* [PATCH v6 1/2] drm/sched: Refactor ring mirror list handling.
@ 2018-12-27 19:28 Andrey Grodzovsky
2018-12-27 19:28 ` [PATCH v6 2/2] drm/sched: Rework HW fence processing Andrey Grodzovsky
` (3 more replies)
0 siblings, 4 replies; 6+ messages in thread
From: Andrey Grodzovsky @ 2018-12-27 19:28 UTC (permalink / raw)
To: dri-devel-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW,
amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW,
ckoenig.leichtzumerken-Re5JQEeQqe8AvxtiuMwx3w,
eric-WhKQ6XTQaPysTnJN9+BGXg,
etnaviv-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW
Cc: david1.zhou-5C7GfCeVMHo, Monk.Liu-5C7GfCeVMHo, Andrey Grodzovsky
Decauple sched threads stop and start and ring mirror
list handling from the policy of what to do about the
guilty jobs.
When stoppping the sched thread and detaching sched fences
from non signaled HW fenes wait for all signaled HW fences
to complete before rerunning the jobs.
v2: Fix resubmission of guilty job into HW after refactoring.
v4:
Full restart for all the jobs, not only from guilty ring.
Extract karma increase into standalone function.
v5:
Rework waiting for signaled jobs without relying on the job
struct itself as those might already be freed for non 'guilty'
job's schedulers.
Expose karma increase to drivers.
v6:
Use list_for_each_entry_safe_continue and drm_sched_process_job
in case fence already signaled.
Call drm_sched_increase_karma only once for amdgpu and add documentation.
Suggested-by: Christian Koenig <Christian.Koenig@amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 20 ++-
drivers/gpu/drm/etnaviv/etnaviv_sched.c | 11 +-
drivers/gpu/drm/scheduler/sched_main.c | 195 +++++++++++++++++++----------
drivers/gpu/drm/v3d/v3d_sched.c | 12 +-
include/drm/gpu_scheduler.h | 8 +-
5 files changed, 157 insertions(+), 89 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 98df8e4..6a0601c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3298,17 +3298,15 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
if (!ring || !ring->sched.thread)
continue;
- kthread_park(ring->sched.thread);
-
- if (job && job->base.sched != &ring->sched)
- continue;
-
- drm_sched_hw_job_reset(&ring->sched, job ? &job->base : NULL);
+ drm_sched_stop(&ring->sched, job ? &job->base : NULL);
/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
amdgpu_fence_driver_force_completion(ring);
}
+ if(job)
+ drm_sched_increase_karma(&job->base);
+
if (!amdgpu_sriov_vf(adev)) {
@@ -3454,14 +3452,10 @@ static void amdgpu_device_post_asic_reset(struct amdgpu_device *adev,
if (!ring || !ring->sched.thread)
continue;
- /* only need recovery sched of the given job's ring
- * or all rings (in the case @job is NULL)
- * after above amdgpu_reset accomplished
- */
- if ((!job || job->base.sched == &ring->sched) && !adev->asic_reset_res)
- drm_sched_job_recovery(&ring->sched);
+ if (!adev->asic_reset_res)
+ drm_sched_resubmit_jobs(&ring->sched);
- kthread_unpark(ring->sched.thread);
+ drm_sched_start(&ring->sched, !adev->asic_reset_res);
}
if (!amdgpu_device_has_dc_support(adev)) {
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index 49a6763..6f1268f 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -109,16 +109,19 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job)
}
/* block scheduler */
- kthread_park(gpu->sched.thread);
- drm_sched_hw_job_reset(&gpu->sched, sched_job);
+ drm_sched_stop(&gpu->sched, sched_job);
+
+ if(sched_job)
+ drm_sched_increase_karma(sched_job);
/* get the GPU back into the init state */
etnaviv_core_dump(gpu);
etnaviv_gpu_recover_hang(gpu);
+ drm_sched_resubmit_jobs(&gpu->sched);
+
/* restart scheduler after GPU is usable again */
- drm_sched_job_recovery(&gpu->sched);
- kthread_unpark(gpu->sched.thread);
+ drm_sched_start(&gpu->sched, true);
}
static void etnaviv_sched_free_job(struct drm_sched_job *sched_job)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index dbb6906..54e809b 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -60,8 +60,6 @@
static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb);
-static void drm_sched_expel_job_unlocked(struct drm_sched_job *s_job);
-
/**
* drm_sched_rq_init - initialize a given run queue struct
*
@@ -335,6 +333,51 @@ static void drm_sched_job_timedout(struct work_struct *work)
spin_unlock_irqrestore(&sched->job_list_lock, flags);
}
+ /**
+ * drm_sched_increase_karma - Update sched_entity guilty flag
+ *
+ * @bad: The job guilty of time out
+ *
+ * Increment on every hang caused by the 'bad' job. If this exceeds the hang
+ * limit of the scheduler then the respective sched entity is marked guilty and
+ * jobs from it will not be scheduled further
+ */
+void drm_sched_increase_karma(struct drm_sched_job *bad)
+{
+ int i;
+ struct drm_sched_entity *tmp;
+ struct drm_sched_entity *entity;
+ struct drm_gpu_scheduler *sched = bad->sched;
+
+ /* don't increase @bad's karma if it's from KERNEL RQ,
+ * because sometimes GPU hang would cause kernel jobs (like VM updating jobs)
+ * corrupt but keep in mind that kernel jobs always considered good.
+ */
+ if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
+ atomic_inc(&bad->karma);
+ for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL;
+ i++) {
+ struct drm_sched_rq *rq = &sched->sched_rq[i];
+
+ spin_lock(&rq->lock);
+ list_for_each_entry_safe(entity, tmp, &rq->entities, list) {
+ if (bad->s_fence->scheduled.context ==
+ entity->fence_context) {
+ if (atomic_read(&bad->karma) >
+ bad->sched->hang_limit)
+ if (entity->guilty)
+ atomic_set(entity->guilty, 1);
+ break;
+ }
+ }
+ spin_unlock(&rq->lock);
+ if (&entity->list != &rq->entities)
+ break;
+ }
+ }
+}
+EXPORT_SYMBOL(drm_sched_increase_karma);
+
/**
* drm_sched_hw_job_reset - stop the scheduler if it contains the bad job
*
@@ -342,13 +385,22 @@ static void drm_sched_job_timedout(struct work_struct *work)
* @bad: bad scheduler job
*
*/
-void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
+void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
{
- struct drm_sched_job *s_job;
- struct drm_sched_entity *entity, *tmp;
+ struct drm_sched_job *s_job, *tmp;
unsigned long flags;
- int i;
+ struct dma_fence *wait_fence = NULL;
+ int r;
+
+ kthread_park(sched->thread);
+ /*
+ * Verify all the signaled jobs in mirror list are removed from the ring
+ * by waiting for their respective scheduler fences to signal.
+ * Continually repeat traversing the ring mirror list until no more signaled
+ * fences are found
+ */
+retry_wait:
spin_lock_irqsave(&sched->job_list_lock, flags);
list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) {
if (s_job->s_fence->parent &&
@@ -357,35 +409,43 @@ void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_jo
dma_fence_put(s_job->s_fence->parent);
s_job->s_fence->parent = NULL;
atomic_dec(&sched->hw_rq_count);
+ } else {
+ wait_fence = dma_fence_get(&s_job->s_fence->finished);
+ break;
}
}
- spin_unlock_irqrestore(&sched->job_list_lock, flags);
- if (bad && bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
- atomic_inc(&bad->karma);
- /* don't increase @bad's karma if it's from KERNEL RQ,
- * becuase sometimes GPU hang would cause kernel jobs (like VM updating jobs)
- * corrupt but keep in mind that kernel jobs always considered good.
