CVE-2026-93275: perf/x86/intel/pt: Fix stop/start with no update

CVE-2026-93275: perf/x86/intel/pt: Fix stop/start with no update

[Greg Kroah-Hartman]

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

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

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

perf/x86/intel/pt: Fix stop/start with no update

If pt_event_stop() is called without PERF_EF_UPDATE flag, then
perf_aux_output_end() is not called.  A subsequent call to pt_event_start()
will call perf_aux_output_begin() again which violates the rule against
nesting and triggers a WARNING in perf_aux_output_begin().

Originally, pt_event_stop() was never called without PERF_EF_UPDATE,
because the only code paths to do so are from event overflow, and Intel PT
does not do that.

However the introduction of group throttling by commit 9734e25fbf5ae
("perf: Fix the throttle logic for a group") meant that an Intel PT event
could be throttled if it was part of a group.  Throttling calls PMU
 ->stop() / ->start() callbacks without flags.

An example is when AUX area sampling is used. The following commands
hit the issue:

  echo 10000 > /proc/sys/kernel/perf_event_max_sample_rate

  perf record -F32000 --aux-sample -e '{intel_pt//u,cycles:u}' \
  -- bash -c 'for i in `seq 1 100000` ; do true ; done'

Use PERF_HES_UPTODATE to track whether perf_aux_output_begin() and
perf_aux_output_end() are balanced.  A cleared PERF_HES_UPTODATE bit
indicates that an AUX output context is still open.

Amend pt_event_start() / pt_event_stop() accordingly so that begin/end
stay balanced:

 - In non-snapshot mode, stop() always closes the buffer (the buffer may
   have run out of space, and that accounting is done by the update), so
   a following start() opens a fresh one as before.

 - In snapshot/overwrite mode, stop() without PERF_EF_UPDATE leaves the
   buffer open so that pt_event_snapshot_aux() can still copy from it,
   and start() then only re-enables tracing instead of calling
   perf_aux_output_begin() again.

Note that pt_event_del() calls pt_event_stop() with PERF_EF_UPDATE flag set
(as is required by the documentation), so a final call to
perf_aux_output_end() is assured.

The Linux kernel CVE team has assigned CVE-2026-93275 to this issue.


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

	Issue introduced in 4.1 with commit 52ca9ced3f70779589e6ecc329baffe69d8f5f7a and fixed in 6.12.110 with commit 9b919fb5512f256e9e0604faf960b2bb98aab454
	Issue introduced in 4.1 with commit 52ca9ced3f70779589e6ecc329baffe69d8f5f7a and fixed in 6.18.52 with commit cab5015ee3f25f789b4a368f2abfa65536576b78
	Issue introduced in 4.1 with commit 52ca9ced3f70779589e6ecc329baffe69d8f5f7a and fixed in 7.2.6 with commit 304844b5545f444d523286da8228a1cbc46ffffa
	Issue introduced in 4.1 with commit 52ca9ced3f70779589e6ecc329baffe69d8f5f7a and fixed in 7.3-rc1 with commit 2e17bf3a469a41457a3bc31b1f8fd66b6ce94a6d

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-2026-93275
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:
	arch/x86/events/intel/pt.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/9b919fb5512f256e9e0604faf960b2bb98aab454
	https://git.kernel.org/stable/c/cab5015ee3f25f789b4a368f2abfa65536576b78
	https://git.kernel.org/stable/c/304844b5545f444d523286da8228a1cbc46ffffa
	https://git.kernel.org/stable/c/2e17bf3a469a41457a3bc31b1f8fd66b6ce94a6d

Re: CVE-2026-93275: perf/x86/intel/pt: Fix stop/start with no update

[Greg KH]

On Fri, Oct 09, 2026 at 04:52:22PM +0800, huaweicloud wrote:
> Dear Linux Kernel CVE Team,
> 
> I would like to request an update to the affected version for
> CVE-2026-93275.
> 
> Although the patch carries a "Fixes:" tag pointing to commit
> 52ca9ced3f707 ("perf/x86/intel/pt: Add Intel PT PMU driver"), which was
> introduced in v4.1, the commit message itself explicitly notes that
> this buggy code path is only exposed after commit 9734e25fbf5ae ("perf:
> Fix the throttle logic for a group") was merged in v6.16.
> 
> Therefore, kernel versions prior to v6.16 that do not include commit
> 9734e25fbf5ae should be considered safe and unaffected by this CVE.
> Please consider updating the CVE record to avoid widespread false
> positives in older LTS branches.
> 
> Proposed Data Amendment:
> • Vulnerability ID: CVE-2026-93275
> • Current Affected Range: From v4.1 (commit 52ca9ced3f707) up to fixed version
> • Corrected Affected Range: From v6.16 (commit 9734e25fbf5ae) up to fixed version
> 
> Thank you for your time and verification.

I've fixed this up now, thanks.  In the future, you can always just send
a patch that adds an updated .vulnerable file for the specific record
and we will be glad to take that.

thanks,

greg k-h