Skip to contentSkip to conversation

FAILED: patch "[PATCH] drm/amdkfd: Fix partial migration bugs" failed to apply to 5.17-stable tree

PATCH [email protected] 1 participant 1 message Jun 13, 2022

Subsystems (4)
Stable branch DRM drivers Radeon and amdgpu DRM drivers AMD KFD
lore
Share & tools
lore

[email protected]

author maintainer
#0 lore raw

The patch below does not apply to the 5.17-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 88467db6e2f46a2e79b1b67ce6873c284e4cf417 Mon Sep 17 00:00:00 2001
From: Philip Yang <[email protected]>
Date: Fri, 3 Jun 2022 09:19:34 -0400
Subject: [PATCH] drm/amdkfd: Fix partial migration bugs

Migration range from system memory to VRAM, if system page can not be locked or unmapped, we do partial migration and leave some pages in system memory. Several bugs found to copy pages and update GPU mapping for this situation:

1. copy to vram should use migrate->npage which is total pages of range as npages, not migrate->cpages which is number of pages can be migrated.

2. After partial copy, set VRAM res cursor as j + 1, j is number of system pages copied plus 1 page to skip copy.

3. copy to ram, should collect all continuous VRAM pages and copy together.

4. Call amdgpu_vm_update_range, should pass in offset as bytes, not as number of pages.

Signed-off-by Philip Yang <[email protected]>
Reviewed-by Felix Kuehling <[email protected]>
Signed-off-by Alex Deucher <[email protected]>
Cc [email protected]
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +3 -3
index 997650d597ec..e44376c2ecdc 100644
@@ -296,7 +296,7 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 			 struct migrate_vma *migrate, struct dma_fence **mfence,
 			 dma_addr_t *scratch)
 {
-	uint64_t npages = migrate->cpages;
+	uint64_t npages = migrate->npages;
 	struct device *dev = adev->dev;
 	struct amdgpu_res_cursor cursor;
 	dma_addr_t *src;

@@ -344,7 +344,7 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 						mfence);
 				if (r)
 					goto out_free_vram_pages;
-				amdgpu_res_next(&cursor, j << PAGE_SHIFT);
+				amdgpu_res_next(&cursor, (j + 1) << PAGE_SHIFT);
 				j = 0;
 			} else {
 				amdgpu_res_next(&cursor, PAGE_SIZE);

@@ -590,7 +590,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 			continue;
 		}
 		src[i] = svm_migrate_addr(adev, spage);
-		if (i > 0 && src[i] != src[i - 1] + PAGE_SIZE) {
+		if (j > 0 && src[i] != src[i - 1] + PAGE_SIZE) {
 			r = svm_migrate_copy_memory_gart(adev, dst + i - j,
 							 src + i - j, j,
 							 FROM_VRAM_TO_RAM,
drivers/gpu/drm/amd/amdkfd/kfd_svm.c +1 -1
index 3bd0f1a670bb..7b332246eda3 100644
@@ -1295,7 +1295,7 @@ svm_range_map_to_gpu(struct kfd_process_device *pdd, struct svm_range *prange,
 		r = amdgpu_vm_update_range(adev, vm, false, false, flush_tlb, NULL,
 					   last_start, prange->start + i,
 					   pte_flags,
-					   last_start - prange->start,
+					   (last_start - prange->start) << PAGE_SHIFT,
 					   bo_adev ? bo_adev->vm_manager.vram_base_offset : 0,
 					   NULL, dma_addr, &vm->last_update);