*** gpu recover patches series v2 ***
Subsystems (2)
cover *** gpu recover patches series v2 ***
v2 series:
fixed some logic error in "imple job skip feature" merge two patches into "implement new GPU recover(v3)"
Monk Liu (7):
amd/scheduler:imple job skip feature(v2) drm/amdgpu:implement new GPU recover(v3) drm/amdgpu:cleanup in_sriov_reset and lock_reset drm/amdgpu:cleanup ucode_init_bo drm/amdgpu:block kms open during gpu_reset drm/amdgpu/sriov:fix memory leak in psp_load_fw drm/amdgpu:fix random missing of FLR NOTIFY
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 9 +- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 311 ++++++++++++-------------- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 10 +- drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 14 +- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 3 + drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 22 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 2 - drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 2 - drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 6 +- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 6 +- drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 16 +- drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 2 +- drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 54 +++-- drivers/gpu/drm/amd/scheduler/gpu_scheduler.h | 2 +- 16 files changed, 236 insertions(+), 229 deletions(-)
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1509013827-8180-1-git-send-email-Monk.Liu-5C7GfCeVMHo@public.gmane.org
PATCH 1/7 amd/scheduler:imple job skip feature(v2)
jobs are skipped under two cases
1)when the entity behind this job marked guilty, the job poped from this entity's queue will be dropped in sched_main loop.
2)in job_recovery(), skip the scheduling job if its karma detected above limit, and also skipped as well for other jobs sharing the same fence context. this approach is becuase job_recovery() cannot access job->entity due to entity may already dead.
v2:
some logic fix
with this feature we can introduce new gpu recover feature.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 9 +++-- drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 54 ++++++++++++++++++++------- drivers/gpu/drm/amd/scheduler/gpu_scheduler.h | 2 +- 3 files changed, 47 insertions(+), 18 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +5 -4
@@ -177,7 +177,7 @@ static struct dma_fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)return fence; } -static struct dma_fence *amdgpu_job_run (struct amd_sched_job *sched_job) +static struct dma_fence *amdgpu_job_run (struct amd_sched_job *sched_job,bool skip) {struct dma_fence *fence =NULL ;struct amdgpu_device *adev;
@@ -194,10 +194,11 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)BUG_ON (amdgpu_sync_peek_fence (&job->sync,NULL ));trace_amdgpu_sched_run_job (job); -/* skip ib schedule when vram is lost */ -if (job->vram_lost_counter !=atomic_read (&adev->vram_lost_counter)) { + +if (skip || job->vram_lost_counter !=atomic_read (&adev->vram_lost_counter)) { +/* skip ib schedule if looks needed, and set error */ dma_fence_set_error (&job->base.s_fence->finished, -ECANCELED ); -DRM_ERROR ("Skip scheduling IBs!\n" ); +DRM_INFO ("Skip scheduling IBs!\n" ); }else { r =amdgpu_ib_schedule (job->ring, job->num_ibs, job->ibs, job, &fence);
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +41 -13
116 lines not on this page · raw message
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +1 -1
@@ -126,7 +126,7 @@ static inline bool amd_sched_invalidate_job(struct amd_sched_job *s_job, int thr*/ struct amd_sched_backend_ops {struct dma_fence *(*dependency)(struct amd_sched_job *sched_job); -struct dma_fence *(*run_job)(struct amd_sched_job *sched_job); +struct dma_fence *(*run_job)(struct amd_sched_job *sched_job,bool skip);void (*timedout_job)(struct amd_sched_job *sched_job);void (*free_job)(struct amd_sched_job *sched_job); };
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1509013827-8180-2-git-send-email-Monk.Liu-5C7GfCeVMHo@public.gmane.org
Re: [PATCH 1/7] amd/scheduler:imple job skip feature(v2)
Am 26.10.2017 um 12:30 schrieb Monk Liu:
Quoted 60 lines
jobs are skipped under two cases
1)when the entity behind this job marked guilty, the job poped from this entity's queue will be dropped insched_mainloop.2)in
job_recovery(), skip the scheduling job if its karma detected above limit, and also skipped as well for other jobs sharing the same fence context. this approach is becuasejob_recovery()cannot accessjob->entitydue to entity may already dead.v2:
some logic fixwith this feature we can introduce new gpu recover feature.
Change-Id I268b1c752c94e6ecd4ea78c87eb226ea3f52908aSigned-off-by Monk Liu <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 9 +++-- drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 54 ++++++++++++++++++++------- drivers/gpu/drm/amd/scheduler/gpu_scheduler.h | 2 +- 3 files changed, 47 insertions(+), 18 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +5
-4@@ -177,7 +177,7 @@ static struct dma_fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)return fence; } -static struct dma_fence *amdgpu_job_run (struct amd_sched_job *sched_job) +static struct dma_fence *amdgpu_job_run (struct amd_sched_job *sched_job,bool skip) {struct dma_fence *fence =NULL ;struct amdgpu_device *adev;@@ -194,10 +194,11 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)BUG_ON (amdgpu_sync_peek_fence (&job->sync,NULL ));trace_amdgpu_sched_run_job (job); -/* skip ib schedule when vram is lost */ -if (job->vram_lost_counter !=atomic_read (&adev->vram_lost_counter)) { + +if (skip || job->vram_lost_counter !=atomic_read (&adev->vram_lost_counter)) { +/* skip ib schedule if looks needed, and set error */ dma_fence_set_error (&job->base.s_fence->finished, -ECANCELED ); -DRM_ERROR ("Skip scheduling IBs!\n" ); +DRM_INFO ("Skip scheduling IBs!\n" ); }else { r =amdgpu_ib_schedule (job->ring, job->num_ibs, job->ibs, job, &fence);drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +2
-0@@ -330,6 +330,28 @@ static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity)return false; } +static void amd_sched_job_fake_signal (struct amd_sched_job *job) +{
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity) · line 344
Quoted 10 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +10
-0+struct amd_sched_fence *s_fence = job->s_fence; +struct amd_gpu_scheduler *sched = job->sched; +struct amd_sched_entity *entity = job->s_entity; + +dma_fence_set_error (&s_fence->finished, -ECANCELED ); + +/* fake signaling the scheduled fence */ +atomic_inc (&sched->hw_rq_count); +amd_sched_fence_scheduled (s_fence); +wake_up (&sched->job_scheduled);
Unnecessary, we know that the scheduler is already awake because it is processing this function.
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity) · line 348
Quoted 4 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +4
-0+ +/* fake signaling the finished fence */ + job->s_entity =NULL ; +spsc_queue_pop (&entity->job_queue);
That code isn't up to date any more, Andrey removed job->s_entity yesterday.
Please rebase on amd-staging-drm-next before resending.
Quoted 10 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +6
-0+ +amd_sched_process_job (NULL , &s_fence->cb); +dma_fence_put (&s_fence->finished); + sched->ops->free_job (job); +} +static struct amd_sched_job *amd_sched_entity_pop_job (struct amd_sched_entity *entity) {
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c amd_sched_entity_pop_job(struct amd_sched_entity *entity) · line 373
Quoted 8 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +5
-0@@ -344,6 +366,11 @@ amd_sched_entity_pop_job(struct amd_sched_entity *entity)if (amd_sched_entity_add_dependency_cb (entity))return NULL ; +if (entity->guilty &&atomic_read (entity->guilty)) { +amd_sched_job_fake_signal (sched_job); +return NULL ; + } +
Better move this after spsc_queue_pop below and remove the extra spsc_queue_pop from amd_sched_job_fake_signal.
