Merge tag 'drm-next-2025-12-03' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "There was a rather late merge of a new color pipeline feature, that
  some userspace projects are blocked on, and has seen a lot of work in
  amdgpu. This should have seen some time in -next. There is additional
  support for this for Intel, that if it arrives in the next day or two
  I'll pass it on in another pull request and you can decide if you want
  to take it.

  Highlights:
   - Arm Ethos NPU accelerator driver
   - new DRM color pipeline support
   - amdgpu will now run discrete SI/CIK cards instead of radeon, which
     enables vulkan support in userspace
   - msm gets gen8 gpu support
   - initial Xe3P support in xe

  Full detail summary:

  New driver:
   - Arm Ethos-U65/U85 accel driver

  Core:
   - support the drm color pipeline in vkms/amdgfx
   - add support for drm colorop pipeline
   - add COLOR PIPELINE plane property
   - add DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE
   - throttle dirty worker with vblank
   - use drm_for_each_bridge_in_chain_scoped in drm's bridge code
   - Ensure drm_client_modeset tests are enabled in UML
   - add simulated vblank interrupt - use in drivers
   - dumb buffer sizing helper
   - move freeing of drm client memory to driver
   - crtc sharpness strength property
   - stop using system_wq in scheduler/drivers
   - support emergency restore in drm-client

  Rust:
   - make slice::as_flattened usable on all supported rustc
   - add FromBytes::from_bytes_prefix() method
   - remove redundant device ptr from Rust GEM object
   - Change how AlwaysRefCounted is implemented for GEM objects

  gpuvm:
   - Add deferred vm_bo cleanup to GPUVM (for rust)

  atomic:
   - cleanup and improve state handling interfaces

  buddy:
   - optimize block management

  dma-buf:
   - heaps: Create heap per CMA reserved location
   - improve userspace documentation

  dp:
   - add POST_LT_ADJ_REQ training sequence
   - DPCD dSC quirk for synaptics panamera devices
   - helpers to query branch DSC max throughput

  ttm:
   - Rename ttm_bo_put to ttm_bo_fini
   - allow page protection flags on risc-v
   - rework pipelined eviction fence handling

  amdgpu:
   - enable amdgpu by default for SI/CI dGPUs
   - enable DC by default on SI
   - refactor CIK/SI enablement
   - add ABM KMS property
   - Re-enable DM idle optimizations
   - DC Analog encoders support
   - Powerplay fixes for fiji/iceland
   - Enable DC on bonaire by default
   - HMM cleanup
   - Add new RAS framework
   - DML2.1 updates
   - YCbCr420 fixes
   - DC FP fixes
   - DMUB fixes
   - LTTPR fixes
   - DTBCLK fixes
   - DMU cursor offload handling
   - Userq validation improvements
   - Unify shutdown callback handling
   - Suspend improvements
   - Power limit code cleanup
   - SR-IOV fixes
   - AUX backlight fixes
   - DCN 3.5 fixes
   - HDMI compliance fixes
   - DCN 4.0.1 cursor updates
   - DCN interrupt fix
   - DC KMS full update improvements
   - Add additional HDCP traces
   - DCN 3.2 fixes
   - DP MST fixes
   - Add support for new SR-IOV mailbox interface
   - UQ reset support
   - HDP flush rework
   - VCE1 support

  amdkfd:
   - HMM cleanups
   - Relax checks on save area overallocations
   - Fix GPU mappings after prefetch

  radeon:
   - refactor CIK/SI enablement

  xe:
   - Initial Xe3P support
   - panic support on VRAM for display
   - fix stolen size check
   - Loosen used tracking restriction
   - New SR-IOV debugfs structure and debugfs updates
   - Hide the GPU madvise flag behind a VM_BIND flag
   - Always expose VRAM provisioning data on discrete GPUs
   - Allow VRAM mappings for userptr when used with SVM
   - Allow pinning of p2p dma-buf
   - Use per-tile debugfs where appropriate
   - Add documentation for Execution Queues
   - PF improvements
   - VF migration recovery redesign work
   - User / Kernel VRAM partitioning
   - Update Tile-based messages
   - Allow configfs to disable specific GT types
   - VF provisioning and migration improvements
   - use SVM range helpers in PT layer
   - Initial CRI support
   - access VF registers using dedicated MMIO view
   - limit number of jobs per exec queue
   - add sriov_admin sysfs tree
   - more crescent island specific support
   - debugfs residency counter
   - SRIOV migration work
   - runtime registers for GFX 35

