All of lore.kernel.org
 help / color / mirror / Atom feed
From: Daniel Vetter <daniel.vetter@ffwll.ch>
To: DRI Development <dri-devel@lists.freedesktop.org>
Cc: "Intel Graphics Development" <intel-gfx@lists.freedesktop.org>,
	"Daniel Vetter" <daniel.vetter@ffwll.ch>,
	"Steven Price" <steven.price@arm.com>,
	"Daniel Vetter" <daniel.vetter@intel.com>,
	"David Airlie" <airlied@linux.ie>,
	"Daniel Vetter" <daniel@ffwll.ch>,
	"Sumit Semwal" <sumit.semwal@linaro.org>,
	"Christian König" <christian.koenig@amd.com>,
	"Andrey Grodzovsky" <andrey.grodzovsky@amd.com>,
	"Lee Jones" <lee.jones@linaro.org>,
	"Nirmoy Das" <nirmoy.aiemd@gmail.com>,
	"Boris Brezillon" <boris.brezillon@collabora.com>,
	"Luben Tuikov" <luben.tuikov@amd.com>,
	"Alex Deucher" <alexander.deucher@amd.com>,
	"Jack Zhang" <Jack.Zhang1@amd.com>,
	linux-media@vger.kernel.org, linaro-mm-sig@lists.linaro.org
Subject: [PATCH v3 04/20] drm/sched: Add dependency tracking
Date: Thu,  8 Jul 2021 19:37:38 +0200	[thread overview]
Message-ID: <20210708173754.3877540-5-daniel.vetter@ffwll.ch> (raw)
In-Reply-To: <20210708173754.3877540-1-daniel.vetter@ffwll.ch>

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.

On the naming bikeshed: The idea for using _await_ to denote adding
dependencies to a job comes from i915, where that's used quite
extensively all over the place, in lots of datastructures.

v2/3: Rebased.

Reviewed-by: Steven Price <steven.price@arm.com> (v1)
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Cc: Lee Jones <lee.jones@linaro.org>
Cc: Nirmoy Das <nirmoy.aiemd@gmail.com>
Cc: Boris Brezillon <boris.brezillon@collabora.com>
Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Jack Zhang <Jack.Zhang1@amd.com>
Cc: linux-media@vger.kernel.org
Cc: linaro-mm-sig@lists.linaro.org
---
 drivers/gpu/drm/scheduler/sched_entity.c |  18 +++-
 drivers/gpu/drm/scheduler/sched_main.c   | 103 +++++++++++++++++++++++
 include/drm/gpu_scheduler.h              |  31 ++++++-
 3 files changed, 146 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 4e1124ed80e0..c7e6d29c9a33 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 7e94754eb34c..ad62f1d2991c 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -594,6 +594,8 @@ 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);
@@ -631,6 +633,98 @@ void drm_sched_job_arm(struct drm_sched_job *job)
 }
 EXPORT_SYMBOL(drm_sched_job_arm);
 
