Merge tag 'drm-fixes-2026-07-04' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Weekly fixes for drm. This is large for rc2 but it's just a lot of
  small fixes across a bunch of drivers, xe, amdgpu as usual, plus some
  sashiko-inspired fixes for panthor, and some dma-fence updates.

  core:
   - kernel doc fix
   - include types.h in drm_ras.h

  dma-fence:
   - fix NULL ptr dereference
   - use correct callback
   - make dma_fence_dedup_array more robust

  dp:
   - handle torn down topology gracefully
   - fix kernel doc

  i915:
   - Input validation fixes for BIOS and EDID
   - Fix HDCP code buffer overflow and seq_num_v monotonic increase check
   - Fix near-NULL deref in i915_active during GFP_ATOMIC exhaustion

  xe:
   - Wedge from the timeout handler only after releasing the queue
   - Fix a NULL pointer dereference
   - Remove redundant exec_queue_suspended
   - RTP / OA whitelist fixes
   - Return error on non-migratable faults requiring devmem
   - Skip FORCE_WC and vm_bound check for external dma-bufs
   - Hold notifier lock for write on inject test path
   - Drop bogus static from finish in force_invalidate
   - Fix double-free of managed BO in error path
   - Don't attempt to process FAST_REQ or EVENT relays
   - Fix NPD in bo_meminfo
   - Prevent invalid cursor access for purged BOs
   - Fix offset alignment for MERT WHITELST_OA_MERT_MMIO_TRG

  amdgpu:
   - Soc24 aborted suspend fix
   - Drop unecessary BUG() and BUG_ON() from error paths
   - SCPM fix
   - Power reporting fix
   - DCE HDR fix
   - UVD boundary checks
   - VCN boundary checks
   - VCE boundary checks
   - DCN 4.2 fixes
   - Large stack allocation fixes
   - Fix aperture mapping leak
   - UserQ fixes
   - Ignore_damage_clips fix
   - ACP fixes
   - DC boundary checks
   - GPUVM fixes
   - JPEG idle check fixes
   - Userptr fix
   - GC 11.7 updates
   - Non-4K page fix
   - SMU 13 fixes
   - DP alt mode fix

  amdkfd:
   - Boundary checks
   - CRIU fixes

  amdxdna:
   - fix device removal issues
   - fix use after free in debug BO

  imagination:
   - fix double call to scheduler fini
   - fix ioctl return values
   - fix user array stride

  virtio:
   - handle EDIDs better

  panthor:
   - irq safe fence lock fix
   - reset work fix
   - fix invalid pointer
   - fix iomem access in suspended state
   - sched resume fix
   - unplug suspend fix
   - drop needless check
   - eviction leak fix
   - bail on group start/resume fix
   - keep irqs masked

  malidp:
   - use clock bulk API

  komeda:
   - clock prepare fixes"

* tag 'drm-fixes-2026-07-04' of https://gitlab.freedesktop.org/drm/kernel: (105 commits)
  drm/xe/oa: Fix offset alignment for MERT WHITELIST_OA_MERT_MMIO_TRG
  drm/xe/pt: prevent invalid cursor access for purged BOs
  drm/xe: fix NPD in bo_meminfo()
  drm/xe/pf: Don't attempt to process FAST_REQ or EVENT relays
  drm/xe/hw_engine: Fix double-free of managed BO in error path
  drm/xe/userptr: Drop bogus static from finish in force_invalidate
  drm/xe/userptr: Hold notifier_lock for write on inject test path
  drm/xe/display: skip FORCE_WC and vm_bound check for external dma-bufs
  drm/xe: Return error on non-migratable faults requiring devmem
  drm/xe/rtp: Ensure locking/ref counting for OA whitelists
  drm/xe/oa: (De-)whitelist OA registers on OA stream open/release
  drm/xe/rtp: (De-)whitelist OA registers for all hwe's for a gt
  drm/xe/rtp: Toggle 'deny' bit to (de-)whitelist OA regs
  drm/xe/rtp: Save OA nonpriv registers to register save/restore lists
  drm/xe/rtp: Generalize whitelist_apply_to_hwe
  drm/xe/rtp: Keep track of non-OA nonpriv slots
  drm/xe/rtp: Maintain OA whitelists separately
  drm/xe/rtp: Fix build error with clang < 21 and non-const initializers
  drm/imagination: Fix user array stride in pvr_set_uobj_array()
  drm/imagination: Fix returned size for DRM_IOCTL_PVR_DEV_QUERY
  ...

