github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-05-23 06:31:58 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

drm/amdgpu: move guilty handling into ring resets

Browse Source 
Move guilty logic into the ring reset callbacks.  This
allows each ring reset callback to better handle fence
errors and force completions in line with the reset
behavior for each IP.  It also allows us to remove
the ring guilty callback since that logic now lives
in the reset callback.

Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Alex Deucher 2025-06-05 23:34:48 -04:00
parent 2dee58ca47
commit 43ca5eb94b
3 changed files with 3 additions and 51 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
View File

@ -91,7 +91,6 @@ 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;
bool set_error = false;
int idx, r;
if (!drm_dev_enter(adev_to_drm(adev), &idx)) {
@ -134,8 +133,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
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) {
bool is_guilty;
dev_err(adev->dev, "Starting %s ring reset\n",
s_job->sched->name);
@ -145,24 +142,9 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
*/
drm_sched_wqueue_stop(&ring->sched);
/* for engine resets, we need to reset the engine,
* but individual queues may be unaffected.
* check here to make sure the accounting is correct.
*/
if (ring->funcs->is_guilty)
is_guilty = ring->funcs->is_guilty(ring);
else
is_guilty = true;
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 (is_guilty)
atomic_inc(&ring->adev->gpu_reset_counter);
atomic_inc(&ring->adev->gpu_reset_counter);
drm_sched_wqueue_start(&ring->sched);
dev_err(adev->dev, "Ring %s reset succeeded\n",
ring->sched.name);
@ -173,8 +155,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
dev_err(adev->dev, "Ring %s reset failed\n", ring->sched.name);
}
if (!set_error)
dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
if (amdgpu_device_should_recover_gpu(ring->adev)) {
struct amdgpu_reset_context reset_context;

1
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
View File

@ -271,7 +271,6 @@ struct amdgpu_ring_funcs {
int (*reset)(struct amdgpu_ring *ring, unsigned int vmid,
struct amdgpu_fence *timedout_fence);
void (*emit_cleaner_shader)(struct amdgpu_ring *ring);
bool (*is_guilty)(struct amdgpu_ring *ring);
};
/**

30
drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
View File

@ -1656,30 +1656,10 @@ static bool sdma_v4_4_2_is_queue_selected(struct amdgpu_device *adev, uint32_t i
return (context_status & SDMA_GFX_CONTEXT_STATUS__SELECTED_MASK) != 0;
}
static bool sdma_v4_4_2_ring_is_guilty(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
uint32_t instance_id = ring->me;
return sdma_v4_4_2_is_queue_selected(adev, instance_id, false);
}
static bool sdma_v4_4_2_page_ring_is_guilty(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
uint32_t instance_id = ring->me;
if (!adev->sdma.has_page_queue)
return false;
return sdma_v4_4_2_is_queue_selected(adev, instance_id, true);
}
static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
bool is_guilty = ring->funcs->is_guilty(ring);
struct amdgpu_device *adev = ring->adev;
u32 id = ring->me;
int r;
@ -1690,13 +1670,7 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring,
amdgpu_amdkfd_suspend(adev, true);
r = amdgpu_sdma_reset_engine(adev, id);
amdgpu_amdkfd_resume(adev, true);
if (r)
return r;
if (is_guilty)
amdgpu_fence_driver_force_completion(ring);
return 0;
return r;
}
static int sdma_v4_4_2_stop_queue(struct amdgpu_ring *ring)
@ -2181,7 +2155,6 @@ static const struct amdgpu_ring_funcs sdma_v4_4_2_ring_funcs = {
.emit_reg_wait = sdma_v4_4_2_ring_emit_reg_wait,
.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
.reset = sdma_v4_4_2_reset_queue,
.is_guilty = sdma_v4_4_2_ring_is_guilty,
};
static const struct amdgpu_ring_funcs sdma_v4_4_2_page_ring_funcs = {
@ -2214,7 +2187,6 @@ static const struct amdgpu_ring_funcs sdma_v4_4_2_page_ring_funcs = {
.emit_reg_wait = sdma_v4_4_2_ring_emit_reg_wait,
.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
.reset = sdma_v4_4_2_reset_queue,
.is_guilty = sdma_v4_4_2_page_ring_is_guilty,
};
static void sdma_v4_4_2_set_ring_funcs(struct amdgpu_device *adev)