Quoted 50 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +6
-9sched_job->s_entity =NULL ;spsc_queue_pop (&entity->job_queue);return sched_job;@@ -441,13 +468,6 @@ static void amd_sched_job_timedout(struct work_struct *work) job->sched->ops->timedout_job (job); } -static void amd_sched_set_guilty (struct amd_sched_job *s_job) -{ -if (atomic_inc_return (&s_job->karma) > s_job->sched->hang_limit) -if (s_job->s_entity->guilty) -atomic_set (s_job->s_entity->guilty,1 ); -} -void amd_sched_hw_job_reset (struct amd_gpu_scheduler *sched,struct amd_sched_job *bad) {struct amd_sched_job *s_job;@@ -466,7 +486,7 @@ void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched, struct amd_sched_jo }spin_unlock (&sched->job_list_lock); -if (bad) { +if (bad &&atomic_inc_return (&bad->karma) > bad->sched->hang_limit) {bool found = false;for (i =AMD_SCHED_PRIORITY_MIN ; i <AMD_SCHED_PRIORITY_MAX ; i++ ) {@@ -476,7 +496,8 @@ void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched, struct amd_sched_jolist_for_each_entry_safe (entity, tmp, &rq->entities, list) {if (bad->s_fence->scheduled.context == entity->fence_context) { found = true; -amd_sched_set_guilty (bad); +if (entity->guilty) +atomic_set (entity->guilty,1 );break ; } }@@ -499,6 +520,7 @@ void amd_sched_job_kickout(struct amd_sched_job *s_job)void amd_sched_job_recovery (struct amd_gpu_scheduler *sched) {struct amd_sched_job *s_job, *tmp; +bool found_guilty = false;int r;spin_lock (&sched->job_list_lock);@@ -510,9 +532,17 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched)list_for_each_entry_safe (s_job, tmp, &sched->ring_mirror_list, node) {struct amd_sched_fence *s_fence = s_job->s_fence;struct dma_fence *fence; +bool skip; +uint64_t guilty_context;
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c void amd_sched_job_recovery(struct amd_gpu_scheduler *sched) · line 545
Quoted 10 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +7
-1+ +if (!found_guilty &&atomic_read (&s_job->karma) > sched->hang_limit) { + found_guilty = true; + guilty_context = s_job->s_fence->scheduled.context; + } + skip = (found_guilty && s_job->s_fence->scheduled.context == guilty_context);spin_unlock (&sched->job_list_lock); - fence = sched->ops->run_job (s_job); + fence = sched->ops->run_job (s_job, skip);
As far as I can see you can use amd_sched_job_fake_signal() here as well, no need for the extra skip parameter to run_job().
Regards,
Christian.
Quoted 33 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +1
-3atomic_inc (&sched->hw_rq_count);if (fence) { s_fence->parent =dma_fence_get (fence);@@ -525,7 +555,6 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched) r);dma_fence_put (fence); }else { -DRM_ERROR ("Failed to run job!\n" );amd_sched_process_job (NULL , &s_fence->cb); }spin_lock (&sched->job_list_lock);@@ -650,7 +679,7 @@ static int amd_sched_main(void *param)atomic_inc (&sched->hw_rq_count);amd_sched_job_begin (sched_job); - fence = sched->ops->run_job (sched_job); + fence = sched->ops->run_job (sched_job, false);amd_sched_fence_scheduled (s_fence);if (fence) {@@ -664,7 +693,6 @@ static int amd_sched_main(void *param) r);dma_fence_put (fence); }else { -DRM_ERROR ("Failed to run job!\n" );amd_sched_process_job (NULL , &s_fence->cb); }drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +0
-0
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h static inline bool amd_sched_invalidate_job(struct amd_sched_job *s_job, int thr · line 132
Quoted 8 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +1
-1@@ -126,7 +126,7 @@ static inline bool amd_sched_invalidate_job(struct amd_sched_job *s_job, int thr*/ struct amd_sched_backend_ops {struct dma_fence *(*dependency)(struct amd_sched_job *sched_job); -struct dma_fence *(*run_job)(struct amd_sched_job *sched_job); +struct dma_fence *(*run_job)(struct amd_sched_job *sched_job,bool skip);void (*timedout_job)(struct amd_sched_job *sched_job);void (*free_job)(struct amd_sched_job *sched_job); };
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): a126acf5-1023-81c1-bebb-fe28be8f525f-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org
RE: [PATCH 1/7] amd/scheduler:imple job skip feature(v2)
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity) · line 344
Quoted 6 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +6
-0+dma_fence_set_error (&s_fence->finished, -ECANCELED ); + +/* fake signaling the scheduled fence */ +atomic_inc (&sched->hw_rq_count); +amd_sched_fence_scheduled (s_fence); +wake_up (&sched->job_scheduled);
Unnecessary, we know that the scheduler is already awake because it is processing this function.
[ml] WHAT ??? this wake_up operate on job_scheduled, like the one at the bottom of sched_main(), It is used to wake up the thread waiting in "sched_entity_fini" on this "sched->job_scheduled", I don't understand why not necessary
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c void amd_sched_job_recovery(struct amd_gpu_scheduler *sched) · line 545
Quoted 8 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +5
-1+ guilty_context = s_job->s_fence->scheduled.context; + } + skip = (found_guilty && s_job->s_fence->scheduled.context == +guilty_context);spin_unlock (&sched->job_list_lock); - fence = sched->ops->run_job (s_job); + fence = sched->ops->run_job (s_job, skip);
As far as I can see you can use amd_sched_job_fake_signal() here as well, no need for the extra skip parameter to run_job().
[ML] no you still didn't get my point, in sched_main() we use fake_signal() because the job hadn't been linked in mirror list, so "job_finish()" Cannot be invoked for those jobs,
But for job_recovery(), it go through mirror list and only focus on jobs from that list, thus all jobs must be handled by "job_finis()" callback, So we need let those jobs go through the run_job() again, only except that it didn't need to submit to ring really , that way the job_finish() callback Can handle that job safely and seemless
BR Monk
-----Original Message-----
From: Christian König [mailto:[email protected]]
Sent: 2017年10月26日 18:52
To: Liu, Monk <[email protected]>; [email protected]
Subject: Re: [PATCH 1/7] amd/scheduler:imple job skip feature(v2)
Am 26.10.2017 um 12:30 schrieb Monk Liu:
Quoted 63 lines
jobs are skipped under two cases
1)when the entity behind this job marked guilty, the job poped from this entity's queue will be dropped insched_mainloop.2)in
job_recovery(), skip the scheduling job if its karma detected above limit, and also skipped as well for other jobs sharing the same fence context. this approach is becuasejob_recovery()cannot accessjob->entitydue to entity may already dead.v2:
some logic fixwith this feature we can introduce new gpu recover feature.
Change-Id I268b1c752c94e6ecd4ea78c87eb226ea3f52908aSigned-off-by Monk Liu <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 9 +++-- drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 54 ++++++++++++++++++++------- drivers/gpu/drm/amd/scheduler/gpu_scheduler.h | 2 +- 3 files changed, 47 insertions(+), 18 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +6
-4@@ -177,7 +177,7 @@ static struct dma_fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)return fence; } -static struct dma_fence *amdgpu_job_run (struct amd_sched_job *sched_job) +static struct dma_fence *amdgpu_job_run (struct amd_sched_job +*sched_job,bool skip) {struct dma_fence *fence =NULL ;struct amdgpu_device *adev;@@ -194,10 +194,11 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)BUG_ON (amdgpu_sync_peek_fence (&job->sync,NULL ));trace_amdgpu_sched_run_job (job); -/* skip ib schedule when vram is lost */ -if (job->vram_lost_counter !=atomic_read (&adev->vram_lost_counter)) { + +if (skip || job->vram_lost_counter !=atomic_read (&adev->vram_lost_counter)) { +/* skip ib schedule if looks needed, and set error */ dma_fence_set_error (&job->base.s_fence->finished, -ECANCELED ); -DRM_ERROR ("Skip scheduling IBs!\n" ); +DRM_INFO ("Skip scheduling IBs!\n" ); }else { r =amdgpu_ib_schedule (job->ring, job->num_ibs, job->ibs, job, &fence);drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +1
-0@@ -330,6 +330,28 @@ static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity)return false; } +static void amd_sched_job_fake_signal (struct amd_sched_job *job) {
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity) · line 343
Quoted 10 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +10
-0+struct amd_sched_fence *s_fence = job->s_fence; +struct amd_gpu_scheduler *sched = job->sched; +struct amd_sched_entity *entity = job->s_entity; + +dma_fence_set_error (&s_fence->finished, -ECANCELED ); + +/* fake signaling the scheduled fence */ +atomic_inc (&sched->hw_rq_count); +amd_sched_fence_scheduled (s_fence); +wake_up (&sched->job_scheduled);
Unnecessary, we know that the scheduler is already awake because it is processing this function.
