2 files changed, 273 insertions, 72 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5266ea7b922b..03ee4d359f6a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -140,12 +140,17 @@ static struct hlist_head *unix_sockets_unbound(void *addr)
 #ifdef CONFIG_SECURITY_NETWORK
 static void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb)
 {
-	memcpy(UNIXSID(skb), &scm->secid, sizeof(u32));
+	UNIXCB(skb).secid = scm->secid;
 }
 
 static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
 {
-	scm->secid = *UNIXSID(skb);
+	scm->secid = UNIXCB(skb).secid;
+}
+
+static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb)
+{
+	return (scm->secid == UNIXCB(skb).secid);
 }
 #else
 static inline void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb)
@@ -153,6 +158,11 @@ static inline void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb)
 
 static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
 { }
+
+static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb)
+{
+	return true;
+}
 #endif /* CONFIG_SECURITY_NETWORK */
 
 /*
@@ -518,6 +528,11 @@ static int unix_ioctl(struct socket *, unsigned int, unsigned long);
 static int unix_shutdown(struct socket *, int);
 static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t);
 static int unix_stream_recvmsg(struct socket *, struct msghdr *, size_t, int);
+static ssize_t unix_stream_sendpage(struct socket *, struct page *, int offset,
+				    size_t size, int flags);
+static ssize_t unix_stream_splice_read(struct socket *,  loff_t *ppos,
+				       struct pipe_inode_info *, size_t size,
+				       unsigned int flags);
 static int unix_dgram_sendmsg(struct socket *, struct msghdr *, size_t);
 static int unix_dgram_recvmsg(struct socket *, struct msghdr *, size_t, int);
 static int unix_dgram_connect(struct socket *, struct sockaddr *,
@@ -558,7 +573,8 @@ static const struct proto_ops unix_stream_ops = {
 	.sendmsg =	unix_stream_sendmsg,
 	.recvmsg =	unix_stream_recvmsg,
 	.mmap =		sock_no_mmap,
-	.sendpage =	sock_no_sendpage,
+	.sendpage =	unix_stream_sendpage,
+	.splice_read =	unix_stream_splice_read,
 	.set_peek_off =	unix_set_peek_off,
 };
 
@@ -620,7 +636,7 @@ static struct proto unix_proto = {
  */
 static struct lock_class_key af_unix_sk_receive_queue_lock_key;
 
-static struct sock *unix_create1(struct net *net, struct socket *sock)
+static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
 {
 	struct sock *sk = NULL;
 	struct unix_sock *u;
@@ -629,7 +645,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock)
 	if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files())
 		goto out;
 
-	sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto);
+	sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto, kern);
 	if (!sk)
 		goto out;
 
@@ -688,7 +704,7 @@ static int unix_create(struct net *net, struct socket *sock, int protocol,
 		return -ESOCKTNOSUPPORT;
 	}
 
-	return unix_create1(net, sock) ? 0 : -ENOMEM;
+	return unix_create1(net, sock, kern) ? 0 : -ENOMEM;
 }
 
 static int unix_release(struct socket *sock)
@@ -1088,7 +1104,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	err = -ENOMEM;
 
 	/* create new sock for complete connection */
-	newsk = unix_create1(sock_net(sk), NULL);
+	newsk = unix_create1(sock_net(sk), NULL, 0);
 	if (newsk == NULL)
 		goto out;
 
@@ -1408,6 +1424,7 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen
 	UNIXCB(skb).uid = scm->creds.uid;
 	UNIXCB(skb).gid = scm->creds.gid;
 	UNIXCB(skb).fp = NULL;
+	unix_get_secdata(scm, skb);
 	if (scm->fp && send_fds)
 		err = unix_attach_fds(scm, skb);
 
@@ -1503,7 +1520,6 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (err < 0)
 		goto out_free;
 	max_level = err + 1;
-	unix_get_secdata(&scm, skb);
 
 	skb_put(skb, len - data_len);
 	skb->data_len = data_len;
@@ -1720,6 +1736,101 @@ out_err:
 	return sent ? : err;
 }
 
