Merge tag 'drm-xe-fixes-2025-12-30' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes

Core Changes:
- Ensure a SVM device memory allocation is idle before migration complete (Thomas)

Driver Changes:
- Fix a SVM debug printout (Thomas)
- Use READ_ONCE() / WRITE_ONCE() for g2h_fence (Jonathan)

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Thomas Hellstrom <thomas.hellstrom@linux.intel.com>
Link: https://patch.msgid.link/aVOTf6-whmkgrUuq@fedora

6 files changed, 99 insertions, 31 deletions

diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c
index 37d7cfbbb3e8..06c1bd8fc4d1 100644
--- a/drivers/gpu/drm/drm_pagemap.c
+++ b/drivers/gpu/drm/drm_pagemap.c
@@ -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_devmem *devmem_allocation,
 		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(struct vm_area_struct *vas,
 	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_ops_get);
  * @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_pagemap_devmem *devmem_allocation,
 	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);
 
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 4ac434ad216f..a5019d1e741b 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -104,7 +104,9 @@ static void g2h_fence_cancel(struct g2h_fence *g2h_fence)
 {
 	g2h_fence->cancel = true;
 	g2h_fence->fail = true;
-	g2h_fence->done = true;
+
+	/* WRITE_ONCE pairs with READ_ONCEs in guc_ct_send_recv. */
+	WRITE_ONCE(g2h_fence->done, true);
 }
 
 static bool g2h_fence_needs_alloc(struct g2h_fence *g2h_fence)
@@ -1203,10 +1205,13 @@ retry_same_fence:
 		return ret;
 	}
 
-	ret = wait_event_timeout(ct->g2h_fence_wq, g2h_fence.done, HZ);
+	/* READ_ONCEs pairs with WRITE_ONCEs in parse_g2h_response
+	 * and g2h_fence_cancel.
+	 */
+	ret = wait_event_timeout(ct->g2h_fence_wq, READ_ONCE(g2h_fence.done), HZ);
 	if (!ret) {
 		LNL_FLUSH_WORK(&ct->g2h_worker);
-		if (g2h_fence.done) {
+		if (READ_ONCE(g2h_fence.done)) {
 			xe_gt_warn(gt, "G2H fence %u, action %04x, done\n",
 				   g2h_fence.seqno, action[0]);
 			ret = 1;
@@ -1454,7 +1459,8 @@ static int parse_g2h_response(struct xe_guc_ct *ct, u32 *msg, u32 len)
 
 	g2h_release_space(ct, GUC_CTB_HXG_MSG_MAX_LEN);
 
-	g2h_fence->done = true;
+	/* WRITE_ONCE pairs with READ_ONCEs in guc_ct_send_recv. */
+	WRITE_ONCE(g2h_fence->done, true);
 	smp_mb();
 
 	wake_up_all(&ct->g2h_fence_wq);
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 2184af413b91..5a95b08a4723 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -2062,6 +2062,7 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m,
 					 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;
@@ -2150,6 +2151,14 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m,
 
 	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);
@@ -2175,6 +2184,8 @@ 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
  *
@@ -2184,10 +2195,11 @@ 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);
 }
 
 /**
@@ -2196,6 +2208,8 @@ struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m,
  * @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
  *
@@ -2205,10 +2219,11 @@ struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m,
 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,
@@ -2384,7 +2399,7 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 		__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)) {
diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h
index 260e298e5dd7..b76441f062b4 100644
--- a/drivers/gpu/drm/xe/xe_migrate.h
+++ b/drivers/gpu/drm/xe/xe_migrate.h
@@ -116,12 +116,14 @@ 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,
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 55c5a0eb82e1..f97e0af6a9b0 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -476,7 +476,8 @@ static void xe_svm_copy_us_stats_incr(struct xe_gt *gt,
 
