From 6209344f5a3795d34b7f2c0061f49802283b6bdd Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Sun, 9 Nov 2008 15:23:57 +0100 Subject: net: unix: fix inflight counting bug in garbage collector Previously I assumed that the receive queues of candidates don't change during the GC. This is only half true, nothing can be received from the queues (see comment in unix_gc()), but buffers could be added through the other half of the socket pair, which may still have file descriptors referring to it. This can result in inc_inflight_move_tail() erronously increasing the "inflight" counter for a unix socket for which dec_inflight() wasn't previously called. This in turn can trigger the "BUG_ON(total_refs < inflight_refs)" in a later garbage collection run. Fix this by only manipulating the "inflight" counter for sockets which are candidates themselves. Duplicating the file references in unix_attach_fds() is also needed to prevent a socket becoming a candidate for GC while the skb that contains it is not yet queued. Reported-by: Andrea Bittau Signed-off-by: Miklos Szeredi CC: stable@kernel.org Signed-off-by: Linus Torvalds --- include/net/af_unix.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net/af_unix.h') diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 7dd29b7e461d..c29ff1da8a18 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -54,6 +54,7 @@ struct unix_sock { atomic_long_t inflight; spinlock_t lock; unsigned int gc_candidate : 1; + unsigned int gc_maybe_cycle : 1; wait_queue_head_t peer_wait; }; #define unix_sk(__sk) ((struct unix_sock *)__sk) -- cgit v1.2.3 From 5f23b734963ec7eaa3ebcd9050da0c9b7d143dd3 Mon Sep 17 00:00:00 2001 From: dann frazier Date: Wed, 26 Nov 2008 15:32:27 -0800 Subject: net: Fix soft lockups/OOM issues w/ unix garbage collector This is an implementation of David Miller's suggested fix in: https://bugzilla.redhat.com/show_bug.cgi?id=470201 It has been updated to use wait_event() instead of wait_event_interruptible(). Paraphrasing the description from the above report, it makes sendmsg() block while UNIX garbage collection is in progress. This avoids a situation where child processes continue to queue new FDs over a AF_UNIX socket to a parent which is in the exit path and running garbage collection on these FDs. This contention can result in soft lockups and oom-killing of unrelated processes. Signed-off-by: dann frazier Signed-off-by: David S. Miller --- include/net/af_unix.h | 1 + net/unix/af_unix.c | 2 ++ net/unix/garbage.c | 13 ++++++++++--- 3 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/net/af_unix.h') diff --git a/include/net/af_unix.h b/include/net/af_unix.h index c29ff1da8a18..1614d78c60ed 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -9,6 +9,7 @@ extern void unix_inflight(struct file *fp); extern void unix_notinflight(struct file *fp); extern void unix_gc(void); +extern void wait_for_unix_gc(void); #define UNIX_HASH_SIZE 256 diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index eb90f77bb0e2..66d5ac4773ab 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1343,6 +1343,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, if (NULL == siocb->scm) siocb->scm = &tmp_scm; + wait_for_unix_gc(); err = scm_send(sock, msg, siocb->scm); if (err < 0) return err; @@ -1493,6 +1494,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, if (NULL == siocb->scm) siocb->scm = &tmp_scm; + wait_for_unix_gc(); err = scm_send(sock, msg, siocb->scm); if (err < 0) return err; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 6d4a9a8de5ef..abb3ab34cb1e 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -80,6 +80,7 @@ #include #include #include +#include #include #include @@ -91,6 +92,7 @@ static LIST_HEAD(gc_inflight_list); static LIST_HEAD(gc_candidates); static DEFINE_SPINLOCK(unix_gc_lock); +static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); unsigned int unix_tot_inflight; @@ -266,12 +268,16 @@ static void inc_inflight_move_tail(struct unix_sock *u) list_move_tail(&u->link, &gc_candidates); } -/* The external entry point: unix_gc() */ +static bool gc_in_progress = false; -void unix_gc(void) +void wait_for_unix_gc(void) { - static bool gc_in_progress = false; + wait_event(unix_gc_wait, gc_in_progress == false); +} +/* The external entry point: unix_gc() */ +void unix_gc(void) +{ struct unix_sock *u; struct unix_sock *next; struct sk_buff_head hitlist; @@ -376,6 +382,7 @@ void unix_gc(void) /* All candidates should have been detached by now. */ BUG_ON(!list_empty(&gc_candidates)); gc_in_progress = false; + wake_up(&unix_gc_wait); out: spin_unlock(&unix_gc_lock); -- cgit v1.2.3