Merge tag 'drm-next-2024-11-21' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "There's a lot of rework, the panic helper support is being added to
  more drivers, v3d gets support for HW superpages, scheduler
  documentation, drm client and video aperture reworks, some new
  MAINTAINERS added, amdgpu has the usual lots of IP refactors, Intel
  has some Pantherlake enablement and xe is getting some SRIOV bits, but
  just lots of stuff everywhere.

  core:
   - split DSC helpers from DP helpers
   - clang build fixes for drm/mm test
   - drop simple pipeline support for gem vram
   - document submission error signaling
   - move drm_rect to drm core module from kms helper
   - add default client setup to most drivers
   - move to video aperture helpers instead of drm ones

  tests:
   - new framebuffer tests

  ttm:
   - remove swapped and pinned BOs from TTM lru

  panic:
   - fix uninit spinlock
   - add ABGR2101010 support

  bridge:
   - add TI TDP158 support
   - use standard PM OPS

  dma-fence:
   - use read_trylock instead of read_lock to help lockdep

  scheduler:
   - add errno to sched start to report different errors
   - add locking to drm_sched_entity_modify_sched
   - improve documentation

  xe:
   - add drm_line_printer
   - lots of refactoring
   - Enable Xe2 + PES disaggregation
   - add new ARL PCI ID
   - SRIOV development work
   - fix exec unnecessary implicit fence
   - define and parse OA sync props
   - forcewake refactoring

  i915:
   - Enable BMG/LNL ultra joiner
   - Enable 10bpx + CCS scanout on ICL+, fp16/CCS on TGL+
   - use DSB for plane/color mgmt
   - Arrow lake PCI IDs
   - lots of i915/xe display refactoring
   - enable PXP GuC autoteardown
   - Pantherlake (PTL) Xe3 LPD display enablement
   - Allow fastset HDR infoframe changes
   - write DP source OUI for non-eDP sinks
   - share PCI IDs between i915 and xe

  amdgpu:
   - SDMA queue reset support
   - SMU 13.0.6, JPEG 4.0.3 updates
   - Initial runtime repartitioning support
   - rework IP structs for multiple IP instances
   - Fetch EDID from _DDC if available
   - SMU13 zero rpm user control
   - lots of fixes/cleanups

  amdkfd:
   - Increase event FIFO size
   - add topology cap flag for per queue reset

  msm:
   - DPU:
      - SA8775P support
      - (disabled by default) MSM8917, MSM8937, MSM8953 and MSM8996 support
      - Enable large framebuffer support
      - Drop MSM8998 and SDM845
   - DP:
      - SA8775P support
   - GPU:
      - a7xx preemption support
      - Adreno A663 support

  ast:
   - warn about unsupported TX chips

  ivpu:
   - add coredump
   - add pantherlake support

  rockchip:
   - 4K@60Hz display enablement
   - generate pll programming tables

  panthor:
   - add timestamp query API
   - add realtime group priority
   - add fdinfo support

  etnaviv:
   - improve handling of DMA address limits
   - improve GPU hangcheck

  exynos:
   - Decon Exynos7870 support

  mediatek:
   - add OF graph support

  omap:
   - locking fixes

  bochs:
   - convert to gem/shmem from simpledrm

  v3d:
   - support big/super pages
   - add gemfs

  vc4:
   - BCM2712 support refactoring
   - add YUV444 format support

  udmabuf:
   - folio related fixes

  nouveau:
   - add panic support on nv50+"

* tag 'drm-next-2024-11-21' of https://gitlab.freedesktop.org/drm/kernel: (1583 commits)
  drm/xe/guc: Fix dereference before NULL check
  drm/amd: Fix initialization mistake for NBIO 7.7.0
  Revert "drm/amd/display: parse umc_info or vram_info based on ASIC"
  drm/amd/display: Fix failure to read vram info due to static BP_RESULT
  drm/amdgpu: enable GTT fallback handling for dGPUs only
  drm/amd/amdgpu: limit single process inside MES
  drm/fourcc: add AMD_FMT_MOD_TILE_GFX9_4K_D_X
  drm/amdgpu/mes12: correct kiq unmap latency
  drm/amdgpu: Support vcn and jpeg error info parsing
  drm/amd : Update MES API header file for v11 & v12
  drm/amd/amdkfd: add/remove kfd queues on start/stop KFD scheduling
  drm/amdkfd: change kfd process kref count at creation
  drm/amdgpu: Cleanup shift coding style
  drm/amd/amdgpu: Increase MES log buffer to dump mes scratch data
  drm/amdgpu: Implement virt req_ras_err_count
  drm/amdgpu: VF Query RAS Caps from Host if supported
  drm/amdgpu: Add msg handlers for SRIOV RAS Telemetry
  drm/amdgpu: Update SRIOV Exchange Headers for RAS Telemetry Support
  drm/amd/display: 3.2.309
  drm/amd/display: Adjust VSDB parser for replay feature
  ...