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity) · line 348
Quoted 4 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +4
-0+ +/* fake signaling the finished fence */ + job->s_entity =NULL ; +spsc_queue_pop (&entity->job_queue);
That code isn't up to date any more, Andrey removed job->s_entity yesterday.
Please rebase on amd-staging-drm-next before resending.
Quoted 10 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +6
-0+ +amd_sched_process_job (NULL , &s_fence->cb); +dma_fence_put (&s_fence->finished); + sched->ops->free_job (job); +} +static struct amd_sched_job *amd_sched_entity_pop_job (struct amd_sched_entity *entity) {
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c amd_sched_entity_pop_job(struct amd_sched_entity *entity) · line 373
Quoted 8 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +5
-0@@ -344,6 +366,11 @@ amd_sched_entity_pop_job(struct amd_sched_entity *entity)if (amd_sched_entity_add_dependency_cb (entity))return NULL ; +if (entity->guilty &&atomic_read (entity->guilty)) { +amd_sched_job_fake_signal (sched_job); +return NULL ; + } +
Better move this after spsc_queue_pop below and remove the extra spsc_queue_pop from amd_sched_job_fake_signal.
Quoted 51 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +2
-7sched_job->s_entity =NULL ;spsc_queue_pop (&entity->job_queue);return sched_job;@@ -441,13 +468,6 @@ static void amd_sched_job_timedout(struct work_struct *work) job->sched->ops->timedout_job (job); } -static void amd_sched_set_guilty(struct amd_sched_job *s_job) -{ -if (atomic_inc_return (&s_job->karma) > s_job->sched->hang_limit) -if (s_job->s_entity->guilty) -atomic_set (s_job->s_entity->guilty,1 ); -} -void amd_sched_hw_job_reset (struct amd_gpu_scheduler *sched,struct amd_sched_job *bad) {struct amd_sched_job *s_job;@@ -466,7 +486,7 @@ void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched, struct amd_sched_jo }spin_unlock (&sched->job_list_lock); -if (bad) { +if (bad &&atomic_inc_return (&bad->karma) > bad->sched->hang_limit) +{bool found = false;for (i =AMD_SCHED_PRIORITY_MIN ; i <AMD_SCHED_PRIORITY_MAX ; i++ ){ @@ -476,7 +496,8 @@ void amd_sched_hw_job_reset(struct
amd_gpu_scheduler*sched, structamd_sched_jo
list_for_each_entry_safe(entity, tmp, &rq->entities, list){
if (bad->s_fence->scheduled.context==entity->fence_context) {
found = true;drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +6
-1-amd_sched_set_guilty (bad); +if (entity->guilty) +atomic_set (entity->guilty,1 );break ; } }@@ -499,6 +520,7 @@ void amd_sched_job_kickout(struct amd_sched_job *s_job)void amd_sched_job_recovery (struct amd_gpu_scheduler *sched) {struct amd_sched_job *s_job, *tmp; +bool found_guilty = false;int r;spin_lock (&sched->job_list_lock);@@ -510,9 +532,17 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched)list_for_each_entry_safe (s_job, tmp, &sched->ring_mirror_list, node) {struct amd_sched_fence *s_fence = s_job->s_fence;struct dma_fence *fence; +bool skip; +uint64_t guilty_context; +
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c void amd_sched_job_recovery(struct amd_gpu_scheduler *sched) · line 546
Quoted 10 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +7
-1+if (!found_guilty &&atomic_read (&s_job->karma) > sched->hang_limit) { + found_guilty = true; + guilty_context = s_job->s_fence->scheduled.context; + } + skip = (found_guilty && s_job->s_fence->scheduled.context == +guilty_context);spin_unlock (&sched->job_list_lock); - fence = sched->ops->run_job (s_job); + fence = sched->ops->run_job (s_job, skip);
As far as I can see you can use amd_sched_job_fake_signal() here as well, no need for the extra skip parameter to run_job().
Regards,
Christian.
Quoted 34 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +0
-0atomic_inc (&sched->hw_rq_count);if (fence) { s_fence->parent = dma_fence_get(fence); @@ -525,7 +555,6 @@ void
amd_sched_job_recovery(struct amd_gpu_scheduler *sched)
r);
dma_fence_put(fence);
} else {drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +1
-3-DRM_ERROR ("Failed to run job!\n" );amd_sched_process_job (NULL , &s_fence->cb); }spin_lock (&sched->job_list_lock);@@ -650,7 +679,7 @@ static int amd_sched_main(void *param)atomic_inc (&sched->hw_rq_count);amd_sched_job_begin (sched_job); - fence = sched->ops->run_job (sched_job); + fence = sched->ops->run_job (sched_job, false);amd_sched_fence_scheduled (s_fence);if (fence) {@@ -664,7 +693,6 @@ static int amd_sched_main(void *param) r);dma_fence_put (fence); }else { -DRM_ERROR ("Failed to run job!\n" );amd_sched_process_job (NULL , &s_fence->cb); }drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +0
-0
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h static inline bool amd_sched_invalidate_job(struct amd_sched_job *s_job, int thr · line 132
Quoted 9 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +2
-1@@ -126,7 +126,7 @@ static inline bool amd_sched_invalidate_job(struct amd_sched_job *s_job, int thr*/ struct amd_sched_backend_ops {struct dma_fence *(*dependency)(struct amd_sched_job *sched_job); -struct dma_fence *(*run_job)(struct amd_sched_job *sched_job); +struct dma_fence *(*run_job)(struct amd_sched_job *sched_job,bool +skip);void (*timedout_job)(struct amd_sched_job *sched_job);void (*free_job)(struct amd_sched_job *sched_job); };
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): BLUPR12MB04499876C7CC8573D9A0D2F484450-7LeqcoF/[email protected]
RE: [PATCH 1/7] amd/scheduler:imple job skip feature(v2)
The simple way I can think of to remove the @skip param for run_job is that we introduce a new member "skip" in sched_job, and remove fake_signal() function, So we always set "skip" in sched_job before run_job(), and in run_job() we skip the real ib_schedule if found job->skip == true,
That way the skipping logic can be unified, but that satisfies the efficiency because:
my current approach won't do begin_job(), won't link job in mirror list, etc.... but above approach actually go through all steps
what do you think
BR Monk
-----Original Message-----
From: Liu, Monk
Sent: 2017年10月26日 19:07
To: Koenig, Christian <[email protected]>; [email protected]
Subject: RE: [PATCH 1/7] amd/scheduler:imple job skip feature(v2)
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity) · line 344
Quoted 6 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +6
-0+dma_fence_set_error (&s_fence->finished, -ECANCELED ); + +/* fake signaling the scheduled fence */ +atomic_inc (&sched->hw_rq_count); +amd_sched_fence_scheduled (s_fence); +wake_up (&sched->job_scheduled);
Unnecessary, we know that the scheduler is already awake because it is processing this function.
