Merge tag 'drm-fixes-2025-03-07' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Fixes across the board, mostly xe and imagination with some amd and
  misc others.

  The xe fixes are mostly hmm related, though there are some others in
  there as well, nothing really stands out otherwise.

  The nouveau Kconfig to select FW_CACHE is in this, which we discussed
  a while back.

  nouveau:
   - rely on fw caching Kconfig fix

  imagination:
   - avoid deadlock on fence release
   - fix fence initialisation
   - fix timestamps firmware traces

  scheduler:
   - fix include guard

  bochs:
   - dpms fix

  i915:
   - bump max stream count to match pipes

  xe:
   - Remove double page flip on initial plane
   - Properly setup userptr pfn_flags_mask
   - Fix GT "for each engine" workarounds
   - Fix userptr races and missed validations
   - Userptr invalid page access fixes
   - Cleanup some style nits

  amdgpu:
   - Fix NULL check in DC code
   - SMU 14 fix

  amdkfd:
   - Fix NULL check in queue validation

  radeon:
   - RS400 HyperZ fix"

* tag 'drm-fixes-2025-03-07' of https://gitlab.freedesktop.org/drm/kernel: (22 commits)
  drm/bochs: Fix DPMS regression
  drm/xe/userptr: Unmap userptrs in the mmu notifier
  drm/xe/hmm: Don't dereference struct page pointers without notifier lock
  drm/xe/hmm: Style- and include fixes
  drm/xe: Add staging tree for VM binds
  drm/xe: Fix fault mode invalidation with unbind
  drm/xe/vm: Fix a misplaced #endif
  drm/xe/vm: Validate userptr during gpu vma prefetching
  drm/amd/pm: always allow ih interrupt from fw
  drm/radeon: Fix rs400_gpu_init for ATI mobility radeon Xpress 200M
  drm/amdkfd: Fix NULL Pointer Dereference in KFD queue
  drm/amd/display: Fix null check for pipe_ctx->plane_state in resource_build_scaling_params
  drm/xe: Fix GT "for each engine" workarounds
  drm/xe/userptr: properly setup pfn_flags_mask
  drm/i915/mst: update max stream count to match number of pipes
  drm/xe: Remove double pageflip
  drm/sched: Fix preprocessor guard
  drm/imagination: Fix timestamps in firmware traces
  drm/imagination: only init job done fences once
  drm/imagination: Hold drm_gem_gpuva lock for unmap
  ...

Author: torvalds

drivers/gpu/drm/amd/amdkfd/kfd_queue.c

@@ -266,8 +266,8 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
 	/* EOP buffer is not required for all ASICs */
 	if (properties->eop_ring_buffer_address) {
 		if (properties->eop_ring_buffer_size != topo_dev->node_props.eop_buffer_size) {
-			pr_debug("queue eop bo size 0x%lx not equal to node eop buf size 0x%x\n",
-				properties->eop_buf_bo->tbo.base.size,
+			pr_debug("queue eop bo size 0x%x not equal to node eop buf size 0x%x\n",
+				properties->eop_ring_buffer_size,
 				topo_dev->node_props.eop_buffer_size);
 			err = -EINVAL;
 			goto out_err_unreserve;

drivers/gpu/drm/amd/display/dc/core/dc_resource.c

@@ -1455,7 +1455,8 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 
 	/* Invalid input */
-	if (!plane_state->dst_rect.width ||
+	if (!plane_state ||
+			!plane_state->dst_rect.width ||
 			!plane_state->dst_rect.height ||
 			!plane_state->src_rect.width ||
 			!plane_state->src_rect.height) {

drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c

@@ -1895,16 +1895,6 @@ static int smu_v14_0_allow_ih_interrupt(struct smu_context *smu)
 				    NULL);
 }
 
-static int smu_v14_0_process_pending_interrupt(struct smu_context *smu)
-{
-	int ret = 0;
-
-	if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_ACDC_BIT))
-		ret = smu_v14_0_allow_ih_interrupt(smu);
-
-	return ret;
-}
-
 int smu_v14_0_enable_thermal_alert(struct smu_context *smu)
 {
 	int ret = 0;
@@ -1916,7 +1906,7 @@ int smu_v14_0_enable_thermal_alert(struct smu_context *smu)
 	if (ret)
 		return ret;
 
