* SPI1 Data 7 */ +#define K210_PCF_SPI1_SS0 78 /* SPI1 Chip Select 0 */ +#define K210_PCF_SPI1_SS1 79 /* SPI1 Chip Select 1 */ +#define K210_PCF_SPI1_SS2 80 /* SPI1 Chip Select 2 */ +#define K210_PCF_SPI1_SS3 81 /* SPI1 Chip Select 3 */ +#define K210_PCF_SPI1_ARB 82 /* SPI1 Arbitration */ +#define K210_PCF_SPI1_SCLK 83 /* SPI1 Serial Clock */ +#define K210_PCF_SPI2_D0 84 /* SPI2 Data 0 */ +#define K210_PCF_SPI2_SS 85 /* SPI2 Select */ +#define K210_PCF_SPI2_SCLK 86 /* SPI2 Serial Clock */ +#define K210_PCF_I2S0_MCLK 87 /* I2S0 Master Clock */ +#define K210_PCF_I2S0_SCLK 88 /* I2S0 Serial Clock(BCLK) */ +#define K210_PCF_I2S0_WS 89 /* I2S0 Word Select(LRCLK) */ +#define K210_PCF_I2S0_IN_D0 90 /* I2S0 Serial Data Input 0 */ +#define K210_PCF_I2S0_IN_D1 91 /* I2S0 Serial Data Input 1 */ +#define K210_PCF_I2S0_IN_D2 92 /* I2S0 Serial Data Input 2 */ +#define K210_PCF_I2S0_IN_D3 93 /* I2S0 Serial Data Input 3 */ +#define K210_PCF_I2S0_OUT_D0 94 /* I2S0 Serial Data Output 0 */ +#define K210_PCF_I2S0_OUT_D1 95 /* I2S0 Serial Data Output 1 */ +#define K210_PCF_I2S0_OUT_D2 96 /* I2S0 Serial Data Output 2 */ +#define K210_PCF_I2S0_OUT_D3 97 /* I2S0 Serial Data Output 3 */ +#define K210_PCF_I2S1_MCLK 98 /* I2S1 Master Clock */ +#define K210_PCF_I2S1_SCLK 99 /* I2S1 Serial Clock(BCLK) */ +#define K210_PCF_I2S1_WS 100 /* I2S1 Word Select(LRCLK) */ +#define K210_PCF_I2S1_IN_D0 101 /* I2S1 Serial Data Input 0 */ +#define K210_PCF_I2S1_IN_D1 102 /* I2S1 Serial Data Input 1 */ +#define K210_PCF_I2S1_IN_D2 103 /* I2S1 Serial Data Input 2 */ +#define K210_PCF_I2S1_IN_D3 104 /* I2S1 Serial Data Input 3 */ +#define K210_PCF_I2S1_OUT_D0 105 /* I2S1 Serial Data Output 0 */ +#define K210_PCF_I2S1_OUT_D1 106 /* I2S1 Serial Data Output 1 */ +#define K210_PCF_I2S1_OUT_D2 107 /* I2S1 Serial Data Output 2 */ +#define K210_PCF_I2S1_OUT_D3 108 /* I2S1 Serial Data Output 3 */ +#define K210_PCF_I2S2_MCLK 109 /* I2S2 Master Clock */ +#define K210_PCF_I2S2_SCLK 110 /* I2S2 Serial Clock(BCLK) */ +#define K210_PCF_I2S2_WS 111 /* I2S2 Word Select(LRCLK) */ +#define K210_PCF_I2S2_IN_D0 112 /* I2S2 Serial Data Input 0 */ +#define K210_PCF_I2S2_IN_D1 113 /* I2S2 Serial Data Input 1 */ +#define K210_PCF_I2S2_IN_D2 114 /* I2S2 Serial Data Input 2 */ +#define K210_PCF_I2S2_IN_D3 115 /* I2S2 Serial Data Input 3 */ +#define K210_PCF_I2S2_OUT_D0 116 /* I2S2 Serial Data Output 0 */ +#define K210_PCF_I2S2_OUT_D1 117 /* I2S2 Serial Data Output 1 */ +#define K210_PCF_I2S2_OUT_D2 118 /* I2S2 Serial Data Output 2 */ +#define K210_PCF_I2S2_OUT_D3 119 /* I2S2 Serial Data Output 3 */ +#define K210_PCF_RESV0 120 /* Reserved function */ +#define K210_PCF_RESV1 121 /* Reserved function */ +#define K210_PCF_RESV2 122 /* Reserved function */ +#define K210_PCF_RESV3 123 /* Reserved function */ +#define K210_PCF_RESV4 124 /* Reserved function */ +#define K210_PCF_RESV5 125 /* Reserved function */ +#define K210_PCF_I2C0_SCLK 126 /* I2C0 Serial Clock */ +#define K210_PCF_I2C0_SDA 127 /* I2C0 Serial Data */ +#define K210_PCF_I2C1_SCLK 128 /* I2C1 Serial Clock */ +#define K210_PCF_I2C1_SDA 129 /* I2C1 Serial Data */ +#define K210_PCF_I2C2_SCLK 130 /* I2C2 Serial Clock */ +#define K210_PCF_I2C2_SDA 131 /* I2C2 Serial Data */ +#define K210_PCF_DVP_XCLK 132 /* DVP System Clock */ +#define K210_PCF_DVP_RST 133 /* DVP System Reset */ +#define K210_PCF_DVP_PWDN 134 /* DVP Power Down Mode */ +#define K210_PCF_DVP_VSYNC 135 /* DVP Vertical Sync */ +#define K210_PCF_DVP_HSYNC 136 /* DVP Horizontal Sync */ +#define K210_PCF_DVP_PCLK 137 /* Pixel Clock */ +#define K210_PCF_DVP_D0 138 /* Data Bit 0 */ +#define K210_PCF_DVP_D1 139 /* Data Bit 1 */ +#define K210_PCF_DVP_D2 140 /* Data Bit 2 */ +#define K210_PCF_DVP_D3 141 /* Data Bit 3 */ +#define K210_PCF_DVP_D4 142 /* Data Bit 4 */ +#define K210_PCF_DVP_D5 143 /* Data Bit 5 */ +#define K210_PCF_DVP_D6 144 /* Data Bit 6 */ +#define K210_PCF_DVP_D7 145 /* Data Bit 7 */ +#define K210_PCF_SCCB_SCLK 146 /* Serial Camera Control Bus Clock */ +#define K210_PCF_SCCB_SDA 147 /* Serial Camera Control Bus Data */ +#define K210_PCF_UART1_CTS 148 /* UART1 Clear To Send */ +#define K210_PCF_UART1_DSR 149 /* UART1 Data Set Ready */ +#define K210_PCF_UART1_DCD 150 /* UART1 Data Carrier Detect */ +#define K210_PCF_UART1_RI 151 /* UART1 Ring Indicator */ +#define K210_PCF_UART1_SIR_IN 152 /* UART1 Serial Infrared Input */ +#define K210_PCF_UART1_DTR 153 /* UART1 Data Terminal Ready */ +#define K210_PCF_UART1_RTS 154 /* UART1 Request To Send */ +#define K210_PCF_UART1_OUT2 155 /* UART1 User-designated Output 2 */ +#define K210_PCF_UART1_OUT1 156 /* UART1 User-designated Output 1 */ +#define K210_PCF_UART1_SIR_OUT 157 /* UART1 Serial Infrared Output */ +#define K210_PCF_UART1_BAUD 158 /* UART1 Transmit Clock Output */ +#define K210_PCF_UART1_RE 159 /* UART1 Receiver Output Enable */ +#define K210_PCF_UART1_DE 160 /* UART1 Driver Output Enable */ +#define K210_PCF_UART1_RS485_EN 161 /* UART1 RS485 Enable */ +#define K210_PCF_UART2_CTS 162 /* UART2 Clear To Send */ +#define K210_PCF_UART2_DSR 163 /* UART2 Data Set Ready */ +#define K210_PCF_UART2_DCD 164 /* UART2 Data Carrier Detect */ +#define K210_PCF_UART2_RI 165 /* UART2 Ring Indicator */ +#define K210_PCF_UART2_SIR_IN 166 /* UART2 Serial Infrared Input */ +#define K210_PCF_UART2_DTR 167 /* UART2 Data Terminal Ready */ +#define K210_PCF_UART2_RTS 168 /* UART2 Request To Send */ +#define K210_PCF_UART2_OUT2 169 /* UART2 User-designated Output 2 */ +#define K210_PCF_UART2_OUT1 170 /* UART2 User-designated Output 1 */ +#define K210_PCF_UART2_SIR_OUT 171 /* UART2 Serial Infrared Output */ +#define K210_PCF_UART2_BAUD 172 /* UART2 Transmit Clock Output */ +#define K210_PCF_UART2_RE 173 /* UART2 Receiver Output Enable */ +#define K210_PCF_UART2_DE 174 /* UART2 Driver Output Enable */ +#define K210_PCF_UART2_RS485_EN 175 /* UART2 RS485 Enable */ +#define K210_PCF_UART3_CTS 176 /* UART3 Clear To Send */ +#define K210_PCF_UART3_DSR 177 /* UART3 Data Set Ready */ +#define K210_PCF_UART3_DCD 178 /* UART3 Data Carrier Detect */ +#define K210_PCF_UART3_RI 179 /* UART3 Ring Indicator */ +#define K210_PCF_UART3_SIR_IN 180 /* UART3 Serial Infrared Input */ +#define K210_PCF_UART3_DTR 181 /* UART3 Data Terminal Ready */ +#define K210_PCF_UART3_RTS 182 /* UART3 Request To Send */ +#define K210_PCF_UART3_OUT2 183 /* UART3 User-designated Output 2 */ +#define K210_PCF_UART3_OUT1 184 /* UART3 User-designated Output 1 */ +#define K210_PCF_UART3_SIR_OUT 185 /* UART3 Serial Infrared Output */ +#define K210_PCF_UART3_BAUD 186 /* UART3 Transmit Clock Output */ +#define K210_PCF_UART3_RE 187 /* UART3 Receiver Output Enable */ +#define K210_PCF_UART3_DE 188 /* UART3 Driver Output Enable */ +#define K210_PCF_UART3_RS485_EN 189 /* UART3 RS485 Enable */ +#define K210_PCF_TIMER0_TOGGLE1 190 /* TIMER0 Toggle Output 1 */ +#define K210_PCF_TIMER0_TOGGLE2 191 /* TIMER0 Toggle Output 2 */ +#define K210_PCF_TIMER0_TOGGLE3 192 /* TIMER0 Toggle Output 3 */ +#define K210_PCF_TIMER0_TOGGLE4 193 /* TIMER0 Toggle Output 4 */ +#define K210_PCF_TIMER1_TOGGLE1 194 /* TIMER1 Toggle Output 1 */ +#define K210_PCF_TIMER1_TOGGLE2 195 /* TIMER1 Toggle Output 2 */ +#define K210_PCF_TIMER1_TOGGLE3 196 /* TIMER1 Toggle Output 3 */ +#define K210_PCF_TIMER1_TOGGLE4 197 /* TIMER1 Toggle Output 4 */ +#define K210_PCF_TIMER2_TOGGLE1 198 /* TIMER2 Toggle Output 1 */ +#define K210_PCF_TIMER2_TOGGLE2 199 /* TIMER2 Toggle Output 2 */ +#define K210_PCF_TIMER2_TOGGLE3 200 /* TIMER2 Toggle Output 3 */ +#define K210_PCF_TIMER2_TOGGLE4 201 /* TIMER2 Toggle Output 4 */ +#define K210_PCF_CLK_SPI2 202 /* Clock SPI2 */ +#define K210_PCF_CLK_I2C2 203 /* Clock I2C2 */ +#define K210_PCF_INTERNAL0 204 /* Internal function signal 0 */ +#define K210_PCF_INTERNAL1 205 /* Internal function signal 1 */ +#define K210_PCF_INTERNAL2 206 /* Internal function signal 2 */ +#define K210_PCF_INTERNAL3 207 /* Internal function signal 3 */ +#define K210_PCF_INTERNAL4 208 /* Internal function signal 4 */ +#define K210_PCF_INTERNAL5 209 /* Internal function signal 5 */ +#define K210_PCF_INTERNAL6 210 /* Internal function signal 6 */ +#define K210_PCF_INTERNAL7 211 /* Internal function signal 7 */ +#define K210_PCF_INTERNAL8 212 /* Internal function signal 8 */ +#define K210_PCF_INTERNAL9 213 /* Internal function signal 9 */ +#define K210_PCF_INTERNAL10 214 /* Internal function signal 10 */ +#define K210_PCF_INTERNAL11 215 /* Internal function signal 11 */ +#define K210_PCF_INTERNAL12 216 /* Internal function signal 12 */ +#define K210_PCF_INTERNAL13 217 /* Internal function signal 13 */ +#define K210_PCF_INTERNAL14 218 /* Internal function signal 14 */ +#define K210_PCF_INTERNAL15 219 /* Internal function signal 15 */ +#define K210_PCF_INTERNAL16 220 /* Internal function signal 16 */ +#define K210_PCF_INTERNAL17 221 /* Internal function signal 17 */ +#define K210_PCF_CONSTANT 222 /* Constant function */ +#define K210_PCF_INTERNAL18 223 /* Internal function signal 18 */ +#define K210_PCF_DEBUG0 224 /* Debug function 0 */ +#define K210_PCF_DEBUG1 225 /* Debug function 1 */ +#define K210_PCF_DEBUG2 226 /* Debug function 2 */ +#define K210_PCF_DEBUG3 227 /* Debug function 3 */ +#define K210_PCF_DEBUG4 228 /* Debug function 4 */ +#define K210_PCF_DEBUG5 229 /* Debug function 5 */ +#define K210_PCF_DEBUG6 230 /* Debug function 6 */ +#define K210_PCF_DEBUG7 231 /* Debug function 7 */ +#define K210_PCF_DEBUG8 232 /* Debug function 8 */ +#define K210_PCF_DEBUG9 233 /* Debug function 9 */ +#define K210_PCF_DEBUG10 234 /* Debug function 10 */ +#define K210_PCF_DEBUG11 235 /* Debug function 11 */ +#define K210_PCF_DEBUG12 236 /* Debug function 12 */ +#define K210_PCF_DEBUG13 237 /* Debug function 13 */ +#define K210_PCF_DEBUG14 238 /* Debug function 14 */ +#define K210_PCF_DEBUG15 239 /* Debug function 15 */ +#define K210_PCF_DEBUG16 240 /* Debug function 16 */ +#define K210_PCF_DEBUG17 241 /* Debug function 17 */ +#define K210_PCF_DEBUG18 242 /* Debug function 18 */ +#define K210_PCF_DEBUG19 243 /* Debug function 19 */ +#define K210_PCF_DEBUG20 244 /* Debug function 20 */ +#define K210_PCF_DEBUG21 245 /* Debug function 21 */ +#define K210_PCF_DEBUG22 246 /* Debug function 22 */ +#define K210_PCF_DEBUG23 247 /* Debug function 23 */ +#define K210_PCF_DEBUG24 248 /* Debug function 24 */ +#define K210_PCF_DEBUG25 249 /* Debug function 25 */ +#define K210_PCF_DEBUG26 250 /* Debug function 26 */ +#define K210_PCF_DEBUG27 251 /* Debug function 27 */ +#define K210_PCF_DEBUG28 252 /* Debug function 28 */ +#define K210_PCF_DEBUG29 253 /* Debug function 29 */ +#define K210_PCF_DEBUG30 254 /* Debug function 30 */ +#define K210_PCF_DEBUG31 255 /* Debug function 31 */ + +#define K210_FPIOA(pin, func) (((pin) << 16) | (func)) + +#define K210_PC_POWER_3V3 0 +#define K210_PC_POWER_1V8 1 + +#endif /* PINCTRL_K210_FPIOA_H */ diff --git a/include/dt-bindings/reset/k210-rst.h b/include/dt-bindings/reset/k210-rst.h new file mode 100644 index 000000000000..883c1aed50e8 --- /dev/null +++ b/include/dt-bindings/reset/k210-rst.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2019 Sean Anderson + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ +#ifndef RESET_K210_SYSCTL_H +#define RESET_K210_SYSCTL_H + +/* + * Kendryte K210 SoC system controller K210_SYSCTL_SOFT_RESET register bits. + * Taken from Kendryte SDK (kendryte-standalone-sdk). + */ +#define K210_RST_ROM 0 +#define K210_RST_DMA 1 +#define K210_RST_AI 2 +#define K210_RST_DVP 3 +#define K210_RST_FFT 4 +#define K210_RST_GPIO 5 +#define K210_RST_SPI0 6 +#define K210_RST_SPI1 7 +#define K210_RST_SPI2 8 +#define K210_RST_SPI3 9 +#define K210_RST_I2S0 10 +#define K210_RST_I2S1 11 +#define K210_RST_I2S2 12 +#define K210_RST_I2C0 13 +#define K210_RST_I2C1 14 +#define K210_RST_I2C2 15 +#define K210_RST_UART1 16 +#define K210_RST_UART2 17 +#define K210_RST_UART3 18 +#define K210_RST_AES 19 +#define K210_RST_FPIOA 20 +#define K210_RST_TIMER0 21 +#define K210_RST_TIMER1 22 +#define K210_RST_TIMER2 23 +#define K210_RST_WDT0 24 +#define K210_RST_WDT1 25 +#define K210_RST_SHA 26 +#define K210_RST_RTC 29 + +#endif /* RESET_K210_SYSCTL_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index a61f192c096b..a5a48303b0f1 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -214,7 +214,7 @@ static inline int get_count_order_long(unsigned long l) * __ffs64 - find first set bit in a 64 bit word * @word: The 64 bit word * - * On 64 bit arches this is a synomyn for __ffs + * On 64 bit arches this is a synonym for __ffs * The result is not defined if no bits are set, so check that @word * is non-zero before calling this. */ diff --git a/include/linux/can/can-ml.h b/include/linux/can/can-ml.h index 2f5d731ae251..8afa92d15a66 100644 --- a/include/linux/can/can-ml.h +++ b/include/linux/can/can-ml.h @@ -44,6 +44,7 @@ #include #include +#include #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS) #define CAN_EFF_RCV_HASH_BITS 10 @@ -65,4 +66,15 @@ struct can_ml_priv { #endif }; +static inline struct can_ml_priv *can_get_ml_priv(struct net_device *dev) +{ + return netdev_get_ml_priv(dev, ML_PRIV_CAN); +} + +static inline void can_set_ml_priv(struct net_device *dev, + struct can_ml_priv *ml_priv) +{ + netdev_set_ml_priv(dev, ml_priv, ML_PRIV_CAN); +} + #endif /* CAN_ML_H */ diff --git a/include/linux/cfag12864b.h b/include/linux/cfag12864b.h index 4060004968c8..6617d9c68d86 100644 --- a/include/linux/cfag12864b.h +++ b/include/linux/cfag12864b.h @@ -4,7 +4,7 @@ * Version: 0.1.0 * Description: cfag12864b LCD driver header * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-12 */ diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 98cff1b4b088..04c0a5a717f7 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -3,16 +3,6 @@ #error "Please don't include directly, include instead." #endif -#define CLANG_VERSION (__clang_major__ * 10000 \ - + __clang_minor__ * 100 \ - + __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 */ /* same as gcc, this was present in clang-2.6 so we can assume it works diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 555ab0fddbef..48750243db4c 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -10,17 +10,6 @@ + __GNUC_MINOR__ * 100 \ + __GNUC_PATCHLEVEL__) -/* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */ -#if GCC_VERSION < 40900 -# error Sorry, your version of GCC is too old - please use 4.9 or newer. -#elif defined(CONFIG_ARM64) && GCC_VERSION < 50100 -/* - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63293 - * https://lore.kernel.org/r/20210107111841.GN1551@shell.armlinux.org.uk - */ -# error Sorry, your version of GCC is too old - please use 5.1 or newer. -#endif - /* * This macro obfuscates arithmetic on a variable address so that gcc * shouldn't recognize the original var, and make assumptions about it. diff --git a/include/linux/cred.h b/include/linux/cred.h index 18639c069263..4c6350503697 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -25,7 +25,7 @@ struct inode; struct group_info { atomic_t usage; int ngroups; - kgid_t gid[0]; + kgid_t gid[]; } __randomize_layout; /** diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 09e23adb351d..9f12efaaa93a 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -372,6 +372,9 @@ static inline void __dma_fence_might_wait(void) {} int dma_fence_signal(struct dma_fence *fence); int dma_fence_signal_locked(struct dma_fence *fence); +int dma_fence_signal_timestamp(struct dma_fence *fence, ktime_t timestamp); +int dma_fence_signal_timestamp_locked(struct dma_fence *fence, + ktime_t timestamp); signed long dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout); int dma_fence_add_callback(struct dma_fence *fence, diff --git a/include/linux/dma-heap.h b/include/linux/dma-heap.h index 23ca21afbb89..0f676887c248 100644 --- a/include/linux/dma-heap.h +++ b/include/linux/dma-heap.h @@ -22,9 +22,9 @@ struct dma_heap; */ struct dma_heap_ops { struct dma_buf *(*allocate)(struct dma_heap *heap, - unsigned long len, - unsigned long fd_flags, - unsigned long heap_flags); + unsigned long len, + unsigned long fd_flags, + unsigned long heap_flags); }; /** diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h new file mode 100644 index 000000000000..c1be37437e77 --- /dev/null +++ b/include/linux/fortify-string.h @@ -0,0 +1,302 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FORTIFY_STRING_H_ +#define _LINUX_FORTIFY_STRING_H_ + + +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) +extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); +extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); +extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); +extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); +extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); +extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); +extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); +#else +#define __underlying_memchr __builtin_memchr +#define __underlying_memcmp __builtin_memcmp +#define __underlying_memcpy __builtin_memcpy +#define __underlying_memmove __builtin_memmove +#define __underlying_memset __builtin_memset +#define __underlying_strcat __builtin_strcat +#define __underlying_strcpy __builtin_strcpy +#define __underlying_strlen __builtin_strlen +#define __underlying_strncat __builtin_strncat +#define __underlying_strncpy __builtin_strncpy +#endif + +__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 1); + + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __underlying_strncpy(p, q, size); +} + +__FORTIFY_INLINE char *strcat(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 1); + + if (p_size == (size_t)-1) + return __underlying_strcat(p, q); + if (strlcat(p, q, p_size) >= p_size) + fortify_panic(__func__); + return p; +} + +__FORTIFY_INLINE __kernel_size_t strlen(const char *p) +{ + __kernel_size_t ret; + size_t p_size = __builtin_object_size(p, 1); + + /* Work around gcc excess stack consumption issue */ + if (p_size == (size_t)-1 || + (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) + return __underlying_strlen(p); + ret = strnlen(p, p_size); + if (p_size <= ret) + fortify_panic(__func__); + return ret; +} + +extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); +__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) +{ + size_t p_size = __builtin_object_size(p, 1); + __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); + + if (p_size <= ret && maxlen != ret) + fortify_panic(__func__); + return ret; +} + +/* defined after fortified strlen to reuse it */ +extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); +__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) +{ + size_t ret; + size_t p_size = __builtin_object_size(p, 1); + size_t q_size = __builtin_object_size(q, 1); + + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __real_strlcpy(p, q, size); + ret = strlen(q); + if (size) { + size_t len = (ret >= size) ? size - 1 : ret; + + if (__builtin_constant_p(len) && len >= p_size) + __write_overflow(); + if (len >= p_size) + fortify_panic(__func__); + __underlying_memcpy(p, q, len); + p[len] = '\0'; + } + return ret; +} + +/* defined after fortified strnlen to reuse it */ +extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); +__FORTIFY_INLINE ssize_t strscpy(char *p, const char *q, size_t size) +{ + size_t len; + /* Use string size rather than possible enclosing struct size. */ + size_t p_size = __builtin_object_size(p, 1); + size_t q_size = __builtin_object_size(q, 1); + + /* If we cannot get size of p and q default to call strscpy. */ + if (p_size == (size_t) -1 && q_size == (size_t) -1) + return __real_strscpy(p, q, size); + + /* + * If size can be known at compile time and is greater than + * p_size, generate a compile time write overflow error. + */ + if (__builtin_constant_p(size) && size > p_size) + __write_overflow(); + + /* + * This call protects from read overflow, because len will default to q + * length if it smaller than size. + */ + len = strnlen(q, size); + /* + * If len equals size, we will copy only size bytes which leads to + * -E2BIG being returned. + * Otherwise we will copy len + 1 because of the final '\O'. + */ + len = len == size ? size : len + 1; + + /* + * Generate a runtime write overflow error if len is greater than + * p_size. + */ + if (len > p_size) + fortify_panic(__func__); + + /* + * We can now safely call vanilla strscpy because we are protected from: + * 1. Read overflow thanks to call to strnlen(). + * 2. Write overflow thanks to above ifs. + */ + return __real_strscpy(p, q, len); +} + +/* defined after fortified strlen and strnlen to reuse them */ +__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) +{ + size_t p_len, copy_len; + size_t p_size = __builtin_object_size(p, 1); + size_t q_size = __builtin_object_size(q, 1); + + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __underlying_strncat(p, q, count); + p_len = strlen(p); + copy_len = strnlen(q, count); + if (p_size < p_len + copy_len + 1) + fortify_panic(__func__); + __underlying_memcpy(p + p_len, q, copy_len); + p[p_len + copy_len] = '\0'; + return p; +} + +__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __underlying_memset(p, c, size); +} + +__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __underlying_memcpy(p, q, size); +} + +__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __underlying_memmove(p, q, size); +} + +extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); +__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memscan(p, c, size); +} + +__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + + if (__builtin_constant_p(size)) { + if (p_size < size) + __read_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __underlying_memcmp(p, q, size); +} + +__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __underlying_memchr(p, c, size); +} + +void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); +__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memchr_inv(p, c, size); +} + +extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); +__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_kmemdup(p, size, gfp); +} + +/* defined after fortified strlen and memcpy to reuse them */ +__FORTIFY_INLINE char *strcpy(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 1); + size_t q_size = __builtin_object_size(q, 1); + size_t size; + + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __underlying_strcpy(p, q); + size = strlen(q) + 1; + /* test here to use the more stringent object size */ + if (p_size < size) + fortify_panic(__func__); + memcpy(p, q, size); + return p; +} + +/* Don't use these outside the FORITFY_SOURCE implementation */ +#undef __underlying_memchr +#undef __underlying_memcmp +#undef __underlying_memcpy +#undef __underlying_memmove +#undef __underlying_memset +#undef __underlying_strcat +#undef __underlying_strcpy +#undef __underlying_strlen +#undef __underlying_strncat +#undef __underlying_strncpy + +#endif /* _LINUX_FORTIFY_STRING_H_ */ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 972046dfca9f..9af2cfee619a 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -625,6 +625,8 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); extern void pm_restrict_gfp_mask(void); extern void pm_restore_gfp_mask(void); +extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); + #ifdef CONFIG_PM_SLEEP extern bool pm_suspended_storage(void); #else diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 452d8978ffc7..9055cb380ee2 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -3,6 +3,7 @@ #define _LINUX_ICMPV6_H #include +#include #include static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) @@ -15,13 +16,16 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) #if IS_ENABLED(CONFIG_IPV6) typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr); + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm); void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr); + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm); #if IS_BUILTIN(CONFIG_IPV6) -static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +static inline void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm) { - icmp6_send(skb, type, code, info, NULL); + icmp6_send(skb, type, code, info, NULL, parm); } static inline int inet6_register_icmp_sender(ip6_icmp_send_t *fn) { @@ -34,18 +38,28 @@ static inline int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) return 0; } #else -extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info); +extern void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); #endif +static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +{ + __icmpv6_send(skb, type, code, info, IP6CB(skb)); +} + int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); #if IS_ENABLED(CONFIG_NF_NAT) void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); #else -#define icmpv6_ndo_send icmpv6_send +static inline void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) +{ + struct inet6_skb_parm parm = { 0 }; + __icmpv6_send(skb_in, type, code, info, &parm); +} #endif #else diff --git a/include/linux/init.h b/include/linux/init.h index a01f01c1a5c5..31f54de58429 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -338,14 +338,14 @@ struct obs_kernel_param { var = 1; \ return 0; \ } \ - __setup_param(str_on, parse_##var##_on, parse_##var##_on, 1); \ + early_param(str_on, parse_##var##_on); \ \ static int __init parse_##var##_off(char *arg) \ { \ var = 0; \ return 0; \ } \ - __setup_param(str_off, parse_##var##_off, parse_##var##_off, 1) + early_param(str_off, parse_##var##_off) /* Relies on boot_command_line being set */ void __init parse_early_param(void); diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 8db6f8c8030b..85c15717af34 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -1,5 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_INITRD_H +#define __LINUX_INITRD_H + #define INITRD_MINOR 250 /* shouldn't collide with /dev/ram* too soon ... */ /* starting block # of image */ @@ -15,6 +18,12 @@ extern int initrd_below_start_ok; extern unsigned long initrd_start, initrd_end; extern void free_initrd_mem(unsigned long, unsigned long); +#ifdef CONFIG_BLK_DEV_INITRD +extern void __init reserve_initrd_mem(void); +#else +static inline void __init reserve_initrd_mem(void) {} +#endif + extern phys_addr_t phys_initrd_start; extern unsigned long phys_initrd_size; @@ -24,3 +33,5 @@ extern char __initramfs_start[]; extern unsigned long __initramfs_size; void console_on_rootfs(void); + +#endif /* __LINUX_INITRD_H */ diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 420553abe852..45c6306d3a6c 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -86,7 +86,6 @@ struct ipv6_params { __s32 autoconf; }; extern struct ipv6_params ipv6_defaults; -#include #include #include diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 7eaf2d9effb4..b91732bd05d7 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -83,6 +83,7 @@ static inline void kasan_disable_current(void) {} struct kasan_cache { int alloc_meta_offset; int free_meta_offset; + bool is_kmalloc; }; #ifdef CONFIG_KASAN_HW_TAGS @@ -143,6 +144,13 @@ static __always_inline void kasan_cache_create(struct kmem_cache *cache, __kasan_cache_create(cache, size, flags); } +void __kasan_cache_create_kmalloc(struct kmem_cache *cache); +static __always_inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) +{ + if (kasan_enabled()) + __kasan_cache_create_kmalloc(cache); +} + size_t __kasan_metadata_size(struct kmem_cache *cache); static __always_inline size_t kasan_metadata_size(struct kmem_cache *cache) { @@ -192,6 +200,13 @@ static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object) return false; } +void __kasan_kfree_large(void *ptr, unsigned long ip); +static __always_inline void kasan_kfree_large(void *ptr) +{ + if (kasan_enabled()) + __kasan_kfree_large(ptr, _RET_IP_); +} + void __kasan_slab_free_mempool(void *ptr, unsigned long ip); static __always_inline void kasan_slab_free_mempool(void *ptr) { @@ -239,13 +254,6 @@ static __always_inline void * __must_check kasan_krealloc(const void *object, return (void *)object; } -void __kasan_kfree_large(void *ptr, unsigned long ip); -static __always_inline void kasan_kfree_large(void *ptr) -{ - if (kasan_enabled()) - __kasan_kfree_large(ptr, _RET_IP_); -} - /* * Unlike kasan_check_read/write(), kasan_check_byte() is performed even for * the hardware tag-based mode that doesn't rely on compiler instrumentation. @@ -278,6 +286,7 @@ static inline void kasan_free_pages(struct page *page, unsigned int order) {} static inline void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, slab_flags_t *flags) {} +static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {} static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } static inline void kasan_poison_slab(struct page *page) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, @@ -293,6 +302,7 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object) { return false; } +static inline void kasan_kfree_large(void *ptr) {} static inline void kasan_slab_free_mempool(void *ptr) {} static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags) @@ -313,7 +323,6 @@ static inline void *kasan_krealloc(const void *object, size_t new_size, { return (void *)object; } -static inline void kasan_kfree_large(void *ptr) {} static inline bool kasan_check_byte(const void *address) { return true; diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 5f61389f5f36..8a7aa1d7e0e3 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -314,6 +314,8 @@ extern void machine_kexec_cleanup(struct kimage *image); extern int kernel_kexec(void); extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); +int machine_kexec_post_load(struct kimage *image); + extern void __crash_kexec(struct pt_regs *); extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); diff --git a/include/linux/kfence.h b/include/linux/kfence.h new file mode 100644 index 000000000000..a70d1ea03532 --- /dev/null +++ b/include/linux/kfence.h @@ -0,0 +1,222 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Kernel Electric-Fence (KFENCE). Public interface for allocator and fault + * handler integration. For more info see Documentation/dev-tools/kfence.rst. + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef _LINUX_KFENCE_H +#define _LINUX_KFENCE_H + +#include +#include + +#ifdef CONFIG_KFENCE + +/* + * We allocate an even number of pages, as it simplifies calculations to map + * address to metadata indices; effectively, the very first page serves as an + * extended guard page, but otherwise has no special purpose. + */ +#define KFENCE_POOL_SIZE ((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 * PAGE_SIZE) +extern char *__kfence_pool; + +#ifdef CONFIG_KFENCE_STATIC_KEYS +#include +DECLARE_STATIC_KEY_FALSE(kfence_allocation_key); +#else +#include +extern atomic_t kfence_allocation_gate; +#endif + +/** + * is_kfence_address() - check if an address belongs to KFENCE pool + * @addr: address to check + * + * Return: true or false depending on whether the address is within the KFENCE + * object range. + * + * KFENCE objects live in a separate page range and are not to be intermixed + * with regular heap objects (e.g. KFENCE objects must never be added to the + * allocator freelists). Failing to do so may and will result in heap + * corruptions, therefore is_kfence_address() must be used to check whether + * an object requires specific handling. + * + * Note: This function may be used in fast-paths, and is performance critical. + * Future changes should take this into account; for instance, we want to avoid + * introducing another load and therefore need to keep KFENCE_POOL_SIZE a + * constant (until immediate patching support is added to the kernel). + */ +static __always_inline bool is_kfence_address(const void *addr) +{ + /* + * The non-NULL check is required in case the __kfence_pool pointer was + * never initialized; keep it in the slow-path after the range-check. + */ + return unlikely((unsigned long)((char *)addr - __kfence_pool) < KFENCE_POOL_SIZE && addr); +} + +/** + * kfence_alloc_pool() - allocate the KFENCE pool via memblock + */ +void __init kfence_alloc_pool(void); + +/** + * kfence_init() - perform KFENCE initialization at boot time + * + * Requires that kfence_alloc_pool() was called before. This sets up the + * allocation gate timer, and requires that workqueues are available. + */ +void __init kfence_init(void); + +/** + * kfence_shutdown_cache() - handle shutdown_cache() for KFENCE objects + * @s: cache being shut down + * + * Before shutting down a cache, one must ensure there are no remaining objects + * allocated from it. Because KFENCE objects are not referenced from the cache + * directly, we need to check them here. + * + * Note that shutdown_cache() is internal to SL*B, and kmem_cache_destroy() does + * not return if allocated objects still exist: it prints an error message and + * simply aborts destruction of a cache, leaking memory. + * + * If the only such objects are KFENCE objects, we will not leak the entire + * cache, but instead try to provide more useful debug info by making allocated + * objects "zombie allocations". Objects may then still be used or freed (which + * is handled gracefully), but usage will result in showing KFENCE error reports + * which include stack traces to the user of the object, the original allocation + * site, and caller to shutdown_cache(). + */ +void kfence_shutdown_cache(struct kmem_cache *s); + +/* + * Allocate a KFENCE object. Allocators must not call this function directly, + * use kfence_alloc() instead. + */ +void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags); + +/** + * kfence_alloc() - allocate a KFENCE object with a low probability + * @s: struct kmem_cache with object requirements + * @size: exact size of the object to allocate (can be less than @s->size + * e.g. for kmalloc caches) + * @flags: GFP flags + * + * Return: + * * NULL - must proceed with allocating as usual, + * * non-NULL - pointer to a KFENCE object. + * + * kfence_alloc() should be inserted into the heap allocation fast path, + * allowing it to transparently return KFENCE-allocated objects with a low + * probability using a static branch (the probability is controlled by the + * kfence.sample_interval boot parameter). + */ +static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) +{ +#ifdef CONFIG_KFENCE_STATIC_KEYS + if (static_branch_unlikely(&kfence_allocation_key)) +#else + if (unlikely(!atomic_read(&kfence_allocation_gate))) +#endif + return __kfence_alloc(s, size, flags); + return NULL; +} + +/** + * kfence_ksize() - get actual amount of memory allocated for a KFENCE object + * @addr: pointer to a heap object + * + * Return: + * * 0 - not a KFENCE object, must call __ksize() instead, + * * non-0 - this many bytes can be accessed without causing a memory error. + * + * kfence_ksize() returns the number of bytes requested for a KFENCE object at + * allocation time. This number may be less than the object size of the + * corresponding struct kmem_cache. + */ +size_t kfence_ksize(const void *addr); + +/** + * kfence_object_start() - find the beginning of a KFENCE object + * @addr: address within a KFENCE-allocated object + * + * Return: address of the beginning of the object. + * + * SL[AU]B-allocated objects are laid out within a page one by one, so it is + * easy to calculate the beginning of an object given a pointer inside it and + * the object size. The same is not true for KFENCE, which places a single + * object at either end of the page. This helper function is used to find the + * beginning of a KFENCE-allocated object. + */ +void *kfence_object_start(const void *addr); + +/** + * __kfence_free() - release a KFENCE heap object to KFENCE pool + * @addr: object to be freed + * + * Requires: is_kfence_address(addr) + * + * Release a KFENCE object and mark it as freed. + */ +void __kfence_free(void *addr); + +/** + * kfence_free() - try to release an arbitrary heap object to KFENCE pool + * @addr: object to be freed + * + * Return: + * * false - object doesn't belong to KFENCE pool and was ignored, + * * true - object was released to KFENCE pool. + * + * Release a KFENCE object and mark it as freed. May be called on any object, + * even non-KFENCE objects, to simplify integration of the hooks into the + * allocator's free codepath. The allocator must check the return value to + * determine if it was a KFENCE object or not. + */ +static __always_inline __must_check bool kfence_free(void *addr) +{ + if (!is_kfence_address(addr)) + return false; + __kfence_free(addr); + return true; +} + +/** + * kfence_handle_page_fault() - perform page fault handling for KFENCE pages + * @addr: faulting address + * @is_write: is access a write + * @regs: current struct pt_regs (can be NULL, but shows full stack trace) + * + * Return: + * * false - address outside KFENCE pool, + * * true - page fault handled by KFENCE, no additional handling required. + * + * A page fault inside KFENCE pool indicates a memory error, such as an + * out-of-bounds access, a use-after-free or an invalid memory access. In these + * cases KFENCE prints an error message and marks the offending page as + * present, so that the kernel can proceed. + */ +bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs); + +#else /* CONFIG_KFENCE */ + +static inline bool is_kfence_address(const void *addr) { return false; } +static inline void kfence_alloc_pool(void) { } +static inline void kfence_init(void) { } +static inline void kfence_shutdown_cache(struct kmem_cache *s) { } +static inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { return NULL; } +static inline size_t kfence_ksize(const void *addr) { return 0; } +static inline void *kfence_object_start(const void *addr) { return NULL; } +static inline void __kfence_free(void *addr) { } +static inline bool __must_check kfence_free(void *addr) { return false; } +static inline bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, + struct pt_regs *regs) +{ + return false; +} + +#endif + +#endif /* _LINUX_KFENCE_H */ diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 0444b44bd156..392a3670944c 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -359,9 +359,11 @@ extern atomic_t kgdb_active; extern bool dbg_is_early; extern void __init dbg_late_init(void); extern void kgdb_panic(const char *msg); +extern void kgdb_free_init_mem(void); #else /* ! CONFIG_KGDB */ #define in_dbg_master() (0) #define dbg_late_init() static inline void kgdb_panic(const char *msg) {} +static inline void kgdb_free_init_mem(void) { } #endif /* ! CONFIG_KGDB */ #endif /* _KGDB_H_ */ diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index c941b7377321..2fcc01891b47 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -3,6 +3,7 @@ #define _LINUX_KHUGEPAGED_H #include /* MMF_VM_HUGEPAGE */ +#include #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -57,6 +58,7 @@ static inline int khugepaged_enter(struct vm_area_struct *vma, { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) if ((khugepaged_always() || + (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) || (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && !(vm_flags & VM_NOHUGEPAGE) && !