[ml] WHAT ??? this wake_up operate on job_scheduled, like the one at the bottom of sched_main(), It is used to wake up the thread waiting in "sched_entity_fini" on this "sched->job_scheduled", I don't understand why not necessary
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c void amd_sched_job_recovery(struct amd_gpu_scheduler *sched) · line 545
Quoted 8 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +5
-1+ guilty_context = s_job->s_fence->scheduled.context; + } + skip = (found_guilty && s_job->s_fence->scheduled.context == +guilty_context);spin_unlock (&sched->job_list_lock); - fence = sched->ops->run_job (s_job); + fence = sched->ops->run_job (s_job, skip);
As far as I can see you can use amd_sched_job_fake_signal() here as well, no need for the extra skip parameter to run_job().
[ML] no you still didn't get my point, in sched_main() we use fake_signal() because the job hadn't been linked in mirror list, so "job_finish()" Cannot be invoked for those jobs,
But for job_recovery(), it go through mirror list and only focus on jobs from that list, thus all jobs must be handled by "job_finis()" callback, So we need let those jobs go through the run_job() again, only except that it didn't need to submit to ring really , that way the job_finish() callback Can handle that job safely and seemless
BR Monk
-----Original Message-----
From: Christian König [mailto:[email protected]]
Sent: 2017年10月26日 18:52
To: Liu, Monk <[email protected]>; [email protected]
Subject: Re: [PATCH 1/7] amd/scheduler:imple job skip feature(v2)
Am 26.10.2017 um 12:30 schrieb Monk Liu:
Quoted 63 lines
jobs are skipped under two cases
1)when the entity behind this job marked guilty, the job poped from this entity's queue will be dropped insched_mainloop.2)in
job_recovery(), skip the scheduling job if its karma detected above limit, and also skipped as well for other jobs sharing the same fence context. this approach is becuasejob_recovery()cannot accessjob->entitydue to entity may already dead.v2:
some logic fixwith this feature we can introduce new gpu recover feature.
Change-Id I268b1c752c94e6ecd4ea78c87eb226ea3f52908aSigned-off-by Monk Liu <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 9 +++-- drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 54 ++++++++++++++++++++------- drivers/gpu/drm/amd/scheduler/gpu_scheduler.h | 2 +- 3 files changed, 47 insertions(+), 18 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +6
-4@@ -177,7 +177,7 @@ static struct dma_fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)return fence; } -static struct dma_fence *amdgpu_job_run (struct amd_sched_job *sched_job) +static struct dma_fence *amdgpu_job_run (struct amd_sched_job +*sched_job,bool skip) {struct dma_fence *fence =NULL ;struct amdgpu_device *adev;@@ -194,10 +194,11 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)BUG_ON (amdgpu_sync_peek_fence (&job->sync,NULL ));trace_amdgpu_sched_run_job (job); -/* skip ib schedule when vram is lost */ -if (job->vram_lost_counter !=atomic_read (&adev->vram_lost_counter)) { + +if (skip || job->vram_lost_counter !=atomic_read (&adev->vram_lost_counter)) { +/* skip ib schedule if looks needed, and set error */ dma_fence_set_error (&job->base.s_fence->finished, -ECANCELED ); -DRM_ERROR ("Skip scheduling IBs!\n" ); +DRM_INFO ("Skip scheduling IBs!\n" ); }else { r =amdgpu_ib_schedule (job->ring, job->num_ibs, job->ibs, job, &fence);drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +1
-0@@ -330,6 +330,28 @@ static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity)return false; } +static void amd_sched_job_fake_signal (struct amd_sched_job *job) {
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity) · line 343
Quoted 10 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +10
-0+struct amd_sched_fence *s_fence = job->s_fence; +struct amd_gpu_scheduler *sched = job->sched; +struct amd_sched_entity *entity = job->s_entity; + +dma_fence_set_error (&s_fence->finished, -ECANCELED ); + +/* fake signaling the scheduled fence */ +atomic_inc (&sched->hw_rq_count); +amd_sched_fence_scheduled (s_fence); +wake_up (&sched->job_scheduled);
Unnecessary, we know that the scheduler is already awake because it is processing this function.
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity) · line 348
Quoted 4 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +4
-0+ +/* fake signaling the finished fence */ + job->s_entity =NULL ; +spsc_queue_pop (&entity->job_queue);
That code isn't up to date any more, Andrey removed job->s_entity yesterday.
Please rebase on amd-staging-drm-next before resending.
Quoted 10 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +6
-0+ +amd_sched_process_job (NULL , &s_fence->cb); +dma_fence_put (&s_fence->finished); + sched->ops->free_job (job); +} +static struct amd_sched_job *amd_sched_entity_pop_job (struct amd_sched_entity *entity) {
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c amd_sched_entity_pop_job(struct amd_sched_entity *entity) · line 373
Quoted 8 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +5
-0@@ -344,6 +366,11 @@ amd_sched_entity_pop_job(struct amd_sched_entity *entity)if (amd_sched_entity_add_dependency_cb (entity))return NULL ; +if (entity->guilty &&atomic_read (entity->guilty)) { +amd_sched_job_fake_signal (sched_job); +return NULL ; + } +
Better move this after spsc_queue_pop below and remove the extra spsc_queue_pop from amd_sched_job_fake_signal.
Quoted 51 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +2
-7sched_job->s_entity =NULL ;spsc_queue_pop (&entity->job_queue);return sched_job;@@ -441,13 +468,6 @@ static void amd_sched_job_timedout(struct work_struct *work) job->sched->ops->timedout_job (job); } -static void amd_sched_set_guilty(struct amd_sched_job *s_job) -{ -if (atomic_inc_return (&s_job->karma) > s_job->sched->hang_limit) -if (s_job->s_entity->guilty) -atomic_set (s_job->s_entity->guilty,1 ); -} -void amd_sched_hw_job_reset (struct amd_gpu_scheduler *sched,struct amd_sched_job *bad) {struct amd_sched_job *s_job;@@ -466,7 +486,7 @@ void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched, struct amd_sched_jo }spin_unlock (&sched->job_list_lock); -if (bad) { +if (bad &&atomic_inc_return (&bad->karma) > bad->sched->hang_limit) +{bool found = false;for (i =AMD_SCHED_PRIORITY_MIN ; i <AMD_SCHED_PRIORITY_MAX ; i++ ){ @@ -476,7 +496,8 @@ void amd_sched_hw_job_reset(struct
amd_gpu_scheduler*sched, structamd_sched_jo
list_for_each_entry_safe(entity, tmp, &rq->entities, list){
if (bad->s_fence->scheduled.context==entity->fence_context) {
found = true;drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +6
-1-amd_sched_set_guilty (bad); +if (entity->guilty) +atomic_set (entity->guilty,1 );break ; } }@@ -499,6 +520,7 @@ void amd_sched_job_kickout(struct amd_sched_job *s_job)void amd_sched_job_recovery (struct amd_gpu_scheduler *sched) {struct amd_sched_job *s_job, *tmp; +bool found_guilty = false;int r;spin_lock (&sched->job_list_lock);@@ -510,9 +532,17 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched)list_for_each_entry_safe (s_job, tmp, &sched->ring_mirror_list, node) {struct amd_sched_fence *s_fence = s_job->s_fence;struct dma_fence *fence; +bool skip; +uint64_t guilty_context; +
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c void amd_sched_job_recovery(struct amd_gpu_scheduler *sched) · line 546
Quoted 10 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +7
-1+if (!found_guilty &&atomic_read (&s_job->karma) > sched->hang_limit) { + found_guilty = true; + guilty_context = s_job->s_fence->scheduled.context; + } + skip = (found_guilty && s_job->s_fence->scheduled.context == +guilty_context);spin_unlock (&sched->job_list_lock); - fence = sched->ops->run_job (s_job); + fence = sched->ops->run_job (s_job, skip);
As far as I can see you can use amd_sched_job_fake_signal() here as well, no need for the extra skip parameter to run_job().
