6.18.4-rc1 review

index f884d155a832..3b9df655e837 100644
@@ -979,8 +979,10 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data,
 	if (!obj)
 		return -ENOENT;
 
-	if (args->handle == args->new_handle)
-		return 0;
+	if (args->handle == args->new_handle) {
+		ret = 0;
+		goto out;
+	}
 
 	mutex_lock(&file_priv->prime.lock);
 

@@ -1012,6 +1014,8 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data,
 
 out_unlock:
 	mutex_unlock(&file_priv->prime.lock);
+out:
+	drm_gem_object_put(obj);
 
 	return ret;
 }

@@ -113,7 +113,7 @@ static struct sg_table *xe_dma_buf_map(s
 	case XE_PL_TT:
 		sgt = drm_prime_pages_to_sg(obj->dev,
 					    bo->ttm.ttm->pages,
-					    bo->ttm.ttm->num_pages);
+					    obj->size >> PAGE_SHIFT);
 		if (IS_ERR(sgt))
 			return sgt;
 

@@ -1346,7 +1346,7 @@ static int xe_oa_user_ext_set_property(s
 		     ARRAY_SIZE(xe_oa_set_property_funcs_config));
 
 	if (XE_IOCTL_DBG(oa->xe, ext.property >= ARRAY_SIZE(xe_oa_set_property_funcs_open)) ||
-	    XE_IOCTL_DBG(oa->xe, ext.pad))
+	    XE_IOCTL_DBG(oa->xe, !ext.property) || XE_IOCTL_DBG(oa->xe, ext.pad))
 		return -EINVAL;
 
 	idx = array_index_nospec(ext.property, ARRAY_SIZE(xe_oa_set_property_funcs_open));

@@ -290,7 +290,7 @@ static int xe_eu_stall_user_ext_set_prop
 		return -EFAULT;
 
 	if (XE_IOCTL_DBG(xe, ext.property >= ARRAY_SIZE(xe_set_eu_stall_property_funcs)) ||
-	    XE_IOCTL_DBG(xe, ext.pad))
+	    XE_IOCTL_DBG(xe, !ext.property) || XE_IOCTL_DBG(xe, ext.pad))
 		return -EINVAL;
 
 	idx = array_index_nospec(ext.property, ARRAY_SIZE(xe_set_eu_stall_property_funcs));

@@ -1481,7 +1481,10 @@ struct xe_vm *xe_vm_create(struct xe_dev
 	INIT_WORK(&vm->destroy_work, vm_destroy_work_func);
 
 	INIT_LIST_HEAD(&vm->preempt.exec_queues);
-	vm->preempt.min_run_period_ms = 10;	/* FIXME: Wire up to uAPI */
+	if (flags & XE_VM_FLAG_FAULT_MODE)
+		vm->preempt.min_run_period_ms = 0;
+	else
+		vm->preempt.min_run_period_ms = 5;
 
 	for_each_tile(tile, xe, id)
 		xe_range_fence_tree_init(&vm->rftree[id]);

@@ -268,7 +268,7 @@ struct xe_vm {
 		 * @min_run_period_ms: The minimum run period before preempting
 		 * an engine again
 		 */
-		s64 min_run_period_ms;
+		unsigned int min_run_period_ms;
 		/** @exec_queues: list of exec queues attached to this VM */
 		struct list_head exec_queues;
 		/** @num_exec_queues: number exec queues attached to this VM */

@@ -670,6 +670,24 @@ static u32 wq_space_until_wrap(struct xe
 	return (WQ_SIZE - q->guc->wqi_tail);
 }
 
+static inline void relaxed_ms_sleep(unsigned int delay_ms)
+{
+	unsigned long min_us, max_us;
+
+	if (!delay_ms)
+		return;
+
+	if (delay_ms > 20) {
+		msleep(delay_ms);
+		return;
+	}
+
+	min_us = mul_u32_u32(delay_ms, 1000);
+	max_us = min_us + 500;
+
+	usleep_range(min_us, max_us);
+}
+
 static int wq_wait_for_space(struct xe_exec_queue *q, u32 wqi_size)
 {
 	struct xe_guc *guc = exec_queue_to_guc(q);

@@ -1559,7 +1577,7 @@ static void __guc_exec_queue_process_msg
 				since_resume_ms;
 
 			if (wait_ms > 0 && q->guc->resume_time)
-				msleep(wait_ms);
+				relaxed_ms_sleep(wait_ms);
 
 			set_exec_queue_suspended(q);
 			disable_scheduling(q, false);

@@ -1480,7 +1480,7 @@ static bool xe_ttm_bo_lock_in_destructor
 	 * always succeed here, as long as we hold the lru lock.
 	 */
 	spin_lock(&ttm_bo->bdev->lru_lock);
-	locked = dma_resv_trylock(ttm_bo->base.resv);
+	locked = dma_resv_trylock(&ttm_bo->base._resv);
 	spin_unlock(&ttm_bo->bdev->lru_lock);
 	xe_assert(xe, locked);
 