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) diff --git a/include/linux/ks0108.h b/include/linux/ks0108.h index 0738389b42b6..1a37a664f915 100644 --- a/include/linux/ks0108.h +++ b/include/linux/ks0108.h @@ -4,7 +4,7 @@ * Version: 0.1.0 * Description: ks0108 LCD Controller driver header * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-31 */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e126ebda36d0..1b65e7204344 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -506,6 +507,8 @@ struct kvm { struct mmu_notifier mmu_notifier; unsigned long mmu_notifier_seq; long mmu_notifier_count; + unsigned long mmu_notifier_range_start; + unsigned long mmu_notifier_range_end; #endif long tlbs_dirty; struct list_head devices; @@ -733,7 +736,7 @@ kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool *async, bool write_fault, - bool *writable); + bool *writable, hva_t *hva); void kvm_release_pfn_clean(kvm_pfn_t pfn); void kvm_release_pfn_dirty(kvm_pfn_t pfn); @@ -1207,6 +1210,26 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) return 1; return 0; } + +static inline int mmu_notifier_retry_hva(struct kvm *kvm, + unsigned long mmu_seq, + unsigned long hva) +{ + lockdep_assert_held(&kvm->mmu_lock); + /* + * If mmu_notifier_count is non-zero, then the range maintained by + * kvm_mmu_notifier_invalidate_range_start contains all addresses that + * might be being invalidated. Note that it may include some false + * positives, due to shortcuts when handing concurrent invalidations. + */ + if (unlikely(kvm->mmu_notifier_count) && + hva >= kvm->mmu_notifier_range_start && + hva < kvm->mmu_notifier_range_end) + return 1; + if (kvm->mmu_notifier_seq != mmu_seq) + return 1; + return 0; +} #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING diff --git a/include/linux/led-class-flash.h b/include/linux/led-class-flash.h index 21a3358a1731..612b4cab3819 100644 --- a/include/linux/led-class-flash.h +++ b/include/linux/led-class-flash.h @@ -85,6 +85,7 @@ static inline struct led_classdev_flash *lcdev_to_flcdev( return container_of(lcdev, struct led_classdev_flash, led_cdev); } +#if IS_ENABLED(CONFIG_LEDS_CLASS_FLASH) /** * led_classdev_flash_register_ext - register a new object of LED class with * init data and with support for flash LEDs @@ -98,12 +99,6 @@ int led_classdev_flash_register_ext(struct device *parent, struct led_classdev_flash *fled_cdev, struct led_init_data *init_data); -static inline int led_classdev_flash_register(struct device *parent, - struct led_classdev_flash *fled_cdev) -{ - return led_classdev_flash_register_ext(parent, fled_cdev, NULL); -} - /** * led_classdev_flash_unregister - unregisters an object of led_classdev class * with support for flash LEDs @@ -118,15 +113,44 @@ int devm_led_classdev_flash_register_ext(struct device *parent, struct led_init_data *init_data); +void devm_led_classdev_flash_unregister(struct device *parent, + struct led_classdev_flash *fled_cdev); + +#else + +static inline int led_classdev_flash_register_ext(struct device *parent, + struct led_classdev_flash *fled_cdev, + struct led_init_data *init_data) +{ + return 0; +} + +static inline void led_classdev_flash_unregister(struct led_classdev_flash *fled_cdev) {}; +static inline int devm_led_classdev_flash_register_ext(struct device *parent, + struct led_classdev_flash *fled_cdev, + struct led_init_data *init_data) +{ + return 0; +} + +static inline void devm_led_classdev_flash_unregister(struct device *parent, + struct led_classdev_flash *fled_cdev) +{}; + +#endif /* IS_ENABLED(CONFIG_LEDS_CLASS_FLASH) */ + +static inline int led_classdev_flash_register(struct device *parent, + struct led_classdev_flash *fled_cdev) +{ + return led_classdev_flash_register_ext(parent, fled_cdev, NULL); +} + static inline int devm_led_classdev_flash_register(struct device *parent, struct led_classdev_flash *fled_cdev) { return devm_led_classdev_flash_register_ext(parent, fled_cdev, NULL); } -void devm_led_classdev_flash_unregister(struct device *parent, - struct led_classdev_flash *fled_cdev); - /** * led_set_flash_strobe - setup flash strobe * @fled_cdev: the flash LED to set strobe on diff --git a/include/linux/led-class-multicolor.h b/include/linux/led-class-multicolor.h index 5116f9a866cc..210d57bcd767 100644 --- a/include/linux/led-class-multicolor.h +++ b/include/linux/led-class-multicolor.h @@ -44,12 +44,6 @@ int led_classdev_multicolor_register_ext(struct device *parent, struct led_classdev_mc *mcled_cdev, struct led_init_data *init_data); -static inline int led_classdev_multicolor_register(struct device *parent, - struct led_classdev_mc *mcled_cdev) -{ - return led_classdev_multicolor_register_ext(parent, mcled_cdev, NULL); -} - /** * led_classdev_multicolor_unregister - unregisters an object of led_classdev * class with support for multicolor LEDs @@ -68,13 +62,6 @@ int devm_led_classdev_multicolor_register_ext(struct device *parent, struct led_classdev_mc *mcled_cdev, struct led_init_data *init_data); -static inline int devm_led_classdev_multicolor_register(struct device *parent, - struct led_classdev_mc *mcled_cdev) -{ - return devm_led_classdev_multicolor_register_ext(parent, mcled_cdev, - NULL); -} - void devm_led_classdev_multicolor_unregister(struct device *parent, struct led_classdev_mc *mcled_cdev); #else @@ -83,27 +70,33 @@ static inline int led_classdev_multicolor_register_ext(struct device *parent, struct led_classdev_mc *mcled_cdev, struct led_init_data *init_data) { - return -EINVAL; -} - -static inline int led_classdev_multicolor_register(struct device *parent, - struct led_classdev_mc *mcled_cdev) -{ - return led_classdev_multicolor_register_ext(parent, mcled_cdev, NULL); + return 0; } static inline void led_classdev_multicolor_unregister(struct led_classdev_mc *mcled_cdev) {}; static inline int led_mc_calc_color_components(struct led_classdev_mc *mcled_cdev, enum led_brightness brightness) { - return -EINVAL; + return 0; } static inline int devm_led_classdev_multicolor_register_ext(struct device *parent, struct led_classdev_mc *mcled_cdev, struct led_init_data *init_data) { - return -EINVAL; + return 0; +} + +static inline void devm_led_classdev_multicolor_unregister(struct device *parent, + struct led_classdev_mc *mcled_cdev) +{}; + +#endif /* IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR) */ + +static inline int led_classdev_multicolor_register(struct device *parent, + struct led_classdev_mc *mcled_cdev) +{ + return led_classdev_multicolor_register_ext(parent, mcled_cdev, NULL); } static inline int devm_led_classdev_multicolor_register(struct device *parent, @@ -113,9 +106,4 @@ static inline int devm_led_classdev_multicolor_register(struct device *parent, NULL); } -static inline void devm_led_classdev_multicolor_unregister(struct device *parent, - struct led_classdev_mc *mcled_cdev) -{}; - -#endif /* IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR) */ #endif /* _LINUX_MULTICOLOR_LEDS_H_INCLUDED */ diff --git a/include/linux/leds.h b/include/linux/leds.h index 6a8d6409c993..329fd914cf24 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -63,8 +63,8 @@ struct led_hw_trigger_type { struct led_classdev { const char *name; - enum led_brightness brightness; - enum led_brightness max_brightness; + unsigned int brightness; + unsigned int max_brightness; int flags; /* Lower 16 bits reflect status */ @@ -253,8 +253,7 @@ void led_blink_set_oneshot(struct led_classdev *led_cdev, * software blink timer that implements blinking when the * hardware doesn't. This function is guaranteed not to sleep. */ -void led_set_brightness(struct led_classdev *led_cdev, - enum led_brightness brightness); +void led_set_brightness(struct led_classdev *led_cdev, unsigned int brightness); /** * led_set_brightness_sync - set LED brightness synchronously @@ -267,8 +266,7 @@ void led_set_brightness(struct led_classdev *led_cdev, * * Returns: 0 on success or negative error value on failure */ -int led_set_brightness_sync(struct led_classdev *led_cdev, - enum led_brightness value); +int led_set_brightness_sync(struct led_classdev *led_cdev, unsigned int value); /** * led_update_brightness - update LED brightness @@ -565,7 +563,7 @@ static inline void ledtrig_cpu(enum cpu_led_event evt) #ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED void led_classdev_notify_brightness_hw_changed( - struct led_classdev *led_cdev, enum led_brightness brightness); + struct led_classdev *led_cdev, unsigned int brightness); #else static inline void led_classdev_notify_brightness_hw_changed( struct led_classdev *led_cdev, enum led_brightness brightness) { } diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 9004375c462e..27eb383cb95d 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -42,7 +42,7 @@ struct device *mdev_get_iommu_device(struct device *dev); * @mdev: mdev_device structure on of mediated device * that is being created * Returns integer: success (0) or error (< 0) - * @remove: Called to free resources in parent device's driver for a + * @remove: Called to free resources in parent device's driver for * a mediated device. It is mandatory to provide 'remove' * ops. * @mdev: mdev_device device structure which is being diff --git a/include/linux/memory.h b/include/linux/memory.h index 439a89e758d8..4da95e684e20 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -27,9 +27,8 @@ struct memory_block { unsigned long start_section_nr; unsigned long state; /* serialized by the dev->lock */ int online_type; /* for passing data to online routine */ - int phys_device; /* to which fru does this belong? */ - struct device dev; int nid; /* NID for this memory block */ + struct device dev; }; int arch_get_memory_phys_device(unsigned long start_pfn); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 15acce5ab106..7288aa5ef73b 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -16,22 +16,7 @@ struct resource; struct vmem_altmap; #ifdef CONFIG_MEMORY_HOTPLUG -/* - * Return page for the valid pfn only if the page is online. All pfn - * walkers which rely on the fully initialized page->flags and others - * should use this rather than pfn_valid && pfn_to_page - */ -#define pfn_to_online_page(pfn) \ -({ \ - struct page *___page = NULL; \ - unsigned long ___pfn = pfn; \ - unsigned long ___nr = pfn_to_section_nr(___pfn); \ - \ - if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \ - pfn_valid_within(___pfn)) \ - ___page = pfn_to_page(___pfn); \ - ___page; \ -}) +struct page *pfn_to_online_page(unsigned long pfn); /* * Types for free bootmem stored in page->lru.next. These have to be in @@ -68,7 +53,7 @@ typedef int __bitwise mhp_t; * with this flag set, the resource pointer must no longer be used as it * might be stale, or the resource might have changed. */ -#define MEMHP_MERGE_RESOURCE ((__force mhp_t)BIT(0)) +#define MHP_MERGE_RESOURCE ((__force mhp_t)BIT(0)) /* * Extended parameters for memory hotplug: @@ -81,6 +66,9 @@ struct mhp_params { pgprot_t pgprot; }; +bool mhp_range_allowed(u64 start, u64 size, bool need_mapping); +struct range mhp_get_pluggable_range(bool need_mapping); + /* * Zone resizing functions * @@ -131,10 +119,10 @@ extern int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params); extern u64 max_mem_size; -extern int memhp_online_type_from_str(const char *str); +extern int mhp_online_type_from_str(const char *str); /* Default online_type (MMOP_*) when new memory blocks are added. */ -extern int memhp_default_online_type; +extern int mhp_default_online_type; /* If movable_node boot option specified */ extern bool movable_node_enabled; static inline bool movable_node_is_enabled(void) @@ -281,6 +269,13 @@ static inline bool movable_node_is_enabled(void) } #endif /* ! CONFIG_MEMORY_HOTPLUG */ +/* + * Keep this declaration outside CONFIG_MEMORY_HOTPLUG as some + * platforms might override and use arch_get_mappable_range() + * for internal non memory hotplug purposes. + */ +struct range arch_get_mappable_range(void); + #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * pgdat resizing functions diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 79c49e7f5c30..f5b464daeeca 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -137,6 +137,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap); +bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); @@ -165,6 +166,11 @@ static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, return NULL; } +static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) +{ + return false; +} + static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { return 0; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b594dc7e779e..aa2560a3d36d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -501,6 +501,9 @@ struct zone { * bootmem allocator): * managed_pages = present_pages - reserved_pages; * + * cma pages is present pages that are assigned for CMA use + * (MIGRATE_CMA). + * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used @@ -525,6 +528,9 @@ struct zone { atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; +#ifdef CONFIG_CMA + unsigned long cma_pages; +#endif const char *name; @@ -622,6 +628,15 @@ static inline unsigned long zone_managed_pages(struct zone *zone) return (unsigned long)atomic_long_read(&zone->managed_pages); } +static inline unsigned long zone_cma_pages(struct zone *zone) +{ +#ifdef CONFIG_CMA + return zone->cma_pages; +#else + return 0; +#endif +} + static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; @@ -901,6 +916,18 @@ static inline int local_memory_node(int node_id) { return node_id; }; */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) +#ifdef CONFIG_ZONE_DEVICE +static inline bool zone_is_zone_device(struct zone *zone) +{ + return zone_idx(zone) == ZONE_DEVICE; +} +#else +static inline bool zone_is_zone_device(struct zone *zone) +{ + return false; +} +#endif + /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than @@ -1289,13 +1316,14 @@ extern size_t mem_section_usage_size(void); * which results in PFN_SECTION_SHIFT equal 6. * To sum it up, at least 6 bits are available. */ -#define SECTION_MARKED_PRESENT (1UL<<0) -#define SECTION_HAS_MEM_MAP (1UL<<1) -#define SECTION_IS_ONLINE (1UL<<2) -#define SECTION_IS_EARLY (1UL<<3) -#define SECTION_MAP_LAST_BIT (1UL<<4) -#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) -#define SECTION_NID_SHIFT 3 +#define SECTION_MARKED_PRESENT (1UL<<0) +#define SECTION_HAS_MEM_MAP (1UL<<1) +#define SECTION_IS_ONLINE (1UL<<2) +#define SECTION_IS_EARLY (1UL<<3) +#define SECTION_TAINT_ZONE_DEVICE (1UL<<4) +#define SECTION_MAP_LAST_BIT (1UL<<5) +#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) +#define SECTION_NID_SHIFT 3 static inline struct page *__section_mem_map_addr(struct mem_section *section) { @@ -1334,6 +1362,13 @@ static inline int online_section(struct mem_section *section) return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } +static inline int online_device_section(struct mem_section *section) +{ + unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; + + return section && ((section->section_mem_map & flags) == flags); +} + static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ddf4cfc12615..f06fbee8638e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1584,6 +1584,12 @@ enum netdev_priv_flags { #define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER #define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK +/* Specifies the type of the struct net_device::ml_priv pointer */ +enum netdev_ml_priv_type { + ML_PRIV_NONE, + ML_PRIV_CAN, +}; + /** * struct net_device - The DEVICE structure. * @@ -1779,6 +1785,7 @@ enum netdev_priv_flags { * @nd_net: Network namespace this network device is inside * * @ml_priv: Mid-layer private + * @ml_priv_type: Mid-layer private type * @lstats: Loopback statistics * @tstats: Tunnel statistics * @dstats: Dummy statistics @@ -2094,8 +2101,10 @@ struct net_device { possible_net_t nd_net; /* mid-layer private */ + void *ml_priv; + enum netdev_ml_priv_type ml_priv_type; + union { - void *ml_priv; struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; @@ -2286,6 +2295,29 @@ static inline void netdev_reset_rx_headroom(struct net_device *dev) netdev_set_rx_headroom(dev, -1); } +static inline void *netdev_get_ml_priv(struct net_device *dev, + enum netdev_ml_priv_type type) +{ + if (dev->ml_priv_type != type) + return NULL; + + return dev->ml_priv; +} + +static inline void netdev_set_ml_priv(struct net_device *dev, + void *ml_priv, + enum netdev_ml_priv_type type) +{ + WARN(dev->ml_priv_type && dev->ml_priv_type != type, + "Overwriting already set ml_priv_type (%u) with different ml_priv_type (%u)!\n", + dev->ml_priv_type, type); + WARN(!dev->ml_priv_type && dev->ml_priv, + "Overwriting already set ml_priv and ml_priv_type is ML_PRIV_NONE!\n"); + + dev->ml_priv = ml_priv; + dev->ml_priv_type = type; +} + /* * Net namespace inlines */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8c6c4e32fc2f..eadaabd18dc7 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -388,6 +388,7 @@ extern int nfs_open(struct inode *, struct file *); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); +extern int nfs_clear_invalid_mapping(struct address_space *mapping); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_revalidate_mapping_rcu(struct inode *inode); @@ -571,8 +572,6 @@ nfs_have_writebacks(struct inode *inode) extern int nfs_readpage(struct file *, struct page *); extern int nfs_readpages(struct file *, struct address_space *, struct list_head *, unsigned); -extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, - struct page *); /* * inline functions diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 38e60ec742df..6f76b32a0238 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -142,7 +142,7 @@ struct nfs_server { struct nlm_host *nlm_host; /* NLM client handle */ struct nfs_iostats __percpu *io_stats; /* I/O statistics */ atomic_long_t writeback; /* number of writeback pages */ - int flags; /* various flags */ + unsigned int flags; /* various flags */ /* The following are for internal use only. Also see uapi/linux/nfs_mount.h */ #define NFS_MOUNT_LOOKUP_CACHE_NONEG 0x10000 @@ -153,6 +153,8 @@ struct nfs_server { #define NFS_MOUNT_LOCAL_FCNTL 0x200000 #define NFS_MOUNT_SOFTERR 0x400000 #define NFS_MOUNT_SOFTREVAL 0x800000 +#define NFS_MOUNT_WRITE_EAGER 0x01000000 +#define NFS_MOUNT_WRITE_WAIT 0x02000000 unsigned int caps; /* server capabilities */ unsigned int rsize; /* read size */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index db914477057b..04a34c08e0a6 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -810,7 +810,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) /* * Flags checked when a page is freed. Pages being freed should not have - * these flags set. It they are, there is a problem. + * these flags set. If they are, there is a problem. */ #define PAGE_FLAGS_CHECK_AT_FREE \ (1UL << PG_lru | 1UL << PG_locked | \ @@ -821,7 +821,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) /* * Flags checked when a page is prepped for return by the page allocator. - * Pages being prepped should not have these flags set. It they are set, + * Pages being prepped should not have these flags set. If they are set, * there has been a kernel bug or struct page corruption. * * __PG_HWPOISON is exceptional because it needs to be kept beyond page's diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d91a1adf80fb..8ebe655f3fd0 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -313,6 +313,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_NOWAIT 0x00000020 #define FGP_FOR_MMAP 0x00000040 #define FGP_HEAD 0x00000080 +#define FGP_ENTRY 0x00000100 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, int fgp_flags, gfp_t cache_gfp_mask); @@ -448,8 +449,7 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) } unsigned find_get_entries(struct address_space *mapping, pgoff_t start, - unsigned int nr_entries, struct page **entries, - pgoff_t *indices); + pgoff_t end, struct pagevec *pvec, pgoff_t *indices); unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages); @@ -757,6 +757,8 @@ extern void __delete_from_page_cache(struct page *page, void *shadow); void replace_page_cache_page(struct page *old, struct page *new); void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec); +loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end, + int whence); /* * Like add_to_page_cache_locked, but used to add newly allocated pages: diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index ad4ddc17d403..7f3f19065a9f 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -25,10 +25,6 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); -unsigned pagevec_lookup_entries(struct pagevec *pvec, - struct address_space *mapping, - pgoff_t start, unsigned nr_entries, - pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 36eb748f3c97..cdfc4e9f253e 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -432,14 +432,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres * To be differentiate with macro pte_mkyoung, this macro is used on platforms * where software maintains page access bit. */ -#ifndef pte_sw_mkyoung -static inline pte_t pte_sw_mkyoung(pte_t pte) -{ - return pte; -} -#define pte_sw_mkyoung pte_sw_mkyoung -#endif - #ifndef pte_savedwrite #define pte_savedwrite pte_write #endif diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index a26542d53058..a6329003aee7 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -12,9 +12,8 @@ #include /* - * If more options are added please update profile_names - * array in platform-profile.c and sysfs-platform-profile.rst - * documentation. + * If more options are added please update profile_names array in + * platform_profile.c and sysfs-platform_profile documentation. */ enum platform_profile_option { @@ -22,6 +21,7 @@ enum platform_profile_option { PLATFORM_PROFILE_COOL, PLATFORM_PROFILE_QUIET, PLATFORM_PROFILE_BALANCED, + PLATFORM_PROFILE_BALANCED_PERFORMANCE, PLATFORM_PROFILE_PERFORMANCE, PLATFORM_PROFILE_LAST, /*must always be last */ }; diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 2a9df80ea887..b5ebf6c01292 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -171,7 +171,7 @@ static inline void ptrace_event(int event, unsigned long message) * * Check whether @event is enabled and, if so, report @event and @pid * to the ptrace parent. @pid is reported as the pid_t seen from the - * the ptrace parent's pid namespace. + * ptrace parent's pid namespace. * * Called without locks. */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 70085ca1a3fc..def5c62c93b3 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -213,7 +213,8 @@ struct page_vma_mapped_walk { static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { - if (pvmw->pte) + /* HugeTLB pte is set to the relevant page table entry without pte_mapped. */ + if (pvmw->pte && !PageHuge(pvmw->page)) pte_unmap(pvmw->pte); if (pvmw->ptl) spin_unlock(pvmw->ptl); diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 9eb430c163c2..3aa5e1e73ab6 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -2,6 +2,7 @@ #ifndef _LINUX_SLAB_DEF_H #define _LINUX_SLAB_DEF_H +#include #include /* @@ -114,6 +115,8 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache, static inline int objs_per_slab_page(const struct kmem_cache *cache, const struct page *page) { + if (is_kfence_address(page_address(page))) + return 1; return cache->num; } diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 1be0ed5befa1..dcde82a4434c 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -7,6 +7,7 @@ * * (C) 2007 SGI, Christoph Lameter */ +#include #include #include @@ -185,6 +186,8 @@ static inline unsigned int __obj_to_index(const struct kmem_cache *cache, static inline unsigned int obj_to_index(const struct kmem_cache *cache, const struct page *page, void *obj) { + if (is_kfence_address(obj)) + return 0; return __obj_to_index(cache, page_address(page), obj); } diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 24d49c732341..6bb4bc1a5f54 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -21,4 +21,13 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); +#ifdef CONFIG_STACKDEPOT +int stack_depot_init(void); +#else +static inline int stack_depot_init(void) +{ + return 0; +} +#endif /* CONFIG_STACKDEPOT */ + #endif diff --git a/include/linux/string.h b/include/linux/string.h index 4fcfb56abcf5..9521d8cab18e 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -266,287 +266,7 @@ void __read_overflow3(void) __compiletime_error("detected read beyond size of ob void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) - -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) -extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); -extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); -extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); -extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); -extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); -extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); -extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); -extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); -extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); -extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); -#else -#define __underlying_memchr __builtin_memchr -#define __underlying_memcmp __builtin_memcmp -#define __underlying_memcpy __builtin_memcpy -#define __underlying_memmove __builtin_memmove -#define __underlying_memset __builtin_memset -#define __underlying_strcat __builtin_strcat -#define __underlying_strcpy __builtin_strcpy -#define __underlying_strlen __builtin_strlen -#define __underlying_strncat __builtin_strncat -#define __underlying_strncpy __builtin_strncpy -#endif - -__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 1); - if (__builtin_constant_p(size) && p_size < size) - __write_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __underlying_strncpy(p, q, size); -} - -__FORTIFY_INLINE char *strcat(char *p, const char *q) -{ - size_t p_size = __builtin_object_size(p, 1); - if (p_size == (size_t)-1) - return __underlying_strcat(p, q); - if (strlcat(p, q, p_size) >= p_size) - fortify_panic(__func__); - return p; -} - -__FORTIFY_INLINE __kernel_size_t strlen(const char *p) -{ - __kernel_size_t ret; - size_t p_size = __builtin_object_size(p, 1); - - /* Work around gcc excess stack consumption issue */ - if (p_size == (size_t)-1 || - (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) - return __underlying_strlen(p); - ret = strnlen(p, p_size); - if (p_size <= ret) - fortify_panic(__func__); - return ret; -} - -extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); -__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) -{ - size_t p_size = __builtin_object_size(p, 1); - __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); - if (p_size <= ret && maxlen != ret) - fortify_panic(__func__); - return ret; -} - -/* defined after fortified strlen to reuse it */ -extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); -__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) -{ - size_t ret; - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); - if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __real_strlcpy(p, q, size); - ret = strlen(q); - if (size) { - size_t len = (ret >= size) ? size - 1 : ret; - if (__builtin_constant_p(len) && len >= p_size) - __write_overflow(); - if (len >= p_size) - fortify_panic(__func__); - __underlying_memcpy(p, q, len); - p[len] = '\0'; - } - return ret; -} - -/* defined after fortified strnlen to reuse it */ -extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); -__FORTIFY_INLINE ssize_t strscpy(char *p, const char *q, size_t size) -{ - size_t len; - /* Use string size rather than possible enclosing struct size. */ - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); - - /* If we cannot get size of p and q default to call strscpy. */ - if (p_size == (size_t) -1 && q_size == (size_t) -1) - return __real_strscpy(p, q, size); - - /* - * If size can be known at compile time and is greater than - * p_size, generate a compile time write overflow error. - */ - if (__builtin_constant_p(size) && size > p_size) - __write_overflow(); - - /* - * This call protects from read overflow, because len will default to q - * length if it smaller than size. - */ - len = strnlen(q, size); - /* - * If len equals size, we will copy only size bytes which leads to - * -E2BIG being returned. - * Otherwise we will copy len + 1 because of the final '\O'. - */ - len = len == size ? size : len + 1; - - /* - * Generate a runtime write overflow error if len is greater than - * p_size. - */ - if (len > p_size) - fortify_panic(__func__); - - /* - * We can now safely call vanilla strscpy because we are protected from: - * 1. Read overflow thanks to call to strnlen(). - * 2. Write overflow thanks to above ifs. - */ - return __real_strscpy(p, q, len); -} - -/* defined after fortified strlen and strnlen to reuse them */ -__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) -{ - size_t p_len, copy_len; - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); - if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __underlying_strncat(p, q, count); - p_len = strlen(p); - copy_len = strnlen(q, count); - if (p_size < p_len + copy_len + 1) - fortify_panic(__func__); - __underlying_memcpy(p + p_len, q, copy_len); - p[p_len + copy_len] = '\0'; - return p; -} - -__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __write_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __underlying_memset(p, c, size); -} - -__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - if (__builtin_constant_p(size)) { - if (p_size < size) - __write_overflow(); - if (q_size < size) - __read_overflow2(); - } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memcpy(p, q, size); -} - -__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - if (__builtin_constant_p(size)) { - if (p_size < size) - __write_overflow(); - if (q_size < size) - __read_overflow2(); - } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memmove(p, q, size); -} - -extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); -__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __read_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __real_memscan(p, c, size); -} - -__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - if (__builtin_constant_p(size)) { - if (p_size < size) - __read_overflow(); - if (q_size < size) - __read_overflow2(); - } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memcmp(p, q, size); -} - -__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __read_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __underlying_memchr(p, c, size); -} - -void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); -__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __read_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __real_memchr_inv(p, c, size); -} - -extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); -__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __read_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __real_kmemdup(p, size, gfp); -} - -/* defined after fortified strlen and memcpy to reuse them */ -__FORTIFY_INLINE char *strcpy(char *p, const char *q) -{ - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); - size_t size; - if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __underlying_strcpy(p, q); - size = strlen(q) + 1; - /* test here to use the more stringent object size */ - if (p_size < size) - fortify_panic(__func__); - memcpy(p, q, size); - return p; -} - -/* Don't use these outside the FORITFY_SOURCE implementation */ -#undef __underlying_memchr -#undef __underlying_memcmp -#undef __underlying_memcpy -#undef __underlying_memmove -#undef __underlying_memset -#undef __underlying_strcat -#undef __underlying_strcpy -#undef __underlying_strlen -#undef __underlying_strncat -#undef __underlying_strncpy +#include #endif /** diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 4d352204e819..cf090af26629 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -575,8 +575,8 @@ static inline u16 get_default_bcdDevice(void) { u16 bcdDevice; - bcdDevice = bin2bcd((LINUX_VERSION_CODE >> 16 & 0xff)) << 8; - bcdDevice |= bin2bcd((LINUX_VERSION_CODE >> 8 & 0xff)); + bcdDevice = bin2bcd(LINUX_VERSION_MAJOR) << 8; + bcdDevice |= bin2bcd(LINUX_VERSION_PATCHLEVEL); return bcdDevice; } diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 0fefeb976877..4ab5494503a8 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -35,6 +35,8 @@ struct vdpa_vq_state { u16 avail_index; }; +struct vdpa_mgmt_dev; + /** * vDPA device - representation of a vDPA device * @dev: underlying device @@ -43,6 +45,8 @@ struct vdpa_vq_state { * @index: device index * @features_valid: were features initialized? for legacy guests * @nvqs: maximum number of supported virtqueues + * @mdev: management device pointer; caller must setup when registering device as part + * of dev_add() mgmtdev ops callback before invoking _vdpa_register_device(). */ struct vdpa_device { struct device dev; @@ -51,6 +55,7 @@ struct vdpa_device { unsigned int index; bool features_valid; int nvqs; + struct vdpa_mgmt_dev *mdev; }; /** @@ -245,20 +250,22 @@ struct vdpa_config_ops { struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, - int nvqs, - size_t size); + int nvqs, size_t size, const char *name); -#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs) \ +#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs, name) \ container_of(__vdpa_alloc_device( \ parent, config, nvqs, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member))), \ + dev_struct, member)), name), \ dev_struct, member) int vdpa_register_device(struct vdpa_device *vdev); void vdpa_unregister_device(struct vdpa_device *vdev); +int _vdpa_register_device(struct vdpa_device *vdev); +void _vdpa_unregister_device(struct vdpa_device *vdev); + /** * vdpa_driver - operations for a vDPA driver * @driver: underlying device driver @@ -336,4 +343,33 @@ static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset, ops->get_config(vdev, offset, buf, len); } +/** + * vdpa_mgmtdev_ops - vdpa device ops + * @dev_add: Add a vdpa device using alloc and register + * @mdev: parent device to use for device addition + * @name: name of the new vdpa device + * Driver need to add a new device using _vdpa_register_device() + * after fully initializing the vdpa device. Driver must return 0 + * on success or appropriate error code. + * @dev_del: Remove a vdpa device using unregister + * @mdev: parent device to use for device removal + * @dev: vdpa device to remove + * Driver need to remove the specified device by calling + * _vdpa_unregister_device(). + */ +struct vdpa_mgmtdev_ops { + int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name); + void (*dev_del)(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev); +}; + +struct vdpa_mgmt_dev { + struct device *device; + const struct vdpa_mgmtdev_ops *ops; + const struct virtio_device_id *id_table; /* supported ids */ + struct list_head list; +}; + +int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev); +void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev); + #endif /* _LINUX_VDPA_H */ diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h new file mode 100644 index 000000000000..f26acbeec965 --- /dev/null +++ b/include/linux/virtio_pci_modern.h @@ -0,0 +1,111 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VIRTIO_PCI_MODERN_H +#define _LINUX_VIRTIO_PCI_MODERN_H + +#include +#include + +struct virtio_pci_modern_device { + struct pci_dev *pci_dev; + + struct virtio_pci_common_cfg __iomem *common; + /* Device-specific data (non-legacy mode) */ + void __iomem *device; + /* Base of vq notifications (non-legacy mode). */ + void __iomem *notify_base; + /* Where to read and clear interrupt */ + u8 __iomem *isr; + + /* So we can sanity-check accesses. */ + size_t notify_len; + size_t device_len; + + /* Capability for when we need to map notifications per-vq. */ + int notify_map_cap; + + /* Multiply queue_notify_off by this value. (non-legacy mode). */ + u32 notify_offset_multiplier; + + int modern_bars; + + struct virtio_device_id id; +}; + +/* + * Type-safe wrappers for io accesses. + * Use these to enforce at compile time the following spec requirement: + * + * The driver MUST access each field using the “natural” access + * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses + * for 16-bit fields and 8-bit accesses for 8-bit fields. + */ +static inline u8 vp_ioread8(const u8 __iomem *addr) +{ + return ioread8(addr); +} +static inline u16 vp_ioread16 (const __le16 __iomem *addr) +{ + return ioread16(addr); +} + +static inline u32 vp_ioread32(const __le32 __iomem *addr) +{ + return ioread32(addr); +} + +static inline void vp_iowrite8(u8 value, u8 __iomem *addr) +{ + iowrite8(value, addr); +} + +static inline void vp_iowrite16(u16 value, __le16 __iomem *addr) +{ + iowrite16(value, addr); +} + +static inline void vp_iowrite32(u32 value, __le32 __iomem *addr) +{ + iowrite32(value, addr); +} + +static inline void vp_iowrite64_twopart(u64 val, + __le32 __iomem *lo, + __le32 __iomem *hi) +{ + vp_iowrite32((u32)val, lo); + vp_iowrite32(val >> 32, hi); +} + +u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev); +void vp_modern_set_features(struct virtio_pci_modern_device *mdev, + u64 features); +u32 vp_modern_generation(struct virtio_pci_modern_device *mdev); +u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev); +void vp_modern_set_status(struct virtio_pci_modern_device *mdev, + u8 status); +u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev, + u16 idx, u16 vector); +u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev, + u16 vector); +void vp_modern_queue_address(struct virtio_pci_modern_device *mdev, + u16 index, u64 desc_addr, u64 driver_addr, + u64 device_addr); +void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev, + u16 idx, bool enable); +bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev, + u16 idx); +void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev, + u16 idx, u16 size); +u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev, + u16 idx); +u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev); +u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev, + u16 idx); +void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off, + size_t minlen, + u32 align, + u32 start, u32 size, + size_t *len); +int vp_modern_probe(struct virtio_pci_modern_device *mdev); +void vp_modern_remove(struct virtio_pci_modern_device *mdev); +#endif diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 773135fc6e19..506d625163a1 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -313,6 +313,12 @@ static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { if (vmstat_item_in_bytes(item)) { + /* + * Only cgroups use subpage accounting right now; at + * the global level, these items still change in + * multiples of whole pages. Store them as pages + * internally to keep the per-cpu counters compact. + */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } diff --git a/include/linux/zpool.h b/include/linux/zpool.h index 51bf43076165..e8997010612a 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -73,6 +73,7 @@ u64 zpool_get_total_size(struct zpool *pool); * @malloc: allocate mem from a pool. * @free: free mem from a pool. * @shrink: shrink the pool. + * @sleep_mapped: whether zpool driver can sleep during map. * @map: map a handle. * @unmap: unmap a handle. * @total_size: get total size of a pool. @@ -100,6 +101,7 @@ struct zpool_driver { int (*shrink)(void *pool, unsigned int pages, unsigned int *reclaimed); + bool sleep_mapped; void *(*map)(void *pool, unsigned long handle, enum zpool_mapmode mm); void (*unmap)(void *pool, unsigned long handle); @@ -112,5 +114,6 @@ void zpool_register_driver(struct zpool_driver *driver); int zpool_unregister_driver(struct zpool_driver *driver); bool zpool_evictable(struct zpool *pool); +bool zpool_can_sleep_mapped(struct zpool *pool); #endif diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index 4807ca4d52e0..2a430e713ce5 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -35,7 +35,7 @@ enum zs_mapmode { struct zs_pool_stats { /* How many pages were migrated (freed) */ - unsigned long pages_compacted; + atomic_long_t pages_compacted; }; struct zs_pool; diff --git a/include/net/icmp.h b/include/net/icmp.h index 9ac2d2672a93..fd84adc47963 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -46,7 +46,11 @@ static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 #if IS_ENABLED(CONFIG_NF_NAT) void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info); #else -#define icmp_ndo_send icmp_send +static inline void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) +{ + struct ip_options opts = { 0 }; + __icmp_send(skb_in, type, code, info, &opts); +} #endif int icmp_rcv(struct sk_buff *skb); diff --git a/include/soc/canaan/k210-sysctl.h b/include/soc/canaan/k210-sysctl.h new file mode 100644 index 000000000000..0c2b2c2dabca --- /dev/null +++ b/include/soc/canaan/k210-sysctl.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ +#ifndef K210_SYSCTL_H +#define K210_SYSCTL_H + +/* + * Kendryte K210 SoC system controller registers offsets. + * Taken from Kendryte SDK (kendryte-standalone-sdk). + */ +#define K210_SYSCTL_GIT_ID 0x00 /* Git short commit id */ +#define K210_SYSCTL_UART_BAUD 0x04 /* Default UARTHS baud rate */ +#define K210_SYSCTL_PLL0 0x08 /* PLL0 controller */ +#define K210_SYSCTL_PLL1 0x0C /* PLL1 controller */ +#define K210_SYSCTL_PLL2 0x10 /* PLL2 controller */ +#define K210_SYSCTL_PLL_LOCK 0x18 /* PLL lock tester */ +#define K210_SYSCTL_ROM_ERROR 0x1C /* AXI ROM detector */ +#define K210_SYSCTL_SEL0 0x20 /* Clock select controller 0 */ +#define K210_SYSCTL_SEL1 0x24 /* Clock select controller 1 */ +#define K210_SYSCTL_EN_CENT 0x28 /* Central clock enable */ +#define K210_SYSCTL_EN_PERI 0x2C /* Peripheral clock enable */ +#define K210_SYSCTL_SOFT_RESET 0x30 /* Soft reset ctrl */ +#define K210_SYSCTL_PERI_RESET 0x34 /* Peripheral reset controller */ +#define K210_SYSCTL_THR0 0x38 /* Clock threshold controller 0 */ +#define K210_SYSCTL_THR1 0x3C /* Clock threshold controller 1 */ +#define K210_SYSCTL_THR2 0x40 /* Clock threshold controller 2 */ +#define K210_SYSCTL_THR3 0x44 /* Clock threshold controller 3 */ +#define K210_SYSCTL_THR4 0x48 /* Clock threshold controller 4 */ +#define K210_SYSCTL_THR5 0x4C /* Clock threshold controller 5 */ +#define K210_SYSCTL_THR6 0x50 /* Clock threshold controller 6 */ +#define K210_SYSCTL_MISC 0x54 /* Miscellaneous controller */ +#define K210_SYSCTL_PERI 0x58 /* Peripheral controller */ +#define K210_SYSCTL_SPI_SLEEP 0x5C /* SPI sleep controller */ +#define K210_SYSCTL_RESET_STAT 0x60 /* Reset source status */ +#define K210_SYSCTL_DMA_SEL0 0x64 /* DMA handshake selector 0 */ +#define K210_SYSCTL_DMA_SEL1 0x68 /* DMA handshake selector 1 */ +#define K210_SYSCTL_POWER_SEL 0x6C /* IO Power Mode Select controller */ + +void k210_clk_early_init(void __iomem *regs); + +#endif diff --git a/include/trace/events/error_report.h b/include/trace/events/error_report.h new file mode 100644 index 000000000000..96f64bf218b2 --- /dev/null +++ b/include/trace/events/error_report.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Declarations for error reporting tracepoints. + * + * Copyright (C) 2021, Google LLC. + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM error_report + +#if !defined(_TRACE_ERROR_REPORT_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_ERROR_REPORT_H + +#include + +#ifndef __ERROR_REPORT_DECLARE_TRACE_ENUMS_ONCE_ONLY +#define __ERROR_REPORT_DECLARE_TRACE_ENUMS_ONCE_ONLY + +enum error_detector { + ERROR_DETECTOR_KFENCE, + ERROR_DETECTOR_KASAN +}; + +#endif /* __ERROR_REPORT_DECLARE_TRACE_ENUMS_ONCE_ONLY */ + +#define error_detector_list \ + EM(ERROR_DETECTOR_KFENCE, "kfence") \ + EMe(ERROR_DETECTOR_KASAN, "kasan") +/* Always end the list with an EMe. */ + +#undef EM +#undef EMe + +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define EMe(a, b) TRACE_DEFINE_ENUM(a); + +error_detector_list + +#undef EM +#undef EMe + +#define EM(a, b) { a, b }, +#define EMe(a, b) { a, b } + +#define show_error_detector_list(val) \ + __print_symbolic(val, error_detector_list) + +DECLARE_EVENT_CLASS(error_report_template, + TP_PROTO(enum error_detector error_detector, unsigned long id), + TP_ARGS(error_detector, id), + TP_STRUCT__entry(__field(enum error_detector, error_detector) + __field(unsigned long, id)), + TP_fast_assign(__entry->error_detector = error_detector; + __entry->id = id;), + TP_printk("[%s] %lx", + show_error_detector_list(__entry->error_detector), + __entry->id)); + +/** + * error_report_end - called after printing the error report + * @error_detector: short string describing the error detection tool + * @id: pseudo-unique descriptor identifying the report + * (e.g. the memory access address) + * + * This event occurs right after a debugging tool finishes printing the error + * report. + */ +DEFINE_EVENT(error_report_template, error_report_end, + TP_PROTO(enum error_detector error_detector, unsigned long id), + TP_ARGS(error_detector, id)); + +#endif /* _TRACE_ERROR_REPORT_H */ + +/* This part must be outside protection */ +#include diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 40845b0d5dad..3a60b6b6db32 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -144,17 +144,17 @@ TRACE_EVENT(kmem_cache_free, TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) - __field( const char *, name ) + __string( name, name ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; - __entry->name = name; + __assign_str(name, name); ), TP_printk("call_site=%pS ptr=%p name=%s", - (void *)__entry->call_site, __entry->ptr, __entry->name) + (void *)__entry->call_site, __entry->ptr, __get_str(name)) ); TRACE_EVENT(mm_page_free, diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 76e85e16854b..c838e7ac1c2d 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -60,6 +60,51 @@ DECLARE_EVENT_CLASS(rpcrdma_completion_class, ), \ TP_ARGS(wc, cid)) +DECLARE_EVENT_CLASS(rpcrdma_receive_completion_class, + TP_PROTO( + const struct ib_wc *wc, + const struct rpc_rdma_cid *cid + ), + + TP_ARGS(wc, cid), + + TP_STRUCT__entry( + __field(u32, cq_id) + __field(int, completion_id) + __field(u32, received) + __field(unsigned long, status) + __field(unsigned int, vendor_err) + ), + + TP_fast_assign( + __entry->cq_id = cid->ci_queue_id; + __entry->completion_id = cid->ci_completion_id; + __entry->status = wc->status; + if (wc->status) { + __entry->received = 0; + __entry->vendor_err = wc->vendor_err; + } else { + __entry->received = wc->byte_len; + __entry->vendor_err = 0; + } + ), + + TP_printk("cq.id=%u cid=%d status=%s (%lu/0x%x) received=%u", + __entry->cq_id, __entry->completion_id, + rdma_show_wc_status(__entry->status), + __entry->status, __entry->vendor_err, + __entry->received + ) +); + +#define DEFINE_RECEIVE_COMPLETION_EVENT(name) \ + DEFINE_EVENT(rpcrdma_receive_completion_class, name, \ + TP_PROTO( \ + const struct ib_wc *wc, \ + const struct rpc_rdma_cid *cid \ + ), \ + TP_ARGS(wc, cid)) + DECLARE_EVENT_CLASS(xprtrdma_reply_class, TP_PROTO( const struct rpcrdma_rep *rep @@ -838,7 +883,8 @@ TRACE_EVENT(xprtrdma_post_linv_err, ** Completion events **/ -DEFINE_COMPLETION_EVENT(xprtrdma_wc_receive); +DEFINE_RECEIVE_COMPLETION_EVENT(xprtrdma_wc_receive); + DEFINE_COMPLETION_EVENT(xprtrdma_wc_send); DEFINE_COMPLETION_EVENT(xprtrdma_wc_fastreg); DEFINE_COMPLETION_EVENT(xprtrdma_wc_li); @@ -1790,7 +1836,7 @@ TRACE_EVENT(svcrdma_post_recv, ) ); -DEFINE_COMPLETION_EVENT(svcrdma_wc_receive); +DEFINE_RECEIVE_COMPLETION_EVENT(svcrdma_wc_receive); TRACE_EVENT(svcrdma_rq_post_err, TP_PROTO( diff --git a/include/uapi/linux/firewire-cdev.h b/include/uapi/linux/firewire-cdev.h index 7e5b5c10a49c..5effa9832802 100644 --- a/include/uapi/linux/firewire-cdev.h +++ b/include/uapi/linux/firewire-cdev.h @@ -844,7 +844,7 @@ struct fw_cdev_queue_iso { * struct fw_cdev_start_iso - Start an isochronous transmission or reception * @cycle: Cycle in which to start I/O. If @cycle is greater than or * equal to 0, the I/O will start on that cycle. - * @sync: Determines the value to wait for for receive packets that have + * @sync: Determines the value to wait for receive packets that have * the %FW_CDEV_ISO_SYNC bit set * @tags: Tag filter bit mask. Only valid for isochronous reception. * Determines the tag values for which packets will be accepted. diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index 9a61c28ed3ae..ee3127461ee0 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -84,7 +84,7 @@ struct input_id { * in units per radian. * When INPUT_PROP_ACCELEROMETER is set the resolution changes. * The main axes (ABS_X, ABS_Y, ABS_Z) are then reported in - * in units per g (units/g) and in units per degree per second + * units per g (units/g) and in units per degree per second * (units/deg/s) for rotational axes (ABS_RX, ABS_RY, ABS_RZ). */ struct input_absinfo { diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h new file mode 100644 index 000000000000..66a41e4ec163 --- /dev/null +++ b/include/uapi/linux/vdpa.