From f55bb7f9cb82dec2f2e803d7bd0fc5929248e4d8 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Tue, 21 Feb 2012 07:31:51 +0000 Subject: unix: Support peeking offset for datagram and seqpacket sockets The sk_peek_off manipulations are protected with the unix_sk->readlock mutex. This mutex is enough since all we need is to syncronize setting the offset vs reading the queue head. The latter is fully covered with the mentioned lock. The recently added __skb_recv_datagram's offset is used to pick the skb to read the data from. Signed-off-by: Pavel Emelyanov Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/unix/af_unix.c | 30 +++++++++++++++++++++++++----- 1 file changed, 25 insertions(+), 5 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 85d3bb7490a..3d9481de031 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -530,6 +530,16 @@ static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *, static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t, int); +static void unix_set_peek_off(struct sock *sk, int val) +{ + struct unix_sock *u = unix_sk(sk); + + mutex_lock(&u->readlock); + sk->sk_peek_off = val; + mutex_unlock(&u->readlock); +} + + static const struct proto_ops unix_stream_ops = { .family = PF_UNIX, .owner = THIS_MODULE, @@ -570,6 +580,7 @@ static const struct proto_ops unix_dgram_ops = { .recvmsg = unix_dgram_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, + .set_peek_off = unix_set_peek_off, }; static const struct proto_ops unix_seqpacket_ops = { @@ -591,6 +602,7 @@ static const struct proto_ops unix_seqpacket_ops = { .recvmsg = unix_seqpacket_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, + .set_peek_off = unix_set_peek_off, }; static struct proto unix_proto = { @@ -1756,6 +1768,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, int noblock = flags & MSG_DONTWAIT; struct sk_buff *skb; int err; + int peeked, skip; err = -EOPNOTSUPP; if (flags&MSG_OOB) @@ -1769,7 +1782,9 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, goto out; } - skb = skb_recv_datagram(sk, flags, noblock, &err); + skip = sk_peek_offset(sk, flags); + + skb = __skb_recv_datagram(sk, flags, &peeked, &skip, &err); if (!skb) { unix_state_lock(sk); /* Signal EOF on disconnected non-blocking SEQPACKET socket. */ @@ -1786,12 +1801,12 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, if (msg->msg_name) unix_copy_addr(msg, skb->sk); - if (size > skb->len) - size = skb->len; - else if (size < skb->len) + if (size > skb->len - skip) + size = skb->len - skip; + else if (size < skb->len - skip) msg->msg_flags |= MSG_TRUNC; - err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, size); + err = skb_copy_datagram_iovec(skb, skip, msg->msg_iov, size); if (err) goto out_free; @@ -1808,6 +1823,8 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, if (!(flags & MSG_PEEK)) { if (UNIXCB(skb).fp) unix_detach_fds(siocb->scm, skb); + + sk_peek_offset_bwd(sk, skb->len); } else { /* It is questionable: on PEEK we could: - do not return fds - good, but too simple 8) @@ -1821,6 +1838,9 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, clearly however! */ + + sk_peek_offset_fwd(sk, size); + if (UNIXCB(skb).fp) siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp); } -- cgit v1.2.3-70-g09d2 From fc0d753641f7b919c7273d9bd21ae6ab45e757f3 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Tue, 21 Feb 2012 07:32:06 +0000 Subject: unix: Support peeking offset for stream sockets The same here -- we can protect the sk_peek_off manipulations with the unix_sk->readlock mutex. The peeking of data from a stream socket is done in the datagram style, i.e. even if there's enough room for more data in the user buffer, only the head skb's data is copied in there. This feature is preserved when peeking data from a given offset -- the data is read till the nearest skb's boundary. Signed-off-by: Pavel Emelyanov Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/unix/af_unix.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3d9481de031..0be4d24f6ae 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -559,6 +559,7 @@ static const struct proto_ops unix_stream_ops = { .recvmsg = unix_stream_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, + .set_peek_off = unix_set_peek_off, }; static const struct proto_ops unix_dgram_ops = { @@ -1904,6 +1905,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, int target; int err = 0; long timeo; + int skip; err = -EINVAL; if (sk->sk_state != TCP_ESTABLISHED) @@ -1933,12 +1935,15 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, goto out; } + skip = sk_peek_offset(sk, flags); + do { int chunk; struct sk_buff *skb; unix_state_lock(sk); skb = skb_peek(&sk->sk_receive_queue); +again: if (skb == NULL) { unix_sk(sk)->recursion_level = 0; if (copied >= target) @@ -1973,6 +1978,13 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, unix_state_unlock(sk); break; } + + if (skip >= skb->len) { + skip -= skb->len; + skb = skb_peek_next(skb, &sk->sk_receive_queue); + goto again; + } + unix_state_unlock(sk); if (check_creds) { @@ -1992,8 +2004,8 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, sunaddr = NULL; } - chunk = min_t(unsigned int, skb->len, size); - if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) { + chunk = min_t(unsigned int, skb->len - skip, size); + if (memcpy_toiovec(msg->msg_iov, skb->data + skip, chunk)) { if (copied == 0) copied = -EFAULT; break; @@ -2005,6 +2017,8 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (!(flags & MSG_PEEK)) { skb_pull(skb, chunk); + sk_peek_offset_bwd(sk, chunk); + if (UNIXCB(skb).fp) unix_detach_fds(siocb->scm, skb); @@ -2022,6 +2036,8 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (UNIXCB(skb).fp) siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp); + sk_peek_offset_fwd(sk, chunk); + break; } } while (size); -- cgit v1.2.3-70-g09d2 From 9f6f9af7694ede6314bed281eec74d588ba9474f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Feb 2012 23:24:55 +0000 Subject: af_unix: MSG_TRUNC support for dgram sockets Piergiorgio Beruto expressed the need to fetch size of first datagram in queue for AF_UNIX sockets and suggested a patch against SIOCINQ ioctl. I suggested instead to implement MSG_TRUNC support as a recv() input flag, as already done for RAW, UDP & NETLINK sockets. len = recv(fd, &byte, 1, MSG_PEEK | MSG_TRUNC); MSG_TRUNC asks recv() to return the real length of the packet, even when is was longer than the passed buffer. There is risk that a userland application used MSG_TRUNC by accident (since it had no effect on af_unix sockets) and this might break after this patch. Signed-off-by: Eric Dumazet Tested-by: Piergiorgio Beruto CC: Michael Kerrisk Signed-off-by: David S. Miller --- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0be4d24f6ae..8ee85aa79fa 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1845,7 +1845,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, if (UNIXCB(skb).fp) siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp); } - err = size; + err = (flags & MSG_TRUNC) ? skb->len - skip : size; scm_recv(sock, msg, siocb->scm, flags); -- cgit v1.2.3-70-g09d2