+static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page,
+				    int offset, size_t size, int flags)
+{
+	int err = 0;
+	bool send_sigpipe = true;
+	struct sock *other, *sk = socket->sk;
+	struct sk_buff *skb, *newskb = NULL, *tail = NULL;
+
+	if (flags & MSG_OOB)
+		return -EOPNOTSUPP;
+
+	other = unix_peer(sk);
+	if (!other || sk->sk_state != TCP_ESTABLISHED)
+		return -ENOTCONN;
+
+	if (false) {
+alloc_skb:
+		unix_state_unlock(other);
+		mutex_unlock(&unix_sk(other)->readlock);
+		newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
+					      &err, 0);
+		if (!newskb)
+			return err;
+	}
+
+	/* we must acquire readlock as we modify already present
+	 * skbs in the sk_receive_queue and mess with skb->len
+	 */
+	err = mutex_lock_interruptible(&unix_sk(other)->readlock);
+	if (err) {
+		err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;
+		send_sigpipe = false;
+		goto err;
+	}
+
+	if (sk->sk_shutdown & SEND_SHUTDOWN) {
+		err = -EPIPE;
+		goto err_unlock;
+	}
+
+	unix_state_lock(other);
+
+	if (sock_flag(other, SOCK_DEAD) ||
+	    other->sk_shutdown & RCV_SHUTDOWN) {
+		err = -EPIPE;
+		goto err_state_unlock;
+	}
+
+	skb = skb_peek_tail(&other->sk_receive_queue);
+	if (tail && tail == skb) {
+		skb = newskb;
+	} else if (!skb) {
+		if (newskb)
+			skb = newskb;
+		else
+			goto alloc_skb;
+	} else if (newskb) {
+		/* this is fast path, we don't necessarily need to
+		 * call to kfree_skb even though with newskb == NULL
+		 * this - does no harm
+		 */
+		consume_skb(newskb);
+	}
+
+	if (skb_append_pagefrags(skb, page, offset, size)) {
+		tail = skb;
+		goto alloc_skb;
+	}
+
+	skb->len += size;
+	skb->data_len += size;
+	skb->truesize += size;
+	atomic_add(size, &sk->sk_wmem_alloc);
+
+	if (newskb)
+		__skb_queue_tail(&other->sk_receive_queue, newskb);
+
+	unix_state_unlock(other);
+	mutex_unlock(&unix_sk(other)->readlock);
+
+	other->sk_data_ready(other);
+
+	return size;
+
+err_state_unlock:
+	unix_state_unlock(other);
+err_unlock:
+	mutex_unlock(&unix_sk(other)->readlock);
+err:
+	kfree_skb(newskb);
+	if (send_sigpipe && !(flags & MSG_NOSIGNAL))
+		send_sig(SIGPIPE, current, 0);
+	return err;
+}
+
 static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg,
 				  size_t len)
 {
@@ -1860,8 +1971,9 @@ out:
  *	Sleep until more data has arrived. But check for races..
  */
 static long unix_stream_data_wait(struct sock *sk, long timeo,
-				  struct sk_buff *last)
+				  struct sk_buff *last, unsigned int last_len)
 {
+	struct sk_buff *tail;
 	DEFINE_WAIT(wait);
 
 	unix_state_lock(sk);
@@ -1869,7 +1981,9 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 	for (;;) {
 		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 
-		if (skb_peek_tail(&sk->sk_receive_queue) != last ||
+		tail = skb_peek_tail(&sk->sk_receive_queue);
+		if (tail != last ||
+		    (tail && tail->len != last_len) ||
 		    sk->sk_err ||
 		    (sk->sk_shutdown & RCV_SHUTDOWN) ||
 		    signal_pending(current) ||
@@ -1880,6 +1994,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 		unix_state_unlock(sk);
 		timeo = freezable_schedule_timeout(timeo);
 		unix_state_lock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD))
+			break;
+
 		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	}
 
@@ -1893,38 +2011,50 @@ static unsigned int unix_skb_len(const struct sk_buff *skb)
 	return skb->len - UNIXCB(skb).consumed;
 }
 
