CVE-2026-64210
Beschrijving NL
In de Linux kernel is de volgende kwetsbaarheid verholpen:
net/mlx5e: xsk: Fix ontgrendeld schrijven naar ICOSQ
Tijdens de napi-peiling, wanneer de affiniteit verandert en er nog steeds XSK-werk is
te doen, activeren we een ICOSQ-interrupt op de nieuwe CPU. Dit
activeren op de ICOSQ gebeurt onbeschermd. Er zijn 2 van dergelijke rassen:
A) mlx5e_trigger_irq() wordt aangeroepen terwijl mlx5e_xsk_alloc_rx_mpwqe ()
draaien vanaf een andere CPU vanwege affiniteitsverandering. Dit kan gebeuren
omdat IRQ-triggering wordt uitgevoerd na napi_complete_done(). Op dit punt
de NAPI kan op een andere CPU worden gepland. Zo werkt het:
CPU A (oude affiniteit, NAPI staart) CPU B (nieuwe affiniteit, verse NAPI)
------------------------------- --------------------------------
napi_complete_done() wist SCHED
mlx5e_cq_arm(...)
napi_schedule_prep() sets GEPLAND
mlx5e_napi_poll()
mlx5e_xsk_alloc_rx_mpwqe()
mlx5e_icosq_sync_lock() // noop memcpy 640 B UMR body
voorschot sq->pc met 10
mlx5e_trigger_irq(&c->icosq)
wqe_info[pi] = {NOP, 1}
mlx5e_post_nop() voorschotten sq->pc
B) mlx5e_trigger_irq() wordt aangeroepen op de ICOSQ wanneer
mlx5e_trigger_napi_icosq() wordt uitgevoerd. De voor de hand liggende oplossing zou zijn om de ICOSQ te vergrendelen. Maar ICOSQ heeft een geoptimaliseerde
vergrendelingsschema dat niet werkt voor dit scenario. Kick the async ICOSQ
in plaats daarvan die altijd vergrendeld is. Dit probleem werd in het wild opgemerkt met de volgende splat:
netdevice: ge-0-0-1: Slechte OP in ICOSQ CQE: 0xd
WAARSCHUWING: drivers/net/ethernet/mellanox/mlx5/core/en_rx.c:826 [...]
[...]
Oproeptracering:
mlx5e_napi_poll+0x11d/0x7f0 [mlx5_core]
__napi_poll+0x30/0x200
? skb_defer_free_flush+0x9c/0xc0
net_rx_action+0x2fe/0x3f0
handle_softirqs+0xd8/0x340
__irq_exit_rcu+0xbc/0xe0
common_interrupt+0x85/0xa0
asm_common_interrupt+0x26/0x40
[...]
---[ eindspoor 0000000000000000 ]---
mlx5_core 0000:08:00.0 ge-0-0-1: Fout cqe op cqn 0x548, ci 0x2022, qn 0x8f4,
opcode 0xd, syndroom 0x2, vendorsyndroom 0x68
00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000030: 00 00 00 00 01 00 68 02 01 00 08 f4 de 14 59 d2
WQE DUMP: WQ size 16384 WQ CUR size 0, WQE index 0x1e14, len: 64
00000000: 00 00 00 01 d9 ed 80 02 00 00 00 01 d9 ed 90 02
00000010: 00 00 00 01 d9 ed a0 02 00 00 00 01 d9 ed b0 02
00000020: 00 00 00 01 d9 ed c0 02 00 00 00 01 d9 ed d0 02
00000030: 00 00 00 01 d9 ed e0 02 00 00 00 01 d9 ed f0 02
mlx5_core 0000:08:00.0 ge-0-0-1: Fout cqe op cqn 0x548, ci 0x2023, qn 0x8f4,
opcode 0xd, syndroom 0x5, vendorsyndroom 0xf9
00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000030: 00 00 00 00 01 00 f9 05 01 00 08 f4 de 15 cf d2
Origineel (Engels) tonen
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: xsk: Fix unlocked writing to ICOSQ
During napi poll, when the affinity changes and there's still XSK work
to be done, we trigger an ICOSQ interrupt on the new CPU. However, this
triggering on the ICOSQ is done unprotected.
There are 2 such races:
A) mlx5e_trigger_irq() is called while mlx5e_xsk_alloc_rx_mpwqe() is
running from a different CPU due to affinity change. This can happen
because IRQ triggering is done after napi_complete_done(). At this point
the NAPI can be scheduled on a different CPU. Like this:
CPU A (old affinity, NAPI tail) CPU B (new affinity, fresh NAPI)
------------------------------- --------------------------------
napi_complete_done() clears SCHED
mlx5e_cq_arm(...)
napi_schedule_prep() sets SCHED
mlx5e_napi_poll()
mlx5e_xsk_alloc_rx_mpwqe()
mlx5e_icosq_sync_lock() // noop
memcpy 640 B UMR body
advance sq->pc by 10
mlx5e_trigger_irq(&c->icosq)
wqe_info[pi] = {NOP, 1}
mlx5e_post_nop() advances sq->pc
B) mlx5e_trigger_irq() is called on the ICOSQ when
mlx5e_trigger_napi_icosq() is running.
The obvious fix would be to lock the ICOSQ. But ICOSQ has an optimized
locking scheme that doesn't work for this scenario. Kick the async ICOSQ
instead which is always locked.
This issue was noticed in the wild with the following splat:
netdevice: ge-0-0-1: Bad OP in ICOSQ CQE: 0xd
WARNING: drivers/net/ethernet/mellanox/mlx5/core/en_rx.c:826 [...]
[...]
Call Trace:
mlx5e_napi_poll+0x11d/0x7f0 [mlx5_core]
__napi_poll+0x30/0x200
? skb_defer_free_flush+0x9c/0xc0
net_rx_action+0x2fe/0x3f0
handle_softirqs+0xd8/0x340
__irq_exit_rcu+0xbc/0xe0
common_interrupt+0x85/0xa0
asm_common_interrupt+0x26/0x40
[...]
---[ end trace 0000000000000000 ]---
mlx5_core 0000:08:00.0 ge-0-0-1: Error cqe on cqn 0x548, ci 0x2022, qn 0x8f4,
opcode 0xd, syndrome 0x2, vendor syndrome 0x68
00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000030: 00 00 00 00 01 00 68 02 01 00 08 f4 de 14 59 d2
WQE DUMP: WQ size 16384 WQ cur size 0, WQE index 0x1e14, len: 64
00000000: 00 00 00 01 d9 ed 80 02 00 00 00 01 d9 ed 90 02
00000010: 00 00 00 01 d9 ed a0 02 00 00 00 01 d9 ed b0 02
00000020: 00 00 00 01 d9 ed c0 02 00 00 00 01 d9 ed d0 02
00000030: 00 00 00 01 d9 ed e0 02 00 00 00 01 d9 ed f0 02
mlx5_core 0000:08:00.0 ge-0-0-1: Error cqe on cqn 0x548, ci 0x2023, qn 0x8f4,
opcode 0xd, syndrome 0x5, vendor syndrome 0xf9
00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000030: 00 00 00 00 01 00 f9 05 01 00 08 f4 de 15 cf d2