UAPI Changes:
- Expose per-engine activity via perf pmu (Riana, Lucas, Umesh)
- Add support for EU stall sampling (Harish, Ashutosh)
- Allow userspace to provide low latency hint for submission (Tejas)
- GPU SVM and Xe SVM implementation (Matthew Brost)
Cross-subsystem Changes:
- devres handling for component drivers (Lucas)
- Backmege drm-next to allow cross dependent change with i915
- GPU SVM and Xe SVM implementation (Matthew Brost)
Core Changes:
Driver Changes:
- Fixes to userptr and missing validations (Matthew Auld, Thomas
Hellström, Matthew Brost)
- devcoredump typos and error handling improvement (Shuicheng)
- Allow oa_exponent value of 0 (Umesh)
- Finish moving device probe to devm (Lucas)
- Fix race between submission restart and scheduled being freed (Tejas)
- Fix counter overflows in gt_stats (Francois)
- Refactor and add missing workarounds and tunings for pre-Xe2 platforms
(Aradhya, Tvrtko)
- Fix PXP locks interaction with exec queues being killed (Daniele)
- Eliminate TIMESTAMP_OVERRIDE from xe (Matt Roper)
- Change xe_gen_wa_oob to allow building on MacOS (Daniel Gomez)
- New workarounds for Panther Lake (Tejas)
- Fix VF resume errors (Satyanarayana)
- Fix workaround infra skipping some workarounds dependent on engine
initialization (Tvrtko)
- Improve per-IP descriptors (Gustavo)
- Add more error injections to probe sequence (Francois)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ilc5jvtyaoyi6woyhght5a6sw5jcluiojjueorcyxbynrcpcjp@mw2mi6rd6a7l
drm-misc-next for v6.15:
Cross-subsystem Changes:
base:
- component: Provide helper to query bound status
fbdev:
- fbtft: Remove access to page->index
Core Changes:
- Fix usage of logging macros in several places
gem:
- Add test function for imported dma-bufs and use it in core and helpers
- Avoid struct drm_gem_object.import_attach
tests:
- Fix lockdep warnings
ttm:
- Add helpers for TTM shrinker
Driver Changes:
adp:
- Add support for Apple Touch Bar displays on M1/M2
amdxdna:
- Fix interrupt handling
appletbdrm:
- Add support for Apple Touch Bar displays on x86
bridge:
- synopsys: Add HDMI audio support
- ti-sn65dsi83: Support negative DE polarity
ipu-v3:
- Remove unused code
nouveau:
- Avoid multiple -Wflex-array-member-not-at-end warnings
panthor:
- Fix CS_STATUS_ defines
- Improve locking
rockchip:
- analogix_dp: Add eDP support
- lvds: Improve logging
- vop2: Improve HDMI mode handling; Add support for RK3576
- Fix shutdown
- Support rk3562-mali
xe:
- Use TTM shrinker
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306130700.GA485504@linux.fritz.box
This patch introduces support for GPU Shared Virtual Memory (SVM) in the
Direct Rendering Manager (DRM) subsystem. SVM allows for seamless
sharing of memory between the CPU and GPU, enhancing performance and
flexibility in GPU computing tasks.
The patch adds the necessary infrastructure for SVM, including data
structures and functions for managing SVM ranges and notifiers. It also
provides mechanisms for allocating, deallocating, and migrating memory
regions between system RAM and GPU VRAM.
This is largely inspired by GPUVM.