- */
- for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL; i++ ) {
- struct drm_sched_rq *rq = &sched->sched_rq[i];
+ /* No signaled jobs in the ring, its safe to proceed to ASIC reset */
+ if (!wait_fence) {
+ spin_unlock_irqrestore(&sched->job_list_lock, flags);
+ return;
+ }
- spin_lock(&rq->lock);
- list_for_each_entry_safe(entity, tmp, &rq->entities, list) {
- if (bad->s_fence->scheduled.context == entity->fence_context) {
- if (atomic_read(&bad->karma) > bad->sched->hang_limit)
- if (entity->guilty)
- atomic_set(entity->guilty, 1);
- break;
- }
- }
- spin_unlock(&rq->lock);
- if (&entity->list != &rq->entities)
- break;
+ /* Restore removed cb since removing again already removed cb is undefined */
+ list_for_each_entry_safe_continue(s_job, tmp, &sched->ring_mirror_list, node) {
+
+ if (s_job->s_fence->parent) {
+ r = dma_fence_add_callback(s_job->s_fence->parent,
+ &s_job->s_fence->cb,
+ drm_sched_process_job);
+ if (r == -ENOENT)
+ drm_sched_process_job(s_job->s_fence->parent,
+ &s_job->s_fence->cb);
+ else if (r)
+ DRM_ERROR("fence add callback failed (%d)\n",
+ r);
}
}
+ spin_unlock_irqrestore(&sched->job_list_lock, flags);
+
+ dma_fence_wait(wait_fence, false);
+ dma_fence_put(wait_fence);
+ wait_fence = NULL;
+
+ goto retry_wait;
}
-EXPORT_SYMBOL(drm_sched_hw_job_reset);
+
+EXPORT_SYMBOL(drm_sched_stop);
/**
* drm_sched_job_recovery - recover jobs after a reset
@@ -393,33 +453,21 @@ EXPORT_SYMBOL(drm_sched_hw_job_reset);
* @sched: scheduler instance
*
*/
-void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
+void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
{
struct drm_sched_job *s_job, *tmp;
- bool found_guilty = false;
unsigned long flags;
int r;
+ if (!full_recovery)
+ goto unpark;
+
spin_lock_irqsave(&sched->job_list_lock, flags);
list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
struct drm_sched_fence *s_fence = s_job->s_fence;
- struct dma_fence *fence;
- uint64_t guilty_context;
-
- if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) {
- found_guilty = true;
- guilty_context = s_job->s_fence->scheduled.context;
- }
-
- if (found_guilty && s_job->s_fence->scheduled.context == guilty_context)
- dma_fence_set_error(&s_fence->finished, -ECANCELED);
-
- spin_unlock_irqrestore(&sched->job_list_lock, flags);
- fence = sched->ops->run_job(s_job);
- atomic_inc(&sched->hw_rq_count);
+ struct dma_fence *fence = s_job->s_fence->parent;
if (fence) {
- s_fence->parent = dma_fence_get(fence);
r = dma_fence_add_callback(fence, &s_fence->cb,
drm_sched_process_job);
if (r == -ENOENT)
@@ -427,18 +475,47 @@ void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
else if (r)
DRM_ERROR("fence add callback failed (%d)\n",
r);
- dma_fence_put(fence);
- } else {
- if (s_fence->finished.error < 0)
- drm_sched_expel_job_unlocked(s_job);
+ } else
drm_sched_process_job(NULL, &s_fence->cb);
- }
- spin_lock_irqsave(&sched->job_list_lock, flags);
}
+
drm_sched_start_timeout(sched);
spin_unlock_irqrestore(&sched->job_list_lock, flags);
+
+unpark:
+ kthread_unpark(sched->thread);
+}
+EXPORT_SYMBOL(drm_sched_start);
+
+/**
+ * drm_sched_resubmit_jobs - helper to relunch job from mirror ring list
+ *
+ * @sched: scheduler instance
+ *
+ */
+void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
+{
+ struct drm_sched_job *s_job, *tmp;
+ uint64_t guilty_context;
+ bool found_guilty = false;
+
+ /*TODO DO we need spinlock here ? */
+ list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
+ struct drm_sched_fence *s_fence = s_job->s_fence;
+
+ if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) {
+ found_guilty = true;
+ guilty_context = s_job->s_fence->scheduled.context;
+ }
+
+ if (found_guilty && s_job->s_fence->scheduled.context == guilty_context)
+ dma_fence_set_error(&s_fence->finished, -ECANCELED);
+
+ s_job->s_fence->parent = sched->ops->run_job(s_job);
+ atomic_inc(&sched->hw_rq_count);
+ }
}
-EXPORT_SYMBOL(drm_sched_job_recovery);
+EXPORT_SYMBOL(drm_sched_resubmit_jobs);
/**
* drm_sched_job_init - init a scheduler job
@@ -634,26 +711,14 @@ static int drm_sched_main(void *param)
DRM_ERROR("fence add callback failed (%d)\n",
r);
dma_fence_put(fence);
- } else {
- if (s_fence->finished.error < 0)
- drm_sched_expel_job_unlocked(sched_job);
+ } else
drm_sched_process_job(NULL, &s_fence->cb);
- }
wake_up(&sched->job_scheduled);
}
return 0;
}
-static void drm_sched_expel_job_unlocked(struct drm_sched_job *s_job)
-{
- struct drm_gpu_scheduler *sched = s_job->sched;
-
- spin_lock(&sched->job_list_lock);
- list_del_init(&s_job->node);
- spin_unlock(&sched->job_list_lock);
-}
-
/**
* drm_sched_init - Init a gpu scheduler instance
*
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 445b2ef..f76d9ed 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -178,18 +178,22 @@ v3d_job_timedout(struct drm_sched_job *sched_job)
for (q = 0; q < V3D_MAX_QUEUES; q++) {
struct drm_gpu_scheduler *sched = &v3d->queue[q].sched;
- kthread_park(sched->thread);
- drm_sched_hw_job_reset(sched, (sched_job->sched == sched ?
+ drm_sched_stop(sched, (sched_job->sched == sched ?
sched_job : NULL));
+
+ if(sched_job)
+ drm_sched_increase_karma(sched_job);
}
/* get the GPU back into the init state */
v3d_reset(v3d);
+ for (q = 0; q < V3D_MAX_QUEUES; q++)
+ drm_sched_resubmit_jobs(sched_job->sched);
+
/* Unblock schedulers and restart their jobs. */
for (q = 0; q < V3D_MAX_QUEUES; q++) {
- drm_sched_job_recovery(&v3d->queue[q].sched);
- kthread_unpark(v3d->queue[q].sched.thread);
+ drm_sched_start(&v3d->queue[q].sched, true);
}
mutex_unlock(&v3d->reset_lock);
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 47e1979..4f21faf 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -298,9 +298,11 @@ int drm_sched_job_init(struct drm_sched_job *job,
void *owner);
void drm_sched_job_cleanup(struct drm_sched_job *job);
void drm_sched_wakeup(struct drm_gpu_scheduler *sched);
-void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched,
- struct drm_sched_job *job);
-void drm_sched_job_recovery(struct drm_gpu_scheduler *sched);
+void drm_sched_stop(struct drm_gpu_scheduler *sched,
+ struct drm_sched_job *job);
+void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery);
+void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched);
+void drm_sched_increase_karma(struct drm_sched_job *bad);
bool drm_sched_dependency_optimized(struct dma_fence* fence,
struct drm_sched_entity *entity);
void drm_sched_fault(struct drm_gpu_scheduler *sched);
--
2.7.4
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH v6 2/2] drm/sched: Rework HW fence processing.
2018-12-27 19:28 [PATCH v6 1/2] drm/sched: Refactor ring mirror list handling Andrey Grodzovsky
@ 2018-12-27 19:28 ` Andrey Grodzovsky
2018-12-27 22:07 ` [PATCH v6 1/2] drm/sched: Refactor ring mirror list handling kbuild test robot
` (2 subsequent siblings)
3 siblings, 0 replies; 6+ messages in thread
From: Andrey Grodzovsky @ 2018-12-27 19:28 UTC (permalink / raw)
To: dri-devel, amd-gfx, ckoenig.leichtzumerken, eric, etnaviv; +Cc: Monk.Liu
Expedite job deletion from ring mirror list to the HW fence signal
callback instead from finish_work, together with waiting for all
such fences to signal in drm_sched_stop we garantee that
already signaled job will not be processed twice.
