For a failing smc_listen_rdma_finish() smc_listen_decline() is
called. If fallback is possible, the new socket is already enqueued
to be accepted in smc_listen_decline(). Avoid enqueuing a second time
afterwards in this case, otherwise the smc_create_lgr_pending lock
is released twice:
[ 373.463976] WARNING: bad unlock balance detected!
[ 373.463978] 4.18.0-rc7+ #123 Tainted: G O
[ 373.463979] -------------------------------------
[ 373.463980] kworker/1:1/30 is trying to release lock (smc_create_lgr_pending) at:
[ 373.463990] [<000003ff801205fc>] smc_listen_work+0x22c/0x5d0 [smc]
[ 373.463991] but there are no more locks to release!
[ 373.463991]
other info that might help us debug this:
[ 373.463993] 2 locks held by kworker/1:1/30:
[ 373.463994] #0: 00000000772cbaed ((wq_completion)"events"){+.+.}, at: process_one_work+0x1ec/0x6b0
[ 373.464000] #1: 000000003ad0894a ((work_completion)(&new_smc->smc_listen_work)){+.+.}, at: process_one_work+0x1ec/0x6b0
[ 373.464003]
stack backtrace:
[ 373.464005] CPU: 1 PID: 30 Comm: kworker/1:1 Kdump: loaded Tainted: G O 4.18.0-rc7uschi+ #123
[ 373.464007] Hardware name: IBM 2827 H43 738 (LPAR)
[ 373.464010] Workqueue: events smc_listen_work [smc]
[ 373.464011] Call Trace:
[ 373.464015] ([<0000000000114100>] show_stack+0x60/0xd8)
[ 373.464019] [<0000000000a8c9bc>] dump_stack+0x9c/0xd8
[ 373.464021] [<00000000001dcaf8>] print_unlock_imbalance_bug+0xf8/0x108
[ 373.464022] [<00000000001e045c>] lock_release+0x114/0x4f8
[ 373.464025] [<0000000000aa87fa>] __mutex_unlock_slowpath+0x4a/0x300
[ 373.464027] [<000003ff801205fc>] smc_listen_work+0x22c/0x5d0 [smc]
[ 373.464029] [<0000000000197a68>] process_one_work+0x2a8/0x6b0
[ 373.464030] [<0000000000197ec2>] worker_thread+0x52/0x410
[ 373.464033] [<000000000019fd0e>] kthread+0x15e/0x178
[ 373.464035] [<0000000000aaf58a>] kernel_thread_starter+0x6/0xc
[ 373.464052] [<0000000000aaf584>] kernel_thread_starter+0x0/0xc
[ 373.464054] INFO: lockdep is turned off.
Signed-off-by: Ursula Braun <ubraun@xxxxxxxxxxxxx>
---
net/smc/af_smc.c | 15 +++++++++------
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 9c3976bcde46..5c6d30eb4a71 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1153,9 +1153,9 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact)
}
/* listen worker: finish RDMA setup */
-static void smc_listen_rdma_finish(struct smc_sock *new_smc,
- struct smc_clc_msg_accept_confirm *cclc,
- int local_contact)
+static int smc_listen_rdma_finish(struct smc_sock *new_smc,
+ struct smc_clc_msg_accept_confirm *cclc,
+ int local_contact)
{
struct smc_link *link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
int reason_code = 0;
@@ -1178,11 +1178,12 @@ static void smc_listen_rdma_finish(struct smc_sock *new_smc,
if (reason_code)
goto decline;
}
- return;
+ return 0;
decline:
mutex_unlock(&smc_create_lgr_pending);
smc_listen_decline(new_smc, reason_code, local_contact);
+ return reason_code;
}
/* setup for RDMA connection of server */
@@ -1279,8 +1280,10 @@ static void smc_listen_work(struct work_struct *work)
}
/* finish worker */
- if (!ism_supported)
- smc_listen_rdma_finish(new_smc, &cclc, local_contact);
+ if (!ism_supported) {
+ if (smc_listen_rdma_finish(new_smc, &cclc, local_contact))
+ return;
+ }
smc_conn_save_peer_info(new_smc, &cclc);
mutex_unlock(&smc_create_lgr_pending);
smc_listen_out_connected(new_smc);
--
2.16.4
