[PATCH 1/3] drm/scheduler: rework job destruction
Andrey Grodzovsky
andrey.grodzovsky at amd.com
Mon Apr 8 16:08:10 UTC 2019
From: Christian König <christian.koenig at amd.com>
We now destroy finished jobs from the worker thread to make sure that
we never destroy a job currently in timeout processing.
By this we avoid holding lock around ring mirror list in drm_sched_stop
which should solve a deadlock reported by a user.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109692
Signed-off-by: Christian König <christian.koenig at amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky at amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 17 ++--
drivers/gpu/drm/etnaviv/etnaviv_dump.c | 4 -
drivers/gpu/drm/etnaviv/etnaviv_sched.c | 9 +-
drivers/gpu/drm/scheduler/sched_main.c | 140 +++++++++++++++++------------
drivers/gpu/drm/v3d/v3d_sched.c | 9 +-
include/drm/gpu_scheduler.h | 6 +-
6 files changed, 110 insertions(+), 75 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index fcb3d95..aabd043 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3339,15 +3339,23 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
if (!ring || !ring->sched.thread)
continue;
- drm_sched_stop(&ring->sched);
+ drm_sched_stop(&ring->sched, &job->base);
/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
amdgpu_fence_driver_force_completion(ring);
}
- if(job)
+ if(job) {
drm_sched_increase_karma(&job->base);
+ /*
+ * Guilty job did complete and hence needs to be manually removed
+ * See drm_sched_stop doc.
+ */
+ if (list_empty(&job->base.node))
+ job->base.sched->ops->free_job(&job->base);
+ }
+
if (!amdgpu_sriov_vf(adev)) {
@@ -3487,8 +3495,7 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
return r;
}
-static void amdgpu_device_post_asic_reset(struct amdgpu_device *adev,
- struct amdgpu_job *job)
+static void amdgpu_device_post_asic_reset(struct amdgpu_device *adev)
{
int i;
@@ -3628,7 +3635,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
/* Post ASIC reset for all devs .*/
list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
- amdgpu_device_post_asic_reset(tmp_adev, tmp_adev == adev ? job : NULL);
+ amdgpu_device_post_asic_reset(tmp_adev);
if (r) {
/* bad news, how to tell it to userspace ? */
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c
index 3fbb485..8434715 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c
@@ -135,13 +135,11 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu)
mmu_size + gpu->buffer.size;
/* Add in the active command buffers */
- spin_lock_irqsave(&gpu->sched.job_list_lock, flags);
list_for_each_entry(s_job, &gpu->sched.ring_mirror_list, node) {
submit = to_etnaviv_submit(s_job);
file_size += submit->cmdbuf.size;
n_obj++;
}
- spin_unlock_irqrestore(&gpu->sched.job_list_lock, flags);
/* Add in the active buffer objects */
list_for_each_entry(vram, &gpu->mmu->mappings, mmu_node) {
@@ -183,14 +181,12 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu)
gpu->buffer.size,
etnaviv_cmdbuf_get_va(&gpu->buffer));
- spin_lock_irqsave(&gpu->sched.job_list_lock, flags);
list_for_each_entry(s_job, &gpu->sched.ring_mirror_list, node) {
submit = to_etnaviv_submit(s_job);
etnaviv_core_dump_mem(&iter, ETDUMP_BUF_CMD,
submit->cmdbuf.vaddr, submit->cmdbuf.size,
etnaviv_cmdbuf_get_va(&submit->cmdbuf));
}
- spin_unlock_irqrestore(&gpu->sched.job_list_lock, flags);
/* Reserve space for the bomap */
if (n_bomap_pages) {
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index 67ae266..8795c19 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -109,11 +109,18 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job)
}
/* block scheduler */
- drm_sched_stop(&gpu->sched);
+ drm_sched_stop(&gpu->sched, sched_job);
if(sched_job)
drm_sched_increase_karma(sched_job);
+ /*
+ * Guilty job did complete and hence needs to be manually removed
+ * See drm_sched_stop doc.
