Commit 7b6275c8 authored by Eric Badger's avatar Eric Badger Committed by Anna Schumaker
Browse files

xprtrdma: Decrement re_receiving on the early exit paths



In the event that rpcrdma_post_recvs() fails to create a work request
(due to memory allocation failure, say) or otherwise exits early, we
should decrement ep->re_receiving before returning. Otherwise we will
hang in rpcrdma_xprt_drain() as re_receiving will never reach zero and
the completion will never be triggered.

On a system with high memory pressure, this can appear as the following
hung task:

    INFO: task kworker/u385:17:8393 blocked for more than 122 seconds.
          Tainted: G S          E       6.19.0 #3
    "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
    task:kworker/u385:17 state:D stack:0     pid:8393  tgid:8393  ppid:2      task_flags:0x4248060 flags:0x00080000
    Workqueue: xprtiod xprt_autoclose [sunrpc]
    Call Trace:
     <TASK>
     __schedule+0x48b/0x18b0
     ? ib_post_send_mad+0x247/0xae0 [ib_core]
     schedule+0x27/0xf0
     schedule_timeout+0x104/0x110
     __wait_for_common+0x98/0x180
     ? __pfx_schedule_timeout+0x10/0x10
     wait_for_completion+0x24/0x40
     rpcrdma_xprt_disconnect+0x444/0x460 [rpcrdma]
     xprt_rdma_close+0x12/0x40 [rpcrdma]
     xprt_autoclose+0x5f/0x120 [sunrpc]
     process_one_work+0x191/0x3e0
     worker_thread+0x2e3/0x420
     ? __pfx_worker_thread+0x10/0x10
     kthread+0x10d/0x230
     ? __pfx_kthread+0x10/0x10
     ret_from_fork+0x273/0x2b0
     ? __pfx_kthread+0x10/0x10
     ret_from_fork_asm+0x1a/0x30

Fixes: 15788d1d ("xprtrdma: Do not refresh Receive Queue while it is draining")
Signed-off-by: default avatarEric Badger <ebadger@purestorage.com>
Reviewed-by: default avatarChuck Lever <chuck.lever@oracle.com>
Signed-off-by: default avatarAnna Schumaker <anna.schumaker@oracle.com>
parent 410666a2
Loading
Loading
Loading
Loading
+4 −3
Original line number Diff line number Diff line
@@ -1362,7 +1362,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed)
	needed += RPCRDMA_MAX_RECV_BATCH;

	if (atomic_inc_return(&ep->re_receiving) > 1)
		goto out;
		goto out_dec;

	/* fast path: all needed reps can be found on the free list */
	wr = NULL;
@@ -1385,7 +1385,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed)
		++count;
	}
	if (!wr)
		goto out;
		goto out_dec;

	rc = ib_post_recv(ep->re_id->qp, wr,
			  (const struct ib_recv_wr **)&bad_wr);
@@ -1400,9 +1400,10 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed)
			--count;
		}
	}

out_dec:
	if (atomic_dec_return(&ep->re_receiving) > 0)
		complete(&ep->re_done);

out:
	trace_xprtrdma_post_recvs(r_xprt, count);
	ep->re_receive_count += count;