v2:
- Take order into account in check pages
- Clear range->pages in get pages error
- Drop setting dirty or accessed bit in get pages (Vetter)
- Remove mmap assert for cpu faults
- Drop mmap write lock abuse (Vetter, Christian)
- Decouple zdd from range (Vetter, Oak)
- Add drm_gpusvm_range_evict, make it work with coherent pages
- Export drm_gpusvm_evict_to_sram, only use in BO evict path (Vetter)
- mmget/put in drm_gpusvm_evict_to_sram
- Drop range->vram_alloation variable
- Don't return in drm_gpusvm_evict_to_sram until all pages detached
- Don't warn on mixing sram and device pages
- Update kernel doc
- Add coherent page support to get pages
- Use DMA_FROM_DEVICE rather than DMA_BIDIRECTIONAL
- Add struct drm_gpusvm_vram and ops (Thomas)
- Update the range's seqno if the range is valid (Thomas)
- Remove the is_unmapped check before hmm_range_fault (Thomas)
- Use drm_pagemap (Thomas)
- Drop kfree_mapping (Thomas)
- dma mapp pages under notifier lock (Thomas)
- Remove ctx.prefault
- Remove ctx.mmap_locked
- Add ctx.check_pages
- s/vram/devmem (Thomas)
v3:
- Fix memory leak drm_gpusvm_range_get_pages
- Only migrate pages with same zdd on CPU fault
- Loop over al VMAs in drm_gpusvm_range_evict
- Make GPUSVM a drm level module
- GPL or MIT license
- Update main kernel doc (Thomas)
- Prefer foo() vs foo for functions in kernel doc (Thomas)
- Prefer functions over macros (Thomas)
- Use unsigned long vs u64 for addresses (Thomas)
- Use standard interval_tree (Thomas)
- s/drm_gpusvm_migration_put_page/drm_gpusvm_migration_unlock_put_page (Thomas)
- Drop err_out label in drm_gpusvm_range_find_or_insert (Thomas)
- Fix kernel doc in drm_gpusvm_range_free_pages (Thomas)
- Newlines between functions defs in header file (Thomas)
- Drop shall language in driver vfunc kernel doc (Thomas)
- Move some static inlines from head to C file (Thomas)
- Don't allocate pages under page lock in drm_gpusvm_migrate_populate_ram_pfn (Thomas)
- Change check_pages to a threshold
v4:
- Fix NULL ptr deref in drm_gpusvm_migrate_populate_ram_pfn (Thomas, Himal)
- Fix check pages threshold
- Check for range being unmapped under notifier lock in get pages (Testing)
- Fix characters per line
- Drop WRITE_ONCE for zdd->devmem_allocation assignment (Thomas)
- Use completion for devmem_allocation->detached (Thomas)
- Make GPU SVM depend on ZONE_DEVICE (CI)
- Use hmm_range_fault for eviction (Thomas)
- Drop zdd worker (Thomas)
v5:
- Select Kconfig deps (CI)
- Set device to NULL in __drm_gpusvm_migrate_to_ram (Matt Auld, G.G.)
- Drop Thomas's SoB (Thomas)
- Add drm_gpusvm_range_start/end/size helpers (Thomas)
- Add drm_gpusvm_notifier_start/end/size helpers (Thomas)
- Absorb drm_pagemap name changes (Thomas)
- Fix driver lockdep assert (Thomas)
- Move driver lockdep assert to static function (Thomas)
- Assert mmap lock held in drm_gpusvm_migrate_to_devmem (Thomas)
- Do not retry forever on eviction (Thomas)
v6:
- Fix drm_gpusvm_get_devmem_page alignment (Checkpatch)
- Modify Kconfig (CI)
- Compile out lockdep asserts (CI)
v7:
- Add kernel doc for flags fields (CI, Auld)
Cc: Simona Vetter <simona.vetter@ffwll.ch>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: <dri-devel@lists.freedesktop.org>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-7-matthew.brost@intel.com
Introduce drm_pagemap ops to map and unmap dma to VRAM resources. In the
local memory case it's a matter of merely providing an offset into the
device's physical address. For future p2p the map and unmap functions may
encode as needed.
Similar to how dma-buf works, let the memory provider (drm_pagemap) provide
the mapping functionality.
v3:
- Move to drm level include
v4:
- Fix kernel doc (G.G.)
v5:
- s/map_dma/device_map (Thomas)
- s/unmap_dma/device_unmap (Thomas)
v7:
- Fix kernel doc (CI, Auld)
- Drop P2P define (Thomas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-5-matthew.brost@intel.com
Add drm_gem_is_imported() that tests if a GEM object's buffer has
been imported. Update the GEM code accordingly.
GEM code usually tests for imports if import_attach has been set
in struct drm_gem_object. But attaching a dma-buf on import requires
a DMA-capable importer device, which is not the case for many serial
busses like USB or I2C. The new helper tests if a GEM object's dma-buf
has been created from the GEM object.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Anusha Srivatsa <asrivats@redhat.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250226172457.217725-2-tzimmermann@suse.de
Following the design direction communicated here:
https://lore.kernel.org/linux-mm/b7491378-defd-4f1c-31e2-29e4c77e2d67@amd.com/T/#ma918844aa8a6efe8768fdcda0c6590d5c93850c9
Export a LRU walker for driver shrinker use. The walker
initially supports only trylocking, since that's the
method used by shrinkes. The walker makes use of
scoped_guard() to allow exiting from the LRU walk loop
without performing any explicit unlocking or
cleanup.
v8:
- Split out from another patch.
