From 77cc0da39c7ce203cd3ce6bc5696421947a979d7 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 27 May 2025 21:35:00 -0400 Subject: drm/amdgpu: track ring state associated with a fence MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We need to know the wptr and sequence number associated with a fence so that we can re-emit the unprocessed state after a ring reset. Pre-allocate storage space for the ring buffer contents and add helpers to save off and re-emit the unprocessed state so that it can be re-emitted after the queue is reset. Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_job.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 2b58e353cca1..5cb7bf9420f7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -90,8 +90,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched); struct amdgpu_job *job = to_amdgpu_job(s_job); struct drm_wedge_task_info *info = NULL; - struct amdgpu_task_info *ti; struct amdgpu_device *adev = ring->adev; + struct amdgpu_task_info *ti; int idx, r; if (!drm_dev_enter(adev_to_drm(adev), &idx)) { @@ -134,7 +134,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) } else if (amdgpu_gpu_recovery && ring->funcs->reset) { dev_err(adev->dev, "Starting %s ring reset\n", s_job->sched->name); - r = amdgpu_ring_reset(ring, job->vmid, NULL); + r = amdgpu_ring_reset(ring, job->vmid, &job->hw_fence); if (!r) { atomic_inc(&ring->adev->gpu_reset_counter); dev_err(adev->dev, "Ring %s reset succeeded\n", -- cgit v1.2.3 From 6ac55eab4fc41e0ea80f9064945e4340f13d8b5c Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 15 Jul 2025 11:55:05 -0400 Subject: drm/amdgpu: move reset support type checks into the caller Rather than checking in the callbacks, check if the reset type is supported in the caller. Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_job.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 5cb7bf9420f7..32a08529307d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -112,6 +112,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) amdgpu_job_core_dump(adev, job); if (amdgpu_gpu_recovery && + amdgpu_ring_is_reset_type_supported(ring, AMDGPU_RESET_TYPE_SOFT_RESET) && amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { dev_err(adev->dev, "ring %s timeout, but soft recovered\n", s_job->sched->name); @@ -131,7 +132,9 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) /* attempt a per ring reset */ if (unlikely(adev->debug_disable_gpu_ring_reset)) { dev_err(adev->dev, "Ring reset disabled by debug mask\n"); - } else if (amdgpu_gpu_recovery && ring->funcs->reset) { + } else if (amdgpu_gpu_recovery && + amdgpu_ring_is_reset_type_supported(ring, AMDGPU_RESET_TYPE_PER_QUEUE) && + ring->funcs->reset) { dev_err(adev->dev, "Starting %s ring reset\n", s_job->sched->name); r = amdgpu_ring_reset(ring, job->vmid, &job->hw_fence); -- cgit v1.2.3