Merge branch 'drm-next-4.19' of git://people.freedesktop.org/~agd5f/linux into drm-next

First feature request for 4.19.  Highlights:
- Add initial amdgpu documentation
- Add initial GPU scheduler documention
- GPU scheduler fixes for dying processes
- Add support for the JPEG engine on VCN
- Switch CI to use powerplay by default
- EDC support for CZ
- More powerplay cleanups
- Misc DC fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>

Link: https://patchwork.freedesktop.org/patch/msgid/20180621161138.3008-1-alexander.deucher@amd.com

2 files changed, 152 insertions, 32 deletions

diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index dec655894d08..7c2dfd6cc1af 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -27,6 +27,8 @@
 #include <drm/spsc_queue.h>
 #include <linux/dma-fence.h>
 
+#define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000)
+
 struct drm_gpu_scheduler;
 struct drm_sched_rq;
 
@@ -43,13 +45,33 @@ enum drm_sched_priority {
 };
 
 /**
- * drm_sched_entity - A wrapper around a job queue (typically attached
- * to the DRM file_priv).
+ * struct drm_sched_entity - A wrapper around a job queue (typically
+ * attached to the DRM file_priv).
+ *
+ * @list: used to append this struct to the list of entities in the
+ *        runqueue.
+ * @rq: runqueue to which this entity belongs.
+ * @rq_lock: lock to modify the runqueue to which this entity belongs.
+ * @sched: the scheduler instance to which this entity is enqueued.
+ * @job_queue: the list of jobs of this entity.
+ * @fence_seq: a linearly increasing seqno incremented with each
+ *             new &drm_sched_fence which is part of the entity.
+ * @fence_context: a unique context for all the fences which belong
+ *                 to this entity.
+ *                 The &drm_sched_fence.scheduled uses the
+ *                 fence_context but &drm_sched_fence.finished uses
+ *                 fence_context + 1.
+ * @dependency: the dependency fence of the job which is on the top
+ *              of the job queue.
+ * @cb: callback for the dependency fence above.
+ * @guilty: points to ctx's guilty.
+ * @fini_status: contains the exit status in case the process was signalled.
+ * @last_scheduled: points to the finished fence of the last scheduled job.
  *
  * Entities will emit jobs in order to their corresponding hardware
  * ring, and the scheduler will alternate between entities based on
  * scheduling policy.
-*/
+ */
 struct drm_sched_entity {
 	struct list_head		list;
 	struct drm_sched_rq		*rq;
@@ -63,47 +85,95 @@ struct drm_sched_entity {
 
 	struct dma_fence		*dependency;
 	struct dma_fence_cb		cb;
-	atomic_t			*guilty; /* points to ctx's guilty */
-	int            fini_status;
-	struct dma_fence    *last_scheduled;
+	atomic_t			*guilty;
+	struct dma_fence                *last_scheduled;
 };
 
 /**
+ * struct drm_sched_rq - queue of entities to be scheduled.
+ *
+ * @lock: to modify the entities list.
+ * @entities: list of the entities to be scheduled.
+ * @current_entity: the entity which is to be scheduled.
+ *
  * Run queue is a set of entities scheduling command submissions for
  * one specific ring. It implements the scheduling policy that selects
  * the next entity to emit commands from.
-*/
+ */
 struct drm_sched_rq {
 	spinlock_t			lock;
 	struct list_head		entities;
 	struct drm_sched_entity		*current_entity;
 };
 
+/**
+ * struct drm_sched_fence - fences corresponding to the scheduling of a job.
+ */
 struct drm_sched_fence {
+        /**
+         * @scheduled: this fence is what will be signaled by the scheduler
+         * when the job is scheduled.
+         */
 	struct dma_fence		scheduled;
 
-	/* This fence is what will be signaled by the scheduler when
-	 * the job is completed.
-	 *
-	 * When setting up an out fence for the job, you should use
-	 * this, since it's available immediately upon
-	 * drm_sched_job_init(), and the fence returned by the driver
-	 * from run_job() won't be created until the dependencies have
-	 * resolved.
-	 */
+        /**
+         * @finished: this fence is what will be signaled by the scheduler
+         * when the job is completed.
+         *
+         * When setting up an out fence for the job, you should use
+         * this, since it's available immediately upon
+         * drm_sched_job_init(), and the fence returned by the driver
+         * from run_job() won't be created until the dependencies have
+         * resolved.
+         */
 	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.
+         */
 	struct dma_fence		*parent;
+        /**
+         * @sched: the scheduler instance to which the job having this struct
+         * belongs to.
+         */
 	struct drm_gpu_scheduler	*sched;
+        /**
+         * @lock: the lock used by the scheduled and the finished fences.
+         */
 	spinlock_t			lock;
+        /**
+         * @owner: job owner for debugging
+         */
 	void				*owner;
 };
 
 struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f);
 
 /**
- * drm_sched_job - A job to be run by an entity.
+ * struct drm_sched_job - A job to be run by an entity.
+ *
+ * @queue_node: used to append this struct to the queue of jobs in an entity.
+ * @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.
+ * @work_tdr: schedules a delayed call to @drm_sched_job_timedout after the timeout
+ *            interval is over.
+ * @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
+ *         limit of the scheduler then the job is marked guilty and will not
+ *         be scheduled further.
+ * @s_priority: the priority of the job.
+ * @entity: the entity to which this job belongs.
  *
  * 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
@@ -130,38 +200,64 @@ static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job,
 }
 
