<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:DengXian;
panose-1:2 1 6 0 3 1 1 1 1 1;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:Aptos;}
@font-face
{font-family:"\@DengXian";
panose-1:2 1 6 0 3 1 1 1 1 1;}
@font-face
{font-family:Consolas;
panose-1:2 11 6 9 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
font-size:12.0pt;
font-family:"Aptos",sans-serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
pre
{mso-style-priority:99;
mso-style-link:"HTML Preformatted Char";
margin:0in;
font-size:10.0pt;
font-family:"Courier New";}
span.HTMLPreformattedChar
{mso-style-name:"HTML Preformatted Char";
mso-style-priority:99;
mso-style-link:"HTML Preformatted";
font-family:Consolas;}
span.EmailStyle21
{mso-style-type:personal-reply;
font-family:"Arial",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;
mso-ligatures:none;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="EN-US" link="blue" vlink="purple" style="word-wrap:break-word">
<p style="font-family:Calibri;font-size:10pt;color:#0000FF;margin:5pt;font-style:normal;font-weight:normal;text-decoration:none;" align="Left">
[AMD Official Use Only - AMD Internal Distribution Only]<br>
</p>
<br>
<div>
<div class="WordSection1">
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif"><o:p> </o:p></span></p>
<div style="border:none;border-left:solid blue 1.5pt;padding:0in 0in 0in 4.0pt">
<div>
<div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0in 0in 0in">
<p class="MsoNormal"><b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif">From:</span></b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"> Yang, Philip <Philip.Yang@amd.com>
<br>
<b>Sent:</b> Tuesday, January 7, 2025 7:51 AM<br>
<b>To:</b> Deng, Emily <Emily.Deng@amd.com>; amd-gfx@lists.freedesktop.org<br>
<b>Subject:</b> Re: [PATCH] drm/amdkfd: Fix partial migrate issue<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
<p><o:p> </o:p></p>
<div>
<p class="MsoNormal">On 2025-01-02 19:06, Emily Deng wrote:<o:p></o:p></p>
</div>
<blockquote style="margin-top:5.0pt;margin-bottom:5.0pt">
<pre>For partial migrate from ram to vram, the migrate->cpages is not<o:p></o:p></pre>
<pre>equal to migrate->npages, should use migrate->npages to check all needed<o:p></o:p></pre>
<pre>migrate pages which could be copied or not.<o:p></o:p></pre>
<pre><o:p> </o:p></pre>
<pre>And only need to set those pages could be migrated to migrate->dst[i], or<o:p></o:p></pre>
<pre>the migrate_vma_pages will migrate the wrong pages based on the migrate->dst[i].<o:p></o:p></pre>
<pre><o:p> </o:p></pre>
<pre>Signed-off-by: Emily Deng <a href="mailto:Emily.Deng@amd.com"><Emily.Deng@amd.com></a><o:p></o:p></pre>
<pre>---<o:p></o:p></pre>
<pre> drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 8 ++++----<o:p></o:p></pre>
<pre> 1 file changed, 4 insertions(+), 4 deletions(-)<o:p></o:p></pre>
<pre><o:p> </o:p></pre>
<pre>diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c<o:p></o:p></pre>
<pre>index 4b275937d05e..5c96c2d425e3 100644<o:p></o:p></pre>
<pre>--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c<o:p></o:p></pre>
<pre>+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c<o:p></o:p></pre>
<pre>@@ -278,7 +278,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,<o:p></o:p></pre>
