Merge tag 'drm-next-2021-02-19' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "A pretty normal tree, lots of refactoring across the board, ttm, i915,
  nouveau, and bunch of features in various drivers.

  docs:
   - lots of updated docs

  core:
   - require crtc to have unique primary plane
   - fourcc macro fix
   - PCI bar quirk for bar resizing
   - don't sent hotplug on error
   - move vm code to legacy
   - nuke hose only used on old oboslete alpha

  dma-buf:
   - kernel doc updates
   - improved lock tracking

  dp/hdmi:
   - DP-HDMI2.1 protocol converter support

  ttm:
   - bo size handling cleanup
   - release a pinned bo warning
   - cleanup lru handler
   - avoid using pages with drm_prime_sg_to_page_addr_arrays

  cma-helper:
   - prime/mmap fixes

  bridge:
   - add DP support

  gma500:
   - remove gma3600 support

  i915:
   - try eDP fast/narrow link again with fallback
   - Intel eDP backlight control
   - replace display register read/write macros
   - refactor intel_display.c
   - display power improvements
   - HPD code cleanup
   - Rocketlake display fixes
   - Power/backlight/RPM fixes
   - DG1 display fix
   - IVB/BYT clear residuals security fix again
   - make i915 mitigations options via parameter
   - HSW GT1 GPU hangs fixes
   - DG1 workaround hang fixes
   - TGL DMAR hang avoidance
   - Lots of GT fixes
   - follow on fixes for residuals clear
   - gen7 per-engine-reset support
   - HDCP2.2 + HDCP1.4 GEN12 DP MST support
   - TGL clear color support
   - backlight refactoring
   - VRR/Adaptive sync enabling on DP/EDP for TGL+
   - async flips for all ilk+

  amdgpu:
   - rework IH ring handling (Vega/Navi)
   - rework HDP handling (Vega/Navi)
   - swSMU updates for renoir/vangogh
   - Sienna Cichild overdrive support
   - FP16 on DCE8-11 support
   - GPU reset on navy flounder/vangogh
   - SMU profile fixes for APU
   - SR-IOV fixes
   - Vangogh SMU fixes
   - fan speed control fixes

  amdkfd:
   - config handling fix
   - buffer free fix
   - recursive lock warnings fix

  nouveau:
   - Turing MMU fault recovery fixes
   - mDP connectors reporting fix
   - audio locking fixes
   - rework engines/instances code to support new scheme

  tegra:
   - VIC newer firmware support
   - display/gr2d fixes for older tegra
   - pm reference leak fix

  mediatek:
   - SOC MT8183 support
   - decouple sub driver + share mtk mutex driver

  radeon:
   - PCI resource fix for some platforms

  ingenic:
   - pm support
   - 8-bit delta RGB panels

  vmwgfx:
   - managed driver helpers

  vc4:
   - BCM2711 DSI1 support
   - converted to atomic helpers
   - enable 10/12 bpc outputs
   - gem prime mmap helpers
   - CEC fix

  omap:
   - use degamma table
   - CTM support
   - rework DSI support

  imx:
   - stack usage fixes
   - drm managed support
   - imx-tve clock provider leak fix
-

  rcar-du:
   - default mode fixes
   - conversion to managed API

  hisilicon:
   - use simple encoder

  vkms:
   - writeback connector support

  d3:
   - BT2020 support"

