summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorUrsula Braun <ubraun@linux.ibm.com>2020-09-03 21:53:18 +0200
committerDavid S. Miller <davem@davemloft.net>2020-09-03 16:52:33 -0700
commit5fb8642a17aa2ab9077372977d67a72d3899a98d (patch)
tree8925e86535384bb9dd76991deab789daf4fcbcb4
parent1d8df41d896d75c6eababaa912e3a814585d9f61 (diff)
downloadlinux-5fb8642a17aa2ab9077372977d67a72d3899a98d.tar.gz
linux-5fb8642a17aa2ab9077372977d67a72d3899a98d.tar.bz2
linux-5fb8642a17aa2ab9077372977d67a72d3899a98d.zip
net/smc: fix sock refcounting in case of termination
When an ISM device is removed, all its linkgroups are terminated, i.e. all the corresponding connections are killed. Connection killing invokes smc_close_active_abort(), which decreases the sock refcount for certain states to simulate passive closing. And it cancels the close worker and has to give up the sock lock for this timeframe. This opens the door for a passive close worker or a socket close to run in between. In this case smc_close_active_abort() and passive close worker resp. smc_release() might do a sock_put for passive closing. This causes: [ 1323.315943] refcount_t: underflow; use-after-free. [ 1323.316055] WARNING: CPU: 3 PID: 54469 at lib/refcount.c:28 refcount_warn_saturate+0xe8/0x130 [ 1323.316069] Kernel panic - not syncing: panic_on_warn set ... [ 1323.316084] CPU: 3 PID: 54469 Comm: uperf Not tainted 5.9.0-20200826.rc2.git0.46328853ed20.300.fc32.s390x+debug #1 [ 1323.316096] Hardware name: IBM 2964 NC9 702 (z/VM 6.4.0) [ 1323.316108] Call Trace: [ 1323.316125] [<00000000c0d4aae8>] show_stack+0x90/0xf8 [ 1323.316143] [<00000000c15989b0>] dump_stack+0xa8/0xe8 [ 1323.316158] [<00000000c0d8344e>] panic+0x11e/0x288 [ 1323.316173] [<00000000c0d83144>] __warn+0xac/0x158 [ 1323.316187] [<00000000c1597a7a>] report_bug+0xb2/0x130 [ 1323.316201] [<00000000c0d36424>] monitor_event_exception+0x44/0xc0 [ 1323.316219] [<00000000c195c716>] pgm_check_handler+0x1da/0x238 [ 1323.316234] [<00000000c151844c>] refcount_warn_saturate+0xec/0x130 [ 1323.316280] ([<00000000c1518448>] refcount_warn_saturate+0xe8/0x130) [ 1323.316310] [<000003ff801f2e2a>] smc_release+0x192/0x1c8 [smc] [ 1323.316323] [<00000000c169f1fa>] __sock_release+0x5a/0xe0 [ 1323.316334] [<00000000c169f2ac>] sock_close+0x2c/0x40 [ 1323.316350] [<00000000c1086de0>] __fput+0xb8/0x278 [ 1323.316362] [<00000000c0db1e0e>] task_work_run+0x76/0xb8 [ 1323.316393] [<00000000c0d8ab84>] do_exit+0x26c/0x520 [ 1323.316408] [<00000000c0d8af08>] do_group_exit+0x48/0xc0 [ 1323.316421] [<00000000c0d8afa8>] __s390x_sys_exit_group+0x28/0x38 [ 1323.316433] [<00000000c195c32c>] system_call+0xe0/0x2b4 [ 1323.316446] 1 lock held by uperf/54469: [ 1323.316456] #0: 0000000044125e60 (&sb->s_type->i_mutex_key#9){+.+.}-{3:3}, at: __sock_release+0x44/0xe0 The patch rechecks sock state in smc_close_active_abort() after smc_close_cancel_work() to avoid duplicate decrease of sock refcount for the same purpose. Fixes: 611b63a12732 ("net/smc: cancel tx worker in case of socket aborts") Reviewed-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--net/smc/smc_close.c15
1 files changed, 8 insertions, 7 deletions
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 290270c821ca..35e30d39510d 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -116,7 +116,6 @@ static void smc_close_cancel_work(struct smc_sock *smc)
cancel_work_sync(&smc->conn.close_work);
cancel_delayed_work_sync(&smc->conn.tx_work);
lock_sock(sk);
- sk->sk_state = SMC_CLOSED;
}
/* terminate smc socket abnormally - active abort
@@ -134,22 +133,22 @@ void smc_close_active_abort(struct smc_sock *smc)
}
switch (sk->sk_state) {
case SMC_ACTIVE:
- sk->sk_state = SMC_PEERABORTWAIT;
- smc_close_cancel_work(smc);
- sk->sk_state = SMC_CLOSED;
- sock_put(sk); /* passive closing */
- break;
case SMC_APPCLOSEWAIT1:
case SMC_APPCLOSEWAIT2:
+ sk->sk_state = SMC_PEERABORTWAIT;
smc_close_cancel_work(smc);
+ if (sk->sk_state != SMC_PEERABORTWAIT)
+ break;
sk->sk_state = SMC_CLOSED;
- sock_put(sk); /* postponed passive closing */
+ sock_put(sk); /* (postponed) passive closing */
break;
case SMC_PEERCLOSEWAIT1:
case SMC_PEERCLOSEWAIT2:
case SMC_PEERFINCLOSEWAIT:
sk->sk_state = SMC_PEERABORTWAIT;
smc_close_cancel_work(smc);
+ if (sk->sk_state != SMC_PEERABORTWAIT)
+ break;
sk->sk_state = SMC_CLOSED;
smc_conn_free(&smc->conn);
release_clcsock = true;
@@ -159,6 +158,8 @@ void smc_close_active_abort(struct smc_sock *smc)
case SMC_APPFINCLOSEWAIT:
sk->sk_state = SMC_PEERABORTWAIT;
smc_close_cancel_work(smc);
+ if (sk->sk_state != SMC_PEERABORTWAIT)
+ break;
sk->sk_state = SMC_CLOSED;
smc_conn_free(&smc->conn);
release_clcsock = true;