@@ -1500,13 +1500,6 @@ static void xe_ttm_bo_release_notify(str
 	bo = ttm_to_xe_bo(ttm_bo);
 	xe_assert(xe_bo_device(bo), !(bo->created && kref_read(&ttm_bo->base.refcount)));
 
-	/*
-	 * Corner case where TTM fails to allocate memory and this BOs resv
-	 * still points the VMs resv
-	 */
-	if (ttm_bo->base.resv != &ttm_bo->base._resv)
-		return;
-
 	if (!xe_ttm_bo_lock_in_destructor(ttm_bo))
 		return;
 

@@ -1516,14 +1509,14 @@ static void xe_ttm_bo_release_notify(str
 	 * TODO: Don't do this for external bos once we scrub them after
 	 * unbind.
 	 */
-	dma_resv_for_each_fence(&cursor, ttm_bo->base.resv,
+	dma_resv_for_each_fence(&cursor, &ttm_bo->base._resv,
 				DMA_RESV_USAGE_BOOKKEEP, fence) {
 		if (xe_fence_is_xe_preempt(fence) &&
 		    !dma_fence_is_signaled(fence)) {
 			if (!replacement)
 				replacement = dma_fence_get_stub();
 
-			dma_resv_replace_fences(ttm_bo->base.resv,
+			dma_resv_replace_fences(&ttm_bo->base._resv,
 						fence->context,
 						replacement,
 						DMA_RESV_USAGE_BOOKKEEP);

@@ -1531,7 +1524,7 @@ static void xe_ttm_bo_release_notify(str
 	}
 	dma_fence_put(replacement);
 
-	dma_resv_unlock(ttm_bo->base.resv);
+	dma_resv_unlock(&ttm_bo->base._resv);
 }
 
 static void xe_ttm_bo_delete_mem_notify(struct ttm_buffer_object *ttm_bo)

@@ -247,14 +247,12 @@ static void dpu_encoder_phys_wb_setup_ct
 		if (hw_cdm)
 			intf_cfg.cdm = hw_cdm->idx;
 
-		if (phys_enc->hw_pp->merge_3d && phys_enc->hw_pp->merge_3d->ops.setup_3d_mode)
-			phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,
-					mode_3d);
+		if (hw_pp && hw_pp->merge_3d && hw_pp->merge_3d->ops.setup_3d_mode)
+			hw_pp->merge_3d->ops.setup_3d_mode(hw_pp->merge_3d, mode_3d);
 
 		/* setup which pp blk will connect to this wb */
-		if (hw_pp && phys_enc->hw_wb->ops.bind_pingpong_blk)
-			phys_enc->hw_wb->ops.bind_pingpong_blk(phys_enc->hw_wb,
-					phys_enc->hw_pp->idx);
+		if (hw_pp && hw_wb->ops.bind_pingpong_blk)
+			hw_wb->ops.bind_pingpong_blk(hw_wb, hw_pp->idx);
 
 		phys_enc->hw_ctl->ops.setup_intf_cfg(phys_enc->hw_ctl, &intf_cfg);
 	} else if (phys_enc->hw_ctl && phys_enc->hw_ctl->ops.setup_intf_cfg) {

@@ -1360,6 +1360,7 @@ static const u32 a750_ifpc_reglist_regs[
 	REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(2),
 	REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(3),
 	REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(4),
+	REG_A6XX_RBBM_PERFCTR_CNTL,
 	REG_A6XX_TPL1_NC_MODE_CNTL,
 	REG_A6XX_SP_NC_MODE_CNTL,
 	REG_A6XX_CP_DBG_ECO_CNTL,

@@ -950,13 +950,13 @@ static int eb_lookup_vmas(struct i915_ex
 		vma = eb_lookup_vma(eb, eb->exec[i].handle);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
-			goto err;
+			return err;
 		}
 
 		err = eb_validate_vma(eb, &eb->exec[i], vma);
 		if (unlikely(err)) {
 			i915_vma_put(vma);
-			goto err;
+			return err;
 		}
 
 		err = eb_add_vma(eb, &current_batch, i, vma);

@@ -965,19 +965,8 @@ static int eb_lookup_vmas(struct i915_ex
 
 		if (i915_gem_object_is_userptr(vma->obj)) {
 			err = i915_gem_object_userptr_submit_init(vma->obj);
-			if (err) {
-				if (i + 1 < eb->buffer_count) {
-					/*
-					 * Execbuffer code expects last vma entry to be NULL,
-					 * since we already initialized this entry,
-					 * set the next value to NULL or we mess up
-					 * cleanup handling.
-					 */
-					eb->vma[i + 1].vma = NULL;
-				}
-
+			if (err)
 				return err;
-			}
 
 			eb->vma[i].flags |= __EXEC_OBJECT_USERPTR_INIT;
 			eb->args->flags |= __EXEC_USERPTR_USED;