5 files changed, 98 insertions, 53 deletions

diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
index e9fbd8c14364..54486960cbf5 100644
--- a/drivers/accel/amdxdna/aie2_ctx.c
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -59,6 +59,18 @@ static bool aie2_tdr_detect(struct amdxdna_dev *xdna)
 	return false;
 }
 
+static void aie2_cmd_release(struct kref *ref)
+{
+	struct amdxdna_drv_cmd *drv_cmd = container_of(ref, struct amdxdna_drv_cmd, refcnt);
+
+	kfree(drv_cmd);
+}
+
+static void aie2_cmd_put(struct amdxdna_drv_cmd *drv_cmd)
+{
+	kref_put(&drv_cmd->refcnt, aie2_cmd_release);
+}
+
 static void aie2_job_release(struct kref *ref)
 {
 	struct amdxdna_sched_job *job;
@@ -70,6 +82,8 @@ static void aie2_job_release(struct kref *ref)
 	wake_up(&job->hwctx->priv->job_free_wq);
 	if (job->out_fence)
 		dma_fence_put(job->out_fence);
+	if (job->drv_cmd)
+		aie2_cmd_put(job->drv_cmd);
 	kfree(job->aie2_job_health);
 	kfree(job);
 }
@@ -901,7 +915,7 @@ static int aie2_hwctx_cfg_debug_bo(struct amdxdna_hwctx *hwctx, u32 bo_hdl,
 {
 	struct amdxdna_client *client = hwctx->client;
 	struct amdxdna_dev *xdna = client->xdna;
-	struct amdxdna_drv_cmd cmd = { 0 };
+	struct amdxdna_drv_cmd *cmd;
 	struct amdxdna_gem_obj *abo;
 	u64 seq;
 	int ret;
@@ -912,32 +926,39 @@ static int aie2_hwctx_cfg_debug_bo(struct amdxdna_hwctx *hwctx, u32 bo_hdl,
 		return -EINVAL;
 	}
 
+	cmd = kzalloc_obj(*cmd);
+	if (!cmd) {
+		ret = -ENOMEM;
+		goto put_obj;
+	}
+	kref_init(&cmd->refcnt);
+
 	if (attach) {
 		if (abo->assigned_hwctx != AMDXDNA_INVALID_CTX_HANDLE) {
 			ret = -EBUSY;
-			goto put_obj;
+			goto put_cmd;
 		}
-		cmd.opcode = ATTACH_DEBUG_BO;
+		cmd->opcode = ATTACH_DEBUG_BO;
 	} else {
 		if (abo->assigned_hwctx != hwctx->id) {
 			ret = -EINVAL;
-			goto put_obj;
+			goto put_cmd;
 		}
-		cmd.opcode = DETACH_DEBUG_BO;
+		cmd->opcode = DETACH_DEBUG_BO;
 	}
 
-	ret = amdxdna_cmd_submit(client, &cmd, AMDXDNA_INVALID_BO_HANDLE,
+	ret = amdxdna_cmd_submit(client, cmd, AMDXDNA_INVALID_BO_HANDLE,
 				 &bo_hdl, 1, hwctx->id, &seq);
 	if (ret) {
 		XDNA_ERR(xdna, "Submit command failed");
-		goto put_obj;
+		goto put_cmd;
 	}
 
 	aie2_cmd_wait(hwctx, seq);
-	if (cmd.result) {
-		XDNA_ERR(xdna, "Response failure 0x%x", cmd.result);
+	if (cmd->result) {
+		XDNA_ERR(xdna, "Response failure 0x%x", cmd->result);
 		ret = -EINVAL;
-		goto put_obj;
+		goto put_cmd;
 	}
 
 	if (attach)
@@ -947,6 +968,8 @@ static int aie2_hwctx_cfg_debug_bo(struct amdxdna_hwctx *hwctx, u32 bo_hdl,
 
 	XDNA_DBG(xdna, "Config debug BO %d to %s", bo_hdl, hwctx->name);
 
+put_cmd:
+	aie2_cmd_put(cmd);
 put_obj:
 	amdxdna_gem_put_obj(abo);
 	return ret;
@@ -974,25 +997,32 @@ int aie2_hwctx_sync_debug_bo(struct amdxdna_hwctx *hwctx, u32 debug_bo_hdl)
 {
 	struct amdxdna_client *client = hwctx->client;
 	struct amdxdna_dev *xdna = client->xdna;
-	struct amdxdna_drv_cmd cmd = { 0 };
+	struct amdxdna_drv_cmd *cmd;
 	u64 seq;
 	int ret;
 