* tag 'drm-next-2021-02-19' of git://anongit.freedesktop.org/drm/drm: (1459 commits)
  drm/amdgpu: Set reference clock to 100Mhz on Renoir (v2)
  drm/radeon: OLAND boards don't have VCE
  drm/amdkfd: Fix recursive lock warnings
  drm/amd/display: Add FPU wrappers to dcn21_validate_bandwidth()
  drm/amd/display: Fix potential integer overflow
  drm/amdgpu/display: remove hdcp_srm sysfs on device removal
  drm/amdgpu: fix CGTS_TCC_DISABLE register offset on gfx10.3
  drm/i915/gt: Correct surface base address for renderclear
  drm/i915: Disallow plane x+w>stride on ilk+ with X-tiling
  drm/nouveau/top/ga100: initial support
  drm/nouveau/top: add ioctrl/nvjpg
  drm/nouveau/privring: rename from ibus
  drm/nouveau/nvkm: remove nvkm_subdev.index
  drm/nouveau/nvkm: determine subdev id/order from layout
  drm/nouveau/vic: switch to instanced constructor
  drm/nouveau/sw: switch to instanced constructor
  drm/nouveau/sec2: switch to instanced constructor
  drm/nouveau/sec: switch to instanced constructor
  drm/nouveau/pm: switch to instanced constructor
  drm/nouveau/nvenc: switch to instanced constructor
  ...

1 files changed, 67 insertions, 56 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index b498d474ef9e..92637b70c9bf 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -60,8 +60,6 @@
 #define to_drm_sched_job(sched_job)		\
 		container_of((sched_job), struct drm_sched_job, queue_node)
 
-static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb);
-
 /**
  * drm_sched_rq_init - initialize a given run queue struct
  *
@@ -164,6 +162,40 @@ drm_sched_rq_select_entity(struct drm_sched_rq *rq)
 }
 
 /**
+ * drm_sched_job_done - complete a job
+ * @s_job: pointer to the job which is done
+ *
+ * Finish the job's fence and wake up the worker thread.
+ */
+static void drm_sched_job_done(struct drm_sched_job *s_job)
+{
+	struct drm_sched_fence *s_fence = s_job->s_fence;
+	struct drm_gpu_scheduler *sched = s_fence->sched;
+
+	atomic_dec(&sched->hw_rq_count);
+	atomic_dec(&sched->score);
+
+	trace_drm_sched_process_job(s_fence);
+
+	dma_fence_get(&s_fence->finished);
+	drm_sched_fence_finished(s_fence);
+	dma_fence_put(&s_fence->finished);
+	wake_up_interruptible(&sched->wake_up_worker);
+}
+
+/**
+ * drm_sched_job_done_cb - the callback for a done job
+ * @f: fence
+ * @cb: fence callbacks
+ */
+static void drm_sched_job_done_cb(struct dma_fence *f, struct dma_fence_cb *cb)
+{
+	struct drm_sched_job *s_job = container_of(cb, struct drm_sched_job, cb);
+
+	drm_sched_job_done(s_job);
+}
+
+/**
  * drm_sched_dependency_optimized
  *
  * @fence: the dependency fence
@@ -199,7 +231,7 @@ EXPORT_SYMBOL(drm_sched_dependency_optimized);
 static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched)
 {
 	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
-	    !list_empty(&sched->ring_mirror_list))
+	    !list_empty(&sched->pending_list))
 		schedule_delayed_work(&sched->work_tdr, sched->timeout);
 }
 
@@ -259,7 +291,7 @@ void drm_sched_resume_timeout(struct drm_gpu_scheduler *sched,
 {
 	spin_lock(&sched->job_list_lock);
 
-	if (list_empty(&sched->ring_mirror_list))
+	if (list_empty(&sched->pending_list))
 		cancel_delayed_work(&sched->work_tdr);
 	else
 		mod_delayed_work(system_wq, &sched->work_tdr, remaining);
@@ -273,7 +305,7 @@ static void drm_sched_job_begin(struct drm_sched_job *s_job)
 	struct drm_gpu_scheduler *sched = s_job->sched;
 
 	spin_lock(&sched->job_list_lock);
-	list_add_tail(&s_job->node, &sched->ring_mirror_list);
+	list_add_tail(&s_job->list, &sched->pending_list);
 	drm_sched_start_timeout(sched);
 	spin_unlock(&sched->job_list_lock);
 }
@@ -287,8 +319,8 @@ static void drm_sched_job_timedout(struct work_struct *work)
 
 	/* Protects against concurrent deletion in drm_sched_get_cleanup_job */
 	spin_lock(&sched->job_list_lock);
-	job = list_first_entry_or_null(&sched->ring_mirror_list,
-				       struct drm_sched_job, node);
+	job = list_first_entry_or_null(&sched->pending_list,
+				       struct drm_sched_job, list);
 
 	if (job) {
 		/*
@@ -296,7 +328,7 @@ static void drm_sched_job_timedout(struct work_struct *work)
 		 * drm_sched_cleanup_jobs. It will be reinserted back after sched->thread
 		 * is parked at which point it's safe.
 		 */
-		list_del_init(&job->node);
+		list_del_init(&job->list);
 		spin_unlock(&sched->job_list_lock);
 
 		job->sched->ops->timedout_job(job);
@@ -372,7 +404,7 @@ EXPORT_SYMBOL(drm_sched_increase_karma);
  * 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.
+ * pending list any more.
  *
  */
 void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
@@ -393,26 +425,27 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
 		 * Add at the head of the queue to reflect it was the earliest
 		 * job extracted.
 		 */
-		list_add(&bad->node, &sched->ring_mirror_list);
+		list_add(&bad->list, &sched->pending_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
+	 * their HW callbacks or remove them from pending list if they already
 	 * signaled.
 	 * This iteration is thread safe as sched thread is stopped.
 	 */
-	list_for_each_entry_safe_reverse(s_job, tmp, &sched->ring_mirror_list, node) {
+	list_for_each_entry_safe_reverse(s_job, tmp, &sched->pending_list,
+					 list) {
 		if (s_job->s_fence->parent &&
 		    dma_fence_remove_callback(s_job->s_fence->parent,
 					      &s_job->cb)) {
 			atomic_dec(&sched->hw_rq_count);
 		} else {
 			/*
-			 * remove job from ring_mirror_list.
+			 * remove job from pending_list.
 			 * Locking here is for concurrent resume timeout
 			 */
 			spin_lock(&sched->job_list_lock);
-			list_del_init(&s_job->node);
+			list_del_init(&s_job->list);
 			spin_unlock(&sched->job_list_lock);
 
 			/*
@@ -463,7 +496,7 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
 	 * 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) {
+	list_for_each_entry_safe(s_job, tmp, &sched->pending_list, list) {
 		struct dma_fence *fence = s_job->s_fence->parent;
 
 		atomic_inc(&sched->hw_rq_count);
@@ -473,14 +506,14 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
 
 		if (fence) {
 			r = dma_fence_add_callback(fence, &s_job->cb,
-						   drm_sched_process_job);
+						   drm_sched_job_done_cb);
 			if (r == -ENOENT)
-				drm_sched_process_job(fence, &s_job->cb);
+				drm_sched_job_done(s_job);
 			else if (r)
 				DRM_ERROR("fence add callback failed (%d)\n",
 					  r);
 		} else
-			drm_sched_process_job(NULL, &s_job->cb);
+			drm_sched_job_done(s_job);
 	}
 
 	if (full_recovery) {
@@ -494,7 +527,7 @@ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
 EXPORT_SYMBOL(drm_sched_start);
 
 /**
- * drm_sched_resubmit_jobs - helper to relunch job from mirror ring list
+ * drm_sched_resubmit_jobs - helper to relunch job from pending ring list
  *
  * @sched: scheduler instance
  *
@@ -506,7 +539,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 	bool found_guilty = false;
 	struct dma_fence *fence;
 
-	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
+	list_for_each_entry_safe(s_job, tmp, &sched->pending_list, list) {
 		struct drm_sched_fence *s_fence = s_job->s_fence;
 
 		if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) {
@@ -566,7 +599,7 @@ int drm_sched_job_init(struct drm_sched_job *job,
 		return -ENOMEM;
 	job->id = atomic64_inc_return(&sched->job_id_count);
 
