Merge tag 'drm-next-2023-10-31-1' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Highlights:
   - AMD adds some more upcoming HW platforms
   - Intel made Meteorlake stable and started adding Lunarlake
   - nouveau has a bunch of display rework in prepartion for the NVIDIA
     GSP firmware support
   - msm adds a7xx support
   - habanalabs has finished migration to accel subsystem

  Detail summary:

  kernel:
   - add initial vmemdup-user-array

  core:
   - fix platform remove() to return void
   - drm_file owner updated to reflect owner
   - move size calcs to drm buddy allocator
   - let GPUVM build as a module
   - allow variable number of run-queues in scheduler

  edid:
   - handle bad h/v sync_end in EDIDs

  panfrost:
   - add Boris as maintainer

  fbdev:
   - use fb_ops helpers more
   - only allow logo use from fbcon
   - rename fb_pgproto to pgprot_framebuffer
   - add HPD state to drm_connector_oob_hotplug_event
   - convert to fbdev i/o mem helpers

  i915:
   - Enable meteorlake by default
   - Early Xe2 LPD/Lunarlake display enablement
   - Rework subplatforms into IP version checks
   - GuC based TLB invalidation for Meteorlake
   - Display rework for future Xe driver integration
   - LNL FBC features
   - LNL display feature capability reads
   - update recommended fw versions for DG2+
   - drop fastboot module parameter
   - added deviceid for Arrowlake-S
   - drop preproduction workarounds
   - don't disable preemption for resets
   - cleanup inlines in headers
   - PXP firmware loading fix
   - Fix sg list lengths
   - DSC PPS state readout/verification
   - Add more RPL P/U PCI IDs
   - Add new DG2-G12 stepping
   - DP enhanced framing support to state checker
   - Improve shared link bandwidth management
   - stop using GEM macros in display code
   - refactor related code into display code
   - locally enable W=1 warnings
   - remove PSR watchdog timers on LNL

  amdgpu:
   - RAS/FRU EEPROM updatse
   - IP discovery updatses
   - GC 11.5 support
   - DCN 3.5 support
   - VPE 6.1 support
   - NBIO 7.11 support
   - DML2 support
   - lots of IP updates
   - use flexible arrays for bo list handling
   - W=1 fixes
   - Enable seamless boot in more cases
   - Enable context type property for HDMI
   - Rework GPUVM TLB flushing
   - VCN IB start/size alignment fixes

  amdkfd:
   - GC 10/11 fixes
   - GC 11.5 support
   - use partial migration in GPU faults

  radeon:
   - W=1 Fixes
   - fix some possible buffer overflow/NULL derefs

  nouveau:
   - update uapi for NO_PREFETCH
   - scheduler/fence fixes
   - rework suspend/resume for GSP-RM
   - rework display in preparation for GSP-RM

  habanalabs:
   - uapi: expose tsc clock
   - uapi: block access to eventfd through control device
   - uapi: force dma-buf export to PAGE_SIZE alignments
   - complete move to accel subsystem
   - move firmware interface include files
   - perform hard reset on PCIe AXI drain event
   - optimise user interrupt handling

  msm:
   - DP: use existing helpers for DPCD
   - DPU: interrupts reworked
   - gpu: a7xx (a730/a740) support
   - decouple msm_drv from kms for headless devices

  mediatek:
   - MT8188 dsi/dp/edp support
   - DDP GAMMA - 12 bit LUT support
   - connector dynamic selection capability

  rockchip:
   - rv1126 mipi-dsi/vop support
   - add planar formats

  ast:
   - rename constants

  panels:
   - Mitsubishi AA084XE01
   - JDI LPM102A188A
   - LTK050H3148W-CTA6

  ivpu:
   - power management fixes

  qaic:
   - add detach slice bo api

  komeda:
   - add NV12 writeback

  tegra:
   - support NVSYNC/NHSYNC
   - host1x suspend fixes

  ili9882t:
   - separate into own driver"