-	cmd.opcode = SYNC_DEBUG_BO;
-	ret = amdxdna_cmd_submit(client, &cmd, AMDXDNA_INVALID_BO_HANDLE,
+	cmd = kzalloc_obj(*cmd);
+	if (!cmd)
+		return -ENOMEM;
+	kref_init(&cmd->refcnt);
+
+	cmd->opcode = SYNC_DEBUG_BO;
+	ret = amdxdna_cmd_submit(client, cmd, AMDXDNA_INVALID_BO_HANDLE,
 				 &debug_bo_hdl, 1, hwctx->id, &seq);
 	if (ret) {
 		XDNA_ERR(xdna, "Submit command failed");
-		return ret;
+		goto put_cmd;
 	}
 
 	aie2_cmd_wait(hwctx, seq);
-	if (cmd.result) {
-		XDNA_ERR(xdna, "Response failure 0x%x", cmd.result);
-		return -EINVAL;
+	if (cmd->result) {
+		XDNA_ERR(xdna, "Response failure 0x%x", cmd->result);
+		ret = -EINVAL;
 	}
 
-	return 0;
+put_cmd:
+	aie2_cmd_put(cmd);
+	return ret;
 }
 
 static int aie2_populate_range(struct amdxdna_gem_obj *abo)
@@ -1142,6 +1172,8 @@ retry:
 		dma_resv_add_fence(job->bos[i]->resv, job->out_fence, DMA_RESV_USAGE_WRITE);
 	job->seq = hwctx->priv->seq++;
 	kref_get(&job->refcnt);
+	if (job->drv_cmd)
+		kref_get(&job->drv_cmd->refcnt);
 	drm_sched_entity_push_job(&job->base);
 
 	*seq = job->seq;
diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h
index aaae16430466..b6bef3af7dab 100644
--- a/drivers/accel/amdxdna/amdxdna_ctx.h
+++ b/drivers/accel/amdxdna/amdxdna_ctx.h
@@ -132,6 +132,7 @@ enum amdxdna_job_opcode {
 struct amdxdna_drv_cmd {
 	enum amdxdna_job_opcode	opcode;
 	u32			result;
+	struct kref		refcnt;
 };
 
 struct app_health_report;
diff --git a/drivers/accel/amdxdna/amdxdna_iommu.c b/drivers/accel/amdxdna/amdxdna_iommu.c
index eff00131d0f8..4f245b969eef 100644
--- a/drivers/accel/amdxdna/amdxdna_iommu.c
+++ b/drivers/accel/amdxdna/amdxdna_iommu.c
@@ -4,6 +4,7 @@
  */
 
 #include <drm/amdxdna_accel.h>
+#include <drm/drm_managed.h>
 #include <linux/iommu.h>
 #include <linux/iova.h>
 
@@ -153,10 +154,30 @@ void amdxdna_iommu_free(struct amdxdna_dev *xdna, size_t size,
 	free_pages((unsigned long)cpu_addr, get_order(size));
 }
 
+static void amdxdna_cleanup_force_iova(struct drm_device *dev, void *res)
+{
+	struct amdxdna_dev *xdna = to_xdna_dev(dev);
+
+	if (xdna->domain) {
+		iommu_detach_group(xdna->domain, xdna->group);
+		put_iova_domain(&xdna->iovad);
+		iova_cache_put();
+		iommu_domain_free(xdna->domain);
+	}
+
+	iommu_group_put(xdna->group);
+}
+
+void amdxdna_iommu_fini(struct amdxdna_dev *xdna)
+{
+	if (xdna->group && !xdna->domain)
+		iommu_group_put(xdna->group);
+}
+
 int amdxdna_iommu_init(struct amdxdna_dev *xdna)
 {
 	unsigned long order;
-	int ret;
+	int ret = 0;
 
 	xdna->group = iommu_group_get(xdna->ddev.dev);
 	if (!xdna->group || !force_iova)
@@ -182,8 +203,14 @@ int amdxdna_iommu_init(struct amdxdna_dev *xdna)
 	if (ret)
 		goto put_iova;
 
+	ret = drmm_add_action(&xdna->ddev, amdxdna_cleanup_force_iova, NULL);
+	if (ret)
+		goto detach_group;
+
 	return 0;
 
+detach_group:
+	iommu_detach_group(xdna->domain, xdna->group);
 put_iova:
 	put_iova_domain(&xdna->iovad);
 	iova_cache_put();
@@ -191,20 +218,8 @@ free_domain:
 	iommu_domain_free(xdna->domain);
 put_group:
 	iommu_group_put(xdna->group);
+	xdna->group = NULL;
 	xdna->domain = NULL;
 
 	return ret;
 }
-
-void amdxdna_iommu_fini(struct amdxdna_dev *xdna)
-{
-	if (xdna->domain) {
-		iommu_detach_group(xdna->domain, xdna->group);
-		put_iova_domain(&xdna->iovad);
-		iova_cache_put();
-		iommu_domain_free(xdna->domain);
-	}
-
-	if (xdna->group)
-		iommu_group_put(xdna->group);
-}
diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c
index 65489bb3f2b0..e94d8290a807 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.c
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c
@@ -138,9 +138,11 @@ static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp)
 		    xdna->dev_info->dev_heap_max_size);
 	mutex_init(&client->mm_lock);
 