Regards,
Christian.
Quoted 34 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +0
-0atomic_inc (&sched->hw_rq_count);if (fence) { s_fence->parent = dma_fence_get(fence); @@ -525,7 +555,6 @@ void
amd_sched_job_recovery(struct amd_gpu_scheduler *sched)
r);
dma_fence_put(fence);
} else {drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +1
-3-DRM_ERROR ("Failed to run job!\n" );amd_sched_process_job (NULL , &s_fence->cb); }spin_lock (&sched->job_list_lock);@@ -650,7 +679,7 @@ static int amd_sched_main(void *param)atomic_inc (&sched->hw_rq_count);amd_sched_job_begin (sched_job); - fence = sched->ops->run_job (sched_job); + fence = sched->ops->run_job (sched_job, false);amd_sched_fence_scheduled (s_fence);if (fence) {@@ -664,7 +693,6 @@ static int amd_sched_main(void *param) r);dma_fence_put (fence); }else { -DRM_ERROR ("Failed to run job!\n" );amd_sched_process_job (NULL , &s_fence->cb); }drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +0
-0
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h static inline bool amd_sched_invalidate_job(struct amd_sched_job *s_job, int thr · line 132
Quoted 9 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +2
-1@@ -126,7 +126,7 @@ static inline bool amd_sched_invalidate_job(struct amd_sched_job *s_job, int thr*/ struct amd_sched_backend_ops {struct dma_fence *(*dependency)(struct amd_sched_job *sched_job); -struct dma_fence *(*run_job)(struct amd_sched_job *sched_job); +struct dma_fence *(*run_job)(struct amd_sched_job *sched_job,bool +skip);void (*timedout_job)(struct amd_sched_job *sched_job);void (*free_job)(struct amd_sched_job *sched_job); };
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): BLUPR12MB0449F7595A55DC9ED73D9B0984450-7LeqcoF/[email protected]
Re: [PATCH 1/7] amd/scheduler:imple job skip feature(v2)
Quoted 3 lines
Unnecessary, we know that the scheduler is already awake because it is processing this function.
[ml] WHAT ??? this
wake_upoperate onjob_scheduled, like the one at the bottom ofsched_main(), It is used to wake up the thread waiting in "sched_entity_fini" on this "sched->job_scheduled", I don't understand why not necessary
Ah! You not wake up the scheduler, but the waiter for the scheduler. In this case the order is incorrect, but let's focus on your other idea.
Quoted 2 lines
The simple way I can think of to remove the @skip param for
run_jobis that we introduce a new member "skip" insched_job, and removefake_signal()function, So we always set "skip" insched_jobbeforerun_job(), and inrun_job()we skip the realib_scheduleif foundjob->skip== true,
Cool idea. How about setting the fence error code? Then we test if the error code is already set and skip calling run_job() altogether when it is.
Quoted 1 line
my current approach won't do
begin_job(), won't link job in mirror list, etc.... but above approach actually go through all steps
This is just for error recovery and doesn't need to be very efficient, but I see what you mean.
I think we should just keep one straight handling as much as possible and not to many corner cases. So your idea to skip the job when a flag is set sounds really good to me.
Regards,
Christian.
Am 26.10.2017 um 14:04 schrieb Liu, Monk:
Quoted 251 lines
The simple way I can think of to remove the @skip param for
run_jobis that we introduce a new member "skip" insched_job, and removefake_signal()function, So we always set "skip" insched_jobbeforerun_job(), and inrun_job()we skip the realib_scheduleif foundjob->skip== true,That way the skipping logic can be unified, but that satisfies the efficiency because:
my current approach won't do
begin_job(), won't link job in mirror list, etc.... but above approach actually go through all stepswhat do you think
BR Monk
-----Original Message-----
From: Liu, Monk
Sent: 2017年10月26日 19:07
To: Koenig, Christian <[email protected]>; [email protected]
Subject: RE: [PATCH 1/7] amd/scheduler:imple job skip feature(v2)Review
Quoted 6 lines
(quoted diff) +6
-0+ dma_fence_set_error(&s_fence->finished, -ECANCELED); + + /* fake signaling the scheduled fence */ + atomic_inc(&sched->hw_rq_count); + amd_sched_fence_scheduled(s_fence); + wake_up(&sched->job_scheduled);Unnecessary, we know that the scheduler is already awake because it is processing this function.
[ml] WHAT ??? this
wake_upoperate onjob_scheduled, like the one at the bottom ofsched_main(), It is used to wake up the thread waiting in "sched_entity_fini" on this "sched->job_scheduled", I don't understand why not necessaryReview
Quoted 8 lines
(quoted diff) +5
-1+ guilty_context = s_job->s_fence->scheduled.context; + } + skip = (found_guilty && s_job->s_fence->scheduled.context == +guilty_context); spin_unlock(&sched->job_list_lock); - fence = sched->ops->run_job(s_job); + fence = sched->ops->run_job(s_job, skip);As far as I can see you can use
amd_sched_job_fake_signal()here as well, no need for the extra skip parameter torun_job().[ML] no you still didn't get my point, in
sched_main()we usefake_signal()because the job hadn't been linked in mirror list, so "job_finish()" Cannot be invoked for those jobs,But for
job_recovery(), it go through mirror list and only focus on jobs from that list, thus all jobs must be handled by "job_finis()" callback, So we need let those jobs go through therun_job()again, only except that it didn't need to submit to ring really , that way thejob_finish()callback Can handle that job safely and seemlessBR Monk
-----Original Message-----
From: Christian König [mailto:[email protected]]
Sent: 2017年10月26日 18:52
To: Liu, Monk <[email protected]>; [email protected]
Subject: Re: [PATCH 1/7] amd/scheduler:imple job skip feature(v2)Am 26.10.2017 um 12:30 schrieb Monk Liu:
Quoted 63 lines
jobs are skipped under two cases
1)when the entity behind this job marked guilty, the job poped from this entity's queue will be dropped insched_mainloop.2)in
job_recovery(), skip the scheduling job if its karma detected above limit, and also skipped as well for other jobs sharing the same fence context. this approach is becuasejob_recovery()cannot accessjob->entitydue to entity may already dead.v2:
some logic fixwith this feature we can introduce new gpu recover feature.
Change-Id I268b1c752c94e6ecd4ea78c87eb226ea3f52908aSigned-off-by Monk Liu <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 9 +++-- drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 54 ++++++++++++++++++++------- drivers/gpu/drm/amd/scheduler/gpu_scheduler.h | 2 +- 3 files changed, 47 insertions(+), 18 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +6
-4@@ -177,7 +177,7 @@ static struct dma_fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)return fence; } -static struct dma_fence *amdgpu_job_run (struct amd_sched_job *sched_job) +static struct dma_fence *amdgpu_job_run (struct amd_sched_job +*sched_job,bool skip) {struct dma_fence *fence =NULL ;struct amdgpu_device *adev;@@ -194,10 +194,11 @@ static struct dma_fence *amdgpu_job_run(struct amd_sched_job *sched_job)BUG_ON (amdgpu_sync_peek_fence (&job->sync,NULL ));trace_amdgpu_sched_run_job (job); -/* skip ib schedule when vram is lost */ -if (job->vram_lost_counter !=atomic_read (&adev->vram_lost_counter)) { + +if (skip || job->vram_lost_counter !=atomic_read (&adev->vram_lost_counter)) { +/* skip ib schedule if looks needed, and set error */ dma_fence_set_error (&job->base.s_fence->finished, -ECANCELED ); -DRM_ERROR ("Skip scheduling IBs!\n" ); +DRM_INFO ("Skip scheduling IBs!\n" ); }else { r =amdgpu_ib_schedule (job->ring, job->num_ibs, job->ibs, job, &fence);drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +1
-0@@ -330,6 +330,28 @@ static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity)return false; } +static void amd_sched_job_fake_signal (struct amd_sched_job *job) {drivers/gpu/drm/amd/scheduler/gpu_scheduler.c static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity) · line 343
Quoted 10 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +10
-0+struct amd_sched_fence *s_fence = job->s_fence; +struct amd_gpu_scheduler *sched = job->sched; +struct amd_sched_entity *entity = job->s_entity; + +dma_fence_set_error (&s_fence->finished, -ECANCELED ); + +/* fake signaling the scheduled fence */ +atomic_inc (&sched->hw_rq_count); +amd_sched_fence_scheduled (s_fence); +wake_up (&sched->job_scheduled);Unnecessary, we know that the scheduler is already awake because it is processing this function.