* tag 'drm-next-2023-10-31-1' of git://anongit.freedesktop.org/drm/drm: (1803 commits)
  drm/amdgpu: Remove unused variables from amdgpu_show_fdinfo
  drm/amdgpu: Remove duplicate fdinfo fields
  drm/amd/amdgpu: avoid to disable gfxhub interrupt when driver is unloaded
  drm/amdgpu: Add EXT_COHERENT support for APU and NUMA systems
  drm/amdgpu: Retrieve CE count from ce_count_lo_chip in EccInfo table
  drm/amdgpu: Identify data parity error corrected in replay mode
  drm/amdgpu: Fix typo in IP discovery parsing
  drm/amd/display: fix S/G display enablement
  drm/amdxcp: fix amdxcp unloads incompletely
  drm/amd/amdgpu: fix the GPU power print error in pm info
  drm/amdgpu: Use pcie domain of xcc acpi objects
  drm/amd: check num of link levels when update pcie param
  drm/amdgpu: Add a read to GFX v9.4.3 ring test
  drm/amd/pm: call smu_cmn_get_smc_version in is_mode1_reset_supported.
  drm/amdgpu: get RAS poison status from DF v4_6_2
  drm/amdgpu: Use discovery table's subrevision
  drm/amd/display: 3.2.256
  drm/amd/display: add interface to query SubVP status
  drm/amd/display: Read before writing Backlight Mode Set Register
  drm/amd/display: Disable SYMCLK32_SE RCO on DCN314
  ...

1 files changed, 60 insertions, 14 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 5a3a622fc672..99797a8c836a 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -632,8 +632,14 @@ int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_sched_entity *entity,
 		       void *owner)
 {
-	if (!entity->rq)
+	if (!entity->rq) {
+		/* This will most likely be followed by missing frames
+		 * or worse--a blank screen--leave a trail in the
+		 * logs, so this can be debugged easier.
+		 */
+		drm_err(job->sched, "%s: entity has no rq!\n", __func__);
 		return -ENOENT;
+	}
 
 	job->entity = entity;
 	job->s_fence = drm_sched_fence_alloc(entity, owner);
@@ -671,7 +677,7 @@ void drm_sched_job_arm(struct drm_sched_job *job)
 	sched = entity->rq->sched;
 
 	job->sched = sched;
-	job->s_priority = entity->rq - sched->sched_rq;
+	job->s_priority = entity->priority;
 	job->id = atomic64_inc_return(&sched->job_id_count);
 
 	drm_sched_fence_init(job->s_fence, job->entity);
@@ -888,10 +894,10 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
 		return NULL;
 
 	/* Kernel run queue has higher priority than normal run queue*/
-	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
+	for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
 		entity = drm_sched_policy == DRM_SCHED_POLICY_FIFO ?
-			drm_sched_rq_select_entity_fifo(&sched->sched_rq[i]) :
-			drm_sched_rq_select_entity_rr(&sched->sched_rq[i]);
+			drm_sched_rq_select_entity_fifo(sched->sched_rq[i]) :
+			drm_sched_rq_select_entity_rr(sched->sched_rq[i]);
 		if (entity)
 			break;
 	}
@@ -1071,6 +1077,7 @@ static int drm_sched_main(void *param)
  *
  * @sched: scheduler instance
  * @ops: backend operations for this scheduler
+ * @num_rqs: number of runqueues, one for each priority, up to DRM_SCHED_PRIORITY_COUNT
  * @hw_submission: number of hw submissions that can be in flight
  * @hang_limit: number of times to allow a job to hang before dropping it
  * @timeout: timeout value in jiffies for the scheduler
@@ -1084,11 +1091,12 @@ static int drm_sched_main(void *param)
  */
 int drm_sched_init(struct drm_gpu_scheduler *sched,
 		   const struct drm_sched_backend_ops *ops,
-		   unsigned hw_submission, unsigned hang_limit,
+		   u32 num_rqs, uint32_t hw_submission, unsigned int hang_limit,
 		   long timeout, struct workqueue_struct *timeout_wq,
 		   atomic_t *score, const char *name, struct device *dev)
 {
 	int i, ret;
+
 	sched->ops = ops;
 	sched->hw_submission_limit = hw_submission;
 	sched->name = name;
@@ -1097,8 +1105,36 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 	sched->hang_limit = hang_limit;
 	sched->score = score ? score : &sched->_score;
 	sched->dev = dev;
-	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; i++)
-		drm_sched_rq_init(sched, &sched->sched_rq[i]);
+
+	if (num_rqs > DRM_SCHED_PRIORITY_COUNT) {
+		/* This is a gross violation--tell drivers what the  problem is.
+		 */
+		drm_err(sched, "%s: num_rqs cannot be greater than DRM_SCHED_PRIORITY_COUNT\n",
+			__func__);
+		return -EINVAL;
+	} else if (sched->sched_rq) {
+		/* Not an error, but warn anyway so drivers can
+		 * fine-tune their DRM calling order, and return all
+		 * is good.
+		 */
+		drm_warn(sched, "%s: scheduler already initialized!\n", __func__);
+		return 0;
+	}
+
+	sched->sched_rq = kmalloc_array(num_rqs, sizeof(*sched->sched_rq),
+					GFP_KERNEL | __GFP_ZERO);
+	if (!sched->sched_rq) {
+		drm_err(sched, "%s: out of memory for sched_rq\n", __func__);
+		return -ENOMEM;
+	}
+	sched->num_rqs = num_rqs;
+	ret = -ENOMEM;
+	for (i = DRM_SCHED_PRIORITY_MIN; i < sched->num_rqs; i++) {
+		sched->sched_rq[i] = kzalloc(sizeof(*sched->sched_rq[i]), GFP_KERNEL);
+		if (!sched->sched_rq[i])
+			goto Out_unroll;
+		drm_sched_rq_init(sched, sched->sched_rq[i]);
+	}
 