 static int xe_svm_copy(struct page **pages,
 		       struct drm_pagemap_addr *pagemap_addr,
-		       unsigned long npages, const enum xe_svm_copy_dir dir)
+		       unsigned long npages, const enum xe_svm_copy_dir dir,
+		       struct dma_fence *pre_migrate_fence)
 {
 	struct xe_vram_region *vr = NULL;
 	struct xe_gt *gt = NULL;
@@ -565,7 +566,8 @@ static int xe_svm_copy(struct page **pages,
 					__fence = xe_migrate_from_vram(vr->migrate,
 								       i - pos + incr,
 								       vram_addr,
-								       &pagemap_addr[pos]);
+								       &pagemap_addr[pos],
+								       pre_migrate_fence);
 				} else {
 					vm_dbg(&xe->drm,
 					       "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%ld",
@@ -574,13 +576,14 @@ static int xe_svm_copy(struct page **pages,
 					__fence = xe_migrate_to_vram(vr->migrate,
 								     i - pos + incr,
 								     &pagemap_addr[pos],
-								     vram_addr);
+								     vram_addr,
+								     pre_migrate_fence);
 				}
 				if (IS_ERR(__fence)) {
 					err = PTR_ERR(__fence);
 					goto err_out;
 				}
-
+				pre_migrate_fence = NULL;
 				dma_fence_put(fence);
 				fence = __fence;
 			}
@@ -603,20 +606,22 @@ static int xe_svm_copy(struct page **pages,
 					       vram_addr, (u64)pagemap_addr[pos].addr, 1);
 					__fence = xe_migrate_from_vram(vr->migrate, 1,
 								       vram_addr,
-								       &pagemap_addr[pos]);
+								       &pagemap_addr[pos],
+								       pre_migrate_fence);
 				} else {
 					vm_dbg(&xe->drm,
 					       "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%d",
 					       (u64)pagemap_addr[pos].addr, vram_addr, 1);
 					__fence = xe_migrate_to_vram(vr->migrate, 1,
 								     &pagemap_addr[pos],
-								     vram_addr);
+								     vram_addr,
+								     pre_migrate_fence);
 				}
 				if (IS_ERR(__fence)) {
 					err = PTR_ERR(__fence);
 					goto err_out;
 				}
-
+				pre_migrate_fence = NULL;
 				dma_fence_put(fence);
 				fence = __fence;
 			}
@@ -629,6 +634,8 @@ err_out:
 		dma_fence_wait(fence, false);
 		dma_fence_put(fence);
 	}
+	if (pre_migrate_fence)
+		dma_fence_wait(pre_migrate_fence, false);
 
 	/*
 	 * XXX: We can't derive the GT here (or anywhere in this functions, but
@@ -645,16 +652,20 @@ err_out:
 
 static int xe_svm_copy_to_devmem(struct page **pages,
 				 struct drm_pagemap_addr *pagemap_addr,
-				 unsigned long npages)
+				 unsigned long npages,
+				 struct dma_fence *pre_migrate_fence)
 {
-	return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_VRAM);
+	return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_VRAM,
+			   pre_migrate_fence);
 }
 
 static int xe_svm_copy_to_ram(struct page **pages,
 			      struct drm_pagemap_addr *pagemap_addr,
-			      unsigned long npages)
+			      unsigned long npages,
+			      struct dma_fence *pre_migrate_fence)
 {
-	return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_SRAM);
+	return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_SRAM,
+			   pre_migrate_fence);
 }
 
 static struct xe_bo *to_xe_bo(struct drm_pagemap_devmem *devmem_allocation)
@@ -667,6 +678,7 @@ static void xe_svm_devmem_release(struct drm_pagemap_devmem *devmem_allocation)
 	struct xe_bo *bo = to_xe_bo(devmem_allocation);
 	struct xe_device *xe = xe_bo_device(bo);
 
+	dma_fence_put(devmem_allocation->pre_migrate_fence);
 	xe_bo_put_async(bo);
 	xe_pm_runtime_put(xe);
 }
@@ -861,6 +873,7 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap,
 				      unsigned long timeslice_ms)
 {
 	struct xe_vram_region *vr = container_of(dpagemap, typeof(*vr), dpagemap);
+	struct dma_fence *pre_migrate_fence = NULL;
 	struct xe_device *xe = vr->xe;
 	struct device *dev = xe->drm.dev;
 	struct drm_buddy_block *block;
@@ -887,8 +900,20 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap,
 			break;
 		}
 
+		/* Ensure that any clearing or async eviction will complete before migration. */
+		if (!dma_resv_test_signaled(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL)) {
+			err = dma_resv_get_singleton(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL,
+						     &pre_migrate_fence);
+			if (err)
+				dma_resv_wait_timeout(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL,
+						      false, MAX_SCHEDULE_TIMEOUT);
+			else if (pre_migrate_fence)
+				dma_fence_enable_sw_signaling(pre_migrate_fence);
+		}
+
 		drm_pagemap_devmem_init(&bo->devmem_allocation, dev, mm,
-					&dpagemap_devmem_ops, dpagemap, end - start);
+					&dpagemap_devmem_ops, dpagemap, end - start,
+					pre_migrate_fence);
 
 		blocks = &to_xe_ttm_vram_mgr_resource(bo->ttm.resource)->blocks;
 		list_for_each_entry(block, blocks, link)
@@ -941,7 +966,7 @@ bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range, struct xe_vm
 	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;
 	}
 
diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h
index f6e7e234c089..70a7991f784f 100644
--- a/include/drm/drm_pagemap.h
+++ b/include/drm/drm_pagemap.h
@@ -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_dpagemap(struct page *page);
 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,