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * vdpa device management interface + * Copyright (c) 2020 Mellanox Technologies Ltd. All rights reserved. + */ + +#ifndef _UAPI_LINUX_VDPA_H_ +#define _UAPI_LINUX_VDPA_H_ + +#define VDPA_GENL_NAME "vdpa" +#define VDPA_GENL_VERSION 0x1 + +enum vdpa_command { + VDPA_CMD_UNSPEC, + VDPA_CMD_MGMTDEV_NEW, + VDPA_CMD_MGMTDEV_GET, /* can dump */ + VDPA_CMD_DEV_NEW, + VDPA_CMD_DEV_DEL, + VDPA_CMD_DEV_GET, /* can dump */ +}; + +enum vdpa_attr { + VDPA_ATTR_UNSPEC, + + /* bus name (optional) + dev name together make the parent device handle */ + VDPA_ATTR_MGMTDEV_BUS_NAME, /* string */ + VDPA_ATTR_MGMTDEV_DEV_NAME, /* string */ + VDPA_ATTR_MGMTDEV_SUPPORTED_CLASSES, /* u64 */ + + VDPA_ATTR_DEV_NAME, /* string */ + VDPA_ATTR_DEV_ID, /* u32 */ + VDPA_ATTR_DEV_VENDOR_ID, /* u32 */ + VDPA_ATTR_DEV_MAX_VQS, /* u32 */ + VDPA_ATTR_DEV_MAX_VQ_SIZE, /* u16 */ + + /* new attributes must be added above here */ + VDPA_ATTR_MAX, +}; + +#endif diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index bf3cfc7c35d0..0b1386073d49 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -88,6 +88,13 @@ struct xenbus_device { struct completion down; struct work_struct work; struct semaphore reclaim_sem; + + /* Event channel based statistics and settings. */ + atomic_t event_channels; + atomic_t events; + atomic_t spurious_events; + atomic_t jiffies_eoi_delayed; + unsigned int spurious_threshold; }; static inline struct xenbus_device *to_xenbus_device(struct device *dev) diff --git a/init/Kconfig b/init/Kconfig index 9c02412bc04d..9e6fc6a26ff3 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -19,37 +19,43 @@ config CC_VERSION_TEXT CC_VERSION_TEXT so it is recorded in include/config/auto.conf.cmd. When the compiler is updated, Kconfig will be invoked. - - Ensure full rebuild when the compier is updated + - Ensure full rebuild when the compiler is updated include/linux/kconfig.h contains this option in the comment line so fixdep adds include/config/cc/version/text.h into the auto-generated dependency. When the compiler is updated, syncconfig will touch it and then every file will be rebuilt. config CC_IS_GCC - def_bool $(success,echo "$(CC_VERSION_TEXT)" | grep -q gcc) + def_bool $(success,test "$(cc-name)" = GCC) config GCC_VERSION int - default $(shell,$(srctree)/scripts/gcc-version.sh $(CC)) if CC_IS_GCC + default $(cc-version) if CC_IS_GCC default 0 -config LD_VERSION - int - default $(shell,$(LD) --version | $(srctree)/scripts/ld-version.sh) - config CC_IS_CLANG - def_bool $(success,echo "$(CC_VERSION_TEXT)" | grep -q clang) - -config LD_IS_LLD - def_bool $(success,$(LD) -v | head -n 1 | grep -q LLD) + def_bool $(success,test "$(cc-name)" = Clang) config CLANG_VERSION int - default $(shell,$(srctree)/scripts/clang-version.sh $(CC)) + default $(cc-version) if CC_IS_CLANG + default 0 + +config LD_IS_BFD + def_bool $(success,test "$(ld-name)" = BFD) + +config LD_VERSION + int + default $(ld-version) if LD_IS_BFD + default 0 + +config LD_IS_LLD + def_bool $(success,test "$(ld-name)" = LLD) config LLD_VERSION int - default $(shell,$(srctree)/scripts/lld-version.sh $(LD)) + default $(ld-version) if LD_IS_LLD + default 0 config CC_CAN_LINK bool diff --git a/init/initramfs.c b/init/initramfs.c index 55b74d7e5260..d677e8e717f1 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -45,6 +46,16 @@ static void __init error(char *x) message = x; } +static void panic_show_mem(const char *fmt, ...) +{ + va_list args; + + show_mem(0, NULL); + va_start(args, fmt); + panic(fmt, args); + va_end(args); +} + /* link hash */ #define N_ALIGN(len) ((((len) + 1) & ~3) + 2) @@ -80,7 +91,7 @@ static char __init *find_link(int major, int minor, int ino, } q = kmalloc(sizeof(struct hash), GFP_KERNEL); if (!q) - panic("can't allocate link hash entry"); + panic_show_mem("can't allocate link hash entry"); q->major = major; q->minor = minor; q->ino = ino; @@ -125,7 +136,7 @@ static void __init dir_add(const char *name, time64_t mtime) { struct dir_entry *de = kmalloc(sizeof(struct dir_entry), GFP_KERNEL); if (!de) - panic("can't allocate dir_entry buffer"); + panic_show_mem("can't allocate dir_entry buffer"); INIT_LIST_HEAD(&de->list); de->name = kstrdup(name, GFP_KERNEL); de->mtime = mtime; @@ -460,7 +471,7 @@ static char * __init unpack_to_rootfs(char *buf, unsigned long len) name_buf = kmalloc(N_ALIGN(PATH_MAX), GFP_KERNEL); if (!header_buf || !symlink_buf || !name_buf) - panic("can't allocate buffers"); + panic_show_mem("can't allocate buffers"); state = Start; this_header = 0; @@ -535,6 +546,51 @@ extern unsigned long __initramfs_size; #include #include +void __init reserve_initrd_mem(void) +{ + phys_addr_t start; + unsigned long size; + + /* Ignore the virtul address computed during device tree parsing */ + initrd_start = initrd_end = 0; + + if (!phys_initrd_size) + return; + /* + * Round the memory region to page boundaries as per free_initrd_mem() + * This allows us to detect whether the pages overlapping the initrd + * are in use, but more importantly, reserves the entire set of pages + * as we don't want these pages allocated for other purposes. + */ + start = round_down(phys_initrd_start, PAGE_SIZE); + size = phys_initrd_size + (phys_initrd_start - start); + size = round_up(size, PAGE_SIZE); + + if (!memblock_is_region_memory(start, size)) { + pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region", + (u64)start, size); + goto disable; + } + + if (memblock_is_region_reserved(start, size)) { + pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region\n", + (u64)start, size); + goto disable; + } + + memblock_reserve(start, size); + /* Now convert initrd to virtual addresses */ + initrd_start = (unsigned long)__va(phys_initrd_start); + initrd_end = initrd_start + phys_initrd_size; + initrd_below_start_ok = 1; + + return; +disable: + pr_cont(" - disabling initrd\n"); + initrd_start = 0; + initrd_end = 0; +} + void __weak __init free_initrd_mem(unsigned long start, unsigned long end) { #ifdef CONFIG_ARCH_KEEP_MEMBLOCK @@ -607,7 +663,7 @@ static int __init populate_rootfs(void) /* Load the built in initramfs */ char *err = unpack_to_rootfs(__initramfs_start, __initramfs_size); if (err) - panic("%s", err); /* Failed to decompress INTERNAL initramfs */ + panic_show_mem("%s", err); /* Failed to decompress INTERNAL initramfs */ if (!initrd_start || IS_ENABLED(CONFIG_INITRAMFS_FORCE)) goto done; diff --git a/init/main.c b/init/main.c index e9933cbf60d4..53b278845b88 100644 --- a/init/main.c +++ b/init/main.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include #include @@ -96,6 +97,7 @@ #include #include #include +#include #include #include @@ -824,7 +826,9 @@ static void __init mm_init(void) */ page_ext_init_flatmem(); init_mem_debugging_and_hardening(); + kfence_alloc_pool(); report_meminit(); + stack_depot_init(); mem_init(); /* page_owner must be initialized after buddy is ready */ page_ext_init_flatmem_late(); @@ -955,6 +959,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) hrtimers_init(); softirq_init(); timekeeping_init(); + kfence_init(); /* * For best initial stack canary entropy, prepare it after: @@ -1421,6 +1426,7 @@ static int __ref kernel_init(void *unused) async_synchronize_full(); kprobe_free_init_mem(); ftrace_free_init_mem(); + kgdb_free_init_mem(); free_initmem(); mark_readonly(); diff --git a/init/version.c b/init/version.c index 80d2b7566b39..92afc782b043 100644 --- a/init/version.c +++ b/init/version.c @@ -16,14 +16,6 @@ #include #include -#ifndef CONFIG_KALLSYMS -#define version(a) Version_ ## a -#define version_string(a) version(a) - -extern int version_string(LINUX_VERSION_CODE); -int version_string(LINUX_VERSION_CODE); -#endif - struct uts_namespace init_uts_ns = { .ns.count = REFCOUNT_INIT(2), .name = { diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index b636d517c02c..4708aec492df 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -455,6 +455,17 @@ int dbg_remove_all_break(void) return 0; } +void kgdb_free_init_mem(void) +{ + int i; + + /* Clear init memory breakpoints. */ + for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) { + if (init_section_contains((void *)kgdb_break[i].bpt_addr, 0)) + kgdb_break[i].state = BP_UNDEFINED; + } +} + #ifdef CONFIG_KGDB_KDB void kdb_dump_stack_on_cpu(int cpu) { diff --git a/kernel/events/core.c b/kernel/events/core.c index cc36f7546d7d..ec99baf58c2d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -269,7 +269,7 @@ static void event_function_call(struct perf_event *event, event_f func, void *da if (!event->parent) { /* * If this is a !child event, we must hold ctx::mutex to - * stabilize the the event->ctx relation. See + * stabilize the event->ctx relation. See * perf_event_ctx_lock(). */ lockdep_assert_held(&ctx->mutex); @@ -1303,7 +1303,7 @@ static void put_ctx(struct perf_event_context *ctx) * life-time rules separate them. That is an exiting task cannot fork, and a * spawning task cannot (yet) exit. * - * But remember that that these are parent<->child context relations, and + * But remember that these are parent<->child context relations, and * migration does not affect children, therefore these two orderings should not * interact. * @@ -1442,7 +1442,7 @@ static u64 primary_event_id(struct perf_event *event) /* * Get the perf_event_context for a task and lock it. * - * This has to cope with with the fact that until it is locked, + * This has to cope with the fact that until it is locked, * the context could get moved to another task. */ static struct perf_event_context * @@ -2486,7 +2486,7 @@ static void perf_set_shadow_time(struct perf_event *event, * But this is a bit hairy. * * So instead, we have an explicit cgroup call to remain - * within the time time source all along. We believe it + * within the time source all along. We believe it * is cleaner and simpler to understand. */ if (is_cgroup_event(event)) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 3ea7f8f92f1d..6addc9780319 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1733,7 +1733,7 @@ void uprobe_free_utask(struct task_struct *t) } /* - * Allocate a uprobe_task object for the task if if necessary. + * Allocate a uprobe_task object for the task if necessary. * Called when the thread hits a breakpoint. * * Returns: diff --git a/kernel/groups.c b/kernel/groups.c index fe7e6385530e..787b381c7c00 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -15,12 +15,7 @@ struct group_info *groups_alloc(int gidsetsize) { struct group_info *gi; - unsigned int len; - - len = sizeof(struct group_info) + sizeof(kgid_t) * gidsetsize; - gi = kmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_NOWARN|__GFP_NORETRY); - if (!gi) - gi = __vmalloc(len, GFP_KERNEL_ACCOUNT); + gi = kvmalloc(struct_size(gi, gid, gidsetsize), GFP_KERNEL_ACCOUNT); if (!gi) return NULL; diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 39d30ccf8d87..48aaf2ac0d0d 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -13,8 +13,6 @@ void kimage_terminate(struct kimage *image); int kimage_is_destination_range(struct kimage *image, unsigned long start, unsigned long end); -int machine_kexec_post_load(struct kimage *image); - extern struct mutex kexec_mutex; #ifdef CONFIG_KEXEC_FILE diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 03b21135313c..48fff6437901 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1420,7 +1420,7 @@ rt_mutex_fasttrylock(struct rt_mutex *lock, } /* - * Performs the wakeup of the the top-waiter and re-enables preemption. + * Performs the wakeup of the top-waiter and re-enables preemption. */ void rt_mutex_postunlock(struct wake_q_head *wake_q) { @@ -1819,7 +1819,7 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock) * been started. * @waiter: the pre-initialized rt_mutex_waiter * - * Wait for the the lock acquisition started on our behalf by + * Wait for the lock acquisition started on our behalf by * rt_mutex_start_proxy_lock(). Upon failure, the caller must call * rt_mutex_cleanup_proxy_lock(). * diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 218671c9463c..d9f478233626 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1065,7 +1065,7 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) /* * If there were already threads queued before us and: - * 1) there are no no active locks, wake the front + * 1) there are no active locks, wake the front * queued process(es) as the handoff bit might be set. * 2) there are no active writers and some readers, the lock * must be read owned; so we try to wake any read lock diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c index d9dd94defc0a..9aa855a96c4a 100644 --- a/kernel/locking/semaphore.c +++ b/kernel/locking/semaphore.c @@ -119,7 +119,7 @@ EXPORT_SYMBOL(down_killable); * @sem: the semaphore to be acquired * * Try to acquire the semaphore atomically. Returns 0 if the semaphore has - * been acquired successfully or 1 if it it cannot be acquired. + * been acquired successfully or 1 if it cannot be acquired. * * NOTE: This return value is inverted from both spin_trylock and * mutex_trylock! Be careful about this when converting code. diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index feff7b7fd0f0..83e856e0bf15 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5129,7 +5129,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) /* * When a group wakes up we want to make sure that its quota is not already * expired/exceeded, otherwise it may be allowed to steal additional ticks of - * runtime as update_curr() throttling can not not trigger until it's on-rq. + * runtime as update_curr() throttling can not trigger until it's on-rq. */ static void check_enqueue_throttle(struct cfs_rq *cfs_rq) { diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 08ae45ad9261..acdae625c636 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -454,7 +454,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm) /* * For each cpu runqueue, if the task's mm match @mm, ensure that all - * @mm's membarrier state set bits are also set in in the runqueue's + * @mm's membarrier state set bits are also set in the runqueue's * membarrier state. This ensures that a runqueue scheduling * between threads which are users of @mm has its membarrier state * updated. diff --git a/kernel/sys.c b/kernel/sys.c index 2e6855b2bca4..fc5c7ef5b57b 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1244,7 +1244,7 @@ static int override_release(char __user *release, size_t len) break; rest++; } - v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 60; + v = LINUX_VERSION_PATCHLEVEL + 60; copy = clamp_t(size_t, len, 1, sizeof(buf)); copy = scnprintf(buf, copy, "2.6.%u%s", v, rest); ret = copy_to_user(release, buf, copy + 1); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c89ea7424305..a56202f01488 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2973,7 +2973,7 @@ static struct ctl_table vm_table[] = { .data = &block_dump, .maxlen = sizeof(block_dump), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { @@ -2981,7 +2981,7 @@ static struct ctl_table vm_table[] = { .data = &sysctl_vfs_cache_pressure, .maxlen = sizeof(sysctl_vfs_cache_pressure), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \ @@ -2991,7 +2991,7 @@ static struct ctl_table vm_table[] = { .data = &sysctl_legacy_va_layout, .maxlen = sizeof(sysctl_legacy_va_layout), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #endif @@ -3001,7 +3001,7 @@ static struct ctl_table vm_table[] = { .data = &node_reclaim_mode, .maxlen = sizeof(node_reclaim_mode), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 7e44cea89fdc..b28d3e5013cd 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -81,6 +81,7 @@ obj-$(CONFIG_SYNTH_EVENTS) += trace_events_synth.o obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o +obj-$(CONFIG_TRACEPOINTS) += error_report-traces.o obj-$(CONFIG_TRACEPOINTS) += power-traces.o ifeq ($(CONFIG_PM),y) obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o diff --git a/kernel/trace/error_report-traces.c b/kernel/trace/error_report-traces.c new file mode 100644 index 000000000000..f89792c25b11 --- /dev/null +++ b/kernel/trace/error_report-traces.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Error reporting trace points. + * + * Copyright (C) 2021, Google LLC. + */ + +#define CREATE_TRACE_POINTS +#include + +EXPORT_TRACEPOINT_SYMBOL_GPL(error_report_end); diff --git a/lib/Kconfig b/lib/Kconfig index 46806332a8cc..a38cc61256f1 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -651,6 +651,15 @@ config STACKDEPOT bool select STACKTRACE +config STACK_HASH_ORDER + int "stack depot hash size (12 => 4KB, 20 => 1024KB)" + range 12 20 + default 20 + depends on STACKDEPOT + help + Select the hash size as a power of 2 for the stackdepot hash table. + Choose a lower value to reduce the memory impact. + config SBITMAP bool diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 5ea0c1773b0a..2779c29d9981 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -256,14 +256,51 @@ config DEBUG_INFO_SPLIT to know about the .dwo files and include them. Incompatible with older versions of ccache. -config DEBUG_INFO_DWARF4 - bool "Generate dwarf4 debuginfo" - depends on $(cc-option,-gdwarf-4) +choice + prompt "DWARF version" help - Generate dwarf4 debug info. This requires recent versions - of gcc and gdb. It makes the debug information larger. - But it significantly improves the success of resolving - variables in gdb on optimized code. + Which version of DWARF debug info to emit. + +config DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT + bool "Rely on the toolchain's implicit default DWARF version" + help + The implicit default version of DWARF debug info produced by a + toolchain changes over time. + + This can break consumers of the debug info that haven't upgraded to + support newer revisions, and prevent testing newer versions, but + those should be less common scenarios. + + If unsure, say Y. + +config DEBUG_INFO_DWARF4 + bool "Generate DWARF Version 4 debuginfo" + help + Generate DWARF v4 debug info. This requires gcc 4.5+ and gdb 7.0+. + + If you have consumers of DWARF debug info that are not ready for + newer revisions of DWARF, you may wish to choose this or have your + config select this. + +config DEBUG_INFO_DWARF5 + bool "Generate DWARF Version 5 debuginfo" + depends on GCC_VERSION >= 50000 || CC_IS_CLANG + depends on CC_IS_GCC || $(success,$(srctree)/scripts/test_dwarf5_support.sh $(CC) $(CLANG_FLAGS)) + depends on !DEBUG_INFO_BTF + help + Generate DWARF v5 debug info. Requires binutils 2.35.2, gcc 5.0+ (gcc + 5.0+ accepts the -gdwarf-5 flag but only had partial support for some + draft features until 7.0), and gdb 8.0+. + + Changes to the structure of debug info in Version 5 allow for around + 15-18% savings in resulting image and debug info section sizes as + compared to DWARF Version 4. DWARF Version 5 standardizes previous + extensions such as accelerators for symbol indexing and the format + for fission (.dwo/.dwp) files. Users may not want to select this + config if they rely on tooling that has not yet been updated to + support DWARF Version 5. + +endchoice # "DWARF version" config DEBUG_INFO_BTF bool "Generate BTF typeinfo" @@ -901,6 +938,7 @@ config DEBUG_STACKOVERFLOW If in doubt, say "N". source "lib/Kconfig.kasan" +source "lib/Kconfig.kfence" endmenu # "Memory Debugging" diff --git a/lib/Kconfig.kfence b/lib/Kconfig.kfence new file mode 100644 index 000000000000..78f50ccb3b45 --- /dev/null +++ b/lib/Kconfig.kfence @@ -0,0 +1,82 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config HAVE_ARCH_KFENCE + bool + +menuconfig KFENCE + bool "KFENCE: low-overhead sampling-based memory safety error detector" + depends on HAVE_ARCH_KFENCE && (SLAB || SLUB) + select STACKTRACE + help + KFENCE is a low-overhead sampling-based detector of heap out-of-bounds + access, use-after-free, and invalid-free errors. KFENCE is designed + to have negligible cost to permit enabling it in production + environments. + + See for more details. + + Note that, KFENCE is not a substitute for explicit testing with tools + such as KASAN. KFENCE can detect a subset of bugs that KASAN can + detect, albeit at very different performance profiles. If you can + afford to use KASAN, continue using KASAN, for example in test + environments. If your kernel targets production use, and cannot + enable KASAN due to its cost, consider using KFENCE. + +if KFENCE + +config KFENCE_STATIC_KEYS + bool "Use static keys to set up allocations" + default y + depends on JUMP_LABEL # To ensure performance, require jump labels + help + Use static keys (static branches) to set up KFENCE allocations. Using + static keys is normally recommended, because it avoids a dynamic + branch in the allocator's fast path. However, with very low sample + intervals, or on systems that do not support jump labels, a dynamic + branch may still be an acceptable performance trade-off. + +config KFENCE_SAMPLE_INTERVAL + int "Default sample interval in milliseconds" + default 100 + help + The KFENCE sample interval determines the frequency with which heap + allocations will be guarded by KFENCE. May be overridden via boot + parameter "kfence.sample_interval". + + Set this to 0 to disable KFENCE by default, in which case only + setting "kfence.sample_interval" to a non-zero value enables KFENCE. + +config KFENCE_NUM_OBJECTS + int "Number of guarded objects available" + range 1 65535 + default 255 + help + The number of guarded objects available. For each KFENCE object, 2 + pages are required; with one containing the object and two adjacent + ones used as guard pages. + +config KFENCE_STRESS_TEST_FAULTS + int "Stress testing of fault handling and error reporting" if EXPERT + default 0 + help + The inverse probability with which to randomly protect KFENCE object + pages, resulting in spurious use-after-frees. The main purpose of + this option is to stress test KFENCE with concurrent error reports + and allocations/frees. A value of 0 disables stress testing logic. + + Only for KFENCE testing; set to 0 if you are not a KFENCE developer. + +config KFENCE_KUNIT_TEST + tristate "KFENCE integration test suite" if !KUNIT_ALL_TESTS + default KUNIT_ALL_TESTS + depends on TRACEPOINTS && KUNIT + help + Test suite for KFENCE, testing various error detection scenarios with + various allocation types, and checking that reports are correctly + output to console. + + Say Y here if you want the test to be built into the kernel and run + during boot; say M if you want the test to build as a module; say N + if you are unsure. + +endif # KFENCE diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index f09d33be44dc..661f13a214ba 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -112,23 +112,6 @@ config UBSAN_UNREACHABLE This option enables -fsanitize=unreachable which checks for control flow reaching an expected-to-be-unreachable position. -config UBSAN_SIGNED_OVERFLOW - bool "Perform checking for signed arithmetic overflow" - default UBSAN - depends on $(cc-option,-fsanitize=signed-integer-overflow) - help - This option enables -fsanitize=signed-integer-overflow which checks - for overflow of any arithmetic operations with signed integers. - -config UBSAN_UNSIGNED_OVERFLOW - bool "Perform checking for unsigned arithmetic overflow" - depends on $(cc-option,-fsanitize=unsigned-integer-overflow) - depends on !X86_32 # avoid excessive stack usage on x86-32/clang - help - This option enables -fsanitize=unsigned-integer-overflow which checks - for overflow of any arithmetic operations with unsigned integers. This - currently causes x86 to fail to boot. - config UBSAN_OBJECT_SIZE bool "Perform checking for accesses beyond the end of objects" default UBSAN diff --git a/lib/cmdline.c b/lib/cmdline.c index dfd4c4423f9a..5d474c626e24 100644 --- a/lib/cmdline.c +++ b/lib/cmdline.c @@ -228,7 +228,6 @@ char *next_arg(char *args, char **param, char **val) { unsigned int i, equals = 0; int in_quote = 0, quoted = 0; - char *next; if (*args == '"') { args++; @@ -266,10 +265,10 @@ char *next_arg(char *args, char **param, char **val) if (args[i]) { args[i] = '\0'; - next = args + i + 1; + args += i + 1; } else - next = args + i; + args += i; /* Chew up trailing spaces. */ - return skip_spaces(next); + return skip_spaces(args); } diff --git a/lib/genalloc.c b/lib/genalloc.c index dab97bb69df6..5dcf9cdcbc46 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -81,7 +81,8 @@ static int clear_bits_ll(unsigned long *addr, unsigned long mask_to_clear) * users set the same bit, one user will return remain bits, otherwise * return 0. */ -static int bitmap_set_ll(unsigned long *map, unsigned long start, unsigned long nr) +static unsigned long +bitmap_set_ll(unsigned long *map, unsigned long start, unsigned long nr) { unsigned long *p = map + BIT_WORD(start); const unsigned long size = start + nr; diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 890dcc2e984e..49f67a0c6e5d 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -31,6 +31,7 @@ #include #include #include +#include #define DEPOT_STACK_BITS (sizeof(depot_stack_handle_t) * 8) @@ -141,14 +142,38 @@ static struct stack_record *depot_alloc_stack(unsigned long *entries, int size, return stack; } -#define STACK_HASH_ORDER 20 -#define STACK_HASH_SIZE (1L << STACK_HASH_ORDER) +#define STACK_HASH_SIZE (1L << CONFIG_STACK_HASH_ORDER) #define STACK_HASH_MASK (STACK_HASH_SIZE - 1) #define STACK_HASH_SEED 0x9747b28c -static struct stack_record *stack_table[STACK_HASH_SIZE] = { - [0 ... STACK_HASH_SIZE - 1] = NULL -}; +static bool stack_depot_disable; +static struct stack_record **stack_table; + +static int __init is_stack_depot_disabled(char *str) +{ + int ret; + + ret = kstrtobool(str, &stack_depot_disable); + if (!ret && stack_depot_disable) { + pr_info("Stack Depot is disabled\n"); + stack_table = NULL; + } + return 0; +} +early_param("stack_depot_disable", is_stack_depot_disabled); + +int __init stack_depot_init(void) +{ + if (!stack_depot_disable) { + size_t size = (STACK_HASH_SIZE * sizeof(struct stack_record *)); + int i; + + stack_table = memblock_alloc(size, size); + for (i = 0; i < STACK_HASH_SIZE; i++) + stack_table[i] = NULL; + } + return 0; +} /* Calculate hash for a stack */ static inline u32 hash_stack(unsigned long *entries, unsigned int size) @@ -242,7 +267,7 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned long flags; u32 hash; - if (unlikely(nr_entries == 0)) + if (unlikely(nr_entries == 0) || stack_depot_disable) goto fast_exit; hash = hash_stack(entries, nr_entries); diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 25576303897b..e5647d147b35 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -252,11 +252,14 @@ static void kmalloc_large_oob_right(struct kunit *test) kfree(ptr); } -static void kmalloc_oob_krealloc_more(struct kunit *test) +static void krealloc_more_oob_helper(struct kunit *test, + size_t size1, size_t size2) { char *ptr1, *ptr2; - size_t size1 = 17; - size_t size2 = 19; + size_t middle; + + KUNIT_ASSERT_LT(test, size1, size2); + middle = size1 + (size2 - size1) / 2; ptr1 = kmalloc(size1, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1); @@ -264,15 +267,31 @@ static void kmalloc_oob_krealloc_more(struct kunit *test) ptr2 = krealloc(ptr1, size2, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2); - KUNIT_EXPECT_KASAN_FAIL(test, ptr2[size2 + OOB_TAG_OFF] = 'x'); + /* All offsets up to size2 must be accessible. */ + ptr2[size1 - 1] = 'x'; + ptr2[size1] = 'x'; + ptr2[middle] = 'x'; + ptr2[size2 - 1] = 'x'; + + /* Generic mode is precise, so unaligned size2 must be inaccessible. */ + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) + KUNIT_EXPECT_KASAN_FAIL(test, ptr2[size2] = 'x'); + + /* For all modes first aligned offset after size2 must be inaccessible. */ + KUNIT_EXPECT_KASAN_FAIL(test, + ptr2[round_up(size2, KASAN_GRANULE_SIZE)] = 'x'); + kfree(ptr2); } -static void kmalloc_oob_krealloc_less(struct kunit *test) +static void krealloc_less_oob_helper(struct kunit *test, + size_t size1, size_t size2) { char *ptr1, *ptr2; - size_t size1 = 17; - size_t size2 = 15; + size_t middle; + + KUNIT_ASSERT_LT(test, size2, size1); + middle = size2 + (size1 - size2) / 2; ptr1 = kmalloc(size1, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1); @@ -280,10 +299,79 @@ static void kmalloc_oob_krealloc_less(struct kunit *test) ptr2 = krealloc(ptr1, size2, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2); - KUNIT_EXPECT_KASAN_FAIL(test, ptr2[size2 + OOB_TAG_OFF] = 'x'); + /* Must be accessible for all modes. */ + ptr2[size2 - 1] = 'x'; + + /* Generic mode is precise, so unaligned size2 must be inaccessible. */ + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) + KUNIT_EXPECT_KASAN_FAIL(test, ptr2[size2] = 'x'); + + /* For all modes first aligned offset after size2 must be inaccessible. */ + KUNIT_EXPECT_KASAN_FAIL(test, + ptr2[round_up(size2, KASAN_GRANULE_SIZE)] = 'x'); + + /* + * For all modes all size2, middle, and size1 should land in separate + * granules and thus the latter two offsets should be inaccessible. + */ + KUNIT_EXPECT_LE(test, round_up(size2, KASAN_GRANULE_SIZE), + round_down(middle, KASAN_GRANULE_SIZE)); + KUNIT_EXPECT_LE(test, round_up(middle, KASAN_GRANULE_SIZE), + round_down(size1, KASAN_GRANULE_SIZE)); + KUNIT_EXPECT_KASAN_FAIL(test, ptr2[middle] = 'x'); + KUNIT_EXPECT_KASAN_FAIL(test, ptr2[size1 - 1] = 'x'); + KUNIT_EXPECT_KASAN_FAIL(test, ptr2[size1] = 'x'); + kfree(ptr2); } +static void krealloc_more_oob(struct kunit *test) +{ + krealloc_more_oob_helper(test, 201, 235); +} + +static void krealloc_less_oob(struct kunit *test) +{ + krealloc_less_oob_helper(test, 235, 201); +} + +static void krealloc_pagealloc_more_oob(struct kunit *test) +{ + /* page_alloc fallback in only implemented for SLUB. */ + KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_SLUB); + + krealloc_more_oob_helper(test, KMALLOC_MAX_CACHE_SIZE + 201, + KMALLOC_MAX_CACHE_SIZE + 235); +} + +static void krealloc_pagealloc_less_oob(struct kunit *test) +{ + /* page_alloc fallback in only implemented for SLUB. */ + KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_SLUB); + + krealloc_less_oob_helper(test, KMALLOC_MAX_CACHE_SIZE + 235, + KMALLOC_MAX_CACHE_SIZE + 201); +} + +/* + * Check that krealloc() detects a use-after-free, returns NULL, + * and doesn't unpoison the freed object. + */ +static void krealloc_uaf(struct kunit *test) +{ + char *ptr1, *ptr2; + int size1 = 201; + int size2 = 235; + + ptr1 = kmalloc(size1, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1); + kfree(ptr1); + + KUNIT_EXPECT_KASAN_FAIL(test, ptr2 = krealloc(ptr1, size2, GFP_KERNEL)); + KUNIT_ASSERT_PTR_EQ(test, (void *)ptr2, NULL); + KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)ptr1); +} + static void kmalloc_oob_16(struct kunit *test) { struct { @@ -977,8 +1065,11 @@ static struct kunit_case kasan_kunit_test_cases[] = { KUNIT_CASE(pagealloc_oob_right), KUNIT_CASE(pagealloc_uaf), KUNIT_CASE(kmalloc_large_oob_right), - KUNIT_CASE(kmalloc_oob_krealloc_more), - KUNIT_CASE(kmalloc_oob_krealloc_less), + KUNIT_CASE(krealloc_more_oob), + KUNIT_CASE(krealloc_less_oob), + KUNIT_CASE(krealloc_pagealloc_more_oob), + KUNIT_CASE(krealloc_pagealloc_less_oob), + KUNIT_CASE(krealloc_uaf), KUNIT_CASE(kmalloc_oob_16), KUNIT_CASE(kmalloc_uaf_16), KUNIT_CASE(kmalloc_oob_in_memset), diff --git a/lib/test_ubsan.c b/lib/test_ubsan.c index 5e5d9355ef49..7e7bbd0f3fd2 100644 --- a/lib/test_ubsan.c +++ b/lib/test_ubsan.c @@ -11,51 +11,6 @@ typedef void(*test_ubsan_fp)(void); #config, IS_ENABLED(config) ? "y" : "n"); \ } while (0) -static void test_ubsan_add_overflow(void) -{ - volatile int val = INT_MAX; - volatile unsigned int uval = UINT_MAX; - - UBSAN_TEST(CONFIG_UBSAN_SIGNED_OVERFLOW); - val += 2; - - UBSAN_TEST(CONFIG_UBSAN_UNSIGNED_OVERFLOW); - uval += 2; -} - -static void test_ubsan_sub_overflow(void) -{ - volatile int val = INT_MIN; - volatile unsigned int uval = 0; - volatile int val2 = 2; - - UBSAN_TEST(CONFIG_UBSAN_SIGNED_OVERFLOW); - val -= val2; - - UBSAN_TEST(CONFIG_UBSAN_UNSIGNED_OVERFLOW); - uval -= val2; -} - -static void test_ubsan_mul_overflow(void) -{ - volatile int val = INT_MAX / 2; - volatile unsigned int uval = UINT_MAX / 2; - - UBSAN_TEST(CONFIG_UBSAN_SIGNED_OVERFLOW); - val *= 3; - - UBSAN_TEST(CONFIG_UBSAN_UNSIGNED_OVERFLOW); - uval *= 3; -} - -static void test_ubsan_negate_overflow(void) -{ - volatile int val = INT_MIN; - - UBSAN_TEST(CONFIG_UBSAN_SIGNED_OVERFLOW); - val = -val; -} - static void test_ubsan_divrem_overflow(void) { volatile int val = 16; @@ -155,10 +110,6 @@ static void test_ubsan_object_size_mismatch(void) } static const test_ubsan_fp test_ubsan_array[] = { - test_ubsan_add_overflow, - test_ubsan_sub_overflow, - test_ubsan_mul_overflow, - test_ubsan_negate_overflow, test_ubsan_shift_out_of_bounds, test_ubsan_out_of_bounds, test_ubsan_load_invalid_value, diff --git a/lib/ubsan.c b/lib/ubsan.c index bec38c64d6a6..26229973049d 100644 --- a/lib/ubsan.c +++ b/lib/ubsan.c @@ -163,74 +163,6 @@ static void ubsan_epilogue(void) } } -static void handle_overflow(struct overflow_data *data, void *lhs, - void *rhs, char op) -{ - - struct type_descriptor *type = data->type; - char lhs_val_str[VALUE_LENGTH]; - char rhs_val_str[VALUE_LENGTH]; - - if (suppress_report(&data->location)) - return; - - ubsan_prologue(&data->location, type_is_signed(type) ? - "signed-integer-overflow" : - "unsigned-integer-overflow"); - - val_to_string(lhs_val_str, sizeof(lhs_val_str), type, lhs); - val_to_string(rhs_val_str, sizeof(rhs_val_str), type, rhs); - pr_err("%s %c %s cannot be represented in type %s\n", - lhs_val_str, - op, - rhs_val_str, - type->type_name); - - ubsan_epilogue(); -} - -void __ubsan_handle_add_overflow(void *data, - void *lhs, void *rhs) -{ - - handle_overflow(data, lhs, rhs, '+'); -} -EXPORT_SYMBOL(__ubsan_handle_add_overflow); - -void __ubsan_handle_sub_overflow(void *data, - void *lhs, void *rhs) -{ - handle_overflow(data, lhs, rhs, '-'); -} -EXPORT_SYMBOL(__ubsan_handle_sub_overflow); - -void __ubsan_handle_mul_overflow(void *data, - void *lhs, void *rhs) -{ - handle_overflow(data, lhs, rhs, '*'); -} -EXPORT_SYMBOL(__ubsan_handle_mul_overflow); - -void __ubsan_handle_negate_overflow(void *_data, void *old_val) -{ - struct overflow_data *data = _data; - char old_val_str[VALUE_LENGTH]; - - if (suppress_report(&data->location)) - return; - - ubsan_prologue(&data->location, "negation-overflow"); - - val_to_string(old_val_str, sizeof(old_val_str), data->type, old_val); - - pr_err("negation of %s cannot be represented in type %s:\n", - old_val_str, data->type->type_name); - - ubsan_epilogue(); -} -EXPORT_SYMBOL(__ubsan_handle_negate_overflow); - - void __ubsan_handle_divrem_overflow(void *_data, void *lhs, void *rhs) { struct overflow_data *data = _data; diff --git a/mm/Makefile b/mm/Makefile index 135bbb65511a..72227b24a616 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -81,6 +81,7 @@ obj-$(CONFIG_PAGE_POISONING) += page_poison.o obj-$(CONFIG_SLAB) += slab.o obj-$(CONFIG_SLUB) += slub.o obj-$(CONFIG_KASAN) += kasan/ +obj-$(CONFIG_KFENCE) += kfence/ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_MEMTEST) += memtest.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index eca555f658d9..576220acd686 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -578,7 +579,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, { struct bdi_writeback *wb; - might_sleep_if(gfpflags_allow_blocking(gfp)); + might_alloc(gfp); if (!memcg_css->parent) return &bdi->wb; diff --git a/mm/cma.c b/mm/cma.c index 844d4d71fd2b..1699287879e7 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -98,34 +98,29 @@ static void cma_clear_bitmap(struct cma *cma, unsigned long pfn, static void __init cma_activate_area(struct cma *cma) { - unsigned long base_pfn = cma->base_pfn, pfn = base_pfn; - unsigned i = cma->count >> pageblock_order; + unsigned long base_pfn = cma->base_pfn, pfn; struct zone *zone; cma->bitmap = bitmap_zalloc(cma_bitmap_maxno(cma), GFP_KERNEL); if (!cma->bitmap) goto out_error; - WARN_ON_ONCE(!pfn_valid(pfn)); - zone = page_zone(pfn_to_page(pfn)); + /* + * alloc_contig_range() requires the pfn range specified to be in the + * same zone. Simplify by forcing the entire CMA resv range to be in the + * same zone. + */ + WARN_ON_ONCE(!pfn_valid(base_pfn)); + zone = page_zone(pfn_to_page(base_pfn)); + for (pfn = base_pfn + 1; pfn < base_pfn + cma->count; pfn++) { + WARN_ON_ONCE(!pfn_valid(pfn)); + if (page_zone(pfn_to_page(pfn)) != zone) + goto not_in_zone; + } - do { - unsigned j; - - base_pfn = pfn; - for (j = pageblock_nr_pages; j; --j, pfn++) { - WARN_ON_ONCE(!pfn_valid(pfn)); - /* - * alloc_contig_range requires the pfn range - * specified to be in the same zone. Make this - * simple by forcing the entire CMA resv range - * to be in the same zone. - */ - if (page_zone(pfn_to_page(pfn)) != zone) - goto not_in_zone; - } - init_cma_reserved_pageblock(pfn_to_page(base_pfn)); - } while (--i); + for (pfn = base_pfn; pfn < base_pfn + cma->count; + pfn += pageblock_nr_pages) + init_cma_reserved_pageblock(pfn_to_page(pfn)); mutex_init(&cma->lock); @@ -139,6 +134,10 @@ static void __init cma_activate_area(struct cma *cma) not_in_zone: bitmap_free(cma->bitmap); out_error: + /* Expose all pages to the buddy, they are useless for CMA. */ + for (pfn = base_pfn; pfn < base_pfn + cma->count; pfn++) + free_reserved_page(pfn_to_page(pfn)); + totalcma_pages -= cma->count; cma->count = 0; pr_err("CMA area %s could not be activated\n", cma->name); return; @@ -340,6 +339,23 @@ int __init cma_declare_contiguous_nid(phys_addr_t base, limit = highmem_start; } + /* + * If there is enough memory, try a bottom-up allocation first. + * It will place the new cma area close to the start of the node + * and guarantee that the compaction is moving pages out of the + * cma area and not into it. + * Avoid using first 4GB to not interfere with constrained zones + * like DMA/DMA32. + */ +#ifdef CONFIG_PHYS_ADDR_T_64BIT + if (!memblock_bottom_up() && memblock_end >= SZ_4G + size) { + memblock_set_bottom_up(true); + addr = memblock_alloc_range_nid(size, alignment, SZ_4G, + limit, nid, true); + memblock_set_bottom_up(false); + } +#endif + if (!addr) { addr = memblock_alloc_range_nid(size, alignment, base, limit, nid, true); @@ -510,8 +526,8 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, } if (ret && !no_warn) { - pr_err("%s: alloc failed, req-size: %zu pages, ret: %d\n", - __func__, count, ret); + pr_err("%s: %s: alloc failed, req-size: %zu pages, ret: %d\n", + __func__, cma->name, count, ret); cma_debug_show_areas(cma); } diff --git a/mm/dmapool.c b/mm/dmapool.c index a97c97232337..f3791532fef2 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -319,7 +320,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, size_t offset; void *retval; - might_sleep_if(gfpflags_allow_blocking(mem_flags)); + might_alloc(mem_flags); spin_lock_irqsave(&pool->lock, flags); list_for_each_entry(page, &pool->page_list, page_list) { diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c index a0018ad1a1f6..164607c7cdf1 100644 --- a/mm/early_ioremap.c +++ b/mm/early_ioremap.c @@ -181,17 +181,17 @@ void __init early_iounmap(void __iomem *addr, unsigned long size) } } - if (WARN(slot < 0, "early_iounmap(%p, %08lx) not found slot\n", - addr, size)) + if (WARN(slot < 0, "%s(%p, %08lx) not found slot\n", + __func__, addr, size)) return; if (WARN(prev_size[slot] != size, - "early_iounmap(%p, %08lx) [%d] size not consistent %08lx\n", - addr, size, slot, prev_size[slot])) + "%s(%p, %08lx) [%d] size not consistent %08lx\n", + __func__, addr, size, slot, prev_size[slot])) return; - WARN(early_ioremap_debug, "early_iounmap(%p, %08lx) [%d]\n", - addr, size, slot); + WARN(early_ioremap_debug, "%s(%p, %08lx) [%d]\n", + __func__, addr, size, slot); virt_addr = (unsigned long)addr; if (WARN_ON(virt_addr < fix_to_virt(FIX_BTMAP_BEGIN))) diff --git a/mm/filemap.c b/mm/filemap.c index 0eb33c3d840e..6ed9ce01db92 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1658,8 +1658,8 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, } EXPORT_SYMBOL(page_cache_prev_miss); -/** - * find_get_entry - find and get a page cache entry +/* + * mapping_get_entry - Get a page cache entry. * @mapping: the address_space to search * @index: The page cache index. * @@ -1671,7 +1671,8 @@ EXPORT_SYMBOL(page_cache_prev_miss); * * Return: The head page or shadow entry, %NULL if nothing is found. */ -struct page *find_get_entry(struct address_space *mapping, pgoff_t index) +static struct page *mapping_get_entry(struct address_space *mapping, + pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct page *page; @@ -1707,39 +1708,6 @@ struct page *find_get_entry(struct address_space *mapping, pgoff_t index) return page; } -/** - * find_lock_entry - Locate and lock a page cache entry. - * @mapping: The address_space to search. - * @index: The page cache index. - * - * Looks up the page at @mapping & @index. If there is a page in the - * cache, the head page is returned locked and with an increased refcount. - * - * If the slot holds a shadow entry of a previously evicted page, or a - * swap entry from shmem/tmpfs, it is returned. - * - * Context: May sleep. - * Return: The head page or shadow entry, %NULL if nothing is found. - */ -struct page *find_lock_entry(struct address_space *mapping, pgoff_t index) -{ - struct page *page; - -repeat: - page = find_get_entry(mapping, index); - if (page && !xa_is_value(page)) { - lock_page(page); - /* Has the page been truncated? */ - if (unlikely(page->mapping != mapping)) { - unlock_page(page); - put_page(page); - goto repeat; - } - VM_BUG_ON_PAGE(!thp_contains(page, index), page); - } - return page; -} - /** * pagecache_get_page - Find and get a reference to a page. * @mapping: The address_space to search. @@ -1755,6 +1723,8 @@ struct page *find_lock_entry(struct address_space *mapping, pgoff_t index) * * %FGP_LOCK - The page is returned locked. * * %FGP_HEAD - If the page is present and a THP, return the head page * rather than the exact page specified by the index. + * * %FGP_ENTRY - If there is a shadow / swap / DAX entry, return it + * instead of allocating a new page to replace it. * * %FGP_CREAT - If no page is present then a new page is allocated using * @gfp_mask and added to the page cache and the VM's LRU list. * The page is returned locked and with an increased refcount. @@ -1778,9 +1748,12 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, struct page *page; repeat: - page = find_get_entry(mapping, index); - if (xa_is_value(page)) + page = mapping_get_entry(mapping, index); + if (xa_is_value(page)) { + if (fgp_flags & FGP_ENTRY) + return page; page = NULL; + } if (!page) goto no_page; @@ -1852,18 +1825,53 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, } EXPORT_SYMBOL(pagecache_get_page); +static inline struct page *find_get_entry(struct xa_state *xas, pgoff_t max, + xa_mark_t mark) +{ + struct page *page; + +retry: + if (mark == XA_PRESENT) + page = xas_find(xas, max); + else + page = xas_find_marked(xas, max, mark); + + if (xas_retry(xas, page)) + goto retry; + /* + * A shadow entry of a recently evicted page, a swap + * entry from shmem/tmpfs or a DAX entry. Return it + * without attempting to raise page count. + */ + if (!page || xa_is_value(page)) + return page; + + if (!page_cache_get_speculative(page)) + goto reset; + + /* Has the page moved or been split? */ + if (unlikely(page != xas_reload(xas))) { + put_page(page); + goto reset; + } + + return page; +reset: + xas_reset(xas); + goto retry; +} + /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index - * @nr_entries: The maximum number of entries - * @entries: Where the resulting entries are placed + * @end: The final page index (inclusive). + * @pvec: Where the resulting entries are placed. * @indices: The cache indices corresponding to the entries in @entries * - * find_get_entries() will search for and return a group of up to - * @nr_entries entries in the mapping. The entries are placed at - * @entries. find_get_entries() takes a reference against any actual - * pages it returns. + * find_get_entries() will search for and return a batch of entries in + * the mapping. The entries are placed in @pvec. find_get_entries() + * takes