-static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
-			       size_t size, int flags)
+struct unix_stream_read_state {
+	int (*recv_actor)(struct sk_buff *, int, int,
+			  struct unix_stream_read_state *);
+	struct socket *socket;
+	struct msghdr *msg;
+	struct pipe_inode_info *pipe;
+	size_t size;
+	int flags;
+	unsigned int splice_flags;
+};
+
+static int unix_stream_read_generic(struct unix_stream_read_state *state)
 {
 	struct scm_cookie scm;
+	struct socket *sock = state->socket;
 	struct sock *sk = sock->sk;
 	struct unix_sock *u = unix_sk(sk);
-	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
 	int copied = 0;
+	int flags = state->flags;
 	int noblock = flags & MSG_DONTWAIT;
-	int check_creds = 0;
+	bool check_creds = false;
 	int target;
 	int err = 0;
 	long timeo;
 	int skip;
+	size_t size = state->size;
+	unsigned int last_len;
 
 	err = -EINVAL;
 	if (sk->sk_state != TCP_ESTABLISHED)
 		goto out;
 
 	err = -EOPNOTSUPP;
-	if (flags&MSG_OOB)
+	if (flags & MSG_OOB)
 		goto out;
 
-	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
+	target = sock_rcvlowat(sk, flags & MSG_WAITALL, size);
 	timeo = sock_rcvtimeo(sk, noblock);
 
+	memset(&scm, 0, sizeof(scm));
+
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
 	 */
-
-	memset(&scm, 0, sizeof(scm));
-
 	err = mutex_lock_interruptible(&u->readlock);
 	if (unlikely(err)) {
 		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
@@ -1939,7 +2069,12 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 		struct sk_buff *skb, *last;
 
 		unix_state_lock(sk);
+		if (sock_flag(sk, SOCK_DEAD)) {
+			err = -ECONNRESET;
+			goto unlock;
+		}
 		last = skb = skb_peek(&sk->sk_receive_queue);
+		last_len = last ? last->len : 0;
 again:
 		if (skb == NULL) {
 			unix_sk(sk)->recursion_level = 0;
@@ -1962,16 +2097,17 @@ again:
 				break;
 			mutex_unlock(&u->readlock);
 
-			timeo = unix_stream_data_wait(sk, timeo, last);
+			timeo = unix_stream_data_wait(sk, timeo, last,
+						      last_len);
 
-			if (signal_pending(current)
-			    ||  mutex_lock_interruptible(&u->readlock)) {
+			if (signal_pending(current) ||
+			    mutex_lock_interruptible(&u->readlock)) {
 				err = sock_intr_errno(timeo);
 				goto out;
 			}
 
 			continue;
- unlock:
+unlock:
 			unix_state_unlock(sk);
 			break;
 		}
@@ -1980,6 +2116,7 @@ again:
 		while (skip >= unix_skb_len(skb)) {
 			skip -= unix_skb_len(skb);
 			last = skb;
+			last_len = skb->len;
 			skb = skb_peek_next(skb, &sk->sk_receive_queue);
 			if (!skb)
 				goto again;
@@ -1991,23 +2128,27 @@ again:
 			/* Never glue messages from different writers */
 			if ((UNIXCB(skb).pid  != scm.pid) ||
 			    !uid_eq(UNIXCB(skb).uid, scm.creds.uid) ||
-			    !gid_eq(UNIXCB(skb).gid, scm.creds.gid))
+			    !gid_eq(UNIXCB(skb).gid, scm.creds.gid) ||
+			    !unix_secdata_eq(&scm, skb))
 				break;
 		} else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
 			/* Copy credentials */
 			scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
-			check_creds = 1;
+			unix_set_secdata(&scm, skb);
+			check_creds = true;
 		}
 
 		/* Copy address just once */
-		if (sunaddr) {
-			unix_copy_addr(msg, skb->sk);
+		if (state->msg && state->msg->msg_name) {
+			DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr,
+					 state->msg->msg_name);
+			unix_copy_addr(state->msg, skb->sk);
 			sunaddr = NULL;
 		}
 
 		chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size);
-		if (skb_copy_datagram_msg(skb, UNIXCB(skb).consumed + skip,
-					  msg, chunk)) {
+		chunk = state->recv_actor(skb, skip, chunk, state);
+		if (chunk < 0) {
 			if (copied == 0)
 				copied = -EFAULT;
 			break;
@@ -2045,11 +2186,85 @@ again:
 	} while (size);
 
 	mutex_unlock(&u->readlock);
-	scm_recv(sock, msg, &scm, flags);
+	if (state->msg)
+		scm_recv(sock, state->msg, &scm, flags);
+	else
+		scm_destroy(&scm);
 out:
 	return copied ? : err;
 }
 
