Bug 1224851 (CVE-2021-47226) - VUL-0: CVE-2021-47226: kernel: x86/fpu: Invalidate FPU state after a failed XRSTOR from a user buffer
Summary: VUL-0: CVE-2021-47226: kernel: x86/fpu: Invalidate FPU state after a failed X...
Status: RESOLVED FIXED
Alias: CVE-2021-47226
Product: SUSE Security Incidents
Classification: Novell Products
Component: Incidents (show other bugs)
Version: unspecified
Hardware: Other Other
: P3 - Medium : Normal
Target Milestone: ---
Assignee: Security Team bot
QA Contact: Security Team bot
URL: https://smash.suse.de/issue/406852/
Whiteboard: CVSSv3.1:SUSE:CVE-2021-47226:4.7:(AV:...
Keywords:
Depends on:
Blocks:
 
Reported: 2024-05-22 08:10 UTC by SMASH SMASH
Modified: 2024-07-19 11:31 UTC (History)
4 users (show)

See Also:
Found By: Security Response Team
Services Priority:
Business Priority:
Blocker: ---
Marketing QA Status: ---
IT Deployment: ---


Attachments

Note You need to log in before you can comment on or make changes to this bug.
Description SMASH SMASH 2024-05-22 08:10:05 UTC
In the Linux kernel, the following vulnerability has been resolved:

x86/fpu: Invalidate FPU state after a failed XRSTOR from a user buffer

Both Intel and AMD consider it to be architecturally valid for XRSTOR to
fail with #PF but nonetheless change the register state.  The actual
conditions under which this might occur are unclear [1], but it seems
plausible that this might be triggered if one sibling thread unmaps a page
and invalidates the shared TLB while another sibling thread is executing
XRSTOR on the page in question.

__fpu__restore_sig() can execute XRSTOR while the hardware registers
are preserved on behalf of a different victim task (using the
fpu_fpregs_owner_ctx mechanism), and, in theory, XRSTOR could fail but
modify the registers.

If this happens, then there is a window in which __fpu__restore_sig()
could schedule out and the victim task could schedule back in without
reloading its own FPU registers. This would result in part of the FPU
state that __fpu__restore_sig() was attempting to load leaking into the
victim task's user-visible state.

Invalidate preserved FPU registers on XRSTOR failure to prevent this
situation from corrupting any state.

[1] Frequent readers of the errata lists might imagine "complex
    microarchitectural conditions".

References:
http://web.nvd.nist.gov/view/vuln/detail?vulnId=CVE-2021-47226
https://www.cve.org/CVERecord?id=CVE-2021-47226
https://git.kernel.org/stable/c/002665dcba4bbec8c82f0aeb4bd3f44334ed2c14
https://git.kernel.org/stable/c/a7748e021b9fb7739e3cb88449296539de0b6817
https://git.kernel.org/stable/c/d8778e393afa421f1f117471144f8ce6deb6953a
https://git.kernel.org/pub/scm/linux/security/vulns.git/plain/cve/published/2021/CVE-2021-47226.mbox
Comment 2 Jiri Slaby 2024-06-18 10:08:18 UTC
cve/linux-5.3-LTSS performs __fpu_invalidate_fpregs_state(fpu) unconditionally before the load. And makes the fpu state valid (by fpregs_mark_activate()) only if the load succeeded.

So d8778e393afa would be a nop in case of cve/linux-5.3-LTSS.