Merge v2.6.37-rc8 into powerpc/next

2 files changed, 66 insertions, 19 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 4414a18c63b4..2268e6798124 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -117,7 +117,7 @@
 
 static struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
 static DEFINE_SPINLOCK(unix_table_lock);
-static atomic_t unix_nr_socks = ATOMIC_INIT(0);
+static atomic_long_t unix_nr_socks;
 
 #define unix_sockets_unbound    (&unix_socket_table[UNIX_HASH_SIZE])
 
@@ -360,13 +360,13 @@ static void unix_sock_destructor(struct sock *sk)
         if (u->addr)
                 unix_release_addr(u->addr);
 
-        atomic_dec(&unix_nr_socks);
+        atomic_long_dec(&unix_nr_socks);
         local_bh_disable();
         sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
         local_bh_enable();
 #ifdef UNIX_REFCNT_DEBUG
-        printk(KERN_DEBUG "UNIX %p is destroyed, %d are still alive.\n", sk,
-                atomic_read(&unix_nr_socks));
+        printk(KERN_DEBUG "UNIX %p is destroyed, %ld are still alive.\n", sk,
+                atomic_long_read(&unix_nr_socks));
 #endif
 }
 
@@ -606,8 +606,8 @@ static struct sock *unix_create1(struct net *net, struct socket *sock)
         struct sock *sk = NULL;
         struct unix_sock *u;
 
-        atomic_inc(&unix_nr_socks);
-        if (atomic_read(&unix_nr_socks) > 2 * get_max_files())
+        atomic_long_inc(&unix_nr_socks);
+        if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files())
                 goto out;
 
         sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto);
@@ -632,7 +632,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock)
         unix_insert_socket(unix_sockets_unbound, sk);
 out:
         if (sk == NULL)
-                atomic_dec(&unix_nr_socks);
+                atomic_long_dec(&unix_nr_socks);
         else {
                 local_bh_disable();
                 sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -692,6 +692,7 @@ static int unix_autobind(struct socket *sock)
         static u32 ordernum = 1;
         struct unix_address *addr;
         int err;
+        unsigned int retries = 0;
 
         mutex_lock(&u->readlock);
 
@@ -717,9 +718,17 @@ retry:
         if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type,
                                       addr->hash)) {
                 spin_unlock(&unix_table_lock);
-                /* Sanity yield. It is unusual case, but yet... */
-                if (!(ordernum&0xFF))
-                        yield();
+                /*
+                 * __unix_find_socket_byname() may take long time if many names
+                 * are already in use.
+                 */
+                cond_resched();
+                /* Give up if all names seems to be in use. */
+                if (retries++ == 0xFFFFF) {
+                        err = -ENOSPC;
+                        kfree(addr);
+                        goto out;
+                }
                 goto retry;
         }
         addr->hash ^= sk->sk_type;
@@ -1334,9 +1343,25 @@ static void unix_destruct_scm(struct sk_buff *skb)
         sock_wfree(skb);
 }
 
+#define MAX_RECURSION_LEVEL 4
+
 static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 {
         int i;
+        unsigned char max_level = 0;
+        int unix_sock_count = 0;
+
+        for (i = scm->fp->count - 1; i >= 0; i--) {
+                struct sock *sk = unix_get_socket(scm->fp->fp[i]);
+
+                if (sk) {
+                        unix_sock_count++;
+                        max_level = max(max_level,
+                                        unix_sk(sk)->recursion_level);
+                }
+        }
+        if (unlikely(max_level > MAX_RECURSION_LEVEL))
+                return -ETOOMANYREFS;
 
         /*
          * Need to duplicate file references for the sake of garbage
@@ -1347,9 +1372,11 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
         if (!UNIXCB(skb).fp)
                 return -ENOMEM;
 