+static int unix_stream_read_actor(struct sk_buff *skb,
+				  int skip, int chunk,
+				  struct unix_stream_read_state *state)
+{
+	int ret;
+
+	ret = skb_copy_datagram_msg(skb, UNIXCB(skb).consumed + skip,
+				    state->msg, chunk);
+	return ret ?: chunk;
+}
+
+static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
+			       size_t size, int flags)
+{
+	struct unix_stream_read_state state = {
+		.recv_actor = unix_stream_read_actor,
+		.socket = sock,
+		.msg = msg,
+		.size = size,
+		.flags = flags
+	};
+
+	return unix_stream_read_generic(&state);
+}
+
+static ssize_t skb_unix_socket_splice(struct sock *sk,
+				      struct pipe_inode_info *pipe,
+				      struct splice_pipe_desc *spd)
+{
+	int ret;
+	struct unix_sock *u = unix_sk(sk);
+
+	mutex_unlock(&u->readlock);
+	ret = splice_to_pipe(pipe, spd);
+	mutex_lock(&u->readlock);
+
+	return ret;
+}
+
+static int unix_stream_splice_actor(struct sk_buff *skb,
+				    int skip, int chunk,
+				    struct unix_stream_read_state *state)
+{
+	return skb_splice_bits(skb, state->socket->sk,
+			       UNIXCB(skb).consumed + skip,
+			       state->pipe, chunk, state->splice_flags,
+			       skb_unix_socket_splice);
+}
+
+static ssize_t unix_stream_splice_read(struct socket *sock,  loff_t *ppos,
+				       struct pipe_inode_info *pipe,
+				       size_t size, unsigned int flags)
+{
+	struct unix_stream_read_state state = {
+		.recv_actor = unix_stream_splice_actor,
+		.socket = sock,
+		.pipe = pipe,
+		.size = size,
+		.splice_flags = flags,
+	};
+
+	if (unlikely(*ppos))
+		return -ESPIPE;
+
+	if (sock->file->f_flags & O_NONBLOCK ||
+	    flags & SPLICE_F_NONBLOCK)
+		state.flags = MSG_DONTWAIT;
+
+	return unix_stream_read_generic(&state);
+}
+
 static int unix_shutdown(struct socket *sock, int mode)
 {
 	struct sock *sk = sock->sk;
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 99f7012b23b9..a73a226f2d33 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -95,39 +95,36 @@ static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait);
 
 unsigned int unix_tot_inflight;
 
-
 struct sock *unix_get_socket(struct file *filp)
 {
 	struct sock *u_sock = NULL;
 	struct inode *inode = file_inode(filp);
 
-	/*
-	 *	Socket ?
-	 */
+	/* Socket ? */
 	if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) {
 		struct socket *sock = SOCKET_I(inode);
 		struct sock *s = sock->sk;
 
-		/*
-		 *	PF_UNIX ?
-		 */
+		/* PF_UNIX ? */
 		if (s && sock->ops && sock->ops->family == PF_UNIX)
 			u_sock = s;
 	}
 	return u_sock;
 }
 
-/*
- *	Keep the number of times in flight count for the file
- *	descriptor if it is for an AF_UNIX socket.
+/* Keep the number of times in flight count for the file
+ * descriptor if it is for an AF_UNIX socket.
  */
 
 void unix_inflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
+
 		spin_lock(&unix_gc_lock);
+
 		if (atomic_long_inc_return(&u->inflight) == 1) {
 			BUG_ON(!list_empty(&u->link));
 			list_add_tail(&u->link, &gc_inflight_list);
@@ -142,10 +139,13 @@ void unix_inflight(struct file *fp)
 void unix_notinflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
+
 		spin_lock(&unix_gc_lock);
 		BUG_ON(list_empty(&u->link));
+
 		if (atomic_long_dec_and_test(&u->inflight))
 			list_del_init(&u->link);
 		unix_tot_inflight--;
@@ -161,32 +161,27 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
 
 	spin_lock(&x->sk_receive_queue.lock);
 	skb_queue_walk_safe(&x->sk_receive_queue, skb, next) {
-		/*
-		 *	Do we have file descriptors ?
-		 */
+		/* Do we have file descriptors ? */
 		if (UNIXCB(skb).fp) {
 			bool hit = false;
-			/*
-			 *	Process the descriptors of this socket
-			 */
+			/* Process the descriptors of this socket */
 			int nfd = UNIXCB(skb).fp->count;
 			struct file **fp = UNIXCB(skb).fp->fp;
+
 			while (nfd--) {
-				/*
-				 *	Get the socket the fd matches
-				 *	if it indeed does so
-				 */
+				/* Get the socket the fd matches if it indeed does so */
 				struct sock *sk = unix_get_socket(*fp++);
+
 				if (sk) {
 					struct unix_sock *u = unix_sk(sk);
 