+/**
+ * drm_sched_job_await_fence - 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_await_fence(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)
+		dma_fence_put(fence);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_sched_job_await_fence);
+
+/**
+ * drm_sched_job_await_implicit - adds implicit dependencies as job dependencies
+ * @job: scheduler job to add the dependencies to
+ * @obj: the gem object to add new dependencies from.
+ * @write: whether the job might write the object (so we need to depend on
+ * shared fences in the reservation object).
+ *
+ * This should be called after drm_gem_lock_reservations() on your array of
+ * GEM objects used in the job but before updating the reservations with your
+ * own fences.
+ *
+ * Returns:
+ * 0 on success, or an error on failing to expand the array.
+ */
+int drm_sched_job_await_implicit(struct drm_sched_job *job,
+				 struct drm_gem_object *obj,
+				 bool write)
+{
+	int ret;
+	struct dma_fence **fences;
+	unsigned int i, fence_count;
+
+	if (!write) {
+		struct dma_fence *fence = dma_resv_get_excl_unlocked(obj->resv);
+
+		return drm_sched_job_await_fence(job, fence);
+	}
+
+	ret = dma_resv_get_fences(obj->resv, NULL, &fence_count, &fences);
+	if (ret || !fence_count)
+		return ret;
+
+	for (i = 0; i < fence_count; i++) {
+		ret = drm_sched_job_await_fence(job, fences[i]);
+		if (ret)
+			break;
+	}
+
+	for (; i < fence_count; i++)
+		dma_fence_put(fences[i]);
+	kfree(fences);
+	return ret;
+}
+EXPORT_SYMBOL(drm_sched_job_await_implicit);
+
+
 /**
  * drm_sched_job_cleanup - clean up scheduler job resources
  * @job: scheduler job to clean up
@@ -646,6 +740,9 @@ EXPORT_SYMBOL(drm_sched_job_arm);
  */
 void drm_sched_job_cleanup(struct drm_sched_job *job)
 {
+	struct dma_fence *fence;
+	unsigned long index;
+
 	if (kref_read(&job->s_fence->finished.refcount)) {
 		/* drm_sched_job_arm() has been called */
 		dma_fence_put(&job->s_fence->finished);
@@ -655,6 +752,12 @@ void drm_sched_job_cleanup(struct drm_sched_job *job)
 	}
 
 	job->s_fence = NULL;
+
+	xa_for_each(&job->dependencies, index, fence) {
+		dma_fence_put(fence);
+	}
+	xa_destroy(&job->dependencies);
+
 }
 EXPORT_SYMBOL(drm_sched_job_cleanup);
 
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 83afc3aa8e2f..74fb321dbc44 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -27,9 +27,12 @@
 #include <drm/spsc_queue.h>
 #include <linux/dma-fence.h>
 #include <linux/completion.h>
+#include <linux/xarray.h>
 
 #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000)
 
+struct drm_gem_object;
+
 struct drm_gpu_scheduler;
 struct drm_sched_rq;
 
@@ -198,6 +201,16 @@ struct drm_sched_job {
 	enum drm_sched_priority		s_priority;
 	struct drm_sched_entity         *entity;
 	struct dma_fence_cb		cb;
+	/**
+	 * @dependencies:
+	 *
+	 * Contains the dependencies as struct dma_fence for this job, see
+	 * drm_sched_job_await_fence() and drm_sched_job_await_implicit().
+	 */
+	struct xarray			dependencies;
+
+	/** @last_dependency: tracks @dependencies as they signal */
+	unsigned long			last_dependency;
 };
 
 static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job,
@@ -220,9 +233,14 @@ enum drm_gpu_sched_stat {
  */
 struct drm_sched_backend_ops {
 	/**
-         * @dependency: Called when the scheduler is considering scheduling
-         * this job next, to get another struct dma_fence for this job to
-	 * block on.  Once it returns NULL, run_job() may be called.
+	 * @dependency:
+	 *
+	 * Called when the scheduler is considering scheduling this job next, to
+	 * get another struct dma_fence for this job to block on.  Once it
+	 * returns NULL, run_job() may be called.
+	 *
+	 * If a driver exclusively uses drm_sched_job_await_fence() and
+	 * drm_sched_job_await_implicit() this can be ommitted and left as NULL.
 	 */
 	struct dma_fence *(*dependency)(struct drm_sched_job *sched_job,
 					struct drm_sched_entity *s_entity);
@@ -349,6 +367,13 @@ int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_sched_entity *entity,
 		       void *owner);
 void drm_sched_job_arm(struct drm_sched_job *job);
+int drm_sched_job_await_fence(struct drm_sched_job *job,
+			      struct dma_fence *fence);
+int drm_sched_job_await_implicit(struct drm_sched_job *job,
+				 struct drm_gem_object *obj,
+				 bool write);
+
+
 void drm_sched_entity_modify_sched(struct drm_sched_entity *entity,
 				    struct drm_gpu_scheduler **sched_list,
                                    unsigned int num_sched_list);
-- 
2.32.0


