Look up another CVE · open CVE-2025-68174 in the interactive tracker
CVE-2025-68174
amd/amdkfd: enhance kfd process check in switch partition
Published 2025-12-16 (10 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-2025-68174 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 | vulnerable | 6.12.113-1 | No fix published anywhere yet, neither in Debian nor upstream for the series trixie tracks. Watch the Debian tracker page for this CVE. Advisories for trixie have historically landed a median of 11 days after publication. |
| Debian 14forky | fixed | 6.17.8-1 | Update the kernel and reboot. Fixed in 6.17.8-1. A running kernel keeps the old code until the machine restarts. |
| Debian unstablesid | fixed | 6.17.8-1 | Update the kernel and reboot. Fixed in 6.17.8-1. A running kernel keeps the old code until the machine restarts. |
The vulnerability
What the bug is
current switch partition only check if kfd_processes_table is empty. kfd_prcesses_table entry is deleted in kfd_process_notifier_release, but kfd_process tear down is in kfd_process_wq_release. consider two processes: Process A (workqueue) -> kfd_process_wq_release -> Access kfd_node member Process B switch partition -> amdgpu_xcp_pre_partition_switch -> amdgpu_amdkfd_device_fini_sw -> kfd_node tear down. Process A and B may trigger a race as shown in dmesg log. This patch is to resolve the race by adding an atomic kfd_process counter kfd_processes_count, it increment as create kfd process, decrement as finish kfd_process_wq_release. v2: Put kfd_processes_count per kfd_dev, move decrement to kfd_process_destroy_pdds and bug fix. (Philip Yang) [3966658.307702] divide error: 0000 [#1] SMP NOPTI [3966658.350818] i10nm_edac [3966658.356318] CPU: 124 PID: 38435 Comm: kworker/124:0 Kdump: loaded Tainted [3966658.356890] Workqueue: kfd_process_wq kfd_process_wq_release [amdgpu] [3966658.362839] nfit [3966658.366457] RIP: 0010:kfd_get_num_sdma_engines+0x17/0x40 [amdgpu] [3966658.366460] Code: 00 00 e9 ac 81 02 00 66 66 2e 0f 1f 84 00 00 00 00 00 90 0f 1f 44 00 00 48 8b 4f 08 48 8b b7 00 01 00 00 8b 81 58 26 03 00 99 <f7> be b8 01 00 00 80 b9 70 2e 00 00 00 74 0b 83 f8 02 ba 02 00 00 [3966658.380967] x86_pkg_temp_thermal [3966658.391529] RSP: 0018:ffffc900a0edfdd8 EFLAGS: 00010246 [3966658.391531] RAX: 0000000000000008 RBX: ffff8974e593b800 RCX: ffff888645900000 [3966658.391531] RDX: 0000000000000000 RSI: ffff888129154400 RDI: ffff888129151c00 [3966658.391532] RBP: ffff8883ad79d400 R08: 0000000000000000 R09: ffff8890d2750af4 [3966658.391532] R10: 0000000000000018 R11: 0000000000000018 R12: 0000000000000000 [3966658.391533] R13: ffff8883ad79d400 R14: ffffe87ff662ba00 R15: ffff8974e593b800 [3966658.391533] FS: 0000000000000000(0000) GS:ffff88fe7f600000(0000) knlGS:0000000000000000 [3966658.391534] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [3966658.391534] CR2: 0000000000d71000 CR3: 000000dd0e970004 CR4: 0000000002770ee0 [3966658.391535] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [3966658.391535] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 [3966658.391536] PKRU: 55555554 [3966658.391536] Call Trace: [3966658.391674] deallocate_sdma_queue+0x38/0xa0 [amdgpu] [3966658.391762] process_termination_cpsch+0x1ed/0x480 [amdgpu] [3966658.399754] intel_powerclamp [3966658.402831] kfd_process_dequeue_from_all_devices+0x5b/0xc0 [amdgpu] [3966658.402908] kfd_process_wq_release+0x1a/0x1a0 [amdgpu] [3966658.410516] coretemp [3966658.434016] process_one_work+0x1ad/0x380 [3966658.434021] worker_thread+0x49/0x310 [3966658.438963] kvm_intel [3966658.446041] ? process_one_work+0x380/0x380 [3966658.446045] kthread+0x118/0x140 [3966658.446047] ? __kthread_bind_mask+0x60/0x60 [3966658.446050] ret_from_fork+0x1f/0x30 [3966658.446053] Modules linked in: kpatch_20765354(OEK) [3966658.455310] kvm [3966658.464534] mptcp_diag xsk_diag raw_diag unix_diag af_packet_diag netlink_diag udp_diag act_pedit act_mirred act_vlan cls_flower kpatch_21951273(OEK) kpatch_18424469(OEK) kpatch_19749756(OEK) [3966658.473462] idxd_mdev [3966658.482306] kpatch_17971294(OEK) sch_ingress xt_conntrack amdgpu(OE) amdxcp(OE) amddrm_buddy(OE) amd_sched(OE) amdttm(OE) amdkcl(OE) intel_ifs iptable_mangle tcm_loop target_core_pscsi tcp_diag target_core_file inet_diag target_core_iblock target_core_user target_core_mod coldpgs kpatch_18383292(OEK) ip6table_nat ip6table_filter ip6_tables ip_set_hash_ipportip ip_set_hash_ipportnet ip_set_hash_ipport ip_set_bitmap_port xt_comment iptable_nat nf_nat iptable_filter ip_tables ip_set ip_vs_sh ip_vs_wrr ip_vs_rr ip_vs nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 sn_core_odd(OE) i40e overlay binfmt_misc tun bonding(OE) aisqos(OE) aisqo ---truncated---