<pre> struct migrate_vma *migrate, struct dma_fence **mfence,<o:p></o:p></pre>
<pre> dma_addr_t *scratch, uint64_t ttm_res_offset)<o:p></o:p></pre>
<pre> {<o:p></o:p></pre>
<pre>- uint64_t npages = migrate->cpages;<o:p></o:p></pre>
<pre>+ uint64_t npages = migrate->npages;<o:p></o:p></pre>
</blockquote>
<p>As partial migration size is based on prange granularity, by default 2MB, maybe always migrate->cpages equal to migrate->npages, that's why we didn't trigger this bug. Wondering how do you catch this bug? This bug will leak svm_bo too, as svm_migrate_get_vram_page
reference counter is incorrect.<o:p></o:p></p>
<blockquote style="margin-top:5.0pt;margin-bottom:5.0pt">
<pre><o:p> </o:p></pre>
<pre> struct amdgpu_device *adev = node->adev;<o:p></o:p></pre>
<pre> struct device *dev = adev->dev;<o:p></o:p></pre>
<pre> struct amdgpu_res_cursor cursor;<o:p></o:p></pre>
<pre>@@ -299,9 +299,6 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,<o:p></o:p></pre>
<pre> struct page *spage;<o:p></o:p></pre>
<pre> <o:p></o:p></pre>
<pre> dst[i] = cursor.start + (j << PAGE_SHIFT);<o:p></o:p></pre>
<pre>- migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);<o:p></o:p></pre>
<pre>- svm_migrate_get_vram_page(prange, migrate->dst[i]);<o:p></o:p></pre>
<pre>- migrate->dst[i] = migrate_pfn(migrate->dst[i]);<o:p></o:p></pre>
<pre> <o:p></o:p></pre>
<pre> spage = migrate_pfn_to_page(migrate->src[i]);<o:p></o:p></pre>
<pre> if (spage && !is_zone_device_page(spage)) {<o:p></o:p></pre>
<pre>@@ -345,6 +342,9 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,<o:p></o:p></pre>
<pre> } else {<o:p></o:p></pre>
<pre> j++;<o:p></o:p></pre>
<pre> }<o:p></o:p></pre>
<pre>+ migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);<o:p></o:p></pre>
<pre>+ svm_migrate_get_vram_page(prange, migrate->dst[i]);<o:p></o:p></pre>
<pre>+ migrate->dst[i] = migrate_pfn(migrate->dst[i]);<o:p></o:p></pre>
</blockquote>
<p>This should move forward, to handle the corner case to migrate 1 page to the last page of VRAM res cursor.<o:p></o:p></p>
<p><span style="font-size:11.0pt;font-family:"Arial",sans-serif">Sorry, don’t understand what is the corner case? And the place you put has not much different with mine, as it doesn’t have any jump or continue in the code between your<o:p></o:p></span></p>
<p style="margin-left:11.0pt"><span style="font-size:11.0pt;font-family:"Arial",sans-serif">code place and mine. But it has “if (r) goto out_free_vram_pages;” to handle the error case. For error case, I think the
</span>migrate->dst[i] also need to be set to null.<span style="font-size:11.0pt;font-family:"Arial",sans-serif"><o:p></o:p></span></p>
<p>Please check this change, to add mpages accounting to break the loop earlier. <o:p>
</o:p></p>
<p><span style="font-size:11.0pt;font-family:"Arial",sans-serif">Good suggestion, I will add mpages in change.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;mso-ligatures:standardcontextual">Emily Deng<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;mso-ligatures:standardcontextual">Best Wishes<o:p></o:p></span></p>
</div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Arial",sans-serif"><o:p> </o:p></span></p>
<p><span style="font-size:11.0pt;font-family:"Arial",sans-serif"><o:p> </o:p></span></p>
<p style="margin-bottom:12.0pt">- uint64_t npages = migrate->cpages;<br>
