<!DOCTYPE html><html><head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<p><br>
</p>
<div class="moz-cite-prefix">On 1/2/2025 6:06 PM, Emily Deng wrote:<br>
</div>
<blockquote type="cite" cite="mid:20250103000644.1398643-1-Emily.Deng@amd.com">
<pre wrap="" class="moz-quote-pre">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].
Signed-off-by: Emily Deng <a class="moz-txt-link-rfc2396E" href="mailto:Emily.Deng@amd.com"><Emily.Deng@amd.com></a>
---
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 4b275937d05e..5c96c2d425e3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -278,7 +278,7 @@ 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;</pre>
</blockquote>
I agree this part.<br>
<blockquote type="cite" cite="mid:20250103000644.1398643-1-Emily.Deng@amd.com">
<pre wrap="" class="moz-quote-pre">
struct amdgpu_device *adev = node->adev;
struct device *dev = adev->dev;
struct amdgpu_res_cursor cursor;
@@ -299,9 +299,6 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
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)) {
@@ -345,6 +342,9 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
} else {
j++;
}
+ 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]);</pre>
</blockquote>
<p>I think what current code misses here is that <span style="white-space: pre-wrap">migrate->dst[i] should match migrate->src[i]: </span><span style="white-space: pre-wrap">migrate->dst[i](vram page) got set for page that will be migrated from system ram, otherwise </span><span style="white-space: pre-wrap">migrate->dst[i] should be zero. Your change makes </span><span style="white-space: pre-wrap">migrates->dst[i] not set though its page has been migrated by svm_migrate_copy_memory_gart for the case that cpages != npages, because you set </span><span style="white-space: pre-wrap">migrate->dst[i] at end of loop and use 'continue' after migration.</span></p>
<p><span style="white-space: pre-wrap">The page migration happens at svm_migrate_copy_memory_gart, not </span><span style="white-space: pre-wrap">migrate_vma_pages that migrates struct page meta-data from source struct page to destination struct page and has mmu notification.</span></p>
<p><span style="white-space: pre-wrap">Regards</span></p>
<p><span style="white-space: pre-wrap">Xiaogang</span></p>
<blockquote type="cite" cite="mid:20250103000644.1398643-1-Emily.Deng@amd.com">
<pre wrap="" class="moz-quote-pre">
}
r = svm_migrate_copy_memory_gart(adev, src + i - j, dst + i - j, j,
</pre>
</blockquote>
</body>
</html>