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity) · line 347
Quoted 4 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +4
-0+ +/* fake signaling the finished fence */ + job->s_entity =NULL ; +spsc_queue_pop (&entity->job_queue);That code isn't up to date any more, Andrey removed
job->s_entityyesterday.Please rebase on amd-staging-drm-next before resending.
Quoted 10 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +6
-0+ +amd_sched_process_job (NULL , &s_fence->cb); +dma_fence_put (&s_fence->finished); + sched->ops->free_job (job); +} +static struct amd_sched_job *amd_sched_entity_pop_job (struct amd_sched_entity *entity) {drivers/gpu/drm/amd/scheduler/gpu_scheduler.c amd_sched_entity_pop_job(struct amd_sched_entity *entity) · line 373
Quoted 8 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +5
-0@@ -344,6 +366,11 @@ amd_sched_entity_pop_job(struct amd_sched_entity *entity)if (amd_sched_entity_add_dependency_cb (entity))return NULL ; +if (entity->guilty &&atomic_read (entity->guilty)) { +amd_sched_job_fake_signal (sched_job); +return NULL ; + } +Better move this after
spsc_queue_popbelow and remove the extraspsc_queue_popfromamd_sched_job_fake_signal.Quoted 51 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +2
-7sched_job->s_entity =NULL ;spsc_queue_pop (&entity->job_queue);return sched_job;@@ -441,13 +468,6 @@ static void amd_sched_job_timedout(struct work_struct *work) job->sched->ops->timedout_job (job); } -static void amd_sched_set_guilty(struct amd_sched_job *s_job) -{ -if (atomic_inc_return (&s_job->karma) > s_job->sched->hang_limit) -if (s_job->s_entity->guilty) -atomic_set (s_job->s_entity->guilty,1 ); -} -void amd_sched_hw_job_reset (struct amd_gpu_scheduler *sched,struct amd_sched_job *bad) {struct amd_sched_job *s_job;@@ -466,7 +486,7 @@ void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched, struct amd_sched_jo }spin_unlock (&sched->job_list_lock); -if (bad) { +if (bad &&atomic_inc_return (&bad->karma) > bad->sched->hang_limit) +{bool found = false;for (i =AMD_SCHED_PRIORITY_MIN ; i <AMD_SCHED_PRIORITY_MAX ; i++ ){ @@ -476,7 +496,8 @@ void amd_sched_hw_job_reset(struct
amd_gpu_scheduler*sched, structamd_sched_jolist_for_each_entry_safe(entity, tmp, &rq->entities, list) { if (bad->s_fence->scheduled.context == entity->fence_context) { found = true;drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +6
-1-amd_sched_set_guilty (bad); +if (entity->guilty) +atomic_set (entity->guilty,1 );break ; } }@@ -499,6 +520,7 @@ void amd_sched_job_kickout(struct amd_sched_job *s_job)void amd_sched_job_recovery (struct amd_gpu_scheduler *sched) {struct amd_sched_job *s_job, *tmp; +bool found_guilty = false;int r;spin_lock (&sched->job_list_lock);@@ -510,9 +532,17 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched)list_for_each_entry_safe (s_job, tmp, &sched->ring_mirror_list, node) {struct amd_sched_fence *s_fence = s_job->s_fence;struct dma_fence *fence; +bool skip; +uint64_t guilty_context; +drivers/gpu/drm/amd/scheduler/gpu_scheduler.c void amd_sched_job_recovery(struct amd_gpu_scheduler *sched) · line 546
Quoted 10 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +7
-1+if (!found_guilty &&atomic_read (&s_job->karma) > sched->hang_limit) { + found_guilty = true; + guilty_context = s_job->s_fence->scheduled.context; + } + skip = (found_guilty && s_job->s_fence->scheduled.context == +guilty_context);spin_unlock (&sched->job_list_lock); - fence = sched->ops->run_job (s_job); + fence = sched->ops->run_job (s_job, skip);As far as I can see you can use
amd_sched_job_fake_signal()here as well, no need for the extra skip parameter torun_job().Regards,
Christian.Quoted 28 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +0
-0atomic_inc (&sched->hw_rq_count);if (fence) { s_fence->parent = dma_fence_get(fence); @@ -525,7 +555,6 @@ void
amd_sched_job_recovery(struct amd_gpu_scheduler *sched)r); dma_fence_put(fence); } else {drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +1
-3-DRM_ERROR ("Failed to run job!\n" );amd_sched_process_job (NULL , &s_fence->cb); }spin_lock (&sched->job_list_lock);@@ -650,7 +679,7 @@ static int amd_sched_main(void *param)atomic_inc (&sched->hw_rq_count);amd_sched_job_begin (sched_job); - fence = sched->ops->run_job (sched_job); + fence = sched->ops->run_job (sched_job, false);amd_sched_fence_scheduled (s_fence);if (fence) {@@ -664,7 +693,6 @@ static int amd_sched_main(void *param) r);dma_fence_put (fence); }else { -DRM_ERROR ("Failed to run job!\n" );amd_sched_process_job (NULL , &s_fence->cb); }
Quoted 16 lines
Quoted 6 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +0
-0drivers/gpu/drm/amd/scheduler/gpu_scheduler.h static inline bool amd_sched_invalidate_job(struct amd_sched_job *s_job, int thr
Quoted 9 lines
drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +2
-1@@ -126,7 +126,7 @@ static inline bool amd_sched_invalidate_job(struct amd_sched_job *s_job, int thr*/ struct amd_sched_backend_ops {struct dma_fence *(*dependency)(struct amd_sched_job *sched_job); -struct dma_fence *(*run_job)(struct amd_sched_job *sched_job); +struct dma_fence *(*run_job)(struct amd_sched_job *sched_job,bool +skip);void (*timedout_job)(struct amd_sched_job *sched_job);void (*free_job)(struct amd_sched_job *sched_job); };
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 2/7 drm/amdgpu:implement new GPU recover(v3)
In reply to a message not in the archive1,new imple names amdgpu_gpu_recover which gives more hint on what it does compared with gpu_reset
2,gpu_recover unify bare-metal and SR-IOV, only the asic reset part is implemented differently
3,gpu_recover will increase hang job karma and mark its entity/context as guilty if exceeds limit
V2:
4,in scheduler main routine the job from guilty context will be immedialy fake signaled after it poped from queue and its fence be set with "-ECANCELED" error
5,in scheduler recovery routine all jobs from the guilty entity would be dropped
6,in run_job() routine the real IB submission would be skipped if @skip parameter equales true or there was VRAM lost occured.
V3:
7,replace deprecated gpu reset, use new gpu recover
--- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 6 +- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 310 +++++++++++++---------------- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 10 +- drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 5 +- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 1 - drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 2 +- drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 2 +- 8 files changed, 151 insertions(+), 187 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +5 -1
@@ -178,6 +178,10 @@ extern int amdgpu_cik_support;#define CIK_CURSOR_WIDTH 128#define CIK_CURSOR_HEIGHT 128 +/* GPU RESET flags */ +#define AMDGPU_RESET_INFO_VRAM_LOST (1 << 0) +#define AMDGPU_RESET_INFO_FULLRESET (1 << 1) +struct amdgpu_device ;struct amdgpu_ib ;struct amdgpu_cs_parser ;
@@ -1840,7 +1844,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)#define amdgpu_psp_check_fw_loading_status (adev, i) (adev)->firmware.funcs->check_fw_loading_status((adev), (i))/* Common functions */ -int amdgpu_gpu_reset (struct amdgpu_device *adev); +int amdgpu_gpu_recover (struct amdgpu_device *adev,struct amdgpu_job * job);bool amdgpu_need_backup (struct amdgpu_device *adev);void amdgpu_pci_config_reset (struct amdgpu_device *adev);bool amdgpu_need_post (struct amdgpu_device *adev);
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +137 -173
409 lines not on this page · raw message
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +5 -5
@@ -694,25 +694,25 @@ static int amdgpu_debugfs_fence_info(struct seq_file *m, void *data) }/** -* amdgpu_debugfs_gpu_reset - manually trigger a gpu reset +* amdgpu_debugfs_gpu_recover - manually trigger a gpu reset & recover * * Manually trigger a gpu reset at the next fence wait. */ -static int amdgpu_debugfs_gpu_reset (struct seq_file *m,void *data) +static int amdgpu_debugfs_gpu_recover (struct seq_file *m,void *data) {struct drm_info_node *node = (struct drm_info_node *) m->private;struct drm_device *dev = node->minor->dev;struct amdgpu_device *adev = dev->dev_private; -seq_printf (m,"gpu reset\n" ); -amdgpu_gpu_reset (adev); +seq_printf (m,"gpu recover\n" ); +amdgpu_gpu_recover (adev,NULL );return 0 ; }static const struct drm_info_list amdgpu_debugfs_fence_list[] = { {"amdgpu_fence_info" , &amdgpu_debugfs_fence_info,0 ,NULL }, - {"amdgpu_gpu_reset" , &amdgpu_debugfs_gpu_reset,0 ,NULL } + {"amdgpu_gpu_recover" , &amdgpu_debugfs_gpu_recover,0 ,NULL } };static const struct drm_info_list amdgpu_debugfs_fence_list_sriov[] = {
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +1 -1
@@ -88,7 +88,7 @@ static void amdgpu_irq_reset_work_func(struct work_struct *work) reset_work);if (!amdgpu_sriov_vf (adev)) -amdgpu_gpu_reset (adev); +amdgpu_gpu_recover (adev,NULL ); }/* Disable *all* interrupts */
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +1 -4
@@ -37,10 +37,7 @@ static void amdgpu_job_timedout(struct amd_sched_job *s_job)atomic_read (&job->ring->fence_drv.last_seq), job->ring->fence_drv.sync_seq); -if (amdgpu_sriov_vf (job->adev)) -amdgpu_sriov_gpu_reset (job->adev, job); -else -amdgpu_gpu_reset (job->adev); +amdgpu_gpu_recover (job->adev, job); } int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +0 -1
@@ -285,7 +285,6 @@ void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v);int amdgpu_virt_request_full_gpu (struct amdgpu_device *adev,bool init);int amdgpu_virt_release_full_gpu (struct amdgpu_device *adev,bool init);int amdgpu_virt_reset_gpu (struct amdgpu_device *adev); -int amdgpu_sriov_gpu_reset (struct amdgpu_device *adev,struct amdgpu_job *job);int amdgpu_virt_alloc_mm_table (struct amdgpu_device *adev);void amdgpu_virt_free_mm_table (struct amdgpu_device *adev); int amdgpu_virt_fw_reserve_get_checksum(void *obj, unsigned long obj_size,
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +1 -1
@@ -254,7 +254,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work) }/* Trigger recovery due to world switch failure */ -amdgpu_sriov_gpu_reset (adev,NULL ); +amdgpu_gpu_recover (adev,NULL ); } static int xgpu_ai_set_mailbox_rcv_irq(struct amdgpu_device *adev,
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c +1 -1
@@ -514,7 +514,7 @@ static void xgpu_vi_mailbox_flr_work(struct work_struct *work) }/* Trigger recovery due to world switch failure */ -amdgpu_sriov_gpu_reset (adev,NULL ); +amdgpu_gpu_recover (adev,NULL ); } static int xgpu_vi_set_mailbox_rcv_irq(struct amdgpu_device *adev,
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 3/7 drm/amdgpu:cleanup in_sriov_reset and lock_reset
In reply to a message not in the archivesince now gpu reset is unified with gpu_recover
for both bare-metal and SR-IOV:
1)rename in_sriov_reset to in_gpu_reset
2)move lock_reset from adev->virt to adev
--- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 3 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 9 +++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 2 -- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 1 - drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 6 +++--- 8 files changed, 15 insertions(+), 16 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +2 -1
@@ -1650,7 +1650,8 @@ struct amdgpu_device {/* record last mm index being written through WREG32*/ unsigned long last_mm_index; -bool in_sriov_reset; +bool in_gpu_reset; +struct mutex lock_reset; };static inline struct amdgpu_device *amdgpu_ttm_adev (struct ttm_bo_device *bdev)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +5 -4
@@ -2161,6 +2161,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,mutex_init (&adev->mn_lock);mutex_init (&adev->virt.vf_errors.lock);hash_init (adev->mn_hash); +mutex_init (&adev->lock_reset);amdgpu_check_arguments (adev);
@@ -2963,9 +2964,9 @@ int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job *job)dev_info (adev->dev,"GPU reset begin!\n" ); -mutex_lock (&adev->virt.lock_reset); +mutex_lock (&adev->lock_reset);atomic_inc (&adev->gpu_reset_counter); - adev->in_sriov_reset =1 ; + adev->in_gpu_reset =1 ;/* block TTM */ resched =ttm_bo_lock_delayed_workqueue (&adev->mman.bdev);
@@ -3075,8 +3076,8 @@ int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job *job) }amdgpu_vf_error_trans_all (adev); - adev->in_sriov_reset =0 ; -mutex_unlock (&adev->virt.lock_reset); + adev->in_gpu_reset =0 ; +mutex_unlock (&adev->lock_reset);return r; }
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +1 -1
@@ -264,7 +264,7 @@ static int psp_hw_start(struct psp_context *psp)struct amdgpu_device *adev = psp->adev;int ret; -if (!amdgpu_sriov_vf (adev) || !adev->in_sriov_reset) { +if (!amdgpu_sriov_vf (adev) || !adev->in_gpu_reset) { ret =psp_bootloader_load_sysdrv (psp);if (ret)return ret;
drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +1 -1
@@ -370,7 +370,7 @@ int amdgpu_ucode_init_bo(struct amdgpu_device *adev)return 0 ; } -if (!amdgpu_sriov_vf (adev) || !adev->in_sriov_reset) { +if (!amdgpu_sriov_vf (adev) || !adev->in_gpu_reset) { err = amdgpu_bo_create(adev, adev->firmware.fw_size, PAGE_SIZE, true, amdgpu_sriov_vf(adev) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT, AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +0 -2
@@ -107,8 +107,6 @@ void amdgpu_virt_init_setting(struct amdgpu_device *adev) adev->enable_virtual_display = true; adev->cg_flags =0 ; adev->pg_flags =0 ; - -mutex_init (&adev->virt.lock_reset); }uint32_t amdgpu_virt_kiq_rreg (struct amdgpu_device *adev,uint32_t reg)
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +0 -1
@@ -238,7 +238,6 @@ struct amdgpu_virt {uint64_t csa_vmid0_addr;bool chained_ib_support;uint32_t reg_val_offs; -struct mutex lock_reset;struct amdgpu_irq_src ack_irq;struct amdgpu_irq_src rcv_irq;struct work_struct flr_work;
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +3 -3
@@ -4807,7 +4807,7 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)gfx_v8_0_kiq_setting (ring); -if (adev->in_sriov_reset) {/* for GPU_RESET case */ +if (adev->in_gpu_reset) {/* for GPU_RESET case */ /* reset MQD to a clean status */ if (adev->gfx.mec.mqd_backup[mqd_idx])memcpy (mqd, adev->gfx.mec.mqd_backup[mqd_idx],sizeof (struct vi_mqd_allocation ));
@@ -4844,7 +4844,7 @@ static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)struct vi_mqd *mqd = ring->mqd_ptr;int mqd_idx = ring - &adev->gfx.compute_ring[0 ]; -if (!adev->in_sriov_reset && !adev->gfx.in_suspend) { +if (!adev->in_gpu_reset && !adev->gfx.in_suspend) {memset ((void *)mqd,0 ,sizeof (struct vi_mqd_allocation )); ((struct vi_mqd_allocation *)mqd)->dynamic_cu_mask =0xFFFFFFFF ; ((struct vi_mqd_allocation *)mqd)->dynamic_rb_mask =0xFFFFFFFF ;
@@ -4856,7 +4856,7 @@ static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)if (adev->gfx.mec.mqd_backup[mqd_idx])memcpy (adev->gfx.mec.mqd_backup[mqd_idx], mqd,sizeof (struct vi_mqd_allocation )); - }else if (adev->in_sriov_reset) {/* for GPU_RESET case */ + }else if (adev->in_gpu_reset) {/* for GPU_RESET case */ /* reset MQD to a clean status */ if (adev->gfx.mec.mqd_backup[mqd_idx])memcpy (mqd, adev->gfx.mec.mqd_backup[mqd_idx],sizeof (struct vi_mqd_allocation ));
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +3 -3
@@ -2732,7 +2732,7 @@ static int gfx_v9_0_kiq_init_queue(struct amdgpu_ring *ring)gfx_v9_0_kiq_setting (ring); -if (adev->in_sriov_reset) {/* for GPU_RESET case */ +if (adev->in_gpu_reset) {/* for GPU_RESET case */ /* reset MQD to a clean status */ if (adev->gfx.mec.mqd_backup[mqd_idx])memcpy (mqd, adev->gfx.mec.mqd_backup[mqd_idx],sizeof (struct v9_mqd_allocation ));
@@ -2770,7 +2770,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring)struct v9_mqd *mqd = ring->mqd_ptr;int mqd_idx = ring - &adev->gfx.compute_ring[0 ]; -if (!adev->in_sriov_reset && !adev->gfx.in_suspend) { +if (!adev->in_gpu_reset && !adev->gfx.in_suspend) {memset ((void *)mqd,0 ,sizeof (struct v9_mqd_allocation )); ((struct v9_mqd_allocation *)mqd)->dynamic_cu_mask =0xFFFFFFFF ; ((struct v9_mqd_allocation *)mqd)->dynamic_rb_mask =0xFFFFFFFF ;
@@ -2782,7 +2782,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring)if (adev->gfx.mec.mqd_backup[mqd_idx])memcpy (adev->gfx.mec.mqd_backup[mqd_idx], mqd,sizeof (struct v9_mqd_allocation )); - }else if (adev->in_sriov_reset) {/* for GPU_RESET case */ + }else if (adev->in_gpu_reset) {/* for GPU_RESET case */ /* reset MQD to a clean status */ if (adev->gfx.mec.mqd_backup[mqd_idx])memcpy (mqd, adev->gfx.mec.mqd_backup[mqd_idx],sizeof (struct v9_mqd_allocation ));
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 4/7 drm/amdgpu:cleanup ucode_init_bo
In reply to a message not in the archive1,no sriov check since gpu recover is unified 2,need CPU_ACCESS_REQUIRED flag for VRAM if SRIOV because otherwise after following PIN the first allocated VRAM bo is wasted due to some TTM mgr reason.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +2 -2
@@ -370,10 +370,10 @@ int amdgpu_ucode_init_bo(struct amdgpu_device *adev)return 0 ; } -if (!amdgpu_sriov_vf (adev) || !adev->in_gpu_reset) { +if (!adev->in_gpu_reset) { err =amdgpu_bo_create (adev, adev->firmware.fw_size,PAGE_SIZE , true,amdgpu_sriov_vf (adev) ?AMDGPU_GEM_DOMAIN_VRAM :AMDGPU_GEM_DOMAIN_GTT , -AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS , +AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED ,NULL ,NULL ,0 , bo);if (err) {dev_err (adev->dev,"(%d) Firmware buffer allocate failed\n" , err);
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 5/7 drm/amdgpu:block kms open during gpu_reset
In reply to a message not in the archive--- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +3 -0
@@ -813,6 +813,9 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)if (r <0 )return r; +if (adev->in_gpu_reset) +return -ENODEV ; + fpriv =kzalloc (sizeof (*fpriv),GFP_KERNEL );if (unlikely (!fpriv)) { r = -ENOMEM ;
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 6/7 drm/amdgpu/sriov:fix memory leak in psp_load_fw
In reply to a message not in the archivefor SR-IOV when doing gpu reset this routine shouldn't do resource allocating otherwise memory leak
--- drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +12 -8
@@ -334,23 +334,26 @@ static int psp_load_fw(struct amdgpu_device *adev)int ret;struct psp_context *psp = &adev->psp; +if (amdgpu_sriov_vf (adev) && adev->in_gpu_reset !=0 ) + goto skip_memalloc; + psp->cmd =kzalloc (sizeof (struct psp_gfx_cmd_resp ),GFP_KERNEL );if (!psp->cmd)return -ENOMEM ; ret =amdgpu_bo_create_kernel (adev,PSP_1_MEG ,PSP_1_MEG , -AMDGPU_GEM_DOMAIN_GTT , - &psp->fw_pri_bo, - &psp->fw_pri_mc_addr, - &psp->fw_pri_buf); +AMDGPU_GEM_DOMAIN_GTT , + &psp->fw_pri_bo, + &psp->fw_pri_mc_addr, + &psp->fw_pri_buf);if (ret) goto failed; ret =amdgpu_bo_create_kernel (adev,PSP_FENCE_BUFFER_SIZE ,PAGE_SIZE , -AMDGPU_GEM_DOMAIN_VRAM , - &psp->fence_buf_bo, - &psp->fence_buf_mc_addr, - &psp->fence_buf); +AMDGPU_GEM_DOMAIN_VRAM , + &psp->fence_buf_bo, + &psp->fence_buf_mc_addr, + &psp->fence_buf);if (ret) goto failed_mem2;
@@ -375,6 +378,7 @@ static int psp_load_fw(struct amdgpu_device *adev)if (ret) goto failed_mem; +skip_memalloc: ret =psp_hw_start (psp);if (ret) goto failed_mem;
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 7/7 drm/amdgpu:fix random missing of FLR NOTIFY
In reply to a message not in the archive--- drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +11 -3
@@ -282,9 +282,17 @@ static int xgpu_ai_mailbox_rcv_irq(struct amdgpu_device *adev,/* see what event we get */ r =xgpu_ai_mailbox_rcv_msg (adev,IDH_FLR_NOTIFICATION ); -/* only handle FLR_NOTIFY now */ -if (!r) -schedule_work (&adev->virt.flr_work); +/* sometimes the interrupt is delayed to inject to VM, so under such case +* the IDH_FLR_NOTIFICATION is overwritten by VF FLR from GIM side, thus +* above recieve message could be failed, we should schedule the flr_work +* anyway +*/ +if (r) { +DRM_ERROR ("FLR_NOTIFICATION is missed\n" ); +xgpu_ai_mailbox_send_ack (adev); + } + +schedule_work (&adev->virt.flr_work); }return 0 ;
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx