| Message ID | 20210426025001.7899-6-xiyou.wangcong@gmail.com |
|---|---|
| State | Superseded |
| Headers | show |
| Series | sockmap: add sockmap support to Unix datagram socket | expand |
On Mon, Apr 26, 2021 at 04:49 AM CEST, Cong Wang wrote: > 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); > +} > + Nit: We can just pass NULL instead of &addr_len here it seems. [...]
On Fri, May 7, 2021 at 6:29 AM Jakub Sitnicki <jakub@cloudflare.com> wrote: > > On Mon, Apr 26, 2021 at 04:49 AM CEST, Cong Wang wrote: > > 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); > > +} > > + > > Nit: We can just pass NULL instead of &addr_len here it seems. Yeah, we can actually remove this parameter for __unix_dgram_recvmsg(). Only unix_dgram_bpf_recvmsg() needs it as it is enforced by sk_prot. Thanks.
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)