+ */
+ if (list_empty(&sched_job->node))
+ sched_job->sched->ops->free_job(sched_job);
+
/* get the GPU back into the init state */
etnaviv_core_dump(gpu);
etnaviv_gpu_recover_hang(gpu);
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 19fc601..c215cde 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -191,6 +191,8 @@ EXPORT_SYMBOL(drm_sched_dependency_optimized);
*/
static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched)
{
+ unsigned long flags;
+
if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
!list_empty(&sched->ring_mirror_list))
schedule_delayed_work(&sched->work_tdr, sched->timeout);
@@ -265,32 +267,6 @@ void drm_sched_resume_timeout(struct drm_gpu_scheduler *sched,
}
EXPORT_SYMBOL(drm_sched_resume_timeout);
-/* job_finish is called after hw fence signaled
- */
-static void drm_sched_job_finish(struct work_struct *work)
-{
- struct drm_sched_job *s_job = container_of(work, struct drm_sched_job,
- finish_work);
- struct drm_gpu_scheduler *sched = s_job->sched;
- unsigned long flags;
-
- /*
- * Canceling the timeout without removing our job from the ring mirror
- * list is safe, as we will only end up in this worker if our jobs
- * finished fence has been signaled. So even if some another worker
- * manages to find this job as the next job in the list, the fence
- * signaled check below will prevent the timeout to be restarted.
- */
- cancel_delayed_work_sync(&sched->work_tdr);
-
- spin_lock_irqsave(&sched->job_list_lock, flags);
- /* queue TDR for next job */
- drm_sched_start_timeout(sched);
- spin_unlock_irqrestore(&sched->job_list_lock, flags);
-
- sched->ops->free_job(s_job);
-}
-
static void drm_sched_job_begin(struct drm_sched_job *s_job)
{
struct drm_gpu_scheduler *sched = s_job->sched;
@@ -371,23 +347,26 @@ EXPORT_SYMBOL(drm_sched_increase_karma);
* @sched: scheduler instance
* @bad: bad scheduler job
*
+ * Stop the scheduler and also removes and frees all completed jobs.
+ * Note: bad job will not be freed as it might be used later and so it's
+ * callers responsibility to release it manually if it's not part of the
+ * mirror list any more.
+ *
*/
-void drm_sched_stop(struct drm_gpu_scheduler *sched)
+void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
{
- struct drm_sched_job *s_job;
+ struct drm_sched_job *s_job, *tmp;
unsigned long flags;
- struct dma_fence *last_fence = NULL;
kthread_park(sched->thread);
/*
- * Verify all the signaled jobs in mirror list are removed from the ring
- * by waiting for the latest job to enter the list. This should insure that
- * also all the previous jobs that were in flight also already singaled
- * and removed from the list.
+ * Iterate the job list from later to earlier one and either deactive
+ * their HW callbacks or remove them from mirror list if they already
+ * signaled.
+ * This iteration is thread safe as sched thread is stopped.
*/
- spin_lock_irqsave(&sched->job_list_lock, flags);
- list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) {
+ list_for_each_entry_safe_reverse(s_job, tmp, &sched->ring_mirror_list, node) {
if (s_job->s_fence->parent &&
dma_fence_remove_callback(s_job->s_fence->parent,
&s_job->cb)) {
@@ -395,16 +374,30 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched)
s_job->s_fence->parent = NULL;
atomic_dec(&sched->hw_rq_count);
} else {
- last_fence = dma_fence_get(&s_job->s_fence->finished);
- break;
+ /*
+ * remove job from ring_mirror_list.
+ * Locking here is for concurrent resume timeout
+ */
+ spin_lock_irqsave(&sched->job_list_lock, flags);
+ list_del_init(&s_job->node);
+ spin_unlock_irqrestore(&sched->job_list_lock, flags);
+
+ /*
+ * Wait for job's HW fence callback to finish using s_job
+ * before releasing it.
+ *
+ * Job is still alive so fence refcount at least 1
+ */
+ dma_fence_wait(&s_job->s_fence->finished, false);
+
+ /*
+ * We must keep bad job alive for later use during
+ * recovery by some of the drivers
+ */
+ if (bad != s_job)
+ sched->ops->free_job(s_job);
}
}
- spin_unlock_irqrestore(&sched->job_list_lock, flags);
-
- if (last_fence) {
- dma_fence_wait(last_fence, false);
- dma_fence_put(last_fence);
- }
}
EXPORT_SYMBOL(drm_sched_stop);
@@ -418,6 +411,7 @@ 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)
@@ -425,9 +419,7 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
/*
* 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
+ * so no new jobs are being inserted or removed. Also concurrent
* GPU recovers can't run in parallel.