Remove the sched finish fence callback and just submit finish_work
directly from the HW fence callback.
v2: Fix comments.
v3: Attach hw fence cb to sched_job
v5: Rebase
Suggested-by: Christian Koenig <Christian.Koenig@amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
---
drivers/gpu/drm/scheduler/sched_main.c | 59 +++++++++++++++++-----------------
include/drm/gpu_scheduler.h | 6 ++--
2 files changed, 31 insertions(+), 34 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 54e809b..58bd33a 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -284,8 +284,6 @@ static void drm_sched_job_finish(struct work_struct *work)
cancel_delayed_work_sync(&sched->work_tdr);
spin_lock_irqsave(&sched->job_list_lock, flags);
- /* remove job from ring_mirror_list */
- list_del_init(&s_job->node);
/* queue TDR for next job */
drm_sched_start_timeout(sched);
spin_unlock_irqrestore(&sched->job_list_lock, flags);
@@ -293,22 +291,11 @@ static void drm_sched_job_finish(struct work_struct *work)
sched->ops->free_job(s_job);
}
-static void drm_sched_job_finish_cb(struct dma_fence *f,
- struct dma_fence_cb *cb)
-{
- struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
- finish_cb);
- schedule_work(&job->finish_work);
-}
-
static void drm_sched_job_begin(struct drm_sched_job *s_job)
{
struct drm_gpu_scheduler *sched = s_job->sched;
unsigned long flags;
- dma_fence_add_callback(&s_job->s_fence->finished, &s_job->finish_cb,
- drm_sched_job_finish_cb);
-
spin_lock_irqsave(&sched->job_list_lock, flags);
list_add_tail(&s_job->node, &sched->ring_mirror_list);
drm_sched_start_timeout(sched);
@@ -405,7 +392,7 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) {
if (s_job->s_fence->parent &&
dma_fence_remove_callback(s_job->s_fence->parent,
- &s_job->s_fence->cb)) {
+ &s_job->cb)) {
dma_fence_put(s_job->s_fence->parent);
s_job->s_fence->parent = NULL;
atomic_dec(&sched->hw_rq_count);
@@ -426,11 +413,11 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
if (s_job->s_fence->parent) {
r = dma_fence_add_callback(s_job->s_fence->parent,
- &s_job->s_fence->cb,
+ &s_job->cb,
drm_sched_process_job);
if (r == -ENOENT)
drm_sched_process_job(s_job->s_fence->parent,
- &s_job->s_fence->cb);
+ &s_job->cb);
else if (r)
DRM_ERROR("fence add callback failed (%d)\n",
r);
@@ -456,31 +443,34 @@ EXPORT_SYMBOL(drm_sched_stop);
void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
{
struct drm_sched_job *s_job, *tmp;
- unsigned long flags;
int r;
if (!full_recovery)
goto unpark;
- spin_lock_irqsave(&sched->job_list_lock, flags);
+ /*
+ * Locking the list is not required here as the sched thread is parked
+ * so no new jobs are being pushed in to HW and in drm_sched_stop we
+ * flushed all the jobs who were still in mirror list but who already
+ * signaled and removed them self from the list. Also concurrent
+ * GPU recovers can't run in parallel.
+ */
list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
- struct drm_sched_fence *s_fence = s_job->s_fence;
struct dma_fence *fence = s_job->s_fence->parent;
if (fence) {
- r = dma_fence_add_callback(fence, &s_fence->cb,
+ r = dma_fence_add_callback(fence, &s_job->cb,
drm_sched_process_job);
if (r == -ENOENT)
- drm_sched_process_job(fence, &s_fence->cb);
+ drm_sched_process_job(fence, &s_job->cb);
else if (r)
DRM_ERROR("fence add callback failed (%d)\n",
r);
} else
- drm_sched_process_job(NULL, &s_fence->cb);
+ drm_sched_process_job(NULL, &s_job->cb);
}
drm_sched_start_timeout(sched);
- spin_unlock_irqrestore(&sched->job_list_lock, flags);
unpark:
kthread_unpark(sched->thread);
@@ -629,18 +619,27 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
*/
static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
{
- struct drm_sched_fence *s_fence =
- container_of(cb, struct drm_sched_fence, cb);
+ struct drm_sched_job *s_job = container_of(cb, struct drm_sched_job, cb);
+ struct drm_sched_fence *s_fence = s_job->s_fence;
struct drm_gpu_scheduler *sched = s_fence->sched;
+ unsigned long flags;
+
+ cancel_delayed_work(&sched->work_tdr);
- dma_fence_get(&s_fence->finished);
atomic_dec(&sched->hw_rq_count);
atomic_dec(&sched->num_jobs);
+
+ spin_lock_irqsave(&sched->job_list_lock, flags);
+ /* remove job from ring_mirror_list */
+ list_del_init(&s_job->node);
+ spin_unlock_irqrestore(&sched->job_list_lock, flags);
+
drm_sched_fence_finished(s_fence);
trace_drm_sched_process_job(s_fence);
- dma_fence_put(&s_fence->finished);
wake_up_interruptible(&sched->wake_up_worker);
+
+ schedule_work(&s_job->finish_work);
}
/**
@@ -703,16 +702,16 @@ static int drm_sched_main(void *param)
if (fence) {
s_fence->parent = dma_fence_get(fence);
- r = dma_fence_add_callback(fence, &s_fence->cb,
+ r = dma_fence_add_callback(fence, &sched_job->cb,
drm_sched_process_job);
if (r == -ENOENT)
- drm_sched_process_job(fence, &s_fence->cb);
+ drm_sched_process_job(fence, &sched_job->cb);
else if (r)
DRM_ERROR("fence add callback failed (%d)\n",
r);
dma_fence_put(fence);
} else
- drm_sched_process_job(NULL, &s_fence->cb);
+ drm_sched_process_job(NULL, &sched_job->cb);
wake_up(&sched->job_scheduled);
}
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 4f21faf..62c2352 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -138,10 +138,6 @@ struct drm_sched_fence {
struct dma_fence finished;
/**
- * @cb: the callback for the parent fence below.
- */
- struct dma_fence_cb cb;
- /**
* @parent: the fence returned by &drm_sched_backend_ops.run_job
* when scheduling the job on hardware. We signal the
* &drm_sched_fence.finished fence once parent is signalled.
@@ -181,6 +177,7 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f);
* be scheduled further.
* @s_priority: the priority of the job.
* @entity: the entity to which this job belongs.
+ * @cb: the callback for the parent fence in s_fence.
*
* A job is created by the driver using drm_sched_job_init(), and
* should call drm_sched_entity_push_job() once it wants the scheduler
@@ -197,6 +194,7 @@ struct drm_sched_job {
atomic_t karma;
enum drm_sched_priority s_priority;
struct drm_sched_entity *entity;
+ struct dma_fence_cb cb;
};
static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job,
--
2.7.4
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH v6 1/2] drm/sched: Refactor ring mirror list handling.
2018-12-27 19:28 [PATCH v6 1/2] drm/sched: Refactor ring mirror list handling Andrey Grodzovsky
2018-12-27 19:28 ` [PATCH v6 2/2] drm/sched: Rework HW fence processing Andrey Grodzovsky
@ 2018-12-27 22:07 ` kbuild test robot
2019-03-12 7:43 ` Tomeu Vizoso
[not found] ` <1545938887-22901-1-git-send-email-andrey.grodzovsky-5C7GfCeVMHo@public.gmane.org>
3 siblings, 0 replies; 6+ messages in thread
From: kbuild test robot @ 2018-12-27 22:07 UTC (permalink / raw)
To: Andrey Grodzovsky
Cc: ckoenig.leichtzumerken, dri-devel, etnaviv, amd-gfx, kbuild-all,
Monk.Liu
[-- Attachment #1: Type: text/plain, Size: 25900 bytes --]
Hi Andrey,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on linus/master]
[also build test WARNING on next-20181224]
[cannot apply to v4.20]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Andrey-Grodzovsky/drm-sched-Refactor-ring-mirror-list-handling/20181228-035754
reproduce: make htmldocs
All warnings (new ones prefixed by >>):
net/mac80211/sta_info.h:588: warning: Function parameter or member 'rx_stats_avg.chain_signal' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'status_stats.filtered' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'status_stats.retry_failed' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'status_stats.retry_count' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'status_stats.lost_packets' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'status_stats.last_tdls_pkt_time' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'status_stats.msdu_retries' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'status_stats.msdu_failed' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'status_stats.last_ack' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'status_stats.last_ack_signal' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'status_stats.ack_signal_filled' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'status_stats.avg_ack_signal' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'tx_stats.packets' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'tx_stats.bytes' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'tx_stats.last_rate' not described in 'sta_info'
net/mac80211/sta_info.h:588: warning: Function parameter or member 'tx_stats.msdu' not described in 'sta_info'
kernel/rcu/tree.c:711: warning: Excess function parameter 'irq' description in 'rcu_nmi_exit'
include/linux/dma-buf.h:304: warning: Function parameter or member 'cb_excl.cb' not described in 'dma_buf'
include/linux/dma-buf.h:304: warning: Function parameter or member 'cb_excl.poll' not described in 'dma_buf'
include/linux/dma-buf.h:304: warning: Function parameter or member 'cb_excl.active' not described in 'dma_buf'
include/linux/dma-buf.h:304: warning: Function parameter or member 'cb_shared.cb' not described in 'dma_buf'
include/linux/dma-buf.h:304: warning: Function parameter or member 'cb_shared.poll' not described in 'dma_buf'
include/linux/dma-buf.h:304: warning: Function parameter or member 'cb_shared.active' not described in 'dma_buf'
include/linux/dma-fence-array.h:54: warning: Function parameter or member 'work' not described in 'dma_fence_array'
include/linux/gpio/driver.h:375: warning: Function parameter or member 'init_valid_mask' not described in 'gpio_chip'
