<?xml version='1.0' encoding='UTF-8'?>
<?xml-stylesheet href="/static/style.xsl" type="text/xsl"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
  <channel>
    <title>Most recent entries from all</title>
    <link>https://vulnerability.circl.lu</link>
    <description>Contains only the most 10 recent entries.</description>
    <docs>http://www.rssboard.org/rss-specification</docs>
    <generator>python-feedgen</generator>
    <language>en</language>
    <lastBuildDate>Fri, 09 Oct 2026 17:16:08 +0000</lastBuildDate>
    <item>
      <title>CVE-2026-98178 — drm/amdgpu: Skip KFD mapping clear before initialization</title>
      <link>https://vulnerability.circl.lu/vuln/cve-2026-98178</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; Linux&lt;/p&gt;
&lt;p&gt;In the Linux kernel, the following vulnerability has been resolved:&lt;/p&gt;
&lt;p&gt;drm/amdgpu: Skip KFD mapping clear before initialization&lt;/p&gt;
&lt;p&gt;amdgpu_amdkfd_clear_kfd_mapping() assumes that a non-NULL kfd_dev
has a fully populated node array. This is not true when KFD device
initialization fails after probe.&lt;/p&gt;
&lt;p&gt;For example, kgd2kfd_device_init() sets num_nodes before checking
PCIe atomics support. On Polaris systems without the required atomics,
it returns before allocating nodes[0], but the kfd_dev remains attached
to the amdgpu device. A later GPU reset then dereferences nodes[0]-&amp;gt;id.&lt;/p&gt;
&lt;p&gt;Require the authoritative KFD initialization flag before walking the
node array, matching the existing KFD reset and teardown paths.&lt;/p&gt;
&lt;p&gt;(cherry picked from commit 4ac1835823c47903fbb278bbf474773c46f59edc)&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; Linux&lt;/p&gt;
&lt;p&gt;In the Linux kernel, the following vulnerability has been resolved:&lt;/p&gt;
&lt;p&gt;drm/amdgpu: Skip KFD mapping clear before initialization&lt;/p&gt;
&lt;p&gt;amdgpu_amdkfd_clear_kfd_mapping() assumes that a non-NULL kfd_dev
has a fully populated node array. This is not true when KFD device
initialization fails after probe.&lt;/p&gt;
&lt;p&gt;For example, kgd2kfd_device_init() sets num_nodes before checking
PCIe atomics support. On Polaris systems without the required atomics,
it returns before allocating nodes[0], but the kfd_dev remains attached
to the amdgpu device. A later GPU reset then dereferences nodes[0]-&amp;gt;id.&lt;/p&gt;
&lt;p&gt;Require the authoritative KFD initialization flag before walking the
node array, matching the existing KFD reset and teardown paths.&lt;/p&gt;
&lt;p&gt;(cherry picked from commit 4ac1835823c47903fbb278bbf474773c46f59edc)&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://vulnerability.circl.lu/vuln/cve-2026-98178</guid>
    </item>
  </channel>
</rss>