@@ -985,10 +974,6 @@ static int eb_lookup_vmas(struct i915_ex
 	}
 
 	return 0;
-
-err:
-	eb->vma[i].vma = NULL;
-	return err;
 }
 
 static int eb_lock_vmas(struct i915_execbuffer *eb)

@@ -3374,7 +3359,8 @@ i915_gem_do_execbuffer(struct drm_device
 
 	eb.exec = exec;
 	eb.vma = (struct eb_vma *)(exec + args->buffer_count + 1);
-	eb.vma[0].vma = NULL;
+	memset(eb.vma, 0, (args->buffer_count + 1) * sizeof(struct eb_vma));
+
 	eb.batch_pool = NULL;
 
 	eb.invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS;

@@ -3583,7 +3569,18 @@ i915_gem_execbuffer2_ioctl(struct drm_de
 	if (err)
 		return err;
 
-	/* Allocate extra slots for use by the command parser */
+	/*
+	 * Allocate extra slots for use by the command parser.
+	 *
+	 * Note that this allocation handles two different arrays (the
+	 * exec2_list array, and the eventual eb.vma array introduced in
+	 * i915_gem_do_execbuffer()), that reside in virtually contiguous
+	 * memory. Also note that the allocation intentionally doesn't fill the
+	 * area with zeros, because the exec2_list part doesn't need to be, as
+	 * it's immediately overwritten by user data a few lines below.
+	 * However, the eb.vma part is explicitly zeroed later in
+	 * i915_gem_do_execbuffer().
+	 */
 	exec2_list = kvmalloc_array(count + 2, eb_element_size(),
 				    __GFP_NOWARN | GFP_KERNEL);
 	if (exec2_list == NULL) {

@@ -942,7 +942,7 @@ bool xe_svm_range_needs_migrate_to_vram(
 	xe_assert(vm->xe, IS_DGFX(vm->xe));
 
 	if (xe_svm_range_in_vram(range)) {
-		drm_info(&vm->xe->drm, "Range is already in VRAM\n");
+		drm_dbg(&vm->xe->drm, "Range is already in VRAM\n");
 		return false;
 	}
 

@@ -3,6 +3,7 @@
  * Copyright © 2024-2025 Intel Corporation
  */
 
+#include <linux/dma-fence.h>
 #include <linux/dma-mapping.h>
 #include <linux/migrate.h>
 #include <linux/pagemap.h>

@@ -408,10 +409,14 @@ int drm_pagemap_migrate_to_devmem(struct
 		drm_pagemap_get_devmem_page(page, zdd);
 	}
 
-	err = ops->copy_to_devmem(pages, pagemap_addr, npages);
+	err = ops->copy_to_devmem(pages, pagemap_addr, npages,
+				  devmem_allocation->pre_migrate_fence);
 	if (err)
 		goto err_finalize;
 
+	dma_fence_put(devmem_allocation->pre_migrate_fence);
+	devmem_allocation->pre_migrate_fence = NULL;
+
 	/* Upon success bind devmem allocation to range and zdd */
 	devmem_allocation->timeslice_expiration = get_jiffies_64() +
 		msecs_to_jiffies(timeslice_ms);

@@ -596,7 +601,7 @@ retry:
 	for (i = 0; i < npages; ++i)
 		pages[i] = migrate_pfn_to_page(src[i]);
 
-	err = ops->copy_to_ram(pages, pagemap_addr, npages);
+	err = ops->copy_to_ram(pages, pagemap_addr, npages, NULL);
 	if (err)
 		goto err_finalize;
 

@@ -732,7 +737,7 @@ static int __drm_pagemap_migrate_to_ram(
 	for (i = 0; i < npages; ++i)
 		pages[i] = migrate_pfn_to_page(migrate.src[i]);
 
-	err = ops->copy_to_ram(pages, pagemap_addr, npages);
+	err = ops->copy_to_ram(pages, pagemap_addr, npages, NULL);
 	if (err)
 		goto err_finalize;
 

@@ -813,11 +818,14 @@ EXPORT_SYMBOL_GPL(drm_pagemap_pagemap_op
  * @ops: Pointer to the operations structure for GPU SVM device memory
  * @dpagemap: The struct drm_pagemap we're allocating from.
  * @size: Size of device memory allocation
+ * @pre_migrate_fence: Fence to wait for or pipeline behind before migration starts.
+ * (May be NULL).
  */
 void drm_pagemap_devmem_init(struct drm_pagemap_devmem *devmem_allocation,
 			     struct device *dev, struct mm_struct *mm,
 			     const struct drm_pagemap_devmem_ops *ops,
-			     struct drm_pagemap *dpagemap, size_t size)
+			     struct drm_pagemap *dpagemap, size_t size,
+			     struct dma_fence *pre_migrate_fence)
 {
 	init_completion(&devmem_allocation->detached);
 	devmem_allocation->dev = dev;

