[Intel-gfx] [PATCH v5 04/20] drm/sched: Add dependency tracking
Instead of just a callback we can just glue in the gem helpers that
panfrost, v3d and lima currently use. There's really not that many
ways to skin this cat.
v2/3: Rebased.
v4: Repaint this shed. The functions are now called _add_dependency()
and _add_implicit_dependency()
Reviewed-by: Boris Brezillon (v3)
Reviewed-by: Steven Price (v1)
Acked-by: Melissa Wen
Signed-off-by: Daniel Vetter
Cc: David Airlie
Cc: Daniel Vetter
Cc: Sumit Semwal
Cc: "Christian König"
Cc: Andrey Grodzovsky
Cc: Lee Jones
Cc: Nirmoy Das
Cc: Boris Brezillon
Cc: Luben Tuikov
Cc: Alex Deucher
Cc: linux-me...@vger.kernel.org
Cc: linaro-mm-...@lists.linaro.org
---
drivers/gpu/drm/scheduler/sched_entity.c | 18 +++-
drivers/gpu/drm/scheduler/sched_main.c | 104 +++
include/drm/gpu_scheduler.h | 33 ++-
3 files changed, 149 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c
b/drivers/gpu/drm/scheduler/sched_entity.c
index 89e3f6eaf519..381fbf462ea7 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -211,6 +211,19 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence
*f,
job->sched->ops->free_job(job);
}
+static struct dma_fence *
+drm_sched_job_dependency(struct drm_sched_job *job,
+struct drm_sched_entity *entity)
+{
+ if (!xa_empty(&job->dependencies))
+ return xa_erase(&job->dependencies, job->last_dependency++);
+
+ if (job->sched->ops->dependency)
+ return job->sched->ops->dependency(job, entity);
+
+ return NULL;
+}
+
/**
* drm_sched_entity_kill_jobs - Make sure all remaining jobs are killed
*
@@ -229,7 +242,7 @@ static void drm_sched_entity_kill_jobs(struct
drm_sched_entity *entity)
struct drm_sched_fence *s_fence = job->s_fence;
/* Wait for all dependencies to avoid data corruptions */
- while ((f = job->sched->ops->dependency(job, entity)))
+ while ((f = drm_sched_job_dependency(job, entity)))
dma_fence_wait(f, false);
drm_sched_fence_scheduled(s_fence);
@@ -419,7 +432,6 @@ static bool drm_sched_entity_add_dependency_cb(struct
drm_sched_entity *entity)
*/
struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
{
- struct drm_gpu_scheduler *sched = entity->rq->sched;
struct drm_sched_job *sched_job;
sched_job = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
@@ -427,7 +439,7 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct
drm_sched_entity *entity)
return NULL;
while ((entity->dependency =
- sched->ops->dependency(sched_job, entity))) {
+ drm_sched_job_dependency(sched_job, entity))) {
trace_drm_sched_job_wait_dep(sched_job, entity->dependency);
if (drm_sched_entity_add_dependency_cb(entity))
diff --git a/drivers/gpu/drm/scheduler/sched_main.c
b/drivers/gpu/drm/scheduler/sched_main.c
index 454cb6164bdc..f77456929139 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -603,6 +603,8 @@ int drm_sched_job_init(struct drm_sched_job *job,
INIT_LIST_HEAD(&job->list);
+ xa_init_flags(&job->dependencies, XA_FLAGS_ALLOC);
+
return 0;
}
EXPORT_SYMBOL(drm_sched_job_init);
@@ -637,6 +639,99 @@ void drm_sched_job_arm(struct drm_sched_job *job)
}
EXPORT_SYMBOL(drm_sched_job_arm);
+/**
+ * drm_sched_job_add_dependency - adds the fence as a job dependency
+ * @job: scheduler job to add the dependencies to
+ * @fence: the dma_fence to add to the list of dependencies.
+ *
+ * Note that @fence is consumed in both the success and error cases.
+ *
+ * Returns:
+ * 0 on success, or an error on failing to expand the array.
+ */
+int drm_sched_job_add_dependency(struct drm_sched_job *job,
+struct dma_fence *fence)
+{
+ struct dma_fence *entry;
+ unsigned long index;
+ u32 id = 0;
+ int ret;
+
+ if (!fence)
+ return 0;
+
+ /* Deduplicate if we already depend on a fence from the same context.
+* This lets the size of the array of deps scale with the number of
+* engines involved, rather than the number of BOs.
