Look up another CVE · open CVE-2026-68103 in the interactive tracker
CVE-2026-68103
drm/amdgpu: reject mapping a reserved doorbell to a new queue
Published 2026-08-10 (2 months ago) by the Linux kernel CNA. Subsystem drivers/gpu. Debian urgency: unimportant.
What to do, per Debian release
Debian's own status for CVE-2026-68103 in every release this site tracks, and what each one means in practice. Every status below is the one the Debian Security Team publishes for this CVE. source
| Release | Status | Version | What this means |
|---|---|---|---|
| Debian 12bookworm | not affected | 6.1.190-1 | Nothing to do. bookworm never shipped the vulnerable code. |
| Debian 13trixie | not affected | 6.12.113-1 | Nothing to do. trixie never shipped the vulnerable code. |
| Debian 14forky | fixed | 7.1.6-1 | Update the kernel and reboot. Fixed in 7.1.6-1. A running kernel keeps the old code until the machine restarts. |
| Debian unstablesid | fixed | 7.1.6-1 | Update the kernel and reboot. Fixed in 7.1.6-1. A running kernel keeps the old code until the machine restarts. |
The vulnerability
What the bug is
When creating an user-queue, the user space provides a doorbell BO handle and an offset within the bo to obtain a doorbell. However current implementation using xa_store_irq() to store a doorbell, which allows a later queue created with the same BO and offset parameters to overwrite an existing queue and doorbell mapping. This can cause problems like misrouting fence IRQ processing to a wrong queue, and mislead the cleanup process of one queue erasing the mapping of another queue. This commit fixes this issue by replacing xa_store_irq with xa_insert_irq, which rejects mapping a reserved doorbell to a newly created queue (cherry picked from commit 6244eae22966350db52faf9c1369d3b2ffc5de4e)
Where it lives
The fix touches these files. If the subsystem is one you do not use, the practical exposure is lower, though the package is still the vulnerable one.
drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
- What this is
- RADEON and AMDGPU DRM DRIVERSMAINTAINERS section matched on drivers/gpu/drm/amd/ · amd-gfx@lists.freedesktop.org · Supported
- Kernel module
- amdgpu
Check it on the machine
grep -w CONFIG_DRM_AMDGPU /boot/config-$(uname -r)Reads the booted kernel's own configuration, on the machine and nowhere else. =y is built in, =m is a module, and an is not set line means the code is not there.
lsmod | grep -w amdgpuPrints a line if that module is loaded right now, and nothing if it is not. One that is not loaded can still be loaded later by anything that needs it.
Show whether Debian builds this, per release
Debian builds this, but not on every flavour. At least one release below builds the code on some of its kernel flavours and not on others, so the answer depends on the architecture and flavour installed. The build rule could not be established for 2 releases, so nothing is claimed about those.
- bookworm, trixie?
- forky, sidMnot built on amd64/cloud-amd64, arm64/cloud-arm64, s390x/s390x
- ?
- not established - no Makefile entry for the affected file
- M
- a module where it is built at all; some flavours do not build it
Where a release above reads "not established", no build rule for the affected file was found in that release's kernel tree. That is a gap in this lookup, not a finding that the code is absent.
- Build switch
- CONFIG_DRM_AMDGPU
From the configuration Debian publishes for every kernel flavour it builds. It covers only the architectures Debian ships a linux-config package for, and nothing about a kernel you built yourself. Debian's own status above stays authoritative about the source package.MAINTAINERS kbuild Makefiles Debian linux-config packages
Signals
- Published
- 2026-08-10 (2 months ago)source
- CVSS
- 7.1 high
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:Hsource recompute it - Attack vector
- local (AV:L)source
- EPSS
- 0.15%, higher than 3.9% of all CVEssource
- CISA KEV
- not listedthe KEV catalogue
- Debian urgency
- unimportantsource
- Subsystem
- drivers/gpu
Upstream fixes
The versions the CNA records as introducing and fixing this, and the commit for each. source
| Introduced | Fixed in | Commit |
|---|---|---|
| 6.16 | 7.1.6 | 1050d258c7c5 |
| 6.16 | 7.2 | a609b6278bf3 |
Why the CNA scored it this way
Quoted from the kernel CNA's own scoring file, word for word. A highlighted metric carries the most severe value CVSS v3.1 defines for it, which is what pushes the score up. source
- AV:LAttack vector, local
- The bug is reached only through the AMDGPU DRM_USERQ ioctl on a local render node (/dev/dri/renderD*); fence IRQ handling is driven by local GPU completion events, not remote network input.
- AC:LAttack complexity, low
- An attacker can deterministically trigger the overwrite by issuing AMDGPU_USERQ_OP_CREATE with the same doorbell GEM handle and offset (same process) or by landing on the same global doorbell BAR index (shared-GPU hosts); no race or victim timing is required.
- PR:LPrivileges required, low
- Exploitation requires only access to the AMDGPU render node granted to normal local users (e.g., render/video group on workstations, cloud GPU VMs, ROCm compute nodes); high-priority queue creation is optional and not needed for the attack.
- UI:NUser interaction, none
- The attacker triggers the flaw directly via ioctls; victims need only be running ordinary GPU compute/graphics workloads on the same device, with no additional user interaction.
- S:UScope, unchanged
- Impact is confined to kernel AMDGPU user-queue and fence state on the local GPU; it does not cross VM, IOMMU, or sandbox boundaries into another security authority.
- C:NConfidentiality impact, none
- Misrouting fence IRQs corrupts queue-to-doorbell associations and synchronization but provides no kernel or victim memory read primitive; AMDGPU per-process VM isolation blocks direct disclosure of another tenant's GPU buffers.
- I:HIntegrity impact, high
- Silently overwriting the device-global doorbell xarray lets an attacker hijack another queue's fence IRQ handling and erase its mapping on teardown, corrupting kernel queue state and breaking GPU synchronization integrity for other workloads.
- A:HAvailability impact, high
- Orphaned queues stop receiving fence IRQs, provoking hang detection and amdgpu_userq_mgr_reset_work paths that can force per-queue or full GPU recovery, denying GPU service to all users on shared AMD GPU systems.