a reference on any actual pages it returns. * * The search returns a group of mapping-contiguous page cache entries * with ascending indexes. There may be holes in the indices due to @@ -1879,59 +1887,96 @@ EXPORT_SYMBOL(pagecache_get_page); * * Return: the number of pages and shadow entries which were found. */ -unsigned find_get_entries(struct address_space *mapping, - pgoff_t start, unsigned int nr_entries, - struct page **entries, pgoff_t *indices) +unsigned find_get_entries(struct address_space *mapping, pgoff_t start, + pgoff_t end, struct pagevec *pvec, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned int ret = 0; - - if (!nr_entries) - return 0; + unsigned nr_entries = PAGEVEC_SIZE; rcu_read_lock(); - xas_for_each(&xas, page, ULONG_MAX) { - if (xas_retry(&xas, page)) - continue; - /* - * A shadow entry of a recently evicted page, a swap - * entry from shmem/tmpfs or a DAX entry. Return it - * without attempting to raise page count. - */ - if (xa_is_value(page)) - goto export; - - if (!page_cache_get_speculative(page)) - goto retry; - - /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) - goto put_page; - + while ((page = find_get_entry(&xas, end, XA_PRESENT))) { /* * Terminate early on finding a THP, to allow the caller to * handle it all at once; but continue if this is hugetlbfs. */ - if (PageTransHuge(page) && !PageHuge(page)) { + if (!xa_is_value(page) && PageTransHuge(page) && + !PageHuge(page)) { page = find_subpage(page, xas.xa_index); nr_entries = ret + 1; } -export: + indices[ret] = xas.xa_index; - entries[ret] = page; + pvec->pages[ret] = page; if (++ret == nr_entries) break; - continue; -put_page: - put_page(page); -retry: - xas_reset(&xas); } rcu_read_unlock(); + + pvec->nr = ret; return ret; } +/** + * find_lock_entries - Find a batch of pagecache entries. + * @mapping: The address_space to search. + * @start: The starting page cache index. + * @end: The final page index (inclusive). + * @pvec: Where the resulting entries are placed. + * @indices: The cache indices of the entries in @pvec. + * + * find_lock_entries() will return a batch of entries from @mapping. + * Swap, shadow and DAX entries are included. Pages are returned + * locked and with an incremented refcount. Pages which are locked by + * somebody else or under writeback are skipped. Only the head page of + * a THP is returned. Pages which are partially outside the range are + * not returned. + * + * The entries have ascending indexes. The indices may not be consecutive + * due to not-present entries, THP pages, pages which could not be locked + * or pages under writeback. + * + * Return: The number of entries which were found. + */ +unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, + pgoff_t end, struct pagevec *pvec, pgoff_t *indices) +{ + XA_STATE(xas, &mapping->i_pages, start); + struct page *page; + + rcu_read_lock(); + while ((page = find_get_entry(&xas, end, XA_PRESENT))) { + if (!xa_is_value(page)) { + if (page->index < start) + goto put; + VM_BUG_ON_PAGE(page->index != xas.xa_index, page); + if (page->index + thp_nr_pages(page) - 1 > end) + goto put; + if (!trylock_page(page)) + goto put; + if (page->mapping != mapping || PageWriteback(page)) + goto unlock; + VM_BUG_ON_PAGE(!thp_contains(page, xas.xa_index), + page); + } + indices[pvec->nr] = xas.xa_index; + if (!pagevec_add(pvec, page)) + break; + goto next; +unlock: + unlock_page(page); +put: + put_page(page); +next: + if (!xa_is_value(page) && PageTransHuge(page)) + xas_set(&xas, page->index + thp_nr_pages(page)); + } + rcu_read_unlock(); + + return pagevec_count(pvec); +} + /** * find_get_pages_range - gang pagecache lookup * @mapping: The address_space to search @@ -1965,30 +2010,16 @@ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, return 0; rcu_read_lock(); - xas_for_each(&xas, page, end) { - if (xas_retry(&xas, page)) - continue; + while ((page = find_get_entry(&xas, end, XA_PRESENT))) { /* Skip over shadow, swap and DAX entries */ if (xa_is_value(page)) continue; - if (!page_cache_get_speculative(page)) - goto retry; - - /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) - goto put_page; - pages[ret] = find_subpage(page, xas.xa_index); if (++ret == nr_pages) { *start = xas.xa_index + 1; goto out; } - continue; -put_page: - put_page(page); -retry: - xas_reset(&xas); } /* @@ -2062,7 +2093,7 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, EXPORT_SYMBOL(find_get_pages_contig); /** - * find_get_pages_range_tag - find and return pages in given range matching @tag + * find_get_pages_range_tag - Find and return head pages matching @tag. * @mapping: the address_space to search * @index: the starting page index * @end: The final page index (inclusive) @@ -2070,8 +2101,9 @@ EXPORT_SYMBOL(find_get_pages_contig); * @nr_pages: the maximum number of pages * @pages: where the resulting pages are placed * - * Like find_get_pages, except we only return pages which are tagged with - * @tag. We update @index to index the next page for the traversal. + * Like find_get_pages(), except we only return head pages which are tagged + * with @tag. @index is updated to the index immediately after the last + * page we return, ready for the next iteration. * * Return: the number of pages which were found. */ @@ -2087,9 +2119,7 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, return 0; rcu_read_lock(); - xas_for_each_marked(&xas, page, end, tag) { - if (xas_retry(&xas, page)) - continue; + while ((page = find_get_entry(&xas, end, tag))) { /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict @@ -2098,23 +2128,11 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, if (xa_is_value(page)) continue; - if (!page_cache_get_speculative(page)) - goto retry; - - /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) - goto put_page; - - pages[ret] = find_subpage(page, xas.xa_index); + pages[ret] = page; if (++ret == nr_pages) { - *index = xas.xa_index + 1; + *index = page->index + thp_nr_pages(page); goto out; } - continue; -put_page: - put_page(page); -retry: - xas_reset(&xas); } /* @@ -2592,6 +2610,109 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) } EXPORT_SYMBOL(generic_file_read_iter); +static inline loff_t page_seek_hole_data(struct xa_state *xas, + struct address_space *mapping, struct page *page, + loff_t start, loff_t end, bool seek_data) +{ + const struct address_space_operations *ops = mapping->a_ops; + size_t offset, bsz = i_blocksize(mapping->host); + + if (xa_is_value(page) || PageUptodate(page)) + return seek_data ? start : end; + if (!ops->is_partially_uptodate) + return seek_data ? end : start; + + xas_pause(xas); + rcu_read_unlock(); + lock_page(page); + if (unlikely(page->mapping != mapping)) + goto unlock; + + offset = offset_in_thp(page, start) & ~(bsz - 1); + + do { + if (ops->is_partially_uptodate(page, offset, bsz) == seek_data) + break; + start = (start + bsz) & ~(bsz - 1); + offset += bsz; + } while (offset < thp_size(page)); +unlock: + unlock_page(page); + rcu_read_lock(); + return start; +} + +static inline +unsigned int seek_page_size(struct xa_state *xas, struct page *page) +{ + if (xa_is_value(page)) + return PAGE_SIZE << xa_get_order(xas->xa, xas->xa_index); + return thp_size(page); +} + +/** + * mapping_seek_hole_data - Seek for SEEK_DATA / SEEK_HOLE in the page cache. + * @mapping: Address space to search. + * @start: First byte to consider. + * @end: Limit of search (exclusive). + * @whence: Either SEEK_HOLE or SEEK_DATA. + * + * If the page cache knows which blocks contain holes and which blocks + * contain data, your filesystem can use this function to implement + * SEEK_HOLE and SEEK_DATA. This is useful for filesystems which are + * entirely memory-based such as tmpfs, and filesystems which support + * unwritten extents. + * + * Return: The requested offset on successs, or -ENXIO if @whence specifies + * SEEK_DATA and there is no data after @start. There is an implicit hole + * after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start + * and @end contain data. + */ +loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, + loff_t end, int whence) +{ + XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT); + pgoff_t max = (end - 1) / PAGE_SIZE; + bool seek_data = (whence == SEEK_DATA); + struct page *page; + + if (end <= start) + return -ENXIO; + + rcu_read_lock(); + while ((page = find_get_entry(&xas, max, XA_PRESENT))) { + loff_t pos = xas.xa_index * PAGE_SIZE; + + if (start < pos) { + if (!seek_data) + goto unlock; + start = pos; + } + + pos += seek_page_size(&xas, page); + start = page_seek_hole_data(&xas, mapping, page, start, pos, + seek_data); + if (start < pos) + goto unlock; + if (!xa_is_value(page)) + put_page(page); + } + rcu_read_unlock(); + + if (seek_data) + return -ENXIO; + goto out; + +unlock: + rcu_read_unlock(); + if (!xa_is_value(page)) + put_page(page); +out: + if (start > end) + return end; + return start; +} + #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* diff --git a/mm/huge_memory.c b/mm/huge_memory.c index d77605c30f2e..395c75111d33 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -668,9 +668,9 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, * available * never: never stall for any thp allocation */ -static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) +gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma) { - const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); + const bool vma_madvised = vma && (vma->vm_flags & VM_HUGEPAGE); /* Always do synchronous compaction */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) @@ -762,7 +762,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) } return ret; } - gfp = alloc_hugepage_direct_gfpmask(vma); + gfp = vma_thp_gfp_mask(vma); page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); diff --git a/mm/internal.h b/mm/internal.h index 25d2b2439f19..9902648f2206 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -60,8 +60,8 @@ static inline void force_page_cache_readahead(struct address_space *mapping, force_page_cache_ra(&ractl, &file->f_ra, nr_to_read); } -struct page *find_get_entry(struct address_space *mapping, pgoff_t index); -struct page *find_lock_entry(struct address_space *mapping, pgoff_t index); +unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, + pgoff_t end, struct pagevec *pvec, pgoff_t *indices); /** * page_evictable - test whether a page is evictable diff --git a/mm/kasan/common.c b/mm/kasan/common.c index b18189ef3a92..b5e08d4cefec 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -210,6 +210,11 @@ void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size, *size = optimal_size; } +void __kasan_cache_create_kmalloc(struct kmem_cache *cache) +{ + cache->kasan_info.is_kmalloc = true; +} + size_t __kasan_metadata_size(struct kmem_cache *cache) { if (!kasan_stack_collection_enabled()) @@ -256,7 +261,8 @@ void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object) void __kasan_poison_object_data(struct kmem_cache *cache, void *object) { - kasan_poison(object, cache->object_size, KASAN_KMALLOC_REDZONE); + kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE), + KASAN_KMALLOC_REDZONE); } /* @@ -273,21 +279,12 @@ void __kasan_poison_object_data(struct kmem_cache *cache, void *object) * based on objects indexes, so that objects that are next to each other * get different tags. */ -static u8 assign_tag(struct kmem_cache *cache, const void *object, - bool init, bool keep_tag) +static inline u8 assign_tag(struct kmem_cache *cache, + const void *object, bool init) { if (IS_ENABLED(CONFIG_KASAN_GENERIC)) return 0xff; - /* - * 1. When an object is kmalloc()'ed, two hooks are called: - * kasan_slab_alloc() and kasan_kmalloc(). We assign the - * tag only in the first one. - * 2. We reuse the same tag for krealloc'ed objects. - */ - if (keep_tag) - return get_tag(object); - /* * If the cache neither has a constructor nor has SLAB_TYPESAFE_BY_RCU * set, assign a tag when the object is being allocated (init == false). @@ -320,13 +317,13 @@ void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache, } /* Tag is ignored in set_tag() without CONFIG_KASAN_SW/HW_TAGS */ - object = set_tag(object, assign_tag(cache, object, true, false)); + object = set_tag(object, assign_tag(cache, object, true)); return (void *)object; } -static bool ____kasan_slab_free(struct kmem_cache *cache, void *object, - unsigned long ip, bool quarantine) +static inline bool ____kasan_slab_free(struct kmem_cache *cache, + void *object, unsigned long ip, bool quarantine) { u8 tag; void *tagged_object; @@ -335,6 +332,9 @@ static bool ____kasan_slab_free(struct kmem_cache *cache, void *object, tagged_object = object; object = kasan_reset_tag(object); + if (is_kfence_address(object)) + return false; + if (unlikely(nearest_obj(cache, virt_to_head_page(object), object) != object)) { kasan_report_invalid_free(tagged_object, ip); @@ -350,15 +350,14 @@ static bool ____kasan_slab_free(struct kmem_cache *cache, void *object, return true; } - kasan_poison(object, cache->object_size, KASAN_KMALLOC_FREE); - - if (!kasan_stack_collection_enabled()) - return false; + kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE), + KASAN_KMALLOC_FREE); if ((IS_ENABLED(CONFIG_KASAN_GENERIC) && !quarantine)) return false; - kasan_set_free_info(cache, object, tag); + if (kasan_stack_collection_enabled()) + kasan_set_free_info(cache, object, tag); return kasan_quarantine_put(cache, object); } @@ -368,6 +367,31 @@ bool __kasan_slab_free(struct kmem_cache *cache, void *object, unsigned long ip) return ____kasan_slab_free(cache, object, ip, true); } +static inline bool ____kasan_kfree_large(void *ptr, unsigned long ip) +{ + if (ptr != page_address(virt_to_head_page(ptr))) { + kasan_report_invalid_free(ptr, ip); + return true; + } + + if (!kasan_byte_accessible(ptr)) { + kasan_report_invalid_free(ptr, ip); + return true; + } + + /* + * The object will be poisoned by kasan_free_pages() or + * kasan_slab_free_mempool(). + */ + + return false; +} + +void __kasan_kfree_large(void *ptr, unsigned long ip) +{ + ____kasan_kfree_large(ptr, ip); +} + void __kasan_slab_free_mempool(void *ptr, unsigned long ip) { struct page *page; @@ -381,31 +405,33 @@ void __kasan_slab_free_mempool(void *ptr, unsigned long ip) * KMALLOC_MAX_SIZE, and kmalloc falls back onto page_alloc. */ if (unlikely(!PageSlab(page))) { - if (ptr != page_address(page)) { - kasan_report_invalid_free(ptr, ip); + if (____kasan_kfree_large(ptr, ip)) return; - } kasan_poison(ptr, page_size(page), KASAN_FREE_PAGE); } else { ____kasan_slab_free(page->slab_cache, ptr, ip, false); } } -static void set_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags) +static void set_alloc_info(struct kmem_cache *cache, void *object, + gfp_t flags, bool is_kmalloc) { struct kasan_alloc_meta *alloc_meta; + /* Don't save alloc info for kmalloc caches in kasan_slab_alloc(). */ + if (cache->kasan_info.is_kmalloc && !is_kmalloc) + return; + alloc_meta = kasan_get_alloc_meta(cache, object); if (alloc_meta) kasan_set_track(&alloc_meta->alloc_track, flags); } -static void *____kasan_kmalloc(struct kmem_cache *cache, const void *object, - size_t size, gfp_t flags, bool keep_tag) +void * __must_check __kasan_slab_alloc(struct kmem_cache *cache, + void *object, gfp_t flags) { - unsigned long redzone_start; - unsigned long redzone_end; u8 tag; + void *tagged_object; if (gfpflags_allow_blocking(flags)) kasan_quarantine_reduce(); @@ -413,40 +439,86 @@ static void *____kasan_kmalloc(struct kmem_cache *cache, const void *object, if (unlikely(object == NULL)) return NULL; + if (is_kfence_address(object)) + return (void *)object; + + /* + * Generate and assign random tag for tag-based modes. + * Tag is ignored in set_tag() for the generic mode. + */ + tag = assign_tag(cache, object, false); + tagged_object = set_tag(object, tag); + + /* + * Unpoison the whole object. + * For kmalloc() allocations, kasan_kmalloc() will do precise poisoning. + */ + kasan_unpoison(tagged_object, cache->object_size); + + /* Save alloc info (if possible) for non-kmalloc() allocations. */ + if (kasan_stack_collection_enabled()) + set_alloc_info(cache, (void *)object, flags, false); + + return tagged_object; +} + +static inline void *____kasan_kmalloc(struct kmem_cache *cache, + const void *object, size_t size, gfp_t flags) +{ + unsigned long redzone_start; + unsigned long redzone_end; + + if (gfpflags_allow_blocking(flags)) + kasan_quarantine_reduce(); + + if (unlikely(object == NULL)) + return NULL; + + if (is_kfence_address(kasan_reset_tag(object))) + return (void *)object; + + /* + * The object has already been unpoisoned by kasan_slab_alloc() for + * kmalloc() or by kasan_krealloc() for krealloc(). + */ + + /* + * The redzone has byte-level precision for the generic mode. + * Partially poison the last object granule to cover the unaligned + * part of the redzone. + */ + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) + kasan_poison_last_granule((void *)object, size); + + /* Poison the aligned part of the redzone. */ redzone_start = round_up((unsigned long)(object + size), KASAN_GRANULE_SIZE); - redzone_end = round_up((unsigned long)object + cache->object_size, + redzone_end = round_up((unsigned long)(object + cache->object_size), KASAN_GRANULE_SIZE); - tag = assign_tag(cache, object, false, keep_tag); - - /* Tag is ignored in set_tag without CONFIG_KASAN_SW/HW_TAGS */ - kasan_unpoison(set_tag(object, tag), size); kasan_poison((void *)redzone_start, redzone_end - redzone_start, KASAN_KMALLOC_REDZONE); + /* + * Save alloc info (if possible) for kmalloc() allocations. + * This also rewrites the alloc info when called from kasan_krealloc(). + */ if (kasan_stack_collection_enabled()) - set_alloc_info(cache, (void *)object, flags); + set_alloc_info(cache, (void *)object, flags, true); - return set_tag(object, tag); -} - -void * __must_check __kasan_slab_alloc(struct kmem_cache *cache, - void *object, gfp_t flags) -{ - return ____kasan_kmalloc(cache, object, cache->object_size, flags, false); + /* Keep the tag that was set by kasan_slab_alloc(). */ + return (void *)object; } void * __must_check __kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size, gfp_t flags) { - return ____kasan_kmalloc(cache, object, size, flags, true); + return ____kasan_kmalloc(cache, object, size, flags); } EXPORT_SYMBOL(__kasan_kmalloc); void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags) { - struct page *page; unsigned long redzone_start; unsigned long redzone_end; @@ -456,12 +528,23 @@ void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size, if (unlikely(ptr == NULL)) return NULL; - page = virt_to_page(ptr); + /* + * The object has already been unpoisoned by kasan_alloc_pages() for + * alloc_pages() or by kasan_krealloc() for krealloc(). + */ + + /* + * The redzone has byte-level precision for the generic mode. + * Partially poison the last object granule to cover the unaligned + * part of the redzone. + */ + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) + kasan_poison_last_granule(ptr, size); + + /* Poison the aligned part of the redzone. */ redzone_start = round_up((unsigned long)(ptr + size), KASAN_GRANULE_SIZE); - redzone_end = (unsigned long)ptr + page_size(page); - - kasan_unpoison(ptr, size); + redzone_end = (unsigned long)ptr + page_size(virt_to_page(ptr)); kasan_poison((void *)redzone_start, redzone_end - redzone_start, KASAN_PAGE_REDZONE); @@ -475,20 +558,20 @@ void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flag if (unlikely(object == ZERO_SIZE_PTR)) return (void *)object; + /* + * Unpoison the object's data. + * Part of it might already have been unpoisoned, but it's unknown + * how big that part is. + */ + kasan_unpoison(object, size); + page = virt_to_head_page(object); + /* Piggy-back on kmalloc() instrumentation to poison the redzone. */ if (unlikely(!PageSlab(page))) return __kasan_kmalloc_large(object, size, flags); else - return ____kasan_kmalloc(page->slab_cache, object, size, - flags, true); -} - -void __kasan_kfree_large(void *ptr, unsigned long ip) -{ - if (ptr != page_address(virt_to_head_page(ptr))) - kasan_report_invalid_free(ptr, ip); - /* The object will be poisoned by kasan_free_pages(). */ + return ____kasan_kmalloc(page->slab_cache, object, size, flags); } bool __kasan_check_byte(const void *address, unsigned long ip) diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index 3f17a1218055..2e55e0f82f39 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -331,7 +332,7 @@ void kasan_record_aux_stack(void *addr) struct kasan_alloc_meta *alloc_meta; void *object; - if (!(page && PageSlab(page))) + if (is_kfence_address(addr) || !(page && PageSlab(page))) return; cache = page->slab_cache; diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index b31aeef505dd..2aad21fda156 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -48,7 +48,7 @@ EXPORT_SYMBOL(kasan_flag_enabled); /* Whether to collect alloc/free stack traces. */ DEFINE_STATIC_KEY_FALSE(kasan_flag_stacktrace); -/* Whether panic or disable tag checking on fault. */ +/* Whether to panic or print a report and disable tag checking on fault. */ bool kasan_flag_panic __ro_after_init; /* kasan=off/on */ diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index cc14b6e6c14c..8c55634d6edd 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -3,6 +3,7 @@ #define __MM_KASAN_KASAN_H #include +#include #include #ifdef CONFIG_KASAN_HW_TAGS @@ -329,16 +330,37 @@ static inline u8 kasan_random_tag(void) { return 0; } #ifdef CONFIG_KASAN_HW_TAGS -static inline void kasan_poison(const void *address, size_t size, u8 value) +static inline void kasan_poison(const void *addr, size_t size, u8 value) { - hw_set_mem_tag_range(kasan_reset_tag(address), - round_up(size, KASAN_GRANULE_SIZE), value); + addr = kasan_reset_tag(addr); + + /* Skip KFENCE memory if called explicitly outside of sl*b. */ + if (is_kfence_address(addr)) + return; + + if (WARN_ON((unsigned long)addr & KASAN_GRANULE_MASK)) + return; + if (WARN_ON(size & KASAN_GRANULE_MASK)) + return; + + hw_set_mem_tag_range((void *)addr, size, value); } -static inline void kasan_unpoison(const void *address, size_t size) +static inline void kasan_unpoison(const void *addr, size_t size) { - hw_set_mem_tag_range(kasan_reset_tag(address), - round_up(size, KASAN_GRANULE_SIZE), get_tag(address)); + u8 tag = get_tag(addr); + + addr = kasan_reset_tag(addr); + + /* Skip KFENCE memory if called explicitly outside of sl*b. */ + if (is_kfence_address(addr)) + return; + + if (WARN_ON((unsigned long)addr & KASAN_GRANULE_MASK)) + return; + size = round_up(size, KASAN_GRANULE_SIZE); + + hw_set_mem_tag_range((void *)addr, size, tag); } static inline bool kasan_byte_accessible(const void *addr) @@ -352,12 +374,51 @@ static inline bool kasan_byte_accessible(const void *addr) #else /* CONFIG_KASAN_HW_TAGS */ -void kasan_poison(const void *address, size_t size, u8 value); -void kasan_unpoison(const void *address, size_t size); +/** + * kasan_poison - mark the memory range as unaccessible + * @addr - range start address, must be aligned to KASAN_GRANULE_SIZE + * @size - range size, must be aligned to KASAN_GRANULE_SIZE + * @value - value that's written to metadata for the range + * + * The size gets aligned to KASAN_GRANULE_SIZE before marking the range. + */ +void kasan_poison(const void *addr, size_t size, u8 value); + +/** + * kasan_unpoison - mark the memory range as accessible + * @addr - range start address, must be aligned to KASAN_GRANULE_SIZE + * @size - range size, can be unaligned + * + * For the tag-based modes, the @size gets aligned to KASAN_GRANULE_SIZE before + * marking the range. + * For the generic mode, the last granule of the memory range gets partially + * unpoisoned based on the @size. + */ +void kasan_unpoison(const void *addr, size_t size); + bool kasan_byte_accessible(const void *addr); #endif /* CONFIG_KASAN_HW_TAGS */ +#ifdef CONFIG_KASAN_GENERIC + +/** + * kasan_poison_last_granule - mark the last granule of the memory range as + * unaccessible + * @addr - range start address, must be aligned to KASAN_GRANULE_SIZE + * @size - range size + * + * This function is only available for the generic mode, as it's the only mode + * that has partially poisoned memory granules. + */ +void kasan_poison_last_granule(const void *address, size_t size); + +#else /* CONFIG_KASAN_GENERIC */ + +static inline void kasan_poison_last_granule(const void *address, size_t size) { } + +#endif /* CONFIG_KASAN_GENERIC */ + /* * Exported functions for interfaces called from assembly or from generated * code. Declarations here to avoid warning about missing declarations. diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 234f35a84f19..87b271206163 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -25,6 +25,7 @@ #include #include #include +#include #include @@ -84,8 +85,9 @@ static void start_report(unsigned long *flags) pr_err("==================================================================\n"); } -static void end_report(unsigned long *flags) +static void end_report(unsigned long *flags, unsigned long addr) { + trace_error_report_end(ERROR_DETECTOR_KASAN, addr); pr_err("==================================================================\n"); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); spin_unlock_irqrestore(&report_lock, *flags); @@ -355,7 +357,7 @@ void kasan_report_invalid_free(void *object, unsigned long ip) print_address_description(object, tag); pr_err("\n"); print_memory_metadata(object); - end_report(&flags); + end_report(&flags, (unsigned long)object); } static void __kasan_report(unsigned long addr, size_t size, bool is_write, @@ -401,7 +403,7 @@ static void __kasan_report(unsigned long addr, size_t size, bool is_write, dump_stack(); } - end_report(&flags); + end_report(&flags, addr); } bool kasan_report(unsigned long addr, size_t size, bool is_write, diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 80adc85d0393..63f43443f5d7 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -68,11 +69,7 @@ void *memcpy(void *dest, const void *src, size_t len) return __memcpy(dest, src, len); } -/* - * Poisons the shadow memory for 'size' bytes starting from 'addr'. - * Memory addresses should be aligned to KASAN_GRANULE_SIZE. - */ -void kasan_poison(const void *address, size_t size, u8 value) +void kasan_poison(const void *addr, size_t size, u8 value) { void *shadow_start, *shadow_end; @@ -81,37 +78,62 @@ void kasan_poison(const void *address, size_t size, u8 value) * some of the callers (e.g. kasan_poison_object_data) pass tagged * addresses to this function. */ - address = kasan_reset_tag(address); - size = round_up(size, KASAN_GRANULE_SIZE); + addr = kasan_reset_tag(addr); - shadow_start = kasan_mem_to_shadow(address); - shadow_end = kasan_mem_to_shadow(address + size); + /* Skip KFENCE memory if called explicitly outside of sl*b. */ + if (is_kfence_address(addr)) + return; + + if (WARN_ON((unsigned long)addr & KASAN_GRANULE_MASK)) + return; + if (WARN_ON(size & KASAN_GRANULE_MASK)) + return; + + shadow_start = kasan_mem_to_shadow(addr); + shadow_end = kasan_mem_to_shadow(addr + size); __memset(shadow_start, value, shadow_end - shadow_start); } EXPORT_SYMBOL(kasan_poison); -void kasan_unpoison(const void *address, size_t size) +#ifdef CONFIG_KASAN_GENERIC +void kasan_poison_last_granule(const void *addr, size_t size) { - u8 tag = get_tag(address); + if (size & KASAN_GRANULE_MASK) { + u8 *shadow = (u8 *)kasan_mem_to_shadow(addr + size); + *shadow = size & KASAN_GRANULE_MASK; + } +} +#endif + +void kasan_unpoison(const void *addr, size_t size) +{ + u8 tag = get_tag(addr); /* * Perform shadow offset calculation based on untagged address, as * some of the callers (e.g. kasan_unpoison_object_data) pass tagged * addresses to this function. */ - address = kasan_reset_tag(address); + addr = kasan_reset_tag(addr); - kasan_poison(address, size, tag); + /* + * Skip KFENCE memory if called explicitly outside of sl*b. Also note + * that calls to ksize(), where size is not a multiple of machine-word + * size, would otherwise poison the invalid portion of the word. + */ + if (is_kfence_address(addr)) + return; - if (size & KASAN_GRANULE_MASK) { - u8 *shadow = (u8 *)kasan_mem_to_shadow(address + size); + if (WARN_ON((unsigned long)addr & KASAN_GRANULE_MASK)) + return; - if (IS_ENABLED(CONFIG_KASAN_SW_TAGS)) - *shadow = tag; - else /* CONFIG_KASAN_GENERIC */ - *shadow = size & KASAN_GRANULE_MASK; - } + /* Unpoison all granules that cover the object. */ + kasan_poison(addr, round_up(size, KASAN_GRANULE_SIZE), tag); + + /* Partially poison the last granule for the generic mode. */ + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) + kasan_poison_last_granule(addr, size); } #ifdef CONFIG_MEMORY_HOTPLUG diff --git a/mm/kfence/Makefile b/mm/kfence/Makefile new file mode 100644 index 000000000000..6872cd5e5390 --- /dev/null +++ b/mm/kfence/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_KFENCE) := core.o report.o + +CFLAGS_kfence_test.o := -g -fno-omit-frame-pointer -fno-optimize-sibling-calls +obj-$(CONFIG_KFENCE_KUNIT_TEST) += kfence_test.o diff --git a/mm/kfence/core.c b/mm/kfence/core.c new file mode 100644 index 000000000000..3b8ec938470a --- /dev/null +++ b/mm/kfence/core.c @@ -0,0 +1,841 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KFENCE guarded object allocator and fault handling. + * + * Copyright (C) 2020, Google LLC. + */ + +#define pr_fmt(fmt) "kfence: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "kfence.h" + +/* Disables KFENCE on the first warning assuming an irrecoverable error. */ +#define KFENCE_WARN_ON(cond) \ + ({ \ + const bool __cond = WARN_ON(cond); \ + if (unlikely(__cond)) \ + WRITE_ONCE(kfence_enabled, false); \ + __cond; \ + }) + +/* === Data ================================================================= */ + +static bool kfence_enabled __read_mostly; + +static unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL; + +#ifdef MODULE_PARAM_PREFIX +#undef MODULE_PARAM_PREFIX +#endif +#define MODULE_PARAM_PREFIX "kfence." + +static int param_set_sample_interval(const char *val, const struct kernel_param *kp) +{ + unsigned long num; + int ret = kstrtoul(val, 0, &num); + + if (ret < 0) + return ret; + + if (!num) /* Using 0 to indicate KFENCE is disabled. */ + WRITE_ONCE(kfence_enabled, false); + else if (!READ_ONCE(kfence_enabled) && system_state != SYSTEM_BOOTING) + return -EINVAL; /* Cannot (re-)enable KFENCE on-the-fly. */ + + *((unsigned long *)kp->arg) = num; + return 0; +} + +static int param_get_sample_interval(char *buffer, const struct kernel_param *kp) +{ + if (!READ_ONCE(kfence_enabled)) + return sprintf(buffer, "0\n"); + + return param_get_ulong(buffer, kp); +} + +static const struct kernel_param_ops sample_interval_param_ops = { + .set = param_set_sample_interval, + .get = param_get_sample_interval, +}; +module_param_cb(sample_interval, &sample_interval_param_ops, &kfence_sample_interval, 0600); + +/* The pool of pages used for guard pages and objects. */ +char *__kfence_pool __ro_after_init; +EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */ + +/* + * Per-object metadata, with one-to-one mapping of object metadata to + * backing pages (in __kfence_pool). + */ +static_assert(CONFIG_KFENCE_NUM_OBJECTS > 0); +struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; + +/* Freelist with available objects. */ +static struct list_head kfence_freelist = LIST_HEAD_INIT(kfence_freelist); +static DEFINE_RAW_SPINLOCK(kfence_freelist_lock); /* Lock protecting freelist. */ + +#ifdef CONFIG_KFENCE_STATIC_KEYS +/* The static key to set up a KFENCE allocation. */ +DEFINE_STATIC_KEY_FALSE(kfence_allocation_key); +#endif + +/* Gates the allocation, ensuring only one succeeds in a given period. */ +atomic_t kfence_allocation_gate = ATOMIC_INIT(1); + +/* Statistics counters for debugfs. */ +enum kfence_counter_id { + KFENCE_COUNTER_ALLOCATED, + KFENCE_COUNTER_ALLOCS, + KFENCE_COUNTER_FREES, + KFENCE_COUNTER_ZOMBIES, + KFENCE_COUNTER_BUGS, + KFENCE_COUNTER_COUNT, +}; +static atomic_long_t counters[KFENCE_COUNTER_COUNT]; +static const char *const counter_names[] = { + [KFENCE_COUNTER_ALLOCATED] = "currently allocated", + [KFENCE_COUNTER_ALLOCS] = "total allocations", + [KFENCE_COUNTER_FREES] = "total frees", + [KFENCE_COUNTER_ZOMBIES] = "zombie allocations", + [KFENCE_COUNTER_BUGS] = "total bugs", +}; +static_assert(ARRAY_SIZE(counter_names) == KFENCE_COUNTER_COUNT); + +/* === Internals ============================================================ */ + +static bool kfence_protect(unsigned long addr) +{ + return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), true)); +} + +static bool kfence_unprotect(unsigned long addr) +{ + return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), false)); +} + +static inline struct kfence_metadata *addr_to_metadata(unsigned long addr) +{ + long index; + + /* The checks do not affect performance; only called from slow-paths. */ + + if (!is_kfence_address((void *)addr)) + return NULL; + + /* + * May be an invalid index if called with an address at the edge of + * __kfence_pool, in which case we would report an "invalid access" + * error. + */ + index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1; + if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS) + return NULL; + + return &kfence_metadata[index]; +} + +static inline unsigned long metadata_to_pageaddr(const struct kfence_metadata *meta) +{ + unsigned long offset = (meta - kfence_metadata + 1) * PAGE_SIZE * 2; + unsigned long pageaddr = (unsigned long)&__kfence_pool[offset]; + + /* The checks do not affect performance; only called from slow-paths. */ + + /* Only call with a pointer into kfence_metadata. */ + if (KFENCE_WARN_ON(meta < kfence_metadata || + meta >= kfence_metadata + CONFIG_KFENCE_NUM_OBJECTS)) + return 0; + + /* + * This metadata object only ever maps to 1 page; verify that the stored + * address is in the expected range. + */ + if (KFENCE_WARN_ON(ALIGN_DOWN(meta->addr, PAGE_SIZE) != pageaddr)) + return 0; + + return pageaddr; +} + +/* + * Update the object's metadata state, including updating the alloc/free stacks + * depending on the state transition. + */ +static noinline void metadata_update_state(struct kfence_metadata *meta, + enum kfence_object_state next) +{ + struct kfence_track *track = + next == KFENCE_OBJECT_FREED ? &meta->free_track : &meta->alloc_track; + + lockdep_assert_held(&meta->lock); + + /* + * Skip over 1 (this) functions; noinline ensures we do not accidentally + * skip over the caller by never inlining. + */ + track->num_stack_entries = stack_trace_save(track->stack_entries, KFENCE_STACK_DEPTH, 1); + track->pid = task_pid_nr(current); + + /* + * Pairs with READ_ONCE() in + * kfence_shutdown_cache(), + * kfence_handle_page_fault(). + */ + WRITE_ONCE(meta->state, next); +} + +/* Write canary byte to @addr. */ +static inline bool set_canary_byte(u8 *addr) +{ + *addr = KFENCE_CANARY_PATTERN(addr); + return true; +} + +/* Check canary byte at @addr. */ +static inline bool check_canary_byte(u8 *addr) +{ + if (likely(*addr == KFENCE_CANARY_PATTERN(addr))) + return true; + + atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); + kfence_report_error((unsigned long)addr, false, NULL, addr_to_metadata((unsigned long)addr), + KFENCE_ERROR_CORRUPTION); + return false; +} + +/* __always_inline this to ensure we won't do an indirect call to fn. */ +static __always_inline void for_each_canary(const struct kfence_metadata *meta, bool (*fn)(u8 *)) +{ + const unsigned long pageaddr = ALIGN_DOWN(meta->addr, PAGE_SIZE); + unsigned long addr; + + lockdep_assert_held(&meta->lock); + + /* + * We'll iterate over each canary byte per-side until fn() returns + * false. However, we'll still iterate over the canary bytes to the + * right of the object even if there was an error in the canary bytes to + * the left of the object. Specifically, if check_canary_byte() + * generates an error, showing both sides might give more clues as to + * what the error is about when displaying which bytes were corrupted. + */ + + /* Apply to left of object. */ + for (addr = pageaddr; addr < meta->addr; addr++) { + if (!fn((u8 *)addr)) + break; + } + + /* Apply to right of object. */ + for (addr = meta->addr + meta->size; addr < pageaddr + PAGE_SIZE; addr++) { + if (!fn((u8 *)addr)) + break; + } +} + +static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp) +{ + struct kfence_metadata *meta = NULL; + unsigned long flags; + struct page *page; + void *addr; + + /* Try to obtain a free object. */ + raw_spin_lock_irqsave(&kfence_freelist_lock, flags); + if (!list_empty(&kfence_freelist)) { + meta = list_entry(kfence_freelist.next, struct kfence_metadata, list); + list_del_init(&meta->list); + } + raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); + if (!meta) + return NULL; + + if (unlikely(!raw_spin_trylock_irqsave(&meta->lock, flags))) { + /* + * This is extremely unlikely -- we are reporting on a + * use-after-free, which locked meta->lock, and the reporting + * code via printk calls kmalloc() which ends up in + * kfence_alloc() and tries to grab the same object that we're + * reporting on. While it has never been observed, lockdep does + * report that there is a possibility of deadlock. Fix it by + * using trylock and bailing out gracefully. + */ + raw_spin_lock_irqsave(&kfence_freelist_lock, flags); + /* Put the object back on the freelist. */ + list_add_tail(&meta->list, &kfence_freelist); + raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); + + return NULL; + } + + meta->addr = metadata_to_pageaddr(meta); + /* Unprotect if we're reusing this page. */ + if (meta->state == KFENCE_OBJECT_FREED) + kfence_unprotect(meta->addr); + + /* + * Note: for allocations made before RNG initialization, will always + * return zero. We still benefit from enabling KFENCE as early as + * possible, even when the RNG is not yet available, as this will allow + * KFENCE to detect bugs due to earlier allocations. The only downside + * is that the out-of-bounds accesses detected are deterministic for + * such allocations. + */ + if (prandom_u32_max(2)) { + /* Allocate on the "right" side, re-calculate address. */ + meta->addr += PAGE_SIZE - size; + meta->addr = ALIGN_DOWN(meta->addr, cache->align); + } + + addr = (void *)meta->addr; + + /* Update remaining metadata. */ + metadata_update_state(meta, KFENCE_OBJECT_ALLOCATED); + /* Pairs with READ_ONCE() in kfence_shutdown_cache(). */ + WRITE_ONCE(meta->cache, cache); + meta->size = size; + for_each_canary(meta, set_canary_byte); + + /* Set required struct page fields. */ + page = virt_to_page(meta->addr); + page->slab_cache = cache; + if (IS_ENABLED(CONFIG_SLUB)) + page->objects = 1; + if (IS_ENABLED(CONFIG_SLAB)) + page->s_mem = addr; + + raw_spin_unlock_irqrestore(&meta->lock, flags); + + /* Memory initialization. */ + + /* + * We check slab_want_init_on_alloc() ourselves, rather than letting + * SL*B do the initialization, as otherwise we might overwrite KFENCE's + * redzone. + */ + if (unlikely(slab_want_init_on_alloc(gfp, cache))) + memzero_explicit(addr, size); + if (cache->ctor) + cache->ctor(addr); + + if (CONFIG_KFENCE_STRESS_TEST_FAULTS && !prandom_u32_max(CONFIG_KFENCE_STRESS_TEST_FAULTS)) + kfence_protect(meta->addr); /* Random "faults" by protecting the object. */ + + atomic_long_inc(&counters[KFENCE_COUNTER_ALLOCATED]); + atomic_long_inc(&counters[KFENCE_COUNTER_ALLOCS]); + + return addr; +} + +static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool zombie) +{ + struct kcsan_scoped_access assert_page_exclusive; + unsigned long flags; + + raw_spin_lock_irqsave(&meta->lock, flags); + + if (meta->state != KFENCE_OBJECT_ALLOCATED || meta->addr != (unsigned long)addr) { + /* Invalid or double-free, bail out. */ + atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); + kfence_report_error((unsigned long)addr, false, NULL, meta, + KFENCE_ERROR_INVALID_FREE); + raw_spin_unlock_irqrestore(&meta->lock, flags); + return; + } + + /* Detect racy use-after-free, or incorrect reallocation of this page by KFENCE. */ + kcsan_begin_scoped_access((void *)ALIGN_DOWN((unsigned long)addr, PAGE_SIZE), PAGE_SIZE, + KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT, + &assert_page_exclusive); + + if (CONFIG_KFENCE_STRESS_TEST_FAULTS) + kfence_unprotect((unsigned long)addr); /* To check canary bytes. */ + + /* Restore page protection if there was an OOB access. */ + if (meta->unprotected_page) { + kfence_protect(meta->unprotected_page); + meta->unprotected_page = 0; + } + + /* Check canary bytes for memory corruption. */ + for_each_canary(meta, check_canary_byte); + + /* + * Clear memory if init-on-free is set. While we protect the page, the + * data is still there, and after a use-after-free is detected, we + * unprotect the page, so the data is still accessible. + */ + if (!zombie && unlikely(slab_want_init_on_free(meta->cache))) + memzero_explicit(addr, meta->size); + + /* Mark the object as freed. */ + metadata_update_state(meta, KFENCE_OBJECT_FREED); + + raw_spin_unlock_irqrestore(&meta->lock, flags); + + /* Protect to detect use-after-frees. */ + kfence_protect((unsigned long)addr); + + kcsan_end_scoped_access(&assert_page_exclusive); + if (!zombie) { + /* Add it to the tail of the freelist for reuse. */ + raw_spin_lock_irqsave(&kfence_freelist_lock, flags); + KFENCE_WARN_ON(!list_empty(&meta->list)); + list_add_tail(&meta->list, &kfence_freelist); + raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); + + atomic_long_dec(&counters[KFENCE_COUNTER_ALLOCATED]); + atomic_long_inc(&counters[KFENCE_COUNTER_FREES]); + } else { + /* See kfence_shutdown_cache(). */ + atomic_long_inc(&counters[KFENCE_COUNTER_ZOMBIES]); + } +} + +static void rcu_guarded_free(struct rcu_head *h) +{ + struct kfence_metadata *meta = container_of(h, struct kfence_metadata, rcu_head); + + kfence_guarded_free((void *)meta->addr, meta, false); +} + +static bool __init kfence_init_pool(void) +{ + unsigned long addr = (unsigned long)__kfence_pool; + struct page *pages; + int i; + + if (!