Commit 3c32da19 authored by Kirill Tkhai's avatar Kirill Tkhai Committed by David S. Miller
Browse files

unix: Show number of pending scm files of receive queue in fdinfo 



Unix sockets like a block box. You never know what is stored there:
there may be a file descriptor holding a mount or a block device,
or there may be whole universes with namespaces, sockets with receive
queues full of sockets etc.

The patch adds a little debug and accounts number of files (not recursive),
which is in receive queue of a unix socket. Sometimes this is useful
to determine, that socket should be investigated or which task should
be killed to put reference counter on a resourse.

v2: Pass correct argument to lockdep

Signed-off-by: default avatarKirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent b4653342

include/net/af_unix.h

+5 −0
Original line number Diff line number Diff line
@@ -41,6 +41,10 @@ struct unix_skb_parms { 
	u32			consumed;

} __randomize_layout;



struct scm_stat {

	u32 nr_fds;

};



#define UNIXCB(skb)	(*(struct unix_skb_parms *)&((skb)->cb))



#define unix_state_lock(s)	spin_lock(&unix_sk(s)->lock)
@@ -65,6 +69,7 @@ struct unix_sock { 
#define UNIX_GC_MAYBE_CYCLE	1

	struct socket_wq	peer_wq;

	wait_queue_entry_t	peer_wake;

	struct scm_stat		scm_stat;

};



static inline struct unix_sock *unix_sk(const struct sock *sk)

net/unix/af_unix.c

+51 −5
Original line number Diff line number Diff line
@@ -676,6 +676,16 @@ static int unix_set_peek_off(struct sock *sk, int val) 
	return 0;

}



static void unix_show_fdinfo(struct seq_file *m, struct socket *sock)

{

	struct sock *sk = sock->sk;

	struct unix_sock *u;



	if (sk) {

		u = unix_sk(sock->sk);

		seq_printf(m, "scm_fds: %u\n", READ_ONCE(u->scm_stat.nr_fds));

	}

}



static const struct proto_ops unix_stream_ops = {

	.family =	PF_UNIX,
@@ -701,6 +711,7 @@ static const struct proto_ops unix_stream_ops = { 
	.sendpage =	unix_stream_sendpage,

	.splice_read =	unix_stream_splice_read,

	.set_peek_off =	unix_set_peek_off,

	.show_fdinfo =	unix_show_fdinfo,

};



static const struct proto_ops unix_dgram_ops = {
@@ -726,6 +737,7 @@ static const struct proto_ops unix_dgram_ops = { 
	.mmap =		sock_no_mmap,

	.sendpage =	sock_no_sendpage,

	.set_peek_off =	unix_set_peek_off,

	.show_fdinfo =	unix_show_fdinfo,

};



static const struct proto_ops unix_seqpacket_ops = {
@@ -751,6 +763,7 @@ static const struct proto_ops unix_seqpacket_ops = { 
	.mmap =		sock_no_mmap,

	.sendpage =	sock_no_sendpage,

	.set_peek_off =	unix_set_peek_off,

	.show_fdinfo =	unix_show_fdinfo,

};



static struct proto unix_proto = {
@@ -788,6 +801,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) 
	mutex_init(&u->bindlock); /* single task binding lock */

	init_waitqueue_head(&u->peer_wait);

	init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);

	memset(&u->scm_stat, 0, sizeof(struct scm_stat));

	unix_insert_socket(unix_sockets_unbound(sk), sk);

out:

	if (sk == NULL)
@@ -1572,6 +1586,28 @@ static bool unix_skb_scm_eq(struct sk_buff *skb, 
	       unix_secdata_eq(scm, skb);

}



static void scm_stat_add(struct sock *sk, struct sk_buff *skb)

{

	struct scm_fp_list *fp = UNIXCB(skb).fp;

	struct unix_sock *u = unix_sk(sk);



	lockdep_assert_held(&sk->sk_receive_queue.lock);



	if (unlikely(fp && fp->count))

		u->scm_stat.nr_fds += fp->count;

}



static void scm_stat_del(struct sock *sk, struct sk_buff *skb)

{

	struct scm_fp_list *fp = UNIXCB(skb).fp;

	struct unix_sock *u = unix_sk(sk);



	lockdep_assert_held(&sk->sk_receive_queue.lock);



	if (unlikely(fp && fp->count))

		u->scm_stat.nr_fds -= fp->count;

}



/*

 *	Send AF_UNIX data.

 */
@@ -1757,7 +1793,10 @@ restart_locked: 
	if (sock_flag(other, SOCK_RCVTSTAMP))

		__net_timestamp(skb);

	maybe_add_creds(skb, sock, other);

	skb_queue_tail(&other->sk_receive_queue, skb);

	spin_lock(&other->sk_receive_queue.lock);

	scm_stat_add(other, skb);

	__skb_queue_tail(&other->sk_receive_queue, skb);

	spin_unlock(&other->sk_receive_queue.lock);

	unix_state_unlock(other);

	other->sk_data_ready(other);

	sock_put(other);
@@ -1859,7 +1898,10 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, 
			goto pipe_err_free;



		maybe_add_creds(skb, sock, other);

		skb_queue_tail(&other->sk_receive_queue, skb);

		spin_lock(&other->sk_receive_queue.lock);

		scm_stat_add(other, skb);

		__skb_queue_tail(&other->sk_receive_queue, skb);

		spin_unlock(&other->sk_receive_queue.lock);

		unix_state_unlock(other);

		other->sk_data_ready(other);

		sent += size;
@@ -2058,8 +2100,8 @@ 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, NULL, &skip, &err,

					      &last);

		skb = __skb_try_recv_datagram(sk, flags, scm_stat_del,

					      &skip, &err, &last);

		if (skb)

			break;
@@ -2353,8 +2395,12 @@ unlock: 


			sk_peek_offset_bwd(sk, chunk);



			if (UNIXCB(skb).fp)

			if (UNIXCB(skb).fp) {

				spin_lock(&sk->sk_receive_queue.lock);

				scm_stat_del(sk, skb);

				spin_unlock(&sk->sk_receive_queue.lock);

				unix_detach_fds(&scm, skb);

			}



			if (unix_skb_len(skb))

				break;

CRA Git | Maintained and supported by SUSTech CRA and CCSE