-					/*
-					 * Ignore non-candidates, they could
+					/* Ignore non-candidates, they could
 					 * have been added to the queues after
 					 * starting the garbage collection
 					 */
 					if (test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) {
 						hit = true;
+
 						func(u);
 					}
 				}
@@ -203,24 +198,22 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
 static void scan_children(struct sock *x, void (*func)(struct unix_sock *),
 			  struct sk_buff_head *hitlist)
 {
-	if (x->sk_state != TCP_LISTEN)
+	if (x->sk_state != TCP_LISTEN) {
 		scan_inflight(x, func, hitlist);
-	else {
+	} else {
 		struct sk_buff *skb;
 		struct sk_buff *next;
 		struct unix_sock *u;
 		LIST_HEAD(embryos);
 
-		/*
-		 * For a listening socket collect the queued embryos
+		/* For a listening socket collect the queued embryos
 		 * and perform a scan on them as well.
 		 */
 		spin_lock(&x->sk_receive_queue.lock);
 		skb_queue_walk_safe(&x->sk_receive_queue, skb, next) {
 			u = unix_sk(skb->sk);
 
-			/*
-			 * An embryo cannot be in-flight, so it's safe
+			/* An embryo cannot be in-flight, so it's safe
 			 * to use the list link.
 			 */
 			BUG_ON(!list_empty(&u->link));
@@ -249,8 +242,7 @@ static void inc_inflight(struct unix_sock *usk)
 static void inc_inflight_move_tail(struct unix_sock *u)
 {
 	atomic_long_inc(&u->inflight);
-	/*
-	 * If this still might be part of a cycle, move it to the end
+	/* If this still might be part of a cycle, move it to the end
 	 * of the list, so that it's checked even if it was already
 	 * passed over
 	 */
@@ -263,8 +255,7 @@ static bool gc_in_progress;
 
 void wait_for_unix_gc(void)
 {
-	/*
-	 * If number of inflight sockets is insane,
+	/* If number of inflight sockets is insane,
 	 * force a garbage collect right now.
 	 */
 	if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress)
@@ -288,8 +279,7 @@ void unix_gc(void)
 		goto out;
 
 	gc_in_progress = true;
-	/*
-	 * First, select candidates for garbage collection.  Only
+	/* First, select candidates for garbage collection.  Only
 	 * in-flight sockets are considered, and from those only ones
 	 * which don't have any external reference.
 	 *
@@ -320,15 +310,13 @@ void unix_gc(void)
 		}
 	}
 
-	/*
-	 * Now remove all internal in-flight reference to children of
+	/* Now remove all internal in-flight reference to children of
 	 * the candidates.
 	 */
 	list_for_each_entry(u, &gc_candidates, link)
 		scan_children(&u->sk, dec_inflight, NULL);
 
-	/*
-	 * Restore the references for children of all candidates,
+	/* Restore the references for children of all candidates,
 	 * which have remaining references.  Do this recursively, so
 	 * only those remain, which form cyclic references.
 	 *
@@ -350,8 +338,7 @@ void unix_gc(void)
 	}
 	list_del(&cursor);
 
-	/*
-	 * not_cycle_list contains those sockets which do not make up a
+	/* not_cycle_list contains those sockets which do not make up a
 	 * cycle.  Restore these to the inflight list.
 	 */
 	while (!list_empty(&not_cycle_list)) {
@@ -360,8 +347,7 @@ void unix_gc(void)
 		list_move_tail(&u->link, &gc_inflight_list);
 	}
 
-	/*
-	 * Now gc_candidates contains only garbage.  Restore original
+	/* Now gc_candidates contains only garbage.  Restore original
 	 * inflight counters for these as well, and remove the skbuffs
 	 * which are creating the cycle(s).
 	 */