+ uint64_t npages = migrate->npages;<br>
struct amdgpu_device *adev = node->adev;<br>
struct device *dev = adev->dev;<br>
struct amdgpu_res_cursor cursor;<br>
+ uint64_t mpages = 0;<br>
dma_addr_t *src;<br>
uint64_t *dst;<br>
uint64_t i, j;<br>
@@ -295,14 +296,9 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,<br>
<br>
amdgpu_res_first(prange->ttm_res, ttm_res_offset,<br>
npages << PAGE_SHIFT, &cursor);<br>
- for (i = j = 0; i < npages; i++) {<br>
+ for (i = j = 0; i < npages && mpages < migrate->cpages; i++) {<br>
struct page *spage;<br>
<br>
- dst[i] = cursor.start + (j << PAGE_SHIFT);<br>
- migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);<br>
- svm_migrate_get_vram_page(prange, migrate->dst[i]);<br>
- migrate->dst[i] = migrate_pfn(migrate->dst[i]);<br>
-<br>
spage = migrate_pfn_to_page(migrate->src[i]);<br>
if (spage && !is_zone_device_page(spage)) {<br>
src[i] = dma_map_page(dev, spage, 0, PAGE_SIZE,<br>
@@ -322,6 +318,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,<br>
mfence);<br>
if (r)<br>
goto out_free_vram_pages;<br>
+ mpages += j;<br>
amdgpu_res_next(&cursor, (j + 1) << PAGE_SHIFT);<br>
j = 0;<br>
} else {<br>
@@ -333,6 +330,11 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,<br>
pr_debug_ratelimited("dma mapping src to 0x%llx, pfn 0x%lx\n",<br>
src[i] >> PAGE_SHIFT, page_to_pfn(spage));<br>
<br>
+ dst[i] = cursor.start + (j << PAGE_SHIFT);<br>
+ migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);<br>
+ svm_migrate_get_vram_page(prange, migrate->dst[i]);<br>
+ migrate->dst[i] = migrate_pfn(migrate->dst[i]);<br>
+<br>
if (j >= (cursor.size >> PAGE_SHIFT) - 1 && i < npages - 1) {<br>
r = svm_migrate_copy_memory_gart(adev, src + i - j,<br>
dst + i - j, j + 1,<br>
@@ -340,6 +342,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,<br>
mfence);<br>
if (r)<br>
goto out_free_vram_pages;<br>
+ mpages += j + 1;<br>
amdgpu_res_next(&cursor, (j + 1) * PAGE_SIZE);<br>
j = 0;<br>
} else {<br>
(END)<br>
@@ -322,6 +318,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,<br>
mfence);<br>
if (r)<br>
goto out_free_vram_pages;<br>
+ mpages += j;<br>
amdgpu_res_next(&cursor, (j + 1) << PAGE_SHIFT);<br>
j = 0;<br>
} else {<br>
@@ -333,6 +330,11 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,<br>
pr_debug_ratelimited("dma mapping src to 0x%llx, pfn 0x%lx\n",<br>
src[i] >> PAGE_SHIFT, page_to_pfn(spage));<br>
<br>
+ dst[i] = cursor.start + (j << PAGE_SHIFT);<br>
+ migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);<br>
+ svm_migrate_get_vram_page(prange, migrate->dst[i]);<br>
+ migrate->dst[i] = migrate_pfn(migrate->dst[i]);<br>
+<br>
if (j >= (cursor.size >> PAGE_SHIFT) - 1 && i < npages - 1) {<br>
r = svm_migrate_copy_memory_gart(adev, src + i - j,<br>
dst + i - j, j + 1,<br>
@@ -340,6 +342,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,<br>
mfence);<br>
if (r)<br>
goto out_free_vram_pages;<br>
+ mpages += j + 1;<br>
amdgpu_res_next(&cursor, (j + 1) * PAGE_SIZE);<br>
j = 0;<br>
} else {<o:p></o:p></p>
<blockquote style="margin-top:5.0pt;margin-bottom:5.0pt">
<pre><o:p> </o:p></pre>
<pre> }<o:p></o:p></pre>
<pre> <o:p></o:p></pre>
<pre> r = svm_migrate_copy_memory_gart(adev, src + i - j, dst + i - j, j,<o:p></o:p></pre>
</blockquote>
</div>
</div>
</body>
</html>