+	mutex_lock(&xdna->client_lock);
 	mutex_lock(&xdna->dev_lock);
 	list_add_tail(&client->node, &xdna->client_list);
 	mutex_unlock(&xdna->dev_lock);
+	mutex_unlock(&xdna->client_lock);
 
 	filp->driver_priv = client;
 	client->filp = filp;
@@ -174,18 +176,14 @@ static void amdxdna_drm_close(struct drm_device *ddev, struct drm_file *filp)
 {
 	struct amdxdna_client *client = filp->driver_priv;
 	struct amdxdna_dev *xdna = to_xdna_dev(ddev);
-	int idx;
 
 	XDNA_DBG(xdna, "closing pid %d", client->pid);
 
-	if (!drm_dev_enter(&xdna->ddev, &idx))
-		return;
-
+	mutex_lock(&xdna->client_lock);
 	mutex_lock(&xdna->dev_lock);
 	amdxdna_client_cleanup(client);
 	mutex_unlock(&xdna->dev_lock);
-
-	drm_dev_exit(idx);
+	mutex_unlock(&xdna->client_lock);
 }
 
 static int amdxdna_drm_get_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
@@ -371,6 +369,10 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!xdna->dev_info)
 		return -ENODEV;
 
+	ret = drmm_mutex_init(ddev, &xdna->client_lock);
+	if (ret)
+		return ret;
+
 	drmm_mutex_init(ddev, &xdna->dev_lock);
 	init_rwsem(&xdna->notifier_lock);
 	INIT_LIST_HEAD(&xdna->client_list);
@@ -390,9 +392,9 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		return ret;
 
-	xdna->notifier_wq = alloc_ordered_workqueue("notifier_wq", WQ_MEM_RECLAIM);
-	if (!xdna->notifier_wq) {
-		ret = -ENOMEM;
+	xdna->notifier_wq = drmm_alloc_ordered_workqueue(ddev, "notifier_wq", WQ_MEM_RECLAIM);
+	if (IS_ERR(xdna->notifier_wq)) {
+		ret = PTR_ERR(xdna->notifier_wq);
 		goto iommu_fini;
 	}
 
@@ -401,7 +403,7 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mutex_unlock(&xdna->dev_lock);
 	if (ret) {
 		XDNA_ERR(xdna, "Hardware init failed, ret %d", ret);
-		goto destroy_notifier_wq;
+		goto iommu_fini;
 	}
 
 	ret = amdxdna_sysfs_init(xdna);
@@ -425,8 +427,6 @@ failed_dev_fini:
 	mutex_lock(&xdna->dev_lock);
 	xdna->dev_info->ops->fini(xdna);
 	mutex_unlock(&xdna->dev_lock);
-destroy_notifier_wq:
-	destroy_workqueue(xdna->notifier_wq);
 iommu_fini:
 	amdxdna_iommu_fini(xdna);
 	return ret;
@@ -437,23 +437,19 @@ static void amdxdna_remove(struct pci_dev *pdev)
 	struct amdxdna_dev *xdna = pci_get_drvdata(pdev);
 	struct amdxdna_client *client;
 
-	destroy_workqueue(xdna->notifier_wq);
-
 	drm_dev_unplug(&xdna->ddev);
 	amdxdna_sysfs_fini(xdna);
 
+	mutex_lock(&xdna->client_lock);
 	mutex_lock(&xdna->dev_lock);
-	client = list_first_entry_or_null(&xdna->client_list,
-					  struct amdxdna_client, node);
-	while (client) {
-		amdxdna_client_cleanup(client);
-
-		client = list_first_entry_or_null(&xdna->client_list,
-						  struct amdxdna_client, node);
+	list_for_each_entry(client, &xdna->client_list, node) {
+		amdxdna_hwctx_remove_all(client);
+		amdxdna_sva_fini(client);
 	}
 
 	xdna->dev_info->ops->fini(xdna);
 	mutex_unlock(&xdna->dev_lock);
+	mutex_unlock(&xdna->client_lock);
 
 	amdxdna_iommu_fini(xdna);
 }
diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h
index 34271c14d359..a997d27a504d 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.h
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h
@@ -120,6 +120,7 @@ struct amdxdna_dev {
 
 	struct mutex			dev_lock; /* per device lock */
 	struct list_head		client_list;
+	struct mutex			client_lock; /* client_list */
 	struct amdxdna_fw_ver		fw_ver;
 	struct rw_semaphore		notifier_lock; /* for mmu notifier*/
 	struct workqueue_struct		*notifier_wq;