Merge tag 'drm-next-2025-03-28' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "Outside of drm there are some rust patches from Danilo who maintains
  that area in here, and some pieces for drm header check tests.

  The major things in here are a new driver supporting the touchbar
  displays on M1/M2, the nova-core stub driver which is just the vehicle
  for adding rust abstractions and start developing a real driver inside
  of.

  xe adds support for SVM with a non-driver specific SVM core
  abstraction that will hopefully be useful for other drivers, along
  with support for shrinking for TTM devices. I'm sure xe and AMD
  support new devices, but the pipeline depth on these things is hard to
  know what they end up being in the marketplace!

  uapi:
   - add mediatek tiled fourcc
   - add support for notifying userspace on device wedged

  new driver:
   - appletbdrm: support for Apple Touchbar displays on m1/m2
   - nova-core: skeleton rust driver to develop nova inside off

  firmware:
   - add some rust firmware pieces

  rust:
   - add 'LocalModule' type alias

  component:
   - add helper to query bound status

  fbdev:
   - fbtft: remove access to page->index

  media:
   - cec: tda998x: import driver from drm

  dma-buf:
   - add fast path for single fence merging

  tests:
   - fix lockdep warnings

  atomic:
   - allow full modeset on connector changes
   - clarify semantics of allow_modeset and drm_atomic_helper_check
   - async-flip: support on arbitary planes
   - writeback: fix UAF
   - Document atomic-state history

  format-helper:
   - support ARGB8888 to ARGB4444 conversions

  buddy:
   - fix multi-root cleanup

  ci:
   - update IGT

  dp:
   - support extended wake timeout
   - mst: fix RAD to string conversion
   - increase DPCD eDP control CAP size to 5 bytes
   - add DPCD eDP v1.5 definition
   - add helpers for LTTPR transparent mode

  panic:
   - encode QR code according to Fido 2.2

  scheduler:
   - add parameter struct for init
   - improve job peek/pop operations
   - optimise drm_sched_job struct layout

  ttm:
   - refactor pool allocation
   - add helpers for TTM shrinker

  panel-orientation:
   - add a bunch of new quirks

  panel:
   - convert panels to multi-style functions
   - edp: Add support for B140UAN04.4, BOE NV140FHM-NZ, CSW MNB601LS1-3,
     LG LP079QX1-SP0V, MNE007QS3-7, STA 116QHD024002, Starry
     116KHD024006, Lenovo T14s Gen6 Snapdragon
   - himax-hx83102: Add support for CSOT PNA957QT1-1, Kingdisplay
     kd110n11-51ie, Starry 2082109qfh040022-50e
   - visionox-r66451: use multi-style MIPI-DSI functions
   - raydium-rm67200: Add driver for Raydium RM67200
   - simple: Add support for BOE AV123Z7M-N17, BOE AV123Z7M-N17
   - sony-td4353-jdi: Use MIPI-DSI multi-func interface
   - summit: Add driver for Apple Summit display panel
   - visionox-rm692e5: Add driver for Visionox RM692E5

  bridge:
   - pass full atomic state to various callbacks
   - adv7511: Report correct capabilities
   - it6505: Fix HDCP V compare
   - snd65dsi86: fix device IDs
   - nwl-dsi: set bridge type
   - ti-sn65si83: add error recovery and set bridge type
   - synopsys: add HDMI audio support

  xe:
   - support device-wedged event
   - add mmap support for PCI memory barrier
   - perf pmu integration and expose per-engien activity
   - add EU stall sampling support
   - GPU SVM and Xe SVM implementation
   - use TTM shrinker
   - add survivability mode to allow the driver to do firmware updates
     in critical failure states
   - PXP HWDRM support for MTL and LNL
   - expose package/vram temps over hwmon
   - enable DP tunneling
   - drop mmio_ext abstraction
   - Reject BO evcition if BO is bound to current VM
   - Xe suballocator improvements
   - re-use display vmas when possible
   - add GuC Buffer Cache abstraction
   - PCI ID update for Panther Lake and Battlemage
   - Enable SRIOV for Panther Lake
   - Refactor VRAM manager location

