kernel/linux.git/include/drm/gpu_scheduler.h, branch v5.15.209

drm/sched: Allow using a dedicated workqueue for the timeout/fault tdr

2021-07-01T06:53:25+00:00

Mali Midgard/Bifrost GPUs have 3 hardware queues but only a global GPU reset. This leads to extra complexity when we need to synchronize timeout works with the reset work. One solution to address that is to have an ordered workqueue at the driver level that will be used by the different schedulers to queue their timeout work. Thanks to the serialization provided by the ordered workqueue we are guaranteed that timeout handlers are executed sequentially, and can thus easily reset the GPU from the timeout handler without extra synchronization. v5: * Add a new paragraph to the timedout_job() method v3: * New patch v4: * Actually use the timeout_wq to queue the timeout work Suggested-by: Daniel Vetter Signed-off-by: Boris Brezillon Reviewed-by: Steven Price Reviewed-by: Lucas Stach Acked-by: Daniel Vetter Acked-by: Christian König Cc: Qiang Yu Cc: Emma Anholt Cc: Alex Deucher Cc: "Christian König" Link: https://patchwork.freedesktop.org/patch/msgid/20210630062751.2832545-3-boris.brezillon@collabora.com

drm/sched: Document what the timedout_job method should do

2021-07-01T06:53:25+00:00

The documentation is a bit vague and doesn't really describe what the ->timedout_job() is expected to do. Let's add a few more details. v5: * New patch Suggested-by: Daniel Vetter Signed-off-by: Boris Brezillon Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210630062751.2832545-2-boris.brezillon@collabora.com

drm/sched: Fix inverted comment for hang_limit

2021-06-03T08:32:49+00:00

The hang_limit is the threshold after which the kernel no longer attempts to schedule a job. Its documentation stated the opposite due to a typo. Correct the wording to indicate the actual purpose of the field. Signed-off-by: Alyssa Rosenzweig Cc: David Airlie Cc: Daniel Vetter Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210528235152.38447-1-alyssa.rosenzweig@collabora.com

drm/amd/amdgpu implement tdr advanced mode

2021-04-09T20:45:45+00:00

[Why] Previous tdr design treats the first job in job_timeout as the bad job. But sometimes a later bad compute job can block a good gfx job and cause an unexpected gfx job timeout because gfx and compute ring share internal GC HW mutually. [How] This patch implements an advanced tdr mode.It involves an additinal synchronous pre-resubmit step(Step0 Resubmit) before normal resubmit step in order to find the real bad job. 1. At Step0 Resubmit stage, it synchronously submits and pends for the first job being signaled. If it gets timeout, we identify it as guilty and do hw reset. After that, we would do the normal resubmit step to resubmit left jobs. 2. For whole gpu reset(vram lost), do resubmit as the old way. v2: squash in build fix (Alex) Signed-off-by: Jack Zhang Reviewed-by: Andrey Grodzovsky Signed-off-by: Alex Deucher

drm/sched: add missing member documentation

2021-04-08T12:59:45+00:00

Just fix a warning. Signed-off-by: Christian König Reported-by: Stephen Rothwell Fixes: f2f12eb9c32b ("drm/scheduler: provide scheduler score externally") Reviewed-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20210401125213.138855-1-christian.koenig@amd.com

drm/scheduler: provide scheduler score externally

2021-02-05T09:47:11+00:00

Allow multiple schedulers to share the load balancing score. This is useful when one engine has different hw rings. Signed-off-by: Christian König Reviewed-and-Tested-by: Leo Liu Link: https://patchwork.freedesktop.org/patch/msgid/20210204144405.2737-1-christian.koenig@amd.com

drm/scheduler: Job timeout handler returns status (v3)

2021-01-29T10:30:22+00:00

This patch does not change current behaviour. The driver's job timeout handler now returns status indicating back to the DRM layer whether the device (GPU) is no longer available, such as after it's been unplugged, or whether all is normal, i.e. current behaviour. All drivers which make use of the drm_sched_backend_ops' .timedout_job() callback have been accordingly renamed and return the would've-been default value of DRM_GPU_SCHED_STAT_NOMINAL to restart the task's timeout timer--this is the old behaviour, and is preserved by this patch. v2: Use enum as the status of a driver's job timeout callback method. v3: Return scheduler/device information, rather than task information. Cc: Alexander Deucher Cc: Andrey Grodzovsky Cc: Christian König Cc: Daniel Vetter Cc: Lucas Stach Cc: Russell King Cc: Christian Gmeiner Cc: Qiang Yu Cc: Rob Herring Cc: Tomeu Vizoso Cc: Steven Price Cc: Alyssa Rosenzweig Cc: Eric Anholt Reported-by: kernel test robot Signed-off-by: Luben Tuikov Acked-by: Alyssa Rosenzweig Acked-by: Christian König Acked-by: Steven Price Signed-off-by: Christian König Link: https://patchwork.freedesktop.org/patch/415095/

drm/sched: Add missing structure comment

2020-12-10T12:33:41+00:00

Add a missing structure comment for the recently added @list member. Cc: Stephen Rothwell Cc: Daniel Vetter Cc: Christian König Fixes: 8935ff00e3b1 ("drm/scheduler: "node" --> "list"") Reported-by: Stephen Rothwell Signed-off-by: Luben Tuikov Reviewed-by: Christian König Signed-off-by: Christian König Link: https://patchwork.freedesktop.org/patch/406546/

gpu/drm: ring_mirror_list --> pending_list

2020-12-08T13:38:03+00:00

Rename "ring_mirror_list" to "pending_list", to describe what something is, not what it does, how it's used, or how the hardware implements it. This also abstracts the actual hardware implementation, i.e. how the low-level driver communicates with the device it drives, ring, CAM, etc., shouldn't be exposed to DRM. The pending_list keeps jobs submitted, which are out of our control. Usually this means they are pending execution status in hardware, but the latter definition is a more general (inclusive) definition. Signed-off-by: Luben Tuikov Acked-by: Christian König Link: https://patchwork.freedesktop.org/patch/405573/ Cc: Alexander Deucher Cc: Andrey Grodzovsky Cc: Christian König Cc: Daniel Vetter Signed-off-by: Christian König

drm/scheduler: "node" --> "list"

2020-12-08T13:37:55+00:00

Rename "node" to "list" in struct drm_sched_job, in order to make it consistent with what we see being used throughout gpu_scheduler.h, for instance in struct drm_sched_entity, as well as the rest of DRM and the kernel. Signed-off-by: Luben Tuikov Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/403515/ Cc: Alexander Deucher Cc: Andrey Grodzovsky Cc: Christian König Cc: Daniel Vetter Signed-off-by: Christian König