x86/mm: Eliminate window where TLB flushes may be inadvertently skipped
Summary
| CVE | CVE-2025-37964 |
|---|---|
| State | PUBLISHED |
| Assigner | Linux |
| Source Priority | CVE Program / NVD first with legacy fallback |
| Published | 2025-05-20 16:15:34 UTC |
| Updated | 2026-07-14 13:17:34 UTC |
| Description | In the Linux kernel, the following vulnerability has been resolved: x86/mm: Eliminate window where TLB flushes may be inadvertently skipped tl;dr: There is a window in the mm switching code where the new CR3 is set and the CPU should be getting TLB flushes for the new mm. But should_flush_tlb() has a bug and suppresses the flush. Fix it by widening the window where should_flush_tlb() sends an IPI. Long Version: === History === There were a few things leading up to this. First, updating mm_cpumask() was observed to be too expensive, so it was made lazier. But being lazy caused too many unnecessary IPIs to CPUs due to the now-lazy mm_cpumask(). So code was added to cull mm_cpumask() periodically[2]. But that culling was a bit too aggressive and skipped sending TLB flushes to CPUs that need them. So here we are again. === Problem === The too-aggressive code in should_flush_tlb() strikes in this window: // Turn on IPIs for this CPU/mm combination, but only // if should_flush_tlb() agrees: cpumask_set_cpu(cpu, mm_cpumask(next)); next_tlb_gen = atomic64_read(&next->context.tlb_gen); choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush); load_new_mm_cr3(need_flush); // ^ After 'need_flush' is set to false, IPIs *MUST* // be sent to this CPU and not be ignored. this_cpu_write(cpu_tlbstate.loaded_mm, next); // ^ Not until this point does should_flush_tlb() // become true! should_flush_tlb() will suppress TLB flushes between load_new_mm_cr3() and writing to 'loaded_mm', which is a window where they should not be suppressed. Whoops. === Solution === Thankfully, the fuzzy "just about to write CR3" window is already marked with loaded_mm==LOADED_MM_SWITCHING. Simply checking for that state in should_flush_tlb() is sufficient to ensure that the CPU is targeted with an IPI. This will cause more TLB flush IPIs. But the window is relatively small and I do not expect this to cause any kind of measurable performance impact. Update the comment where LOADED_MM_SWITCHING is written since it grew yet another user. Peter Z also raised a concern that should_flush_tlb() might not observe 'loaded_mm' and 'is_lazy' in the same order that switch_mm_irqs_off() writes them. Add a barrier to ensure that they are observed in the order they are written. |
Risk And Classification
Primary CVSS: v3.1 5.5 MEDIUM from [email protected]
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Problem Types: NVD-CWE-noinfo
CVSS v3.1 Breakdown
Attack Vector
LocalAttack Complexity
LowPrivileges Required
LowUser Interaction
NoneScope
UnchangedConfidentiality
NoneIntegrity
NoneAvailability
HighCVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
NVD Known Affected Configurations (CPE 2.3)
| Type | Vendor | Product | Version | Update | Edition | Language |
|---|---|---|---|---|---|---|
| Operating System | Linux | Linux Kernel | All | All | All | All |
Vendor Declared Affected Products
| Source | Vendor | Product | Version | Platforms |
|---|---|---|---|---|
| CNA | Linux | Linux | affected 848b5815177582de0e1d0118725378e0fbadca20 12f703811af043d32b1c8a30001b2fa04d5cd0ac git | Not specified |
| CNA | Linux | Linux | affected b47002ed65ade940839b7f439ff4a194e7d5ec28 02ad4ce144bd27f71f583f667fdf3b3ba0753477 git | Not specified |
