From: Cong Wang <xiyou.wangcong@gmail.com>
To: netdev@vger.kernel.org
Cc: bpf@vger.kernel.org, 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 v5 07/11] af_unix: implement unix_dgram_bpf_recvmsg()
Date: Sun, 4 Jul 2021 12:02:48 -0700 [thread overview]
Message-ID: <20210704190252.11866-8-xiyou.wangcong@gmail.com> (raw)
In-Reply-To: <20210704190252.11866-1-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 | 2 ++
net/unix/af_unix.c | 19 +++++++++--
net/unix/unix_bpf.c | 75 +++++++++++++++++++++++++++++++++++++++++++
3 files changed, 93 insertions(+), 3 deletions(-)
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index cca645846af1..435a2c3d5a6f 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -82,6 +82,8 @@ 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 flags);
#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 573253c5b5c2..89927678c0dc 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2098,11 +2098,11 @@ 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 flags)
{
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;
@@ -2205,6 +2205,19 @@ 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;
+
+#ifdef CONFIG_BPF_SYSCALL
+ if (sk->sk_prot != &unix_proto)
+ return sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
+ flags & ~MSG_DONTWAIT, NULL);
+#endif
+ return __unix_dgram_recvmsg(sk, msg, size, flags);
+}
+
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..db0cda29fb2f 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -6,6 +6,80 @@
#include <net/sock.h>
#include <net/af_unix.h>
+#define unix_sk_has_data(__sk, __psock) \
+ ({ !skb_queue_empty(&__sk->sk_receive_queue) || \
+ !skb_queue_empty(&__psock->ingress_skb) || \
+ !list_empty(&__psock->ingress_msg); \
+ })
+
+static int unix_msg_wait_data(struct sock *sk, struct sk_psock *psock,
+ long timeo)
+{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ struct unix_sock *u = unix_sk(sk);
+ int ret = 0;
+
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ return 1;
+
+ if (!timeo)
+ return ret;
+
+ add_wait_queue(sk_sleep(sk), &wait);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ if (!unix_sk_has_data(sk, psock)) {
+ mutex_unlock(&u->iolock);
+ wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
+ mutex_lock(&u->iolock);
+ ret = unix_sk_has_data(sk, psock);
+ }
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
+ return ret;
+}
+
+static int unix_dgram_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
+ size_t len, int nonblock, int flags,
+ int *addr_len)
+{
+ struct unix_sock *u = unix_sk(sk);
+ struct sk_psock *psock;
+ int copied, ret;
+
+ psock = sk_psock_get(sk);
+ if (unlikely(!psock))
+ return __unix_dgram_recvmsg(sk, msg, len, flags);
+
+ mutex_lock(&u->iolock);
+ if (!skb_queue_empty(&sk->sk_receive_queue) &&
+ sk_psock_queue_empty(psock)) {
+ ret = __unix_dgram_recvmsg(sk, msg, len, flags);
+ goto out;
+ }
+
+msg_bytes_ready:
+ copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
+ if (!copied) {
+ long timeo;
+ int data;
+
+ timeo = sock_rcvtimeo(sk, nonblock);
+ data = unix_msg_wait_data(sk, psock, timeo);
+ if (data) {
+ if (!sk_psock_queue_empty(psock))
+ goto msg_bytes_ready;
+ ret = __unix_dgram_recvmsg(sk, msg, len, flags);
+ goto out;
+ }
+ copied = -EAGAIN;
+ }
+ ret = copied;
+out:
+ mutex_unlock(&u->iolock);
+ 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 +88,7 @@ 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)
--
2.27.0
next prev parent reply other threads:[~2021-07-04 19:03 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-04 19:02 [PATCH bpf-next v5 00/11] sockmap: add sockmap support for unix datagram socket Cong Wang
2021-07-04 19:02 ` [PATCH bpf-next v5 01/11] sock_map: relax config dependency to CONFIG_NET Cong Wang
2021-07-04 19:02 ` [PATCH bpf-next v5 02/11] sock_map: lift socket state restriction for datagram sockets Cong Wang
2021-07-04 19:02 ` [PATCH bpf-next v5 03/11] af_unix: implement ->read_sock() for sockmap Cong Wang
2021-07-12 17:04 ` John Fastabend
2021-07-04 19:02 ` [PATCH bpf-next v5 04/11] af_unix: set TCP_ESTABLISHED for datagram sockets too Cong Wang
2021-07-04 19:02 ` [PATCH bpf-next v5 05/11] af_unix: add a dummy ->close() for sockmap Cong Wang
2021-07-04 19:02 ` [PATCH bpf-next v5 06/11] af_unix: implement ->psock_update_sk_prot() Cong Wang
2021-07-04 19:02 ` Cong Wang [this message]
2021-07-18 17:49 ` [PATCH bpf-next v5 07/11] af_unix: implement unix_dgram_bpf_recvmsg() Eric Dumazet
2021-07-20 0:03 ` Cong Wang
2021-07-04 19:02 ` [PATCH bpf-next v5 08/11] selftests/bpf: factor out udp_socketpair() Cong Wang
2021-07-04 19:02 ` [PATCH bpf-next v5 09/11] selftests/bpf: factor out add_to_sockmap() Cong Wang
2021-07-04 19:02 ` [PATCH bpf-next v5 10/11] selftests/bpf: add a test case for unix sockmap Cong Wang
2021-07-04 19:02 ` [PATCH bpf-next v5 11/11] selftests/bpf: add test cases for redirection between udp and unix Cong Wang
2021-08-05 22:43 ` Andrii Nakryiko
2021-08-06 2:34 ` Cong Wang
2021-07-12 17:02 ` [PATCH bpf-next v5 00/11] sockmap: add sockmap support for unix datagram socket John Fastabend
2021-07-16 1:31 ` Alexei Starovoitov
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=20210704190252.11866-8-xiyou.wangcong@gmail.com \
--to=xiyou.wangcong@gmail.com \
--cc=bpf@vger.kernel.org \
--cc=cong.wang@bytedance.com \
--cc=daniel@iogearbox.net \
--cc=jakub@cloudflare.com \
--cc=john.fastabend@gmail.com \
--cc=lmb@cloudflare.com \
--cc=netdev@vger.kernel.org \
/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).