-	INIT_LIST_HEAD(&job->node);
+	INIT_LIST_HEAD(&job->list);
 
 	return 0;
 }
@@ -636,36 +669,11 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
 }
 
 /**
- * drm_sched_process_job - process a job
- *
- * @f: fence
- * @cb: fence callbacks
- *
- * Called after job has finished execution.
- */
-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;
-
-	atomic_dec(&sched->hw_rq_count);
-	atomic_dec(&sched->score);
-
-	trace_drm_sched_process_job(s_fence);
-
-	dma_fence_get(&s_fence->finished);
-	drm_sched_fence_finished(s_fence);
-	dma_fence_put(&s_fence->finished);
-	wake_up_interruptible(&sched->wake_up_worker);
-}
-
-/**
  * drm_sched_get_cleanup_job - fetch the next finished job to be destroyed
  *
  * @sched: scheduler instance
  *
- * Returns the next finished job from the mirror list (if there is one)
+ * Returns the next finished job from the pending list (if there is one)
  * ready for it to be destroyed.
  */
 static struct drm_sched_job *
@@ -675,7 +683,7 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 
 	/*
 	 * Don't destroy jobs while the timeout worker is running  OR thread
-	 * is being parked and hence assumed to not touch ring_mirror_list
+	 * is being parked and hence assumed to not touch pending_list
 	 */
 	if ((sched->timeout != MAX_SCHEDULE_TIMEOUT &&
 	    !cancel_delayed_work(&sched->work_tdr)) ||
@@ -684,12 +692,12 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 
 	spin_lock(&sched->job_list_lock);
 
-	job = list_first_entry_or_null(&sched->ring_mirror_list,
-				       struct drm_sched_job, node);
+	job = list_first_entry_or_null(&sched->pending_list,
+				       struct drm_sched_job, list);
 
 	if (job && dma_fence_is_signaled(&job->s_fence->finished)) {
-		/* remove job from ring_mirror_list */
-		list_del_init(&job->node);
+		/* remove job from pending_list */
+		list_del_init(&job->list);
 	} else {
 		job = NULL;
 		/* queue timeout for next job */
@@ -809,9 +817,9 @@ static int drm_sched_main(void *param)
 		if (!IS_ERR_OR_NULL(fence)) {
 			s_fence->parent = dma_fence_get(fence);
 			r = dma_fence_add_callback(fence, &sched_job->cb,
-						   drm_sched_process_job);
+						   drm_sched_job_done_cb);
 			if (r == -ENOENT)
-				drm_sched_process_job(fence, &sched_job->cb);
+				drm_sched_job_done(sched_job);
 			else if (r)
 				DRM_ERROR("fence add callback failed (%d)\n",
 					  r);
@@ -820,7 +828,7 @@ static int drm_sched_main(void *param)
 			if (IS_ERR(fence))
 				dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
 
-			drm_sched_process_job(NULL, &sched_job->cb);
+			drm_sched_job_done(sched_job);
 		}
 
 		wake_up(&sched->job_scheduled);
@@ -858,7 +866,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 
 	init_waitqueue_head(&sched->wake_up_worker);
 	init_waitqueue_head(&sched->job_scheduled);
-	INIT_LIST_HEAD(&sched->ring_mirror_list);
+	INIT_LIST_HEAD(&sched->pending_list);
 	spin_lock_init(&sched->job_list_lock);
 	atomic_set(&sched->hw_rq_count, 0);
 	INIT_DELAYED_WORK(&sched->work_tdr, drm_sched_job_timedout);
@@ -891,6 +899,9 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 	if (sched->thread)
 		kthread_stop(sched->thread);
 
+	/* Confirm no work left behind accessing device structures */
+	cancel_delayed_work_sync(&sched->work_tdr);
+
 	sched->ready = false;
 }
 EXPORT_SYMBOL(drm_sched_fini);