| CNA | Linux | Linux | affected a04fe3bfc71e28009e20357b79df1e8ef7c9d600 d41072906abec8bb8e01ed16afefbaa558908c89 git | Not specified |
| CNA | Linux | Linux | affected 3dbe889a1b829b4c07e0836ff853fe649e51ce4f d87392094f96e162fa5fa5a8640d70cc0952806f git | Not specified |
| CNA | Linux | Linux | affected 6db2526c1d694c91c6e05e2f186c085e9460f202 399ec9ca8fc4999e676ff89a90184ec40031cf59 git | Not specified |
| CNA | Linux | Linux | affected 6db2526c1d694c91c6e05e2f186c085e9460f202 fea4e317f9e7e1f449ce90dedc27a2d2a95bee5a git | Not specified |
| CNA | Linux | Linux | affected d1347977661342cb09a304a17701eb2d4aa21dec git | Not specified |
| CNA | Linux | Linux | affected 5.15.179 5.15.183 semver | Not specified |
| CNA | Linux | Linux | affected 6.1.129 6.1.139 semver | Not specified |
| CNA | Linux | Linux | affected 6.6.79 6.6.91 semver | Not specified |
| CNA | Linux | Linux | affected 6.12.16 6.12.29 semver | Not specified |
| CNA | Linux | Linux | affected 6.13.4 6.14 semver | Not specified |
| CNA | Linux | Linux | affected 6.14 | Not specified |
| CNA | Linux | Linux | unaffected 6.14 semver | Not specified |
| CNA | Linux | Linux | unaffected 5.15.183 5.15.* semver | Not specified |
| CNA | Linux | Linux | unaffected 6.1.139 6.1.* semver | Not specified |
| CNA | Linux | Linux | unaffected 6.6.91 6.6.* semver | Not specified |
| CNA | Linux | Linux | unaffected 6.12.29 6.12.* semver | Not specified |
| CNA | Linux | Linux | unaffected 6.14.7 6.14.* semver | Not specified |
| CNA | Linux | Linux | unaffected 6.15 * original_commit_for_fix | Not specified |
| ADP | Siemens | SIMATIC S7-1500 CPU 1518-4 PN/DP MFP | affected V3.1.6 * custom | Not specified |
| ADP | Siemens | SIMATIC S7-1500 CPU 1518-4 PN/DP MFP | affected V3.1.6 * custom | Not specified |
| ADP | Siemens | SIMATIC S7-1500 CPU 1518F-4 PN/DP MFP | affected V3.1.6 * custom | Not specified |
| ADP | Siemens | SIMATIC S7-1500 CPU 1518F-4 PN/DP MFP | affected V3.1.6 * custom | Not specified |
| ADP | Siemens | SIPLUS S7-1500 CPU 1518-4 PN/DP MFP | affected V3.1.6 * custom | Not specified |
References
| Reference | Source | Link | Tags |
|---|---|---|---|
| git.kernel.org/stable/c/02ad4ce144bd27f71f583f667fdf3b3ba0753477 | 416baaa9-dc9f-4396-8d5f-8c081fb06d67 | git.kernel.org | Patch |
| git.kernel.org/stable/c/12f703811af043d32b1c8a30001b2fa04d5cd0ac | 416baaa9-dc9f-4396-8d5f-8c081fb06d67 | git.kernel.org | Patch |
| lists.debian.org/debian-lts-announce/2025/08/msg00010.html | af854a3a-2127-422b-91ae-364da2661108 | lists.debian.org | Third Party Advisory |
| git.kernel.org/stable/c/399ec9ca8fc4999e676ff89a90184ec40031cf59 | 416baaa9-dc9f-4396-8d5f-8c081fb06d67 | git.kernel.org | Patch |
| cert-portal.siemens.com/productcert/html/ssa-019113.html | 0b142b55-0307-4c5a-b3c9-f314f3fb7c5e | cert-portal.siemens.com | |
| git.kernel.org/stable/c/fea4e317f9e7e1f449ce90dedc27a2d2a95bee5a | 416baaa9-dc9f-4396-8d5f-8c081fb06d67 | git.kernel.org | Patch |
| git.kernel.org/stable/c/d41072906abec8bb8e01ed16afefbaa558908c89 | 416baaa9-dc9f-4396-8d5f-8c081fb06d67 | git.kernel.org | Patch |
| git.kernel.org/stable/c/d87392094f96e162fa5fa5a8640d70cc0952806f | 416baaa9-dc9f-4396-8d5f-8c081fb06d67 | git.kernel.org | Patch |
| CVE Program record | CVE.ORG | www.cve.org | canonical |
| NVD vulnerability detail | NVD | nvd.nist.gov | canonical, analysis |
No vendor comments have been submitted for this CVE.
There are currently no legacy QID mappings associated with this CVE.