@@ -825,6 +833,7 @@ void drm_pagemap_devmem_init(struct drm_
 	devmem_allocation->ops = ops;
 	devmem_allocation->dpagemap = dpagemap;
 	devmem_allocation->size = size;
+	devmem_allocation->pre_migrate_fence = pre_migrate_fence;
 }
 EXPORT_SYMBOL_GPL(drm_pagemap_devmem_init);
 

@@ -1813,6 +1813,7 @@ static struct dma_fence *xe_migrate_vram
 					 unsigned long sram_offset,
 					 struct drm_pagemap_addr *sram_addr,
 					 u64 vram_addr,
+					 struct dma_fence *deps,
 					 const enum xe_migrate_copy_dir dir)
 {
 	struct xe_gt *gt = m->tile->primary_gt;

@@ -1890,6 +1891,14 @@ static struct dma_fence *xe_migrate_vram
 
 	xe_sched_job_add_migrate_flush(job, MI_INVALIDATE_TLB);
 
+	if (deps && !dma_fence_is_signaled(deps)) {
+		dma_fence_get(deps);
+		err = drm_sched_job_add_dependency(&job->drm, deps);
+		if (err)
+			dma_fence_wait(deps, false);
+		err = 0;
+	}
+
 	mutex_lock(&m->job_mutex);
 	xe_sched_job_arm(job);
 	fence = dma_fence_get(&job->drm.s_fence->finished);

@@ -1915,6 +1924,8 @@ err:
  * @npages: Number of pages to migrate.
  * @src_addr: Array of DMA information (source of migrate)
  * @dst_addr: Device physical address of VRAM (destination of migrate)
+ * @deps: struct dma_fence representing the dependencies that need
+ * to be signaled before migration.
  *
  * Copy from an array dma addresses to a VRAM device physical address
  *

@@ -1924,10 +1935,11 @@ err:
 struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m,
 				     unsigned long npages,
 				     struct drm_pagemap_addr *src_addr,
-				     u64 dst_addr)
+				     u64 dst_addr,
+				     struct dma_fence *deps)
 {
 	return xe_migrate_vram(m, npages * PAGE_SIZE, 0, src_addr, dst_addr,
-			       XE_MIGRATE_COPY_TO_VRAM);
+			       deps, XE_MIGRATE_COPY_TO_VRAM);
 }
 
 /**

@@ -1936,6 +1948,8 @@ struct dma_fence *xe_migrate_to_vram(str
  * @npages: Number of pages to migrate.
  * @src_addr: Device physical address of VRAM (source of migrate)
  * @dst_addr: Array of DMA information (destination of migrate)
+ * @deps: struct dma_fence representing the dependencies that need
+ * to be signaled before migration.
  *
  * Copy from a VRAM device physical address to an array dma addresses
  *

@@ -1945,10 +1959,11 @@ struct dma_fence *xe_migrate_to_vram(str
 struct dma_fence *xe_migrate_from_vram(struct xe_migrate *m,
 				       unsigned long npages,
 				       u64 src_addr,
-				       struct drm_pagemap_addr *dst_addr)
+				       struct drm_pagemap_addr *dst_addr,
+				       struct dma_fence *deps)
 {
 	return xe_migrate_vram(m, npages * PAGE_SIZE, 0, dst_addr, src_addr,
-			       XE_MIGRATE_COPY_TO_SRAM);
+			       deps, XE_MIGRATE_COPY_TO_SRAM);
 }
 
 static void xe_migrate_dma_unmap(struct xe_device *xe,

@@ -2121,7 +2136,7 @@ int xe_migrate_access_memory(struct xe_m
 		__fence = xe_migrate_vram(m, current_bytes,
 					  (unsigned long)buf & ~PAGE_MASK,
 					  &pagemap_addr[current_page],
-					  vram_addr, write ?
+					  vram_addr, NULL, write ?
 					  XE_MIGRATE_COPY_TO_VRAM :
 					  XE_MIGRATE_COPY_TO_SRAM);
 		if (IS_ERR(__fence)) {

@@ -111,12 +111,14 @@ int xe_migrate_init(struct xe_migrate *m
 struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m,
 				     unsigned long npages,
 				     struct drm_pagemap_addr *src_addr,
-				     u64 dst_addr);
+				     u64 dst_addr,
+				     struct dma_fence *deps);
 
 struct dma_fence *xe_migrate_from_vram(struct xe_migrate *m,
 				       unsigned long npages,
 				       u64 src_addr,
-				       struct drm_pagemap_addr *dst_addr);
+				       struct drm_pagemap_addr *dst_addr,
+				       struct dma_fence *deps);
 
 struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 				  struct xe_bo *src_bo,

126 lines not on this page · raw message

@@ -8,6 +8,7 @@
 
 #define NR_PAGES(order) (1U << (order))
 