  i915:
   - enable extends wake timeout
   - support device-wedged event
   - Enable DP 128b/132b SST DSC
   - FBC dirty rectangle support for display version 30+
   - convert i915/xe to drm client setup
   - Compute HDMI PLLS for rates not in fixed tables
   - Allow DSB usage when PSR is enabled on LNL+
   - Enable panel replay without full modeset
   - Enable async flips with compressed buffers on ICL+
   - support luminance based brightness via DPCD for eDP
   - enable VRR enable/disable without full modeset
   - allow GuC SLPC default strategies on MTL+ for performance
   - lots of display refactoring in move to struct intel_display

  amdgpu:
   - add device wedged event
   - support async page flips on overlay planes
   - enable broadcast RGB drm property
   - add info ioctl for virt mode
   - OEM i2c support for RGB lights
   - GC 11.5.2 + 11.5.3 support
   - SDMA 6.1.3 support
   - NBIO 7.9.1 + 7.11.2 support
   - MMHUB 1.8.1 + 3.3.2 support
   - DCN 3.6.0 support
   - Add dynamic workload profile switching for GC 10-12
   - support larger VBIOS sizes
   - Mark gttsize parameters as deprecated
   - Initial JPEG queue resset support

  amdkfd:
   - add KFD per process flags for setting precision
   - sync pasid values between KGD and KFD
   - improve GTT/VRAM handling for APUs
   - fix user queue validation on GC7/8
   - SDMA queue reset support

  raedeon:
   - rs400 hyperz fix

  i2c:
   - td998x: drop platform_data, split driver into media and bridge

  ast:
   - transmitter chip detection refactoring
   - vbios display mode refactoring
   - astdp: fix connection status and filter unsupported modes
   - cursor handling refactoring

  imagination:
   - check job dependencies with sched helper

  ivpu:
   - improve command queue handling
   - use workqueue for IRQ handling
   - add support HW fault injection
   - locking fixes

  mgag200:
   - add support for G200eH5

  msm:
   - dpu: add concurrent writeback support for DPU 10.x+
   - use LTTPR helpers
   - GPU:
     - Fix obscure GMU suspend failure
     - Expose syncobj timeline support
     - Extend GPU devcoredump with pagetable info
     - a623 support
     - Fix a6xx gen1/gen2 indexed-register blocks in gpu snapshot /
       devcoredump
   - Display:
     - Add cpu-cfg interconnect paths on SM8560 and SM8650
     - Introduce KMS OMMU fault handler, causing devcoredump snapshot
     - Fixed error pointer dereference in msm_kms_init_aspace()
   - DPU:
     - Fix mode_changing handling
     - Add writeback support on SM6150 (QCS615)
     - Fix DSC programming in 1:1:1 topology
     - Reworked hardware resource allocation, moving it to the CRTC code
     - Enabled support for Concurrent WriteBack (CWB) on SM8650
     - Enabled CDM blocks on all relevant platforms
     - Reworked debugfs interface for BW/clocks debugging
     - Clear perf params before calculating bw
     - Support YUV formats on writeback
     - Fixed double inclusion
     - Fixed writeback in YUV formats when using cloned output, Dropped
       wb2_formats_rgb
     - Corrected dpu_crtc_check_mode_changed and struct dpu_encoder_virt
       kerneldocs
     - Fixed uninitialized variable in dpu_crtc_kickoff_clone_mode()
   - DSI:
     - DSC-related fixes
     - Rework clock programming
   - DSI PHY:
     - Fix 7nm (and lower) PHY programming
     - Add proper DT schema definitions for DSI PHY clocks
   - HDMI:
     - Rework the driver, enabling the use of the HDMI Connector
       framework
   - Bindings:
     - Added eDP PHY on SA8775P

  nouveau:
   - move drm_slave_encoder interface into driver
   - nvkm: refactor GSP RPC
   - use LTTPR helpers

  mediatek:
   - HDMI fixup and refinement
   - add MT8188 dsc compatible
   - MT8365 SoC support

  panthor:
   - Expose sizes of intenral BOs via fdinfo
   - Fix race between reset and suspend
   - Improve locking

  qaic:
   - Add support for AIC200

  renesas:
   - Fix limits in DT bindings

  rockchip:
   - support rk3562-mali
   - rk3576: Add HDMI support
   - vop2: Add new display modes on RK3588 HDMI0 up to 4K
   - Don't change HDMI reference clock rate
   - Fix DT bindings
   - analogix_dp: add eDP support
   - fix shutodnw