WARNING: multiple messages have this Message-ID
From: Daniel Vetter <daniel.vetter@ffwll.ch>
To: DRI Development <dri-devel@lists.freedesktop.org>
Cc: "Jack Zhang" <Jack.Zhang1@amd.com>,
	"Christian König" <christian.koenig@amd.com>,
	"David Airlie" <airlied@linux.ie>,
	"Daniel Vetter" <daniel.vetter@ffwll.ch>,
	"Intel Graphics Development" <intel-gfx@lists.freedesktop.org>,
	"Steven Price" <steven.price@arm.com>,
	linaro-mm-sig@lists.linaro.org,
	"Boris Brezillon" <boris.brezillon@collabora.com>,
	"Alex Deucher" <alexander.deucher@amd.com>,
	"Daniel Vetter" <daniel.vetter@intel.com>,
	linux-media@vger.kernel.org, "Lee Jones" <lee.jones@linaro.org>,
	"Luben Tuikov" <luben.tuikov@amd.com>,
	"Nirmoy Das" <nirmoy.aiemd@gmail.com>
Subject: [PATCH v3 04/20] drm/sched: Add dependency tracking
Date: Thu,  8 Jul 2021 19:37:38 +0200	[thread overview]
Message-ID: <20210708173754.3877540-5-daniel.vetter@ffwll.ch> (raw)
In-Reply-To: <20210708173754.3877540-1-daniel.vetter@ffwll.ch>

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.

On the naming bikeshed: The idea for using _await_ to denote adding
dependencies to a job comes from i915, where that's used quite
extensively all over the place, in lots of datastructures.

v2/3: Rebased.

Reviewed-by: Steven Price <steven.price@arm.com> (v1)
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Cc: Lee Jones <lee.jones@linaro.org>
Cc: Nirmoy Das <nirmoy.aiemd@gmail.com>
Cc: Boris Brezillon <boris.brezillon@collabora.com>
Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Jack Zhang <Jack.Zhang1@amd.com>
Cc: linux-media@vger.kernel.org
Cc: linaro-mm-sig@lists.linaro.org
---
 drivers/gpu/drm/scheduler/sched_entity.c |  18 +++-
 drivers/gpu/drm/scheduler/sched_main.c   | 103 +++++++++++++++++++++++
 include/drm/gpu_scheduler.h              |  31 ++++++-
 3 files changed, 146 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 4e1124ed80e0..c7e6d29c9a33 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 7e94754eb34c..ad62f1d2991c 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -594,6 +594,8 @@ 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);
@@ -631,6 +633,98 @@ void drm_sched_job_arm(struct drm_sched_job *job)
 }
 EXPORT_SYMBOL(drm_sched_job_arm);
 
+/**
+ * drm_sched_job_await_fence - 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_await_fence(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)
+		dma_fence_put(fence);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_sched_job_await_fence);
+
+/**
+ * drm_sched_job_await_implicit - adds implicit dependencies as job dependencies
+ * @job: scheduler job to add the dependencies to
+ * @obj: the gem object to add new dependencies from.
+ * @write: whether the job might write the object (so we need to depend on
+ * shared fences in the reservation object).
+ *
+ * This should be called after drm_gem_lock_reservations() on your array of
+ * GEM objects used in the job but before updating the reservations with your
+ * own fences.
+ *
+ * Returns:
+ * 0 on success, or an error on failing to expand the array.
+ */
+int drm_sched_job_await_implicit(struct drm_sched_job *job,
+				 struct drm_gem_object *obj,
+				 bool write)
+{
+	int ret;
+	struct dma_fence **fences;
+	unsigned int i, fence_count;
+
+	if (!write) {
+		struct dma_fence *fence = dma_resv_get_excl_unlocked(obj->resv);
+
+		return drm_sched_job_await_fence(job, fence);
+	}
+
+	ret = dma_resv_get_fences(obj->resv, NULL, &fence_count, &fences);
+	if (ret || !fence_count)
+		return ret;
+
+	for (i = 0; i < fence_count; i++) {
+		ret = drm_sched_job_await_fence(job, fences[i]);
+		if (ret)
+			break;
+	}
+
+	for (; i < fence_count; i++)
+		dma_fence_put(fences[i]);
+	kfree(fences);
+	return ret;
+}
+EXPORT_SYMBOL(drm_sched_job_await_implicit);
+
+
 /**
  * drm_sched_job_cleanup - clean up scheduler job resources
  * @job: scheduler job to clean up
@@ -646,6 +740,9 @@ EXPORT_SYMBOL(drm_sched_job_arm);
  */
 void drm_sched_job_cleanup(struct drm_sched_job *job)
 {
+	struct dma_fence *fence;
+	unsigned long index;
+
 	if (kref_read(&job->s_fence->finished.refcount)) {
 		/* drm_sched_job_arm() has been called */
 		dma_fence_put(&job->s_fence->finished);
@@ -655,6 +752,12 @@ void drm_sched_job_cleanup(struct drm_sched_job *job)
 	}
 