  i915:
   - add initial Xe3p_LPD display version 35 support
   - Enable LNL+ content adaptive sharpness filter
   - Use optimized VRR guardband
   - Enable Xe3p LT PHY
   - enable FBC support for Xe3p_LPD display
   - add display 30.02 firmware support
   - refactor SKL+ watermark latency setup
   - refactor fbdev handling
   - call i915/xe runtime PM via function pointers
   - refactor i915/xe stolen memory/display interfaces
   - use display version instead of gfx version in display code
   - extend i915_display_info with Type-C port details
   - lots of display cleanups/refactorings
   - set O_LARGEFILE in __create_shmem
   - skuip guc communication warning on reset
   - fix time conversions
   - defeature DRRS on LNL+
   - refactor intel_frontbuffer split between i915/xe/display
   - convert inteL_rom interfaces to struct drm_device
   - unify display register polling interfaces
   - aovid lock inversion when pinning to GGTT on CHV/BXT+VTD

  panel:
   - Add KD116N3730A08/A12, chromebook mt8189
   - JT101TM023, LQ079L1SX01,
   - GLD070WX3-SL01 MIPI DSI
   - Samsung LTL106AL0, Samsung LTL106AL01
   - Raystar RFF500F-AWH-DNN
   - Winstar WF70A8SYJHLNGA
   - Wanchanglong w552946aaa
   - Samsung SOFEF00
   - Lenovo X13s panel
   - ilitek-ili9881c - add rpi 5" support
   - visionx-rm69299 - add backlight support
   - edp - support AUI B116XAN02.0

  bridge:
   - improve ref counting
   - ti-sn65dsi86 - add support for DP mode with HPD
   - synopsis: support CEC, init timer with correct freq
   - ASL CS5263 DP-to-HDMI bridge support

  nova-core:
   - introduce bitfield! macro
   - introduce safe integer converters
   - GSP inits to fully booted state on Ampere
   - Use more future-proof register for GPU identification

  nova-drm:
   - select NOVA_CORE
   - 64-bit only

  nouveau:
   - improve reclocking on tegra 186+
   - add large page and compression support

  msm:
   - GPU:
      - Gen8 support: A840 (Kaanapali) and X2-85 (Glymur)
      - A612 support
   - MDSS:
      - Added support for Glymur and QCS8300 platforms
   - DPU:
      - Enabled Quad-Pipe support, unlocking higher resolutions support
      - Added support for Glymur platform
      - Documented DPU on QCS8300 platform as supported
   - DisplayPort:
      - Added support for Glymur platform
      - Added support lame remapping inside DP block
      - Documented DisplayPort controller on QCS8300 and SM6150/QCS615
        as supported

  tegra:
   - NVJPG driver

  panfrost:
   - display JM contexts over debugfs
   - export JM contexts to userspace
   - improve error and job handling

  panthor:
   - support custom ASN_HASH for mt8196
   - support mali-G1 GPU
   - flush shmem write before mapping buffers uncached
   - make timeout per-queue instead of per-job

  mediatek:
   - MT8195/88 HDMIv2/DDCv2 support

  rockchip:
   - dsi: add support for RK3368

  amdxdna:
   - enhance runtime PM
   - last hardware error reading uapi
   - support firmware debug output
   - add resource and telemetry data uapi
   - preemption support

  imx:
   - add driver for HDMI TX Parallel audio interface

  ivpu:
   - add support for user-managed preemption buffer
   - add userptr support
   - update JSM firware API to 3.33.0
   - add better alloc/free warnings
   - fix page fault in unbind all bos
   - rework bind/unbind of imported buffers
   - enable MCA ECC signalling
   - split fw runtime and global memory buffers
   - add fdinfo memory statistics

  tidss:
   - convert to drm logging
   - logging cleanup

  ast:
   - refactor generation init paths
   - add per chip generation detect_tx_chip
   - set quirks for each chip model

  atmel-hlcdc:
   - set LCDC_ATTRE register in plane disable
   - set correct values for plane scaler

  solomon:
   - use drm helper for get_modes and move_valid

  sitronix:
   - fix output position when clearing screens

  qaic:
   - support dma-buf exports
   - support new firmware's READ_DATA implementation
   - sahara AIC200 image table update
   - add sysfs support
   - add coredump support
   - add uevents support
   - PM support

  sun4i:
   - layer refactors to decouple plane from output
   - improve DE33 support

  vc4:
   - switch to generic CEC helpers

  komeda:
   - use drm_ logging functions

  vkms:
   - configfs support for display configuration

  vgem:
   - fix fence timer deadlock

  etnaviv:
   - add HWDB entry for GC8000 Nano Ultra VIP r6205"