include/linux/iio/hw-consumer.h:1: warning: no structured comments found
include/linux/input/sparse-keymap.h:46: warning: Function parameter or member 'sw' not described in 'key_entry'
drivers/mtd/nand/raw/nand_base.c:420: warning: Function parameter or member 'chip' not described in 'nand_fill_oob'
drivers/mtd/nand/raw/nand_bbt.c:173: warning: Function parameter or member 'this' not described in 'read_bbt'
drivers/mtd/nand/raw/nand_bbt.c:173: warning: Excess function parameter 'chip' description in 'read_bbt'
include/linux/regulator/machine.h:199: warning: Function parameter or member 'max_uV_step' not described in 'regulation_constraints'
include/linux/regulator/driver.h:228: warning: Function parameter or member 'resume' not described in 'regulator_ops'
arch/s390/include/asm/cio.h:245: warning: Function parameter or member 'esw.esw0' not described in 'irb'
arch/s390/include/asm/cio.h:245: warning: Function parameter or member 'esw.esw1' not described in 'irb'
arch/s390/include/asm/cio.h:245: warning: Function parameter or member 'esw.esw2' not described in 'irb'
arch/s390/include/asm/cio.h:245: warning: Function parameter or member 'esw.esw3' not described in 'irb'
arch/s390/include/asm/cio.h:245: warning: Function parameter or member 'esw.eadm' not described in 'irb'
drivers/slimbus/stream.c:1: warning: no structured comments found
include/linux/spi/spi.h:180: warning: Function parameter or member 'driver_override' not described in 'spi_device'
drivers/target/target_core_device.c:1: warning: no structured comments found
drivers/usb/typec/bus.c:1: warning: no structured comments found
drivers/usb/typec/class.c:1: warning: no structured comments found
include/linux/w1.h:281: warning: Function parameter or member 'of_match_table' not described in 'w1_family'
fs/direct-io.c:257: warning: Excess function parameter 'offset' description in 'dio_complete'
fs/file_table.c:1: warning: no structured comments found
fs/libfs.c:477: warning: Excess function parameter 'available' description in 'simple_write_end'
fs/posix_acl.c:646: warning: Function parameter or member 'inode' not described in 'posix_acl_update_mode'
fs/posix_acl.c:646: warning: Function parameter or member 'mode_p' not described in 'posix_acl_update_mode'
fs/posix_acl.c:646: warning: Function parameter or member 'acl' not described in 'posix_acl_update_mode'
drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c:183: warning: Function parameter or member 'blockable' not described in 'amdgpu_mn_read_lock'
drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c:254: warning: Function parameter or member 'blockable' not described in 'amdgpu_mn_invalidate_range_start_gfx'
drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c:302: warning: Function parameter or member 'blockable' not described in 'amdgpu_mn_invalidate_range_start_hsa'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:382: warning: cannot understand function prototype: 'struct amdgpu_vm_pt_cursor '
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:383: warning: cannot understand function prototype: 'struct amdgpu_vm_pt_cursor '
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:555: warning: Function parameter or member 'adev' not described in 'for_each_amdgpu_vm_pt_leaf'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:555: warning: Function parameter or member 'vm' not described in 'for_each_amdgpu_vm_pt_leaf'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:555: warning: Function parameter or member 'start' not described in 'for_each_amdgpu_vm_pt_leaf'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:555: warning: Function parameter or member 'end' not described in 'for_each_amdgpu_vm_pt_leaf'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:555: warning: Function parameter or member 'cursor' not described in 'for_each_amdgpu_vm_pt_leaf'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:603: warning: Function parameter or member 'adev' not described in 'for_each_amdgpu_vm_pt_dfs_safe'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:603: warning: Function parameter or member 'vm' not described in 'for_each_amdgpu_vm_pt_dfs_safe'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:603: warning: Function parameter or member 'cursor' not described in 'for_each_amdgpu_vm_pt_dfs_safe'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:603: warning: Function parameter or member 'entry' not described in 'for_each_amdgpu_vm_pt_dfs_safe'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:845: warning: Function parameter or member 'level' not described in 'amdgpu_vm_bo_param'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1353: warning: Function parameter or member 'params' not described in 'amdgpu_vm_update_func'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1353: warning: Function parameter or member 'bo' not described in 'amdgpu_vm_update_func'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1353: warning: Function parameter or member 'pe' not described in 'amdgpu_vm_update_func'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1353: warning: Function parameter or member 'addr' not described in 'amdgpu_vm_update_func'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1353: warning: Function parameter or member 'count' not described in 'amdgpu_vm_update_func'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1353: warning: Function parameter or member 'incr' not described in 'amdgpu_vm_update_func'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1353: warning: Function parameter or member 'flags' not described in 'amdgpu_vm_update_func'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1520: warning: Function parameter or member 'params' not described in 'amdgpu_vm_update_huge'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1520: warning: Function parameter or member 'bo' not described in 'amdgpu_vm_update_huge'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1520: warning: Function parameter or member 'level' not described in 'amdgpu_vm_update_huge'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1520: warning: Function parameter or member 'pe' not described in 'amdgpu_vm_update_huge'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1520: warning: Function parameter or member 'addr' not described in 'amdgpu_vm_update_huge'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1520: warning: Function parameter or member 'count' not described in 'amdgpu_vm_update_huge'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1520: warning: Function parameter or member 'incr' not described in 'amdgpu_vm_update_huge'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1520: warning: Function parameter or member 'flags' not described in 'amdgpu_vm_update_huge'
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:3096: warning: Function parameter or member 'pasid' not described in 'amdgpu_vm_make_compute'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:128: warning: Incorrect use of kernel-doc format: * @atomic_obj
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:203: warning: Function parameter or member 'atomic_obj' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:203: warning: Function parameter or member 'atomic_obj_lock' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:203: warning: Function parameter or member 'backlight_link' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:203: warning: Function parameter or member 'backlight_caps' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:203: warning: Function parameter or member 'freesync_module' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:203: warning: Function parameter or member 'fw_dmcu' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:203: warning: Function parameter or member 'dmcu_fw_version' not described in 'amdgpu_display_manager'
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c:1: warning: no structured comments found
include/drm/drm_drv.h:618: warning: Function parameter or member 'gem_prime_pin' not described in 'drm_driver'
include/drm/drm_drv.h:618: warning: Function parameter or member 'gem_prime_unpin' not described in 'drm_driver'
include/drm/drm_drv.h:618: warning: Function parameter or member 'gem_prime_res_obj' not described in 'drm_driver'
include/drm/drm_drv.h:618: warning: Function parameter or member 'gem_prime_get_sg_table' not described in 'drm_driver'
include/drm/drm_drv.h:618: warning: Function parameter or member 'gem_prime_import_sg_table' not described in 'drm_driver'
include/drm/drm_drv.h:618: warning: Function parameter or member 'gem_prime_vmap' not described in 'drm_driver'
include/drm/drm_drv.h:618: warning: Function parameter or member 'gem_prime_vunmap' not described in 'drm_driver'
include/drm/drm_drv.h:618: warning: Function parameter or member 'gem_prime_mmap' not described in 'drm_driver'
include/drm/drm_atomic_state_helper.h:1: warning: no structured comments found
drivers/gpu/drm/drm_dp_helper.c:1362: warning: Function parameter or member 'dsc_dpcd' not described in 'drm_dp_dsc_sink_max_slice_count'
drivers/gpu/drm/drm_dp_helper.c:1362: warning: Function parameter or member 'is_edp' not described in 'drm_dp_dsc_sink_max_slice_count'
>> drivers/gpu/drm/scheduler/sched_main.c:458: warning: Function parameter or member 'full_recovery' not described in 'drm_sched_start'
drivers/gpu/drm/i915/i915_vma.h:49: warning: cannot understand function prototype: 'struct i915_vma '
drivers/gpu/drm/i915/i915_vma.h:1: warning: no structured comments found