 	job->s_fence = NULL;
+
+	xa_for_each(&job->dependencies, index, fence) {
+		dma_fence_put(fence);
+	}
+	xa_destroy(&job->dependencies);
+
 }
 EXPORT_SYMBOL(drm_sched_job_cleanup);
 
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 83afc3aa8e2f..74fb321dbc44 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -27,9 +27,12 @@
 #include <drm/spsc_queue.h>
 #include <linux/dma-fence.h>
 #include <linux/completion.h>
+#include <linux/xarray.h>
 
 #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000)
 
+struct drm_gem_object;
+
 struct drm_gpu_scheduler;
 struct drm_sched_rq;
 
@@ -198,6 +201,16 @@ struct drm_sched_job {
 	enum drm_sched_priority		s_priority;
 	struct drm_sched_entity         *entity;
 	struct dma_fence_cb		cb;
+	/**
+	 * @dependencies:
+	 *
+	 * Contains the dependencies as struct dma_fence for this job, see
+	 * drm_sched_job_await_fence() and drm_sched_job_await_implicit().
+	 */
+	struct xarray			dependencies;
+
+	/** @last_dependency: tracks @dependencies as they signal */
+	unsigned long			last_dependency;
 };
 
 static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job,
@@ -220,9 +233,14 @@ enum drm_gpu_sched_stat {
  */
 struct drm_sched_backend_ops {
 	/**
-         * @dependency: Called when the scheduler is considering scheduling
-         * this job next, to get another struct dma_fence for this job to
-	 * block on.  Once it returns NULL, run_job() may be called.
+	 * @dependency:
+	 *
+	 * Called when the scheduler is considering scheduling this job next, to
+	 * get another struct dma_fence for this job to block on.  Once it
+	 * returns NULL, run_job() may be called.
+	 *
+	 * If a driver exclusively uses drm_sched_job_await_fence() and
+	 * drm_sched_job_await_implicit() this can be ommitted and left as NULL.
 	 */
 	struct dma_fence *(*dependency)(struct drm_sched_job *sched_job,
 					struct drm_sched_entity *s_entity);
@@ -349,6 +367,13 @@ int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_sched_entity *entity,
 		       void *owner);
 void drm_sched_job_arm(struct drm_sched_job *job);
+int drm_sched_job_await_fence(struct drm_sched_job *job,
+			      struct dma_fence *fence);
+int drm_sched_job_await_implicit(struct drm_sched_job *job,
+				 struct drm_gem_object *obj,
+				 bool write);
+
+
 void drm_sched_entity_modify_sched(struct drm_sched_entity *entity,
 				    struct drm_gpu_scheduler **sched_list,
                                    unsigned int num_sched_list);
-- 
2.32.0