-	return smu_v14_0_process_pending_interrupt(smu);
+	return smu_v14_0_allow_ih_interrupt(smu);
 }
 
 int smu_v14_0_disable_thermal_alert(struct smu_context *smu)

drivers/gpu/drm/i915/display/intel_dp_mst.c

@@ -1867,7 +1867,8 @@ intel_dp_mst_encoder_init(struct intel_digital_port *dig_port, int conn_base_id)
 	/* create encoders */
 	mst_stream_encoders_create(dig_port);
 	ret = drm_dp_mst_topology_mgr_init(&intel_dp->mst_mgr, display->drm,
-					   &intel_dp->aux, 16, 3, conn_base_id);
+					   &intel_dp->aux, 16,
+					   INTEL_NUM_PIPES(display), conn_base_id);
 	if (ret) {
 		intel_dp->mst_mgr.cbs = NULL;
 		return ret;

drivers/gpu/drm/imagination/pvr_fw_meta.c

@@ -527,8 +527,10 @@ pvr_meta_vm_map(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj)
 static void
 pvr_meta_vm_unmap(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj)
 {
-	pvr_vm_unmap(pvr_dev->kernel_vm_ctx, fw_obj->fw_mm_node.start,
-		     fw_obj->fw_mm_node.size);
+	struct pvr_gem_object *pvr_obj = fw_obj->gem;
+
+	pvr_vm_unmap_obj(pvr_dev->kernel_vm_ctx, pvr_obj,
+			 fw_obj->fw_mm_node.start, fw_obj->fw_mm_node.size);
 }
 
 static bool

drivers/gpu/drm/imagination/pvr_fw_trace.c

@@ -333,8 +333,8 @@ static int fw_trace_seq_show(struct seq_file *s, void *v)
 	if (sf_id == ROGUE_FW_SF_LAST)
 		return -EINVAL;
 
-	timestamp = read_fw_trace(trace_seq_data, 1) |
-		((u64)read_fw_trace(trace_seq_data, 2) << 32);
+	timestamp = ((u64)read_fw_trace(trace_seq_data, 1) << 32) |
+		read_fw_trace(trace_seq_data, 2);
 	timestamp = (timestamp & ~ROGUE_FWT_TIMESTAMP_TIME_CLRMSK) >>
 		ROGUE_FWT_TIMESTAMP_TIME_SHIFT;
 

drivers/gpu/drm/imagination/pvr_queue.c

@@ -109,12 +109,20 @@ pvr_queue_fence_get_driver_name(struct dma_fence *f)
 	return PVR_DRIVER_NAME;
 }
 
+static void pvr_queue_fence_release_work(struct work_struct *w)
+{
+	struct pvr_queue_fence *fence = container_of(w, struct pvr_queue_fence, release_work);
+
+	pvr_context_put(fence->queue->ctx);
+	dma_fence_free(&fence->base);
+}
+
 static void pvr_queue_fence_release(struct dma_fence *f)
 {
 	struct pvr_queue_fence *fence = container_of(f, struct pvr_queue_fence, base);
+	struct pvr_device *pvr_dev = fence->queue->ctx->pvr_dev;
 
-	pvr_context_put(fence->queue->ctx);
-	dma_fence_free(f);
+	queue_work(pvr_dev->sched_wq, &fence->release_work);
 }
 
 static const char *
@@ -268,6 +276,7 @@ pvr_queue_fence_init(struct dma_fence *f,
 
 	pvr_context_get(queue->ctx);
 	fence->queue = queue;
+	INIT_WORK(&fence->release_work, pvr_queue_fence_release_work);
 	dma_fence_init(&fence->base, fence_ops,
 		       &fence_ctx->lock, fence_ctx->id,
 		       atomic_inc_return(&fence_ctx->seqno));
@@ -304,8 +313,9 @@ pvr_queue_cccb_fence_init(struct dma_fence *fence, struct pvr_queue *queue)
 static void
 pvr_queue_job_fence_init(struct dma_fence *fence, struct pvr_queue *queue)
 {
-	pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops,
-			     &queue->job_fence_ctx);
+	if (!fence->ops)
+		pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops,
+				     &queue->job_fence_ctx);
 }
 