-        for (i = scm->fp->count-1; i >= 0; i--)
-                unix_inflight(scm->fp->fp[i]);
-        return 0;
+        if (unix_sock_count) {
+                for (i = scm->fp->count - 1; i >= 0; i--)
+                        unix_inflight(scm->fp->fp[i]);
+        }
+        return max_level;
 }
 
 static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
@@ -1384,6 +1411,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
         struct sk_buff *skb;
         long timeo;
         struct scm_cookie tmp_scm;
+        int max_level;
 
         if (NULL == siocb->scm)
                 siocb->scm = &tmp_scm;
@@ -1422,8 +1450,9 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
                 goto out;
 
         err = unix_scm_to_skb(siocb->scm, skb, true);
-        if (err)
+        if (err < 0)
                 goto out_free;
+        max_level = err + 1;
         unix_get_secdata(siocb->scm, skb);
 
         skb_reset_transport_header(skb);
@@ -1502,7 +1531,11 @@ restart:
                 goto restart;
         }
 
+        if (sock_flag(other, SOCK_RCVTSTAMP))
+                __net_timestamp(skb);
         skb_queue_tail(&other->sk_receive_queue, skb);
+        if (max_level > unix_sk(other)->recursion_level)
+                unix_sk(other)->recursion_level = max_level;
         unix_state_unlock(other);
         other->sk_data_ready(other, len);
         sock_put(other);
@@ -1533,6 +1566,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
         int sent = 0;
         struct scm_cookie tmp_scm;
         bool fds_sent = false;
+        int max_level;
 
         if (NULL == siocb->scm)
                 siocb->scm = &tmp_scm;
@@ -1596,10 +1630,11 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 
                 /* Only send the fds in the first buffer */
                 err = unix_scm_to_skb(siocb->scm, skb, !fds_sent);
-                if (err) {
+                if (err < 0) {
                         kfree_skb(skb);
                         goto out_err;
                 }
+                max_level = err + 1;
                 fds_sent = true;
 
                 err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
@@ -1615,6 +1650,8 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
                         goto pipe_err_free;
 
                 skb_queue_tail(&other->sk_receive_queue, skb);
+                if (max_level > unix_sk(other)->recursion_level)
+                        unix_sk(other)->recursion_level = max_level;
                 unix_state_unlock(other);
                 other->sk_data_ready(other, size);
                 sent += size;
@@ -1713,6 +1750,9 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
         if (err)
                 goto out_free;
 
+        if (sock_flag(sk, SOCK_RCVTSTAMP))
+                __sock_recv_timestamp(msg, sk, skb);
+
         if (!siocb->scm) {
                 siocb->scm = &tmp_scm;
                 memset(&tmp_scm, 0, sizeof(tmp_scm));
@@ -1831,6 +1871,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
                 unix_state_lock(sk);
                 skb = skb_dequeue(&sk->sk_receive_queue);
                 if (skb == NULL) {
+                        unix_sk(sk)->recursion_level = 0;
                         if (copied >= target)
                                 goto unlock;
 
@@ -2024,11 +2065,10 @@ static unsigned int unix_poll(struct file *file, struct socket *sock, poll_table
         if (sk->sk_shutdown == SHUTDOWN_MASK)
                 mask |= POLLHUP;
         if (sk->sk_shutdown & RCV_SHUTDOWN)
-                mask |= POLLRDHUP;
+                mask |= POLLRDHUP | POLLIN | POLLRDNORM;
 
         /* readable? */
-        if (!skb_queue_empty(&sk->sk_receive_queue) ||
-            (sk->sk_shutdown & RCV_SHUTDOWN))
+        if (!skb_queue_empty(&sk->sk_receive_queue))
                 mask |= POLLIN | POLLRDNORM;
 
         /* Connection-based need to check for termination and startup */
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index c8df6fda0b1f..f89f83bf828e 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -96,7 +96,7 @@ static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait);
 unsigned int unix_tot_inflight;
 
 
-static struct sock *unix_get_socket(struct file *filp)
+struct sock *unix_get_socket(struct file *filp)
 {
         struct sock *u_sock = NULL;
         struct inode *inode = filp->f_path.dentry->d_inode;
@@ -259,9 +259,16 @@ static void inc_inflight_move_tail(struct unix_sock *u)
 }
 
 static bool gc_in_progress = false;
+#define UNIX_INFLIGHT_TRIGGER_GC 16000
 
 void wait_for_unix_gc(void)
 {
+        /*
+         * If number of inflight sockets is insane,
+         * force a garbage collect right now.
+         */
+        if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress)
+                unix_gc();
         wait_event(unix_gc_wait, gc_in_progress == false);
 }