  solomon:
   - Set SPI device table to silence warnings
   - Fix pixel and scanline encoding

  v3d:
   - handle clock

  vc4:
   - Use drm_exec
   - Use dma-resv for wait-BO ioctl
   - Remove seqno infrastructure

  virtgpu:
   - Support partial mappings of GEM objects
   - Reserve VGA resources during initialization
   - Fix UAF in virtgpu_dma_buf_free_obj()
   - Add panic support

  vkms:
   - Switch to a managed modesetting pipeline
   - Add support for ARGB8888
   - fix UAf

  xlnx:
   - Set correct DMA segment size
   - use mutex guards
   - Fix error handling
   - Fix docs"

* tag 'drm-next-2025-03-28' of https://gitlab.freedesktop.org/drm/kernel: (1762 commits)
  drm/amd/pm: Update feature list for smu_v13_0_6
  drm/amdgpu: Add parameter documentation for amdgpu_sync_fence
  drm/amdgpu/discovery: optionally use fw based ip discovery
  drm/amdgpu/discovery: use specific ip_discovery.bin for legacy asics
  drm/amdgpu/discovery: check ip_discovery fw file available
  drm/amd/pm: Remove unnecessay UQ10 to UINT conversion
  drm/amd/pm: Remove unnecessay UQ10 to UINT conversion
  drm/amdgpu/sdma_v4_4_2: update VM flush implementation for SDMA
  drm/amdgpu: Optimize VM invalidation engine allocation and synchronize GPU TLB flush
  drm/amd/amdgpu: Increase max rings to enable SDMA page ring
  drm/amdgpu: Decode deferred error type in gfx aca bank parser
  drm/amdgpu/gfx11: Add Cleaner Shader Support for GFX11.5 GPUs
  drm/amdgpu/mes: clean up SDMA HQD loop
  drm/amdgpu/mes: enable compute pipes across all MEC
  drm/amdgpu/mes: drop MES 10.x leftovers
  drm/amdgpu/mes: optimize compute loop handling
  drm/amdgpu/sdma: guilty tracking is per instance
  drm/amdgpu/sdma: fix engine reset handling
  drm/amdgpu: remove invalid usage of sched.ready
  drm/amdgpu: add cleaner shader trace point
  ...

1 files changed, 61 insertions, 70 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 57da84908752..bfea608a7106 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -64,12 +64,6 @@
  * credit limit, the job won't be executed. Instead, the scheduler will wait
  * until the credit count has decreased enough to not overflow its credit limit.
  * This implies waiting for previously executed jobs.
- *
- * Optionally, drivers may register a callback (update_job_credits) provided by
- * struct drm_sched_backend_ops to update the job's credits dynamically. The
- * scheduler executes this callback every time the scheduler considers a job for
- * execution and subsequently checks whether the job fits the scheduler's credit
- * limit.
  */
 
 #include <linux/wait.h>
@@ -84,6 +78,8 @@
 #include <drm/gpu_scheduler.h>
 #include <drm/spsc_queue.h>
 
+#include "sched_internal.h"
+
 #define CREATE_TRACE_POINTS
 #include "gpu_scheduler_trace.h"
 
@@ -93,9 +89,6 @@ static struct lockdep_map drm_sched_lockdep_map = {
 };
 #endif
 
-#define to_drm_sched_job(sched_job)		\
-		container_of((sched_job), struct drm_sched_job, queue_node)
-
 int drm_sched_policy = DRM_SCHED_POLICY_FIFO;
 
 /**
@@ -109,9 +102,9 @@ static u32 drm_sched_available_credits(struct drm_gpu_scheduler *sched)
 {
 	u32 credits;
 
-	drm_WARN_ON(sched, check_sub_overflow(sched->credit_limit,
-					      atomic_read(&sched->credit_count),
-					      &credits));
+	WARN_ON(check_sub_overflow(sched->credit_limit,
+				   atomic_read(&sched->credit_count),
+				   &credits));
 
 	return credits;
 }
@@ -129,23 +122,18 @@ static bool drm_sched_can_queue(struct drm_gpu_scheduler *sched,
 {
 	struct drm_sched_job *s_job;
 
-	s_job = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
+	s_job = drm_sched_entity_queue_peek(entity);
 	if (!s_job)
 		return false;
 