+struct dma_fence;
 struct drm_pagemap;
 struct drm_pagemap_zdd;
 struct device;

@@ -174,6 +175,8 @@ struct drm_pagemap_devmem_ops {
 	 * @pages: Pointer to array of device memory pages (destination)
 	 * @pagemap_addr: Pointer to array of DMA information (source)
 	 * @npages: Number of pages to copy
+	 * @pre_migrate_fence: dma-fence to wait for before migration start.
+	 * May be NULL.
 	 *
 	 * Copy pages to device memory. If the order of a @pagemap_addr entry
 	 * is greater than 0, the entry is populated but subsequent entries

@@ -183,13 +186,16 @@ struct drm_pagemap_devmem_ops {
 	 */
 	int (*copy_to_devmem)(struct page **pages,
 			      struct drm_pagemap_addr *pagemap_addr,
-			      unsigned long npages);
+			      unsigned long npages,
+			      struct dma_fence *pre_migrate_fence);
 
 	/**
 	 * @copy_to_ram: Copy to system RAM (required for migration)
 	 * @pages: Pointer to array of device memory pages (source)
 	 * @pagemap_addr: Pointer to array of DMA information (destination)
 	 * @npages: Number of pages to copy
+	 * @pre_migrate_fence: dma-fence to wait for before migration start.
+	 * May be NULL.
 	 *
 	 * Copy pages to system RAM. If the order of a @pagemap_addr entry
 	 * is greater than 0, the entry is populated but subsequent entries

@@ -199,7 +205,8 @@ struct drm_pagemap_devmem_ops {
 	 */
 	int (*copy_to_ram)(struct page **pages,
 			   struct drm_pagemap_addr *pagemap_addr,
-			   unsigned long npages);
+			   unsigned long npages,
+			   struct dma_fence *pre_migrate_fence);
 };
 
 /**

@@ -212,6 +219,8 @@ struct drm_pagemap_devmem_ops {
  * @dpagemap: The struct drm_pagemap of the pages this allocation belongs to.
  * @size: Size of device memory allocation
  * @timeslice_expiration: Timeslice expiration in jiffies
+ * @pre_migrate_fence: Fence to wait for or pipeline behind before migration starts.
+ * (May be NULL).
  */
 struct drm_pagemap_devmem {
 	struct device *dev;

@@ -221,6 +230,7 @@ struct drm_pagemap_devmem {
 	struct drm_pagemap *dpagemap;
 	size_t size;
 	u64 timeslice_expiration;
+	struct dma_fence *pre_migrate_fence;
 };
 
 int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation,

@@ -238,7 +248,8 @@ struct drm_pagemap *drm_pagemap_page_to_
 void drm_pagemap_devmem_init(struct drm_pagemap_devmem *devmem_allocation,
 			     struct device *dev, struct mm_struct *mm,
 			     const struct drm_pagemap_devmem_ops *ops,
-			     struct drm_pagemap *dpagemap, size_t size);
+			     struct drm_pagemap *dpagemap, size_t size,
+			     struct dma_fence *pre_migrate_fence);
 
 int drm_pagemap_populate_mm(struct drm_pagemap *dpagemap,
 			    unsigned long start, unsigned long end,

@@ -41,7 +41,7 @@ static struct gpio_device *swnode_get_gp
 	    !strcmp(gdev_node->name, GPIOLIB_SWNODE_UNDEFINED_NAME))
 		return ERR_PTR(-ENOENT);
 
-	gdev = gpio_device_find_by_fwnode(fwnode);
+	gdev = gpio_device_find_by_label(gdev_node->name);
 	return gdev ?: ERR_PTR(-EPROBE_DEFER);
 }
 

@@ -152,8 +152,21 @@ static inline struct nv50_head_atom *
 nv50_head_atom_get(struct drm_atomic_state *state, struct drm_crtc *crtc)
 {
 	struct drm_crtc_state *statec = drm_atomic_get_crtc_state(state, crtc);
+
 	if (IS_ERR(statec))
 		return (void *)statec;
+
+	return nv50_head_atom(statec);
+}
+
+static inline struct nv50_head_atom *
+nv50_head_atom_get_new(struct drm_atomic_state *state, struct drm_crtc *crtc)
+{
+	struct drm_crtc_state *statec = drm_atomic_get_new_crtc_state(state, crtc);
+
+	if (!statec)
+		return NULL;
+
 	return nv50_head_atom(statec);
 }
 

@@ -583,7 +583,7 @@ nv50_wndw_prepare_fb(struct drm_plane *p
 	asyw->image.offset[0] = nvbo->offset;
 
 	if (wndw->func->prepare) {
-		asyh = nv50_head_atom_get(asyw->state.state, asyw->state.crtc);
+		asyh = nv50_head_atom_get_new(asyw->state.state, asyw->state.crtc);
 		if (IS_ERR(asyh))
 			return PTR_ERR(asyh);
 