 	init_waitqueue_head(&sched->wake_up_worker);
 	init_waitqueue_head(&sched->job_scheduled);
@@ -1115,11 +1151,18 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 		ret = PTR_ERR(sched->thread);
 		sched->thread = NULL;
 		DRM_DEV_ERROR(sched->dev, "Failed to create scheduler for %s.\n", name);
-		return ret;
+		goto Out_unroll;
 	}
 
 	sched->ready = true;
 	return 0;
+Out_unroll:
+	for (--i ; i >= DRM_SCHED_PRIORITY_MIN; i--)
+		kfree(sched->sched_rq[i]);
+	kfree(sched->sched_rq);
+	sched->sched_rq = NULL;
+	drm_err(sched, "%s: Failed to setup GPU scheduler--out of memory\n", __func__);
+	return ret;
 }
 EXPORT_SYMBOL(drm_sched_init);
 
@@ -1138,8 +1181,8 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 	if (sched->thread)
 		kthread_stop(sched->thread);
 
-	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
-		struct drm_sched_rq *rq = &sched->sched_rq[i];
+	for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
+		struct drm_sched_rq *rq = sched->sched_rq[i];
 
 		spin_lock(&rq->lock);
 		list_for_each_entry(s_entity, &rq->entities, list)
@@ -1150,7 +1193,7 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 			 */
 			s_entity->stopped = true;
 		spin_unlock(&rq->lock);
-
+		kfree(sched->sched_rq[i]);
 	}
 
 	/* Wakeup everyone stuck in drm_sched_entity_flush for this scheduler */
@@ -1160,6 +1203,8 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 	cancel_delayed_work_sync(&sched->work_tdr);
 
 	sched->ready = false;
+	kfree(sched->sched_rq);
+	sched->sched_rq = NULL;
 }
 EXPORT_SYMBOL(drm_sched_fini);
 
@@ -1186,9 +1231,10 @@ void drm_sched_increase_karma(struct drm_sched_job *bad)
 	if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
 		atomic_inc(&bad->karma);
 
-		for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL;
+		for (i = DRM_SCHED_PRIORITY_MIN;
+		     i < min_t(typeof(sched->num_rqs), sched->num_rqs, DRM_SCHED_PRIORITY_KERNEL);
 		     i++) {
-			struct drm_sched_rq *rq = &sched->sched_rq[i];
+			struct drm_sched_rq *rq = sched->sched_rq[i];
 
 			spin_lock(&rq->lock);
 			list_for_each_entry_safe(entity, tmp, &rq->entities, list) {