 /**

drivers/gpu/drm/imagination/pvr_queue.h

@@ -5,6 +5,7 @@
 #define PVR_QUEUE_H
 
 #include <drm/gpu_scheduler.h>
+#include <linux/workqueue.h>
 
 #include "pvr_cccb.h"
 #include "pvr_device.h"
@@ -63,6 +64,9 @@ struct pvr_queue_fence {
 
 	/** @queue: Queue that created this fence. */
 	struct pvr_queue *queue;
+
+	/** @release_work: Fence release work structure. */
+	struct work_struct release_work;
 };
 
 /**

drivers/gpu/drm/imagination/pvr_vm.c

@@ -293,8 +293,9 @@ pvr_vm_bind_op_map_init(struct pvr_vm_bind_op *bind_op,
 
 static int
 pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op,
-			  struct pvr_vm_context *vm_ctx, u64 device_addr,
-			  u64 size)
+			  struct pvr_vm_context *vm_ctx,
+			  struct pvr_gem_object *pvr_obj,
+			  u64 device_addr, u64 size)
 {
 	int err;
 
@@ -318,6 +319,7 @@ pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op,
 		goto err_bind_op_fini;
 	}
 
+	bind_op->pvr_obj = pvr_obj;
 	bind_op->vm_ctx = vm_ctx;
 	bind_op->device_addr = device_addr;
 	bind_op->size = size;
@@ -597,20 +599,6 @@ pvr_vm_create_context(struct pvr_device *pvr_dev, bool is_userspace_context)
 	return ERR_PTR(err);
 }
 
-/**
- * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context.
- * @vm_ctx: Target VM context.
- *
- * This function ensures that no mappings are left dangling by unmapping them
- * all in order of ascending device-virtual address.
- */
-void
-pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx)
-{
-	WARN_ON(pvr_vm_unmap(vm_ctx, vm_ctx->gpuvm_mgr.mm_start,
-			     vm_ctx->gpuvm_mgr.mm_range));
-}
-
 /**
  * pvr_vm_context_release() - Teardown a VM context.
  * @ref_count: Pointer to reference counter of the VM context.
@@ -703,11 +691,7 @@ pvr_vm_lock_extra(struct drm_gpuvm_exec *vm_exec)
 	struct pvr_vm_bind_op *bind_op = vm_exec->extra.priv;
 	struct pvr_gem_object *pvr_obj = bind_op->pvr_obj;
 
-	/* Unmap operations don't have an object to lock. */
-	if (!pvr_obj)
-		return 0;
-
-	/* Acquire lock on the GEM being mapped. */
+	/* Acquire lock on the GEM object being mapped/unmapped. */
 	return drm_exec_lock_obj(&vm_exec->exec, gem_from_pvr_gem(pvr_obj));
 }
 
@@ -772,8 +756,10 @@ pvr_vm_map(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj,
 }
 
 /**
- * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory.
+ * pvr_vm_unmap_obj_locked() - Unmap an already mapped section of device-virtual
+ * memory.
  * @vm_ctx: Target VM context.
+ * @pvr_obj: Target PowerVR memory object.
  * @device_addr: Virtual device address at the start of the target mapping.
  * @size: Size of the target mapping.
  *
@@ -784,9 +770,13 @@ pvr_vm_map(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj,
  *  * Any error encountered while performing internal operations required to
  *    destroy the mapping (returned from pvr_vm_gpuva_unmap or
  *    pvr_vm_gpuva_remap).
+ *
+ * The vm_ctx->lock must be held when calling this function.
  */
-int
-pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
+static int
+pvr_vm_unmap_obj_locked(struct pvr_vm_context *vm_ctx,
+			struct pvr_gem_object *pvr_obj,
+			u64 device_addr, u64 size)
 {
 	struct pvr_vm_bind_op bind_op = {0};
 	struct drm_gpuvm_exec vm_exec = {
@@ -799,11 +789,13 @@ pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
 		},
 	};
 