@@ -28,6 +28,16 @@ static void pvr_gem_object_free(struct d
 	drm_gem_shmem_object_free(obj);
 }
 
+static struct dma_buf *pvr_gem_export(struct drm_gem_object *obj, int flags)
+{
+	struct pvr_gem_object *pvr_obj = gem_to_pvr_gem(obj);
+
+	if (pvr_obj->flags & DRM_PVR_BO_PM_FW_PROTECT)
+		return ERR_PTR(-EPERM);
+
+	return drm_gem_prime_export(obj, flags);
+}
+
 static int pvr_gem_mmap(struct drm_gem_object *gem_obj, struct vm_area_struct *vma)
 {
 	struct pvr_gem_object *pvr_obj = gem_to_pvr_gem(gem_obj);

@@ -42,6 +52,7 @@ static int pvr_gem_mmap(struct drm_gem_o
 static const struct drm_gem_object_funcs pvr_gem_object_funcs = {
 	.free = pvr_gem_object_free,
 	.print_info = drm_gem_shmem_object_print_info,
+	.export = pvr_gem_export,
 	.pin = drm_gem_shmem_object_pin,
 	.unpin = drm_gem_shmem_object_unpin,
 	.get_sg_table = drm_gem_shmem_object_get_sg_table,

@@ -1262,17 +1262,17 @@ static int z_erofs_parse_in_bvecs(struct
 	return err;
 }
 
-static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
+static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, bool eio)
 {
 	struct erofs_sb_info *const sbi = EROFS_SB(be->sb);
 	struct z_erofs_pcluster *pcl = be->pcl;
 	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
 	const struct z_erofs_decompressor *decomp =
 				z_erofs_decomp[pcl->algorithmformat];
-	int i, j, jtop, err2;
+	bool try_free = true;
+	int i, j, jtop, err2, err = eio ? -EIO : 0;
 	struct page *page;
 	bool overlapped;
-	bool try_free = true;
 
 	mutex_lock(&pcl->lock);
 	be->nr_pages = PAGE_ALIGN(pcl->length + pcl->pageofs_out) >> PAGE_SHIFT;

@@ -1400,12 +1400,12 @@ static int z_erofs_decompress_queue(cons
 		.pcl = io->head,
 	};
 	struct z_erofs_pcluster *next;
-	int err = io->eio ? -EIO : 0;
+	int err = 0;
 
 	for (; be.pcl != Z_EROFS_PCLUSTER_TAIL; be.pcl = next) {
 		DBG_BUGON(!be.pcl);
 		next = READ_ONCE(be.pcl->next);
-		err = z_erofs_decompress_pcluster(&be, err) ?: err;
+		err = z_erofs_decompress_pcluster(&be, io->eio) ?: err;
 	}
 	return err;
 }

@@ -736,17 +736,20 @@ static void blk_zone_reset_all_bio_endio
 	unsigned long flags;
 	unsigned int i;
 
-	/* Update the condition of all zone write plugs. */
-	rcu_read_lock();
-	for (i = 0; i < disk_zone_wplugs_hash_size(disk); i++) {
-		hlist_for_each_entry_rcu(zwplug, &disk->zone_wplugs_hash[i],
-					 node) {
-			spin_lock_irqsave(&zwplug->lock, flags);
-			disk_zone_wplug_set_wp_offset(disk, zwplug, 0);
-			spin_unlock_irqrestore(&zwplug->lock, flags);
+	if (atomic_read(&disk->nr_zone_wplugs)) {
+		/* Update the condition of all zone write plugs. */
+		rcu_read_lock();
+		for (i = 0; i < disk_zone_wplugs_hash_size(disk); i++) {
+			hlist_for_each_entry_rcu(zwplug,
+						 &disk->zone_wplugs_hash[i],
+						 node) {
+				spin_lock_irqsave(&zwplug->lock, flags);
+				disk_zone_wplug_set_wp_offset(disk, zwplug, 0);
+				spin_unlock_irqrestore(&zwplug->lock, flags);
+			}
 		}
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
 }
 
 static void blk_zone_finish_bio_endio(struct bio *bio)

@@ -1284,6 +1284,7 @@ static const struct x86_cpu_id rapl_ids[
 	X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X,	&rapl_defaults_spr_server),
 	X86_MATCH_VFM(INTEL_LUNARLAKE_M,	&rapl_defaults_core),
 	X86_MATCH_VFM(INTEL_PANTHERLAKE_L,	&rapl_defaults_core),
+	X86_MATCH_VFM(INTEL_WILDCATLAKE_L,	&rapl_defaults_core),
 	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&rapl_defaults_core),
 	X86_MATCH_VFM(INTEL_ARROWLAKE,		&rapl_defaults_core),
 	X86_MATCH_VFM(INTEL_ARROWLAKE_U,	&rapl_defaults_core),

@@ -151,6 +151,7 @@ static const struct x86_cpu_id pl4_suppo
 	X86_MATCH_VFM(INTEL_ARROWLAKE_U, NULL),
 	X86_MATCH_VFM(INTEL_ARROWLAKE_H, NULL),
 	X86_MATCH_VFM(INTEL_PANTHERLAKE_L, NULL),
+	X86_MATCH_VFM(INTEL_WILDCATLAKE_L, NULL),
 	{}
 };
 

@@ -1285,6 +1285,8 @@ static const struct x86_cpu_id rapl_ids[
 	X86_MATCH_VFM(INTEL_LUNARLAKE_M,	&rapl_defaults_core),
 	X86_MATCH_VFM(INTEL_PANTHERLAKE_L,	&rapl_defaults_core),
 	X86_MATCH_VFM(INTEL_WILDCATLAKE_L,	&rapl_defaults_core),
+	X86_MATCH_VFM(INTEL_NOVALAKE,		&rapl_defaults_core),
+	X86_MATCH_VFM(INTEL_NOVALAKE_L,		&rapl_defaults_core),
 	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&rapl_defaults_core),
 	X86_MATCH_VFM(INTEL_ARROWLAKE,		&rapl_defaults_core),
 	X86_MATCH_VFM(INTEL_ARROWLAKE_U,	&rapl_defaults_core),

@@ -152,6 +152,8 @@ static const struct x86_cpu_id pl4_suppo
 	X86_MATCH_VFM(INTEL_ARROWLAKE_H, NULL),
 	X86_MATCH_VFM(INTEL_PANTHERLAKE_L, NULL),
 	X86_MATCH_VFM(INTEL_WILDCATLAKE_L, NULL),
+	X86_MATCH_VFM(INTEL_NOVALAKE, NULL),
+	X86_MATCH_VFM(INTEL_NOVALAKE_L, NULL),
 	{}
 };
 

@@ -1307,6 +1307,10 @@ int bpf_arch_text_poke(void *ip, enum bp
 		       void *old_addr, void *new_addr)
 {
 	int ret;
+	unsigned long size = 0;
+	unsigned long offset = 0;
+	void *image = NULL;
+	char namebuf[KSYM_NAME_LEN];
 	bool is_call = (poke_type == BPF_MOD_CALL);
 	u32 old_insns[LOONGARCH_LONG_JUMP_NINSNS] = {[0 ... 4] = INSN_NOP};
 	u32 new_insns[LOONGARCH_LONG_JUMP_NINSNS] = {[0 ... 4] = INSN_NOP};

@@ -1314,9 +1318,20 @@ int bpf_arch_text_poke(void *ip, enum bp
 	/* Only poking bpf text is supported. Since kernel function entry
 	 * is set up by ftrace, we rely on ftrace to poke kernel functions.
 	 */
-	if (!is_bpf_text_address((unsigned long)ip))
+	if (!__bpf_address_lookup((unsigned long)ip, &size, &offset, namebuf))
 		return -ENOTSUPP;
 
+	image = ip - offset;
+
+	/* zero offset means we're poking bpf prog entry */
+	if (offset == 0) {
+		/* skip to the nop instruction in bpf prog entry:
+		 * move t0, ra
+		 * nop
+		 */
+		ip = image + LOONGARCH_INSN_SIZE;
+	}
+
 	ret = emit_jump_or_nops(old_addr, ip, old_insns, is_call);
 	if (ret)
 		return ret;

@@ -491,7 +491,7 @@ nvgrace_gpu_map_and_read(struct nvgrace_
 		ret = vfio_pci_core_do_io_rw(&nvdev->core_device, false,
 					     nvdev->resmem.ioaddr,
 					     buf, offset, mem_count,
-					     0, 0, false);
+					     0, 0, false, VFIO_PCI_IO_WIDTH_8);
 	}
 
 	return ret;

@@ -609,7 +609,7 @@ nvgrace_gpu_map_and_write(struct nvgrace
 		ret = vfio_pci_core_do_io_rw(&nvdev->core_device, false,
 					     nvdev->resmem.ioaddr,
 					     (char __user *)buf, pos, mem_count,
-					     0, 0, true);
+					     0, 0, true, VFIO_PCI_IO_WIDTH_8);
 	}
 
 	return ret;

@@ -135,7 +135,8 @@ VFIO_IORDWR(64)
 ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 			       void __iomem *io, char __user *buf,
 			       loff_t off, size_t count, size_t x_start,
-			       size_t x_end, bool iswrite)
+			       size_t x_end, bool iswrite,
+			       enum vfio_pci_io_width max_width)
 {
 	ssize_t done = 0;
 	int ret;

@@ -150,20 +151,19 @@ ssize_t vfio_pci_core_do_io_rw(struct vf
 		else
 			fillable = 0;
 
-		if (fillable >= 8 && !(off % 8)) {
+		if (fillable >= 8 && !(off % 8) && max_width >= 8) {
 			ret = vfio_pci_iordwr64(vdev, iswrite, test_mem,
 						io, buf, off, &filled);
 			if (ret)
 				return ret;
 
