Merge tag 'drm-misc-next-2023-11-17' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

drm-misc-next for 6.8:

UAPI Changes:
  - drm: Introduce CLOSE_FB ioctl
  - drm/dp-mst: Documentation for the PATH property
  - fdinfo: Do not align to a MB if the size is larger than 1MiB
  - virtio-gpu: add explicit virtgpu context debug name

Cross-subsystem Changes:
  - dma-buf: Add dma_fence_timestamp helper

Core Changes:
  - client: Do not acquire module reference
  - edid: split out drm_eld, add SAD helpers
  - format-helper: Cache format conversion buffers
  - sched: Move from a kthread to a workqueue, rename some internal
    functions to make it clearer, implement dynamic job-flow control
  - gpuvm: Provide more features to handle GEM objects
  - tests: Remove slow kunit tests

Driver Changes:
  - ivpu: Update FW API, new debugfs file, a new NOP job submission test
    mode, improve suspend/resume, PM improvements, MMU PT optimizations,
    firmware profiling frequency support, support for uncached buffers,
    switch to gem shmem helpers, replace kthread with threaded
    interrupts
  - panfrost: PM improvements
  - qaic: Allow to run with a single MSI, support host/device time
    synchronization, misc improvements
  - simplefb: Support memory-regions, support power-domains
  - ssd130x: Unitialized variable fixes
  - omapdrm: dma-fence lockdep annotation fix
  - tidss: dma-fence lockdep annotation fix
  - v3d: Support BCM2712 (RaspberryPi5), Support fdinfo and gputop
  - panel:
    - edp: Support AUO B116XTN02, BOE NT116WHM-N21,836X2, NV116WHM-N49
      V8.0, plus a whole bunch of panels used on Mediatek chromebooks.

Note that the one missing s-o-b for 0da611a87021 ("dma-buf: add
dma_fence_timestamp helper") has been supplied here, and rebasing the
entire tree with upsetting committers didn't seem worth the trouble:
https://lore.kernel.org/dri-devel/ce94020e-a7d4-4799-b87d-fbea7b14a268@gmail.com/

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
From: Maxime Ripard <mripard@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/y4awn5vcfy2lr2hpauo7rc4nfpnc6kksr7btmnwaz7zk63pwoi@gwwef5iqpzva

1 files changed, 38 insertions, 12 deletions

diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index d2fb81e34174..9a50348bd5c0 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -320,6 +320,7 @@ 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.
+ * @credits: the number of credits this job contributes to the scheduler
  * @work: Helper to reschdeule job kill to different context.
  * @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
@@ -339,6 +340,8 @@ struct drm_sched_job {
 	struct drm_gpu_scheduler	*sched;
 	struct drm_sched_fence		*s_fence;
 
+	u32				credits;
+
 	/*
 	 * work is used only after finish_cb has been used and will not be
 	 * accessed anymore.
@@ -462,29 +465,42 @@ struct drm_sched_backend_ops {
          * and it's time to clean it up.
 	 */
 	void (*free_job)(struct drm_sched_job *sched_job);
+
+	/**
+	 * @update_job_credits: Called when the scheduler is considering this
+	 * job for execution.
+	 *
+	 * This callback returns the number of credits the job would take if
+	 * pushed to the hardware. Drivers may use this to dynamically update
+	 * the job's credit count. For instance, deduct the number of credits
+	 * for already signalled native fences.
+	 *
+	 * This callback is optional.
+	 */
+	u32 (*update_job_credits)(struct drm_sched_job *sched_job);
 };
 
 /**
  * struct drm_gpu_scheduler - scheduler instance-specific data
  *
  * @ops: backend operations provided by the driver.
- * @hw_submission_limit: the max size of the hardware queue.
+ * @credit_limit: the credit limit of this scheduler
+ * @credit_count: the current credit count of this scheduler
  * @timeout: the time after which a job is removed from the scheduler.
  * @name: name of the ring for which this scheduler is being used.
  * @num_rqs: Number of run-queues. This is at most DRM_SCHED_PRIORITY_COUNT,
  *           as there's usually one run-queue per priority, but could be less.
  * @sched_rq: An allocated array of run-queues of size @num_rqs;
- * @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.
+ * @submit_wq: workqueue used to queue @work_run_job and @work_free_job
  * @timeout_wq: workqueue used to queue @work_tdr
+ * @work_run_job: work which calls run_job op of each scheduler.
+ * @work_free_job: work which calls free_job op of each scheduler.
  * @work_tdr: schedules a delayed call to @drm_sched_job_timedout after the
  *            timeout interval is over.
- * @thread: the kthread on which the scheduler which run.
  * @pending_list: the list of jobs which are currently in the job queue.
  * @job_list_lock: lock to protect the pending_list.
  * @hang_limit: once the hangs by a job crosses this limit then it is marked
@@ -493,24 +509,27 @@ struct drm_sched_backend_ops {
  * @_score: score used when the driver doesn't provide one
  * @ready: marks if the underlying HW is ready to work
  * @free_guilty: A hit to time out handler to free the guilty job.
+ * @pause_submit: pause queuing of @work_run_job on @submit_wq
+ * @own_submit_wq: scheduler owns allocation of @submit_wq
  * @dev: system &struct device
  *
  * One scheduler is implemented for each hardware ring.
  */
 struct drm_gpu_scheduler {
 	const struct drm_sched_backend_ops	*ops;
-	uint32_t			hw_submission_limit;
+	u32				credit_limit;
+	atomic_t			credit_count;
 	long				timeout;
 	const char			*name;
 	u32                             num_rqs;
 	struct drm_sched_rq             **sched_rq;
-	wait_queue_head_t		wake_up_worker;
 	wait_queue_head_t		job_scheduled;
-	atomic_t			hw_rq_count;
 	atomic64_t			job_id_count;
+	struct workqueue_struct		*submit_wq;
 	struct workqueue_struct		*timeout_wq;
+	struct work_struct		work_run_job;
+	struct work_struct		work_free_job;
 	struct delayed_work		work_tdr;
-	struct task_struct		*thread;
 	struct list_head		pending_list;
 	spinlock_t			job_list_lock;
 	int				hang_limit;
@@ -518,19 +537,22 @@ struct drm_gpu_scheduler {
 	atomic_t                        _score;
 	bool				ready;
 	bool				free_guilty;
+	bool				pause_submit;
+	bool				own_submit_wq;
 	struct device			*dev;
 };
 
 int drm_sched_init(struct drm_gpu_scheduler *sched,
 		   const struct drm_sched_backend_ops *ops,
-		   u32 num_rqs, uint32_t hw_submission, unsigned int hang_limit,
+		   struct workqueue_struct *submit_wq,
+		   u32 num_rqs, u32 credit_limit, unsigned int hang_limit,
 		   long timeout, struct workqueue_struct *timeout_wq,
 		   atomic_t *score, const char *name, struct device *dev);
 
 void drm_sched_fini(struct drm_gpu_scheduler *sched);
 int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_sched_entity *entity,
-		       void *owner);
+		       u32 credits, void *owner);
 void drm_sched_job_arm(struct drm_sched_job *job);
 int drm_sched_job_add_dependency(struct drm_sched_job *job,
 				 struct dma_fence *fence);
@@ -550,8 +572,12 @@ void drm_sched_entity_modify_sched(struct drm_sched_entity *entity,
 				    struct drm_gpu_scheduler **sched_list,
                                    unsigned int num_sched_list);
 
+void drm_sched_tdr_queue_imm(struct drm_gpu_scheduler *sched);
 void drm_sched_job_cleanup(struct drm_sched_job *job);
-void drm_sched_wakeup_if_can_queue(struct drm_gpu_scheduler *sched);
+void drm_sched_wakeup(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity);
+bool drm_sched_wqueue_ready(struct drm_gpu_scheduler *sched);
+void drm_sched_wqueue_stop(struct drm_gpu_scheduler *sched);
+void drm_sched_wqueue_start(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);