WARNING: multiple messages have this Message-ID
From: Daniel Vetter <daniel.vetter@ffwll.ch>
To: DRI Development <dri-devel@lists.freedesktop.org>
Cc: "Andrey Grodzovsky" <andrey.grodzovsky@amd.com>,
	"Jack Zhang" <Jack.Zhang1@amd.com>,
	"Christian König" <christian.koenig@amd.com>,
	"David Airlie" <airlied@linux.ie>,
	"Daniel Vetter" <daniel.vetter@ffwll.ch>,
	"Intel Graphics Development" <intel-gfx@lists.freedesktop.org>,
	"Steven Price" <steven.price@arm.com>,
	linaro-mm-sig@lists.linaro.org,
	"Alex Deucher" <alexander.deucher@amd.com>,
	"Daniel Vetter" <daniel.vetter@intel.com>,
	linux-media@vger.kernel.org, "Lee Jones" <lee.jones@linaro.org>,
	"Sumit Semwal" <sumit.semwal@linaro.org>,
	"Luben Tuikov" <luben.tuikov@amd.com>,
	"Nirmoy Das" <nirmoy.aiemd@gmail.com>
Subject: [Intel-gfx] [PATCH v3 04/20] drm/sched: Add dependency tracking
Date: Thu,  8 Jul 2021 19:37:38 +0200	[thread overview]
Message-ID: <20210708173754.3877540-5-daniel.vetter@ffwll.ch> (raw)
In-Reply-To: <20210708173754.3877540-1-daniel.vetter@ffwll.ch>

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.

On the naming bikeshed: The idea for using _await_ to denote adding
dependencies to a job comes from i915, where that's used quite
extensively all over the place, in lots of datastructures.

v2/3: Rebased.

Reviewed-by: Steven Price <steven.price@arm.com> (v1)
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Cc: Lee Jones <lee.jones@linaro.org>
Cc: Nirmoy Das <nirmoy.aiemd@gmail.com>
Cc: Boris Brezillon <boris.brezillon@collabora.com>
Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Jack Zhang <Jack.Zhang1@amd.com>
Cc: linux-media@vger.kernel.org
Cc: linaro-mm-sig@lists.linaro.org
---
 drivers/gpu/drm/scheduler/sched_entity.c |  18 +++-
 drivers/gpu/drm/scheduler/sched_main.c   | 103 +++++++++++++++++++++++
 include/drm/gpu_scheduler.h              |  31 ++++++-
 3 files changed, 146 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 4e1124ed80e0..c7e6d29c9a33 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 7e94754eb34c..ad62f1d2991c 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -594,6 +594,8 @@ 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);
@@ -631,6 +633,98 @@ void drm_sched_job_arm(struct drm_sched_job *job)
 }
 EXPORT_SYMBOL(drm_sched_job_arm);
 
+/**
+ * drm_sched_job_await_fence - 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_await_fence(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)
+		dma_fence_put(fence);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_sched_job_await_fence);
+
+/**
+ * drm_sched_job_await_implicit - adds implicit dependencies as job dependencies
+ * @job: scheduler job to add the dependencies to
+ * @obj: the gem object to add new dependencies from.
+ * @write: whether the job might write the object (so we need to depend on
+ * shared fences in the reservation object).
+ *
+ * This should be called after drm_gem_lock_reservations() on your array of
+ * GEM objects used in the job but before updating the reservations with your
+ * own fences.
+ *
+ * Returns:
+ * 0 on success, or an error on failing to expand the array.
+ */
+int drm_sched_job_await_implicit(struct drm_sched_job *job,
+				 struct drm_gem_object *obj,
+				 bool write)
+{
+	int ret;
+	struct dma_fence **fences;
+	unsigned int i, fence_count;
+
+	if (!write) {
+		struct dma_fence *fence = dma_resv_get_excl_unlocked(obj->resv);
+
+		return drm_sched_job_await_fence(job, fence);
+	}
+
+	ret = dma_resv_get_fences(obj->resv, NULL, &fence_count, &fences);
+	if (ret || !fence_count)
+		return ret;
+
+	for (i = 0; i < fence_count; i++) {
+		ret = drm_sched_job_await_fence(job, fences[i]);
+		if (ret)
+			break;
+	}
+
+	for (; i < fence_count; i++)
+		dma_fence_put(fences[i]);
+	kfree(fences);
+	return ret;
+}
+EXPORT_SYMBOL(drm_sched_job_await_implicit);
+
+
 /**
  * drm_sched_job_cleanup - clean up scheduler job resources
  * @job: scheduler job to clean up
@@ -646,6 +740,9 @@ EXPORT_SYMBOL(drm_sched_job_arm);
  */
 void drm_sched_job_cleanup(struct drm_sched_job *job)
 {
+	struct dma_fence *fence;
+	unsigned long index;
+
 	if (kref_read(&job->s_fence->finished.refcount)) {
 		/* drm_sched_job_arm() has been called */
 		dma_fence_put(&job->s_fence->finished);
@@ -655,6 +752,12 @@ void drm_sched_job_cleanup(struct drm_sched_job *job)
 	}
 