* tag 'drm-next-2025-12-03' of https://gitlab.freedesktop.org/drm/kernel: (1869 commits)
  Revert "drm/amd: Skip power ungate during suspend for VPE"
  drm/amdgpu: use common defines for HUB faults
  drm/amdgpu/gmc12: add amdgpu_vm_handle_fault() handling
  drm/amdgpu/gmc11: add amdgpu_vm_handle_fault() handling
  drm/amdgpu: use static ids for ACP platform devs
  drm/amdgpu/sdma6: Update SDMA 6.0.3 FW version to include UMQ protected-fence fix
  drm/amdgpu: Forward VMID reservation errors
  drm/amdgpu/gmc8: Delegate VM faults to soft IRQ handler ring
  drm/amdgpu/gmc7: Delegate VM faults to soft IRQ handler ring
  drm/amdgpu/gmc6: Delegate VM faults to soft IRQ handler ring
  drm/amdgpu/gmc6: Cache VM fault info
  drm/amdgpu/gmc6: Don't print MC client as it's unknown
  drm/amdgpu/cz_ih: Enable soft IRQ handler ring
  drm/amdgpu/tonga_ih: Enable soft IRQ handler ring
  drm/amdgpu/iceland_ih: Enable soft IRQ handler ring
  drm/amdgpu/cik_ih: Enable soft IRQ handler ring
  drm/amdgpu/si_ih: Enable soft IRQ handler ring
  drm/amd/display: fix typo in display_mode_core_structs.h
  drm/amd/display: fix Smart Power OLED not working after S4
  drm/amd/display: Move RGB-type check for audio sync to DCE HW sequence
  ...

1 files changed, 191 insertions, 0 deletions

diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c
index af63f4d00315..8a06d296561d 100644
--- a/drivers/gpu/drm/drm_gpuvm.c
+++ b/drivers/gpu/drm/drm_gpuvm.c
@@ -26,6 +26,7 @@
  */
 
 #include <drm/drm_gpuvm.h>
+#include <drm/drm_print.h>
 
 #include <linux/export.h>
 #include <linux/interval_tree_generic.h>
@@ -877,6 +878,31 @@ __drm_gpuvm_bo_list_add(struct drm_gpuvm *gpuvm, spinlock_t *lock,
 }
 
 /**
+ * drm_gpuvm_bo_is_zombie() - check whether this vm_bo is scheduled for cleanup
+ * @vm_bo: the &drm_gpuvm_bo
+ *
+ * When a vm_bo is scheduled for cleanup using the bo_defer list, it is not
+ * immediately removed from the evict and extobj lists. Therefore, anyone
+ * iterating these lists should skip entries that are being destroyed.
+ *
+ * Checking the refcount without incrementing it is okay as long as the lock
+ * protecting the evict/extobj list is held for as long as you are using the
+ * vm_bo, because even if the refcount hits zero while you are using it, freeing
+ * the vm_bo requires taking the list's lock.
+ *
+ * Zombie entries can be observed on the evict and extobj lists regardless of
+ * whether DRM_GPUVM_RESV_PROTECTED is used, but they remain on the lists for a
+ * longer time when the resv lock is used because we can't take the resv lock
+ * during run_job() in immediate mode, meaning that they need to remain on the
+ * lists until drm_gpuvm_bo_deferred_cleanup() is called.
+ */
+static bool
+drm_gpuvm_bo_is_zombie(struct drm_gpuvm_bo *vm_bo)
+{
+	return !kref_read(&vm_bo->kref);
+}
+
+/**
  * drm_gpuvm_bo_list_add() - insert a vm_bo into the given list
  * @__vm_bo: the &drm_gpuvm_bo
  * @__list_name: the name of the list to insert into
@@ -1081,6 +1107,8 @@ drm_gpuvm_init(struct drm_gpuvm *gpuvm, const char *name,
 	INIT_LIST_HEAD(&gpuvm->evict.list);
 	spin_lock_init(&gpuvm->evict.lock);
 