-	int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, device_addr,
-					    size);
+	int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, pvr_obj,
+					    device_addr, size);
 	if (err)
 		return err;
 
+	pvr_gem_object_get(pvr_obj);
+
 	err = drm_gpuvm_exec_lock(&vm_exec);
 	if (err)
 		goto err_cleanup;
@@ -818,6 +810,96 @@ pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
 	return err;
 }
 
+/**
+ * pvr_vm_unmap_obj() - Unmap an already mapped section of device-virtual
+ * memory.
+ * @vm_ctx: Target VM context.
+ * @pvr_obj: Target PowerVR memory object.
+ * @device_addr: Virtual device address at the start of the target mapping.
+ * @size: Size of the target mapping.
+ *
+ * Return:
+ *  * 0 on success,
+ *  * Any error encountered by pvr_vm_unmap_obj_locked.
+ */
+int
+pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj,
+		 u64 device_addr, u64 size)
+{
+	int err;
+
+	mutex_lock(&vm_ctx->lock);
+	err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj, device_addr, size);
+	mutex_unlock(&vm_ctx->lock);
+
+	return err;
+}
+
+/**
+ * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory.
+ * @vm_ctx: Target VM context.
+ * @device_addr: Virtual device address at the start of the target mapping.
+ * @size: Size of the target mapping.
+ *
+ * Return:
+ *  * 0 on success,
+ *  * Any error encountered by drm_gpuva_find,
+ *  * Any error encountered by pvr_vm_unmap_obj_locked.
+ */
+int
+pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
+{
+	struct pvr_gem_object *pvr_obj;
+	struct drm_gpuva *va;
+	int err;
+
+	mutex_lock(&vm_ctx->lock);
+
+	va = drm_gpuva_find(&vm_ctx->gpuvm_mgr, device_addr, size);
+	if (va) {
+		pvr_obj = gem_to_pvr_gem(va->gem.obj);
+		err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj,
+					      va->va.addr, va->va.range);
+	} else {
+		err = -ENOENT;
+	}
+
+	mutex_unlock(&vm_ctx->lock);
+
+	return err;
+}
+
+/**
+ * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context.
+ * @vm_ctx: Target VM context.
+ *
+ * This function ensures that no mappings are left dangling by unmapping them
+ * all in order of ascending device-virtual address.
+ */
+void
+pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx)
+{
+	mutex_lock(&vm_ctx->lock);
+
+	for (;;) {
+		struct pvr_gem_object *pvr_obj;
+		struct drm_gpuva *va;
+
+		va = drm_gpuva_find_first(&vm_ctx->gpuvm_mgr,
+					  vm_ctx->gpuvm_mgr.mm_start,
+					  vm_ctx->gpuvm_mgr.mm_range);
+		if (!va)
+			break;
+
+		pvr_obj = gem_to_pvr_gem(va->gem.obj);
+
+		WARN_ON(pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj,
+						va->va.addr, va->va.range));
+	}
+
+	mutex_unlock(&vm_ctx->lock);
+}
+
 /* Static data areas are determined by firmware. */
 static const struct drm_pvr_static_data_area static_data_areas[] = {
 	{

drivers/gpu/drm/imagination/pvr_vm.h

@@ -38,6 +38,9 @@ struct pvr_vm_context *pvr_vm_create_context(struct pvr_device *pvr_dev,
 int pvr_vm_map(struct pvr_vm_context *vm_ctx,
 	       struct pvr_gem_object *pvr_obj, u64 pvr_obj_offset,
 	       u64 device_addr, u64 size);
+int pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx,
+		     struct pvr_gem_object *pvr_obj,
+		     u64 device_addr, u64 size);
 int pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size);
 void pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx);