From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.8 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS, URIBL_BLOCKED autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 039EDC5DF61 for ; Thu, 7 Nov 2019 12:15:16 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id C786F21882 for ; Thu, 7 Nov 2019 12:15:15 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2388297AbfKGMPP (ORCPT ); Thu, 7 Nov 2019 07:15:15 -0500 Received: from relay.sw.ru ([185.231.240.75]:59046 "EHLO relay.sw.ru" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727385AbfKGMPO (ORCPT ); Thu, 7 Nov 2019 07:15:14 -0500 Received: from [172.16.24.104] (helo=localhost.localdomain) by relay.sw.ru with esmtp (Exim 4.92.3) (envelope-from ) id 1iSggk-0004vA-RQ; Thu, 07 Nov 2019 15:14:59 +0300 Subject: [PATCH 2/2] unix: Show number of pending scm files of receive queue in fdinfo From: Kirill Tkhai To: davem@davemloft.net, pankaj.laxminarayan.bharadiya@intel.com, keescook@chromium.org, viro@zeniv.linux.org.uk, hare@suse.com, tglx@linutronix.de, ktkhai@virtuozzo.com, edumazet@google.com, arnd@arndb.de, axboe@kernel.dk, netdev@vger.kernel.org Date: Thu, 07 Nov 2019 15:14:48 +0300 Message-ID: <157312888801.4594.3989315759606369945.stgit@localhost.localdomain> In-Reply-To: <157312863230.4594.18421480718399996953.stgit@localhost.localdomain> References: <157312863230.4594.18421480718399996953.stgit@localhost.localdomain> User-Agent: StGit/0.19 MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org 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. Signed-off-by: Kirill Tkhai --- include/net/af_unix.h | 5 ++++ net/unix/af_unix.c | 56 +++++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 56 insertions(+), 5 deletions(-) diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 3426d6dacc45..17e10fba2152 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -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) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f0a074356012..991f66057718 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -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 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, 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 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, 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;