-		} else
-		if (fillable >= 4 && !(off % 4)) {
+		} else if (fillable >= 4 && !(off % 4) && max_width >= 4) {
 			ret = vfio_pci_iordwr32(vdev, iswrite, test_mem,
 						io, buf, off, &filled);
 			if (ret)
 				return ret;
 
-		} else if (fillable >= 2 && !(off % 2)) {
+		} else if (fillable >= 2 && !(off % 2) && max_width >= 2) {
 			ret = vfio_pci_iordwr16(vdev, iswrite, test_mem,
 						io, buf, off, &filled);
 			if (ret)

@@ -234,6 +234,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_
 	void __iomem *io;
 	struct resource *res = &vdev->pdev->resource[bar];
 	ssize_t done;
+	enum vfio_pci_io_width max_width = VFIO_PCI_IO_WIDTH_8;
 
 	if (pci_resource_start(pdev, bar))
 		end = pci_resource_len(pdev, bar);

@@ -262,6 +263,16 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_
 		if (!io)
 			return -ENOMEM;
 		x_end = end;
+
+		/*
+		 * Certain devices (e.g. Intel X710) don't support qword
+		 * access to the ROM bar. Otherwise PCI AER errors might be
+		 * triggered.
+		 *
+		 * Disable qword access to the ROM bar universally, which
+		 * worked reliably for years before qword access is enabled.
+		 */
+		max_width = VFIO_PCI_IO_WIDTH_4;
 	} else {
 		int ret = vfio_pci_core_setup_barmap(vdev, bar);
 		if (ret) {

@@ -278,7 +289,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_
 	}
 
 	done = vfio_pci_core_do_io_rw(vdev, res->flags & IORESOURCE_MEM, io, buf, pos,
-				      count, x_start, x_end, iswrite);
+				      count, x_start, x_end, iswrite, max_width);
 
 	if (done >= 0)
 		*ppos += done;

@@ -352,7 +363,7 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_
 	 * to the memory enable bit in the command register.
 	 */
 	done = vfio_pci_core_do_io_rw(vdev, false, iomem, buf, off, count,
-				      0, 0, iswrite);
+				      0, 0, iswrite, VFIO_PCI_IO_WIDTH_8);
 
 	vga_put(vdev->pdev, rsrc);
 

@@ -102,6 +102,13 @@ struct vfio_pci_core_device {
 	struct rw_semaphore	memory_lock;
 };
 
+enum vfio_pci_io_width {
+	VFIO_PCI_IO_WIDTH_1 = 1,
+	VFIO_PCI_IO_WIDTH_2 = 2,
+	VFIO_PCI_IO_WIDTH_4 = 4,
+	VFIO_PCI_IO_WIDTH_8 = 8,
+};
+
 /* Will be exported for vfio pci drivers usage */
 int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev,
 				      unsigned int type, unsigned int subtype,

@@ -139,7 +146,8 @@ pci_ers_result_t vfio_pci_core_aer_err_d
 ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 			       void __iomem *io, char __user *buf,
 			       loff_t off, size_t count, size_t x_start,
-			       size_t x_end, bool iswrite);
+			       size_t x_end, bool iswrite,
+			       enum vfio_pci_io_width max_width);
 bool vfio_pci_core_range_intersect_range(loff_t buf_start, size_t buf_cnt,
 					 loff_t reg_start, size_t reg_cnt,
 					 loff_t *buf_offset,

@@ -278,15 +278,35 @@ static void damon_test_split_regions_of(
 	struct damon_target *t;
 	struct damon_region *r;
 
+	if (!c)
+		kunit_skip(test, "ctx alloc fail");
 	t = damon_new_target();
+	if (!t) {
+		damon_destroy_ctx(c);
+		kunit_skip(test, "target alloc fail");
+	}
 	r = damon_new_region(0, 22);
+	if (!r) {
+		damon_destroy_ctx(c);
+		damon_free_target(t);
+		kunit_skip(test, "region alloc fail");
+	}
 	damon_add_region(r, t);
 	damon_split_regions_of(t, 2, DAMON_MIN_REGION);
 	KUNIT_EXPECT_LE(test, damon_nr_regions(t), 2u);
 	damon_free_target(t);
 
 	t = damon_new_target();
+	if (!t) {
+		damon_destroy_ctx(c);
+		kunit_skip(test, "second target alloc fail");
+	}
 	r = damon_new_region(0, 220);
+	if (!r) {
+		damon_destroy_ctx(c);
+		damon_free_target(t);
+		kunit_skip(test, "second region alloc fail");
+	}
 	damon_add_region(r, t);
 	damon_split_regions_of(t, 4, DAMON_MIN_REGION);
 	KUNIT_EXPECT_LE(test, damon_nr_regions(t), 4u);