__kfence_pool) + return false; + + if (!arch_kfence_init_pool()) + goto err; + + pages = virt_to_page(addr); + + /* + * Set up object pages: they must have PG_slab set, to avoid freeing + * these as real pages. + * + * We also want to avoid inserting kfence_free() in the kfree() + * fast-path in SLUB, and therefore need to ensure kfree() correctly + * enters __slab_free() slow-path. + */ + for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { + if (!i || (i % 2)) + continue; + + /* Verify we do not have a compound head page. */ + if (WARN_ON(compound_head(&pages[i]) != &pages[i])) + goto err; + + __SetPageSlab(&pages[i]); + } + + /* + * Protect the first 2 pages. The first page is mostly unnecessary, and + * merely serves as an extended guard page. However, adding one + * additional page in the beginning gives us an even number of pages, + * which simplifies the mapping of address to metadata index. + */ + for (i = 0; i < 2; i++) { + if (unlikely(!kfence_protect(addr))) + goto err; + + addr += PAGE_SIZE; + } + + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + struct kfence_metadata *meta = &kfence_metadata[i]; + + /* Initialize metadata. */ + INIT_LIST_HEAD(&meta->list); + raw_spin_lock_init(&meta->lock); + meta->state = KFENCE_OBJECT_UNUSED; + meta->addr = addr; /* Initialize for validation in metadata_to_pageaddr(). */ + list_add_tail(&meta->list, &kfence_freelist); + + /* Protect the right redzone. */ + if (unlikely(!kfence_protect(addr + PAGE_SIZE))) + goto err; + + addr += 2 * PAGE_SIZE; + } + + return true; + +err: + /* + * Only release unprotected pages, and do not try to go back and change + * page attributes due to risk of failing to do so as well. If changing + * page attributes for some pages fails, it is very likely that it also + * fails for the first page, and therefore expect addr==__kfence_pool in + * most failure cases. + */ + memblock_free_late(__pa(addr), KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool)); + __kfence_pool = NULL; + return false; +} + +/* === DebugFS Interface ==================================================== */ + +static int stats_show(struct seq_file *seq, void *v) +{ + int i; + + seq_printf(seq, "enabled: %i\n", READ_ONCE(kfence_enabled)); + for (i = 0; i < KFENCE_COUNTER_COUNT; i++) + seq_printf(seq, "%s: %ld\n", counter_names[i], atomic_long_read(&counters[i])); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(stats); + +/* + * debugfs seq_file operations for /sys/kernel/debug/kfence/objects. + * start_object() and next_object() return the object index + 1, because NULL is used + * to stop iteration. + */ +static void *start_object(struct seq_file *seq, loff_t *pos) +{ + if (*pos < CONFIG_KFENCE_NUM_OBJECTS) + return (void *)((long)*pos + 1); + return NULL; +} + +static void stop_object(struct seq_file *seq, void *v) +{ +} + +static void *next_object(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + if (*pos < CONFIG_KFENCE_NUM_OBJECTS) + return (void *)((long)*pos + 1); + return NULL; +} + +static int show_object(struct seq_file *seq, void *v) +{ + struct kfence_metadata *meta = &kfence_metadata[(long)v - 1]; + unsigned long flags; + + raw_spin_lock_irqsave(&meta->lock, flags); + kfence_print_object(seq, meta); + raw_spin_unlock_irqrestore(&meta->lock, flags); + seq_puts(seq, "---------------------------------\n"); + + return 0; +} + +static const struct seq_operations object_seqops = { + .start = start_object, + .next = next_object, + .stop = stop_object, + .show = show_object, +}; + +static int open_objects(struct inode *inode, struct file *file) +{ + return seq_open(file, &object_seqops); +} + +static const struct file_operations objects_fops = { + .open = open_objects, + .read = seq_read, + .llseek = seq_lseek, +}; + +static int __init kfence_debugfs_init(void) +{ + struct dentry *kfence_dir = debugfs_create_dir("kfence", NULL); + + debugfs_create_file("stats", 0444, kfence_dir, NULL, &stats_fops); + debugfs_create_file("objects", 0400, kfence_dir, NULL, &objects_fops); + return 0; +} + +late_initcall(kfence_debugfs_init); + +/* === Allocation Gate Timer ================================================ */ + +/* + * Set up delayed work, which will enable and disable the static key. We need to + * use a work queue (rather than a simple timer), since enabling and disabling a + * static key cannot be done from an interrupt. + * + * Note: Toggling a static branch currently causes IPIs, and here we'll end up + * with a total of 2 IPIs to all CPUs. If this ends up a problem in future (with + * more aggressive sampling intervals), we could get away with a variant that + * avoids IPIs, at the cost of not immediately capturing allocations if the + * instructions remain cached. + */ +static struct delayed_work kfence_timer; +static void toggle_allocation_gate(struct work_struct *work) +{ + if (!READ_ONCE(kfence_enabled)) + return; + + /* Enable static key, and await allocation to happen. */ + atomic_set(&kfence_allocation_gate, 0); +#ifdef CONFIG_KFENCE_STATIC_KEYS + static_branch_enable(&kfence_allocation_key); + /* + * Await an allocation. Timeout after 1 second, in case the kernel stops + * doing allocations, to avoid stalling this worker task for too long. + */ + { + unsigned long end_wait = jiffies + HZ; + + do { + set_current_state(TASK_UNINTERRUPTIBLE); + if (atomic_read(&kfence_allocation_gate) != 0) + break; + schedule_timeout(1); + } while (time_before(jiffies, end_wait)); + __set_current_state(TASK_RUNNING); + } + /* Disable static key and reset timer. */ + static_branch_disable(&kfence_allocation_key); +#endif + schedule_delayed_work(&kfence_timer, msecs_to_jiffies(kfence_sample_interval)); +} +static DECLARE_DELAYED_WORK(kfence_timer, toggle_allocation_gate); + +/* === Public interface ===================================================== */ + +void __init kfence_alloc_pool(void) +{ + if (!kfence_sample_interval) + return; + + __kfence_pool = memblock_alloc(KFENCE_POOL_SIZE, PAGE_SIZE); + + if (!__kfence_pool) + pr_err("failed to allocate pool\n"); +} + +void __init kfence_init(void) +{ + /* Setting kfence_sample_interval to 0 on boot disables KFENCE. */ + if (!kfence_sample_interval) + return; + + if (!kfence_init_pool()) { + pr_err("%s failed\n", __func__); + return; + } + + WRITE_ONCE(kfence_enabled, true); + schedule_delayed_work(&kfence_timer, 0); + pr_info("initialized - using %lu bytes for %d objects at 0x%p-0x%p\n", KFENCE_POOL_SIZE, + CONFIG_KFENCE_NUM_OBJECTS, (void *)__kfence_pool, + (void *)(__kfence_pool + KFENCE_POOL_SIZE)); +} + +void kfence_shutdown_cache(struct kmem_cache *s) +{ + unsigned long flags; + struct kfence_metadata *meta; + int i; + + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + bool in_use; + + meta = &kfence_metadata[i]; + + /* + * If we observe some inconsistent cache and state pair where we + * should have returned false here, cache destruction is racing + * with either kmem_cache_alloc() or kmem_cache_free(). Taking + * the lock will not help, as different critical section + * serialization will have the same outcome. + */ + if (READ_ONCE(meta->cache) != s || + READ_ONCE(meta->state) != KFENCE_OBJECT_ALLOCATED) + continue; + + raw_spin_lock_irqsave(&meta->lock, flags); + in_use = meta->cache == s && meta->state == KFENCE_OBJECT_ALLOCATED; + raw_spin_unlock_irqrestore(&meta->lock, flags); + + if (in_use) { + /* + * This cache still has allocations, and we should not + * release them back into the freelist so they can still + * safely be used and retain the kernel's default + * behaviour of keeping the allocations alive (leak the + * cache); however, they effectively become "zombie + * allocations" as the KFENCE objects are the only ones + * still in use and the owning cache is being destroyed. + * + * We mark them freed, so that any subsequent use shows + * more useful error messages that will include stack + * traces of the user of the object, the original + * allocation, and caller to shutdown_cache(). + */ + kfence_guarded_free((void *)meta->addr, meta, /*zombie=*/true); + } + } + + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + meta = &kfence_metadata[i]; + + /* See above. */ + if (READ_ONCE(meta->cache) != s || READ_ONCE(meta->state) != KFENCE_OBJECT_FREED) + continue; + + raw_spin_lock_irqsave(&meta->lock, flags); + if (meta->cache == s && meta->state == KFENCE_OBJECT_FREED) + meta->cache = NULL; + raw_spin_unlock_irqrestore(&meta->lock, flags); + } +} + +void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) +{ + /* + * allocation_gate only needs to become non-zero, so it doesn't make + * sense to continue writing to it and pay the associated contention + * cost, in case we have a large number of concurrent allocations. + */ + if (atomic_read(&kfence_allocation_gate) || atomic_inc_return(&kfence_allocation_gate) > 1) + return NULL; + + if (!READ_ONCE(kfence_enabled)) + return NULL; + + if (size > PAGE_SIZE) + return NULL; + + return kfence_guarded_alloc(s, size, flags); +} + +size_t kfence_ksize(const void *addr) +{ + const struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); + + /* + * Read locklessly -- if there is a race with __kfence_alloc(), this is + * either a use-after-free or invalid access. + */ + return meta ? meta->size : 0; +} + +void *kfence_object_start(const void *addr) +{ + const struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); + + /* + * Read locklessly -- if there is a race with __kfence_alloc(), this is + * either a use-after-free or invalid access. + */ + return meta ? (void *)meta->addr : NULL; +} + +void __kfence_free(void *addr) +{ + struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); + + /* + * If the objects of the cache are SLAB_TYPESAFE_BY_RCU, defer freeing + * the object, as the object page may be recycled for other-typed + * objects once it has been freed. meta->cache may be NULL if the cache + * was destroyed. + */ + if (unlikely(meta->cache && (meta->cache->flags & SLAB_TYPESAFE_BY_RCU))) + call_rcu(&meta->rcu_head, rcu_guarded_free); + else + kfence_guarded_free(addr, meta, false); +} + +bool kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs) +{ + const int page_index = (addr - (unsigned long)__kfence_pool) / PAGE_SIZE; + struct kfence_metadata *to_report = NULL; + enum kfence_error_type error_type; + unsigned long flags; + + if (!is_kfence_address((void *)addr)) + return false; + + if (!READ_ONCE(kfence_enabled)) /* If disabled at runtime ... */ + return kfence_unprotect(addr); /* ... unprotect and proceed. */ + + atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); + + if (page_index % 2) { + /* This is a redzone, report a buffer overflow. */ + struct kfence_metadata *meta; + int distance = 0; + + meta = addr_to_metadata(addr - PAGE_SIZE); + if (meta && READ_ONCE(meta->state) == KFENCE_OBJECT_ALLOCATED) { + to_report = meta; + /* Data race ok; distance calculation approximate. */ + distance = addr - data_race(meta->addr + meta->size); + } + + meta = addr_to_metadata(addr + PAGE_SIZE); + if (meta && READ_ONCE(meta->state) == KFENCE_OBJECT_ALLOCATED) { + /* Data race ok; distance calculation approximate. */ + if (!to_report || distance > data_race(meta->addr) - addr) + to_report = meta; + } + + if (!to_report) + goto out; + + raw_spin_lock_irqsave(&to_report->lock, flags); + to_report->unprotected_page = addr; + error_type = KFENCE_ERROR_OOB; + + /* + * If the object was freed before we took the look we can still + * report this as an OOB -- the report will simply show the + * stacktrace of the free as well. + */ + } else { + to_report = addr_to_metadata(addr); + if (!to_report) + goto out; + + raw_spin_lock_irqsave(&to_report->lock, flags); + error_type = KFENCE_ERROR_UAF; + /* + * We may race with __kfence_alloc(), and it is possible that a + * freed object may be reallocated. We simply report this as a + * use-after-free, with the stack trace showing the place where + * the object was re-allocated. + */ + } + +out: + if (to_report) { + kfence_report_error(addr, is_write, regs, to_report, error_type); + raw_spin_unlock_irqrestore(&to_report->lock, flags); + } else { + /* This may be a UAF or OOB access, but we can't be sure. */ + kfence_report_error(addr, is_write, regs, NULL, KFENCE_ERROR_INVALID); + } + + return kfence_unprotect(addr); /* Unprotect and let access proceed. */ +} diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h new file mode 100644 index 000000000000..24065321ff8a --- /dev/null +++ b/mm/kfence/kfence.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Kernel Electric-Fence (KFENCE). For more info please see + * Documentation/dev-tools/kfence.rst. + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef MM_KFENCE_KFENCE_H +#define MM_KFENCE_KFENCE_H + +#include +#include +#include +#include + +#include "../slab.h" /* for struct kmem_cache */ + +/* + * Get the canary byte pattern for @addr. Use a pattern that varies based on the + * lower 3 bits of the address, to detect memory corruptions with higher + * probability, where similar constants are used. + */ +#define KFENCE_CANARY_PATTERN(addr) ((u8)0xaa ^ (u8)((unsigned long)(addr) & 0x7)) + +/* Maximum stack depth for reports. */ +#define KFENCE_STACK_DEPTH 64 + +/* KFENCE object states. */ +enum kfence_object_state { + KFENCE_OBJECT_UNUSED, /* Object is unused. */ + KFENCE_OBJECT_ALLOCATED, /* Object is currently allocated. */ + KFENCE_OBJECT_FREED, /* Object was allocated, and then freed. */ +}; + +/* Alloc/free tracking information. */ +struct kfence_track { + pid_t pid; + int num_stack_entries; + unsigned long stack_entries[KFENCE_STACK_DEPTH]; +}; + +/* KFENCE metadata per guarded allocation. */ +struct kfence_metadata { + struct list_head list; /* Freelist node; access under kfence_freelist_lock. */ + struct rcu_head rcu_head; /* For delayed freeing. */ + + /* + * Lock protecting below data; to ensure consistency of the below data, + * since the following may execute concurrently: __kfence_alloc(), + * __kfence_free(), kfence_handle_page_fault(). However, note that we + * cannot grab the same metadata off the freelist twice, and multiple + * __kfence_alloc() cannot run concurrently on the same metadata. + */ + raw_spinlock_t lock; + + /* The current state of the object; see above. */ + enum kfence_object_state state; + + /* + * Allocated object address; cannot be calculated from size, because of + * alignment requirements. + * + * Invariant: ALIGN_DOWN(addr, PAGE_SIZE) is constant. + */ + unsigned long addr; + + /* + * The size of the original allocation. + */ + size_t size; + + /* + * The kmem_cache cache of the last allocation; NULL if never allocated + * or the cache has already been destroyed. + */ + struct kmem_cache *cache; + + /* + * In case of an invalid access, the page that was unprotected; we + * optimistically only store one address. + */ + unsigned long unprotected_page; + + /* Allocation and free stack information. */ + struct kfence_track alloc_track; + struct kfence_track free_track; +}; + +extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; + +/* KFENCE error types for report generation. */ +enum kfence_error_type { + KFENCE_ERROR_OOB, /* Detected a out-of-bounds access. */ + KFENCE_ERROR_UAF, /* Detected a use-after-free access. */ + KFENCE_ERROR_CORRUPTION, /* Detected a memory corruption on free. */ + KFENCE_ERROR_INVALID, /* Invalid access of unknown type. */ + KFENCE_ERROR_INVALID_FREE, /* Invalid free. */ +}; + +void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *regs, + const struct kfence_metadata *meta, enum kfence_error_type type); + +void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta); + +#endif /* MM_KFENCE_KFENCE_H */ diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c new file mode 100644 index 000000000000..4acf4251ee04 --- /dev/null +++ b/mm/kfence/kfence_test.c @@ -0,0 +1,858 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test cases for KFENCE memory safety error detector. Since the interface with + * which KFENCE's reports are obtained is via the console, this is the output we + * should verify. For each test case checks the presence (or absence) of + * generated reports. Relies on 'console' tracepoint to capture reports as they + * appear in the kernel log. + * + * Copyright (C) 2020, Google LLC. + * Author: Alexander Potapenko + * Marco Elver + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "kfence.h" + +/* Report as observed from console. */ +static struct { + spinlock_t lock; + int nlines; + char lines[2][256]; +} observed = { + .lock = __SPIN_LOCK_UNLOCKED(observed.lock), +}; + +/* Probe for console output: obtains observed lines of interest. */ +static void probe_console(void *ignore, const char *buf, size_t len) +{ + unsigned long flags; + int nlines; + + spin_lock_irqsave(&observed.lock, flags); + nlines = observed.nlines; + + if (strnstr(buf, "BUG: KFENCE: ", len) && strnstr(buf, "test_", len)) { + /* + * KFENCE report and related to the test. + * + * The provided @buf is not NUL-terminated; copy no more than + * @len bytes and let strscpy() add the missing NUL-terminator. + */ + strscpy(observed.lines[0], buf, min(len + 1, sizeof(observed.lines[0]))); + nlines = 1; + } else if (nlines == 1 && (strnstr(buf, "at 0x", len) || strnstr(buf, "of 0x", len))) { + strscpy(observed.lines[nlines++], buf, min(len + 1, sizeof(observed.lines[0]))); + } + + WRITE_ONCE(observed.nlines, nlines); /* Publish new nlines. */ + spin_unlock_irqrestore(&observed.lock, flags); +} + +/* Check if a report related to the test exists. */ +static bool report_available(void) +{ + return READ_ONCE(observed.nlines) == ARRAY_SIZE(observed.lines); +} + +/* Information we expect in a report. */ +struct expect_report { + enum kfence_error_type type; /* The type or error. */ + void *fn; /* Function pointer to expected function where access occurred. */ + char *addr; /* Address at which the bad access occurred. */ + bool is_write; /* Is access a write. */ +}; + +static const char *get_access_type(const struct expect_report *r) +{ + return r->is_write ? "write" : "read"; +} + +/* Check observed report matches information in @r. */ +static bool report_matches(const struct expect_report *r) +{ + bool ret = false; + unsigned long flags; + typeof(observed.lines) expect; + const char *end; + char *cur; + + /* Doubled-checked locking. */ + if (!report_available()) + return false; + + /* Generate expected report contents. */ + + /* Title */ + cur = expect[0]; + end = &expect[0][sizeof(expect[0]) - 1]; + switch (r->type) { + case KFENCE_ERROR_OOB: + cur += scnprintf(cur, end - cur, "BUG: KFENCE: out-of-bounds %s", + get_access_type(r)); + break; + case KFENCE_ERROR_UAF: + cur += scnprintf(cur, end - cur, "BUG: KFENCE: use-after-free %s", + get_access_type(r)); + break; + case KFENCE_ERROR_CORRUPTION: + cur += scnprintf(cur, end - cur, "BUG: KFENCE: memory corruption"); + break; + case KFENCE_ERROR_INVALID: + cur += scnprintf(cur, end - cur, "BUG: KFENCE: invalid %s", + get_access_type(r)); + break; + case KFENCE_ERROR_INVALID_FREE: + cur += scnprintf(cur, end - cur, "BUG: KFENCE: invalid free"); + break; + } + + scnprintf(cur, end - cur, " in %pS", r->fn); + /* The exact offset won't match, remove it; also strip module name. */ + cur = strchr(expect[0], '+'); + if (cur) + *cur = '\0'; + + /* Access information */ + cur = expect[1]; + end = &expect[1][sizeof(expect[1]) - 1]; + + switch (r->type) { + case KFENCE_ERROR_OOB: + cur += scnprintf(cur, end - cur, "Out-of-bounds %s at", get_access_type(r)); + break; + case KFENCE_ERROR_UAF: + cur += scnprintf(cur, end - cur, "Use-after-free %s at", get_access_type(r)); + break; + case KFENCE_ERROR_CORRUPTION: + cur += scnprintf(cur, end - cur, "Corrupted memory at"); + break; + case KFENCE_ERROR_INVALID: + cur += scnprintf(cur, end - cur, "Invalid %s at", get_access_type(r)); + break; + case KFENCE_ERROR_INVALID_FREE: + cur += scnprintf(cur, end - cur, "Invalid free of"); + break; + } + + cur += scnprintf(cur, end - cur, " 0x%p", (void *)r->addr); + + spin_lock_irqsave(&observed.lock, flags); + if (!report_available()) + goto out; /* A new report is being captured. */ + + /* Finally match expected output to what we actually observed. */ + ret = strstr(observed.lines[0], expect[0]) && strstr(observed.lines[1], expect[1]); +out: + spin_unlock_irqrestore(&observed.lock, flags); + return ret; +} + +/* ===== Test cases ===== */ + +#define TEST_PRIV_WANT_MEMCACHE ((void *)1) + +/* Cache used by tests; if NULL, allocate from kmalloc instead. */ +static struct kmem_cache *test_cache; + +static size_t setup_test_cache(struct kunit *test, size_t size, slab_flags_t flags, + void (*ctor)(void *)) +{ + if (test->priv != TEST_PRIV_WANT_MEMCACHE) + return size; + + kunit_info(test, "%s: size=%zu, ctor=%ps\n", __func__, size, ctor); + + /* + * Use SLAB_NOLEAKTRACE to prevent merging with existing caches. Any + * other flag in SLAB_NEVER_MERGE also works. Use SLAB_ACCOUNT to + * allocate via memcg, if enabled. + */ + flags |= SLAB_NOLEAKTRACE | SLAB_ACCOUNT; + test_cache = kmem_cache_create("test", size, 1, flags, ctor); + KUNIT_ASSERT_TRUE_MSG(test, test_cache, "could not create cache"); + + return size; +} + +static void test_cache_destroy(void) +{ + if (!test_cache) + return; + + kmem_cache_destroy(test_cache); + test_cache = NULL; +} + +static inline size_t kmalloc_cache_alignment(size_t size) +{ + return kmalloc_caches[kmalloc_type(GFP_KERNEL)][kmalloc_index(size)]->align; +} + +/* Must always inline to match stack trace against caller. */ +static __always_inline void test_free(void *ptr) +{ + if (test_cache) + kmem_cache_free(test_cache, ptr); + else + kfree(ptr); +} + +/* + * If this should be a KFENCE allocation, and on which side the allocation and + * the closest guard page should be. + */ +enum allocation_policy { + ALLOCATE_ANY, /* KFENCE, any side. */ + ALLOCATE_LEFT, /* KFENCE, left side of page. */ + ALLOCATE_RIGHT, /* KFENCE, right side of page. */ + ALLOCATE_NONE, /* No KFENCE allocation. */ +}; + +/* + * Try to get a guarded allocation from KFENCE. Uses either kmalloc() or the + * current test_cache if set up. + */ +static void *test_alloc(struct kunit *test, size_t size, gfp_t gfp, enum allocation_policy policy) +{ + void *alloc; + unsigned long timeout, resched_after; + const char *policy_name; + + switch (policy) { + case ALLOCATE_ANY: + policy_name = "any"; + break; + case ALLOCATE_LEFT: + policy_name = "left"; + break; + case ALLOCATE_RIGHT: + policy_name = "right"; + break; + case ALLOCATE_NONE: + policy_name = "none"; + break; + } + + kunit_info(test, "%s: size=%zu, gfp=%x, policy=%s, cache=%i\n", __func__, size, gfp, + policy_name, !!test_cache); + + /* + * 100x the sample interval should be more than enough to ensure we get + * a KFENCE allocation eventually. + */ + timeout = jiffies + msecs_to_jiffies(100 * CONFIG_KFENCE_SAMPLE_INTERVAL); + /* + * Especially for non-preemption kernels, ensure the allocation-gate + * timer can catch up: after @resched_after, every failed allocation + * attempt yields, to ensure the allocation-gate timer is scheduled. + */ + resched_after = jiffies + msecs_to_jiffies(CONFIG_KFENCE_SAMPLE_INTERVAL); + do { + if (test_cache) + alloc = kmem_cache_alloc(test_cache, gfp); + else + alloc = kmalloc(size, gfp); + + if (is_kfence_address(alloc)) { + struct page *page = virt_to_head_page(alloc); + struct kmem_cache *s = test_cache ?: kmalloc_caches[kmalloc_type(GFP_KERNEL)][kmalloc_index(size)]; + + /* + * Verify that various helpers return the right values + * even for KFENCE objects; these are required so that + * memcg accounting works correctly. + */ + KUNIT_EXPECT_EQ(test, obj_to_index(s, page, alloc), 0U); + KUNIT_EXPECT_EQ(test, objs_per_slab_page(s, page), 1); + + if (policy == ALLOCATE_ANY) + return alloc; + if (policy == ALLOCATE_LEFT && IS_ALIGNED((unsigned long)alloc, PAGE_SIZE)) + return alloc; + if (policy == ALLOCATE_RIGHT && + !IS_ALIGNED((unsigned long)alloc, PAGE_SIZE)) + return alloc; + } else if (policy == ALLOCATE_NONE) + return alloc; + + test_free(alloc); + + if (time_after(jiffies, resched_after)) + cond_resched(); + } while (time_before(jiffies, timeout)); + + KUNIT_ASSERT_TRUE_MSG(test, false, "failed to allocate from KFENCE"); + return NULL; /* Unreachable. */ +} + +static void test_out_of_bounds_read(struct kunit *test) +{ + size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_OOB, + .fn = test_out_of_bounds_read, + .is_write = false, + }; + char *buf; + + setup_test_cache(test, size, 0, NULL); + + /* + * If we don't have our own cache, adjust based on alignment, so that we + * actually access guard pages on either side. + */ + if (!test_cache) + size = kmalloc_cache_alignment(size); + + /* Test both sides. */ + + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_LEFT); + expect.addr = buf - 1; + READ_ONCE(*expect.addr); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + test_free(buf); + + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_RIGHT); + expect.addr = buf + size; + READ_ONCE(*expect.addr); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + test_free(buf); +} + +static void test_out_of_bounds_write(struct kunit *test) +{ + size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_OOB, + .fn = test_out_of_bounds_write, + .is_write = true, + }; + char *buf; + + setup_test_cache(test, size, 0, NULL); + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_LEFT); + expect.addr = buf - 1; + WRITE_ONCE(*expect.addr, 42); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + test_free(buf); +} + +static void test_use_after_free_read(struct kunit *test) +{ + const size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_UAF, + .fn = test_use_after_free_read, + .is_write = false, + }; + + setup_test_cache(test, size, 0, NULL); + expect.addr = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + test_free(expect.addr); + READ_ONCE(*expect.addr); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +static void test_double_free(struct kunit *test) +{ + const size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_INVALID_FREE, + .fn = test_double_free, + }; + + setup_test_cache(test, size, 0, NULL); + expect.addr = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + test_free(expect.addr); + test_free(expect.addr); /* Double-free. */ + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +static void test_invalid_addr_free(struct kunit *test) +{ + const size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_INVALID_FREE, + .fn = test_invalid_addr_free, + }; + char *buf; + + setup_test_cache(test, size, 0, NULL); + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + expect.addr = buf + 1; /* Free on invalid address. */ + test_free(expect.addr); /* Invalid address free. */ + test_free(buf); /* No error. */ + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +static void test_corruption(struct kunit *test) +{ + size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_CORRUPTION, + .fn = test_corruption, + }; + char *buf; + + setup_test_cache(test, size, 0, NULL); + + /* Test both sides. */ + + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_LEFT); + expect.addr = buf + size; + WRITE_ONCE(*expect.addr, 42); + test_free(buf); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_RIGHT); + expect.addr = buf - 1; + WRITE_ONCE(*expect.addr, 42); + test_free(buf); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* + * KFENCE is unable to detect an OOB if the allocation's alignment requirements + * leave a gap between the object and the guard page. Specifically, an + * allocation of e.g. 73 bytes is aligned on 8 and 128 bytes for SLUB or SLAB + * respectively. Therefore it is impossible for the allocated object to + * contiguously line up with the right guard page. + * + * However, we test that an access to memory beyond the gap results in KFENCE + * detecting an OOB access. + */ +static void test_kmalloc_aligned_oob_read(struct kunit *test) +{ + const size_t size = 73; + const size_t align = kmalloc_cache_alignment(size); + struct expect_report expect = { + .type = KFENCE_ERROR_OOB, + .fn = test_kmalloc_aligned_oob_read, + .is_write = false, + }; + char *buf; + + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_RIGHT); + + /* + * The object is offset to the right, so there won't be an OOB to the + * left of it. + */ + READ_ONCE(*(buf - 1)); + KUNIT_EXPECT_FALSE(test, report_available()); + + /* + * @buf must be aligned on @align, therefore buf + size belongs to the + * same page -> no OOB. + */ + READ_ONCE(*(buf + size)); + KUNIT_EXPECT_FALSE(test, report_available()); + + /* Overflowing by @align bytes will result in an OOB. */ + expect.addr = buf + size + align; + READ_ONCE(*expect.addr); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + + test_free(buf); +} + +static void test_kmalloc_aligned_oob_write(struct kunit *test) +{ + const size_t size = 73; + struct expect_report expect = { + .type = KFENCE_ERROR_CORRUPTION, + .fn = test_kmalloc_aligned_oob_write, + }; + char *buf; + + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_RIGHT); + /* + * The object is offset to the right, so we won't get a page + * fault immediately after it. + */ + expect.addr = buf + size; + WRITE_ONCE(*expect.addr, READ_ONCE(*expect.addr) + 1); + KUNIT_EXPECT_FALSE(test, report_available()); + test_free(buf); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* Test cache shrinking and destroying with KFENCE. */ +static void test_shrink_memcache(struct kunit *test) +{ + const size_t size = 32; + void *buf; + + setup_test_cache(test, size, 0, NULL); + KUNIT_EXPECT_TRUE(test, test_cache); + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + kmem_cache_shrink(test_cache); + test_free(buf); + + KUNIT_EXPECT_FALSE(test, report_available()); +} + +static void ctor_set_x(void *obj) +{ + /* Every object has at least 8 bytes. */ + memset(obj, 'x', 8); +} + +/* Ensure that SL*B does not modify KFENCE objects on bulk free. */ +static void test_free_bulk(struct kunit *test) +{ + int iter; + + for (iter = 0; iter < 5; iter++) { + const size_t size = setup_test_cache(test, 8 + prandom_u32_max(300), 0, + (iter & 1) ? ctor_set_x : NULL); + void *objects[] = { + test_alloc(test, size, GFP_KERNEL, ALLOCATE_RIGHT), + test_alloc(test, size, GFP_KERNEL, ALLOCATE_NONE), + test_alloc(test, size, GFP_KERNEL, ALLOCATE_LEFT), + test_alloc(test, size, GFP_KERNEL, ALLOCATE_NONE), + test_alloc(test, size, GFP_KERNEL, ALLOCATE_NONE), + }; + + kmem_cache_free_bulk(test_cache, ARRAY_SIZE(objects), objects); + KUNIT_ASSERT_FALSE(test, report_available()); + test_cache_destroy(); + } +} + +/* Test init-on-free works. */ +static void test_init_on_free(struct kunit *test) +{ + const size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_UAF, + .fn = test_init_on_free, + .is_write = false, + }; + int i; + + if (!IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON)) + return; + /* Assume it hasn't been disabled on command line. */ + + setup_test_cache(test, size, 0, NULL); + expect.addr = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + for (i = 0; i < size; i++) + expect.addr[i] = i + 1; + test_free(expect.addr); + + for (i = 0; i < size; i++) { + /* + * This may fail if the page was recycled by KFENCE and then + * written to again -- this however, is near impossible with a + * default config. + */ + KUNIT_EXPECT_EQ(test, expect.addr[i], (char)0); + + if (!i) /* Only check first access to not fail test if page is ever re-protected. */ + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + } +} + +/* Ensure that constructors work properly. */ +static void test_memcache_ctor(struct kunit *test) +{ + const size_t size = 32; + char *buf; + int i; + + setup_test_cache(test, size, 0, ctor_set_x); + buf = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + + for (i = 0; i < 8; i++) + KUNIT_EXPECT_EQ(test, buf[i], (char)'x'); + + test_free(buf); + + KUNIT_EXPECT_FALSE(test, report_available()); +} + +/* Test that memory is zeroed if requested. */ +static void test_gfpzero(struct kunit *test) +{ + const size_t size = PAGE_SIZE; /* PAGE_SIZE so we can use ALLOCATE_ANY. */ + char *buf1, *buf2; + int i; + + if (CONFIG_KFENCE_SAMPLE_INTERVAL > 100) { + kunit_warn(test, "skipping ... would take too long\n"); + return; + } + + setup_test_cache(test, size, 0, NULL); + buf1 = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + for (i = 0; i < size; i++) + buf1[i] = i + 1; + test_free(buf1); + + /* Try to get same address again -- this can take a while. */ + for (i = 0;; i++) { + buf2 = test_alloc(test, size, GFP_KERNEL | __GFP_ZERO, ALLOCATE_ANY); + if (buf1 == buf2) + break; + test_free(buf2); + + if (i == CONFIG_KFENCE_NUM_OBJECTS) { + kunit_warn(test, "giving up ... cannot get same object back\n"); + return; + } + } + + for (i = 0; i < size; i++) + KUNIT_EXPECT_EQ(test, buf2[i], (char)0); + + test_free(buf2); + + KUNIT_EXPECT_FALSE(test, report_available()); +} + +static void test_invalid_access(struct kunit *test) +{ + const struct expect_report expect = { + .type = KFENCE_ERROR_INVALID, + .fn = test_invalid_access, + .addr = &__kfence_pool[10], + .is_write = false, + }; + + READ_ONCE(__kfence_pool[10]); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* Test SLAB_TYPESAFE_BY_RCU works. */ +static void test_memcache_typesafe_by_rcu(struct kunit *test) +{ + const size_t size = 32; + struct expect_report expect = { + .type = KFENCE_ERROR_UAF, + .fn = test_memcache_typesafe_by_rcu, + .is_write = false, + }; + + setup_test_cache(test, size, SLAB_TYPESAFE_BY_RCU, NULL); + KUNIT_EXPECT_TRUE(test, test_cache); /* Want memcache. */ + + expect.addr = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + *expect.addr = 42; + + rcu_read_lock(); + test_free(expect.addr); + KUNIT_EXPECT_EQ(test, *expect.addr, (char)42); + /* + * Up to this point, memory should not have been freed yet, and + * therefore there should be no KFENCE report from the above access. + */ + rcu_read_unlock(); + + /* Above access to @expect.addr should not have generated a report! */ + KUNIT_EXPECT_FALSE(test, report_available()); + + /* Only after rcu_barrier() is the memory guaranteed to be freed. */ + rcu_barrier(); + + /* Expect use-after-free. */ + KUNIT_EXPECT_EQ(test, *expect.addr, (char)42); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + +/* Test krealloc(). */ +static void test_krealloc(struct kunit *test) +{ + const size_t size = 32; + const struct expect_report expect = { + .type = KFENCE_ERROR_UAF, + .fn = test_krealloc, + .addr = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY), + .is_write = false, + }; + char *buf = expect.addr; + int i; + + KUNIT_EXPECT_FALSE(test, test_cache); + KUNIT_EXPECT_EQ(test, ksize(buf), size); /* Precise size match after KFENCE alloc. */ + for (i = 0; i < size; i++) + buf[i] = i + 1; + + /* Check that we successfully change the size. */ + buf = krealloc(buf, size * 3, GFP_KERNEL); /* Grow. */ + /* Note: Might no longer be a KFENCE alloc. */ + KUNIT_EXPECT_GE(test, ksize(buf), size * 3); + for (i = 0; i < size; i++) + KUNIT_EXPECT_EQ(test, buf[i], (char)(i + 1)); + for (; i < size * 3; i++) /* Fill to extra bytes. */ + buf[i] = i + 1; + + buf = krealloc(buf, size * 2, GFP_KERNEL); /* Shrink. */ + KUNIT_EXPECT_GE(test, ksize(buf), size * 2); + for (i = 0; i < size * 2; i++) + KUNIT_EXPECT_EQ(test, buf[i], (char)(i + 1)); + + buf = krealloc(buf, 0, GFP_KERNEL); /* Free. */ + KUNIT_EXPECT_EQ(test, (unsigned long)buf, (unsigned long)ZERO_SIZE_PTR); + KUNIT_ASSERT_FALSE(test, report_available()); /* No reports yet! */ + + READ_ONCE(*expect.addr); /* Ensure krealloc() actually freed earlier KFENCE object. */ + KUNIT_ASSERT_TRUE(test, report_matches(&expect)); +} + +/* Test that some objects from a bulk allocation belong to KFENCE pool. */ +static void test_memcache_alloc_bulk(struct kunit *test) +{ + const size_t size = 32; + bool pass = false; + unsigned long timeout; + + setup_test_cache(test, size, 0, NULL); + KUNIT_EXPECT_TRUE(test, test_cache); /* Want memcache. */ + /* + * 100x the sample interval should be more than enough to ensure we get + * a KFENCE allocation eventually. + */ + timeout = jiffies + msecs_to_jiffies(100 * CONFIG_KFENCE_SAMPLE_INTERVAL); + do { + void *objects[100]; + int i, num = kmem_cache_alloc_bulk(test_cache, GFP_ATOMIC, ARRAY_SIZE(objects), + objects); + if (!num) + continue; + for (i = 0; i < ARRAY_SIZE(objects); i++) { + if (is_kfence_address(objects[i])) { + pass = true; + break; + } + } + kmem_cache_free_bulk(test_cache, num, objects); + /* + * kmem_cache_alloc_bulk() disables interrupts, and calling it + * in a tight loop may not give KFENCE a chance to switch the + * static branch. Call cond_resched() to let KFENCE chime in. + */ + cond_resched(); + } while (!pass && time_before(jiffies, timeout)); + + KUNIT_EXPECT_TRUE(test, pass); + KUNIT_EXPECT_FALSE(test, report_available()); +} + +/* + * KUnit does not provide a way to provide arguments to tests, and we encode + * additional info in the name. Set up 2 tests per test case, one using the + * default allocator, and another using a custom memcache (suffix '-memcache'). + */ +#define KFENCE_KUNIT_CASE(test_name) \ + { .run_case = test_name, .name = #test_name }, \ + { .run_case = test_name, .name = #test_name "-memcache" } + +static struct kunit_case kfence_test_cases[] = { + KFENCE_KUNIT_CASE(test_out_of_bounds_read), + KFENCE_KUNIT_CASE(test_out_of_bounds_write), + KFENCE_KUNIT_CASE(test_use_after_free_read), + KFENCE_KUNIT_CASE(test_double_free), + KFENCE_KUNIT_CASE(test_invalid_addr_free), + KFENCE_KUNIT_CASE(test_corruption), + KFENCE_KUNIT_CASE(test_free_bulk), + KFENCE_KUNIT_CASE(test_init_on_free), + KUNIT_CASE(test_kmalloc_aligned_oob_read), + KUNIT_CASE(test_kmalloc_aligned_oob_write), + KUNIT_CASE(test_shrink_memcache), + KUNIT_CASE(test_memcache_ctor), + KUNIT_CASE(test_invalid_access), + KUNIT_CASE(test_gfpzero), + KUNIT_CASE(test_memcache_typesafe_by_rcu), + KUNIT_CASE(test_krealloc), + KUNIT_CASE(test_memcache_alloc_bulk), + {}, +}; + +/* ===== End test cases ===== */ + +static int test_init(struct kunit *test) +{ + unsigned long flags; + int i; + + spin_lock_irqsave(&observed.lock, flags); + for (i = 0; i < ARRAY_SIZE(observed.lines); i++) + observed.lines[i][0] = '\0'; + observed.nlines = 0; + spin_unlock_irqrestore(&observed.lock, flags); + + /* Any test with 'memcache' in its name will want a memcache. */ + if (strstr(test->name, "memcache")) + test->priv = TEST_PRIV_WANT_MEMCACHE; + else + test->priv = NULL; + + return 0; +} + +static void test_exit(struct kunit *test) +{ + test_cache_destroy(); +} + +static struct kunit_suite kfence_test_suite = { + .name = "kfence", + .test_cases = kfence_test_cases, + .init = test_init, + .exit = test_exit, +}; +static struct kunit_suite *kfence_test_suites[] = { &kfence_test_suite, NULL }; + +static void register_tracepoints(struct tracepoint *tp, void *ignore) +{ + check_trace_callback_type_console(probe_console); + if (!strcmp(tp->name, "console")) + WARN_ON(tracepoint_probe_register(tp, probe_console, NULL)); +} + +static void unregister_tracepoints(struct tracepoint *tp, void *ignore) +{ + if (!strcmp(tp->name, "console")) + tracepoint_probe_unregister(tp, probe_console, NULL); +} + +/* + * We only want to do tracepoints setup and teardown once, therefore we have to + * customize the init and exit functions and cannot rely on kunit_test_suite(). + */ +static int __init kfence_test_init(void) +{ + /* + * Because we want to be able to build the test as a module, we need to + * iterate through all known tracepoints, since the static registration + * won't work here. + */ + for_each_kernel_tracepoint(register_tracepoints, NULL); + return __kunit_test_suites_init(kfence_test_suites); +} + +static void kfence_test_exit(void) +{ + __kunit_test_suites_exit(kfence_test_suites); + for_each_kernel_tracepoint(unregister_tracepoints, NULL); + tracepoint_synchronize_unregister(); +} + +late_initcall(kfence_test_init); +module_exit(kfence_test_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Alexander Potapenko , Marco Elver "); diff --git a/mm/kfence/report.c b/mm/kfence/report.c new file mode 100644 index 000000000000..ab83d5a59bb1 --- /dev/null +++ b/mm/kfence/report.c @@ -0,0 +1,262 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KFENCE reporting. + * + * Copyright (C) 2020, Google LLC. + */ + +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "kfence.h" + +extern bool no_hash_pointers; + +/* Helper function to either print to a seq_file or to console. */ +__printf(2, 3) +static void seq_con_printf(struct seq_file *seq, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + if (seq) + seq_vprintf(seq, fmt, args); + else + vprintk(fmt, args); + va_end(args); +} + +/* + * Get the number of stack entries to skip to get out of MM internals. @type is + * optional, and if set to NULL, assumes an allocation or free stack. + */ +static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries, + const enum kfence_error_type *type) +{ + char buf[64]; + int skipnr, fallback = 0; + + if (type) { + /* Depending on error type, find different stack entries. */ + switch (*type) { + case KFENCE_ERROR_UAF: + case KFENCE_ERROR_OOB: + case KFENCE_ERROR_INVALID: + /* + * kfence_handle_page_fault() may be called with pt_regs + * set to NULL; in that case we'll simply show the full + * stack trace. + */ + return 0; + case KFENCE_ERROR_CORRUPTION: + case KFENCE_ERROR_INVALID_FREE: + break; + } + } + + for (skipnr = 0; skipnr < num_entries; skipnr++) { + int len = scnprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skipnr]); + + if (str_has_prefix(buf, "kfence_") || str_has_prefix(buf, "__kfence_") || + !strncmp(buf, "__slab_free", len)) { + /* + * In case of tail calls from any of the below + * to any of the above. + */ + fallback = skipnr + 1; + } + + /* Also the *_bulk() variants by only checking prefixes. */ + if (str_has_prefix(buf, "kfree") || + str_has_prefix(buf, "kmem_cache_free") || + str_has_prefix(buf, "__kmalloc") || + str_has_prefix(buf, "kmem_cache_alloc")) + goto found; + } + if (fallback < num_entries) + return fallback; +found: + skipnr++; + return skipnr < num_entries ? skipnr : 0; +} + +static void kfence_print_stack(struct seq_file *seq, const struct kfence_metadata *meta, + bool show_alloc) +{ + const struct kfence_track *track = show_alloc ? &meta->alloc_track : &meta->free_track; + + if (track->num_stack_entries) { + /* Skip allocation/free internals stack. */ + int i = get_stack_skipnr(track->stack_entries, track->num_stack_entries, NULL); + + /* stack_trace_seq_print() does not exist; open code our own. */ + for (; i < track->num_stack_entries; i++) + seq_con_printf(seq, " %pS\n", (void *)track->stack_entries[i]); + } else { + seq_con_printf(seq, " no %s stack\n", show_alloc ? "allocation" : "deallocation"); + } +} + +void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta) +{ + const int size = abs(meta->size); + const unsigned long start = meta->addr; + const struct kmem_cache *const cache = meta->cache; + + lockdep_assert_held(&meta->lock); + + if (meta->state == KFENCE_OBJECT_UNUSED) { + seq_con_printf(seq, "kfence-#%zd unused\n", meta - kfence_metadata); + return; + } + + seq_con_printf(seq, + "kfence-#%zd [0x%p-0x%p" + ", size=%d, cache=%s] allocated by task %d:\n", + meta - kfence_metadata, (void *)start, (void *)(start + size - 1), size, + (cache && cache->name) ? cache->name : "", meta->alloc_track.pid); + kfence_print_stack(seq, meta, true); + + if (meta->state == KFENCE_OBJECT_FREED) { + seq_con_printf(seq, "\nfreed by task %d:\n", meta->free_track.pid); + kfence_print_stack(seq, meta, false); + } +} + +/* + * Show bytes at @addr that are different from the expected canary values, up to + * @max_bytes. + */ +static void print_diff_canary(unsigned long address, size_t bytes_to_show, + const struct kfence_metadata *meta) +{ + const unsigned long show_until_addr = address + bytes_to_show; + const u8 *cur, *end; + + /* Do not show contents of object nor read into following guard page. */ + end = (const u8 *)(address < meta->addr ? min(show_until_addr, meta->addr) + : min(show_until_addr, PAGE_ALIGN(address))); + + pr_cont("["); + for (cur = (const u8 *)address; cur < end; cur++) { + if (*cur == KFENCE_CANARY_PATTERN(cur)) + pr_cont(" ."); + else if (no_hash_pointers) + pr_cont(" 0x%02x", *cur); + else /* Do not leak kernel memory in non-debug builds. */ + pr_cont(" !"); + } + pr_cont(" ]"); +} + +static const char *get_access_type(bool is_write) +{ + return is_write ? "write" : "read"; +} + +void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *regs, + const struct kfence_metadata *meta, enum kfence_error_type type) +{ + unsigned long stack_entries[KFENCE_STACK_DEPTH] = { 0 }; + const ptrdiff_t object_index = meta ? meta - kfence_metadata : -1; + int num_stack_entries; + int skipnr = 0; + + if (regs) { + num_stack_entries = stack_trace_save_regs(regs, stack_entries, KFENCE_STACK_DEPTH, 0); + } else { + num_stack_entries = stack_trace_save(stack_entries, KFENCE_STACK_DEPTH, 1); + skipnr = get_stack_skipnr(stack_entries, num_stack_entries, &type); + } + + /* Require non-NULL meta, except if KFENCE_ERROR_INVALID. */ + if (WARN_ON(type != KFENCE_ERROR_INVALID && !meta)) + return; + + if (meta) + lockdep_assert_held(&meta->lock); + /* + * Because we may generate reports in printk-unfriendly parts of the + * kernel, such as scheduler code, the use of printk() could deadlock. + * Until such time that all printing code here is safe in all parts of + * the kernel, accept the risk, and just get our message out (given the + * system might already behave unpredictably due to the memory error). + * As such, also disable lockdep to hide warnings, and avoid disabling + * lockdep for the rest of the kernel. + */ + lockdep_off(); + + pr_err("==================================================================\n"); + /* Print report header. */ + switch (type) { + case KFENCE_ERROR_OOB: { + const bool left_of_object = address < meta->addr; + + pr_err("BUG: KFENCE: out-of-bounds %s in %pS\n\n", get_access_type(is_write), + (void *)stack_entries[skipnr]); + pr_err("Out-of-bounds %s at 0x%p (%luB %s of kfence-#%zd):\n", + get_access_type(is_write), (void *)address, + left_of_object ? meta->addr - address : address - meta->addr, + left_of_object ? "left" : "right", object_index); + break; + } + case KFENCE_ERROR_UAF: + pr_err("BUG: KFENCE: use-after-free %s in %pS\n\n", get_access_type(is_write), + (void *)stack_entries[skipnr]); + pr_err("Use-after-free %s at 0x%p (in kfence-#%zd):\n", + get_access_type(is_write), (void *)address, object_index); + break; + case KFENCE_ERROR_CORRUPTION: + pr_err("BUG: KFENCE: memory corruption in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Corrupted memory at 0x%p ", (void *)address); + print_diff_canary(address, 16, meta); + pr_cont(" (in kfence-#%zd):\n", object_index); + break; + case KFENCE_ERROR_INVALID: + pr_err("BUG: KFENCE: invalid %s in %pS\n\n", get_access_type(is_write), + (void *)stack_entries[skipnr]); + pr_err("Invalid %s at 0x%p:\n", get_access_type(is_write), + (void *)address); + break; + case KFENCE_ERROR_INVALID_FREE: + pr_err("BUG: KFENCE: invalid free in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Invalid free of 0x%p (in kfence-#%zd):\n", (void *)address, + object_index); + break; + } + + /* Print stack trace and object info. */ + stack_trace_print(stack_entries + skipnr, num_stack_entries - skipnr, 0); + + if (meta) { + pr_err("\n"); + kfence_print_object(NULL, meta); + } + + /* Print report footer. */ + pr_err("\n"); + if (no_hash_pointers && regs) + show_regs(regs); + else + dump_stack_print_info(KERN_ERR); + trace_error_report_end(ERROR_DETECTOR_KFENCE, address); + pr_err("==================================================================\n"); + + lockdep_on(); + + if (panic_on_warn) + panic("panic_on_warn set ...