1 files changed, 221 insertions, 26 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 06430598cf51..f25e1675b865 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -518,6 +518,11 @@ 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 +563,8 @@ 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 +626,7 @@ 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 +635,7 @@ 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 +694,7 @@ 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 +1094,7 @@ 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;
 
@@ -1720,6 +1726,101 @@ 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 +1961,9 @@ 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 +1971,9 @@ 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) ||
@@ -1897,38 +2001,50 @@ 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
@@ -1948,6 +2064,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 			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;
@@ -1970,16 +2087,17 @@ 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;
 		}
@@ -1988,6 +2106,7 @@ 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;
@@ -2004,18 +2123,20 @@ again:
 		} 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;
+			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;
@@ -2053,11 +2174,85 @@ 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;