bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Cong Wang <xiyou.wangcong@gmail.com>
To: netdev@vger.kernel.org
Cc: bpf@vger.kernel.org, jiang.wang@bytedance.com,
	duanxiongchun@bytedance.com, wangdongdong.6@bytedance.com,
	Cong Wang <cong.wang@bytedance.com>,
	John Fastabend <john.fastabend@gmail.com>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Jakub Sitnicki <jakub@cloudflare.com>,
	Lorenz Bauer <lmb@cloudflare.com>
Subject: [Patch bpf-next v3 05/10] af_unix: implement unix_dgram_bpf_recvmsg()
Date: Sun, 25 Apr 2021 19:49:56 -0700	[thread overview]
Message-ID: <20210426025001.7899-6-xiyou.wangcong@gmail.com> (raw)
In-Reply-To: <20210426025001.7899-1-xiyou.wangcong@gmail.com>

From: Cong Wang <cong.wang@bytedance.com>

We have to implement unix_dgram_bpf_recvmsg() to replace the
original ->recvmsg() to retrieve skmsg from ingress_msg.

AF_UNIX is again special here because the lack of
sk_prot->recvmsg(). I simply add a special case inside
unix_dgram_recvmsg() to call sk->sk_prot->recvmsg() directly.

Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Cc: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
---
 include/net/af_unix.h |  3 +++
 net/unix/af_unix.c    | 21 ++++++++++++++++---
 net/unix/unix_bpf.c   | 49 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 70 insertions(+), 3 deletions(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index cca645846af1..e524c82794c9 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -82,6 +82,9 @@ static inline struct unix_sock *unix_sk(const struct sock *sk)
 long unix_inq_len(struct sock *sk);
 long unix_outq_len(struct sock *sk);
 
+int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
+			 int nonblock, int flags, int *addr_len);
+
 #ifdef CONFIG_SYSCTL
 int unix_sysctl_register(struct net *net);
 void unix_sysctl_unregister(struct net *net);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c4afc5fbe137..08458fa9f48b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2088,11 +2088,11 @@ static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
 	}
 }
 
-static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
-			      size_t size, int flags)
+int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
+			 int nonblock, int flags, int *addr_len)
 {
 	struct scm_cookie scm;
-	struct sock *sk = sock->sk;
+	struct socket *sock = sk->sk_socket;
 	struct unix_sock *u = unix_sk(sk);
 	struct sk_buff *skb, *last;
 	long timeo;
@@ -2195,6 +2195,21 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 	return err;
 }
 
+static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+			      int flags)
+{
+	struct sock *sk = sock->sk;
+	int addr_len = 0;
+
+#ifdef CONFIG_BPF_SYSCALL
+	if (sk->sk_prot != &unix_proto)
+		return sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
+					    flags & ~MSG_DONTWAIT, &addr_len);
+#endif
+	return __unix_dgram_recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
+				    flags, &addr_len);
+}
+
 static int unix_read_sock(struct sock *sk, read_descriptor_t *desc,
 			  sk_read_actor_t recv_actor)
 {
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index b1582a659427..b2c34aeb848f 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -6,6 +6,54 @@
 #include <net/sock.h>
 #include <net/af_unix.h>
 
+static int unix_dgram_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
+				  size_t len, int nonblock, int flags,
+				  int *addr_len)
+{
+	struct sk_psock *psock;
+	int copied, ret;
+
+	psock = sk_psock_get(sk);
+	if (unlikely(!psock))
+		return __unix_dgram_recvmsg(sk, msg, len, nonblock, flags,
+					    addr_len);
+
+	lock_sock(sk);
+	if (!skb_queue_empty(&sk->sk_receive_queue) &&
+	    sk_psock_queue_empty(psock)) {
+		ret = __unix_dgram_recvmsg(sk, msg, len, nonblock, flags,
+					   addr_len);
+		goto out;
+	}
+
+msg_bytes_ready:
+	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
+	if (!copied) {
+		int data, err = 0;
+		long timeo;
+
+		timeo = sock_rcvtimeo(sk, nonblock);
+		data = sk_msg_wait_data(sk, psock, flags, timeo, &err);
+		if (data) {
+			if (!sk_psock_queue_empty(psock))
+				goto msg_bytes_ready;
+			ret = __unix_dgram_recvmsg(sk, msg, len, nonblock,
+						   flags, addr_len);
+			goto out;
+		}
+		if (err) {
+			ret = err;
+			goto out;
+		}
+		copied = -EAGAIN;
+	}
+	ret = copied;
+out:
+	release_sock(sk);
+	sk_psock_put(sk, psock);
+	return ret;
+}
+
 static struct proto *unix_prot_saved __read_mostly;
 static DEFINE_SPINLOCK(unix_prot_lock);
 static struct proto unix_bpf_prot;
@@ -14,6 +62,7 @@ static void unix_bpf_rebuild_protos(struct proto *prot, const struct proto *base
 {
 	*prot        = *base;
 	prot->close  = sock_map_close;
+	prot->recvmsg = unix_dgram_bpf_recvmsg;
 }
 
 static void unix_bpf_check_needs_rebuild(struct proto *ops)
-- 
2.25.1


  parent reply	other threads:[~2021-04-26  2:50 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-26  2:49 [Patch bpf-next v3 00/10] sockmap: add sockmap support to Unix datagram socket Cong Wang
2021-04-26  2:49 ` [Patch bpf-next v3 01/10] sock_map: relax config dependency to CONFIG_NET Cong Wang
2021-04-26  2:49 ` [Patch bpf-next v3 02/10] af_unix: implement ->read_sock() for sockmap Cong Wang
2021-05-05 17:14   ` Jakub Sitnicki
2021-05-07  1:00     ` Cong Wang
2021-05-11  5:34   ` John Fastabend
2021-05-18  4:46     ` Cong Wang
2021-05-18  5:11       ` John Fastabend
2021-04-26  2:49 ` [Patch bpf-next v3 03/10] af_unix: implement ->psock_update_sk_prot() Cong Wang
2021-05-06 13:04   ` Jakub Sitnicki
2021-05-07  0:55     ` Cong Wang
2021-04-26  2:49 ` [Patch bpf-next v3 04/10] af_unix: set TCP_ESTABLISHED for datagram sockets too Cong Wang
2021-05-07  8:18   ` Jakub Sitnicki
2021-05-08 20:41     ` Cong Wang
2021-04-26  2:49 ` Cong Wang [this message]
2021-05-07 13:29   ` [Patch bpf-next v3 05/10] af_unix: implement unix_dgram_bpf_recvmsg() Jakub Sitnicki
2021-05-08 20:43     ` Cong Wang
2021-04-26  2:49 ` [Patch bpf-next v3 06/10] sock_map: update sock type checks for AF_UNIX Cong Wang
2021-04-26  2:49 ` [Patch bpf-next v3 07/10] selftests/bpf: factor out udp_socketpair() Cong Wang
2021-04-26  2:49 ` [Patch bpf-next v3 08/10] selftests/bpf: factor out add_to_sockmap() Cong Wang
2021-04-26  2:50 ` [Patch bpf-next v3 09/10] selftests/bpf: add a test case for unix sockmap Cong Wang
2021-04-26  2:50 ` [Patch bpf-next v3 10/10] selftests/bpf: add test cases for redirection between udp and unix Cong Wang
2021-05-07 14:07 ` [Patch bpf-next v3 00/10] sockmap: add sockmap support to Unix datagram socket Jakub Sitnicki
2021-05-08 22:27   ` Cong Wang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210426025001.7899-6-xiyou.wangcong@gmail.com \
    --to=xiyou.wangcong@gmail.com \
    --cc=bpf@vger.kernel.org \
    --cc=cong.wang@bytedance.com \
    --cc=daniel@iogearbox.net \
    --cc=duanxiongchun@bytedance.com \
    --cc=jakub@cloudflare.com \
    --cc=jiang.wang@bytedance.com \
    --cc=john.fastabend@gmail.com \
    --cc=lmb@cloudflare.com \
    --cc=netdev@vger.kernel.org \
    --cc=wangdongdong.6@bytedance.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).