The unix_dgram_poll() routine calls sock_poll_wait() not only for the wait
queue associated with the socket s that we are poll'ing against, but also calls
sock_poll_wait() for a remote peer socket p, if it is connected. Thus,
if we call poll()/select()/epoll() for the socket s, there are then
a couple of code paths in which the remote peer socket p and its associated
peer_wait queue can be freed before poll()/select()/epoll() have a chance
to remove themselves from the remote peer socket.
The way that remote peer socket can be freed are:
1. If s calls connect() to a connect to a new socket other than p, it will
drop its reference on p, and thus a close() on p will free it.
2. If we call close on p(), then a subsequent sendmsg() from s, will drop
the final reference to p, allowing it to be freed.
Address this issue, by reverting unix_dgram_poll() to only register with
the wait queue associated with s and register a callback with the remote peer
socket on connect() that will wake up the wait queue associated with s. If
scenarios 1 or 2 occur above we then simply remove the callback from the
remote peer. This then presents the expected semantics to poll()/select()/
epoll().
I've implemented this for sock-type, SOCK_RAW, SOCK_DGRAM, and SOCK_SEQPACKET
but not for SOCK_STREAM, since SOCK_STREAM does not use unix_dgram_poll().
Introduced in commit ec0d215f9420 ("af_unix: fix 'poll for write'/connected
DGRAM sockets").
Tested-by: Mathias Krause <mini...@googlemail.com>
Signed-off-by: Jason Baron <jba...@akamai.com>
---
include/net/af_unix.h | 1 +
net/unix/af_unix.c | 32 +++++++++++++++++++++++++++++++-
2 files changed, 32 insertions(+), 1 deletion(-)
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 4a167b3..9698aff 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -62,6 +62,7 @@ struct unix_sock {
#define UNIX_GC_CANDIDATE 0
#define UNIX_GC_MAYBE_CYCLE 1
struct socket_wq peer_wq;
+ wait_queue_t wait;
};
#define unix_sk(__sk) ((struct unix_sock *)__sk)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 03ee4d3..f789423 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -420,6 +420,9 @@ static void unix_release_sock(struct sock *sk, int embrion)
skpair = unix_peer(sk);
if (skpair != NULL) {
+ if (sk->sk_type != SOCK_STREAM)
+ remove_wait_queue(&unix_sk(skpair)->peer_wait,
+ &u->wait);
if (sk->sk_type == SOCK_STREAM || sk->sk_type ==
SOCK_SEQPACKET) {
unix_state_lock(skpair);
/* No more writes */
@@ -636,6 +639,16 @@ static struct proto unix_proto = {
*/
static struct lock_class_key af_unix_sk_receive_queue_lock_key;
+static int peer_wake(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+ struct unix_sock *u;
+
+ u = container_of(wait, struct unix_sock, wait);
+ wake_up_interruptible_sync_poll(sk_sleep(&u->sk), key);
+
+ return 0;
+}
+
static struct sock *unix_create1(struct net *net, struct socket *sock, int
kern)
{
struct sock *sk = NULL;
@@ -664,6 +677,7 @@ static struct sock *unix_create1(struct net *net, struct
socket *sock, int kern)
INIT_LIST_HEAD(&u->link);
mutex_init(&u->readlock); /* single task reading lock */
init_waitqueue_head(&u->peer_wait);
+ init_waitqueue_func_entry(&u->wait, peer_wake);
unix_insert_socket(unix_sockets_unbound(sk), sk);
out:
if (sk == NULL)
@@ -1030,7 +1044,11 @@ restart:
*/
if (unix_peer(sk)) {
struct sock *old_peer = unix_peer(sk);
+
+ remove_wait_queue(&unix_sk(old_peer)->peer_wait,
+ &unix_sk(sk)->wait);
unix_peer(sk) = other;
+ add_wait_queue(&unix_sk(other)->peer_wait, &unix_sk(sk)->wait);
unix_state_double_unlock(sk, other);
if (other != old_peer)
@@ -1038,8 +1056,12 @@ restart:
sock_put(old_peer);
} else {
unix_peer(sk) = other;
+ add_wait_queue(&unix_sk(other)->peer_wait, &unix_sk(sk)->wait);
unix_state_double_unlock(sk, other);
}
+ /* New remote may have created write space for us */
+ wake_up_interruptible_sync_poll(sk_sleep(sk),
+ POLLOUT | POLLWRNORM | POLLWRBAND);
return 0;
out_unlock:
@@ -1194,6 +1216,8 @@ restart:
sock_hold(sk);
unix_peer(newsk) = sk;
+ if (sk->sk_type == SOCK_SEQPACKET)
+ add_wait_queue(&unix_sk(sk)->peer_wait, &unix_sk(newsk)->wait);
newsk->sk_state = TCP_ESTABLISHED;
newsk->sk_type = sk->sk_type;
init_peercred(newsk);
@@ -1220,6 +1244,8 @@ restart:
smp_mb__after_atomic(); /* sock_hold() does an atomic_inc() */
unix_peer(sk) = newsk;
+ if (sk->sk_type == SOCK_SEQPACKET)
+ add_wait_queue(&unix_sk(newsk)->peer_wait, &unix_sk(sk)->wait);
unix_state_unlock(sk);
@@ -1254,6 +1280,10 @@ static int unix_socketpair(struct socket *socka, struct
socket *sockb)
sock_hold(skb);
unix_peer(ska) = skb;
unix_peer(skb) = ska;
+ if (ska->sk_type != SOCK_STREAM) {
+ add_wait_queue(&unix_sk(ska)->peer_wait, &unix_sk(skb)->wait);
+ add_wait_queue(&unix_sk(skb)->peer_wait, &unix_sk(ska)->wait);
+ }
init_peercred(ska);
init_peercred(skb);
@@ -1565,6 +1595,7 @@ restart:
unix_state_lock(sk);
if (unix_peer(sk) == other) {
unix_peer(sk) = NULL;
+ remove_wait_queue(&unix_sk(other)->peer_wait, &u->wait);
unix_state_unlock(sk);
unix_dgram_disconnected(sk, other);
@@ -2441,7 +2472,6 @@ static unsigned int unix_dgram_poll(struct file *file,
struct socket *sock,
other = unix_peer_get(sk);
if (other) {
if (unix_peer(other) != sk) {
- sock_poll_wait(file, &unix_sk(other)->peer_wait, wait);
if (unix_recvq_full(other))
writable = 0;
}
--
2.6.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