- Use a struct for bool arguments to increase readability (Matt Brost).
- Unmap user-space cpu-mappings before shrinking pages.
- Explain non-fatal error codes (Matt Brost)
v10:
- Instead of using the existing helper, Wrap the interface inside out and
provide a loop to de-midlayer things the LRU iteration (Christian König).
- Removing the R-B by Matt Brost since the patch was significantly changed.
v11:
- Split the patch up to include just the LRU walk helper.
v12:
- Indent after scoped_guard() (Matt Brost)
v15:
- Adapt to new definition of scoped_guard()
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Dave Airlie <airlied@redhat.com>
Acked-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/intel-xe/20250305092220.123405-5-thomas.hellstrom@linux.intel.com
Provide a helper to shrink ttm_tt page-vectors on a per-page
basis. A ttm_backup backend could then in theory get away with
allocating a single temporary page for each struct ttm_tt.
This is accomplished by splitting larger pages before trying to
back them up.
In the future we could allow ttm_backup to handle backing up
large pages as well, but currently there's no benefit in
doing that, since the shmem backup backend would have to
split those anyway to avoid allocating too much temporary
memory, and if the backend instead inserts pages into the
swap-cache, those are split on reclaim by the core.
Due to potential backup- and recover errors, allow partially swapped
out struct ttm_tt's, although mark them as swapped out stopping them
from being swapped out a second time. More details in the ttm_pool.c
DOC section.
v2:
- A couple of cleanups and error fixes in ttm_pool_back_up_tt.
- s/back_up/backup/
- Add a writeback parameter to the exported interface.
v8:
- Use a struct for flags for readability (Matt Brost)
- Address misc other review comments (Matt Brost)
v9:
- Update the kerneldoc for the ttm_tt::backup field.
v10:
- Rebase.
v13:
- Rebase on ttm_backup interface change. Update kerneldoc.
- Rebase and adjust ttm_tt_is_swapped().
v15:
- Rebase on ttm_backup return value change.
- Rebase on previous restructuring of ttm_pool_alloc()
- Rework the ttm_pool backup interface (Christian König)
- Remove cond_resched() (Christian König)
- Get rid of the need to allocate an intermediate page array
when restoring a multi-order page (Christian König)
- Update documentation.
Cc: Christian König <christian.koenig@amd.com>
Cc: Somalapuram Amaranath <Amaranath.Somalapuram@amd.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <dri-devel@lists.freedesktop.org>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Christian Koenig <christian.koenig@amd.com>
Link: https://lore.kernel.org/intel-xe/20250305092220.123405-3-thomas.hellstrom@linux.intel.com
Provide a standalone shmem backup implementation.
Given the ttm_backup interface, this could
later on be extended to providing other backup
implementation than shmem, with one use-case being
GPU swapout to a user-provided fd.
v5:
- Fix a UAF. (kernel test robot, Dan Carptenter)
v6:
- Rename ttm_backup_shmem_copy_page() function argument
(Matthew Brost)
- Add some missing documentation
v8:
- Use folio_file_page to get to the page we want to writeback
instead of using the first page of the folio.
v13:
- Remove the base class abstraction (Christian König)
- Include ttm_backup_bytes_avail().
v14:
- Fix kerneldoc for ttm_backup_bytes_avail() (0-day)
- Work around casting of __randomize_layout struct pointer (0-day)
v15:
- Return negative error code from ttm_backup_backup_page()
(Christian König)
- Doc fixes. (Christian König).
Cc: Christian König <christian.koenig@amd.com>
Cc: Somalapuram Amaranath <Amaranath.Somalapuram@amd.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <dri-devel@lists.freedesktop.org>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/intel-xe/20250305092220.123405-2-thomas.hellstrom@linux.intel.com
UAPI Changes:
- Add mmap support for PCI memory barrier (Tejas, Matthew Auld)
- Enable integration with perf pmu, exposing event counters: for now, just
GT C6 residency (Vinay, Lucas)
- Add "survivability mode" to allow putting the driver in a state capable of
firmware upgrade on critical failures (Riana, Rodrigo)
- Add PXP HWDRM support and enable for compatible platforms:
Meteor Lake and Lunar Lake (Daniele, John Harrison)
- Expose package and vram temperature over hwmon subsystem (Raag, Badal, Rodrigo)
Cross-subsystem Changes:
- Backmege drm-next to synchronize with i915 display and other internal APIs
Display Changes (including i915):
- Device probe re-order to help with flicker-free boot (Maarten)
- Align watermark, hpd and dsm with i915 (Rodrigo)
- Better abstraction for d3cold (Rodrigo)
Driver Changes:
- Make sure changes to ccs_mode is with helper for gt sync reset (Maciej)
- Drop mmio_ext abstraction since it didn't prove useful in its current form
(Matt Roper)
- Reject BO eviction if BO is bound to current VM (Oak, Thomas Hellström)
- Add GuC Power Conservation debugfs (Rodrigo)
- L3 cache topology updates for Xe3 (Francois, Matt Atwood)
- Better logging about missing GuC logs (John Harrison)
- Better logging for hwconfig-related data availability (John Harrison)
- Tracepoint updates for xe_bo_create, xe_vm and xe_vma (Oak)
- Add missing SPDX licenses (Francois)
- Xe suballocator imporovements (Michal Wajdeczko)
- Improve logging for native vs SR-IOV driver mode (Satyanarayana)
- Make sure VF bootstrap is not attempted in execlist mode (Maarten)
- Add GuC Buffer Cache abstraction for some CTB H2G actions and use
during VF provisioning (Michal Wajdeczko)
- Better synchronization in gtidle for new users (Vinay)
- New workarounds for Panther Lake (Nirmoy, Vinay)
- PCI ID updates for Panther Lake (Matt Atwood)
- Enable SR-IOV for Panther Lake (Michal Wajdeczko)
- Update MAINTAINERS to stop directing xe changes to drm-misc (Lucas)
- New PCI IDs for Battle Mage (Shekhar)
- Better pagefault logging (Francois)
- SR-IOV fixes and refactors for past and new platforms (Michal Wajdeczko)
- Platform descriptor refactors and updates (Sai Teja)
- Add gt stats debugfs (Francois)
- Add guc_log debugfs to dump to dmesg (Lucas)
- Abstract per-platform LMTT availability (Piotr Piórkowski)
- Refactor VRAM manager location (Piotr Piórkowski)
- Add missing xe_pm_runtime_put when forcing wedged mode (Shuicheng)
- Fix possible lockup when forcing wedged mode (Xin Wang)
- Probe refactors to use cleanup actions with better error handling (Lucas)
- XE_IOCTL_DBG clarification for userspace (Maarten)
- Better xe_mmio initialization and abstraction (Ilia)
- Drop unnecessary GT lookup (Matt Roper)
- Skip client engine usage from fdinfo for VFs (Marcin Bernatowicz)
- Allow to test xe_sync_entry_parse with error injection (Priyanka)
- OA fix for polled read (Umesh)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/m3gbuh32wgiep43i4zxbyhxqbenvtgvtao5sczivlasj7tikwv@dmlba4bfg2ny
drm/i915 feature pull for v6.15:
Features and functionality:
- Enable DP 128b/132b SST DSC (Jani, Imre)
- Allow DSB to perform commits when VRR is enabled (Ville)
- Compute HDMI PLLs for SNPS/C10 PHYs for rates not in fixed tables (Ankit)
- Allow DSB usage when PSR is enabled on LNL+ (Jouni)
- Enable Panel Replay mode change without full modeset (Jouni)
- Enable async flips with compressed buffers on ICL+ (Ville)
- Support luminance based brightness control via DPCD for eDP (Suraj)
- Enable VRR enable/disable without full modeset (Mitul, Ankit)
- Add debugfs facility for force testing HDCP 1.4 (Suraj)
- Add scaler tracepoints, improve plane tracepoints (Ville)
- Improve DMC wakelock debugging facilities (Gustavo)
- Allow GuC SLPC default strategies on MTL+ for performance (Rodrigo)
- Provide more information on display faults (Ville)
Refactoring and cleanups:
- Continue conversions to struct intel_display (Ville, Jani, Suraj, Imre)
- Joiner and Y plane reorganization (Ville)
- Move HDCP debugfs to intel_hdcp.c (Jani)
- Clean up and unify LSPCON interfaces (Jani)
- Move code out of intel_display.c to reduce its size (Ville)
- Clean up and simplify DDI port enabling/disabling (Imre)
- Make LPT LP a dedicated PCH type, refactor (Jani)
- Simplify DSC range BPG offset calculation (Ankit)
- Scaler cleanups (Ville)
- Remove unused code from GVT (David Alan Gilbert)
- Improve plane debugging (Ville)
- DSB and VRR refactoring (Ville)
Fixes:
- Check if vblank is sufficient for DSC prefill and scaler (Mitul)
- Fix Mesa clear color alignment regression (Ville)
- Add missing TC DP PHY lane stagger delay (Imre)
- Fix DSB + VRR usage for PTL+ (Ville)
- Improve robustness of display VT-d workarounds (Ville)
- Fix platforms for dbuf tracker state service programming (Ravi)
- Fix DMC wakelock support conditions (Gustavo)
- Amend DMC wakelock register ranges (Gustavo)
- Disable the Common Primary Timing Generator (CMTG) (Gustavo)
- Enable C20 PHY SSC (Suraj)
- Add workaround for DKL PHY DP mode write (Nemesa)
- Fix build warnings on clamp() usage (Guenter Roeck, Ankit)
- Fix error handling while adding a connector (Imre)
- Avoid full modeset at probe on vblank delay mismatches (Ville)
- Fix encoder HDMI check for HDCP line rekeying (Suraj)
- Fix HDCP repeater authentication during topology change (Suraj)
- Handle display PHY power state reset for power savings (Mika)
- Fix typos all over the place (Nitin)
- Update HDMI TMDS C20 parameters for various platforms (Dnyaneshwar)
- Guarantee a minimum hblank time for 128b/132b and 8b/10b MST (Arun, Imre)
- Do not hardcode LSPCON settle timeout (Giedrius Statkevičius)
Xe driver changes:
- Re-use display vmas when possible (Maarten)
- Remove double pageflip (Maarten)
- Enable DP tunneling (Imre)
- Separate i915 and xe tracepoints (Ville)
DRM core changes:
- Increase DPCD eDP display control CAP size to 5 bytes (Suraj)
- Add DPCD eDP version 1.5 definition (Suraj)
- Add timeout parameter to drm_lspcon_set_mode() (Giedrius Statkevičius)
Merges:
- Backmerge drm-next (Jani)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/87h64j7b7n.fsf@intel.com
According to the DisplayPort standard, LTTPRs have two operating
modes:
- non-transparent - it replies to DPCD LTTPR field specific AUX
requests, while passes through all other AUX requests
- transparent - it passes through all AUX requests.
Switching between this two modes is done by the DPTX by issuing
an AUX write to the DPCD PHY_REPEATER_MODE register.
Add a generic helper that allows switching between these modes.
Also add a generic wrapper for the helper that handles the explicit
disabling of non-transparent mode and its disable->enable sequence
mentioned in the DP Standard v2.0 section 3.6.6.1. Do this in order
to move this handling out of the vendor specific driver implementation
into the generic framework.
Tested-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250203-drm-dp-msm-add-lttpr-transparent-mode-set-v5-1-c865d0e56d6e@linaro.org
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
User-space cursor-image data is encoded in ARBG8888, while hardware
supports ARGB4444. Implement the format conversion as part of the
format-helper framework, so that other drivers can benefit.
This allows to respect the damage area of the cursor update. In
previous code, all cursor image data had to be converted on each
update. Now, only the changed areas require an update. The hardware
image is always updated completely, as it is required for the
checksum update.
The format-conversion helper still contains the old implementation's
optimization of writing 2 output pixels at the same time.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250217122336.230067-3-tzimmermann@suse.de
Currently, DRM atomic uAPI allows only primary planes to be flipped
asynchronously. However, each driver might be able to perform async
flips in other different plane types. To enable drivers to set their own
restrictions on which type of plane they can or cannot flip, use the
existing atomic_async_check() from struct drm_plane_helper_funcs to
enhance this flexibility, thus allowing different plane types to be able
to do async flips as well.
Create a new parameter for the atomic_async_check(), `bool flip`. This
parameter is used to distinguish when this function is being called from
a plane update from a full page flip.
In order to prevent regressions and such, we keep the current policy: we
skip the driver check for the primary plane, because it is always
allowed to do async flips on it.
Signed-off-by: André Almeida <andrealmeid@igalia.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Christopher Snowhill <chris@kode54.net>
Tested-by: Christopher Snowhill <chris@kode54.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20250127-tonyk-async_flip-v12-1-0f7f8a8610d3@igalia.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Introduce device wedged event, which notifies userspace of 'wedged'
(hanged/unusable) state of the DRM device through a uevent. This is
useful especially in cases where the device is no longer operating as
expected and has become unrecoverable from driver context. Purpose of
this implementation is to provide drivers a generic way to recover the
device with the help of userspace intervention without taking any drastic
measures (like resetting or re-enumerating the full bus, on which the
underlying physical device is sitting) in the driver.
A 'wedged' device is basically a device that is declared dead by the
driver after exhausting all possible attempts to recover it from driver
context. The uevent is the notification that is sent to userspace along
with a hint about what could possibly be attempted to recover the device
from userspace and bring it back to usable state. Different drivers may
have different ideas of a 'wedged' device depending on hardware
implementation of the underlying physical device, and hence the vendor
agnostic nature of the event. It is up to the drivers to decide when they
see the need for device recovery and how they want to recover from the
available methods.
Driver prerequisites
--------------------
The driver, before opting for recovery, needs to make sure that the
'wedged' device doesn't harm the system as a whole by taking care of the
prerequisites. Necessary actions must include disabling DMA to system
memory as well as any communication channels with other devices. Further,
the driver must ensure that all dma_fences are signalled and any device
state that the core kernel might depend on is cleaned up. All existing
mmaps should be invalidated and page faults should be redirected to a
dummy page. Once the event is sent, the device must be kept in 'wedged'
state until the recovery is performed. New accesses to the device
(IOCTLs) should be rejected, preferably with an error code that resembles
the type of failure the device has encountered. This will signify the
reason for wedging, which can be reported to the application if needed.
Recovery
--------
Current implementation defines three recovery methods, out of which,
drivers can use any one, multiple or none. Method(s) of choice will be
sent in the uevent environment as ``WEDGED=<method1>[,..,<methodN>]`` in
order of less to more side-effects. If driver is unsure about recovery
or method is unknown (like soft/hard system reboot, firmware flashing,
physical device replacement or any other procedure which can't be
attempted on the fly), ``WEDGED=unknown`` will be sent instead.
Userspace consumers can parse this event and attempt recovery as per the
following expectations.
=============== ========================================
Recovery method Consumer expectations
=============== ========================================
none optional telemetry collection
rebind unbind + bind driver
bus-reset unbind + bus reset/re-enumeration + bind
unknown consumer policy
=============== ========================================
The only exception to this is ``WEDGED=none``, which signifies that the
device was temporarily 'wedged' at some point but was recovered from driver
context using device specific methods like reset. No explicit recovery is
expected from the consumer in this case, but it can still take additional
steps like gathering telemetry information (devcoredump, syslog). This is
useful because the first hang is usually the most critical one which can
result in consequential hangs or complete wedging.
Consumer prerequisites
----------------------
It is the responsibility of the consumer to make sure that the device or
its resources are not in use by any process before attempting recovery.
With IOCTLs erroring out, all device memory should be unmapped and file
descriptors should be closed to prevent leaks or undefined behaviour. The
idea here is to clear the device of all user context beforehand and set
the stage for a clean recovery.
Example
-------
Udev rule::
SUBSYSTEM=="drm", ENV{WEDGED}=="rebind", DEVPATH=="*/drm/card[0-9]",
RUN+="/path/to/rebind.sh $env{DEVPATH}"
Recovery script::
#!/bin/sh
DEVPATH=$(readlink -f /sys/$1/device)
DEVICE=$(basename $DEVPATH)
DRIVER=$(readlink -f $DEVPATH/driver)
echo -n $DEVICE > $DRIVER/unbind
echo -n $DEVICE > $DRIVER/bind
Customization
-------------
Although basic recovery is possible with a simple script, consumers can
define custom policies around recovery. For example, if the driver supports
multiple recovery methods, consumers can opt for the suitable one depending
on scenarios like repeat offences or vendor specific failures. Consumers
can also choose to have the device available for debugging or telemetry
collection and base their recovery decision on the findings. This is useful
especially when the driver is unsure about recovery or method is unknown.
v4: s/drm_dev_wedged/drm_dev_wedged_event
Use drm_info() (Jani)
Kernel doc adjustment (Aravind)
v5: Send recovery method with uevent (Lina)
v6: Access wedge_recovery_opts[] using helper function (Jani)
Use snprintf() (Jani)
v7: Convert recovery helpers into regular functions (Andy, Jani)
Aesthetic adjustments (Andy)
Handle invalid recovery method
v8: Allow sending multiple methods with uevent (Lucas, Michal)
static_assert() globally (Andy)
v9: Provide 'none' method for device reset (Christian)
Provide recovery opts using switch cases
v11: Log device reset (André)
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: André Almeida <andrealmeid@igalia.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250204070528.1919158-2-raag.jadav@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