drivers/gpu/drm/i915/intel_guc_fwif.h:536: warning: cannot understand function prototype: 'struct guc_log_buffer_state '
drivers/gpu/drm/i915/i915_trace.h:1: warning: no structured comments found
drivers/staging/media/ipu3/include/intel-ipu3.h:122: warning: Function parameter or member '__attribute__((aligned(32' not described in 'ipu3_uapi_awb_config'
drivers/staging/media/ipu3/include/intel-ipu3.h:147: warning: Function parameter or member '__attribute__((aligned(32' not described in 'ipu3_uapi_ae_raw_buffer_aligned'
drivers/staging/media/ipu3/include/intel-ipu3.h:256: warning: Function parameter or member '__attribute__((aligned(32' not described in 'ipu3_uapi_ae_config'
drivers/staging/media/ipu3/include/intel-ipu3.h:413: warning: Function parameter or member '__attribute__((aligned(32' not described in 'ipu3_uapi_af_config_s'
drivers/staging/media/ipu3/include/intel-ipu3.h:476: warning: Function parameter or member '__attribute__((aligned(32' not described in 'ipu3_uapi_4a_config'
drivers/staging/media/ipu3/include/intel-ipu3.h:502: warning: Function parameter or member '__attribute__((aligned(32' not described in 'ipu3_uapi_bubble_info'
drivers/staging/media/ipu3/include/intel-ipu3.h:534: warning: Function parameter or member '__attribute__((aligned(32' not described in 'ipu3_uapi_ff_status'
drivers/staging/media/ipu3/include/intel-ipu3.h:1001: warning: Function parameter or member '__attribute__((aligned(32' not described in 'ipu3_uapi_gamma_config'
drivers/staging/media/ipu3/include/intel-ipu3.h:1205: warning: Function parameter or member '__attribute__((aligned(32' not described in 'ipu3_uapi_shd_config'
drivers/staging/media/ipu3/include/intel-ipu3.h:2425: warning: Function parameter or member '__attribute__((aligned(32' not described in 'ipu3_uapi_anr_config'
drivers/staging/media/ipu3/include/intel-ipu3.h:2485: warning: Function parameter or member '__attribute__((aligned(32' not described in 'ipu3_uapi_acc_param'
drivers/staging/media/ipu3/include/intel-ipu3.h:2783: warning: Function parameter or member '__attribute__((aligned(32' not described in 'ipu3_uapi_params'
include/linux/skbuff.h:862: warning: Function parameter or member 'dev_scratch' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'list' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'ip_defrag_offset' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'skb_mstamp_ns' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member '__cloned_offset' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'head_frag' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member '__pkt_type_offset' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'encapsulation' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'encap_hdr_csum' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'csum_valid' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'csum_complete_sw' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'csum_level' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'inner_protocol_type' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'remcsum_offload' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'offload_fwd_mark' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'offload_mr_fwd_mark' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'sender_cpu' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'reserved_tailroom' not described in 'sk_buff'
include/linux/skbuff.h:862: warning: Function parameter or member 'inner_ipproto' not described in 'sk_buff'
include/net/sock.h:238: warning: Function parameter or member 'skc_addrpair' not described in 'sock_common'
include/net/sock.h:238: warning: Function parameter or member 'skc_portpair' not described in 'sock_common'
include/net/sock.h:238: warning: Function parameter or member 'skc_ipv6only' not described in 'sock_common'
include/net/sock.h:238: warning: Function parameter or member 'skc_net_refcnt' not described in 'sock_common'
include/net/sock.h:238: warning: Function parameter or member 'skc_v6_daddr' not described in 'sock_common'
include/net/sock.h:238: warning: Function parameter or member 'skc_v6_rcv_saddr' not described in 'sock_common'
include/net/sock.h:238: warning: Function parameter or member 'skc_cookie' not described in 'sock_common'
include/net/sock.h:238: warning: Function parameter or member 'skc_listener' not described in 'sock_common'
include/net/sock.h:238: warning: Function parameter or member 'skc_tw_dr' not described in 'sock_common'
include/net/sock.h:238: warning: Function parameter or member 'skc_rcv_wnd' not described in 'sock_common'
include/net/sock.h:238: warning: Function parameter or member 'skc_tw_rcv_nxt' not described in 'sock_common'
include/net/sock.h:509: warning: Function parameter or member 'sk_backlog.rmem_alloc' not described in 'sock'
include/net/sock.h:509: warning: Function parameter or member 'sk_backlog.len' not described in 'sock'
include/net/sock.h:509: warning: Function parameter or member 'sk_backlog.head' not described in 'sock'
include/net/sock.h:509: warning: Function parameter or member 'sk_backlog.tail' not described in 'sock'
include/net/sock.h:509: warning: Function parameter or member 'sk_wq_raw' not described in 'sock'
include/net/sock.h:509: warning: Function parameter or member 'tcp_rtx_queue' not described in 'sock'
include/net/sock.h:509: warning: Function parameter or member 'sk_route_forced_caps' not described in 'sock'
include/net/sock.h:509: warning: Function parameter or member 'sk_txtime_report_errors' not described in 'sock'
include/net/sock.h:509: warning: Function parameter or member 'sk_validate_xmit_skb' not described in 'sock'
include/linux/netdevice.h:2052: warning: Function parameter or member 'adj_list.upper' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'adj_list.lower' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'gso_partial_features' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'switchdev_ops' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'l3mdev_ops' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'xfrmdev_ops' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'tlsdev_ops' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'name_assign_type' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'ieee802154_ptr' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'mpls_ptr' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'xdp_prog' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'gro_flush_timeout' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'nf_hooks_ingress' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member '____cacheline_aligned_in_smp' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'qdisc_hash' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'xps_cpus_map' not described in 'net_device'
include/linux/netdevice.h:2052: warning: Function parameter or member 'xps_rxqs_map' not described in 'net_device'
include/linux/phylink.h:56: warning: Function parameter or member '__ETHTOOL_DECLARE_LINK_MODE_MASK(advertising' not described in 'phylink_link_state'
include/linux/phylink.h:56: warning: Function parameter or member '__ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising' not described in 'phylink_link_state'
Documentation/admin-guide/cgroup-v2.rst:1507: WARNING: Block quote ends without a blank line; unexpected unindent.
Documentation/admin-guide/cgroup-v2.rst:1509: WARNING: Block quote ends without a blank line; unexpected unindent.
Documentation/admin-guide/cgroup-v2.rst:1510: WARNING: Block quote ends without a blank line; unexpected unindent.
include/linux/interrupt.h:252: WARNING: Inline emphasis start-string without end-string.
include/net/mac80211.h:1211: ERROR: Unexpected indentation.
include/net/mac80211.h:1218: WARNING: Block quote ends without a blank line; unexpected unindent.
include/linux/wait.h:110: WARNING: Block quote ends without a blank line; unexpected unindent.
include/linux/wait.h:113: ERROR: Unexpected indentation.
include/linux/wait.h:115: WARNING: Block quote ends without a blank line; unexpected unindent.
kernel/time/hrtimer.c:1120: WARNING: Block quote ends without a blank line; unexpected unindent.
kernel/signal.c:344: WARNING: Inline literal start-string without end-string.
include/linux/kernel.h:137: WARNING: Inline interpreted text or phrase reference start-string without end-string.
include/uapi/linux/firewire-cdev.h:312: WARNING: Inline literal start-string without end-string.
Documentation/driver-api/gpio/board.rst:209: ERROR: Unexpected indentation.
drivers/ata/libata-core.c:5959: ERROR: Unknown target name: "hw".
drivers/message/fusion/mptbase.c:5057: WARNING: Definition list ends without a blank line; unexpected unindent.
drivers/tty/serial/serial_core.c:1938: WARNING: Definition list ends without a blank line; unexpected unindent.
include/linux/mtd/rawnand.h:1192: WARNING: Inline strong start-string without end-string.
include/linux/mtd/rawnand.h:1194: WARNING: Inline strong start-string without end-string.
include/linux/regulator/driver.h:287: ERROR: Unknown target name: "regulator_regmap_x_voltage".
Documentation/driver-api/soundwire/locking.rst:50: ERROR: Inconsistent literal block quoting.
Documentation/driver-api/soundwire/locking.rst:51: WARNING: Line block ends without a blank line.
Documentation/driver-api/soundwire/locking.rst:55: WARNING: Inline substitution_reference start-string without end-string.
Documentation/driver-api/soundwire/locking.rst:56: WARNING: Line block ends without a blank line.
include/linux/spi/spi.h:368: ERROR: Unexpected indentation.
