All of lore.kernel.org
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-cve-announce@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@kernel.org>
Subject: CVE-2026-31406: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
Date: Mon,  6 Apr 2026 09:38:29 +0200	[thread overview]
Message-ID: <2026040628-CVE-2026-31406-e2f3@gregkh> (raw)

From: Greg Kroah-Hartman <gregkh@kernel.org>

Description
===========

In the Linux kernel, the following vulnerability has been resolved:

xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()

After cancel_delayed_work_sync() is called from
xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining
states via __xfrm_state_delete(), which calls
xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work.

The following is a simple race scenario:

           cpu0                             cpu1

cleanup_net() [Round 1]
  ops_undo_list()
    xfrm_net_exit()
      xfrm_nat_keepalive_net_fini()
        cancel_delayed_work_sync(nat_keepalive_work);
      xfrm_state_fini()
        xfrm_state_flush()
          xfrm_state_delete(x)
            __xfrm_state_delete(x)
              xfrm_nat_keepalive_state_updated(x)
                schedule_delayed_work(nat_keepalive_work);
  rcu_barrier();
  net_complete_free();
  net_passive_dec(net);
    llist_add(&net->defer_free_list, &defer_free_list);

cleanup_net() [Round 2]
  rcu_barrier();
  net_complete_free()
    kmem_cache_free(net_cachep, net);
                                     nat_keepalive_work()
                                       // on freed net

To prevent this, cancel_delayed_work_sync() is replaced with
disable_delayed_work_sync().

The Linux kernel CVE team has assigned CVE-2026-31406 to this issue.


Affected and fixed versions
===========================

	Issue introduced in 6.11 with commit f531d13bdfe3f4f084aaa8acae2cb0f02295f5ae and fixed in 6.12.80 with commit 32d0f44c2f14d60fe8e920e69a28c11051543ec1
	Issue introduced in 6.11 with commit f531d13bdfe3f4f084aaa8acae2cb0f02295f5ae and fixed in 6.18.21 with commit 2255ed6adbc3100d2c4a83abd9d0396d04b87792
	Issue introduced in 6.11 with commit f531d13bdfe3f4f084aaa8acae2cb0f02295f5ae and fixed in 6.19.11 with commit 21f2fc49ca6faa393c31da33b8a4e6c41fc84c13
	Issue introduced in 6.11 with commit f531d13bdfe3f4f084aaa8acae2cb0f02295f5ae and fixed in 7.0-rc6 with commit daf8e3b253aa760ff9e96c7768a464bc1d6b3c90

Please see https://www.kernel.org for a full list of currently supported
kernel versions by the kernel community.

Unaffected versions might change over time as fixes are backported to
older supported kernel versions.  The official CVE entry at
	https://cve.org/CVERecord/?id=CVE-2026-31406
will be updated if fixes are backported, please check that for the most
up to date information about this issue.


Affected files
==============

The file(s) affected by this issue are:
	net/xfrm/xfrm_nat_keepalive.c


Mitigation
==========

The Linux kernel CVE team recommends that you update to the latest
stable kernel version for this, and many other bugfixes.  Individual
changes are never tested alone, but rather are part of a larger kernel
release.  Cherry-picking individual commits is not recommended or
supported by the Linux kernel community at all.  If however, updating to
the latest release is impossible, the individual changes to resolve this
issue can be found at these commits:
	https://git.kernel.org/stable/c/32d0f44c2f14d60fe8e920e69a28c11051543ec1
	https://git.kernel.org/stable/c/2255ed6adbc3100d2c4a83abd9d0396d04b87792
	https://git.kernel.org/stable/c/21f2fc49ca6faa393c31da33b8a4e6c41fc84c13
	https://git.kernel.org/stable/c/daf8e3b253aa760ff9e96c7768a464bc1d6b3c90

                 reply	other threads:[~2026-04-06  7:38 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=2026040628-CVE-2026-31406-e2f3@gregkh \
    --to=gregkh@linuxfoundation.org \
    --cc=cve@kernel.org \
    --cc=gregkh@kernel.org \
    --cc=linux-cve-announce@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.