\n"); + + /* We encountered a memory unsafety error, taint the kernel! */ + add_taint(TAINT_BAD_PAGE, LOCKDEP_STILL_OK); +} diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 75e246f680f4..a7d6cb912b05 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -442,18 +442,28 @@ static inline int khugepaged_test_exit(struct mm_struct *mm) static bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags) { - if ((!(vm_flags & VM_HUGEPAGE) && !khugepaged_always()) || - (vm_flags & VM_NOHUGEPAGE) || + /* Explicitly disabled through madvise. */ + if ((vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) return false; - if (shmem_file(vma->vm_file) || - (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && - vma->vm_file && - (vm_flags & VM_DENYWRITE))) { + /* Enabled via shmem mount options or sysfs settings. */ + if (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) { return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, HPAGE_PMD_NR); } + + /* THP settings require madvise. */ + if (!(vm_flags & VM_HUGEPAGE) && !khugepaged_always()) + return false; + + /* Read-only file mappings need to be aligned for THP to work. */ + if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && vma->vm_file && + (vm_flags & VM_DENYWRITE)) { + return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, + HPAGE_PMD_NR); + } + if (!vma->anon_vma || vma->vm_ops) return false; if (vma_is_temporary_stack(vma)) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 55c671904aac..24210c9bd843 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1312,6 +1312,12 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, */ put_page(page); + /* device metadata space is not recoverable */ + if (!pgmap_pfn_valid(pgmap, pfn)) { + rc = -ENXIO; + goto out; + } + /* * Prevent the inode from being freed while we are interrogating * the address_space, typically this would be handled by diff --git a/mm/memory.c b/mm/memory.c index 6aaa52937d76..350186150ab8 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2916,7 +2916,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); - entry = pte_sw_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* @@ -3576,7 +3575,6 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) __SetPageUptodate(page); entry = mk_pte(page, vma->vm_page_prot); - entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); @@ -3761,8 +3759,6 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) if (prefault && arch_wants_old_prefaulted_pte()) entry = pte_mkold(entry); - else - entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index abe43c1ae920..5ba51a8bdaeb 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -67,17 +67,17 @@ void put_online_mems(void) bool movable_node_enabled = false; #ifndef CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE -int memhp_default_online_type = MMOP_OFFLINE; +int mhp_default_online_type = MMOP_OFFLINE; #else -int memhp_default_online_type = MMOP_ONLINE; +int mhp_default_online_type = MMOP_ONLINE; #endif static int __init setup_memhp_default_state(char *str) { - const int online_type = memhp_online_type_from_str(str); + const int online_type = mhp_online_type_from_str(str); if (online_type >= 0) - memhp_default_online_type = online_type; + mhp_default_online_type = online_type; return 1; } @@ -107,6 +107,9 @@ static struct resource *register_memory_resource(u64 start, u64 size, if (strcmp(resource_name, "System RAM")) flags |= IORESOURCE_SYSRAM_DRIVER_MANAGED; + if (!mhp_range_allowed(start, size, true)) + return ERR_PTR(-E2BIG); + /* * Make sure value parsed from 'mem=' only restricts memory adding * while booting, so that memory hotplug won't be impacted. Please @@ -284,21 +287,53 @@ static int check_pfn_span(unsigned long pfn, unsigned long nr_pages, return 0; } -static int check_hotplug_memory_addressable(unsigned long pfn, - unsigned long nr_pages) +/* + * Return page for the valid pfn only if the page is online. All pfn + * walkers which rely on the fully initialized page->flags and others + * should use this rather than pfn_valid && pfn_to_page + */ +struct page *pfn_to_online_page(unsigned long pfn) { - const u64 max_addr = PFN_PHYS(pfn + nr_pages) - 1; + unsigned long nr = pfn_to_section_nr(pfn); + struct dev_pagemap *pgmap; + struct mem_section *ms; - if (max_addr >> MAX_PHYSMEM_BITS) { - const u64 max_allowed = (1ull << (MAX_PHYSMEM_BITS + 1)) - 1; - WARN(1, - "Hotplugged memory exceeds maximum addressable address, range=%#llx-%#llx, maximum=%#llx\n", - (u64)PFN_PHYS(pfn), max_addr, max_allowed); - return -E2BIG; - } + if (nr >= NR_MEM_SECTIONS) + return NULL; - return 0; + ms = __nr_to_section(nr); + if (!online_section(ms)) + return NULL; + + /* + * Save some code text when online_section() + + * pfn_section_valid() are sufficient. + */ + if (IS_ENABLED(CONFIG_HAVE_ARCH_PFN_VALID) && !pfn_valid(pfn)) + return NULL; + + if (!pfn_section_valid(ms, pfn)) + return NULL; + + if (!online_device_section(ms)) + return pfn_to_page(pfn); + + /* + * Slowpath: when ZONE_DEVICE collides with + * ZONE_{NORMAL,MOVABLE} within the same section some pfns in + * the section may be 'offline' but 'valid'. Only + * get_dev_pagemap() can determine sub-section online status. + */ + pgmap = get_dev_pagemap(pfn, NULL); + put_dev_pagemap(pgmap); + + /* The presence of a pgmap indicates ZONE_DEVICE offline pfn */ + if (pgmap) + return NULL; + + return pfn_to_page(pfn); } +EXPORT_SYMBOL_GPL(pfn_to_online_page); /* * Reasonably generic function for adding memory. It is @@ -317,9 +352,7 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, if (WARN_ON_ONCE(!params->pgprot.pgprot)) return -EINVAL; - err = check_hotplug_memory_addressable(pfn, nr_pages); - if (err) - return err; + VM_BUG_ON(!mhp_range_allowed(PFN_PHYS(pfn), nr_pages * PAGE_SIZE, false)); if (altmap) { /* @@ -445,20 +478,19 @@ static void update_pgdat_span(struct pglist_data *pgdat) for (zone = pgdat->node_zones; zone < pgdat->node_zones + MAX_NR_ZONES; zone++) { - unsigned long zone_end_pfn = zone->zone_start_pfn + - zone->spanned_pages; + unsigned long end_pfn = zone_end_pfn(zone); /* No need to lock the zones, they can't change. */ if (!zone->spanned_pages) continue; if (!node_end_pfn) { node_start_pfn = zone->zone_start_pfn; - node_end_pfn = zone_end_pfn; + node_end_pfn = end_pfn; continue; } - if (zone_end_pfn > node_end_pfn) - node_end_pfn = zone_end_pfn; + if (end_pfn > node_end_pfn) + node_end_pfn = end_pfn; if (zone->zone_start_pfn < node_start_pfn) node_start_pfn = zone->zone_start_pfn; } @@ -678,6 +710,14 @@ static void __meminit resize_pgdat_range(struct pglist_data *pgdat, unsigned lon pgdat->node_spanned_pages = max(start_pfn + nr_pages, old_end_pfn) - pgdat->node_start_pfn; } + +static void section_taint_zone_device(unsigned long pfn) +{ + struct mem_section *ms = __pfn_to_section(pfn); + + ms->section_mem_map |= SECTION_TAINT_ZONE_DEVICE; +} + /* * Associate the pfn range with the given zone, initializing the memmaps * and resizing the pgdat/zone data to span the added pages. After this @@ -707,6 +747,19 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, resize_pgdat_range(pgdat, start_pfn, nr_pages); pgdat_resize_unlock(pgdat, &flags); + /* + * Subsection population requires care in pfn_to_online_page(). + * Set the taint to enable the slow path detection of + * ZONE_DEVICE pages in an otherwise ZONE_{NORMAL,MOVABLE} + * section. + */ + if (zone_is_zone_device(zone)) { + if (!IS_ALIGNED(start_pfn, PAGES_PER_SECTION)) + section_taint_zone_device(start_pfn); + if (!IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION)) + section_taint_zone_device(start_pfn + nr_pages); + } + /* * TODO now we have a visible range of pages which are not associated * with their zone properly. Not nice but set_pfnblock_flags_mask @@ -1007,7 +1060,7 @@ static int check_hotplug_memory_range(u64 start, u64 size) static int online_memory_block(struct memory_block *mem, void *arg) { - mem->online_type = memhp_default_online_type; + mem->online_type = mhp_default_online_type; return device_online(&mem->dev); } @@ -1084,11 +1137,11 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) * In case we're allowed to merge the resource, flag it and trigger * merging now that adding succeeded. */ - if (mhp_flags & MEMHP_MERGE_RESOURCE) + if (mhp_flags & MHP_MERGE_RESOURCE) merge_system_ram_resource(res); /* online pages if requested */ - if (memhp_default_online_type != MMOP_OFFLINE) + if (mhp_default_online_type != MMOP_OFFLINE) walk_memory_blocks(start, size, NULL, online_memory_block); return ret; @@ -1180,6 +1233,61 @@ int add_memory_driver_managed(int nid, u64 start, u64 size, } EXPORT_SYMBOL_GPL(add_memory_driver_managed); +/* + * Platforms should define arch_get_mappable_range() that provides + * maximum possible addressable physical memory range for which the + * linear mapping could be created. The platform returned address + * range must adhere to these following semantics. + * + * - range.start <= range.end + * - Range includes both end points [range.start..range.end] + * + * There is also a fallback definition provided here, allowing the + * entire possible physical address range in case any platform does + * not define arch_get_mappable_range(). + */ +struct range __weak arch_get_mappable_range(void) +{ + struct range mhp_range = { + .start = 0UL, + .end = -1ULL, + }; + return mhp_range; +} + +struct range mhp_get_pluggable_range(bool need_mapping) +{ + const u64 max_phys = (1ULL << MAX_PHYSMEM_BITS) - 1; + struct range mhp_range; + + if (need_mapping) { + mhp_range = arch_get_mappable_range(); + if (mhp_range.start > max_phys) { + mhp_range.start = 0; + mhp_range.end = 0; + } + mhp_range.end = min_t(u64, mhp_range.end, max_phys); + } else { + mhp_range.start = 0; + mhp_range.end = max_phys; + } + return mhp_range; +} +EXPORT_SYMBOL_GPL(mhp_get_pluggable_range); + +bool mhp_range_allowed(u64 start, u64 size, bool need_mapping) +{ + struct range mhp_range = mhp_get_pluggable_range(need_mapping); + u64 end = start + size; + + if (start < end && start >= mhp_range.start && (end - 1) <= mhp_range.end) + return true; + + pr_warn("Hotplug memory [%#llx-%#llx] exceeds maximum addressable range [%#llx-%#llx]\n", + start, end, mhp_range.start, mhp_range.end); + return false; +} + #ifdef CONFIG_MEMORY_HOTREMOVE /* * Confirm all pages in a range [start, end) belong to the same zone (skipping diff --git a/mm/memremap.c b/mm/memremap.c index 16b2fb482da1..7aa7d6e80ee5 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -80,6 +80,21 @@ static unsigned long pfn_first(struct dev_pagemap *pgmap, int range_id) return pfn + vmem_altmap_offset(pgmap_altmap(pgmap)); } +bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) +{ + int i; + + for (i = 0; i < pgmap->nr_range; i++) { + struct range *range = &pgmap->ranges[i]; + + if (pfn >= PHYS_PFN(range->start) && + pfn <= PHYS_PFN(range->end)) + return pfn >= pfn_first(pgmap, i); + } + + return false; +} + static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id) { const struct range *range = &pgmap->ranges[range_id]; @@ -185,6 +200,7 @@ static void dev_pagemap_percpu_release(struct percpu_ref *ref) static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, int range_id, int nid) { + const bool is_private = pgmap->type == MEMORY_DEVICE_PRIVATE; struct range *range = &pgmap->ranges[range_id]; struct dev_pagemap *conflict_pgmap; int error, is_ram; @@ -230,6 +246,11 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, if (error) goto err_pfn_remap; + if (!mhp_range_allowed(range->start, range_len(range), !is_private)) { + error = -EINVAL; + goto err_pfn_remap; + } + mem_hotplug_begin(); /* @@ -243,7 +264,7 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, * the CPU, we do want the linear mapping and thus use * arch_add_memory(). */ - if (pgmap->type == MEMORY_DEVICE_PRIVATE) { + if (is_private) { error = add_pages(nid, PHYS_PFN(range->start), PHYS_PFN(range_len(range)), params); } else { diff --git a/mm/mlock.c b/mm/mlock.c index fc5bb3f86d2f..bcc4608763a8 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -622,7 +622,7 @@ static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm, vma = find_vma(mm, start); if (vma == NULL) - vma = mm->mmap; + return 0; for (; vma ; vma = vma->vm_next) { if (start >= vma->vm_end) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 60556a4271a3..c9d7d350923b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2180,6 +2180,7 @@ void __init init_cma_reserved_pageblock(struct page *page) } adjust_managed_page_count(page, pageblock_nr_pages); + page_zone(page)->cma_pages += pageblock_nr_pages; } #endif diff --git a/mm/rmap.c b/mm/rmap.c index e26ae119a131..b0fc27e77d6d 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -168,7 +168,7 @@ static void anon_vma_chain_link(struct vm_area_struct *vma, * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in page_lock_anon_vma_read() - * and that may actually touch the spinlock even in the newly + * and that may actually touch the rwsem even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * @@ -359,7 +359,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) goto out_error_free_anon_vma; /* - * The root anon_vma's spinlock is the lock actually used when we + * The root anon_vma's rwsem is the lock actually used when we * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; @@ -462,8 +462,8 @@ void __init anon_vma_init(void) * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against page_remove_rmap() - * the best this function can do is return a locked anon_vma that might - * have been relevant to this page. + * the best this function can do is return a refcount increased anon_vma + * that might have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). @@ -1086,8 +1086,7 @@ static void __page_check_anon_rmap(struct page *page, * be set up correctly at this point. * * We have exclusion against page_add_anon_rmap because the caller - * always holds the page locked, except if called from page_dup_rmap, - * in which case the page is already known to be setup. + * always holds the page locked. * * We have exclusion against page_add_new_anon_rmap because those pages * are initially only visible via the pagetables, and the pte is locked @@ -1737,9 +1736,9 @@ static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) return vma_is_temporary_stack(vma); } -static int page_mapcount_is_zero(struct page *page) +static int page_not_mapped(struct page *page) { - return !total_mapcount(page); + return !page_mapped(page); } /** @@ -1757,7 +1756,7 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, - .done = page_mapcount_is_zero, + .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, }; @@ -1781,11 +1780,6 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) return !page_mapcount(page) ? true : false; } -static int page_not_mapped(struct page *page) -{ - return !page_mapped(page); -}; - /** * try_to_munlock - try to munlock a page * @page: the page to be munlocked diff --git a/mm/shmem.c b/mm/shmem.c index ff741d229701..b2db4ed0fbc7 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -842,7 +842,6 @@ unsigned long shmem_swap_usage(struct vm_area_struct *vma) void shmem_unlock_mapping(struct address_space *mapping) { struct pagevec pvec; - pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index = 0; pagevec_init(&pvec); @@ -850,16 +849,8 @@ void shmem_unlock_mapping(struct address_space *mapping) * Minor point, but we might as well stop if someone else SHM_LOCKs it. */ while (!mapping_unevictable(mapping)) { - /* - * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it - * has finished, if it hits a row of PAGEVEC_SIZE swap entries. - */ - pvec.nr = find_get_entries(mapping, index, - PAGEVEC_SIZE, pvec.pages, indices); - if (!pvec.nr) + if (!pagevec_lookup(&pvec, mapping, &index)) break; - index = indices[pvec.nr - 1] + 1; - pagevec_remove_exceptionals(&pvec); check_move_unevictable_pages(&pvec); pagevec_release(&pvec); cond_resched(); @@ -916,18 +907,12 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, pagevec_init(&pvec); index = start; - while (index < end) { - pvec.nr = find_get_entries(mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); - if (!pvec.nr) - break; + while (index < end && find_lock_entries(mapping, index, end - 1, + &pvec, indices)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; index = indices[i]; - if (index >= end) - break; if (xa_is_value(page)) { if (unfalloc) @@ -936,18 +921,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index, page); continue; } + index += thp_nr_pages(page) - 1; - VM_BUG_ON_PAGE(page_to_pgoff(page) != index, page); - - if (!trylock_page(page)) - continue; - - if ((!unfalloc || !PageUptodate(page)) && - page_mapping(page) == mapping) { - VM_BUG_ON_PAGE(PageWriteback(page), page); - if (shmem_punch_compound(page, start, end)) - truncate_inode_page(mapping, page); - } + if (!unfalloc || !PageUptodate(page)) + truncate_inode_page(mapping, page); unlock_page(page); } pagevec_remove_exceptionals(&pvec); @@ -988,10 +965,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, while (index < end) { cond_resched(); - pvec.nr = find_get_entries(mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); - if (!pvec.nr) { + if (!find_get_entries(mapping, index, end - 1, &pvec, + indices)) { /* If all gone or hole-punch or unfalloc, we're done */ if (index == start || end != -1) break; @@ -1003,9 +978,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, struct page *page = pvec.pages[i]; index = indices[i]; - if (index >= end) - break; - if (xa_is_value(page)) { if (unfalloc) continue; @@ -1533,6 +1505,30 @@ static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, return page; } +/* + * Make sure huge_gfp is always more limited than limit_gfp. + * Some of the flags set permissions, while others set limitations. + */ +static gfp_t limit_gfp_mask(gfp_t huge_gfp, gfp_t limit_gfp) +{ + gfp_t allowflags = __GFP_IO | __GFP_FS | __GFP_RECLAIM; + gfp_t denyflags = __GFP_NOWARN | __GFP_NORETRY; + gfp_t zoneflags = limit_gfp & GFP_ZONEMASK; + gfp_t result = huge_gfp & ~(allowflags | GFP_ZONEMASK); + + /* Allow allocations only from the originally specified zones. */ + result |= zoneflags; + + /* + * Minimize the result gfp by taking the union with the deny flags, + * and the intersection of the allow flags. + */ + result |= (limit_gfp & denyflags); + result |= (huge_gfp & limit_gfp) & allowflags; + + return result; +} + static struct page *shmem_alloc_hugepage(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { @@ -1547,8 +1543,8 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, return NULL; shmem_pseudo_vma_init(&pvma, info, hindex); - page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, - HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); + page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), + true); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); @@ -1804,6 +1800,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct page *page; enum sgp_type sgp_huge = sgp; pgoff_t hindex = index; + gfp_t huge_gfp; int error; int once = 0; int alloced = 0; @@ -1821,7 +1818,8 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, sbinfo = SHMEM_SB(inode->i_sb); charge_mm = vma ? vma->vm_mm : current->mm; - page = find_lock_entry(mapping, index); + page = pagecache_get_page(mapping, index, + FGP_ENTRY | FGP_HEAD | FGP_LOCK, 0); if (xa_is_value(page)) { error = shmem_swapin_page(inode, index, &page, sgp, gfp, vma, fault_type); @@ -1889,7 +1887,9 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, } alloc_huge: - page = shmem_alloc_and_acct_page(gfp, inode, index, true); + huge_gfp = vma_thp_gfp_mask(vma); + huge_gfp = limit_gfp_mask(huge_gfp, gfp); + page = shmem_alloc_and_acct_page(huge_gfp, inode, index, true); if (IS_ERR(page)) { alloc_nohuge: page = shmem_alloc_and_acct_page(gfp, inode, @@ -2676,86 +2676,20 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) return retval ? retval : error; } -/* - * llseek SEEK_DATA or SEEK_HOLE through the page cache. - */ -static pgoff_t shmem_seek_hole_data(struct address_space *mapping, - pgoff_t index, pgoff_t end, int whence) -{ - struct page *page; - struct pagevec pvec; - pgoff_t indices[PAGEVEC_SIZE]; - bool done = false; - int i; - - pagevec_init(&pvec); - pvec.nr = 1; /* start small: we may be there already */ - while (!done) { - pvec.nr = find_get_entries(mapping, index, - pvec.nr, pvec.pages, indices); - if (!pvec.nr) { - if (whence == SEEK_DATA) - index = end; - break; - } - for (i = 0; i < pvec.nr; i++, index++) { - if (index < indices[i]) { - if (whence == SEEK_HOLE) { - done = true; - break; - } - index = indices[i]; - } - page = pvec.pages[i]; - if (page && !xa_is_value(page)) { - if (!PageUptodate(page)) - page = NULL; - } - if (index >= end || - (page && whence == SEEK_DATA) || - (!page && whence == SEEK_HOLE)) { - done = true; - break; - } - } - pagevec_remove_exceptionals(&pvec); - pagevec_release(&pvec); - pvec.nr = PAGEVEC_SIZE; - cond_resched(); - } - return index; -} - static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) { struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - pgoff_t start, end; - loff_t new_offset; if (whence != SEEK_DATA && whence != SEEK_HOLE) return generic_file_llseek_size(file, offset, whence, MAX_LFS_FILESIZE, i_size_read(inode)); + if (offset < 0) + return -ENXIO; + inode_lock(inode); /* We're holding i_mutex so we can access i_size directly */ - - if (offset < 0 || offset >= inode->i_size) - offset = -ENXIO; - else { - start = offset >> PAGE_SHIFT; - end = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; - new_offset = shmem_seek_hole_data(mapping, start, end, whence); - new_offset <<= PAGE_SHIFT; - if (new_offset > offset) { - if (new_offset < inode->i_size) - offset = new_offset; - else if (whence == SEEK_DATA) - offset = -ENXIO; - else - offset = inode->i_size; - } - } - + offset = mapping_seek_hole_data(mapping, offset, inode->i_size, whence); if (offset >= 0) offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE); inode_unlock(inode); diff --git a/mm/slab.c b/mm/slab.c index 35c68d99d460..51fd424e0d6d 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -100,6 +100,7 @@ #include #include #include +#include #include #include #include @@ -3208,7 +3209,7 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, } static __always_inline void * -slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, +slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, size_t orig_size, unsigned long caller) { unsigned long save_flags; @@ -3221,6 +3222,10 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, if (unlikely(!cachep)) return NULL; + ptr = kfence_alloc(cachep, orig_size, flags); + if (unlikely(ptr)) + goto out_hooks; + cache_alloc_debugcheck_before(cachep, flags); local_irq_save(save_flags); @@ -3253,6 +3258,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, if (unlikely(slab_want_init_on_alloc(flags, cachep)) && ptr) memset(ptr, 0, cachep->object_size); +out_hooks: slab_post_alloc_hook(cachep, objcg, flags, 1, &ptr); return ptr; } @@ -3290,7 +3296,7 @@ __do_cache_alloc(struct kmem_cache *cachep, gfp_t flags) #endif /* CONFIG_NUMA */ static __always_inline void * -slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) +slab_alloc(struct kmem_cache *cachep, gfp_t flags, size_t orig_size, unsigned long caller) { unsigned long save_flags; void *objp; @@ -3301,6 +3307,10 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) if (unlikely(!cachep)) return NULL; + objp = kfence_alloc(cachep, orig_size, flags); + if (unlikely(objp)) + goto out; + cache_alloc_debugcheck_before(cachep, flags); local_irq_save(save_flags); objp = __do_cache_alloc(cachep, flags); @@ -3311,6 +3321,7 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) if (unlikely(slab_want_init_on_alloc(flags, cachep)) && objp) memset(objp, 0, cachep->object_size); +out: slab_post_alloc_hook(cachep, objcg, flags, 1, &objp); return objp; } @@ -3416,6 +3427,12 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac) static __always_inline void __cache_free(struct kmem_cache *cachep, void *objp, unsigned long caller) { + if (is_kfence_address(objp)) { + kmemleak_free_recursive(objp, cachep->flags); + __kfence_free(objp); + return; + } + if (unlikely(slab_want_init_on_free(cachep))) memset(objp, 0, cachep->object_size); @@ -3482,7 +3499,7 @@ void ___cache_free(struct kmem_cache *cachep, void *objp, */ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) { - void *ret = slab_alloc(cachep, flags, _RET_IP_); + void *ret = slab_alloc(cachep, flags, cachep->object_size, _RET_IP_); trace_kmem_cache_alloc(_RET_IP_, ret, cachep->object_size, cachep->size, flags); @@ -3515,7 +3532,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, local_irq_disable(); for (i = 0; i < size; i++) { - void *objp = __do_cache_alloc(s, flags); + void *objp = kfence_alloc(s, s->object_size, flags) ?: __do_cache_alloc(s, flags); if (unlikely(!objp)) goto error; @@ -3548,7 +3565,7 @@ kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size) { void *ret; - ret = slab_alloc(cachep, flags, _RET_IP_); + ret = slab_alloc(cachep, flags, size, _RET_IP_); ret = kasan_kmalloc(cachep, ret, size, flags); trace_kmalloc(_RET_IP_, ret, @@ -3574,7 +3591,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_trace); */ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) { - void *ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_); + void *ret = slab_alloc_node(cachep, flags, nodeid, cachep->object_size, _RET_IP_); trace_kmem_cache_alloc_node(_RET_IP_, ret, cachep->object_size, cachep->size, @@ -3592,7 +3609,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *cachep, { void *ret; - ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_); + ret = slab_alloc_node(cachep, flags, nodeid, size, _RET_IP_); ret = kasan_kmalloc(cachep, ret, size, flags); trace_kmalloc_node(_RET_IP_, ret, @@ -3673,7 +3690,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, cachep = kmalloc_slab(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; - ret = slab_alloc(cachep, flags, caller); + ret = slab_alloc(cachep, flags, size, caller); ret = kasan_kmalloc(cachep, ret, size, flags); trace_kmalloc(caller, ret, @@ -4172,7 +4189,10 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, BUG_ON(objnr >= cachep->num); /* Find offset within object. */ - offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep); + if (is_kfence_address(ptr)) + offset = ptr - kfence_object_start(ptr); + else + offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep); /* Allow address range falling entirely within usercopy region. */ if (offset >= cachep->useroffset && diff --git a/mm/slab_common.c b/mm/slab_common.c index 7c8298c17145..88e833986332 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -430,6 +431,7 @@ static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work) rcu_barrier(); list_for_each_entry_safe(s, s2, &to_destroy, list) { + kfence_shutdown_cache(s); #ifdef SLAB_SUPPORTS_SYSFS sysfs_slab_release(s); #else @@ -455,6 +457,7 @@ static int shutdown_cache(struct kmem_cache *s) list_add_tail(&s->list, &slab_caches_to_rcu_destroy); schedule_work(&slab_caches_to_rcu_destroy_work); } else { + kfence_shutdown_cache(s); #ifdef SLAB_SUPPORTS_SYSFS sysfs_slab_unlink(s); sysfs_slab_release(s); @@ -640,6 +643,7 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, panic("Out of memory when creating slab %s\n", name); create_boot_cache(s, name, size, flags, useroffset, usersize); + kasan_cache_create_kmalloc(s); list_add(&s->list, &slab_caches); s->refcount = 1; return s; @@ -1132,16 +1136,27 @@ static __always_inline void *__do_krealloc(const void *p, size_t new_size, void *ret; size_t ks; - ks = ksize(p); + /* Don't use instrumented ksize to allow precise KASAN poisoning. */ + if (likely(!ZERO_OR_NULL_PTR(p))) { + if (!kasan_check_byte(p)) + return NULL; + ks = kfence_ksize(p) ?: __ksize(p); + } else + ks = 0; + /* If the object still fits, repoison it precisely. */ if (ks >= new_size) { p = kasan_krealloc((void *)p, new_size, flags); return (void *)p; } ret = kmalloc_track_caller(new_size, flags); - if (ret && p) - memcpy(ret, p, ks); + if (ret && p) { + /* Disable KASAN checks as the object's redzone is accessed. */ + kasan_disable_current(); + memcpy(ret, kasan_reset_tag(p), ks); + kasan_enable_current(); + } return ret; } @@ -1235,7 +1250,7 @@ size_t ksize(const void *objp) if (unlikely(ZERO_OR_NULL_PTR(objp)) || !kasan_check_byte(objp)) return 0; - size = __ksize(objp); + size = kfence_ksize(objp) ?: __ksize(objp); /* * We assume that ksize callers could use whole allocated area, * so we need to unpoison this area. diff --git a/mm/slub.c b/mm/slub.c index b2833ce85c92..e26c274b4657 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -1570,6 +1571,11 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, void *old_tail = *tail ? *tail : *head; int rsize; + if (is_kfence_address(next)) { + slab_free_hook(s, next); + return true; + } + /* Head and tail of the reconstructed freelist */ *head = NULL; *tail = NULL; @@ -2809,7 +2815,7 @@ static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s, * Otherwise we can simply pick the next object from the lockless free list. */ static __always_inline void *slab_alloc_node(struct kmem_cache *s, - gfp_t gfpflags, int node, unsigned long addr) + gfp_t gfpflags, int node, unsigned long addr, size_t orig_size) { void *object; struct kmem_cache_cpu *c; @@ -2820,6 +2826,11 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s, s = slab_pre_alloc_hook(s, &objcg, 1, gfpflags); if (!s) return NULL; + + object = kfence_alloc(s, orig_size, gfpflags); + if (unlikely(object)) + goto out; + redo: /* * Must read kmem_cache cpu data via this cpu ptr. Preemption is @@ -2892,20 +2903,21 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s, if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object) memset(kasan_reset_tag(object), 0, s->object_size); +out: slab_post_alloc_hook(s, objcg, gfpflags, 1, &object); return object; } static __always_inline void *slab_alloc(struct kmem_cache *s, - gfp_t gfpflags, unsigned long addr) + gfp_t gfpflags, unsigned long addr, size_t orig_size) { - return slab_alloc_node(s, gfpflags, NUMA_NO_NODE, addr); + return slab_alloc_node(s, gfpflags, NUMA_NO_NODE, addr, orig_size); } void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) { - void *ret = slab_alloc(s, gfpflags, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, _RET_IP_, s->object_size); trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, s->size, gfpflags); @@ -2917,7 +2929,7 @@ EXPORT_SYMBOL(kmem_cache_alloc); #ifdef CONFIG_TRACING void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) { - void *ret = slab_alloc(s, gfpflags, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, _RET_IP_, size); trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags); ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; @@ -2928,7 +2940,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_trace); #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) { - void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_); + void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_, s->object_size); trace_kmem_cache_alloc_node(_RET_IP_, ret, s->object_size, s->size, gfpflags, node); @@ -2942,7 +2954,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { - void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_); + void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_, size); trace_kmalloc_node(_RET_IP_, ret, size, s->size, gfpflags, node); @@ -2976,6 +2988,9 @@ static void __slab_free(struct kmem_cache *s, struct page *page, stat(s, FREE_SLOWPATH); + if (kfence_free(head)) + return; + if (kmem_cache_debug(s) && !free_debug_processing(s, page, head, tail, cnt, addr)) return; @@ -3220,6 +3235,13 @@ int build_detached_freelist(struct kmem_cache *s, size_t size, df->s = cache_from_obj(s, object); /* Support for memcg */ } + if (is_kfence_address(object)) { + slab_free_hook(df->s, object); + __kfence_free(object); + p[size] = NULL; /* mark object processed */ + return size; + } + /* Start new detached freelist */ df->page = page; set_freepointer(df->s, object, NULL); @@ -3295,8 +3317,14 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, c = this_cpu_ptr(s->cpu_slab); for (i = 0; i < size; i++) { - void *object = c->freelist; + void *object = kfence_alloc(s, s->object_size, flags); + if (unlikely(object)) { + p[i] = object; + continue; + } + + object = c->freelist; if (unlikely(!object)) { /* * We may have removed an object from c->freelist using @@ -3551,8 +3579,7 @@ static void early_kmem_cache_node_alloc(int node) init_object(kmem_cache_node, n, SLUB_RED_ACTIVE); init_tracking(kmem_cache_node, n); #endif - n = kasan_kmalloc(kmem_cache_node, n, sizeof(struct kmem_cache_node), - GFP_KERNEL); + n = kasan_slab_alloc(kmem_cache_node, n, GFP_KERNEL); page->freelist = get_freepointer(kmem_cache_node, n); page->inuse = 1; page->frozen = 0; @@ -4021,7 +4048,7 @@ void *__kmalloc(size_t size, gfp_t flags) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc(s, flags, _RET_IP_); + ret = slab_alloc(s, flags, _RET_IP_, size); trace_kmalloc(_RET_IP_, ret, size, s->size, flags); @@ -4069,7 +4096,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc_node(s, flags, node, _RET_IP_); + ret = slab_alloc_node(s, flags, node, _RET_IP_, size); trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node); @@ -4095,6 +4122,7 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, struct kmem_cache *s; unsigned int offset; size_t object_size; + bool is_kfence = is_kfence_address(ptr); ptr = kasan_reset_tag(ptr); @@ -4107,10 +4135,13 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, to_user, 0, n); /* Find offset within object. */ - offset = (ptr - page_address(page)) % s->size; + if (is_kfence) + offset = ptr - kfence_object_start(ptr); + else + offset = (ptr - page_address(page)) % s->size; /* Adjust for redzone and reject if within the redzone. */ - if (kmem_cache_debug_flags(s, SLAB_RED_ZONE)) { + if (!is_kfence && kmem_cache_debug_flags(s, SLAB_RED_ZONE)) { if (offset < s->red_left_pad) usercopy_abort("SLUB object in left red zone", s->name, to_user, offset, n); @@ -4527,7 +4558,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc(s, gfpflags, caller); + ret = slab_alloc(s, gfpflags, caller, size); /* Honor the call site pointer we received. */ trace_kmalloc(caller, ret, size, s->size, gfpflags); @@ -4558,7 +4589,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc_node(s, gfpflags, node, caller); + ret = slab_alloc_node(s, gfpflags, node, caller, size); /* Honor the call site pointer we received. */ trace_kmalloc_node(caller, ret, size, s->size, gfpflags, node); diff --git a/mm/swap.c b/mm/swap.c index ab3258afcbeb..31b844d4ed94 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1017,46 +1017,12 @@ void __pagevec_lru_add(struct pagevec *pvec) pagevec_reinit(pvec); } -/** - * pagevec_lookup_entries - gang pagecache lookup - * @pvec: Where the resulting entries are placed - * @mapping: The address_space to search - * @start: The starting entry index - * @nr_entries: The maximum number of pages - * @indices: The cache indices corresponding to the entries in @pvec - * - * pagevec_lookup_entries() will search for and return a group of up - * to @nr_pages pages and shadow entries in the mapping. All - * entries are placed in @pvec. pagevec_lookup_entries() takes a - * reference against actual pages in @pvec. - * - * The search returns a group of mapping-contiguous entries with - * ascending indexes. There may be holes in the indices due to - * not-present entries. - * - * Only one subpage of a Transparent Huge Page is returned in one call: - * allowing truncate_inode_pages_range() to evict the whole THP without - * cycling through a pagevec of extra references. - * - * pagevec_lookup_entries() returns the number of entries which were - * found. - */ -unsigned pagevec_lookup_entries(struct pagevec *pvec, - struct address_space *mapping, - pgoff_t start, unsigned nr_entries, - pgoff_t *indices) -{ - pvec->nr = find_get_entries(mapping, start, nr_entries, - pvec->pages, indices); - return pagevec_count(pvec); -} - /** * pagevec_remove_exceptionals - pagevec exceptionals pruning * @pvec: The pagevec to prune * - * pagevec_lookup_entries() fills both pages and exceptional radix - * tree entries into the pagevec. This function prunes all + * find_get_entries() fills both pages and XArray value entries (aka + * exceptional entries) into the pagevec. This function prunes all * exceptionals from @pvec without leaving holes, so that it can be * passed on to page-only pagevec operations. */ diff --git a/mm/swap_state.c b/mm/swap_state.c index c1a648d9092b..3cdee7b11da9 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -87,11 +87,9 @@ void *get_shadow_from_swap_cache(swp_entry_t entry) pgoff_t idx = swp_offset(entry); struct page *page; - page = find_get_entry(address_space, idx); + page = xa_load(&address_space->i_pages, idx); if (xa_is_value(page)) return page; - if (page) - put_page(page); return NULL; } @@ -405,7 +403,8 @@ struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index) { swp_entry_t swp; struct swap_info_struct *si; - struct page *page = find_get_entry(mapping, index); + struct page *page = pagecache_get_page(mapping, index, + FGP_ENTRY | FGP_HEAD, 0); if (!page) return page; diff --git a/mm/truncate.c b/mm/truncate.c index 8aa4907e06e0..455944264663 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -57,11 +57,10 @@ static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, * exceptional entries similar to what pagevec_remove_exceptionals does. */ static void truncate_exceptional_pvec_entries(struct address_space *mapping, - struct pagevec *pvec, pgoff_t *indices, - pgoff_t end) + struct pagevec *pvec, pgoff_t *indices) { int i, j; - bool dax, lock; + bool dax; /* Handled by shmem itself */ if (shmem_mapping(mapping)) @@ -75,8 +74,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, return; dax = dax_mapping(mapping); - lock = !dax && indices[j] < end; - if (lock) + if (!dax) xa_lock_irq(&mapping->i_pages); for (i = j; i < pagevec_count(pvec); i++) { @@ -88,9 +86,6 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, continue; } - if (index >= end) - continue; - if (unlikely(dax)) { dax_delete_mapping_entry(mapping, index); continue; @@ -99,7 +94,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, __clear_shadow_entry(mapping, index, page); } - if (lock) + if (!dax) xa_unlock_irq(&mapping->i_pages); pvec->nr = j; } @@ -326,51 +321,19 @@ void truncate_inode_pages_range(struct address_space *mapping, pagevec_init(&pvec); index = start; - while (index < end && pagevec_lookup_entries(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), - indices)) { - /* - * Pagevec array has exceptional entries and we may also fail - * to lock some pages. So we store pages that can be deleted - * in a new pagevec. - */ - struct pagevec locked_pvec; - - pagevec_init(&locked_pvec); - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; - - /* We rely upon deletion not changing page->index */ - index = indices[i]; - if (index >= end) - break; - - if (xa_is_value(page)) - continue; - - if (!trylock_page(page)) - continue; - WARN_ON(page_to_index(page) != index); - if (PageWriteback(page)) { - unlock_page(page); - continue; - } - if (page->mapping != mapping) { - unlock_page(page); - continue; - } - pagevec_add(&locked_pvec, page); - } - for (i = 0; i < pagevec_count(&locked_pvec); i++) - truncate_cleanup_page(mapping, locked_pvec.pages[i]); - delete_from_page_cache_batch(mapping, &locked_pvec); - for (i = 0; i < pagevec_count(&locked_pvec); i++) - unlock_page(locked_pvec.pages[i]); - truncate_exceptional_pvec_entries(mapping, &pvec, indices, end); + while (index < end && find_lock_entries(mapping, index, end - 1, + &pvec, indices)) { + index = indices[pagevec_count(&pvec) - 1] + 1; + truncate_exceptional_pvec_entries(mapping, &pvec, indices); + for (i = 0; i < pagevec_count(&pvec); i++) + truncate_cleanup_page(mapping, pvec.pages[i]); + delete_from_page_cache_batch(mapping, &pvec); + for (i = 0; i < pagevec_count(&pvec); i++) + unlock_page(pvec.pages[i]); pagevec_release(&pvec); cond_resched(); - index++; } + if (partial_start) { struct page *page = find_lock_page(mapping, start - 1); if (page) { @@ -413,8 +376,8 @@ void truncate_inode_pages_range(struct address_space *mapping, index = start; for ( ; ; ) { cond_resched(); - if (!pagevec_lookup_entries(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) { + if (!find_get_entries(mapping, index, end - 1, &pvec, + indices)) { /* If all gone from start onwards, we're done */ if (index == start) break; @@ -422,23 +385,12 @@ void truncate_inode_pages_range(struct address_space *mapping, index = start; continue; } - if (index == start && indices[0] >= end) { - /* All gone out of hole to be punched, we're done */ - pagevec_remove_exceptionals(&pvec); - pagevec_release(&pvec); - break; - } for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; - if (index >= end) { - /* Restart punch to make sure all gone */ - index = start - 1; - break; - } if (xa_is_value(page)) continue; @@ -449,7 +401,7 @@ void truncate_inode_pages_range(struct address_space *mapping, truncate_inode_page(mapping, page); unlock_page(page); } - truncate_exceptional_pvec_entries(mapping, &pvec, indices, end); + truncate_exceptional_pvec_entries(mapping, &pvec, indices); pagevec_release(&pvec); index++; } @@ -539,55 +491,19 @@ static unsigned long __invalidate_mapping_pages(struct address_space *mapping, int i; pagevec_init(&pvec); - while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, - indices)) { + while (find_lock_entries(mapping, index, end, &pvec, indices)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; - if (index > end) - break; if (xa_is_value(page)) { invalidate_exceptional_entry(mapping, index, page); continue; } - - if (!trylock_page(page)) - continue; - - WARN_ON(page_to_index(page) != index); - - /* Middle of THP: skip */ - if (PageTransTail(page)) { - unlock_page(page); - continue; - } else if (PageTransHuge(page)) { - index += HPAGE_PMD_NR - 1; - i += HPAGE_PMD_NR - 1; - /* - * 'end' is in the middle of THP. Don't - * invalidate the page as the part outside of - * 'end' could be still useful. - */ - if (index > end) { - unlock_page(page); - continue; - } - - /* Take a pin outside pagevec */ - get_page(page); - - /* - * Drop extra pins before trying to invalidate - * the huge page. - */ - pagevec_remove_exceptionals(&pvec); - pagevec_release(&pvec); - } + index += thp_nr_pages(page) - 1; ret = invalidate_inode_page(page); unlock_page(page); @@ -601,9 +517,6 @@ static unsigned long __invalidate_mapping_pages(struct