bybrooklyn/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-04-18 14:53:58 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: rework queue reset scheduler interaction

Browse Source 
Stopping the scheduler for queue reset is generally a good idea because
it prevents any worker from touching the ring buffer.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Christian König
2025-05-02 18:17:16 +02:00
committed by Alex Deucher
parent 787e2ce10f
commit 821aacb2dc
1 changed files with 20 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
View File

@@ -91,8 +91,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
struct amdgpu_job *job = to_amdgpu_job(s_job);
struct amdgpu_task_info *ti;
struct amdgpu_device *adev = ring->adev;
int idx;
int r;
bool set_error = false;
int idx, r;
if (!drm_dev_enter(adev_to_drm(adev), &idx)) {
dev_info(adev->dev, "%s - device unplugged skipping recovery on scheduler:%s",
@@ -136,10 +136,12 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
} else if (amdgpu_gpu_recovery && ring->funcs->reset) {
bool is_guilty;
dev_err(adev->dev, "Starting %s ring reset\n", s_job->sched->name);
/* stop the scheduler, but don't mess with the
* bad job yet because if ring reset fails
* we'll fall back to full GPU reset.
dev_err(adev->dev, "Starting %s ring reset\n",
s_job->sched->name);
/*
* Stop the scheduler to prevent anybody else from touching the
* ring buffer.
*/
drm_sched_wqueue_stop(&ring->sched);
@@ -152,26 +154,29 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
else
is_guilty = true;
if (is_guilty)
if (is_guilty) {
dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
set_error = true;
}
r = amdgpu_ring_reset(ring, job->vmid, NULL);
if (!r) {
if (amdgpu_ring_sched_ready(ring))
drm_sched_stop(&ring->sched, s_job);
if (is_guilty) {
atomic_inc(&ring->adev->gpu_reset_counter);
amdgpu_fence_driver_force_completion(ring);
}
if (amdgpu_ring_sched_ready(ring))
drm_sched_start(&ring->sched, 0);
dev_err(adev->dev, "Ring %s reset succeeded\n", ring->sched.name);
drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE);
drm_sched_wqueue_start(&ring->sched);
dev_err(adev->dev, "Ring %s reset succeeded\n",
ring->sched.name);
drm_dev_wedged_event(adev_to_drm(adev),
DRM_WEDGE_RECOVERY_NONE);
goto exit;
}
dev_err(adev->dev, "Ring %s reset failure\n", ring->sched.name);
dev_err(adev->dev, "Ring %s reset failed\n", ring->sched.name);
}
dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
if (!set_error)
dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
if (amdgpu_device_should_recover_gpu(ring->adev)) {
struct amdgpu_reset_context reset_context;