+	init_llist_head(&gpuvm->bo_defer);
+
 	kref_init(&gpuvm->kref);
 
 	gpuvm->name = name ? name : "unknown";
@@ -1122,6 +1150,8 @@ drm_gpuvm_fini(struct drm_gpuvm *gpuvm)
 		 "Extobj list should be empty.\n");
 	drm_WARN(gpuvm->drm, !list_empty(&gpuvm->evict.list),
 		 "Evict list should be empty.\n");
+	drm_WARN(gpuvm->drm, !llist_empty(&gpuvm->bo_defer),
+		 "VM BO cleanup list should be empty.\n");
 
 	drm_gem_object_put(gpuvm->r_obj);
 }
@@ -1217,6 +1247,9 @@ drm_gpuvm_prepare_objects_locked(struct drm_gpuvm *gpuvm,
 
 	drm_gpuvm_resv_assert_held(gpuvm);
 	list_for_each_entry(vm_bo, &gpuvm->extobj.list, list.entry.extobj) {
+		if (drm_gpuvm_bo_is_zombie(vm_bo))
+			continue;
+
 		ret = exec_prepare_obj(exec, vm_bo->obj, num_fences);
 		if (ret)
 			break;
@@ -1460,6 +1493,9 @@ drm_gpuvm_validate_locked(struct drm_gpuvm *gpuvm, struct drm_exec *exec)
 
 	list_for_each_entry_safe(vm_bo, next, &gpuvm->evict.list,
 				 list.entry.evict) {
+		if (drm_gpuvm_bo_is_zombie(vm_bo))
+			continue;
+
 		ret = ops->vm_bo_validate(vm_bo, exec);
 		if (ret)
 			break;
@@ -1560,6 +1596,7 @@ drm_gpuvm_bo_create(struct drm_gpuvm *gpuvm,
 
 	INIT_LIST_HEAD(&vm_bo->list.entry.extobj);
 	INIT_LIST_HEAD(&vm_bo->list.entry.evict);
+	init_llist_node(&vm_bo->list.entry.bo_defer);
 
 	return vm_bo;
 }
@@ -1621,6 +1658,126 @@ drm_gpuvm_bo_put(struct drm_gpuvm_bo *vm_bo)
 }
 EXPORT_SYMBOL_GPL(drm_gpuvm_bo_put);
 