Documentation/driver-api/usb/typec_bus.rst:76: WARNING: Definition list ends without a blank line; unexpected unindent.
vim +458 drivers/gpu/drm/scheduler/sched_main.c
449
450 /**
451 * drm_sched_job_recovery - recover jobs after a reset
452 *
453 * @sched: scheduler instance
454 *
455 */
456 void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
457 {
> 458 struct drm_sched_job *s_job, *tmp;
459 unsigned long flags;
460 int r;
461
462 if (!full_recovery)
463 goto unpark;
464
465 spin_lock_irqsave(&sched->job_list_lock, flags);
466 list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
467 struct drm_sched_fence *s_fence = s_job->s_fence;
468 struct dma_fence *fence = s_job->s_fence->parent;
469
470 if (fence) {
471 r = dma_fence_add_callback(fence, &s_fence->cb,
472 drm_sched_process_job);
473 if (r == -ENOENT)
474 drm_sched_process_job(fence, &s_fence->cb);
475 else if (r)
476 DRM_ERROR("fence add callback failed (%d)\n",
477 r);
478 } else
479 drm_sched_process_job(NULL, &s_fence->cb);
480 }
481
482 drm_sched_start_timeout(sched);
483 spin_unlock_irqrestore(&sched->job_list_lock, flags);
484
485 unpark:
486 kthread_unpark(sched->thread);
487 }
488 EXPORT_SYMBOL(drm_sched_start);
489
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 6600 bytes --]
[-- Attachment #3: Type: text/plain, Size: 160 bytes --]
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v6 1/2] drm/sched: Refactor ring mirror list handling.
2018-12-27 19:28 [PATCH v6 1/2] drm/sched: Refactor ring mirror list handling Andrey Grodzovsky
2018-12-27 19:28 ` [PATCH v6 2/2] drm/sched: Rework HW fence processing Andrey Grodzovsky
2018-12-27 22:07 ` [PATCH v6 1/2] drm/sched: Refactor ring mirror list handling kbuild test robot
@ 2019-03-12 7:43 ` Tomeu Vizoso
[not found] ` <CAAObsKARq5eM__GxfCLAN7d1Y7d3LwjHPDJ=LE6BKvYiq=PLRw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
[not found] ` <1545938887-22901-1-git-send-email-andrey.grodzovsky-5C7GfCeVMHo@public.gmane.org>
3 siblings, 1 reply; 6+ messages in thread
From: Tomeu Vizoso @ 2019-03-12 7:43 UTC (permalink / raw)
To: Andrey Grodzovsky
Cc: ckoenig.leichtzumerken, etnaviv, amd-gfx, dri-devel, Monk.Liu
On Thu, 27 Dec 2018 at 20:28, Andrey Grodzovsky
<andrey.grodzovsky@amd.com> wrote:
>
> Decauple sched threads stop and start and ring mirror
> list handling from the policy of what to do about the
> guilty jobs.
> When stoppping the sched thread and detaching sched fences
> from non signaled HW fenes wait for all signaled HW fences
> to complete before rerunning the jobs.
>
> v2: Fix resubmission of guilty job into HW after refactoring.
>
> v4:
> Full restart for all the jobs, not only from guilty ring.
> Extract karma increase into standalone function.
>
> v5:
> Rework waiting for signaled jobs without relying on the job
> struct itself as those might already be freed for non 'guilty'
> job's schedulers.
> Expose karma increase to drivers.
>
> v6:
> Use list_for_each_entry_safe_continue and drm_sched_process_job
> in case fence already signaled.
> Call drm_sched_increase_karma only once for amdgpu and add documentation.
>
> Suggested-by: Christian Koenig <Christian.Koenig@amd.com>
> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 20 ++-
> drivers/gpu/drm/etnaviv/etnaviv_sched.c | 11 +-
> drivers/gpu/drm/scheduler/sched_main.c | 195 +++++++++++++++++++----------
> drivers/gpu/drm/v3d/v3d_sched.c | 12 +-
> include/drm/gpu_scheduler.h | 8 +-
> 5 files changed, 157 insertions(+), 89 deletions(-)
>
[snip]
> diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
> index 445b2ef..f76d9ed 100644
> --- a/drivers/gpu/drm/v3d/v3d_sched.c
> +++ b/drivers/gpu/drm/v3d/v3d_sched.c
> @@ -178,18 +178,22 @@ v3d_job_timedout(struct drm_sched_job *sched_job)
> for (q = 0; q < V3D_MAX_QUEUES; q++) {
> struct drm_gpu_scheduler *sched = &v3d->queue[q].sched;
>
> - kthread_park(sched->thread);
> - drm_sched_hw_job_reset(sched, (sched_job->sched == sched ?
> + drm_sched_stop(sched, (sched_job->sched == sched ?
> sched_job : NULL));
> +
> + if(sched_job)
> + drm_sched_increase_karma(sched_job);
> }
>
> /* get the GPU back into the init state */
> v3d_reset(v3d);
>
> + for (q = 0; q < V3D_MAX_QUEUES; q++)
> + drm_sched_resubmit_jobs(sched_job->sched);
Hi Andrey,
I'm not sure of what was the original intent, but I guess it wasn't to
repeatedly call resubmit_jobs on that specific job's queue?
Regards,
Tomeu
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v6 1/2] drm/sched: Refactor ring mirror list handling.
[not found] ` <CAAObsKARq5eM__GxfCLAN7d1Y7d3LwjHPDJ=LE6BKvYiq=PLRw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
@ 2019-03-12 14:56 ` Grodzovsky, Andrey
0 siblings, 0 replies; 6+ messages in thread
From: Grodzovsky, Andrey @ 2019-03-12 14:56 UTC (permalink / raw)
To: Tomeu Vizoso
Cc: ckoenig.leichtzumerken-Re5JQEeQqe8AvxtiuMwx3w,
etnaviv-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW,
amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW, Eric Anholt, dri-devel,
Liu, Monk
On 3/12/19 3:43 AM, Tomeu Vizoso wrote:
> On Thu, 27 Dec 2018 at 20:28, Andrey Grodzovsky
> <andrey.grodzovsky@amd.com> wrote:
>> Decauple sched threads stop and start and ring mirror
>> list handling from the policy of what to do about the
>> guilty jobs.
>> When stoppping the sched thread and detaching sched fences
>> from non signaled HW fenes wait for all signaled HW fences
>> to complete before rerunning the jobs.
>>
>> v2: Fix resubmission of guilty job into HW after refactoring.
>>
>> v4:
>> Full restart for all the jobs, not only from guilty ring.
>> Extract karma increase into standalone function.
>>
>> v5:
>> Rework waiting for signaled jobs without relying on the job
>> struct itself as those might already be freed for non 'guilty'
>> job's schedulers.
>> Expose karma increase to drivers.
>>
>> v6:
>> Use list_for_each_entry_safe_continue and drm_sched_process_job
>> in case fence already signaled.
>> Call drm_sched_increase_karma only once for amdgpu and add documentation.
>>
>> Suggested-by: Christian Koenig <Christian.Koenig@amd.com>
>> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
>> ---
>> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 20 ++-
>> drivers/gpu/drm/etnaviv/etnaviv_sched.c | 11 +-
>> drivers/gpu/drm/scheduler/sched_main.c | 195 +++++++++++++++++++----------
>> drivers/gpu/drm/v3d/v3d_sched.c | 12 +-
>> include/drm/gpu_scheduler.h | 8 +-
>> 5 files changed, 157 insertions(+), 89 deletions(-)
>>
> [snip]
>> diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
>> index 445b2ef..f76d9ed 100644
>> --- a/drivers/gpu/drm/v3d/v3d_sched.c
>> +++ b/drivers/gpu/drm/v3d/v3d_sched.c
>> @@ -178,18 +178,22 @@ v3d_job_timedout(struct drm_sched_job *sched_job)
>> for (q = 0; q < V3D_MAX_QUEUES; q++) {
>> struct drm_gpu_scheduler *sched = &v3d->queue[q].sched;
>>
>> - kthread_park(sched->thread);
>> - drm_sched_hw_job_reset(sched, (sched_job->sched == sched ?
>> + drm_sched_stop(sched, (sched_job->sched == sched ?
>> sched_job : NULL));
>> +
>> + if(sched_job)
>> + drm_sched_increase_karma(sched_job);
>> }
>>
>> /* get the GPU back into the init state */
>> v3d_reset(v3d);
>>
>> + for (q = 0; q < V3D_MAX_QUEUES; q++)
>> + drm_sched_resubmit_jobs(sched_job->sched);
> Hi Andrey,
>
> I'm not sure of what was the original intent, but I guess it wasn't to
> repeatedly call resubmit_jobs on that specific job's queue?
>
> Regards,
>
> Tomeu
My bad, there is also another mistake here with increasing karma for
the guilty job's entity multiple times. I will fix that. Thanks for
pointing out.
Andrey
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v6 1/2] drm/sched: Refactor ring mirror list handling.
