Re: [PATCH v3] drm/amdkfd: Fix partial migrate issue

[Philip Yang]

On 2025-01-08 08:19, Emily Deng wrote:

For partial migrate from ram to vram, the migrate->cpages is not
equal to migrate->npages, should use migrate->npages to check all needed
migrate pages which could be copied or not.

And only need to set those pages could be migrated to migrate->dst[i], or
the migrate_vma_pages will migrate the wrong pages based on the migrate->dst[i].

v2:
Add mpages to break the loop earlier.

v3:
Uses MIGRATE_PFN_MIGRATE to identify whether page could be migrated.

Signed-off-by: Emily Deng <emily.d...@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index eacfeb32f35d..b671d12c32f6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -278,10 +278,11 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
 			 struct migrate_vma *migrate, struct dma_fence **mfence,
 			 dma_addr_t *scratch, uint64_t ttm_res_offset)
 {
-	uint64_t npages = migrate->cpages;
+	uint64_t npages = migrate->npages;
 	struct amdgpu_device *adev = node->adev;
 	struct device *dev = adev->dev;
 	struct amdgpu_res_cursor cursor;
+	uint64_t mpages = 0;
 	dma_addr_t *src;
 	uint64_t *dst;
 	uint64_t i, j;
@@ -295,14 +296,17 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
 
 	amdgpu_res_first(prange->ttm_res, ttm_res_offset,
 			 npages << PAGE_SHIFT, &cursor);
-	for (i = j = 0; i < npages; i++) {
+	for (i = j = 0; (i < npages) && (mpages < migrate->cpages); i++) {
 		struct page *spage;
 
 		dst[i] = cursor.start + (j << PAGE_SHIFT);
-		migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);
-		svm_migrate_get_vram_page(prange, migrate->dst[i]);
-		migrate->dst[i] = migrate_pfn(migrate->dst[i]);
 
+		if (migrate->src[i] & MIGRATE_PFN_MIGRATE) {

This should check flag MIGRATE_PFN_VALID, same as migrate_pfn_to_page, so move this inside below if (spage....)

+			migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);
+			svm_migrate_get_vram_page(prange, migrate->dst[i]);
+			migrate->dst[i] = migrate_pfn(migrate->dst[i]);
+			mpages++;

increase mpages here is good, simpler than increasing mpages after each copy, as the last sdma copy outside loop will handle the remaining pages.

+		}
 		spage = migrate_pfn_to_page(migrate->src[i]);
 		if (spage && !is_zone_device_page(spage)) {
 			src[i] = dma_map_page(dev, spage, 0, PAGE_SIZE,

out_free_vram_pages path error handling need fix to put, unlock all migrated pages too, please check changes attached, I only compile but didn't run test with the change.

Regards,

Philip

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 4b275937d05e..5456a3666da3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -278,10 +278,11 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
 			 struct migrate_vma *migrate, struct dma_fence **mfence,
 			 dma_addr_t *scratch, uint64_t ttm_res_offset)
 {
-	uint64_t npages = migrate->cpages;
+	uint64_t npages = migrate->npages;
 	struct amdgpu_device *adev = node->adev;
 	struct device *dev = adev->dev;
 	struct amdgpu_res_cursor cursor;
+	uint64_t mpages = 0;
 	dma_addr_t *src;
 	uint64_t *dst;
 	uint64_t i, j;
@@ -295,14 +296,9 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
 
 	amdgpu_res_first(prange->ttm_res, ttm_res_offset,
 			 npages << PAGE_SHIFT, &cursor);
-	for (i = j = 0; i < npages; i++) {
+	for (i = j = 0; i < npages && mpages < migrate->cpages; i++) {
 		struct page *spage;
 
-		dst[i] = cursor.start + (j << PAGE_SHIFT);
-		migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);
-		svm_migrate_get_vram_page(prange, migrate->dst[i]);
-		migrate->dst[i] = migrate_pfn(migrate->dst[i]);
-
 		spage = migrate_pfn_to_page(migrate->src[i]);
 		if (spage && !is_zone_device_page(spage)) {
 			src[i] = dma_map_page(dev, spage, 0, PAGE_SIZE,
@@ -313,6 +309,12 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
 					__func__, r);
 				goto out_free_vram_pages;
 			}
+
+			dst[i] = cursor.start + (j << PAGE_SHIFT);
+			migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);
+			svm_migrate_get_vram_page(prange, migrate->dst[i]);
+			migrate->dst[i] = migrate_pfn(migrate->dst[i]);
+			mpages++;
 		} else {
 			if (j) {
 				r = svm_migrate_copy_memory_gart(
@@ -353,9 +355,13 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
 out_free_vram_pages:
 	if (r) {
 		pr_debug("failed %d to copy memory to vram\n", r);
-		while (i--) {
+
+		for (i = 0; i < npages && mpages; i++) {
+			if (!dst[i])
+				continue;
 			svm_migrate_put_vram_page(adev, dst[i]);
 			migrate->dst[i] = 0;
+			mpages--;
 		}
 	}