From de43708924438fac2b0c04b099d50e3b523a5817 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Wed, 17 Aug 2022 00:51:54 +0300 Subject: af_unix: Show number of inflight fds for sockets in TCP_LISTEN state too TCP_LISTEN sockets is a special case. They preserve skb with a newly connected sock till accept() makes it fully functional socket. Receive queue of such socket may grow after connected peer send messages there. Since these messages may contain scm_fds, we should expose correct fdinfo::scm_fds for listening socket too. Signed-off-by: Kirill Tkhai Signed-off-by: David S. Miller --- net/unix/af_unix.c | 36 +++++++++++++++++++++++++++++++++--- 1 file changed, 33 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 bf338b782fc4..dea2972c8178 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -785,15 +785,45 @@ static int unix_set_peek_off(struct sock *sk, int val) } #ifdef CONFIG_PROC_FS +static int unix_count_nr_fds(struct sock *sk) +{ + struct sk_buff *skb; + struct unix_sock *u; + int nr_fds = 0; + + spin_lock(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); + while (skb) { + u = unix_sk(skb->sk); + nr_fds += atomic_read(&u->scm_stat.nr_fds); + skb = skb_peek_next(skb, &sk->sk_receive_queue); + } + spin_unlock(&sk->sk_receive_queue.lock); + + return nr_fds; +} + static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) { struct sock *sk = sock->sk; struct unix_sock *u; + int nr_fds; if (sk) { - u = unix_sk(sock->sk); - seq_printf(m, "scm_fds: %u\n", - atomic_read(&u->scm_stat.nr_fds)); + u = unix_sk(sk); + if (sock->type == SOCK_DGRAM) { + nr_fds = atomic_read(&u->scm_stat.nr_fds); + goto out_print; + } + + unix_state_lock(sk); + if (sk->sk_state != TCP_LISTEN) + nr_fds = atomic_read(&u->scm_stat.nr_fds); + else + nr_fds = unix_count_nr_fds(sk); + unix_state_unlock(sk); +out_print: + seq_printf(m, "scm_fds: %u\n", nr_fds); } } #else -- cgit From d6e3b27cbd2df555ff0736796ad2f9a17e74be8b Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Thu, 22 Sep 2022 21:59:26 -0700 Subject: af_unix: Refactor unix_read_skb() Similar to udp_read_skb(), delete the unnecessary while loop in unix_read_skb() for readability. Since recv_actor() cannot return a value greater than skb->len (see sk_psock_verdict_recv()), remove the redundant check. Suggested-by: Cong Wang Signed-off-by: Peilin Ye Link: https://lore.kernel.org/r/7009141683ad6cd3785daced3e4a80ba0eb773b5.1663909008.git.peilin.ye@bytedance.com Signed-off-by: Jakub Kicinski --- net/unix/af_unix.c | 34 ++++++++++------------------------ 1 file changed, 10 insertions(+), 24 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index dea2972c8178..c955c7253d4b 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2536,32 +2536,18 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t si static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { - int copied = 0; - - while (1) { - struct unix_sock *u = unix_sk(sk); - struct sk_buff *skb; - int used, err; - - mutex_lock(&u->iolock); - skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err); - mutex_unlock(&u->iolock); - if (!skb) - return err; + struct unix_sock *u = unix_sk(sk); + struct sk_buff *skb; + int err, copied; - used = recv_actor(sk, skb); - if (used <= 0) { - if (!copied) - copied = used; - kfree_skb(skb); - break; - } else if (used <= skb->len) { - copied += used; - } + mutex_lock(&u->iolock); + skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err); + mutex_unlock(&u->iolock); + if (!skb) + return err; - kfree_skb(skb); - break; - } + copied = recv_actor(sk, skb); + kfree_skb(skb); return copied; } -- cgit From 7a62ed61367b8fd01bae1e18e30602c25060d824 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 29 Sep 2022 08:52:04 -0700 Subject: af_unix: Fix memory leaks of the whole sk due to OOB skb. syzbot reported a sequence of memory leaks, and one of them indicated we failed to free a whole sk: unreferenced object 0xffff8880126e0000 (size 1088): comm "syz-executor419", pid 326, jiffies 4294773607 (age 12.609s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 7d 00 00 00 00 00 00 00 ........}....... 01 00 07 40 00 00 00 00 00 00 00 00 00 00 00 00 ...@............ backtrace: [<000000006fefe750>] sk_prot_alloc+0x64/0x2a0 net/core/sock.c:1970 [<0000000074006db5>] sk_alloc+0x3b/0x800 net/core/sock.c:2029 [<00000000728cd434>] unix_create1+0xaf/0x920 net/unix/af_unix.c:928 [<00000000a279a139>] unix_create+0x113/0x1d0 net/unix/af_unix.c:997 [<0000000068259812>] __sock_create+0x2ab/0x550 net/socket.c:1516 [<00000000da1521e1>] sock_create net/socket.c:1566 [inline] [<00000000da1521e1>] __sys_socketpair+0x1a8/0x550 net/socket.c:1698 [<000000007ab259e1>] __do_sys_socketpair net/socket.c:1751 [inline] [<000000007ab259e1>] __se_sys_socketpair net/socket.c:1748 [inline] [<000000007ab259e1>] __x64_sys_socketpair+0x97/0x100 net/socket.c:1748 [<000000007dedddc1>] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [<000000007dedddc1>] do_syscall_64+0x38/0x90 arch/x86/entry/common.c:80 [<000000009456679f>] entry_SYSCALL_64_after_hwframe+0x63/0xcd We can reproduce this issue by creating two AF_UNIX SOCK_STREAM sockets, send()ing an OOB skb to each other, and close()ing them without consuming the OOB skbs. int skpair[2]; socketpair(AF_UNIX, SOCK_STREAM, 0, skpair); send(skpair[0], "x", 1, MSG_OOB); send(skpair[1], "x", 1, MSG_OOB); close(skpair[0]); close(skpair[1]); Currently, we free an OOB skb in unix_sock_destructor() which is called via __sk_free(), but it's too late because the receiver's unix_sk(sk)->oob_skb is accounted against the sender's sk->sk_wmem_alloc and __sk_free() is called only when sk->sk_wmem_alloc is 0. In the repro sequences, we do not consume the OOB skb, so both two sk's sock_put() never reach __sk_free() due to the positive sk->sk_wmem_alloc. Then, no one can consume the OOB skb nor call __sk_free(), and we finally leak the two whole sk. Thus, we must free the unconsumed OOB skb earlier when close()ing the socket. Fixes: 314001f0bf92 ("af_unix: Add OOB support") Reported-by: syzbot Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/unix/af_unix.c | 13 +++++++------ 1 file changed, 7 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 bf338b782fc4..d686804119c9 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -569,12 +569,6 @@ static void unix_sock_destructor(struct sock *sk) skb_queue_purge(&sk->sk_receive_queue); -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - kfree_skb(u->oob_skb); - u->oob_skb = NULL; - } -#endif DEBUG_NET_WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc)); DEBUG_NET_WARN_ON_ONCE(!sk_unhashed(sk)); DEBUG_NET_WARN_ON_ONCE(sk->sk_socket); @@ -620,6 +614,13 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_state_unlock(sk); +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (u->oob_skb) { + kfree_skb(u->oob_skb); + u->oob_skb = NULL; + } +#endif + wake_up_interruptible_all(&u->peer_wait); if (skpair != NULL) { -- cgit