Re: [PATCH] RDMA/rxe: Fix race condition in QP timer handlers

[Zhu Yanjun <yanjun.zhu@linux.dev>]

在 2026/1/19 23:44, Li Zhijian 写道:
> I encontered the following warning:
>   WARNING: drivers/infiniband/sw/rxe/rxe_task.c:249 at rxe_sched_task+0x1c8/0x238 [rdma_rxe], CPU#0: swapper/0/0
> ...
>    libsha1 [last unloaded: ip6_udp_tunnel]
>   CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Tainted: G         C          6.19.0-rc5-64k-v8+ #37 PREEMPT
>   Tainted: [C]=CRAP
>   Hardware name: Raspberry Pi 4 Model B Rev 1.2
>   Call trace:
>    rxe_sched_task+0x1c8/0x238 [rdma_rxe] (P)
>    retransmit_timer+0x130/0x188 [rdma_rxe]
>    call_timer_fn+0x68/0x4d0
>    __run_timers+0x630/0x888
> ...
>   WARNING: drivers/infiniband/sw/rxe/rxe_task.c:38 at rxe_sched_task+0x1c0/0x238 [rdma_rxe], CPU#0: swapper/0/0
> ...
>   WARNING: drivers/infiniband/sw/rxe/rxe_task.c:111 at do_work+0x488/0x5c8 [rdma_rxe], CPU#3: kworker/u17:4/93400
> ...
>   refcount_t: underflow; use-after-free.
>   WARNING: lib/refcount.c:28 at refcount_warn_saturate+0x138/0x1a0, CPU#3: kworker/u17:4/93400
> 
> The issue is caused by a race condition between retransmit_timer() and
> rxe_destroy_qp, leading to the Queue Pair's (QP) reference count dropping
> to zero during timer handler execution.
> 
> It seems this warning is harmless because rxe_qp_do_cleanup() will flush
> all pending timers and requests.
> 
> Example of flow causing the issue:
> 
> CPU0                                   CPU1
> retransmit_timer() {
>      spin_lock_irqsave
>                             rxe_destroy_qp()
>                              __rxe_cleanup()
>                                __rxe_put() // qp->ref_count decrease to 0

In  __rxe_cleanup, __rxe_put decrease qp->ref_count to 0.

Then in the timer functions retransmit_timer and rnr_nak_timer will 
check qp and resend the packets. IMO, it may be a solution to use the 
function rxe_get to check if ref_count is 0 or not.

I am fine with it.

Reviewed-by: Zhu Yanjun <yanjun.zhu@linux.dev>

Thanks,
Zhu Yanjun

>                              rxe_qp_do_cleanup() {
>      if (qp->valid) {
>          rxe_sched_task() {
>              WARN_ON(rxe_read(task->qp) <= 0);
>          }
>      }
>      spin_unlock_irqrestore
> }
>                                spin_lock_irqsave
>                                qp->valid = 0
>                                spin_unlock_irqrestore
>                              }
> 
> Ensure the QP's reference count is maintained and its validity is checked
> within the timer callbacks by adding calls to rxe_get(qp) and corresponding
> rxe_put(qp) after use.
> 
> Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
> ---
>   drivers/infiniband/sw/rxe/rxe_comp.c | 3 +++
>   drivers/infiniband/sw/rxe/rxe_req.c  | 3 +++
>   2 files changed, 6 insertions(+)
> 
> diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
> index a5b2b62f596b..1390e861bd1d 100644
> --- a/drivers/infiniband/sw/rxe/rxe_comp.c
> +++ b/drivers/infiniband/sw/rxe/rxe_comp.c
> @@ -119,12 +119,15 @@ void retransmit_timer(struct timer_list *t)
>   
>   	rxe_dbg_qp(qp, "retransmit timer fired\n");
>   
> +	if (!rxe_get(qp))
> +		return;
>   	spin_lock_irqsave(&qp->state_lock, flags);
>   	if (qp->valid) {
>   		qp->comp.timeout = 1;
>   		rxe_sched_task(&qp->send_task);
>   	}
>   	spin_unlock_irqrestore(&qp->state_lock, flags);
> +	rxe_put(qp);
>   }
>   
>   void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb)
> diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
> index 373b03f223be..12d03f390b09 100644
> --- a/drivers/infiniband/sw/rxe/rxe_req.c
> +++ b/drivers/infiniband/sw/rxe/rxe_req.c
> @@ -102,6 +102,8 @@ void rnr_nak_timer(struct timer_list *t)
>   
>   	rxe_dbg_qp(qp, "nak timer fired\n");
>   
> +	if (!rxe_get(qp))
> +		return;
>   	spin_lock_irqsave(&qp->state_lock, flags);
>   	if (qp->valid) {
>   		/* request a send queue retry */
> @@ -110,6 +112,7 @@ void rnr_nak_timer(struct timer_list *t)
>   		rxe_sched_task(&qp->send_task);
>   	}
>   	spin_unlock_irqrestore(&qp->state_lock, flags);
> +	rxe_put(qp);
>   }
>   
>   static void req_check_sq_drain_done(struct rxe_qp *qp)