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/amdkfd/kfd_device.c
drivers/gpu/drm/amd/amdkfd/kfd_priv.h
drivers/gpu/drm/amd/amdkfd/kfd_process.c
- What this is
- AMD KFDMAINTAINERS section matched on drivers/gpu/drm/amd/amdkfd/ · amd-gfx@lists.freedesktop.org · Supported
Show whether Debian builds this, per release
Not established. This site could not find the build rule for the affected file in the kernel trees Debian ships, so it has no answer about whether Debian compiles this code. Read that as unknown, never as absent.
- bookworm, trixie, forky, sid?
- ?
- not established - no Makefile entry for the affected file
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.
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
Signals
- Published
- 2025-12-16 (10 months ago)source
- CVSS
- 7.8 high
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:Hsource recompute it - Attack vector
- local (AV:L)source
- EPSS
- 0.14%, higher than 3.3% 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 |
|---|---|---|
| 6.5 | 6.17.8 | 536d80f660ec |
| 6.5 | 6.18 | 45da20e00d5d |
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
- Exploitation requires local access to the `/dev/kfd` character device to create the KFD process whose deferred teardown races the partition switch, and the free side is driven through a local sysfs attribute. There is no network-reachable path into `kfd_process_wq_release()` or `amdgpu_xcp_switch_partition_mode()`.
- AC:LAttack complexity, low
- The attacker controls the UAF side directly and can widen the window from milliseconds to seconds (`flush_workqueue` + `synchronize_rcu` + bulk BO/SVM teardown in `kfd_process_wq_release()`), and on MI300-class multi-tenant hosts the partition switch is an automated orchestrator action performed at job boundaries — precisely when the attacker's process teardown is still in flight — so the collision is reliably reproducible rather than dependent on chance memory layout.
- PR:LPrivileges required, low
- `kfd_open()` performs no capability check, so any unprivileged local user or container tenant with `/dev/kfd` (mode 0666 or the `render` group under standard ROCm udev rules) can create the KFD process and pdd that leave stale `kfd_node` references in the pending workqueue item. No root or capability is needed on the attacker's side of the race.
- UI:NUser interaction, none
- The vulnerable window opens automatically at process exit via the mmu_notifier release callback, with no victim action required. In the datacenter deployments where XCP repartitioning exists, the partition switch is issued by an automated scheduler/orchestrator with no human in the loop.
- S:UScope, unchanged
- The corrupted objects (`kfd_node`, `kfd_dev`, `device_queue_manager`) and the resulting code execution all live in host kernel memory, within the same security authority as the vulnerable component. No hypervisor, IOMMU, or sandbox boundary is crossed by the flaw itself.
- C:HConfidentiality impact, high
- This is a use-after-free where freed slab contents are read back and used as pointers (`pdd->dev->kfd`, `pdd->dev->adev`, `dqm->ops`), so an attacker who reclaims the freed `kfd_node`/`dqm` allocations gains a controlled kernel read primitive that can be escalated to arbitrary memory disclosure.
- I:HIntegrity impact, high
- The stale references yield both an arbitrary-ish write — `set_bit(q->sdma_id, dqm->sdma_bitmap)` whose target and bound are both read from freed memory — and a direct indirect call through a function pointer in the freed `dqm` (`dev->dqm->ops.process_termination`), which is a textbook control-flow hijack primitive once the slab is sprayed.
- A:HAvailability impact, high
- The commit's own dmesg shows a fatal kernel oops (`divide error` in `kfd_get_num_sdma_engines` from the `kfd_process_wq` kworker) caused by reading `num_nodes == 0` out of the freed `kfd_dev`. Any unhandled UAF here panics the machine, taking down a shared GPU compute node.