+/*
+ * drm_gpuvm_bo_into_zombie() - called when the vm_bo becomes a zombie due to
+ * deferred cleanup
+ *
+ * If deferred cleanup is used, then this must be called right after the vm_bo
+ * refcount drops to zero. Must be called with GEM mutex held. After releasing
+ * the GEM mutex, drm_gpuvm_bo_defer_zombie_cleanup() must be called.
+ */
+static void
+drm_gpuvm_bo_into_zombie(struct kref *kref)
+{
+	struct drm_gpuvm_bo *vm_bo = container_of(kref, struct drm_gpuvm_bo,
+						  kref);
+
+	if (!drm_gpuvm_resv_protected(vm_bo->vm)) {
+		drm_gpuvm_bo_list_del(vm_bo, extobj, true);
+		drm_gpuvm_bo_list_del(vm_bo, evict, true);
+	}
+
+	list_del(&vm_bo->list.entry.gem);
+}
+
+/*
+ * drm_gpuvm_bo_defer_zombie_cleanup() - adds a new zombie vm_bo to the
+ * bo_defer list
+ *
+ * Called after drm_gpuvm_bo_into_zombie(). GEM mutex must not be held.
+ *
+ * It's important that the GEM stays alive for the duration in which we hold
+ * the mutex, but the instant we add the vm_bo to bo_defer, another thread
+ * might call drm_gpuvm_bo_deferred_cleanup() and put the GEM. Therefore, to
+ * avoid kfreeing a mutex we are holding, the GEM mutex must be released
+ * *before* calling this function.
+ */
+static void
+drm_gpuvm_bo_defer_zombie_cleanup(struct drm_gpuvm_bo *vm_bo)
+{
+	llist_add(&vm_bo->list.entry.bo_defer, &vm_bo->vm->bo_defer);
+}
+
+static void
+drm_gpuvm_bo_defer_free(struct kref *kref)
+{
+	struct drm_gpuvm_bo *vm_bo = container_of(kref, struct drm_gpuvm_bo,
+						  kref);
+
+	drm_gpuvm_bo_into_zombie(kref);
+	mutex_unlock(&vm_bo->obj->gpuva.lock);
+	drm_gpuvm_bo_defer_zombie_cleanup(vm_bo);
+}
+
+/**
+ * drm_gpuvm_bo_put_deferred() - drop a struct drm_gpuvm_bo reference with
+ * deferred cleanup
+ * @vm_bo: the &drm_gpuvm_bo to release the reference of
+ *
+ * This releases a reference to @vm_bo.
+ *
+ * This might take and release the GEMs GPUVA lock. You should call
+ * drm_gpuvm_bo_deferred_cleanup() later to complete the cleanup process.
+ *
+ * Returns: true if vm_bo is being destroyed, false otherwise.
+ */
+bool
+drm_gpuvm_bo_put_deferred(struct drm_gpuvm_bo *vm_bo)
+{
+	if (!vm_bo)
+		return false;
+
+	drm_WARN_ON(vm_bo->vm->drm, !drm_gpuvm_immediate_mode(vm_bo->vm));
+
+	return !!kref_put_mutex(&vm_bo->kref,
+				drm_gpuvm_bo_defer_free,
+				&vm_bo->obj->gpuva.lock);
+}
+EXPORT_SYMBOL_GPL(drm_gpuvm_bo_put_deferred);
+
+/**
+ * drm_gpuvm_bo_deferred_cleanup() - clean up BOs in the deferred list
+ * deferred cleanup
+ * @gpuvm: the VM to clean up
+ *
+ * Cleans up &drm_gpuvm_bo instances in the deferred cleanup list.
+ */
+void
+drm_gpuvm_bo_deferred_cleanup(struct drm_gpuvm *gpuvm)
+{
+	const struct drm_gpuvm_ops *ops = gpuvm->ops;
+	struct drm_gpuvm_bo *vm_bo;
+	struct drm_gem_object *obj;
+	struct llist_node *bo_defer;
+
+	bo_defer = llist_del_all(&gpuvm->bo_defer);
+	if (!bo_defer)
+		return;
+
+	if (drm_gpuvm_resv_protected(gpuvm)) {
+		dma_resv_lock(drm_gpuvm_resv(gpuvm), NULL);
+		llist_for_each_entry(vm_bo, bo_defer, list.entry.bo_defer) {
+			drm_gpuvm_bo_list_del(vm_bo, extobj, false);
+			drm_gpuvm_bo_list_del(vm_bo, evict, false);
+		}
+		dma_resv_unlock(drm_gpuvm_resv(gpuvm));
+	}
+
+	while (bo_defer) {
+		vm_bo = llist_entry(bo_defer, struct drm_gpuvm_bo, list.entry.bo_defer);
+		bo_defer = bo_defer->next;
+		obj = vm_bo->obj;
+		if (ops && ops->vm_bo_free)
+			ops->vm_bo_free(vm_bo);
+		else
+			kfree(vm_bo);
+
+		drm_gpuvm_put(gpuvm);
+		drm_gem_object_put(obj);
+	}
+}
+EXPORT_SYMBOL_GPL(drm_gpuvm_bo_deferred_cleanup);
+
 static struct drm_gpuvm_bo *
 __drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm,
 		    struct drm_gem_object *obj)
@@ -1949,6 +2106,40 @@ drm_gpuva_unlink(struct drm_gpuva *va)
 EXPORT_SYMBOL_GPL(drm_gpuva_unlink);
 
 /**
+ * drm_gpuva_unlink_defer() - unlink a &drm_gpuva with deferred vm_bo cleanup
+ * @va: the &drm_gpuva to unlink
+ *
+ * Similar to drm_gpuva_unlink(), but uses drm_gpuvm_bo_put_deferred() and takes
+ * the lock for the caller.
+ */
+void
+drm_gpuva_unlink_defer(struct drm_gpuva *va)
+{
+	struct drm_gem_object *obj = va->gem.obj;
+	struct drm_gpuvm_bo *vm_bo = va->vm_bo;
+	bool should_defer_bo;
+
+	if (unlikely(!obj))
+		return;
+
+	drm_WARN_ON(vm_bo->vm->drm, !drm_gpuvm_immediate_mode(vm_bo->vm));
+
+	mutex_lock(&obj->gpuva.lock);
+	list_del_init(&va->gem.entry);
+
+	/*
+	 * This is drm_gpuvm_bo_put_deferred() except we already hold the mutex.
+	 */
+	should_defer_bo = kref_put(&vm_bo->kref, drm_gpuvm_bo_into_zombie);
+	mutex_unlock(&obj->gpuva.lock);
+	if (should_defer_bo)
+		drm_gpuvm_bo_defer_zombie_cleanup(vm_bo);
+
+	va->vm_bo = NULL;
+}
+EXPORT_SYMBOL_GPL(drm_gpuva_unlink_defer);
+
+/**
  * drm_gpuva_find_first() - find the first &drm_gpuva in the given range
  * @gpuvm: the &drm_gpuvm to search in
  * @addr: the &drm_gpuvas address