 	job->s_fence = NULL;
+
+	xa_for_each(&job->dependencies, index, fence) {
+		dma_fence_put(fence);
+	}
+	xa_destroy(&job->dependencies);
+
 }
 EXPORT_SYMBOL(drm_sched_job_cleanup);
 
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 83afc3aa8e2f..74fb321dbc44 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -27,9 +27,12 @@
 #include <drm/spsc_queue.h>
 #include <linux/dma-fence.h>
 #include <linux/completion.h>
+#include <linux/xarray.h>
 
 #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000)
 
+struct drm_gem_object;
+
 struct drm_gpu_scheduler;
 struct drm_sched_rq;
 
@@ -198,6 +201,16 @@ struct drm_sched_job {
 	enum drm_sched_priority		s_priority;
 	struct drm_sched_entity         *entity;
 	struct dma_fence_cb		cb;
+	/**
+	 * @dependencies:
+	 *
+	 * Contains the dependencies as struct dma_fence for this job, see
+	 * drm_sched_job_await_fence() and drm_sched_job_await_implicit().
+	 */
+	struct xarray			dependencies;
+
+	/** @last_dependency: tracks @dependencies as they signal */
+	unsigned long			last_dependency;
 };
 
 static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job,
@@ -220,9 +233,14 @@ enum drm_gpu_sched_stat {
  */
 struct drm_sched_backend_ops {
 	/**
-         * @dependency: Called when the scheduler is considering scheduling
-         * this job next, to get another struct dma_fence for this job to
-	 * block on.  Once it returns NULL, run_job() may be called.
+	 * @dependency:
+	 *
+	 * Called when the scheduler is considering scheduling this job next, to
+	 * get another struct dma_fence for this job to block on.  Once it
+	 * returns NULL, run_job() may be called.
+	 *
+	 * If a driver exclusively uses drm_sched_job_await_fence() and
+	 * drm_sched_job_await_implicit() this can be ommitted and left as NULL.
 	 */
 	struct dma_fence *(*dependency)(struct drm_sched_job *sched_job,
 					struct drm_sched_entity *s_entity);
@@ -349,6 +367,13 @@ int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_sched_entity *entity,
 		       void *owner);
 void drm_sched_job_arm(struct drm_sched_job *job);
+int drm_sched_job_await_fence(struct drm_sched_job *job,
+			      struct dma_fence *fence);
+int drm_sched_job_await_implicit(struct drm_sched_job *job,
+				 struct drm_gem_object *obj,
+				 bool write);
+
+
 void drm_sched_entity_modify_sched(struct drm_sched_entity *entity,
 				    struct drm_gpu_scheduler **sched_list,
                                    unsigned int num_sched_list);
-- 
2.32.0

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2021-07-08 17:38 UTC|newest]

