From e7947ea770d0de434d38a0f823e660d3fd4bebb5 Mon Sep 17 00:00:00 2001 From: Isaac Boukris Date: Tue, 1 Nov 2016 02:41:35 +0200 Subject: unix: escape all null bytes in abstract unix domain socket Abstract unix domain socket may embed null characters, these should be translated to '@' when printed out to proc the same way the null prefix is currently being translated. This helps for tools such as netstat, lsof and the proc based implementation in ss to show all the significant bytes of the name (instead of getting cut at the first null occurrence). Signed-off-by: Isaac Boukris Signed-off-by: David S. Miller --- net/unix/af_unix.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 145082e2ba36..5d1c14a2f268 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2812,7 +2812,8 @@ static int unix_seq_show(struct seq_file *seq, void *v) i++; } for ( ; i < len; i++) - seq_putc(seq, u->addr->name->sun_path[i]); + seq_putc(seq, u->addr->name->sun_path[i] ?: + '@'); } unix_state_unlock(s); seq_putc(seq, '\n'); -- cgit v1.2.3 From 7c13f97ffde63cc792c49ec1513f3974f2f05229 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 4 Nov 2016 11:28:59 +0100 Subject: udp: do fwd memory scheduling on dequeue A new argument is added to __skb_recv_datagram to provide an explicit skb destructor, invoked under the receive queue lock. The UDP protocol uses such argument to perform memory reclaiming on dequeue, so that the UDP protocol does not set anymore skb->desctructor. Instead explicit memory reclaiming is performed at close() time and when skbs are removed from the receive queue. The in kernel UDP protocol users now need to call a skb_recv_udp() variant instead of skb_recv_datagram() to properly perform memory accounting on dequeue. Overall, this allows acquiring only once the receive queue lock on dequeue. Tested using pktgen with random src port, 64 bytes packet, wire-speed on a 10G link as sender and udp_sink as the receiver, using an l4 tuple rxhash to stress the contention, and one or more udp_sink instances with reuseport. nr sinks vanilla patched 1 440 560 3 2150 2300 6 3650 3800 9 4450 4600 12 6250 6450 v1 -> v2: - do rmem and allocated memory scheduling under the receive lock - do bulk scheduling in first_packet_length() and in udp_destruct_sock() - avoid the typdef for the dequeue callback Suggested-by: Eric Dumazet Acked-by: Hannes Frederic Sowa Signed-off-by: Paolo Abeni Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/unix/af_unix.c | 4 ++-- 1 file changed, 2 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 145082e2ba36..87620183910e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2113,8 +2113,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, mutex_lock(&u->iolock); skip = sk_peek_offset(sk, flags); - skb = __skb_try_recv_datagram(sk, flags, &peeked, &skip, &err, - &last); + skb = __skb_try_recv_datagram(sk, flags, NULL, &peeked, &skip, + &err, &last); if (skb) break; -- cgit v1.2.3 From 06a77b07e3b44aea2b3c0e64de420ea2cfdcbaa9 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Thu, 17 Nov 2016 15:55:26 -0800 Subject: af_unix: conditionally use freezable blocking calls in read Commit 2b15af6f95 ("af_unix: use freezable blocking calls in read") converts schedule_timeout() to its freezable version, it was probably correct at that time, but later, commit 2b514574f7e8 ("net: af_unix: implement splice for stream af_unix sockets") breaks the strong requirement for a freezable sleep, according to commit 0f9548ca1091: We shouldn't try_to_freeze if locks are held. Holding a lock can cause a deadlock if the lock is later acquired in the suspend or hibernate path (e.g. by dpm). Holding a lock can also cause a deadlock in the case of cgroup_freezer if a lock is held inside a frozen cgroup that is later acquired by a process outside that group. The pipe_lock is still held at that point. So use freezable version only for the recvmsg call path, avoid impact for Android. Fixes: 2b514574f7e8 ("net: af_unix: implement splice for stream af_unix sockets") Reported-by: Dmitry Vyukov Cc: Tejun Heo Cc: Colin Cross Cc: Rafael J. Wysocki Cc: Hannes Frederic Sowa Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/unix/af_unix.