1 files changed, 34 insertions, 22 deletions

diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 9c437a057e5d..95e17504e46a 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -33,11 +33,11 @@
 #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000)
 
 /**
- * DRM_SCHED_FENCE_DONT_PIPELINE - Prefent dependency pipelining
+ * DRM_SCHED_FENCE_DONT_PIPELINE - Prevent dependency pipelining
  *
  * Setting this flag on a scheduler fence prevents pipelining of jobs depending
  * on this fence. In other words we always insert a full CPU round trip before
- * dependen jobs are pushed to the hw queue.
+ * dependent jobs are pushed to the hw queue.
  */
 #define DRM_SCHED_FENCE_DONT_PIPELINE	DMA_FENCE_FLAG_USER_BITS
 
@@ -71,7 +71,7 @@ enum drm_sched_priority {
 	DRM_SCHED_PRIORITY_COUNT
 };
 
-/* Used to chose between FIFO and RR jobs scheduling */
+/* Used to choose between FIFO and RR job-scheduling */
 extern int drm_sched_policy;
 
 #define DRM_SCHED_POLICY_RR    0
@@ -97,13 +97,21 @@ struct drm_sched_entity {
 	struct list_head		list;
 
 	/**
+	 * @lock:
+	 *
+	 * Lock protecting the run-queue (@rq) to which this entity belongs,
+	 * @priority and the list of schedulers (@sched_list, @num_sched_list).
+	 */
+	spinlock_t			lock;
+
+	/**
 	 * @rq:
 	 *
 	 * Runqueue on which this entity is currently scheduled.
 	 *
 	 * FIXME: Locking is very unclear for this. Writers are protected by
-	 * @rq_lock, but readers are generally lockless and seem to just race
-	 * with not even a READ_ONCE.
+	 * @lock, but readers are generally lockless and seem to just race with
+	 * not even a READ_ONCE.
 	 */
 	struct drm_sched_rq		*rq;
 
@@ -136,18 +144,11 @@ struct drm_sched_entity {
 	 * @priority:
 	 *
 	 * Priority of the entity. This can be modified by calling
-	 * drm_sched_entity_set_priority(). Protected by &rq_lock.
+	 * drm_sched_entity_set_priority(). Protected by @lock.
 	 */
 	enum drm_sched_priority         priority;
 
 	/**
-	 * @rq_lock:
-	 *
-	 * Lock to modify the runqueue to which this entity belongs.
-	 */
-	spinlock_t			rq_lock;
-
-	/**
 	 * @job_queue: the list of jobs of this entity.
 	 */
 	struct spsc_queue		job_queue;
@@ -198,7 +199,7 @@ struct drm_sched_entity {
 	 *
 	 * Points to the finished fence of the last scheduled job. Only written
 	 * by the scheduler thread, can be accessed locklessly from
-	 * drm_sched_job_arm() iff the queue is empty.
+	 * drm_sched_job_arm() if the queue is empty.
 	 */
 	struct dma_fence __rcu		*last_scheduled;
 
@@ -243,21 +244,23 @@ struct drm_sched_entity {
 /**
  * struct drm_sched_rq - queue of entities to be scheduled.
  *
- * @lock: to modify the entities list.
  * @sched: the scheduler to which this rq belongs to.
- * @entities: list of the entities to be scheduled.
+ * @lock: protects @entities, @rb_tree_root and @current_entity.
  * @current_entity: the entity which is to be scheduled.
- * @rb_tree_root: root of time based priory queue of entities for FIFO scheduling
+ * @entities: list of the entities to be scheduled.
+ * @rb_tree_root: root of time based priority queue of entities for FIFO scheduling
  *
  * 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 drm_gpu_scheduler	*sched;
-	struct list_head		entities;
+
+	spinlock_t			lock;
+	/* Following members are protected by the @lock: */
 	struct drm_sched_entity		*current_entity;
+	struct list_head		entities;
 	struct rb_root_cached		rb_tree_root;
 };
 
@@ -321,7 +324,7 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f);
  * @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.
+ * @work: Helper to reschedule 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
  *         limit of the scheduler then the job is marked guilty and will not
@@ -337,6 +340,14 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f);
 struct drm_sched_job {
 	struct spsc_node		queue_node;
 	struct list_head		list;
+
+	/**
+	 * @sched:
+	 *
+	 * The scheduler this job is or will be scheduled on. Gets set by
+	 * drm_sched_job_arm(). Valid until drm_sched_backend_ops.free_job()
+	 * has finished.
+	 */
 	struct drm_gpu_scheduler	*sched;
 	struct drm_sched_fence		*s_fence;
 
@@ -579,7 +590,7 @@ 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);
+void drm_sched_start(struct drm_gpu_scheduler *sched, int errno);
 void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched);
 void drm_sched_increase_karma(struct drm_sched_job *bad);
 void drm_sched_reset_karma(struct drm_sched_job *bad);
@@ -593,7 +604,8 @@ void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
 void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
 				struct drm_sched_entity *entity);
 
-void drm_sched_rq_update_fifo(struct drm_sched_entity *entity, ktime_t ts);
+void drm_sched_rq_update_fifo_locked(struct drm_sched_entity *entity,
+				     struct drm_sched_rq *rq, ktime_t ts);
 
 int drm_sched_entity_init(struct drm_sched_entity *entity,
 			  enum drm_sched_priority priority,