{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-74447","assignerOrgId":"416baaa9-dc9f-4396-8d5f-8c081fb06d67","state":"PUBLISHED","assignerShortName":"Linux","dateReserved":"2026-08-15T05:44:03.898Z","datePublished":"2026-08-15T12:26:53.305Z","dateUpdated":"2026-08-17T05:47:18.735Z"},"containers":{"cna":{"providerMetadata":{"orgId":"416baaa9-dc9f-4396-8d5f-8c081fb06d67","shortName":"Linux","dateUpdated":"2026-08-17T05:47:18.735Z"},"descriptions":[{"lang":"en","value":"In the Linux kernel, the following vulnerability has been resolved:\n\ndrm/amdkfd: fix uint32_t overflow in EOP ring buffer size alignment\n\neop_ring_buffer_size in struct queue_properties is a u32. In\nkfd_queue_acquire_buffers() the expected EOP buffer size is computed as\nALIGN(eop_ring_buffer_size, PAGE_SIZE); ALIGN uses typeof(x), so the\naddition is done in 32-bit. A user-supplied size of 0xFFFFF001 wraps to\n0, causing kfd_queue_buffer_get() to skip its exact-size check (gated on\nsize != 0) and accept any BO mapped at the address. On GFX8/GFX9 the MQD\ncp_hqd_eop_control is then programmed for an 8KB EOP ring backed by a 4KB\nBO, so CP EOP writes can land past the buffer and fault the GPU.\n\nCast the operand to u64 so the alignment is computed in 64-bit; the size\ncheck in kfd_queue_buffer_get() then rejects the oversized request.\n\n(cherry picked from commit ae443117b742c357bfef3a7bddabf76fcf86e9ef)"}],"metrics":[{"cvssV3_1":{"version":"3.1","vectorString":"CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H","baseScore":7.8,"baseSeverity":"HIGH"},"scenarios":[{"lang":"en","value":"AV:L - Exploitation requires local ioctl access to /dev/kfd (KFD_IOC_CREATE_QUEUE) after opening the AMDGPU render node; there is no network, adjacent-wireless, or physical-device path to the vulnerable kfd_queue_acquire_buffers() code.\nAC:L - An attacker who can open /dev/kfd and map GPU buffers can reliably bypass the EOP size check with eop_buffer_size=0xFFFFF001 (32-bit ALIGN wraps to 0) and trigger CP EOP writes by submitting compute work on the created queue.\nPR:L - Only a local unprivileged user with AMDGPU/KFD access (typically membership in the render group for /dev/dri/renderD* and /dev/kfd) is required; no real-root or init-namespace capabilities are needed.\nUI:N - No victim interaction is required; the attacker drives the full chain via their own KFD and DRM file descriptors, GPU memory mappings, and queue submission.\nS:U - The bug corrupts GPU virtual memory within the attacker's own process VMID and can fault or reset the shared GPU; it does not cross a VM/host, IOMMU, or sandbox security boundary into another authority.\nC:H - CP hardware performs out-of-bounds EOP writes up to 8KB into a 4KB backing object, corrupting adjacent GPU-mapped memory that can be read back or chained into further memory disclosure primitives.\nI:H - The MQD is programmed with an 8KB EOP ring while only a 4KB buffer is validated, causing the GPU command processor to write attacker-triggered data past the buffer end into adjacent GPU mappings.\nA:H - EOP writes beyond the undersized buffer cause GPU VM faults that can hang the device and schedule amdgpu_amdkfd_gpu_reset(), denying GPU service to all co-located workloads on shared cloud/HPC/desktop GPUs."}]}],"affected":[{"product":"Linux","vendor":"Linux","defaultStatus":"unaffected","repo":"https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git","programFiles":["drivers/gpu/drm/amd/amdkfd/kfd_queue.c"],"versions":[{"version":"ee0dc6c66a913260311876a4b2b53fe0b9bc3f94","lessThan":"273548eb997c6be85230c1236b18784b09f6203c","status":"affected","versionType":"git"},{"version":"acfc84cfa70aca5b970faf152979bc97b9f8b0c0","lessThan":"6dc0b4b39ed4f11ef70f76ecea8537e35f45342b","status":"affected","versionType":"git"},{"version":"42ea9cf2f16b7131cb7302acb3dac510968f8bdc","lessThan":"7c54bd225d83bc1bcb44430ed4b4d3a5c36b1961","status":"affected","versionType":"git"},{"version":"42ea9cf2f16b7131cb7302acb3dac510968f8bdc","lessThan":"83463a96ea3c7d8ae636a4d6a0ba63c9ce410724","status":"affected","versionType":"git"},{"version":"c6ce687077cc67e4f3cbd0c89cb356fbbce91f4c","status":"affected","versionType":"git"},{"version":"6.12.75","lessThan":"6.12.103","status":"affected","versionType":"semver"},{"version":"6.18.16","lessThan":"6.18.44","status":"affected","versionType":"semver"},{"version":"6.19.6","lessThan":"6.20","status":"affected","versionType":"semver"}]},{"product":"Linux","vendor":"Linux","defaultStatus":"affected","repo":"https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git","programFiles":["drivers/gpu/drm/amd/amdkfd/kfd_queue.c"],"versions":[{"version":"7.0","status":"affected"},{"version":"0","lessThan":"7.0","status":"unaffected","versionType":"semver"},{"version":"6.12.103","lessThanOrEqual":"6.12.*","status":"unaffected","versionType":"semver"},{"version":"6.18.44","lessThanOrEqual":"6.18.*","status":"unaffected","versionType":"semver"},{"version":"7.1.8","lessThanOrEqual":"7.1.*","status":"unaffected","versionType":"semver"},{"version":"7.2","lessThanOrEqual":"*","status":"unaffected","versionType":"original_commit_for_fix"}]}],"cpeApplicability":[{"nodes":[{"operator":"OR","negate":false,"cpeMatch":[{"vulnerable":true,"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionStartIncluding":"6.12.75","versionEndExcluding":"6.12.103"},{"vulnerable":true,"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionStartIncluding":"6.18.16","versionEndExcluding":"6.18.44"},{"vulnerable":true,"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionStartIncluding":"7.0","versionEndExcluding":"7.1.8"},{"vulnerable":true,"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionStartIncluding":"7.0","versionEndExcluding":"7.2"},{"vulnerable":true,"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionStartIncluding":"6.19.6"}]}]}],"references":[{"url":"https://git.kernel.org/stable/c/273548eb997c6be85230c1236b18784b09f6203c"},{"url":"https://git.kernel.org/stable/c/6dc0b4b39ed4f11ef70f76ecea8537e35f45342b"},{"url":"https://git.kernel.org/stable/c/7c54bd225d83bc1bcb44430ed4b4d3a5c36b1961"},{"url":"https://git.kernel.org/stable/c/83463a96ea3c7d8ae636a4d6a0ba63c9ce410724"}],"title":"drm/amdkfd: fix uint32_t overflow in EOP ring buffer size alignment","x_generator":{"engine":"bippy-1.2.0"}}}}