All of lore.kernel.org
 help / color / mirror / Atom feed
From: Cong Wang <xiyou.wangcong@gmail.com>
To: netdev@vger.kernel.org
Cc: bpf@vger.kernel.org, duanxiongchun@bytedance.com,
	wangdongdong.6@bytedance.com, jiang.wang@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 16/19] af_unix: implement unix_dgram_bpf_recvmsg()
Date: Tue,  2 Feb 2021 20:16:33 -0800	[thread overview]
Message-ID: <20210203041636.38555-17-xiyou.wangcong@gmail.com> (raw)
In-Reply-To: <20210203041636.38555-1-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 fa75f899e88a..f6c43667e995 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 21c4406f879b..eebcd6f7ef88 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2094,11 +2094,11 @@ 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;
@@ -2201,6 +2201,21 @@ 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_SOCK_MAP
+	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);
+}
+
 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 2e6a26ec4958..570261fd18cd 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -5,6 +5,54 @@
 #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;
@@ -13,6 +61,7 @@ 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:[~2021-02-03  4:21 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-03  4:16 [Patch bpf-next 00/19] sock_map: add non-TCP and cross-protocol support Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 01/19] bpf: rename BPF_STREAM_PARSER to BPF_SOCK_MAP Cong Wang
2021-02-05 10:32   ` Jakub Sitnicki
2021-02-09  1:40     ` Cong Wang
2021-02-08  8:21   ` John Fastabend
2021-02-08  9:50     ` Lorenz Bauer
2021-02-09  1:45     ` Cong Wang
2021-02-09  6:48       ` John Fastabend
2021-02-03  4:16 ` [Patch bpf-next 02/19] skmsg: get rid of struct sk_psock_parser Cong Wang
2021-02-05 11:25   ` Jakub Sitnicki
2021-02-08  8:39     ` John Fastabend
2021-02-09  0:19       ` Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 03/19] skmsg: use skb ext instead of TCP_SKB_CB Cong Wang
2021-02-05 22:09   ` Jakub Sitnicki
2021-02-08 18:56     ` Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 04/19] sock_map: rename skb_parser and skb_verdict Cong Wang
2021-02-08  8:27   ` John Fastabend
2021-02-03  4:16 ` [Patch bpf-next 05/19] sock_map: introduce BPF_SK_SKB_VERDICT Cong Wang
2021-02-08  8:31   ` John Fastabend
2021-02-03  4:16 ` [Patch bpf-next 06/19] sock: introduce sk_prot->update_proto() Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 07/19] udp: implement ->sendmsg_locked() Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 08/19] udp: implement ->read_sock() for sockmap Cong Wang
2021-02-08  9:48   ` Lorenz Bauer
2021-02-09  1:35     ` Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 09/19] udp: add ->read_sock() and ->sendmsg_locked() to ipv6 Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 10/19] af_unix: implement ->sendmsg_locked for dgram socket Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 11/19] af_unix: implement ->read_sock() for sockmap Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 12/19] af_unix: implement ->update_proto() Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 13/19] af_unix: set TCP_ESTABLISHED for datagram sockets too Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 14/19] skmsg: extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data() Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 15/19] udp: implement udp_bpf_recvmsg() for sockmap Cong Wang
2021-02-03  4:16 ` Cong Wang [this message]
2021-02-03  4:16 ` [Patch bpf-next 17/19] sock_map: update sock type checks Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 18/19] selftests/bpf: add test cases for unix and udp sockmap Cong Wang
2021-02-05 10:53   ` Jakub Sitnicki
2021-02-08 18:43     ` Cong Wang
2021-02-03  4:16 ` [Patch bpf-next 19/19] selftests/bpf: add test case for redirection between udp and unix Cong Wang
2021-02-03 17:48 ` [Patch bpf-next 00/19] sock_map: add non-TCP and cross-protocol support Alexei Starovoitov
2021-02-03 19:22   ` Cong Wang
2021-02-03 20:29     ` John Fastabend

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=20210203041636.38555-17-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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.