 /**
+ * struct drm_sched_backend_ops
+ *
  * Define the backend operations called by the scheduler,
- * these functions should be implemented in driver side
-*/
+ * these functions should be implemented in driver side.
+ */
 struct drm_sched_backend_ops {
-	/* Called when the scheduler is considering scheduling this
-	 * job next, to get another struct dma_fence for this job to
+	/**
+         * @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.
 	 */
 	struct dma_fence *(*dependency)(struct drm_sched_job *sched_job,
 					struct drm_sched_entity *s_entity);
 
-	/* Called to execute the job once all of the dependencies have
-	 * been resolved.  This may be called multiple times, if
+	/**
+         * @run_job: Called to execute the job once all of the dependencies
+         * have been resolved.  This may be called multiple times, if
 	 * timedout_job() has happened and drm_sched_job_recovery()
 	 * decides to try it again.
 	 */
 	struct dma_fence *(*run_job)(struct drm_sched_job *sched_job);
 
-	/* Called when a job has taken too long to execute, to trigger
-	 * GPU recovery.
+	/**
+         * @timedout_job: Called when a job has taken too long to execute,
+         * to trigger GPU recovery.
 	 */
 	void (*timedout_job)(struct drm_sched_job *sched_job);
 
-	/* Called once the job's finished fence has been signaled and
-	 * it's time to clean it up.
+	/**
+         * @free_job: Called once the job's finished fence has been signaled
+         * and it's time to clean it up.
 	 */
 	void (*free_job)(struct drm_sched_job *sched_job);
 };
 
 /**
- * One scheduler is implemented for each hardware ring
-*/
+ * struct drm_gpu_scheduler
+ *
+ * @ops: backend operations provided by the driver.
+ * @hw_submission_limit: the max size of the hardware queue.
+ * @timeout: the time after which a job is removed from the scheduler.
+ * @name: name of the ring for which this scheduler is being used.
+ * @sched_rq: priority wise array of run queues.
+ * @wake_up_worker: the wait queue on which the scheduler sleeps until a job
+ *                  is ready to be scheduled.
+ * @job_scheduled: once @drm_sched_entity_do_release is called the scheduler
+ *                 waits on this wait queue until all the scheduled jobs are
+ *                 finished.
+ * @hw_rq_count: the number of jobs currently in the hardware queue.
+ * @job_id_count: used to assign unique id to the each job.
+ * @thread: the kthread on which the scheduler which run.
+ * @ring_mirror_list: the list of jobs which are currently in the job queue.
+ * @job_list_lock: lock to protect the ring_mirror_list.
+ * @hang_limit: once the hangs by a job crosses this limit then it is marked
+ *              guilty and it will be considered for scheduling further.
+ *
+ * One scheduler is implemented for each hardware ring.
+ */
 struct drm_gpu_scheduler {
 	const struct drm_sched_backend_ops	*ops;
 	uint32_t			hw_submission_limit;
@@ -188,8 +284,8 @@ int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
 			  struct drm_sched_entity *entity,
 			  struct drm_sched_rq *rq,
 			  atomic_t *guilty);
-void drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity);
+long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
+			   struct drm_sched_entity *entity, long timeout);
 void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
 			   struct drm_sched_entity *entity);
 void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 78b4dd89fcb4..784b0fe470ee 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -72,6 +72,29 @@ extern "C" {
 #define DRM_IOCTL_AMDGPU_FENCE_TO_HANDLE DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_FENCE_TO_HANDLE, union drm_amdgpu_fence_to_handle)
 #define DRM_IOCTL_AMDGPU_SCHED		DRM_IOW(DRM_COMMAND_BASE + DRM_AMDGPU_SCHED, union drm_amdgpu_sched)
 
+/**
+ * DOC: memory domains
+ *
+ * %AMDGPU_GEM_DOMAIN_CPU	System memory that is not GPU accessible.
+ * Memory in this pool could be swapped out to disk if there is pressure.
+ *
+ * %AMDGPU_GEM_DOMAIN_GTT	GPU accessible system memory, mapped into the
+ * GPU's virtual address space via gart. Gart memory linearizes non-contiguous
+ * pages of system memory, allows GPU access system memory in a linezrized
+ * fashion.
+ *
+ * %AMDGPU_GEM_DOMAIN_VRAM	Local video memory. For APUs, it is memory
+ * carved out by the BIOS.
+ *
+ * %AMDGPU_GEM_DOMAIN_GDS	Global on-chip data storage used to share data
+ * across shader threads.
+ *
+ * %AMDGPU_GEM_DOMAIN_GWS	Global wave sync, used to synchronize the
+ * execution of all the waves on a device.
+ *
+ * %AMDGPU_GEM_DOMAIN_OA	Ordered append, used by 3D or Compute engines
+ * for appending data.
+ */
 #define AMDGPU_GEM_DOMAIN_CPU		0x1
 #define AMDGPU_GEM_DOMAIN_GTT		0x2
 #define AMDGPU_GEM_DOMAIN_VRAM		0x4
@@ -483,7 +506,8 @@ struct drm_amdgpu_gem_va {
 #define AMDGPU_HW_IP_UVD_ENC      5
 #define AMDGPU_HW_IP_VCN_DEC      6
 #define AMDGPU_HW_IP_VCN_ENC      7
-#define AMDGPU_HW_IP_NUM          8
+#define AMDGPU_HW_IP_VCN_JPEG     8
+#define AMDGPU_HW_IP_NUM          9
 
 #define AMDGPU_HW_IP_INSTANCE_MAX_COUNT 1