[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <3552a4927029e9504f4d4b4e5de4908ab053a5dc.1432135413.git.hannes@stressinduktion.org>
Date: Wed, 20 May 2015 17:35:08 +0200
From: Hannes Frederic Sowa <hannes@...essinduktion.org>
To: netdev@...r.kernel.org
Subject: [PATCH net-next 4/4] net: af_unix: implement splice for stream af_unix sockets
unix_stream_recvmsg is refactored to unix_stream_read_generic in this
patch and enhanced to deal with pipe splicing. The refactoring is
inneglible, we mostly have to deal with a non-existing struct msghdr
argument.
Signed-off-by: Hannes Frederic Sowa <hannes@...essinduktion.org>
---
net/unix/af_unix.c | 141 +++++++++++++++++++++++++++++++++++++++++++++--------
1 file changed, 120 insertions(+), 21 deletions(-)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 9bb880a..d2d3ebf 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -520,6 +520,9 @@ 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 *,
@@ -561,6 +564,7 @@ static const struct proto_ops unix_stream_ops = {
.recvmsg = unix_stream_recvmsg,
.mmap = sock_no_mmap,
.sendpage = unix_stream_sendpage,
+ .splice_read = unix_stream_splice_read,
.set_peek_off = unix_set_peek_off,
};
@@ -1963,8 +1967,9 @@ 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);
@@ -1972,7 +1977,9 @@ 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) ||
@@ -1996,38 +2003,51 @@ 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 __always_inline
+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
@@ -2043,6 +2063,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
unix_state_lock(sk);
last = skb = skb_peek(&sk->sk_receive_queue);
+ last_len = last ? last->len : 0;
again:
if (skb == NULL) {
unix_sk(sk)->recursion_level = 0;
@@ -2065,16 +2086,17 @@ 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;
}
@@ -2083,6 +2105,7 @@ 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;
@@ -2099,18 +2122,20 @@ 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;
@@ -2148,11 +2173,85 @@ 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;
--
2.1.0
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists