High · published April 16, 2025
In the Linux kernel, the following vulnerability has been resolved:
x86/mm: Fix flush_tlb_range() when used for zapping normal PMDs
On the following path, flush_tlb_range() can be used for zapping normal
PMD entries (PMD entries that point to page tables) together with the PTE
entries in the pointed-to page table:
collapse_pte_mapped_thp
pmdp_collapse_flush
flush_tlb_range
The arm64 version of flush_tlb_range() has a comment describing that it can
be used for page table removal, and does not use any last-level
invalidation optimizations. Fix the X86 version by making it behave the
same way.
Currently, X86 only uses this information for the following two purposes,
which I think means the issue doesn't have much impact:
- In native_flush_tlb_multi() for checking if lazy TLB CPUs need to be
IPI'd to avoid issues with speculative page table walks.
- In Hyper-V TLB paravirtualization, again for lazy TLB stuff.
The patch "x86/mm: only invalidate final translations with INVLPGB" which
is currently under review (see
<https://lore.kernel.org/all/[email protected]/>)
would probably be making the impact of this a lot worse.
| Product | Versions | Fixed in |
|---|---|---|
| linux/linux_kernel | ≥ 4.20, < 5.4.292 | 5.4.292 |
| linux/linux_kernel | ≥ 5.5, < 5.10.236 | 5.10.236 |
| linux/linux_kernel | ≥ 5.11, < 5.15.180 | 5.15.180 |
| linux/linux_kernel | ≥ 5.16, < 6.1.134 | 6.1.134 |
| linux/linux_kernel | ≥ 6.2, < 6.6.87 | 6.6.87 |
| linux/linux_kernel | ≥ 6.7, < 6.12.23 | 6.12.23 |
| linux/linux_kernel | ≥ 6.13, < 6.13.11 | 6.13.11 |
| linux/linux_kernel | ≥ 6.14, < 6.14.2 | 6.14.2 |