-	if (sched->ops->update_job_credits) {
-		s_job->credits = sched->ops->update_job_credits(s_job);
-
-		drm_WARN(sched, !s_job->credits,
-			 "Jobs with zero credits bypass job-flow control.\n");
-	}
-
 	/* If a job exceeds the credit limit, truncate it to the credit limit
 	 * itself to guarantee forward progress.
 	 */
-	if (drm_WARN(sched, s_job->credits > sched->credit_limit,
-		     "Jobs may not exceed the credit limit, truncate.\n"))
+	if (s_job->credits > sched->credit_limit) {
+		dev_WARN(sched->dev,
+			 "Jobs may not exceed the credit limit, truncate.\n");
 		s_job->credits = sched->credit_limit;
+	}
 
 	return drm_sched_available_credits(sched) >= s_job->credits;
 }
@@ -803,7 +791,7 @@ int drm_sched_job_init(struct drm_sched_job *job,
 		 * 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__);
+		dev_err(job->sched->dev, "%s: entity has no rq!\n", __func__);
 		return -ENOENT;
 	}
 
@@ -998,17 +986,42 @@ int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job,
 EXPORT_SYMBOL(drm_sched_job_add_implicit_dependencies);
 
 /**
+ * drm_sched_job_has_dependency - check whether fence is the job's dependency
+ * @job: scheduler job to check
+ * @fence: fence to look for
+ *
+ * Returns:
+ * True if @fence is found within the job's dependencies, or otherwise false.
+ */
+bool drm_sched_job_has_dependency(struct drm_sched_job *job,
+				  struct dma_fence *fence)
+{
+	struct dma_fence *f;
+	unsigned long index;
+
+	xa_for_each(&job->dependencies, index, f) {
+		if (f == fence)
+			return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL(drm_sched_job_has_dependency);
+
+/**
  * drm_sched_job_cleanup - clean up scheduler job resources
  * @job: scheduler job to clean up
  *
  * Cleans up the resources allocated with drm_sched_job_init().
  *
  * Drivers should call this from their error unwind code if @job is aborted
- * before drm_sched_job_arm() is called.
+ * before it was submitted to an entity with drm_sched_entity_push_job().
  *
- * After that point of no return @job is committed to be executed by the
- * scheduler, and this function should be called from the
- * &drm_sched_backend_ops.free_job callback.
+ * Since calling drm_sched_job_arm() causes the job's fences to be initialized,
+ * it is up to the driver to ensure that fences that were exposed to external
+ * parties get signaled. drm_sched_job_cleanup() does not ensure this.
+ *
+ * This function must also be called in &struct drm_sched_backend_ops.free_job
  */
 void drm_sched_job_cleanup(struct drm_sched_job *job)
 {
@@ -1019,7 +1032,7 @@ void drm_sched_job_cleanup(struct drm_sched_job *job)
 		/* drm_sched_job_arm() has been called */
 		dma_fence_put(&job->s_fence->finished);
 	} else {
-		/* aborted job before committing to run it */
+		/* aborted job before arming */
 		drm_sched_fence_free(job->s_fence);
 	}
 
@@ -1166,9 +1179,6 @@ static void drm_sched_free_job_work(struct work_struct *w)
 		container_of(w, struct drm_gpu_scheduler, work_free_job);
 	struct drm_sched_job *job;
 
-	if (READ_ONCE(sched->pause_submit))
-		return;
-
 	job = drm_sched_get_finished_job(sched);
 	if (job)
 		sched->ops->free_job(job);
@@ -1192,9 +1202,6 @@ static void drm_sched_run_job_work(struct work_struct *w)
 	struct drm_sched_job *sched_job;
 	int r;
 