*/
list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
@@ -445,7 +437,9 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
drm_sched_process_job(NULL, &s_job->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);
@@ -464,7 +458,6 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
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;
@@ -514,7 +507,6 @@ int drm_sched_job_init(struct drm_sched_job *job,
return -ENOMEM;
job->id = atomic64_inc_return(&sched->job_id_count);
- INIT_WORK(&job->finish_work, drm_sched_job_finish);
INIT_LIST_HEAD(&job->node);
return 0;
@@ -597,24 +589,53 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *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);
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);
+ trace_drm_sched_process_job(s_fence);
drm_sched_fence_finished(s_fence);
-
- trace_drm_sched_process_job(s_fence);
wake_up_interruptible(&sched->wake_up_worker);
+}
+
+/**
+ * drm_sched_cleanup_jobs - destroy finished jobs
+ *
+ * @sched: scheduler instance
+ *
+ * Remove all finished jobs from the mirror list and destroy them.
+ */
+static void drm_sched_cleanup_jobs(struct drm_gpu_scheduler *sched)
+{
+ unsigned long flags;
+
+ /* Don't destroy jobs while the timeout worker is running */
+ if (!cancel_delayed_work(&sched->work_tdr))
+ return;
+
+
+ while (!list_empty(&sched->ring_mirror_list)) {
+ struct drm_sched_job *job;
+
+ job = list_first_entry(&sched->ring_mirror_list,
+ struct drm_sched_job, node);
+ if (!dma_fence_is_signaled(&job->s_fence->finished))
+ break;
+
+ spin_lock_irqsave(&sched->job_list_lock, flags);
+ /* remove job from ring_mirror_list */
+ list_del_init(&job->node);
+ spin_unlock_irqrestore(&sched->job_list_lock, flags);
+
+ sched->ops->free_job(job);
+ }
+
+ /* queue timeout for next job */
+ spin_lock_irqsave(&sched->job_list_lock, flags);
+ drm_sched_start_timeout(sched);
+ spin_unlock_irqrestore(&sched->job_list_lock, flags);
- schedule_work(&s_job->finish_work);
}
/**
@@ -656,9 +677,10 @@ static int drm_sched_main(void *param)
struct dma_fence *fence;
wait_event_interruptible(sched->wake_up_worker,
+ (drm_sched_cleanup_jobs(sched),
(!drm_sched_blocked(sched) &&
(entity = drm_sched_select_entity(sched))) ||
- kthread_should_stop());
+ kthread_should_stop()));
if (!entity)
continue;
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index ce7c737b..8efb091 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -232,11 +232,18 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job)
/* block scheduler */
for (q = 0; q < V3D_MAX_QUEUES; q++)
- drm_sched_stop(&v3d->queue[q].sched);
+ drm_sched_stop(&v3d->queue[q].sched, sched_job);
if(sched_job)
drm_sched_increase_karma(sched_job);
+ /*
+ * Guilty job did complete and hence needs to be manually removed
+ * See drm_sched_stop doc.
+ */
+ if (list_empty(&sched_job->node))
+ sched_job->sched->ops->free_job(sched_job);
+
/* get the GPU back into the init state */
v3d_reset(v3d);
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 0daca4d..9ee0f27 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -167,9 +167,6 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f);
* @sched: the scheduler instance on which this job is scheduled.
* @s_fence: contains the fences for the scheduling of job.
* @finish_cb: the callback for the finished fence.
- * @finish_work: schedules the function @drm_sched_job_finish once the job has
- * finished to remove the job from the
- * @drm_gpu_scheduler.ring_mirror_list.
* @node: used to append this struct to the @drm_gpu_scheduler.ring_mirror_list.
* @id: a unique id assigned to each job scheduled on the scheduler.
* @karma: increment on every hang caused by this job. If this exceeds the hang
@@ -188,7 +185,6 @@ struct drm_sched_job {
struct drm_gpu_scheduler *sched;
struct drm_sched_fence *s_fence;
struct dma_fence_cb finish_cb;
- struct work_struct finish_work;
struct list_head node;
uint64_t id;
atomic_t karma;
@@ -296,7 +292,7 @@ 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_stop(struct drm_gpu_scheduler *sched);
+void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad);
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);
--
2.7.4
More information about the etnaviv
mailing list