From: Cong Wang <cong.wang@xxxxxxxxxxxxx>
Yucong noticed we can't poll() sockets in sockmap even
when they are the destination sockets of redirections.
This is because we never poll any psock queues in ->poll(),
except for TCP. With ->sock_is_readable() now we can
overwrite >sock_is_readable(), invoke and implement it for
both UDP and AF_UNIX sockets.
Reported-by: Yucong Sun <sunyucong@xxxxxxxxx>
Cc: John Fastabend <john.fastabend@xxxxxxxxx>
Cc: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
Cc: Jakub Sitnicki <jakub@xxxxxxxxxxxxxx>
Cc: Lorenz Bauer <lmb@xxxxxxxxxxxxxx>
Signed-off-by: Cong Wang <cong.wang@xxxxxxxxxxxxx>
---
net/ipv4/udp.c | 2 ++
net/ipv4/udp_bpf.c | 1 +
net/unix/af_unix.c | 4 ++++
net/unix/unix_bpf.c | 2 ++
4 files changed, 9 insertions(+)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 2a7825a5b842..4a7e15a43a68 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2866,6 +2866,8 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
!(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
mask &= ~(EPOLLIN | EPOLLRDNORM);
+ if (sk_is_readable(sk))
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 7a1d5f473878..bbe6569c9ad3 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -114,6 +114,7 @@ static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = udp_bpf_recvmsg;
+ prot->sock_is_readable = sk_msg_is_readable;
}
static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index f505b89bda6a..3e65d9f5531d 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -3029,6 +3029,8 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
/* readable? */
if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
+ if (sk_is_readable(sk))
+ mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
@@ -3068,6 +3070,8 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
/* readable? */
if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
+ if (sk_is_readable(sk))
+ mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
if (sk->sk_type == SOCK_SEQPACKET) {
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index b927e2baae50..452376c6f419 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -102,6 +102,7 @@ static void unix_dgram_bpf_rebuild_protos(struct proto *prot, const struct proto
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = unix_bpf_recvmsg;
+ prot->sock_is_readable = sk_msg_is_readable;
}
static void unix_stream_bpf_rebuild_protos(struct proto *prot,
@@ -110,6 +111,7 @@ static void unix_stream_bpf_rebuild_protos(struct proto *prot,
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = unix_bpf_recvmsg;
+ prot->sock_is_readable = sk_msg_is_readable;
prot->unhash = sock_map_unhash;
}
--
2.30.2