-	if (READ_ONCE(sched->pause_submit))
-		return;
-
 	/* Find entity with a ready job */
 	entity = drm_sched_select_entity(sched);
 	if (!entity)
@@ -1240,43 +1247,27 @@ static void drm_sched_run_job_work(struct work_struct *w)
  * drm_sched_init - Init a gpu scheduler instance
  *
  * @sched: scheduler instance
- * @ops: backend operations for this scheduler
- * @submit_wq: workqueue to use for submission. If NULL, an ordered wq is
- *	       allocated and used
- * @num_rqs: number of runqueues, one for each priority, up to DRM_SCHED_PRIORITY_COUNT
- * @credit_limit: the number of credits this scheduler can hold from all jobs
- * @hang_limit: number of times to allow a job to hang before dropping it
- * @timeout: timeout value in jiffies for the scheduler
- * @timeout_wq: workqueue to use for timeout work. If NULL, the system_wq is
- *		used
- * @score: optional score atomic shared with other schedulers
- * @name: name used for debugging
- * @dev: target &struct device
+ * @args: scheduler initialization arguments
  *
  * Return 0 on success, otherwise error code.
  */
-int drm_sched_init(struct drm_gpu_scheduler *sched,
-		   const struct drm_sched_backend_ops *ops,
-		   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)
+int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_init_args *args)
 {
 	int i;
 
-	sched->ops = ops;
-	sched->credit_limit = credit_limit;
-	sched->name = name;
-	sched->timeout = timeout;
-	sched->timeout_wq = timeout_wq ? : system_wq;
-	sched->hang_limit = hang_limit;
-	sched->score = score ? score : &sched->_score;
-	sched->dev = dev;
+	sched->ops = args->ops;
+	sched->credit_limit = args->credit_limit;
+	sched->name = args->name;
+	sched->timeout = args->timeout;
+	sched->hang_limit = args->hang_limit;
+	sched->timeout_wq = args->timeout_wq ? args->timeout_wq : system_wq;
+	sched->score = args->score ? args->score : &sched->_score;
+	sched->dev = args->dev;
 
-	if (num_rqs > DRM_SCHED_PRIORITY_COUNT) {
+	if (args->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",
+		dev_err(sched->dev, "%s: num_rqs cannot be greater than DRM_SCHED_PRIORITY_COUNT\n",
 			__func__);
 		return -EINVAL;
 	} else if (sched->sched_rq) {
@@ -1284,20 +1275,20 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 		 * fine-tune their DRM calling order, and return all
 		 * is good.
 		 */
-		drm_warn(sched, "%s: scheduler already initialized!\n", __func__);
+		dev_warn(sched->dev, "%s: scheduler already initialized!\n", __func__);
 		return 0;
 	}
 
-	if (submit_wq) {
-		sched->submit_wq = submit_wq;
+	if (args->submit_wq) {
+		sched->submit_wq = args->submit_wq;
 		sched->own_submit_wq = false;
 	} else {
 #ifdef CONFIG_LOCKDEP
-		sched->submit_wq = alloc_ordered_workqueue_lockdep_map(name,
+		sched->submit_wq = alloc_ordered_workqueue_lockdep_map(args->name,
 								       WQ_MEM_RECLAIM,
 								       &drm_sched_lockdep_map);
 #else
-		sched->submit_wq = alloc_ordered_workqueue(name, WQ_MEM_RECLAIM);
+		sched->submit_wq = alloc_ordered_workqueue(args->name, WQ_MEM_RECLAIM);
 #endif
 		if (!sched->submit_wq)
 			return -ENOMEM;
@@ -1305,11 +1296,11 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 		sched->own_submit_wq = true;
 	}
 
-	sched->sched_rq = kmalloc_array(num_rqs, sizeof(*sched->sched_rq),
+	sched->sched_rq = kmalloc_array(args->num_rqs, sizeof(*sched->sched_rq),
 					GFP_KERNEL | __GFP_ZERO);
 	if (!sched->sched_rq)
 		goto Out_check_own;
-	sched->num_rqs = num_rqs;
+	sched->num_rqs = args->num_rqs;
 	for (i = DRM_SCHED_PRIORITY_KERNEL; i < sched->num_rqs; i++) {
 		sched->sched_rq[i] = kzalloc(sizeof(*sched->sched_rq[i]), GFP_KERNEL);
 		if (!sched->sched_rq[i])
@@ -1339,7 +1330,7 @@ Out_unroll:
 Out_check_own:
 	if (sched->own_submit_wq)
 		destroy_workqueue(sched->submit_wq);
-	drm_err(sched, "%s: Failed to setup GPU scheduler--out of memory\n", __func__);
+	dev_err(sched->dev, "%s: Failed to setup GPU scheduler--out of memory\n", __func__);
 	return -ENOMEM;
 }
 EXPORT_SYMBOL(drm_sched_init);