@@ -8060,8 +8060,6 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
pr_debug("%s: begins, snum:%d\n", __func__, snum);
- local_bh_disable();
-
if (snum == 0) {
/* Search for an available port. */
int low, high, remaining, index;
@@ -8079,20 +8077,21 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
continue;
index = sctp_phashfn(net, rover);
head = &sctp_port_hashtable[index];
- spin_lock(&head->lock);
+ spin_lock_bh(&head->lock);
sctp_for_each_hentry(pp, &head->chain)
if ((pp->port == rover) &&
net_eq(net, pp->net))
goto next;
break;
next:
- spin_unlock(&head->lock);
+ spin_unlock_bh(&head->lock);
+ cond_resched();
} while (--remaining > 0);
/* Exhausted local port range during search? */
ret = 1;
if (remaining <= 0)
- goto fail;
+ return ret;
/* OK, here is the one we will use. HEAD (the port
* hash table list entry) is non-NULL and we hold it's
@@ -8107,7 +8106,7 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
* port iterator, pp being NULL.
*/
head = &sctp_port_hashtable[sctp_phashfn(net, snum)];
- spin_lock(&head->lock);
+ spin_lock_bh(&head->lock);
sctp_for_each_hentry(pp, &head->chain) {
if ((pp->port == snum) && net_eq(pp->net, net))
goto pp_found;
@@ -8207,10 +8206,7 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
ret = 0;
fail_unlock:
- spin_unlock(&head->lock);
-
-fail:
- local_bh_enable();
+ spin_unlock_bh(&head->lock);
return ret;
}
With disabling bh in the whole sctp_get_port_local(), when snum == 0 and too many ports have been used, the do-while loop will take the cpu for a long time and cause cpu stuck: [ ] watchdog: BUG: soft lockup - CPU#11 stuck for 22s! [ ] RIP: 0010:native_queued_spin_lock_slowpath+0x4de/0x940 [ ] Call Trace: [ ] _raw_spin_lock+0xc1/0xd0 [ ] sctp_get_port_local+0x527/0x650 [sctp] [ ] sctp_do_bind+0x208/0x5e0 [sctp] [ ] sctp_autobind+0x165/0x1e0 [sctp] [ ] sctp_connect_new_asoc+0x355/0x480 [sctp] [ ] __sctp_connect+0x360/0xb10 [sctp] There's no need to disable bh in the whole function of sctp_get_port_local. So fix this cpu stuck by removing local_bh_disable() called at the beginning, and using spin_lock_bh() instead. The same thing was actually done for inet_csk_get_port() in Commit ea8add2b1903 ("tcp/dccp: better use of ephemeral ports in bind()"). Thanks to Marcelo for pointing the buggy code out. v1->v2: - use cond_resched() to yield cpu to other tasks if needed, as Eric noticed. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Ying Xu <yinxu@redhat.com> Signed-off-by: Xin Long <lucien.xin@gmail.com> --- net/sctp/socket.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-)