Thread overview: 84+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-08 17:37 [PATCH v3 00/20] drm/sched dependency tracking and dma-resv fixes Daniel Vetter
2021-07-08 17:37 ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 01/20] drm/sched: entity->rq selection cannot fail Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-09  6:53   ` Christian König
2021-07-09  6:53     ` [Intel-gfx] " Christian König
2021-07-09  7:14     ` Daniel Vetter
2021-07-09  7:14       ` [Intel-gfx] " Daniel Vetter
2021-07-09  7:23       ` Christian König
2021-07-09  7:23         ` [Intel-gfx] " Christian König
2021-07-09  8:00         ` Daniel Vetter
2021-07-09  8:00           ` [Intel-gfx] " Daniel Vetter
2021-07-09  8:11           ` Christian König
2021-07-09  8:11             ` [Intel-gfx] " Christian König
2021-07-08 17:37 ` [PATCH v3 02/20] drm/sched: Split drm_sched_job_init Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37   ` Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 03/20] drm/sched: Barriers are needed for entity->last_scheduled Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 18:56   ` Andrey Grodzovsky
2021-07-08 18:56     ` [Intel-gfx] " Andrey Grodzovsky
2021-07-08 19:53     ` Daniel Vetter
2021-07-08 19:53       ` [Intel-gfx] " Daniel Vetter
2021-07-08 21:54   ` [PATCH] " Daniel Vetter
2021-07-08 21:54     ` [Intel-gfx] " Daniel Vetter
2021-07-09  6:57     ` Christian König
2021-07-09  6:57       ` [Intel-gfx] " Christian König
2021-07-09  7:40       ` Daniel Vetter
2021-07-09  7:40         ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37 ` Daniel Vetter [this message]
2021-07-08 17:37   ` [Intel-gfx] [PATCH v3 04/20] drm/sched: Add dependency tracking Daniel Vetter
2021-07-08 17:37   ` Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 05/20] drm/sched: drop entity parameter from drm_sched_push_job Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37   ` Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 06/20] drm/sched: improve docs around drm_sched_entity Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 07/20] drm/panfrost: use scheduler dependency tracking Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37   ` Daniel Vetter
2021-07-12  9:19   ` Steven Price
2021-07-12  9:19     ` [Intel-gfx] " Steven Price
2021-07-12  9:19     ` Steven Price
2021-07-08 17:37 ` [PATCH v3 08/20] drm/lima: " Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37   ` Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 09/20] drm/v3d: Move drm_sched_job_init to v3d_job_init Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 10/20] drm/v3d: Use scheduler dependency handling Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 11/20] drm/etnaviv: " Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37   ` Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 12/20] drm/gem: Delete gem array fencing helpers Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37   ` Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 13/20] drm/sched: Don't store self-dependencies Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 14/20] drm/sched: Check locking in drm_sched_job_await_implicit Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 15/20] drm/msm: Don't break exclusive fence ordering Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37   ` Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 16/20] drm/msm: always wait for the exclusive fence Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37   ` Daniel Vetter
2021-07-09  8:48   ` Christian König
2021-07-09  8:48     ` [Intel-gfx] " Christian König
2021-07-09  8:48     ` Christian König
2021-07-09  9:15     ` Daniel Vetter
2021-07-09  9:15       ` [Intel-gfx] " Daniel Vetter
2021-07-09  9:15       ` Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 17/20] drm/etnaviv: Don't break exclusive fence ordering Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 18/20] drm/i915: delete exclude argument from i915_sw_fence_await_reservation Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 19/20] drm/i915: Don't break exclusive fence ordering Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37 ` [PATCH v3 20/20] dma-resv: Give the docs a do-over Daniel Vetter
2021-07-08 17:37   ` [Intel-gfx] " Daniel Vetter
2021-07-08 17:37   ` Daniel Vetter
2021-07-09  0:03 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for drm/sched dependency tracking and dma-resv fixes (rev2) Patchwork
2021-07-09  0:29 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-07-09 15:27 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210708173754.3877540-5-daniel.vetter@ffwll.ch \
    --to=daniel.vetter@ffwll.ch \
    --cc=Jack.Zhang1@amd.com \
    --cc=airlied@linux.ie \
    --cc=alexander.deucher@amd.com \
    --cc=andrey.grodzovsky@amd.com \
    --cc=boris.brezillon@collabora.com \
    --cc=christian.koenig@amd.com \
    --cc=daniel.vetter@intel.com \
    --cc=daniel@ffwll.ch \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=lee.jones@linaro.org \
    --cc=linaro-mm-sig@lists.linaro.org \
    --cc=linux-media@vger.kernel.org \
    --cc=luben.tuikov@amd.com \
    --cc=nirmoy.aiemd@gmail.com \
    --cc=steven.price@arm.com \
    --cc=sumit.semwal@linaro.org \
    --subject='Re: [PATCH v3 04/20] drm/sched: Add dependency tracking' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

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.