<?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://db.gcve.eu</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, 20 Nov 2026 20:53:10 +0000</lastBuildDate>
    <item>
      <title>CVE-2026-99797 — io_uring/cancel: drop sqd-&gt;lock while SQPOLL waits</title>
      <link>https://db.gcve.eu/vuln/cve-2026-99797</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;io_uring/cancel: drop sqd-&amp;gt;lock while SQPOLL waits&lt;/p&gt;
&lt;p&gt;An exiting SQPOLL thread calls io_uring_cancel_generic() with sqd-&amp;gt;lock
held, and keeps it across cond_resched() and the sleep until nothing is
in flight anymore. A zero-copy send notification can&amp;#39;t be canceled and
stays pending as long as the peer doesn&amp;#39;t read, so the lock is held for
as long as a user cares to. io_ring_exit_work() needs it to park the
thread, and so do IORING_REGISTER_IOWQ_AFF and IOWQ_MAX_WORKERS. With
64 such rings sharing the thread, every iou_exit slot sleeps on the lock
and no ring gets freed for anyone.&lt;/p&gt;
&lt;p&gt;Drop the lock around cond_resched() and the sleep, like the main loop of
the thread does. Each walk of ctx_list is still under one hold, and
nothing is kept across the unlock. The thread drops its io-wq, frees its
tctx and clears sqd-&amp;gt;thread under one hold after the loop, so whoever
holds the lock and finds sqd-&amp;gt;thread set can still use them.&lt;/p&gt;
&lt;p&gt;[axboe: adapted to the schedule_timeout() based loop]&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;io_uring/cancel: drop sqd-&amp;gt;lock while SQPOLL waits&lt;/p&gt;
&lt;p&gt;An exiting SQPOLL thread calls io_uring_cancel_generic() with sqd-&amp;gt;lock
held, and keeps it across cond_resched() and the sleep until nothing is
in flight anymore. A zero-copy send notification can&amp;#39;t be canceled and
stays pending as long as the peer doesn&amp;#39;t read, so the lock is held for
as long as a user cares to. io_ring_exit_work() needs it to park the
thread, and so do IORING_REGISTER_IOWQ_AFF and IOWQ_MAX_WORKERS. With
64 such rings sharing the thread, every iou_exit slot sleeps on the lock
and no ring gets freed for anyone.&lt;/p&gt;
&lt;p&gt;Drop the lock around cond_resched() and the sleep, like the main loop of
the thread does. Each walk of ctx_list is still under one hold, and
nothing is kept across the unlock. The thread drops its io-wq, frees its
tctx and clears sqd-&amp;gt;thread under one hold after the loop, so whoever
holds the lock and finds sqd-&amp;gt;thread set can still use them.&lt;/p&gt;
&lt;p&gt;[axboe: adapted to the schedule_timeout() based loop]&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://db.gcve.eu/vuln/cve-2026-99797</guid>
    </item>
  </channel>
</rss>
