[SCTP]: Verify all the paths to a peer via heartbeat before using them.

[linux-2.6] / net / unix / af_unix.c

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c323cc6a28b0e3f6042058879ead5dd9d5d36aaa..f70475bfb62a1c19d9d2215dcf479e9381427a9f 100644 (file)
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -83,7 +83,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/config.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
@@ -128,6 +127,30 @@ static atomic_t unix_nr_socks = ATOMIC_INIT(0);
 
 #define UNIX_ABSTRACT(sk)      (unix_sk(sk)->addr->hash != UNIX_HASH_SIZE)
 
+#ifdef CONFIG_SECURITY_NETWORK
+static void unix_get_peersec_dgram(struct sk_buff *skb)
+{
+       int err;
+
+       err = security_socket_getpeersec_dgram(skb, UNIXSECDATA(skb),
+                                              UNIXSECLEN(skb));
+       if (err)
+               *(UNIXSECDATA(skb)) = NULL;
+}
+
+static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
+{
+       scm->secdata = *UNIXSECDATA(skb);
+       scm->seclen = *UNIXSECLEN(skb);
+}
+#else
+static inline void unix_get_peersec_dgram(struct sk_buff *skb)
+{ }
+
+static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
+{ }
+#endif /* CONFIG_SECURITY_NETWORK */
+
 /*
  *  SMP locking strategy:
  *    hash table is protected with spinlock unix_table_lock
@@ -542,6 +565,14 @@ static struct proto unix_proto = {
        .obj_size = sizeof(struct unix_sock),
 };
 
+/*
+ * AF_UNIX sockets do not interact with hardware, hence they
+ * dont trigger interrupts - so it's safe for them to have
+ * bh-unsafe locking for their sk_receive_queue.lock. Split off
+ * this special lock-class by reinitializing the spinlock key:
+ */
+static struct lock_class_key af_unix_sk_receive_queue_lock_key;
+
 static struct sock * unix_create1(struct socket *sock)
 {
        struct sock *sk = NULL;
@@ -557,6 +588,8 @@ static struct sock * unix_create1(struct socket *sock)
        atomic_inc(&unix_nr_socks);
 
        sock_init_data(sock,sk);
+       lockdep_set_class(&sk->sk_receive_queue.lock,
+                               &af_unix_sk_receive_queue_lock_key);
 
        sk->sk_write_space      = unix_write_space;
        sk->sk_max_ack_backlog  = sysctl_unix_max_dgram_qlen;
@@ -566,7 +599,7 @@ static struct sock * unix_create1(struct socket *sock)
        u->mnt    = NULL;
        spin_lock_init(&u->lock);
        atomic_set(&u->inflight, sock ? 0 : -1);
-       init_MUTEX(&u->readsem); /* single task reading lock */
+       mutex_init(&u->readlock); /* single task reading lock */
        init_waitqueue_head(&u->peer_wait);
        unix_insert_socket(unix_sockets_unbound, sk);
 out:
@@ -623,7 +656,7 @@ static int unix_autobind(struct socket *sock)
        struct unix_address * addr;
        int err;
 
-       down(&u->readsem);
+       mutex_lock(&u->readlock);
 
        err = 0;
        if (u->addr)
@@ -661,7 +694,7 @@ retry:
        spin_unlock(&unix_table_lock);
        err = 0;
 
-out:   up(&u->readsem);
+out:   mutex_unlock(&u->readlock);
        return err;
 }
 
@@ -744,7 +777,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
                goto out;
        addr_len = err;
 
-       down(&u->readsem);
+       mutex_lock(&u->readlock);
 
        err = -EINVAL;
        if (u->addr)
@@ -816,7 +849,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 out_unlock:
        spin_unlock(&unix_table_lock);
 out_up:
-       up(&u->readsem);
+       mutex_unlock(&u->readlock);
 out:
        return err;
 
@@ -1022,7 +1055,7 @@ restart:
                goto out_unlock;
        }
 
-       unix_state_wlock(sk);
+       unix_state_wlock_nested(sk);
 
        if (sk->sk_state != st) {
                unix_state_wunlock(sk);
@@ -1291,6 +1324,8 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
        if (siocb->scm->fp)
                unix_attach_fds(siocb->scm, skb);
 
+       unix_get_peersec_dgram(skb);
+
        skb->h.raw = skb->data;
        err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len);
        if (err)
@@ -1427,15 +1462,15 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
        while(sent < len)
        {
                /*
-                *      Optimisation for the fact that under 0.01% of X messages typically
-                *      need breaking up.
+                *      Optimisation for the fact that under 0.01% of X
+                *      messages typically need breaking up.
                 */
 
-               size=len-sent;
+               size = len-sent;
 
                /* Keep two messages in the pipe so it schedules better */
-               if (size > sk->sk_sndbuf / 2 - 64)
-                       size = sk->sk_sndbuf / 2 - 64;
+               if (size > ((sk->sk_sndbuf >> 1) - 64))
+                       size = (sk->sk_sndbuf >> 1) - 64;
 
                if (size > SKB_MAX_ALLOC)
                        size = SKB_MAX_ALLOC;
@@ -1545,7 +1580,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 
        msg->msg_namelen = 0;
 
-       down(&u->readsem);
+       mutex_lock(&u->readlock);
 
        skb = skb_recv_datagram(sk, flags, noblock, &err);
        if (!skb)
@@ -1570,6 +1605,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
                memset(&tmp_scm, 0, sizeof(tmp_scm));
        }
        siocb->scm->creds = *UNIXCREDS(skb);
+       unix_set_secdata(siocb->scm, skb);
 
        if (!(flags & MSG_PEEK))
        {
@@ -1600,7 +1636,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 out_free:
        skb_free_datagram(sk,skb);
 out_unlock:
-       up(&u->readsem);
+       mutex_unlock(&u->readlock);
 out:
        return err;
 }
@@ -1676,7 +1712,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
                memset(&tmp_scm, 0, sizeof(tmp_scm));
        }
 
-       down(&u->readsem);
+       mutex_lock(&u->readlock);
 
        do
        {
@@ -1700,7 +1736,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
                        err = -EAGAIN;
                        if (!timeo)
                                break;
-                       up(&u->readsem);
+                       mutex_unlock(&u->readlock);
 
                        timeo = unix_stream_data_wait(sk, timeo);
 
@@ -1708,7 +1744,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
                                err = sock_intr_errno(timeo);
                                goto out;
                        }
-                       down(&u->readsem);
+                       mutex_lock(&u->readlock);
                        continue;
                }
 
@@ -1774,7 +1810,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
                }
        } while (size);
 
-       up(&u->readsem);
+       mutex_unlock(&u->readlock);
        scm_recv(sock, msg, siocb->scm, flags);
 out:
        return copied ? : err;
@@ -1878,6 +1914,8 @@ static unsigned int unix_poll(struct file * file, struct socket *sock, poll_tabl
                mask |= POLLERR;
        if (sk->sk_shutdown == SHUTDOWN_MASK)
                mask |= POLLHUP;
+       if (sk->sk_shutdown & RCV_SHUTDOWN)
+               mask |= POLLRDHUP;
 
        /* readable? */
        if (!skb_queue_empty(&sk->sk_receive_queue) ||