CVE-2026-53374: drm/amdgpu: zero-initialize GART table on allocation

Severity: high (CVSS 8.8 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 0.1% probability of exploitation in the next 30 days
Public exploit or detection template: none known
Published: 2026-07-19 · updated 2026-10-19
Weakness: CWE-457

Description

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: zero-initialize GART table on allocation GART TLB is flushed after unmapping but not after mapping. Since amdgpu_bo_create_kernel() does not zero-initialize the buffer, when a single PTE is written the TLB may speculatively load other uninitialized entries from the same cacheline. Those garbage entries can appear valid, and a subsequent write to another PTE in the same cacheline may cause the GPU to use a stale garbage PTE from the TLB. Fix this by calling memset_io() to zero-initialize the GART table with gart_pte_flags immediately after allocation. Using AMDGPU_GEM_CREATE_VRAM_CLEARED, SDMA-based clear will not work since SDMA needs GART to be initialized to work. (cherry picked from commit d9af8263b82b6eaa60c5718e0c6631c5037e4b24)

Affected products

Linux kernel: from 4.2 before 6.1.175; from 6.2 before 6.6.140; from 6.7 before 6.12.90; from 6.13 before 6.18.32; from 6.19 before 7.0.9; 7.1-rc1, 7.1-rc2 — fixed in 6.1.175, 6.12.90, 6.18.32, 6.6.140, 7.0.9

How to fix

Upgrade to a fixed version: Linux kernel 6.1.175, 6.12.90, 6.18.32, 6.6.140. Check the vendor advisory for mitigations.

References

Get alerted when CVE-2026-53374 or the next vulnerability affects your stack