address_space *mapping, if (nr_pagevec) (*nr_pagevec)++; } - - if (PageTransHuge(page)) - put_page(page); count += ret; } pagevec_remove_exceptionals(&pvec); @@ -725,16 +638,12 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pagevec_init(&pvec); index = start; - while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, - indices)) { + while (find_get_entries(mapping, index, end, &pvec, indices)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; - if (index > end) - break; if (xa_is_value(page)) { if (!invalidate_exceptional_entry2(mapping, diff --git a/mm/vmstat.c b/mm/vmstat.c index 85a7809b0f0e..eed5c7ec1449 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -342,6 +342,12 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, long t; if (vmstat_item_in_bytes(item)) { + /* + * Only cgroups use subpage accounting right now; at + * the global level, these items still change in + * multiples of whole pages. Store them as pages + * internally to keep the per-cpu counters compact. + */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } @@ -551,6 +557,12 @@ static inline void mod_node_state(struct pglist_data *pgdat, long o, n, t, z; if (vmstat_item_in_bytes(item)) { + /* + * Only cgroups use subpage accounting right now; at + * the global level, these items still change in + * multiples of whole pages. Store them as pages + * internally to keep the per-cpu counters compact. + */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } @@ -1635,14 +1647,16 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n high %lu" "\n spanned %lu" "\n present %lu" - "\n managed %lu", + "\n managed %lu" + "\n cma %lu", zone_page_state(zone, NR_FREE_PAGES), min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), zone->spanned_pages, zone->present_pages, - zone_managed_pages(zone)); + zone_managed_pages(zone), + zone_cma_pages(zone)); seq_printf(m, "\n protection: (%ld", @@ -1890,16 +1904,12 @@ static void vmstat_update(struct work_struct *w) */ static bool need_update(int cpu) { + pg_data_t *last_pgdat = NULL; struct zone *zone; for_each_populated_zone(zone) { struct per_cpu_pageset *p = per_cpu_ptr(zone->pageset, cpu); - - BUILD_BUG_ON(sizeof(p->vm_stat_diff[0]) != 1); -#ifdef CONFIG_NUMA - BUILD_BUG_ON(sizeof(p->vm_numa_stat_diff[0]) != 2); -#endif - + struct per_cpu_nodestat *n; /* * The fast way of checking if there are any vmstat diffs. */ @@ -1911,6 +1921,13 @@ static bool need_update(int cpu) sizeof(p->vm_numa_stat_diff[0]))) return true; #endif + if (last_pgdat == zone->zone_pgdat) + continue; + last_pgdat = zone->zone_pgdat; + n = per_cpu_ptr(zone->zone_pgdat->per_cpu_nodestats, cpu); + if (memchr_inv(n->vm_node_stat_diff, 0, NR_VM_NODE_STAT_ITEMS * + sizeof(n->vm_node_stat_diff[0]))) + return true; } return false; } @@ -1961,6 +1978,8 @@ static void vmstat_shepherd(struct work_struct *w) if (!delayed_work_pending(dw) && need_update(cpu)) queue_delayed_work_on(cpu, mm_percpu_wq, dw, 0); + + cond_resched(); } put_online_cpus(); diff --git a/mm/z3fold.c b/mm/z3fold.c index c1ccf6bb0ffb..b5dafa7e44e4 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -1771,6 +1771,7 @@ static u64 z3fold_zpool_total_size(void *pool) static struct zpool_driver z3fold_zpool_driver = { .type = "z3fold", + .sleep_mapped = true, .owner = THIS_MODULE, .create = z3fold_zpool_create, .destroy = z3fold_zpool_destroy, diff --git a/mm/zbud.c b/mm/zbud.c index c49966ece674..7ec5f27a68b0 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -203,6 +203,7 @@ static u64 zbud_zpool_total_size(void *pool) static struct zpool_driver zbud_zpool_driver = { .type = "zbud", + .sleep_mapped = true, .owner = THIS_MODULE, .create = zbud_zpool_create, .destroy = zbud_zpool_destroy, diff --git a/mm/zpool.c b/mm/zpool.c index 3744a2d1a624..5ed71207ced7 100644 --- a/mm/zpool.c +++ b/mm/zpool.c @@ -23,6 +23,7 @@ struct zpool { void *pool; const struct zpool_ops *ops; bool evictable; + bool can_sleep_mapped; struct list_head list; }; @@ -183,6 +184,7 @@ struct zpool *zpool_create_pool(const char *type, const char *name, gfp_t gfp, zpool->pool = driver->create(name, gfp, ops, zpool); zpool->ops = ops; zpool->evictable = driver->shrink && ops && ops->evict; + zpool->can_sleep_mapped = driver->sleep_mapped; if (!zpool->pool) { pr_err("couldn't create %s pool\n", type); @@ -393,6 +395,17 @@ bool zpool_evictable(struct zpool *zpool) return zpool->evictable; } +/** + * zpool_can_sleep_mapped - Test if zpool can sleep when do mapped. + * @zpool: The zpool to test + * + * Returns: true if zpool can sleep; false otherwise. + */ +bool zpool_can_sleep_mapped(struct zpool *zpool) +{ + return zpool->can_sleep_mapped; +} + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Dan Streetman "); MODULE_DESCRIPTION("Common API for compressed memory storage"); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 7289f502ffac..30c358b72025 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -357,7 +357,7 @@ static void cache_free_handle(struct zs_pool *pool, unsigned long handle) static struct zspage *cache_alloc_zspage(struct zs_pool *pool, gfp_t flags) { - return kmem_cache_alloc(pool->zspage_cachep, + return kmem_cache_zalloc(pool->zspage_cachep, flags & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); } @@ -816,7 +816,7 @@ static int get_pages_per_zspage(int class_size) static struct zspage *get_zspage(struct page *page) { - struct zspage *zspage = (struct zspage *)page->private; + struct zspage *zspage = (struct zspage *)page_private(page); BUG_ON(zspage->magic != ZSPAGE_MAGIC); return zspage; @@ -1064,7 +1064,6 @@ static struct zspage *alloc_zspage(struct zs_pool *pool, if (!zspage) return NULL; - memset(zspage, 0, sizeof(struct zspage)); zspage->magic = ZSPAGE_MAGIC; migrate_lock_init(zspage); @@ -2213,11 +2212,13 @@ static unsigned long zs_can_compact(struct size_class *class) return obj_wasted * class->pages_per_zspage; } -static void __zs_compact(struct zs_pool *pool, struct size_class *class) +static unsigned long __zs_compact(struct zs_pool *pool, + struct size_class *class) { struct zs_compact_control cc; struct zspage *src_zspage; struct zspage *dst_zspage = NULL; + unsigned long pages_freed = 0; spin_lock(&class->lock); while ((src_zspage = isolate_zspage(class, true))) { @@ -2247,7 +2248,7 @@ static void __zs_compact(struct zs_pool *pool, struct size_class *class) putback_zspage(class, dst_zspage); if (putback_zspage(class, src_zspage) == ZS_EMPTY) { free_zspage(pool, class, src_zspage); - pool->stats.pages_compacted += class->pages_per_zspage; + pages_freed += class->pages_per_zspage; } spin_unlock(&class->lock); cond_resched(); @@ -2258,12 +2259,15 @@ static void __zs_compact(struct zs_pool *pool, struct size_class *class) putback_zspage(class, src_zspage); spin_unlock(&class->lock); + + return pages_freed; } unsigned long zs_compact(struct zs_pool *pool) { int i; struct size_class *class; + unsigned long pages_freed = 0; for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) { class = pool->size_class[i]; @@ -2271,10 +2275,11 @@ unsigned long zs_compact(struct zs_pool *pool) continue; if (class->index != i) continue; - __zs_compact(pool, class); + pages_freed += __zs_compact(pool, class); } + atomic_long_add(pages_freed, &pool->stats.pages_compacted); - return pool->stats.pages_compacted; + return pages_freed; } EXPORT_SYMBOL_GPL(zs_compact); @@ -2291,13 +2296,12 @@ static unsigned long zs_shrinker_scan(struct shrinker *shrinker, struct zs_pool *pool = container_of(shrinker, struct zs_pool, shrinker); - pages_freed = pool->stats.pages_compacted; /* * Compact classes and calculate compaction delta. * Can run concurrently with a manually triggered * (by user) compaction. */ - pages_freed = zs_compact(pool) - pages_freed; + pages_freed = zs_compact(pool); return pages_freed ? pages_freed : SHRINK_STOP; } diff --git a/mm/zswap.c b/mm/zswap.c index 182f6ad5aa69..578d9f256920 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -935,13 +935,19 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) struct scatterlist input, output; struct crypto_acomp_ctx *acomp_ctx; - u8 *src; + u8 *src, *tmp = NULL; unsigned int dlen; int ret; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, }; + if (!zpool_can_sleep_mapped(pool)) { + tmp = kmalloc(PAGE_SIZE, GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + } + /* extract swpentry from data */ zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO); swpentry = zhdr->swpentry; /* here */ @@ -955,6 +961,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) /* entry was invalidated */ spin_unlock(&tree->lock); zpool_unmap_handle(pool, handle); + kfree(tmp); return 0; } spin_unlock(&tree->lock); @@ -979,6 +986,14 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) dlen = PAGE_SIZE; src = (u8 *)zhdr + sizeof(struct zswap_header); + if (!zpool_can_sleep_mapped(pool)) { + + memcpy(tmp, src, entry->length); + src = tmp; + + zpool_unmap_handle(pool, handle); + } + mutex_lock(acomp_ctx->mutex); sg_init_one(&input, src, entry->length); sg_init_table(&output, 1); @@ -1022,10 +1037,10 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) /* * if we get here due to ZSWAP_SWAPCACHE_EXIST - * a load may happening concurrently - * it is safe and okay to not free the entry + * a load may be happening concurrently. + * it is safe and okay to not free the entry. * if we free the entry in the following put - * it it either okay to return !0 + * it is also okay to return !0 */ fail: spin_lock(&tree->lock); @@ -1033,7 +1048,11 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) spin_unlock(&tree->lock); end: - zpool_unmap_handle(pool, handle); + if (zpool_can_sleep_mapped(pool)) + zpool_unmap_handle(pool, handle); + else + kfree(tmp); + return ret; } @@ -1235,7 +1254,7 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, struct zswap_entry *entry; struct scatterlist input, output; struct crypto_acomp_ctx *acomp_ctx; - u8 *src, *dst; + u8 *src, *dst, *tmp; unsigned int dlen; int ret; @@ -1253,15 +1272,33 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, dst = kmap_atomic(page); zswap_fill_page(dst, entry->value); kunmap_atomic(dst); + ret = 0; goto freeentry; } + if (!zpool_can_sleep_mapped(entry->pool->zpool)) { + + tmp = kmalloc(entry->length, GFP_ATOMIC); + if (!tmp) { + ret = -ENOMEM; + goto freeentry; + } + } + /* decompress */ dlen = PAGE_SIZE; src = zpool_map_handle(entry->pool->zpool, entry->handle, ZPOOL_MM_RO); if (zpool_evictable(entry->pool->zpool)) src += sizeof(struct zswap_header); + if (!zpool_can_sleep_mapped(entry->pool->zpool)) { + + memcpy(tmp, src, entry->length); + src = tmp; + + zpool_unmap_handle(entry->pool->zpool, entry->handle); + } + acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); mutex_lock(acomp_ctx->mutex); sg_init_one(&input, src, entry->length); @@ -1271,7 +1308,11 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait); mutex_unlock(acomp_ctx->mutex); - zpool_unmap_handle(entry->pool->zpool, entry->handle); + if (zpool_can_sleep_mapped(entry->pool->zpool)) + zpool_unmap_handle(entry->pool->zpool, entry->handle); + else + kfree(tmp); + BUG_ON(ret); freeentry: @@ -1279,7 +1320,7 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, zswap_entry_put(tree, entry); spin_unlock(&tree->lock); - return 0; + return ret; } /* frees an entry in zswap */ diff --git a/net/can/af_can.c b/net/can/af_can.c index 837bb8af0ec3..cce2af10eb3e 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -304,8 +304,8 @@ static struct can_dev_rcv_lists *can_dev_rcv_lists_find(struct net *net, struct net_device *dev) { if (dev) { - struct can_ml_priv *ml_priv = dev->ml_priv; - return &ml_priv->dev_rcv_lists; + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + return &can_ml->dev_rcv_lists; } else { return net->can.rx_alldev_list; } @@ -790,25 +790,6 @@ void can_proto_unregister(const struct can_proto *cp) } EXPORT_SYMBOL(can_proto_unregister); -/* af_can notifier to create/remove CAN netdevice specific structs */ -static int can_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) -{ - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; - - switch (msg) { - case NETDEV_REGISTER: - WARN(!dev->ml_priv, - "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n"); - break; - } - - return NOTIFY_DONE; -} - static int can_pernet_init(struct net *net) { spin_lock_init(&net->can.rcvlists_lock); @@ -876,11 +857,6 @@ static const struct net_proto_family can_family_ops = { .owner = THIS_MODULE, }; -/* notifier block for netdevice event */ -static struct notifier_block can_netdev_notifier __read_mostly = { - .notifier_call = can_notifier, -}; - static struct pernet_operations can_pernet_ops __read_mostly = { .init = can_pernet_init, .exit = can_pernet_exit, @@ -911,17 +887,12 @@ static __init int can_init(void) err = sock_register(&can_family_ops); if (err) goto out_sock; - err = register_netdevice_notifier(&can_netdev_notifier); - if (err) - goto out_notifier; dev_add_pack(&can_packet); dev_add_pack(&canfd_packet); return 0; -out_notifier: - sock_unregister(PF_CAN); out_sock: unregister_pernet_subsys(&can_pernet_ops); out_pernet: @@ -935,7 +906,6 @@ static __exit void can_exit(void) /* protocol unregister */ dev_remove_pack(&canfd_packet); dev_remove_pack(&can_packet); - unregister_netdevice_notifier(&can_netdev_notifier); sock_unregister(PF_CAN); unregister_pernet_subsys(&can_pernet_ops); diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index bb914d8b4216..da3a7a7bcff2 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -140,9 +140,9 @@ static struct j1939_priv *j1939_priv_create(struct net_device *ndev) static inline void j1939_priv_set(struct net_device *ndev, struct j1939_priv *priv) { - struct can_ml_priv *can_ml_priv = ndev->ml_priv; + struct can_ml_priv *can_ml = can_get_ml_priv(ndev); - can_ml_priv->j1939_priv = priv; + can_ml->j1939_priv = priv; } static void __j1939_priv_release(struct kref *kref) @@ -211,12 +211,9 @@ static void __j1939_rx_release(struct kref *kref) /* get pointer to priv without increasing ref counter */ static inline struct j1939_priv *j1939_ndev_to_priv(struct net_device *ndev) { - struct can_ml_priv *can_ml_priv = ndev->ml_priv; + struct can_ml_priv *can_ml = can_get_ml_priv(ndev); - if (!can_ml_priv) - return NULL; - - return can_ml_priv->j1939_priv; + return can_ml->j1939_priv; } static struct j1939_priv *j1939_priv_get_by_ndev_locked(struct net_device *ndev) @@ -225,9 +222,6 @@ static struct j1939_priv *j1939_priv_get_by_ndev_locked(struct net_device *ndev) lockdep_assert_held(&j1939_netdev_lock); - if (ndev->type != ARPHRD_CAN) - return NULL; - priv = j1939_ndev_to_priv(ndev); if (priv) j1939_priv_get(priv); @@ -348,15 +342,16 @@ static int j1939_netdev_notify(struct notifier_block *nb, unsigned long msg, void *data) { struct net_device *ndev = netdev_notifier_info_to_dev(data); + struct can_ml_priv *can_ml = can_get_ml_priv(ndev); struct j1939_priv *priv; + if (!can_ml) + goto notify_done; + priv = j1939_priv_get_by_ndev(ndev); if (!priv) goto notify_done; - if (ndev->type != ARPHRD_CAN) - goto notify_put; - switch (msg) { case NETDEV_DOWN: j1939_cancel_active_session(priv, NULL); @@ -365,7 +360,6 @@ static int j1939_netdev_notify(struct notifier_block *nb, break; } -notify_put: j1939_priv_put(priv); notify_done: diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index f23966526a88..56aa66147d5a 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -453,6 +454,7 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) j1939_jsk_del(priv, jsk); j1939_local_ecu_put(priv, jsk->addr.src_name, jsk->addr.sa); } else { + struct can_ml_priv *can_ml; struct net_device *ndev; ndev = dev_get_by_index(net, addr->can_ifindex); @@ -461,15 +463,8 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out_release_sock; } - if (ndev->type != ARPHRD_CAN) { - dev_put(ndev); - ret = -ENODEV; - goto out_release_sock; - } - - if (!ndev->ml_priv) { - netdev_warn_once(ndev, - "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n"); + can_ml = can_get_ml_priv(ndev); + if (!can_ml) { dev_put(ndev); ret = -ENODEV; goto out_release_sock; diff --git a/net/can/proc.c b/net/can/proc.c index 5ea8695f507e..b15760b5c1cc 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -322,8 +322,11 @@ static int can_rcvlist_proc_show(struct seq_file *m, void *v) /* receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { - if (dev->type == ARPHRD_CAN && dev->ml_priv) - can_rcvlist_proc_show_one(m, idx, dev, dev->ml_priv); + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + + if (can_ml) + can_rcvlist_proc_show_one(m, idx, dev, + &can_ml->dev_rcv_lists); } rcu_read_unlock(); @@ -375,8 +378,10 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v) /* sff receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { - if (dev->type == ARPHRD_CAN && dev->ml_priv) { - dev_rcv_lists = dev->ml_priv; + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + + if (can_ml) { + dev_rcv_lists = &can_ml->dev_rcv_lists; can_rcvlist_proc_show_array(m, dev, dev_rcv_lists->rx_sff, ARRAY_SIZE(dev_rcv_lists->rx_sff)); } @@ -406,8 +411,10 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v) /* eff receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { - if (dev->type == ARPHRD_CAN && dev->ml_priv) { - dev_rcv_lists = dev->ml_priv; + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + + if (can_ml) { + dev_rcv_lists = &can_ml->dev_rcv_lists; can_rcvlist_proc_show_array(m, dev, dev_rcv_lists->rx_eff, ARRAY_SIZE(dev_rcv_lists->rx_eff)); } diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index a45572cfb71a..3589224c8da9 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -9,6 +9,7 @@ menuconfig NET_DSA tristate "Distributed Switch Architecture" depends on HAVE_NET_DSA depends on BRIDGE || BRIDGE=n + depends on HSR || HSR=n select GRO_CELLS select NET_SWITCHDEV select PHYLINK diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index f9a8cc82ae2e..bb1351c38397 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -164,8 +164,10 @@ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, * as initialization. (0 could trigger an spurious ring error warning). */ now = jiffies; - for (i = 0; i < HSR_PT_PORTS; i++) + for (i = 0; i < HSR_PT_PORTS; i++) { new_node->time_in[i] = now; + new_node->time_out[i] = now; + } for (i = 0; i < HSR_PT_PORTS; i++) new_node->seq_out[i] = seq_out; @@ -413,9 +415,12 @@ void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port, int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, u16 sequence_nr) { - if (seq_nr_before_or_eq(sequence_nr, node->seq_out[port->type])) + if (seq_nr_before_or_eq(sequence_nr, node->seq_out[port->type]) && + time_is_after_jiffies(node->time_out[port->type] + + msecs_to_jiffies(HSR_ENTRY_FORGET_TIME))) return 1; + node->time_out[port->type] = jiffies; node->seq_out[port->type] = sequence_nr; return 0; } diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 86b43f539f2c..d9628e7a5f05 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -75,6 +75,7 @@ struct hsr_node { enum hsr_port_type addr_B_port; unsigned long time_in[HSR_PT_PORTS]; bool time_in_stale[HSR_PT_PORTS]; + unsigned long time_out[HSR_PT_PORTS]; /* if the node is a SAN */ bool san_a; bool san_b; diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index a169808ee78a..8f264672b70b 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -22,6 +22,7 @@ #define HSR_LIFE_CHECK_INTERVAL 2000 /* ms */ #define HSR_NODE_FORGET_TIME 60000 /* ms */ #define HSR_ANNOUNCE_INTERVAL 100 /* ms */ +#define HSR_ENTRY_FORGET_TIME 400 /* ms */ /* By how much may slave1 and slave2 timestamps of latest received frame from * each node differ before we notify of communication problem? diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 396b492c804f..616e2dc1c8fa 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -775,13 +775,14 @@ EXPORT_SYMBOL(__icmp_send); void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct sk_buff *cloned_skb = NULL; + struct ip_options opts = { 0 }; enum ip_conntrack_info ctinfo; struct nf_conn *ct; __be32 orig_ip; ct = nf_ct_get(skb_in, &ctinfo); if (!ct || !(ct->status & IPS_SRC_NAT)) { - icmp_send(skb_in, type, code, info); + __icmp_send(skb_in, type, code, info, &opts); return; } @@ -796,7 +797,7 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) orig_ip = ip_hdr(skb_in)->saddr; ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip; - icmp_send(skb_in, type, code, info); + __icmp_send(skb_in, type, code, info, &opts); ip_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index f3d05866692e..fd1f896115c1 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -331,10 +331,9 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st } #if IS_ENABLED(CONFIG_IPV6_MIP6) -static void mip6_addr_swap(struct sk_buff *skb) +static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) { struct ipv6hdr *iph = ipv6_hdr(skb); - struct inet6_skb_parm *opt = IP6CB(skb); struct ipv6_destopt_hao *hao; struct in6_addr tmp; int off; @@ -351,7 +350,7 @@ static void mip6_addr_swap(struct sk_buff *skb) } } #else -static inline void mip6_addr_swap(struct sk_buff *skb) {} +static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {} #endif static struct dst_entry *icmpv6_route_lookup(struct net *net, @@ -446,7 +445,8 @@ static int icmp6_iif(const struct sk_buff *skb) * Send an ICMP message in response to a packet in error */ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr) + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm) { struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -542,7 +542,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type)) goto out_bh_enable; - mip6_addr_swap(skb); + mip6_addr_swap(skb, parm); sk = icmpv6_xmit_lock(net); if (!sk) @@ -559,7 +559,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, /* select a more meaningful saddr from input if */ struct net_device *in_netdev; - in_netdev = dev_get_by_index(net, IP6CB(skb)->iif); + in_netdev = dev_get_by_index(net, parm->iif); if (in_netdev) { ipv6_dev_get_saddr(net, in_netdev, &fl6.daddr, inet6_sk(sk)->srcprefs, @@ -640,7 +640,7 @@ EXPORT_SYMBOL(icmp6_send); */ void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { - icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL); + icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb)); kfree_skb(skb); } @@ -697,10 +697,10 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, } if (type == ICMP_TIME_EXCEEDED) icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); else icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); if (rt) ip6_rt_put(rt); diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c index 70c8c2f36c98..9e3574880cb0 100644 --- a/net/ipv6/ip6_icmp.c +++ b/net/ipv6/ip6_icmp.c @@ -33,23 +33,25 @@ int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) } EXPORT_SYMBOL(inet6_unregister_icmp_sender); -void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm) { ip6_icmp_send_t *send; rcu_read_lock(); send = rcu_dereference(ip6_icmp_send); if (send) - send(skb, type, code, info, NULL); + send(skb, type, code, info, NULL, parm); rcu_read_unlock(); } -EXPORT_SYMBOL(icmpv6_send); +EXPORT_SYMBOL(__icmpv6_send); #endif #if IS_ENABLED(CONFIG_NF_NAT) #include void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) { + struct inet6_skb_parm parm = { 0 }; struct sk_buff *cloned_skb = NULL; enum ip_conntrack_info ctinfo; struct in6_addr orig_ip; @@ -57,7 +59,7 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) ct = nf_ct_get(skb_in, &ctinfo); if (!ct || !(ct->status & IPS_SRC_NAT)) { - icmpv6_send(skb_in, type, code, info); + __icmpv6_send(skb_in, type, code, info, &parm); return; } @@ -72,7 +74,7 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) orig_ip = ipv6_hdr(skb_in)->saddr; ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6; - icmpv6_send(skb_in, type, code, info); + __icmpv6_send(skb_in, type, code, info, &parm); ipv6_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b63574d6b812..444a38681e93 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -411,6 +411,7 @@ static void clear_3rdack_retransmission(struct sock *sk) } static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, + bool snd_data_fin_enable, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) @@ -428,9 +429,10 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, if (!skb) return false; - /* MPC/MPJ needed only on 3rd ack packet */ - if (subflow->fully_established || - subflow->snd_isn != TCP_SKB_CB(skb)->seq) + /* MPC/MPJ needed only on 3rd ack packet, DATA_FIN and TCP shutdown take precedence */ + if (subflow->fully_established || snd_data_fin_enable || + subflow->snd_isn != TCP_SKB_CB(skb)->seq || + sk->sk_state != TCP_ESTABLISHED) return false; if (subflow->mp_capable) { @@ -502,20 +504,20 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, } static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, + bool snd_data_fin_enable, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - u64 snd_data_fin_enable, ack_seq; unsigned int dss_size = 0; struct mptcp_ext *mpext; unsigned int ack_size; bool ret = false; + u64 ack_seq; mpext = skb ? mptcp_get_ext(skb) : NULL; - snd_data_fin_enable = mptcp_data_fin_enabled(msk); if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) { unsigned int map_size; @@ -717,12 +719,15 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); unsigned int opt_size = 0; + bool snd_data_fin; bool ret = false; opts->suboptions = 0; - if (unlikely(mptcp_check_fallback(sk))) + if (unlikely(__mptcp_check_fallback(msk))) return false; /* prevent adding of any MPTCP related options on reset packet @@ -731,10 +736,10 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) return false; - if (mptcp_established_options_mp(sk, skb, &opt_size, remaining, opts)) + snd_data_fin = mptcp_data_fin_enabled(msk); + if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, remaining, opts)) ret = true; - else if (mptcp_established_options_dss(sk, skb, &opt_size, remaining, - opts)) + else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts)) ret = true; /* we reserved enough space for the above options, and exceeding the diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a57f3eab7b6a..c5d5e68940ea 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -19,6 +20,7 @@ #include #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include +#include #endif #include #include @@ -2264,13 +2266,12 @@ static void mptcp_worker(struct work_struct *work) __mptcp_check_send_data_fin(sk); mptcp_check_data_fin(sk); - /* if the msk data is completely acked, or the socket timedout, - * there is no point in keeping around an orphaned sk + /* There is no point in keeping around an orphaned sk timedout or + * closed, but we need the msk around to reply to incoming DATA_FIN, + * even if it is orphaned and in FIN_WAIT2 state */ if (sock_flag(sk, SOCK_DEAD) && - (mptcp_check_close_timeout(sk) || - (state != sk->sk_state && - ((1 << inet_sk_state_load(sk)) & (TCPF_CLOSE | TCPF_FIN_WAIT2))))) { + (mptcp_check_close_timeout(sk) || sk->sk_state == TCP_CLOSE)) { inet_sk_state_store(sk, TCP_CLOSE); __mptcp_destroy_sock(sk); goto unlock; @@ -3375,10 +3376,34 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, return mask; } +static int mptcp_release(struct socket *sock) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = sock->sk; + struct mptcp_sock *msk; + + if (!sk) + return 0; + + lock_sock(sk); + + msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ip_mc_drop_socket(ssk); + } + + release_sock(sk); + + return inet_release(sock); +} + static const struct proto_ops mptcp_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, - .release = inet_release, + .release = mptcp_release, .bind = mptcp_bind, .connect = mptcp_stream_connect, .socketpair = sock_no_socketpair, @@ -3470,10 +3495,35 @@ void __init mptcp_proto_init(void) } #if IS_ENABLED(CONFIG_MPTCP_IPV6) +static int mptcp6_release(struct socket *sock) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk; + struct sock *sk = sock->sk; + + if (!sk) + return 0; + + lock_sock(sk); + + msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ip_mc_drop_socket(ssk); + ipv6_sock_mc_close(ssk); + ipv6_sock_ac_close(ssk); + } + + release_sock(sk); + return inet6_release(sock); +} + static const struct proto_ops mptcp_v6_stream_ops = { .family = PF_INET6, .owner = THIS_MODULE, - .release = inet6_release, + .release = mptcp6_release, .bind = mptcp_bind, .connect = mptcp_stream_connect, .socketpair = sock_no_socketpair, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 06e233410e0e..e1fbcab257e6 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1096,6 +1096,12 @@ static void subflow_data_ready(struct sock *sk) msk = mptcp_sk(parent); if (state & TCPF_LISTEN) { + /* MPJ subflow are removed from accept queue before reaching here, + * avoid stray wakeups + */ + if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) + return; + set_bit(MPTCP_DATA_READY, &msk->flags); parent->sk_data_ready(parent); return; diff --git a/net/psample/psample.c b/net/psample/psample.c index 33e238c965bd..482c07f2766b 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -309,10 +309,10 @@ static int psample_tunnel_meta_len(struct ip_tunnel_info *tun_info) unsigned short tun_proto = ip_tunnel_info_af(tun_info); const struct ip_tunnel_key *tun_key = &tun_info->key; int tun_opts_len = tun_info->options_len; - int sum = 0; + int sum = nla_total_size(0); /* PSAMPLE_ATTR_TUNNEL */ if (tun_key->tun_flags & TUNNEL_KEY) - sum += nla_total_size(sizeof(u64)); + sum += nla_total_size_64bit(sizeof(u64)); if (tun_info->mode & IP_TUNNEL_INFO_BRIDGE) sum += nla_total_size(0); diff --git a/net/qrtr/tun.c b/net/qrtr/tun.c index b238c40a9984..304b41fea5ab 100644 --- a/net/qrtr/tun.c +++ b/net/qrtr/tun.c @@ -31,6 +31,7 @@ static int qrtr_tun_send(struct qrtr_endpoint *ep, struct sk_buff *skb) static int qrtr_tun_open(struct inode *inode, struct file *filp) { struct qrtr_tun *tun; + int ret; tun = kzalloc(sizeof(*tun), GFP_KERNEL); if (!tun) @@ -43,7 +44,16 @@ static int qrtr_tun_open(struct inode *inode, struct file *filp) filp->private_data = tun; - return qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO); + ret = qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO); + if (ret) + goto out; + + return 0; + +out: + filp->private_data = NULL; + kfree(tun); + return ret; } static ssize_t qrtr_tun_read_iter(struct kiocb *iocb, struct iov_iter *to) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 2409e522c68f..d097b5c15faa 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1417,6 +1417,21 @@ static int fl_validate_ct_state(u16 state, struct nlattr *tb, return -EINVAL; } + if (state & TCA_FLOWER_KEY_CT_FLAGS_INVALID && + state & ~(TCA_FLOWER_KEY_CT_FLAGS_TRACKED | + TCA_FLOWER_KEY_CT_FLAGS_INVALID)) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "when inv is set, only trk may be set"); + return -EINVAL; + } + + if (state & TCA_FLOWER_KEY_CT_FLAGS_NEW && + state & TCA_FLOWER_KEY_CT_FLAGS_REPLY) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "new and rpl are mutually exclusive"); + return -EINVAL; + } + return 0; } diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 8241f5a4a01c..09c000d490a1 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -478,6 +478,7 @@ rpc_get_inode(struct super_block *sb, umode_t mode) inode->i_fop = &simple_dir_operations; inode->i_op = &simple_dir_inode_operations; inc_nlink(inode); + break; default: break; } diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 946edf2db646..a249837d6a55 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -2,7 +2,7 @@ /* * Copyright (c) 2015-2020, Oracle and/or its affiliates. * - * Support for backward direction RPCs on RPC/RDMA. + * Support for reverse-direction RPCs on RPC/RDMA. */ #include @@ -208,7 +208,7 @@ static struct rpc_rqst *rpcrdma_bc_rqst_get(struct rpcrdma_xprt *r_xprt) } /** - * rpcrdma_bc_receive_call - Handle a backward direction call + * rpcrdma_bc_receive_call - Handle a reverse-direction Call * @r_xprt: transport receiving the call * @rep: receive buffer containing the call * diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index baca49fe83af..766a1048a48a 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -306,20 +306,14 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, if (nsegs > ep->re_max_fr_depth) nsegs = ep->re_max_fr_depth; for (i = 0; i < nsegs;) { - if (seg->mr_page) - sg_set_page(&mr->mr_sg[i], - seg->mr_page, - seg->mr_len, - offset_in_page(seg->mr_offset)); - else - sg_set_buf(&mr->mr_sg[i], seg->mr_offset, - seg->mr_len); + sg_set_page(&mr->mr_sg[i], seg->mr_page, + seg->mr_len, seg->mr_offset); ++seg; ++i; if (ep->re_mrtype == IB_MR_TYPE_SG_GAPS) continue; - if ((i < nsegs && offset_in_page(seg->mr_offset)) || + if ((i < nsegs && seg->mr_offset) || offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) break; } diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 8f5d0cb68360..292f066d006e 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -204,9 +204,7 @@ rpcrdma_alloc_sparse_pages(struct xdr_buf *buf) return 0; } -/* Split @vec on page boundaries into SGEs. FMR registers pages, not - * a byte range. Other modes coalesce these SGEs into a single MR - * when they can. +/* Convert @vec to a single SGL element. * * Returns pointer to next available SGE, and bumps the total number * of SGEs consumed. @@ -215,22 +213,11 @@ static struct rpcrdma_mr_seg * rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, unsigned int *n) { - u32 remaining, page_offset; - char *base; - - base = vec->iov_base; - page_offset = offset_in_page(base); - remaining = vec->iov_len; - while (remaining) { - seg->mr_page = NULL; - seg->mr_offset = base; - seg->mr_len = min_t(u32, PAGE_SIZE - page_offset, remaining); - remaining -= seg->mr_len; - base += seg->mr_len; - ++seg; - ++(*n); - page_offset = 0; - } + seg->mr_page = virt_to_page(vec->iov_base); + seg->mr_offset = offset_in_page(vec->iov_base); + seg->mr_len = vec->iov_len; + ++seg; + ++(*n); return seg; } @@ -259,7 +246,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, page_base = offset_in_page(xdrbuf->page_base); while (len) { seg->mr_page = *ppages; - seg->mr_offset = (char *)page_base; + seg->mr_offset = page_base; seg->mr_len = min_t(u32, PAGE_SIZE - page_base, len); len -= seg->mr_len; ++ppages; @@ -268,10 +255,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, page_base = 0; } - /* When encoding a Read chunk, the tail iovec contains an - * XDR pad and may be omitted. - */ - if (type == rpcrdma_readch && r_xprt->rx_ep->re_implicit_roundup) + if (type == rpcrdma_readch) goto out; /* When encoding a Write chunk, some servers need to see an @@ -283,7 +267,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, goto out; if (xdrbuf->tail[0].iov_len) - seg = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, &n); + rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, &n); out: if (unlikely(n > RPCRDMA_MAX_SEGS)) @@ -644,9 +628,8 @@ static bool rpcrdma_prepare_pagelist(struct rpcrdma_req *req, return false; } -/* The tail iovec may include an XDR pad for the page list, - * as well as additional content, and may not reside in the - * same page as the head iovec. +/* The tail iovec might not reside in the same page as the + * head iovec. */ static bool rpcrdma_prepare_tail_iov(struct rpcrdma_req *req, struct xdr_buf *xdr, @@ -764,27 +747,19 @@ static bool rpcrdma_prepare_readch(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, struct xdr_buf *xdr) { + struct kvec *tail = &xdr->tail[0]; + if (!rpcrdma_prepare_head_iov(r_xprt, req, xdr->head[0].iov_len)) return false; - /* If there is a Read chunk, the page list is being handled + /* If there is a Read chunk, the page list is handled * via explicit RDMA, and thus is skipped here. */ - /* Do not include the tail if it is only an XDR pad */ - if (xdr->tail[0].iov_len > 3) { - unsigned int page_base, len; - - /* If the content in the page list is an odd length, - * xdr_write_pages() adds a pad at the beginning of - * the tail iovec. Force the tail's non-pad content to - * land at the next XDR position in the Send message. - */ - page_base = offset_in_page(xdr->tail[0].iov_base); - len = xdr->tail[0].iov_len; - page_base += len & 3; - len -= len & 3; - if (!rpcrdma_prepare_tail_iov(req, xdr, page_base, len)) + if (tail->iov_len) { + if (!rpcrdma_prepare_tail_iov(req, xdr, + offset_in_page(tail->iov_base), + tail->iov_len)) return false; kref_get(&req->rl_kref); } @@ -1164,14 +1139,10 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep) */ p = xdr_inline_decode(xdr, 3 * sizeof(*p)); if (unlikely(!p)) - goto out_short; + return true; rpcrdma_bc_receive_call(r_xprt, rep); return true; - -out_short: - pr_warn("RPC/RDMA short backward direction call\n"); - return true; } #else /* CONFIG_SUNRPC_BACKCHANNEL */ { diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index 63f8be974df2..4a1edbb4028e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -2,7 +2,7 @@ /* * Copyright (c) 2015-2018 Oracle. All rights reserved. * - * Support for backward direction RPCs on RPC/RDMA (server-side). + * Support for reverse-direction RPCs on RPC/RDMA (server-side). */ #include @@ -59,7 +59,7 @@ void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp, spin_unlock(&xprt->queue_lock); } -/* Send a backwards direction RPC call. +/* Send a reverse-direction RPC Call. * * Caller holds the connection's mutex and has already marshaled * the RPC/RDMA request. diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 94b28657aeeb..fe3be985e239 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -98,9 +98,9 @@ struct rpcrdma_ep { atomic_t re_completion_ids; }; -/* Pre-allocate extra Work Requests for handling backward receives - * and sends. This is a fixed value because the Work Queues are - * allocated when the forward channel is set up, long before the +/* Pre-allocate extra Work Requests for handling reverse-direction + * Receives and Sends. This is a fixed value because the Work Queues + * are allocated when the forward channel is set up, long before the * backchannel is provisioned. This value is two times * NFS4_DEF_CB_SLOT_TABLE_SIZE. */ @@ -283,10 +283,11 @@ enum { RPCRDMA_MAX_IOV_SEGS, }; -struct rpcrdma_mr_seg { /* chunk descriptors */ - u32 mr_len; /* length of chunk or segment */ - struct page *mr_page; /* owning page, if any */ - char *mr_offset; /* kva if no page, else offset */ +/* Arguments for DMA mapping and registration */ +struct rpcrdma_mr_seg { + u32 mr_len; /* length of segment */ + struct page *mr_page; /* underlying struct page */ + u64 mr_offset; /* IN: page offset, OUT: iova */ }; /* The Send SGE array is provisioned to send a maximum size diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c56a66cdf4ac..e35760f238a4 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -829,7 +829,7 @@ xs_stream_record_marker(struct xdr_buf *xdr) * EAGAIN: The socket was blocked, please call again later to * complete the request * ENOTCONN: Caller needs to invoke connect logic then call again - * other: Some other error occured, the request was not sent + * other: Some other error occurred, the request was not sent */ static int xs_local_send_request(struct rpc_rqst *req) { @@ -1665,7 +1665,7 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock) * This ensures that we can continue to establish TCP * connections even when all local ephemeral ports are already * a part of some TCP connection. This makes no difference - * for UDP sockets, but also doens't harm them. + * for UDP sockets, but also doesn't harm them. * * If we're asking for any reserved port (i.e. port == 0 && * transport->xprt.resvport == 1) xs_get_srcport above will @@ -1875,6 +1875,7 @@ static int xs_local_setup_socket(struct sock_xprt *transport) xprt->stat.connect_time += (long)jiffies - xprt->stat.connect_start; xprt_set_connected(xprt); + break; case -ENOBUFS: break; case -ENOENT: @@ -2276,10 +2277,8 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EHOSTUNREACH: case -EADDRINUSE: case -ENOBUFS: - /* - * xs_tcp_force_close() wakes tasks with -EIO. - * We need to wake them first to ensure the - * correct error code. + /* xs_tcp_force_close() wakes tasks with a fixed error code. + * We need to wake them first to ensure the correct error code. */ xprt_wake_pending_tasks(xprt, status); xs_tcp_force_close(xprt); @@ -2380,7 +2379,7 @@ static void xs_error_handle(struct work_struct *work) } /** - * xs_local_print_stats - display AF_LOCAL socket-specifc stats + * xs_local_print_stats - display AF_LOCAL socket-specific stats * @xprt: rpc_xprt struct containing statistics * @seq: output file * @@ -2409,7 +2408,7 @@ static void xs_local_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) } /** - * xs_udp_print_stats - display UDP socket-specifc stats + * xs_udp_print_stats - display UDP socket-specific stats * @xprt: rpc_xprt struct containing statistics * @seq: output file * @@ -2433,7 +2432,7 @@ static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) } /** - * xs_tcp_print_stats - display TCP socket-specifc stats + * xs_tcp_print_stats - display TCP socket-specific stats * @xprt: rpc_xprt struct containing statistics * @seq: output file * diff --git a/samples/auxdisplay/cfag12864b-example.c b/samples/auxdisplay/cfag12864b-example.c index bfeab44f81d0..2e3bb7375c99 100644 --- a/samples/auxdisplay/cfag12864b-example.c +++ b/samples/auxdisplay/cfag12864b-example.c @@ -4,7 +4,7 @@ * Version: 0.1.0 * Description: cfag12864b LCD userspace example program * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-31 */ diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index 08e011175b4c..509e0856d653 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -141,13 +141,9 @@ cc-ifversion = $(shell [ $(CONFIG_GCC_VERSION)0 $(1) $(2)000 ] && echo $(3) || e # Usage: KBUILD_LDFLAGS += $(call ld-option, -X, -Y) ld-option = $(call try-run, $(LD) $(KBUILD_LDFLAGS) $(1) -v,$(1),$(2),$(3)) -# ld-version -# Note this is mainly for HJ Lu's 3 number binutil versions -ld-version = $(shell $(LD) --version | $(srctree)/scripts/ld-version.sh) - # ld-ifversion # Usage: $(call ld-ifversion, -ge, 22252, y) -ld-ifversion = $(shell [ $(ld-version) $(1) $(2) ] && echo $(3) || echo $(4)) +ld-ifversion = $(shell [ $(CONFIG_LD_VERSION)0 $(1) $(2)0 ] && echo $(3) || echo $(4)) ###### diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include index a5fe72c504ff..58fdb5308725 100644 --- a/scripts/Kconfig.include +++ b/scripts/Kconfig.include @@ -39,8 +39,17 @@ as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -c -x assembler $(error-if,$(failure,command -v $(CC)),compiler '$(CC)' not found) $(error-if,$(failure,command -v $(LD)),linker '$(LD)' not found) -# Fail if the linker is gold as it's not capable of linking the kernel proper -$(error-if,$(success, $(LD) -v | grep -q gold), gold linker '$(LD)' not supported) +# Get the compiler name, version, and error out if it is not supported. +cc-info := $(shell,$(srctree)/scripts/cc-version.sh $(CC)) +$(error-if,$(success,test -z "$(cc-info)"),Sorry$(comma) this compiler is not supported.) +cc-name := $(shell,set -- $(cc-info) && echo $1) +cc-version := $(shell,set -- $(cc-info) && echo $2) + +# Get the linker name, version, and error out if it is not supported. +ld-info := $(shell,$(srctree)/scripts/ld-version.sh $(LD)) +$(error-if,$(success,test -z "$(ld-info)"),Sorry$(comma) this linker is not supported.) +ld-name := $(shell,set -- $(ld-info) && echo $1) +ld-version := $(shell,set -- $(ld-info) && echo $2) # machine bit flags # $(m32-flag): -m32 if the compiler supports it, or an empty string otherwise. diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 3f6bf0ea7c0e..1b6094a13034 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -15,7 +15,6 @@ obj-y := obj-m := lib-y := lib-m := -always := always-y := always-m := targets := diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean index d9e0ceace6a6..22a8172bce1f 100644 --- a/scripts/Makefile.clean +++ b/scripts/Makefile.clean @@ -34,9 +34,6 @@ __clean-files := \ $(hostprogs-always-y) $(hostprogs-always-m) $(hostprogs-always-) \ $(userprogs-always-y) $(userprogs-always-m) $(userprogs-always-) -# deprecated -__clean-files += $(always) $(hostprogs-y) $(hostprogs-m) $(hostprogs-) - __clean-files := $(filter-out $(no-clean-files), $(__clean-files)) # clean-files is given relative to the current directory, unless it diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 29e8a816d9ab..bf98014a8fad 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -4,18 +4,6 @@ asflags-y += $(EXTRA_AFLAGS) ccflags-y += $(EXTRA_CFLAGS) cppflags-y += $(EXTRA_CPPFLAGS) ldflags-y += $(EXTRA_LDFLAGS) -ifneq ($(always),) -$(warning 'always' is deprecated. Please use 'always-y' instead) -always-y += $(always) -endif -ifneq ($(hostprogs-y),) -$(warning 'hostprogs-y' is deprecated. Please use 'hostprogs' instead) -hostprogs += $(hostprogs-y) -endif -ifneq ($(hostprogs-m),) -$(warning 'hostprogs-m' is deprecated. Please use 'hostprogs' instead) -hostprogs += $(hostprogs-m) -endif # flags that take effect in current and sub directories KBUILD_AFLAGS += $(subdir-asflags-y) @@ -56,15 +44,19 @@ else obj-y := $(filter-out %/, $(obj-y)) endif +# Expand $(foo-objs) $(foo-y) by calling $(call suffix-search,foo.o,-objs -y) +suffix-search = $(foreach s,$(2),$($(1:.o=$s))) # If $(foo-objs), $(foo-y), $(foo-m), or $(foo-) exists, foo.o is a composite object -multi-used-y := $(sort $(foreach m,$(obj-y), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y)) $($(m:.o=-))), $(m)))) -multi-used-m := $(sort $(foreach m,$(obj-m), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y)) $($(m:.o=-m)) $($(m:.o=-))), $(m)))) +multi-search = $(sort $(foreach m,$(1), $(if $(strip $(call suffix-search,$(m),$(2) -)), $(m)))) +multi-used-y := $(call multi-search,$(obj-y),-objs -y) +multi-used-m := $(call multi-search,$(obj-m),-objs -y -m) multi-used := $(multi-used-y) $(multi-used-m) # Replace multi-part objects by their individual parts, # including built-in.a from subdirectories -real-obj-y := $(foreach m, $(obj-y), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y)) $($(m:.o=-))),$($(m:.o=-objs)) $($(m:.o=-y)),$(m))) -real-obj-m := $(foreach m, $(obj-m), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y)) $($(m:.o=-m)) $($(m:.o=-))),$($(m:.o=-objs)) $($(m:.o=-y)) $($(m:.o=-m)),$(m))) +real-search = $(foreach m,$(1), $(if $(strip $(call suffix-search,$(m),$(2) -)),$(call suffix-search,$(m),$(2)),$(m))) +real-obj-y := $(call real-search, $(obj-y),-objs -y) +real-obj-m := $(call real-search, $(obj-m),-objs -y -m) always-y += $(always-m) @@ -81,14 +73,14 @@ always-y += $(userprogs-always-y) $(userprogs-always-m) # DTB # If CONFIG_OF_ALL_DTBS is enabled, all DT blobs are built -extra-y += $(dtb-y) -extra-$(CONFIG_OF_ALL_DTBS) += $(dtb-) +always-y += $(dtb-y) +always-$(CONFIG_OF_ALL_DTBS) += $(dtb-) ifneq ($(CHECK_DTBS),) -extra-y += $(patsubst %.dtb,%.dt.yaml, $(dtb-y)) -extra-y += $(patsubst %.dtbo,%.dt.yaml, $(dtb-y)) -extra-$(CONFIG_OF_ALL_DTBS) += $(patsubst %.dtb,%.dt.yaml, $(dtb-)) -extra-$(CONFIG_OF_ALL_DTBS) += $(patsubst %.dtbo,%.dt.yaml, $(dtb-)) +always-y += $(patsubst %.dtb,%.dt.yaml, $(dtb-y)) +always-y += $(patsubst %.dtbo,%.dt.yaml, $(dtb-y)) +always-$(CONFIG_OF_ALL_DTBS) += $(patsubst %.dtb,%.dt.yaml, $(dtb-)) +always-$(CONFIG_OF_ALL_DTBS) += $(patsubst %.dtbo,%.dt.yaml, $(dtb-)) endif # Add subdir path @@ -263,7 +255,7 @@ $(obj)/%: $(src)/%_shipped # target: source(s) FORCE # $(if_changed,ld/objcopy/gzip) # -# and add target to extra-y so that we know we have to +# and add target to 'targets' so that we know we have to # read in the saved command line # Linking diff --git a/scripts/Makefile.ubsan b/scripts/Makefile.ubsan index 0e53a93e8f15..9e2092fd5206 100644 --- a/scripts/Makefile.ubsan +++ b/scripts/Makefile.ubsan @@ -8,8 +8,6 @@ ubsan-cflags-$(CONFIG_UBSAN_LOCAL_BOUNDS) += -fsanitize=local-bounds ubsan-cflags-$(CONFIG_UBSAN_SHIFT) += -fsanitize=shift ubsan-cflags-$(CONFIG_UBSAN_DIV_ZERO) += -fsanitize=integer-divide-by-zero ubsan-cflags-$(CONFIG_UBSAN_UNREACHABLE) += -fsanitize=unreachable -ubsan-cflags-$(CONFIG_UBSAN_SIGNED_OVERFLOW) += -fsanitize=signed-integer-overflow -ubsan-cflags-$(CONFIG_UBSAN_UNSIGNED_OVERFLOW) += -fsanitize=unsigned-integer-overflow ubsan-cflags-$(CONFIG_UBSAN_OBJECT_SIZE) += -fsanitize=object-size ubsan-cflags-$(CONFIG_UBSAN_BOOL) += -fsanitize=bool ubsan-cflags-$(CONFIG_UBSAN_ENUM) += -fsanitize=enum diff --git a/scripts/cc-version.sh b/scripts/cc-version.sh new file mode 100755 index 000000000000..3f2ee885b116 --- /dev/null +++ b/scripts/cc-version.sh @@ -0,0 +1,82 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Print the compiler name and its version in a 5 or 6-digit form. +# Also, perform the minimum version check. + +set -e + +# When you raise the minimum compiler version, please update +# Documentation/process/changes.rst as well. +gcc_min_version=4.9.0 +clang_min_version=10.0.1 +icc_min_version=16.0.3 # temporary + +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63293 +# https://lore.kernel.org/r/20210107111841.GN1551@shell.armlinux.org.uk +if [ "$SRCARCH" = arm64 ]; then + gcc_min_version=5.1.0 +fi + +# Print the compiler name and some version components. +get_compiler_info() +{ + cat <<- EOF | "$@" -E -P -x c - 2>/dev/null + #if defined(__clang__) + Clang __clang_major__ __clang_minor__ __clang_patchlevel__ + #elif defined(__INTEL_COMPILER) + ICC __INTEL_COMPILER __INTEL_COMPILER_UPDATE + #elif defined(__GNUC__) + GCC __GNUC__ __GNUC_MINOR__ __GNUC_PATCHLEVEL__ + #else + unknown + #endif + EOF +} + +# Convert the version string x.y.z to a canonical 5 or 6-digit form. +get_canonical_version() +{ + IFS=. + set -- $1 + echo $((10000 * $1 + 100 * $2 + $3)) +} + +# $@ instead of $1 because multiple words might be given, e.g. CC="ccache gcc". +orig_args="$@" +set -- $(get_compiler_info "$@") + +name=$1 + +case "$name" in +GCC) + version=$2.