+*/
+ xa_for_each(&job->dependencies, index, entry) {
+ if (entry->context != fence->context)
+ continue;
+
+ if (dma_fence_is_later(fence, entry)) {
+ dma_fence_put(entry);
+ xa_store(&job->dependencies, index, fence, GFP_KERNEL);
+ } else {
+ dma_fence_put(fence);
+ }
+ return 0;
+ }
+
+ ret = xa_alloc(&job->dependencies, &id, fence, xa_limit_32b,
GFP_KERNEL);
+ if (ret != 0)
+
Re: [Intel-gfx] [PATCH v5 04/20] drm/sched: Add dependency tracking
Am 05.08.21 um 12:46 schrieb Daniel Vetter:
Instead of just a callback we can just glue in the gem helpers that
panfrost, v3d and lima currently use. There's really not that many
ways to skin this cat.
v2/3: Rebased.
v4: Repaint this shed. The functions are now called _add_dependency()
and _add_implicit_dependency()
Reviewed-by: Boris Brezillon (v3)
Reviewed-by: Steven Price (v1)
Acked-by: Melissa Wen
Signed-off-by: Daniel Vetter
Reviewed-by: Christian König
Cc: David Airlie
Cc: Daniel Vetter
Cc: Sumit Semwal
Cc: "Christian König"
Cc: Andrey Grodzovsky
Cc: Lee Jones
Cc: Nirmoy Das
Cc: Boris Brezillon
Cc: Luben Tuikov
Cc: Alex Deucher
Cc: linux-me...@vger.kernel.org
Cc: linaro-mm-...@lists.linaro.org
---
drivers/gpu/drm/scheduler/sched_entity.c | 18 +++-
drivers/gpu/drm/scheduler/sched_main.c | 104 +++
include/drm/gpu_scheduler.h | 33 ++-
3 files changed, 149 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c
b/drivers/gpu/drm/scheduler/sched_entity.c
index 89e3f6eaf519..381fbf462ea7 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -211,6 +211,19 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence
*f,
job->sched->ops->free_job(job);
}
+static struct dma_fence *
+drm_sched_job_dependency(struct drm_sched_job *job,
+struct drm_sched_entity *entity)
+{
+ if (!xa_empty(&job->dependencies))
+ return xa_erase(&job->dependencies, job->last_dependency++);
+
+ if (job->sched->ops->dependency)
+ return job->sched->ops->dependency(job, entity);
+
+ return NULL;
+}
+
/**
* drm_sched_entity_kill_jobs - Make sure all remaining jobs are killed
*
@@ -229,7 +242,7 @@ static void drm_sched_entity_kill_jobs(struct
drm_sched_entity *entity)
struct drm_sched_fence *s_fence = job->s_fence;
/* Wait for all dependencies to avoid data corruptions */
- while ((f = job->sched->ops->dependency(job, entity)))
+ while ((f = drm_sched_job_dependency(job, entity)))
dma_fence_wait(f, false);
drm_sched_fence_scheduled(s_fence);
@@ -419,7 +432,6 @@ static bool drm_sched_entity_add_dependency_cb(struct
drm_sched_entity *entity)
*/
struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity
*entity)
{
- struct drm_gpu_scheduler *sched = entity->rq->sched;
struct drm_sched_job *sched_job;
sched_job = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
@@ -427,7 +439,7 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct
drm_sched_entity *entity)
return NULL;
while ((entity->dependency =
- sched->ops->dependency(sched_job, entity))) {
+ drm_sched_job_dependency(sched_job, entity))) {
trace_drm_sched_job_wait_dep(sched_job, entity->dependency);
if (drm_sched_entity_add_dependency_cb(entity))
diff --git a/drivers/gpu/drm/scheduler/sched_main.c
b/drivers/gpu/drm/scheduler/sched_main.c
index 454cb6164bdc..f77456929139 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -603,6 +603,8 @@ int drm_sched_job_init(struct drm_sched_job *job,
INIT_LIST_HEAD(&job->list);
+ xa_init_flags(&job->dependencies, XA_FLAGS_ALLOC);
+
return 0;
}
EXPORT_SYMBOL(drm_sched_job_init);
@@ -637,6 +639,99 @@ void drm_sched_job_arm(struct drm_sched_job *job)
}
EXPORT_SYMBOL(drm_sched_job_arm);
+/**
+ * drm_sched_job_add_dependency - adds the fence as a job dependency
+ * @job: scheduler job to add the dependencies to
+ * @fence: the dma_fence to add to the list of dependencies.
+ *
+ * Note that @fence is consumed in both the success and error cases.
+ *
+ * Returns:
+ * 0 on success, or an error on failing to expand the array.
+ */
+int drm_sched_job_add_dependency(struct drm_sched_job *job,
+struct dma_fence *fence)
+{
+ struct dma_fence *entry;
+ unsigned long index;
+ u32 id = 0;
+ int ret;
+
+ if (!fence)
+ return 0;
+
+ /* Deduplicate if we already depend on a fence from the same context.
+* This lets the size of the array of deps scale with the number of
+* engines involved, rather than the number of BOs.
+*/
+ xa_for_each(&job->dependencies, index, entry) {
+ if (entry->context != fence->context)
+ continue;
+
+ if (dma_fence_is_later(fence, entry)) {
+ dma_fence_put(entry);
+ xa_store(&job->dependencies, index, fence, GFP_KERNEL);
+ } else {
+ dma_fence_put(fence);
+ }
+ return 0;
+ }
+
+ ret = xa_alloc(&job->dependencies, &id, fen