[not found] ` <1545938887-22901-1-git-send-email-andrey.grodzovsky-5C7GfCeVMHo@public.gmane.org>
@ 2019-05-29 10:04 ` Daniel Vetter
0 siblings, 0 replies; 6+ messages in thread
From: Daniel Vetter @ 2019-05-29 10:04 UTC (permalink / raw)
To: Andrey Grodzovsky
Cc: Christian König, The etnaviv authors, amd-gfx list, Anholt,
Eric, dri-devel, Liu, Monk
On Thu, Dec 27, 2018 at 8:28 PM Andrey Grodzovsky
<andrey.grodzovsky@amd.com> wrote:
>
> Decauple sched threads stop and start and ring mirror
> list handling from the policy of what to do about the
> guilty jobs.
> When stoppping the sched thread and detaching sched fences
> from non signaled HW fenes wait for all signaled HW fences
> to complete before rerunning the jobs.
>
> v2: Fix resubmission of guilty job into HW after refactoring.
>
> v4:
> Full restart for all the jobs, not only from guilty ring.
> Extract karma increase into standalone function.
>
> v5:
> Rework waiting for signaled jobs without relying on the job
> struct itself as those might already be freed for non 'guilty'
> job's schedulers.
> Expose karma increase to drivers.
>
> v6:
> Use list_for_each_entry_safe_continue and drm_sched_process_job
> in case fence already signaled.
> Call drm_sched_increase_karma only once for amdgpu and add documentation.
>
> Suggested-by: Christian Koenig <Christian.Koenig@amd.com>
> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
./drivers/gpu/drm/scheduler/sched_main.c:429: warning: Function
parameter or member 'full_recovery' not described in 'drm_sched_start'
Please fix, thanks.
-Daniel
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 20 ++-
> drivers/gpu/drm/etnaviv/etnaviv_sched.c | 11 +-
> drivers/gpu/drm/scheduler/sched_main.c | 195 +++++++++++++++++++----------
> drivers/gpu/drm/v3d/v3d_sched.c | 12 +-
> include/drm/gpu_scheduler.h | 8 +-
> 5 files changed, 157 insertions(+), 89 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 98df8e4..6a0601c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -3298,17 +3298,15 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
> if (!ring || !ring->sched.thread)
> continue;
>
> - kthread_park(ring->sched.thread);
> -
> - if (job && job->base.sched != &ring->sched)
> - continue;
> -
> - drm_sched_hw_job_reset(&ring->sched, job ? &job->base : NULL);
> + drm_sched_stop(&ring->sched, job ? &job->base : NULL);
>
> /* after all hw jobs are reset, hw fence is meaningless, so force_completion */
> amdgpu_fence_driver_force_completion(ring);
> }
>
> + if(job)
> + drm_sched_increase_karma(&job->base);
> +
>
>
> if (!amdgpu_sriov_vf(adev)) {
> @@ -3454,14 +3452,10 @@ static void amdgpu_device_post_asic_reset(struct amdgpu_device *adev,
> if (!ring || !ring->sched.thread)
> continue;
>
> - /* only need recovery sched of the given job's ring
> - * or all rings (in the case @job is NULL)
> - * after above amdgpu_reset accomplished
> - */
> - if ((!job || job->base.sched == &ring->sched) && !adev->asic_reset_res)
> - drm_sched_job_recovery(&ring->sched);
> + if (!adev->asic_reset_res)
> + drm_sched_resubmit_jobs(&ring->sched);
>
> - kthread_unpark(ring->sched.thread);
> + drm_sched_start(&ring->sched, !adev->asic_reset_res);
> }
>
> if (!amdgpu_device_has_dc_support(adev)) {
> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> index 49a6763..6f1268f 100644
> --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> @@ -109,16 +109,19 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job)
> }
>
> /* block scheduler */
> - kthread_park(gpu->sched.thread);
> - drm_sched_hw_job_reset(&gpu->sched, sched_job);
> + drm_sched_stop(&gpu->sched, sched_job);
> +
> + if(sched_job)
> + drm_sched_increase_karma(sched_job);
>
> /* get the GPU back into the init state */
> etnaviv_core_dump(gpu);
> etnaviv_gpu_recover_hang(gpu);
>
> + drm_sched_resubmit_jobs(&gpu->sched);
> +
> /* restart scheduler after GPU is usable again */
> - drm_sched_job_recovery(&gpu->sched);
> - kthread_unpark(gpu->sched.thread);
> + drm_sched_start(&gpu->sched, true);
> }
>
> static void etnaviv_sched_free_job(struct drm_sched_job *sched_job)
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index dbb6906..54e809b 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -60,8 +60,6 @@
>
> static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb);
>
> -static void drm_sched_expel_job_unlocked(struct drm_sched_job *s_job);
> -
> /**
> * drm_sched_rq_init - initialize a given run queue struct
> *
> @@ -335,6 +333,51 @@ static void drm_sched_job_timedout(struct work_struct *work)
> spin_unlock_irqrestore(&sched->job_list_lock, flags);
> }
>
> + /**
> + * drm_sched_increase_karma - Update sched_entity guilty flag
> + *
> + * @bad: The job guilty of time out
> + *
> + * Increment on every hang caused by the 'bad' job. If this exceeds the hang
> + * limit of the scheduler then the respective sched entity is marked guilty and
> + * jobs from it will not be scheduled further
> + */
> +void drm_sched_increase_karma(struct drm_sched_job *bad)
> +{
> + int i;
> + struct drm_sched_entity *tmp;
> + struct drm_sched_entity *entity;
> + struct drm_gpu_scheduler *sched = bad->sched;
> +
> + /* don't increase @bad's karma if it's from KERNEL RQ,
> + * because sometimes GPU hang would cause kernel jobs (like VM updating jobs)
> + * corrupt but keep in mind that kernel jobs always considered good.
> + */
> + if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
> + atomic_inc(&bad->karma);
> + for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL;
> + i++) {
> + struct drm_sched_rq *rq = &sched->sched_rq[i];
> +
> + spin_lock(&rq->lock);
> + list_for_each_entry_safe(entity, tmp, &rq->entities, list) {
> + if (bad->s_fence->scheduled.context ==
> + entity->fence_context) {
> + if (atomic_read(&bad->karma) >
> + bad->sched->hang_limit)
> + if (entity->guilty)
> + atomic_set(entity->guilty, 1);
> + break;
> + }
> + }
> + spin_unlock(&rq->lock);
> + if (&entity->list != &rq->entities)
> + break;
> + }
> + }
> +}
> +EXPORT_SYMBOL(drm_sched_increase_karma);
> +
> /**
> * drm_sched_hw_job_reset - stop the scheduler if it contains the bad job
> *
> @@ -342,13 +385,22 @@ static void drm_sched_job_timedout(struct work_struct *work)
> * @bad: bad scheduler job
> *
> */
> -void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
> +void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
> {
> - struct drm_sched_job *s_job;
> - struct drm_sched_entity *entity, *tmp;
> + struct drm_sched_job *s_job, *tmp;
> unsigned long flags;
> - int i;
> + struct dma_fence *wait_fence = NULL;
> + int r;
> +
> + kthread_park(sched->thread);
>
> + /*
> + * Verify all the signaled jobs in mirror list are removed from the ring
> + * by waiting for their respective scheduler fences to signal.
> + * Continually repeat traversing the ring mirror list until no more signaled
> + * fences are found
> + */
> +retry_wait:
> spin_lock_irqsave(&sched->job_list_lock, flags);
> list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) {
> if (s_job->s_fence->parent &&
> @@ -357,35 +409,43 @@ void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_jo
> dma_fence_put(s_job->s_fence->parent);
> s_job->s_fence->parent = NULL;
> atomic_dec(&sched->hw_rq_count);
> + } else {
> + wait_fence = dma_fence_get(&s_job->s_fence->finished);
> + break;
> }
> }
> - spin_unlock_irqrestore(&sched->job_list_lock, flags);
>
> - if (bad && bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
> - atomic_inc(&bad->karma);
> - /* don't increase @bad's karma if it's from KERNEL RQ,
> - * becuase sometimes GPU hang would cause kernel jobs (like VM updating jobs)
> - * corrupt but keep in mind that kernel jobs always considered good.