$3.$4 + min_version=$gcc_min_version + ;; +Clang) + version=$2.$3.$4 + min_version=$clang_min_version + ;; +ICC) + version=$(($2 / 100)).$(($2 % 100)).$3 + min_version=$icc_min_version + ;; +*) + echo "$orig_args: unknown compiler" >&2 + exit 1 + ;; +esac + +cversion=$(get_canonical_version $version) +min_cversion=$(get_canonical_version $min_version) + +if [ "$cversion" -lt "$min_cversion" ]; then + echo >&2 "***" + echo >&2 "*** Compiler is too old." + echo >&2 "*** Your $name version: $version" + echo >&2 "*** Minimum $name version: $min_version" + echo >&2 "***" + exit 1 +fi + +echo $name $cversion diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index ca4201753d5e..df8b23dc1eb0 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -382,6 +382,7 @@ our $InitAttribute = qr{$InitAttributeData|$InitAttributeConst|$InitAttributeIni # We need \b after 'init' otherwise 'initconst' will cause a false positive in a check our $Attribute = qr{ const| + volatile| __percpu| __nocast| __safe| @@ -486,7 +487,7 @@ our $logFunctions = qr{(?x: our $allocFunctions = qr{(?x: (?:(?:devm_)? - (?:kv|k|v)[czm]alloc(?:_node|_array)? | + (?:kv|k|v)[czm]alloc(?:_array)?(?:_node)? | kstrdup(?:_const)? | kmemdup(?:_nul)?) | (?:\w+)?alloc_skb(?:_ip_align)? | @@ -506,6 +507,30 @@ our $signature_tags = qr{(?xi: Cc: )}; +our $tracing_logging_tags = qr{(?xi: + [=-]*> | + <[=-]* | + \[ | + \] | + start | + called | + entered | + entry | + enter | + in | + inside | + here | + begin | + exit | + end | + done | + leave | + completed | + out | + return | + [\.\!:\s]* +)}; + sub edit_distance_min { my (@arr) = @_; my $len = scalar @arr; @@ -2428,6 +2453,15 @@ sub get_raw_comment { return $comment; } +sub exclude_global_initialisers { + my ($realfile) = @_; + + # Do not check for BPF programs (tools/testing/selftests/bpf/progs/*.c, samples/bpf/*_kern.c, *.bpf.c). + return $realfile =~ m@^tools/testing/selftests/bpf/progs/.*\.c$@ || + $realfile =~ m@^samples/bpf/.*_kern\.c$@ || + $realfile =~ m@/bpf/.*\.bpf\.c$@; +} + sub process { my $filename = shift; @@ -2973,7 +3007,7 @@ sub process { } if (!defined $lines[$linenr]) { WARN("BAD_SIGN_OFF", - "Co-developed-by: must be immediately followed by Signed-off-by:\n" . "$here\n" . $rawline); + "Co-developed-by: must be immediately followed by Signed-off-by:\n" . "$here\n" . $rawline); } elsif ($rawlines[$linenr] !~ /^\s*signed-off-by:\s*(.*)/i) { WARN("BAD_SIGN_OFF", "Co-developed-by: must be immediately followed by Signed-off-by:\n" . "$here\n" . $rawline . "\n" .$rawlines[$linenr]); @@ -2996,8 +3030,8 @@ sub process { if (ERROR("GERRIT_CHANGE_ID", "Remove Gerrit Change-Id's before submitting upstream\n" . $herecurr) && $fix) { - fix_delete_line($fixlinenr, $rawline); - } + fix_delete_line($fixlinenr, $rawline); + } } # Check if the commit log is in a possible stack dump @@ -3239,10 +3273,10 @@ sub process { next if ($start_char =~ /^\S$/); next if (index(" \t.,;?!", $end_char) == -1); - # avoid repeating hex occurrences like 'ff ff fe 09 ...' - if ($first =~ /\b[0-9a-f]{2,}\b/i) { - next if (!exists($allow_repeated_words{lc($first)})); - } + # avoid repeating hex occurrences like 'ff ff fe 09 ...' + if ($first =~ /\b[0-9a-f]{2,}\b/i) { + next if (!exists($allow_repeated_words{lc($first)})); + } if (WARN("REPEATED_WORD", "Possible repeated word: '$first'\n" . $herecurr) && @@ -3574,6 +3608,13 @@ sub process { } } +# check for .L prefix local symbols in .S files + if ($realfile =~ /\.S$/ && + $line =~ /^\+\s*(?:[A-Z]+_)?SYM_[A-Z]+_(?:START|END)(?:_[A-Z_]+)?\s*\(\s*\.L/) { + WARN("AVOID_L_PREFIX", + "Avoid using '.L' prefixed local symbol names for denoting a range of code via 'SYM_*_START/END' annotations; see Documentation/asm-annotations.rst\n" . $herecurr); + } + # check we are in a valid source file C or perl if not then ignore this hunk next if ($realfile !~ /\.(h|c|pl|dtsi|dts)$/); @@ -3776,43 +3817,48 @@ sub process { } # check for missing blank lines after declarations - if ($sline =~ /^\+\s+\S/ && #Not at char 1 - # actual declarations - ($prevline =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || +# (declarations must have the same indentation and not be at the start of line) + if (($prevline =~ /\+(\s+)\S/) && $sline =~ /^\+$1\S/) { + # use temporaries + my $sl = $sline; + my $pl = $prevline; + # remove $Attribute/$Sparse uses to simplify comparisons + $sl =~ s/\b(?:$Attribute|$Sparse)\b//g; + $pl =~ s/\b(?:$Attribute|$Sparse)\b//g; + if (($pl =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || # function pointer declarations - $prevline =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || + $pl =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || # foo bar; where foo is some local typedef or #define - $prevline =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || + $pl =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || # known declaration macros - $prevline =~ /^\+\s+$declaration_macros/) && + $pl =~ /^\+\s+$declaration_macros/) && # for "else if" which can look like "$Ident $Ident" - !($prevline =~ /^\+\s+$c90_Keywords\b/ || + !($pl =~ /^\+\s+$c90_Keywords\b/ || # other possible extensions of declaration lines - $prevline =~ /(?:$Compare|$Assignment|$Operators)\s*$/ || + $pl =~ /(?:$Compare|$Assignment|$Operators)\s*$/ || # not starting a section or a macro "\" extended line - $prevline =~ /(?:\{\s*|\\)$/) && + $pl =~ /(?:\{\s*|\\)$/) && # looks like a declaration - !($sline =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || + !($sl =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || # function pointer declarations - $sline =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || + $sl =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || # foo bar; where foo is some local typedef or #define - $sline =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || + $sl =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || # known declaration macros - $sline =~ /^\+\s+$declaration_macros/ || + $sl =~ /^\+\s+$declaration_macros/ || # start of struct or union or enum - $sline =~ /^\+\s+(?:static\s+)?(?:const\s+)?(?:union|struct|enum|typedef)\b/ || + $sl =~ /^\+\s+(?:static\s+)?(?:const\s+)?(?:union|struct|enum|typedef)\b/ || # start or end of block or continuation of declaration - $sline =~ /^\+\s+(?:$|[\{\}\.\#\"\?\:\(\[])/ || + $sl =~ /^\+\s+(?:$|[\{\}\.\#\"\?\:\(\[])/ || # bitfield continuation - $sline =~ /^\+\s+$Ident\s*:\s*\d+\s*[,;]/ || + $sl =~ /^\+\s+$Ident\s*:\s*\d+\s*[,;]/ || # other possible extensions of declaration lines - $sline =~ /^\+\s+\(?\s*(?:$Compare|$Assignment|$Operators)/) && - # indentation of previous and current line are the same - (($prevline =~ /\+(\s+)\S/) && $sline =~ /^\+$1\S/)) { - if (WARN("LINE_SPACING", - "Missing a blank line after declarations\n" . $hereprev) && - $fix) { - fix_insert_line($fixlinenr, "\+"); + $sl =~ /^\+\s+\(?\s*(?:$Compare|$Assignment|$Operators)/)) { + if (WARN("LINE_SPACING", + "Missing a blank line after declarations\n" . $hereprev) && + $fix) { + fix_insert_line($fixlinenr, "\+"); + } } } @@ -4321,7 +4367,8 @@ sub process { } # check for global initialisers. - if ($line =~ /^\+$Type\s*$Ident(?:\s+$Modifier)*\s*=\s*($zero_initializer)\s*;/) { + if ($line =~ /^\+$Type\s*$Ident(?:\s+$Modifier)*\s*=\s*($zero_initializer)\s*;/ && + !exclude_global_initialisers($realfile)) { if (ERROR("GLOBAL_INITIALISERS", "do not initialise globals to $1\n" . $herecurr) && $fix) { @@ -4417,7 +4464,7 @@ sub process { WARN("STATIC_CONST_CHAR_ARRAY", "char * array declaration might be better as static const\n" . $herecurr); - } + } # check for sizeof(foo)/sizeof(foo[0]) that could be ARRAY_SIZE(foo) if ($line =~ m@\bsizeof\s*\(\s*($Lval)\s*\)@) { @@ -5007,7 +5054,7 @@ sub process { # A colon needs no spaces before when it is # terminating a case value or a label. } elsif ($opv eq ':C' || $opv eq ':L') { - if ($ctx =~ /Wx./) { + if ($ctx =~ /Wx./ and $realfile !~ m@.*\.lds\.h$@) { if (ERROR("SPACING", "space prohibited before that '$op' $at\n" . $hereptr)) { $good = rtrim($fix_elements[$n]) . trim($fix_elements[$n + 1]); @@ -5270,7 +5317,7 @@ sub process { $lines[$linenr - 3] !~ /^[ +]\s*$Ident\s*:/) { WARN("RETURN_VOID", "void function return statements are not generally useful\n" . $hereprev); - } + } # if statements using unnecessary parentheses - ie: if ((foo == bar)) if ($perl_version_ok && @@ -5966,6 +6013,17 @@ sub process { "Prefer using '\"%s...\", __func__' to using '$context_function', this function's name, in a string\n" . $herecurr); } +# check for unnecessary function tracing like uses +# This does not use $logFunctions because there are many instances like +# 'dprintk(FOO, "%s()\n", __func__);' which do not match $logFunctions + if ($rawline =~ /^\+.*\([^"]*"$tracing_logging_tags{0,3}%s(?:\s*\(\s*\)\s*)?$tracing_logging_tags{0,3}(?:\\n)?"\s*,\s*__func__\s*\)\s*;/) { + if (WARN("TRACING_LOGGING", + "Unnecessary ftrace-like logging - prefer using ftrace\n" . $herecurr) && + $fix) { + fix_delete_line($fixlinenr, $rawline); + } + } + # check for spaces before a quoted newline if ($rawline =~ /^.*\".*\s\\n/) { if (WARN("QUOTED_WHITESPACE_BEFORE_NEWLINE", @@ -6477,18 +6535,18 @@ sub process { if ($line =~ /(\(\s*$C90_int_types\s*\)\s*)($Constant)\b/) { my $cast = $1; my $const = $2; + my $suffix = ""; + my $newconst = $const; + $newconst =~ s/${Int_type}$//; + $suffix .= 'U' if ($cast =~ /\bunsigned\b/); + if ($cast =~ /\blong\s+long\b/) { + $suffix .= 'LL'; + } elsif ($cast =~ /\blong\b/) { + $suffix .= 'L'; + } if (WARN("TYPECAST_INT_CONSTANT", - "Unnecessary typecast of c90 int constant\n" . $herecurr) && + "Unnecessary typecast of c90 int constant - '$cast$const' could be '$const$suffix'\n" . $herecurr) && $fix) { - my $suffix = ""; - my $newconst = $const; - $newconst =~ s/${Int_type}$//; - $suffix .= 'U' if ($cast =~ /\bunsigned\b/); - if ($cast =~ /\blong\s+long\b/) { - $suffix .= 'LL'; - } elsif ($cast =~ /\blong\b/) { - $suffix .= 'L'; - } $fixed[$fixlinenr] =~ s/\Q$cast\E$const\b/$newconst$suffix/; } } @@ -7019,12 +7077,14 @@ sub process { # use of NR_CPUS is usually wrong # ignore definitions of NR_CPUS and usage to define arrays as likely right +# ignore designated initializers using NR_CPUS if ($line =~ /\bNR_CPUS\b/ && $line !~ /^.\s*\s*#\s*if\b.*\bNR_CPUS\b/ && $line !~ /^.\s*\s*#\s*define\b.*\bNR_CPUS\b/ && $line !~ /^.\s*$Declare\s.*\[[^\]]*NR_CPUS[^\]]*\]/ && $line !~ /\[[^\]]*\.\.\.[^\]]*NR_CPUS[^\]]*\]/ && - $line !~ /\[[^\]]*NR_CPUS[^\]]*\.\.\.[^\]]*\]/) + $line !~ /\[[^\]]*NR_CPUS[^\]]*\.\.\.[^\]]*\]/ && + $line !~ /^.\s*\.\w+\s*=\s*.*\bNR_CPUS\b/) { WARN("NR_CPUS", "usage of NR_CPUS is often wrong - consider using cpu_possible(), num_possible_cpus(), for_each_possible_cpu(), etc\n" . $herecurr); diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py index 8ddb5d099029..b7e9ecf16e56 100755 --- a/scripts/clang-tools/gen_compile_commands.py +++ b/scripts/clang-tools/gen_compile_commands.py @@ -20,7 +20,9 @@ _DEFAULT_LOG_LEVEL = 'WARNING' _FILENAME_PATTERN = r'^\..*\.cmd$' _LINE_PATTERN = r'^cmd_[^ ]*\.o := (.* )([^ ]*\.c)$' _VALID_LOG_LEVELS = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'] - +# The tools/ directory adopts a different build system, and produces .cmd +# files in a different format. Do not support it. +_EXCLUDE_DIRS = ['.git', 'Documentation', 'include', 'tools'] def parse_arguments(): """Sets up and parses command-line arguments. @@ -80,8 +82,14 @@ def cmdfiles_in_dir(directory): """ filename_matcher = re.compile(_FILENAME_PATTERN) + exclude_dirs = [ os.path.join(directory, d) for d in _EXCLUDE_DIRS ] + + for dirpath, dirnames, filenames in os.walk(directory, topdown=True): + # Prune unwanted directories. + if dirpath in exclude_dirs: + dirnames[:] = [] + continue - for dirpath, _, filenames in os.walk(directory): for filename in filenames: if filename_matcher.match(filename): yield os.path.join(dirpath, filename) diff --git a/scripts/clang-version.sh b/scripts/clang-version.sh deleted file mode 100755 index 6fabf0695761..000000000000 --- a/scripts/clang-version.sh +++ /dev/null @@ -1,19 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# clang-version clang-command -# -# Print the compiler version of `clang-command' in a 5 or 6-digit form -# such as `50001' for clang-5.0.1 etc. - -compiler="$*" - -if ! ( $compiler --version | grep -q clang) ; then - echo 0 - exit 1 -fi - -MAJOR=$(echo __clang_major__ | $compiler -E -x c - | tail -n 1) -MINOR=$(echo __clang_minor__ | $compiler -E -x c - | tail -n 1) -PATCHLEVEL=$(echo __clang_patchlevel__ | $compiler -E -x c - | tail -n 1) -printf "%d%02d%02d\\n" $MAJOR $MINOR $PATCHLEVEL diff --git a/scripts/gcc-version.sh b/scripts/gcc-version.sh deleted file mode 100755 index ae353432539b..000000000000 --- a/scripts/gcc-version.sh +++ /dev/null @@ -1,20 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# gcc-version gcc-command -# -# Print the gcc version of `gcc-command' in a 5 or 6-digit form -# such as `29503' for gcc-2.95.3, `30301' for gcc-3.3.1, etc. - -compiler="$*" - -if [ ${#compiler} -eq 0 ]; then - echo "Error: No compiler specified." >&2 - printf "Usage:\n\t$0 \n" >&2 - exit 1 -fi - -MAJOR=$(echo __GNUC__ | $compiler -E -x c - | tail -n 1) -MINOR=$(echo __GNUC_MINOR__ | $compiler -E -x c - | tail -n 1) -PATCHLEVEL=$(echo __GNUC_PATCHLEVEL__ | $compiler -E -x c - | tail -n 1) -printf "%d%02d%02d\\n" $MAJOR $MINOR $PATCHLEVEL diff --git a/scripts/gdb/linux/Makefile b/scripts/gdb/linux/Makefile index 124755087510..48941faa6ea6 100644 --- a/scripts/gdb/linux/Makefile +++ b/scripts/gdb/linux/Makefile @@ -7,7 +7,7 @@ symlinks := $(patsubst $(srctree)/$(src)/%,%,$(wildcard $(srctree)/$(src)/*.py)) quiet_cmd_symlink = SYMLINK $@ cmd_symlink = ln -fsn $(patsubst $(obj)/%,$(abspath $(srctree))/$(src)/%,$@) $@ -extra-y += $(symlinks) +always-y += $(symlinks) $(addprefix $(obj)/, $(symlinks)): FORCE $(call if_changed,symlink) @@ -18,7 +18,7 @@ quiet_cmd_gen_constants_py = GEN $@ $(CPP) -E -x c -P $(c_flags) $< > $@ ;\ sed -i '1,//d;' $@ -extra-y += constants.py +always-y += constants.py $(obj)/constants.py: $(src)/constants.py.in FORCE $(call if_changed_dep,gen_constants_py) diff --git a/scripts/gdb/linux/lists.py b/scripts/gdb/linux/lists.py index c487ddf09d38..bae4d70b7eae 100644 --- a/scripts/gdb/linux/lists.py +++ b/scripts/gdb/linux/lists.py @@ -27,6 +27,11 @@ def list_for_each(head): raise TypeError("Must be struct list_head not {}" .format(head.type)) + if head['next'] == 0: + gdb.write("list_for_each: Uninitialized list '{}' treated as empty\n" + .format(head.address)) + return + node = head['next'].dereference() while node.address != head.address: yield node.address diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c index 23eff234184f..4827c5abe5b7 100644 --- a/scripts/genksyms/genksyms.c +++ b/scripts/genksyms/genksyms.c @@ -29,7 +29,7 @@ static struct symbol *symtab[HASH_BUCKETS]; static FILE *debugfile; int cur_line = 1; -char *cur_filename, *source_file; +char *cur_filename; int in_source_file; static int flag_debug, flag_dump_defs, flag_reference, flag_dump_types, diff --git a/scripts/genksyms/genksyms.h b/scripts/genksyms/genksyms.h index 2bcdb9bebab4..21ed2ec2d98c 100644 --- a/scripts/genksyms/genksyms.h +++ b/scripts/genksyms/genksyms.h @@ -47,7 +47,7 @@ typedef struct string_list **yystype; #define YYSTYPE yystype extern int cur_line; -extern char *cur_filename, *source_file; +extern char *cur_filename; extern int in_source_file; struct symbol *find_symbol(const char *name, enum symbol_type ns, int exact); diff --git a/scripts/genksyms/lex.l b/scripts/genksyms/lex.l index ae76472efc43..a4d7495eaf75 100644 --- a/scripts/genksyms/lex.l +++ b/scripts/genksyms/lex.l @@ -119,12 +119,11 @@ yylex(void) static enum { ST_NOTSTARTED, ST_NORMAL, ST_ATTRIBUTE, ST_ASM, ST_TYPEOF, ST_TYPEOF_1, ST_BRACKET, ST_BRACE, ST_EXPRESSION, ST_STATIC_ASSERT, - ST_TABLE_1, ST_TABLE_2, ST_TABLE_3, ST_TABLE_4, - ST_TABLE_5, ST_TABLE_6 } lexstate = ST_NOTSTARTED; static int suppress_type_lookup, dont_want_brace_phrase; static struct string_list *next_node; + static char *source_file; int token, count = 0; struct string_list *cur_node; @@ -235,7 +234,6 @@ repeat: lexstate = ST_EXPRESSION; break; - case DOTS: default: APP; break; @@ -426,58 +424,6 @@ repeat: } break; - case ST_TABLE_1: - goto repeat; - - case ST_TABLE_2: - if (token == IDENT && yyleng == 1 && yytext[0] == 'X') - { - token = EXPORT_SYMBOL_KEYW; - lexstate = ST_TABLE_5; - APP; - break; - } - lexstate = ST_TABLE_6; - /* FALLTHRU */ - - case ST_TABLE_6: - switch (token) - { - case '{': case '[': case '(': - ++count; - break; - case '}': case ']': case ')': - --count; - break; - case ',': - if (count == 0) - lexstate = ST_TABLE_2; - break; - }; - goto repeat; - - case ST_TABLE_3: - goto repeat; - - case ST_TABLE_4: - if (token == ';') - lexstate = ST_NORMAL; - goto repeat; - - case ST_TABLE_5: - switch (token) - { - case ',': - token = ';'; - lexstate = ST_TABLE_2; - APP; - break; - default: - APP; - break; - } - break; - default: exit(1); } diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index 2c40e68853dd..8c19b82c6035 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -3,9 +3,6 @@ # Kernel configuration targets # These targets are used from top-level makefile -PHONY += xconfig gconfig menuconfig config localmodconfig localyesconfig \ - build_menuconfig build_nconfig build_gconfig build_xconfig - ifdef KBUILD_KCONFIG Kconfig := $(KBUILD_KCONFIG) else @@ -19,29 +16,24 @@ endif # We need this, in case the user has it in its environment unexport CONFIG_ -xconfig: $(obj)/qconf - $(Q)$< $(silent) $(Kconfig) +config-prog := conf +menuconfig-prog := mconf +nconfig-prog := nconf +gconfig-prog := gconf +xconfig-prog := qconf -gconfig: $(obj)/gconf - $(Q)$< $(silent) $(Kconfig) +define config_rule +PHONY += $(1) +$(1): $(obj)/$($(1)-prog) + $(Q)$$< $(silent) $(Kconfig) -menuconfig: $(obj)/mconf - $(Q)$< $(silent) $(Kconfig) +PHONY += build_$(1) +build_$(1): $(obj)/$($(1)-prog) +endef -config: $(obj)/conf - $(Q)$< $(silent) --oldaskconfig $(Kconfig) - -nconfig: $(obj)/nconf - $(Q)$< $(silent) $(Kconfig) - -build_menuconfig: $(obj)/mconf - -build_nconfig: $(obj)/nconf - -build_gconfig: $(obj)/gconf - -build_xconfig: $(obj)/qconf +$(foreach c, config menuconfig nconfig gconfig xconfig, $(eval $(call config_rule,$(c)))) +PHONY += localmodconfig localyesconfig localyesconfig localmodconfig: $(obj)/conf $(Q)$(PERL) $(srctree)/$(src)/streamline_config.pl --$@ $(srctree) $(Kconfig) > .tmp.config $(Q)if [ -f .config ]; then \ diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c index db03e2f45de4..957d2a0832f7 100644 --- a/scripts/kconfig/conf.c +++ b/scripts/kconfig/conf.c @@ -84,8 +84,6 @@ static void xfgets(char *str, int size, FILE *in) static int conf_askvalue(struct symbol *sym, const char *def) { - enum symbol_type type = sym_get_type(sym); - if (!sym_has_value(sym)) printf("(NEW) "); @@ -107,24 +105,12 @@ static int conf_askvalue(struct symbol *sym, const char *def) return 0; } /* fall through */ - case oldaskconfig: + default: fflush(stdout); xfgets(line, sizeof(line), stdin); - return 1; - default: break; } - switch (type) { - case S_INT: - case S_HEX: - case S_STRING: - printf("%s\n", def); - return 1; - default: - ; - } - printf("%s", line); return 1; } @@ -137,7 +123,7 @@ static int conf_string(struct menu *menu) printf("%*s%s ", indent - 1, "", menu->prompt->text); printf("(%s) ", sym->name); def = sym_get_string_value(sym); - if (sym_get_string_value(sym)) + if (def) printf("[%s] ", def); if (!conf_askvalue(sym, def)) return 0; @@ -419,34 +405,37 @@ static void check_conf(struct menu *menu) return; sym = menu->sym; - if (sym && !sym_has_value(sym)) { - if (sym_is_changeable(sym) || - (sym_is_choice(sym) && sym_get_tristate_value(sym) == yes)) { - if (input_mode == listnewconfig) { - if (sym->name) { - const char *str; + if (sym && !sym_has_value(sym) && + (sym_is_changeable(sym) || + (sym_is_choice(sym) && sym_get_tristate_value(sym) == yes))) { - if (sym->type == S_STRING) { - str = sym_get_string_value(sym); - str = sym_escape_string_value(str); - printf("%s%s=%s\n", CONFIG_, sym->name, str); - free((void *)str); - } else { - str = sym_get_string_value(sym); - printf("%s%s=%s\n", CONFIG_, sym->name, str); - } + switch (input_mode) { + case listnewconfig: + if (sym->name) { + const char *str; + + if (sym->type == S_STRING) { + str = sym_get_string_value(sym); + str = sym_escape_string_value(str); + printf("%s%s=%s\n", CONFIG_, sym->name, str); + free((void *)str); + } else { + str = sym_get_string_value(sym); + printf("%s%s=%s\n", CONFIG_, sym->name, str); } - } else if (input_mode == helpnewconfig) { - printf("-----\n"); - print_help(menu); - printf("-----\n"); - - } else { - if (!conf_cnt++) - printf("*\n* Restart config...\n*\n"); - rootEntry = menu_get_parent_menu(menu); - conf(rootEntry); } + break; + case helpnewconfig: + printf("-----\n"); + print_help(menu); + printf("-----\n"); + break; + default: + if (!conf_cnt++) + printf("*\n* Restart config...\n*\n"); + rootEntry = menu_get_parent_menu(menu); + conf(rootEntry); + break; } } @@ -494,6 +483,7 @@ static void conf_usage(const char *progname) printf(" --randconfig New config with random answer to all options\n"); printf(" --yes2modconfig Change answers from yes to mod if possible\n"); printf(" --mod2yesconfig Change answers from mod to yes if possible\n"); + printf(" (If none of the above is given, --oldaskconfig is the default)\n"); } int main(int ac, char **av) @@ -505,7 +495,7 @@ int main(int ac, char **av) tty_stdio = isatty(0) && isatty(1); - while ((opt = getopt_long(ac, av, "s", long_opts, NULL)) != -1) { + while ((opt = getopt_long(ac, av, "hs", long_opts, NULL)) != -1) { if (opt == 's') { conf_set_message_callback(NULL); continue; @@ -561,7 +551,7 @@ int main(int ac, char **av) case yes2modconfig: case mod2yesconfig: break; - case '?': + case 'h': conf_usage(progname); exit(1); break; diff --git a/scripts/ld-version.sh b/scripts/ld-version.sh index f2be0ff9a738..a463273509b5 100755 --- a/scripts/ld-version.sh +++ b/scripts/ld-version.sh @@ -1,11 +1,73 @@ -#!/usr/bin/awk -f +#!/bin/sh # SPDX-License-Identifier: GPL-2.0 -# extract linker version number from stdin and turn into single number - { - gsub(".*\\)", ""); - gsub(".*version ", ""); - gsub("-.*", ""); - split($1,a, "."); - print a[1]*100000000 + a[2]*1000000 + a[3]*10000; - exit - } +# +# Print the linker name and its version in a 5 or 6-digit form. +# Also, perform the minimum version check. + +set -e + +# When you raise the minimum linker version, please update +# Documentation/process/changes.rst as well. +bfd_min_version=2.23.0 +lld_min_version=10.0.1 + +# Convert the version string x.y.z to a canonical 5 or 6-digit form. +get_canonical_version() +{ + IFS=. + set -- $1 + + # If the 2nd or 3rd field is missing, fill it with a zero. + # + # The 4th field, if present, is ignored. + # This occurs in development snapshots as in 2.35.1.20201116 + echo $((10000 * $1 + 100 * ${2:-0} + ${3:-0})) +} + +orig_args="$@" + +# Get the first line of the --version output. +IFS=' +' +set -- $("$@" --version) + +# Split the line on spaces. +IFS=' ' +set -- $1 + +if [ "$1" = GNU -a "$2" = ld ]; then + shift $(($# - 1)) + version=$1 + min_version=$bfd_min_version + name=BFD + disp_name="GNU ld" +elif [ "$1" = GNU -a "$2" = gold ]; then + echo "gold linker is not supported as it is not capable of linking the kernel proper." >&2 + exit 1 +elif [ "$1" = LLD ]; then + version=$2 + min_version=$lld_min_version + name=LLD + disp_name=LLD +else + echo "$orig_args: unknown linker" >&2 + exit 1 +fi + +# Some distributions append a package release number, as in 2.34-4.fc32 +# Trim the hyphen and any characters that follow. +version=${version%-*} + +cversion=$(get_canonical_version $version) +min_cversion=$(get_canonical_version $min_version) + +if [ "$cversion" -lt "$min_cversion" ]; then + echo >&2 "***" + echo >&2 "*** Linker is too old." + echo >&2 "*** Your $disp_name version: $version" + echo >&2 "*** Minimum $disp_name version: $min_version" + echo >&2 "***" + exit 1 +fi + +echo $name $cversion diff --git a/scripts/lld-version.sh b/scripts/lld-version.sh deleted file mode 100755 index d70edb4d8a4f..000000000000 --- a/scripts/lld-version.sh +++ /dev/null @@ -1,20 +0,0 @@ -#!/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/syscallhdr.sh b/scripts/syscallhdr.sh new file mode 100755 index 000000000000..848ac2735115 --- /dev/null +++ b/scripts/syscallhdr.sh @@ -0,0 +1,98 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-only +# +# Generate a syscall number header. +# +# Each line of the syscall table should have the following format: +# +# NR ABI NAME [NATIVE] [COMPAT] +# +# NR syscall number +# ABI ABI name +# NAME syscall name +# NATIVE native entry point (optional) +# COMPAT compat entry point (optional) + +set -e + +usage() { + echo >&2 "usage: $0 [--abis ABIS] [--emit-nr] [--offset OFFSET] [--prefix PREFIX] INFILE OUTFILE" >&2 + echo >&2 + echo >&2 " INFILE input syscall table" + echo >&2 " OUTFILE output header file" + echo >&2 + echo >&2 "options:" + echo >&2 " --abis ABIS ABI(s) to handle (By default, all lines are handled)" + echo >&2 " --emit-nr Emit the macro of the number of syscalls (__NR_syscalls)" + echo >&2 " --offset OFFSET The offset of syscall numbers" + echo >&2 " --prefix PREFIX The prefix to the macro like __NR_" + exit 1 +} + +# default unless specified by options +abis= +emit_nr= +offset= +prefix= + +while [ $# -gt 0 ] +do + case $1 in + --abis) + abis=$(echo "($2)" | tr ',' '|') + shift 2;; + --emit-nr) + emit_nr=1 + shift 1;; + --offset) + offset=$2 + shift 2;; + --prefix) + prefix=$2 + shift 2;; + -*) + echo "$1: unknown option" >&2 + usage;; + *) + break;; + esac +done + +if [ $# -ne 2 ]; then + usage +fi + +infile="$1" +outfile="$2" + +guard=_UAPI_ASM_$(basename "$outfile" | + sed -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \ + -e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g') + +grep -E "^[0-9A-Fa-fXx]+[[:space:]]+$abis" "$infile" | sort -n | { + echo "#ifndef $guard" + echo "#define $guard" + echo + + max=0 + while read nr abi name native compat ; do + + max=$nr + + if [ -n "$offset" ]; then + nr="($offset + $nr)" + fi + + echo "#define __NR_$prefix$name $nr" + done + + if [ -n "$emit_nr" ]; then + echo + echo "#ifdef __KERNEL__" + echo "#define __NR_${prefix}syscalls $(($max + 1))" + echo "#endif" + fi + + echo + echo "#endif /* $guard */" +} > "$outfile" diff --git a/scripts/syscalltbl.sh b/scripts/syscalltbl.sh new file mode 100755 index 000000000000..aa6ab156301c --- /dev/null +++ b/scripts/syscalltbl.sh @@ -0,0 +1,73 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-only +# +# Generate a syscall table header. +# +# Each line of the syscall table should have the following format: +# +# NR ABI NAME [NATIVE] [COMPAT] +# +# NR syscall number +# ABI ABI name +# NAME syscall name +# NATIVE native entry point (optional) +# COMPAT compat entry point (optional) + +set -e + +usage() { + echo >&2 "usage: $0 [--abis ABIS] INFILE OUTFILE" >&2 + echo >&2 + echo >&2 " INFILE input syscall table" + echo >&2 " OUTFILE output header file" + echo >&2 + echo >&2 "options:" + echo >&2 " --abis ABIS ABI(s) to handle (By default, all lines are handled)" + exit 1 +} + +# default unless specified by options +abis= + +while [ $# -gt 0 ] +do + case $1 in + --abis) + abis=$(echo "($2)" | tr ',' '|') + shift 2;; + -*) + echo "$1: unknown option" >&2 + usage;; + *) + break;; + esac +done + +if [ $# -ne 2 ]; then + usage +fi + +infile="$1" +outfile="$2" + +nxt=0 + +grep -E "^[0-9]+[[:space:]]+$abis" "$infile" | sort -n | { + + while read nr abi name native compat ; do + + while [ $nxt -lt $nr ]; do + echo "__SYSCALL($nxt, sys_ni_syscall)" + nxt=$((nxt + 1)) + done + + if [ -n "$compat" ]; then + echo "__SYSCALL_WITH_COMPAT($nr, $native, $compat)" + elif [ -n "$native" ]; then + echo "__SYSCALL($nr, $native)" + else + echo "__SYSCALL($nr, sys_ni_syscall)" + fi + nxt=$((nr + 1)) + done +} > "$outfile" diff --git a/scripts/test_dwarf5_support.sh b/scripts/test_dwarf5_support.sh new file mode 100755 index 000000000000..c46e2456b47a --- /dev/null +++ b/scripts/test_dwarf5_support.sh @@ -0,0 +1,8 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +# Test that the assembler doesn't need -Wa,-gdwarf-5 when presented with DWARF +# v5 input, such as `.file 0` and `md5 0x00`. Should be fixed in GNU binutils +# 2.35.2. https://sourceware.org/bugzilla/show_bug.cgi?id=25611 +echo '.file 0 "filename" md5 0x7a0b65214090b6693bd1dc24dd248245' | \ + $* -gdwarf-5 -Wno-unused-command-line-argument -c -x assembler -o /dev/null - diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 3a84394829ea..32b87cc77c8e 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -33,6 +33,7 @@ /demand_paging_test /dirty_log_test /dirty_log_perf_test +/hardware_disable_test /kvm_create_max_vcpus /memslot_modification_stress_test /set_memory_region_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 8c8eda429576..a6d61f451f88 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -67,6 +67,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_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 += hardware_disable_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test TEST_GEN_PROGS_x86_64 += set_memory_region_test diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c new file mode 100644 index 000000000000..2f2eeb8a1d86 --- /dev/null +++ b/tools/testing/selftests/kvm/hardware_disable_test.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This test is intended to reproduce a crash that happens when + * kvm_arch_hardware_disable is called and it attempts to unregister the user + * return notifiers. + */ + +#define _GNU_SOURCE + +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "kvm_util.h" + +#define VCPU_NUM 4 +#define SLEEPING_THREAD_NUM (1 << 4) +#define FORK_NUM (1ULL << 9) +#define DELAY_US_MAX 2000 +#define GUEST_CODE_PIO_PORT 4 + +sem_t *sem; + +/* Arguments for the pthreads */ +struct payload { + struct kvm_vm *vm; + uint32_t index; +}; + +static void guest_code(void) +{ + for (;;) + ; /* Some busy work */ + printf("Should not be reached.\n"); +} + +static void *run_vcpu(void *arg) +{ + struct payload *payload = (struct payload *)arg; + struct kvm_run *state = vcpu_state(payload->vm, payload->index); + + vcpu_run(payload->vm, payload->index); + + TEST_ASSERT(false, "%s: exited with reason %d: %s\n", + __func__, state->exit_reason, + exit_reason_str(state->exit_reason)); + pthread_exit(NULL); +} + +static void *sleeping_thread(void *arg) +{ + int fd; + + while (true) { + fd = open("/dev/null", O_RDWR); + close(fd); + } + TEST_ASSERT(false, "%s: exited\n", __func__); + pthread_exit(NULL); +} + +static inline void check_create_thread(pthread_t *thread, pthread_attr_t *attr, + void *(*f)(void *), void *arg) +{ + int r; + + r = pthread_create(thread, attr, f, arg); + TEST_ASSERT(r == 0, "%s: failed to create thread", __func__); +} + +static inline void check_set_affinity(pthread_t thread, cpu_set_t *cpu_set) +{ + int r; + + r = pthread_setaffinity_np(thread, sizeof(cpu_set_t), cpu_set); + TEST_ASSERT(r == 0, "%s: failed set affinity", __func__); +} + +static inline void check_join(pthread_t thread, void **retval) +{ + int r; + + r = pthread_join(thread, retval); + TEST_ASSERT(r == 0, "%s: failed to join thread", __func__); +} + +static void run_test(uint32_t run) +{ + struct kvm_vm *vm; + cpu_set_t cpu_set; + pthread_t threads[VCPU_NUM]; + pthread_t throw_away; + struct payload payloads[VCPU_NUM]; + void *b; + uint32_t i, j; + + CPU_ZERO(&cpu_set); + for (i = 0; i < VCPU_NUM; i++) + CPU_SET(i, &cpu_set); + + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + kvm_vm_elf_load(vm, program_invocation_name, 0, 0); + vm_create_irqchip(vm); + + fprintf(stderr, "%s: [%d] start vcpus\n", __func__, run); + for (i = 0; i < VCPU_NUM; ++i) { + vm_vcpu_add_default(vm, i, guest_code); + payloads[i].vm = vm; + payloads[i].index = i; + + check_create_thread(&threads[i], NULL, run_vcpu, + (void *)&payloads[i]); + check_set_affinity(threads[i], &cpu_set); + + for (j = 0; j < SLEEPING_THREAD_NUM; ++j) { + check_create_thread(&throw_away, NULL, sleeping_thread, + (void *)NULL); + check_set_affinity(throw_away, &cpu_set); + } + } + fprintf(stderr, "%s: [%d] all threads launched\n", __func__, run); + sem_post(sem); + for (i = 0; i < VCPU_NUM; ++i) + check_join(threads[i], &b); + /* Should not be reached */ + TEST_ASSERT(false, "%s: [%d] child escaped the ninja\n", __func__, run); +} + +int main(int argc, char **argv) +{ + uint32_t i; + int s, r; + pid_t pid; + + sem = sem_open("vm_sem", O_CREAT | O_EXCL, 0644, 0); + sem_unlink("vm_sem"); + + for (i = 0; i < FORK_NUM; ++i) { + pid = fork(); + TEST_ASSERT(pid >= 0, "%s: unable to fork", __func__); + if (pid == 0) + run_test(i); /* This function always exits */ + + fprintf(stderr, "%s: [%d] waiting semaphore\n", __func__, i); + sem_wait(sem); + r = (rand() % DELAY_US_MAX) + 1; + fprintf(stderr, "%s: [%d] waiting %dus\n", __func__, i, r); + usleep(r); + r = waitpid(pid, &s, WNOHANG); + TEST_ASSERT(r != pid, + "%s: [%d] child exited unexpectedly status: [%d]", + __func__, i, s); + fprintf(stderr, "%s: [%d] killing child\n", __func__, i); + kill(pid, SIGKILL); + } + + sem_destroy(sem); + exit(0); +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index de0c76177d02..a8906e60a108 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -720,7 +720,8 @@ struct kvm_cpuid2 *vcpu_get_cpuid(struct kvm_vm *vm, uint32_t vcpuid) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); struct kvm_cpuid2 *cpuid; - int rc, max_ent; + int max_ent; + int rc = -1; TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 74c69b75f6f5..7ed7cd95e58f 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -39,7 +39,7 @@ ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; } ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; } ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; } sleep() { read -t "$1" -N 1 || true; } -waitiperf() { pretty "${1//*-}" "wait for iperf:5201 pid $2"; while [[ $(ss -N "$1" -tlpH 'sport = 5201') != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; } +waitiperf() { pretty "${1//*-}" "wait for iperf:${3:-5201} pid $2"; while [[ $(ss -N "$1" -tlpH "sport = ${3:-5201}") != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; } waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; } waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; } @@ -141,6 +141,19 @@ tests() { n2 iperf3 -s -1 -B fd00::2 & waitiperf $netns2 $! n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2 + + # TCP over IPv4, in parallel + for max in 4 5 50; do + local pids=( ) + for ((i=0; i < max; ++i)) do + n2 iperf3 -p $(( 5200 + i )) -s -1 -B 192.168.241.2 & + pids+=( $! ); waitiperf $netns2 $! $(( 5200 + i )) + done + for ((i=0; i < max; ++i)) do + n1 iperf3 -Z -t 3 -p $(( 5200 + i )) -c 192.168.241.2 & + done + wait "${pids[@]}" + done } [[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}" diff --git a/tools/tracing/latency/latency-collector.c b/tools/tracing/latency/latency-collector.c index 57b20802e71b..b69de9263ee6 100644 --- a/tools/tracing/latency/latency-collector.c +++ b/tools/tracing/latency/latency-collector.c @@ -1650,7 +1650,7 @@ static void start_printthread(void) if (ufd < 0 || read(ufd, seed, sizeof(*seed)) != sizeof(*seed)) { printf( -"Warning! Using trivial random nummer seed, since %s not available\n", +"Warning! Using trivial random number seed, since %s not available\n", DEV_URANDOM); fflush(stdout); *seed = i; @@ -1711,8 +1711,8 @@ static void show_usage(void) "\t\t\tbeginning, end, and backtrace.\n\n" "-g, --graph\t\tEnable the display-graph option in trace_option. This\n" -"\t\t\toption causes ftrace to show the functionph of how\n" -"\t\t\tfunctions are calling other functions.\n\n" +"\t\t\toption causes ftrace to show the graph of how functions\n" +"\t\t\tare calling other functions.\n\n" "-c, --policy POL\tRun the program with scheduling policy POL. POL can be\n" "\t\t\tother, batch, idle, rr or fifo. The default is rr. When\n" diff --git a/usr/Kconfig b/usr/Kconfig index 2599bc21c1b2..8bbcf699fe3b 100644 --- a/usr/Kconfig +++ b/usr/Kconfig @@ -103,7 +103,6 @@ config RD_LZ4 config RD_ZSTD bool "Support initial ramdisk/ramfs compressed using ZSTD" default y - depends on BLK_DEV_INITRD select DECOMPRESS_ZSTD help Support loading of a ZSTD encoded initial ramdisk or cpio buffer. diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 001b9de4e727..383df23514b9 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -486,6 +486,24 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, * count is also read inside the mmu_lock critical section. */ kvm->mmu_notifier_count++; + if (likely(kvm->mmu_notifier_count == 1)) { + kvm->mmu_notifier_range_start = range->start; + kvm->mmu_notifier_range_end = range->end; + } else { + /* + * Fully tracking multiple concurrent ranges has dimishing + * returns. Keep things simple and just find the minimal range + * which includes the current and new ranges. As there won't be + * enough information to subtract a range after its invalidate + * completes, any ranges invalidated concurrently will + * accumulate and persist until all outstanding invalidates + * complete. + */ + kvm->mmu_notifier_range_start = + min(kvm->mmu_notifier_range_start, range->start); + kvm->mmu_notifier_range_end = + max(kvm->mmu_notifier_range_end, range->end); + } need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end, range->flags); /* we've to flush the tlb before the pages can be freed */ @@ -2023,10 +2041,13 @@ static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool *async, bool write_fault, - bool *writable) + bool *writable, hva_t *hva) { unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault); + if (hva) + *hva = addr; + if (addr == KVM_HVA_ERR_RO_BAD) { if (writable) *writable = false; @@ -2054,19 +2075,19 @@ kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable) { return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL, - write_fault, writable); + write_fault, writable, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { - return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL); + return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot); kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) { - return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL); + return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);