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5d1c14a2f268..2358f2690ec5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2199,7 +2199,8 @@ 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, unsigned int last_len) + struct sk_buff *last, unsigned int last_len, + bool freezable) { struct sk_buff *tail; DEFINE_WAIT(wait); @@ -2220,7 +2221,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); unix_state_unlock(sk); - timeo = freezable_schedule_timeout(timeo); + if (freezable) + timeo = freezable_schedule_timeout(timeo); + else + timeo = schedule_timeout(timeo); unix_state_lock(sk); if (sock_flag(sk, SOCK_DEAD)) @@ -2250,7 +2254,8 @@ struct unix_stream_read_state { unsigned int splice_flags; }; -static int unix_stream_read_generic(struct unix_stream_read_state *state) +static int unix_stream_read_generic(struct unix_stream_read_state *state, + bool freezable) { struct scm_cookie scm; struct socket *sock = state->socket; @@ -2330,7 +2335,7 @@ again: mutex_unlock(&u->iolock); timeo = unix_stream_data_wait(sk, timeo, last, - last_len); + last_len, freezable); if (signal_pending(current)) { err = sock_intr_errno(timeo); @@ -2472,7 +2477,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, .flags = flags }; - return unix_stream_read_generic(&state); + return unix_stream_read_generic(&state, true); } static int unix_stream_splice_actor(struct sk_buff *skb, @@ -2503,7 +2508,7 @@ static ssize_t unix_stream_splice_read(struct socket *sock, loff_t *ppos, flags & SPLICE_F_NONBLOCK) state.flags = MSG_DONTWAIT; - return unix_stream_read_generic(&state); + return unix_stream_read_generic(&state, false); } static int unix_shutdown(struct socket *sock, int mode) -- cgit v1.2.3 From beef5121f3a4d1566c8ab8cd99b4e001862048cf Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 16 Dec 2016 11:02:53 +0100 Subject: Revert "af_unix: fix hard linked sockets on overlay" This reverts commit eb0a4a47ae89aaa0674ab3180de6a162f3be2ddf. Since commit 51f7e52dc943 ("ovl: share inode for hard link") there's no need to call d_real_inode() to check two overlay inodes for equality. Side effect of this revert is that it's no longer possible to connect one socket on overlayfs to one on the underlying layer (something which didn't make sense anyway). Signed-off-by: Miklos Szeredi --- net/unix/af_unix.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 2358f2690ec5..6f72508cccb7 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -315,7 +315,7 @@ static struct sock *unix_find_socket_byinode(struct inode *i) &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) { struct dentry *dentry = unix_sk(s)->path.dentry; - if (dentry && d_real_inode(dentry) == i) { + if (dentry && d_backing_inode(dentry) == i) { sock_hold(s); goto found; } @@ -913,7 +913,7 @@ static struct sock *unix_find_other(struct net *net, err = kern_path(sunname->sun_path, LOOKUP_FOLLOW, &path); if (err) goto fail; - inode = d_real_inode(path.dentry); + inode = d_backing_inode(path.dentry); err = inode_permission(inode, MAY_WRITE); if (err) goto put_fail; @@ -1040,7 +1040,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out_up; } addr->hash = UNIX_HASH_SIZE; - hash = d_real_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1); + hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1); spin_lock(&unix_table_lock); u->path = path; list = &unix_socket_table[hash]; -- cgit v1.2.3 From 7c0f6ba682b9c7632072ffbedf8d328c8f3c42ba Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 24 Dec 2016 11:46:01 -0800 Subject: Replace with globally This was entirely automated, using the script by Al: PATT='^[[:blank:]]*#[[:blank:]]*include[[:blank:]]*' sed -i -e "s!$PATT!#include !" \ $(git grep -l "$PATT"|grep -v ^include/linux/uaccess.h) to do the replacement at the end of the merge window. Requested-by: Al Viro Signed-off-by: Linus Torvalds --- 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 310882fb698e..127656ebe7be 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -100,7 +100,7 @@ #include #include #include -#include +#include #include #include #include -- cgit v1.2.3