> - */
> - for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL; i++ ) {
> - struct drm_sched_rq *rq = &sched->sched_rq[i];
> + /* No signaled jobs in the ring, its safe to proceed to ASIC reset */
> + if (!wait_fence) {
> + spin_unlock_irqrestore(&sched->job_list_lock, flags);
> + return;
> + }
>
> - spin_lock(&rq->lock);
> - list_for_each_entry_safe(entity, tmp, &rq->entities, list) {
> - if (bad->s_fence->scheduled.context == entity->fence_context) {
> - if (atomic_read(&bad->karma) > bad->sched->hang_limit)
> - if (entity->guilty)
> - atomic_set(entity->guilty, 1);
> - break;
> - }
> - }
> - spin_unlock(&rq->lock);
> - if (&entity->list != &rq->entities)
> - break;
> + /* Restore removed cb since removing again already removed cb is undefined */
> + list_for_each_entry_safe_continue(s_job, tmp, &sched->ring_mirror_list, node) {
> +
> + if (s_job->s_fence->parent) {
> + r = dma_fence_add_callback(s_job->s_fence->parent,
> + &s_job->s_fence->cb,
> + drm_sched_process_job);
> + if (r == -ENOENT)
> + drm_sched_process_job(s_job->s_fence->parent,
> + &s_job->s_fence->cb);
> + else if (r)
> + DRM_ERROR("fence add callback failed (%d)\n",
> + r);
> }
> }
> + spin_unlock_irqrestore(&sched->job_list_lock, flags);
> +
> + dma_fence_wait(wait_fence, false);
> + dma_fence_put(wait_fence);
> + wait_fence = NULL;
> +
> + goto retry_wait;
> }
> -EXPORT_SYMBOL(drm_sched_hw_job_reset);
> +
> +EXPORT_SYMBOL(drm_sched_stop);
>
> /**
> * drm_sched_job_recovery - recover jobs after a reset
> @@ -393,33 +453,21 @@ EXPORT_SYMBOL(drm_sched_hw_job_reset);
> * @sched: scheduler instance
> *
> */
> -void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
> +void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
> {
> struct drm_sched_job *s_job, *tmp;
> - bool found_guilty = false;
> unsigned long flags;
> int r;
>
> + if (!full_recovery)
> + goto unpark;
> +
> spin_lock_irqsave(&sched->job_list_lock, flags);
> list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
> struct drm_sched_fence *s_fence = s_job->s_fence;
> - struct dma_fence *fence;
> - uint64_t guilty_context;
> -
> - if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) {
> - found_guilty = true;
> - guilty_context = s_job->s_fence->scheduled.context;
> - }
> -
> - if (found_guilty && s_job->s_fence->scheduled.context == guilty_context)
> - dma_fence_set_error(&s_fence->finished, -ECANCELED);
> -
> - spin_unlock_irqrestore(&sched->job_list_lock, flags);
> - fence = sched->ops->run_job(s_job);
> - atomic_inc(&sched->hw_rq_count);
> + struct dma_fence *fence = s_job->s_fence->parent;
>
> if (fence) {
> - s_fence->parent = dma_fence_get(fence);
> r = dma_fence_add_callback(fence, &s_fence->cb,
> drm_sched_process_job);
> if (r == -ENOENT)
> @@ -427,18 +475,47 @@ void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
> else if (r)
> DRM_ERROR("fence add callback failed (%d)\n",
> r);
> - dma_fence_put(fence);
> - } else {
> - if (s_fence->finished.error < 0)
> - drm_sched_expel_job_unlocked(s_job);
> + } else
> drm_sched_process_job(NULL, &s_fence->cb);
> - }
> - spin_lock_irqsave(&sched->job_list_lock, flags);
> }
> +
> drm_sched_start_timeout(sched);
> spin_unlock_irqrestore(&sched->job_list_lock, flags);
> +
> +unpark:
> + kthread_unpark(sched->thread);
> +}
> +EXPORT_SYMBOL(drm_sched_start);
> +
> +/**
> + * drm_sched_resubmit_jobs - helper to relunch job from mirror ring list
> + *
> + * @sched: scheduler instance
> + *
> + */
> +void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
> +{
> + struct drm_sched_job *s_job, *tmp;
> + uint64_t guilty_context;
> + bool found_guilty = false;
> +
> + /*TODO DO we need spinlock here ? */
> + list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
> + struct drm_sched_fence *s_fence = s_job->s_fence;
> +
> + if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) {
> + found_guilty = true;
> + guilty_context = s_job->s_fence->scheduled.context;
> + }
> +
> + if (found_guilty && s_job->s_fence->scheduled.context == guilty_context)
> + dma_fence_set_error(&s_fence->finished, -ECANCELED);
> +
> + s_job->s_fence->parent = sched->ops->run_job(s_job);
> + atomic_inc(&sched->hw_rq_count);
> + }
> }
> -EXPORT_SYMBOL(drm_sched_job_recovery);
> +EXPORT_SYMBOL(drm_sched_resubmit_jobs);
>
> /**
> * drm_sched_job_init - init a scheduler job
> @@ -634,26 +711,14 @@ static int drm_sched_main(void *param)
> DRM_ERROR("fence add callback failed (%d)\n",
> r);
> dma_fence_put(fence);
> - } else {
> - if (s_fence->finished.error < 0)
> - drm_sched_expel_job_unlocked(sched_job);
> + } else
> drm_sched_process_job(NULL, &s_fence->cb);
> - }
>
> wake_up(&sched->job_scheduled);
> }
> return 0;
> }
>
> -static void drm_sched_expel_job_unlocked(struct drm_sched_job *s_job)
> -{
> - struct drm_gpu_scheduler *sched = s_job->sched;
> -
> - spin_lock(&sched->job_list_lock);
> - list_del_init(&s_job->node);
> - spin_unlock(&sched->job_list_lock);
> -}
> -
> /**
> * drm_sched_init - Init a gpu scheduler instance
> *
> diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
> index 445b2ef..f76d9ed 100644
> --- a/drivers/gpu/drm/v3d/v3d_sched.c
> +++ b/drivers/gpu/drm/v3d/v3d_sched.c
> @@ -178,18 +178,22 @@ v3d_job_timedout(struct drm_sched_job *sched_job)
> for (q = 0; q < V3D_MAX_QUEUES; q++) {
> struct drm_gpu_scheduler *sched = &v3d->queue[q].sched;
>
> - kthread_park(sched->thread);
> - drm_sched_hw_job_reset(sched, (sched_job->sched == sched ?
> + drm_sched_stop(sched, (sched_job->sched == sched ?
> sched_job : NULL));
> +
> + if(sched_job)
> + drm_sched_increase_karma(sched_job);
> }
>
> /* get the GPU back into the init state */
> v3d_reset(v3d);
>
> + for (q = 0; q < V3D_MAX_QUEUES; q++)
> + drm_sched_resubmit_jobs(sched_job->sched);
> +
> /* Unblock schedulers and restart their jobs. */
> for (q = 0; q < V3D_MAX_QUEUES; q++) {
> - drm_sched_job_recovery(&v3d->queue[q].sched);
> - kthread_unpark(v3d->queue[q].sched.thread);
> + drm_sched_start(&v3d->queue[q].sched, true);
> }
>
> mutex_unlock(&v3d->reset_lock);
> diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
> index 47e1979..4f21faf 100644
> --- a/include/drm/gpu_scheduler.h
> +++ b/include/drm/gpu_scheduler.h
> @@ -298,9 +298,11 @@ int drm_sched_job_init(struct drm_sched_job *job,
> void *owner);
> void drm_sched_job_cleanup(struct drm_sched_job *job);
> void drm_sched_wakeup(struct drm_gpu_scheduler *sched);
> -void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched,
> - struct drm_sched_job *job);
> -void drm_sched_job_recovery(struct drm_gpu_scheduler *sched);
> +void drm_sched_stop(struct drm_gpu_scheduler *sched,
> + struct drm_sched_job *job);
> +void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery);
> +void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched);
> +void drm_sched_increase_karma(struct drm_sched_job *bad);
> bool drm_sched_dependency_optimized(struct dma_fence* fence,
> struct drm_sched_entity *entity);
> void drm_sched_fault(struct drm_gpu_scheduler *sched);
> --
> 2.7.4
>
> _______________________________________________
> dri-devel mailing list
> dri-devel@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/dri-devel
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2019-05-29 10:04 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-12-27 19:28 [PATCH v6 1/2] drm/sched: Refactor ring mirror list handling Andrey Grodzovsky
2018-12-27 19:28 ` [PATCH v6 2/2] drm/sched: Rework HW fence processing Andrey Grodzovsky
2018-12-27 22:07 ` [PATCH v6 1/2] drm/sched: Refactor ring mirror list handling kbuild test robot
2019-03-12 7:43 ` Tomeu Vizoso
[not found] ` <CAAObsKARq5eM__GxfCLAN7d1Y7d3LwjHPDJ=LE6BKvYiq=PLRw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2019-03-12 14:56 ` Grodzovsky, Andrey
[not found] ` <1545938887-22901-1-git-send-email-andrey.grodzovsky-5C7GfCeVMHo@public.gmane.org>
2019-05-29 10:04 ` Daniel Vetter
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.