Merge branch 'sock_map: fix ->poll() and update selftests'

Cong Wang says:

====================
This patchset fixes ->poll() for sockets in sockmap and updates
selftests accordingly with select(). Please check each patch
for more details.

Fixes: c50524ec4e3a ("Merge branch 'sockmap: add sockmap support for unix datagram socket'")
Fixes: 89d69c5d0fbc ("Merge branch 'sockmap: introduce BPF_SK_SKB_VERDICT and support UDP'")
Acked-by: John Fastabend <john.fastabend@gmail.com>

---
v4: add a comment in udp_poll()

v3: drop sk_psock_get_checked()
    reuse tcp_bpf_sock_is_readable()

v2: rename and reuse ->stream_memory_read()
    fix a compile error in sk_psock_get_checked()

Cong Wang (3):
  net: rename ->stream_memory_read to ->sock_is_readable
  skmsg: extract and reuse sk_msg_is_readable()
  net: implement ->sock_is_readable() for UDP and AF_UNIX

====================

Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

9 files changed, 29 insertions, 21 deletions

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 2d6249b28928..a86ef7e844f8 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -474,6 +474,20 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 }
 EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
 
+bool sk_msg_is_readable(struct sock *sk)
+{
+	struct sk_psock *psock;
+	bool empty = true;
+
+	rcu_read_lock();
+	psock = sk_psock(sk);
+	if (likely(psock))
+		empty = list_empty(&psock->ingress_msg);
+	rcu_read_unlock();
+	return !empty;
+}
+EXPORT_SYMBOL_GPL(sk_msg_is_readable);
+
 static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
 						  struct sk_buff *skb)
 {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e8b48df73c85..f5c336f8b0c8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -486,10 +486,7 @@ static bool tcp_stream_is_readable(struct sock *sk, int target)
 {
 	if (tcp_epollin_ready(sk, target))
 		return true;
-
-	if (sk->sk_prot->stream_memory_read)
-		return sk->sk_prot->stream_memory_read(sk);
-	return false;
+	return sk_is_readable(sk);
 }
 
 /*
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 9d068153c316..5f4d6f45d87f 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -150,19 +150,6 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg,
 EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir);
 
 #ifdef CONFIG_BPF_SYSCALL
-static bool tcp_bpf_stream_read(const struct sock *sk)
-{
-	struct sk_psock *psock;
-	bool empty = true;
-
-	rcu_read_lock();
-	psock = sk_psock(sk);
-	if (likely(psock))
-		empty = list_empty(&psock->ingress_msg);
-	rcu_read_unlock();
-	return !empty;
-}
-
 static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
 			     long timeo)
 {
@@ -491,7 +478,7 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
 	prot[TCP_BPF_BASE].unhash		= sock_map_unhash;
 	prot[TCP_BPF_BASE].close		= sock_map_close;
 	prot[TCP_BPF_BASE].recvmsg		= tcp_bpf_recvmsg;
-	prot[TCP_BPF_BASE].stream_memory_read	= tcp_bpf_stream_read;
+	prot[TCP_BPF_BASE].sock_is_readable	= sk_msg_is_readable;
 
 	prot[TCP_BPF_TX]			= prot[TCP_BPF_BASE];
 	prot[TCP_BPF_TX].sendmsg		= tcp_bpf_sendmsg;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8536b2a7210b..2fffcf2b54f3 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2867,6 +2867,9 @@ __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);
 
+	/* psock ingress_msg queue should not contain any bad checksum frames */
+	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/tls/tls_main.c b/net/tls/tls_main.c
index fde56ff49163..9ab81db8a654 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -681,12 +681,12 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
 
 	prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE];
 	prot[TLS_BASE][TLS_SW].recvmsg		  = tls_sw_recvmsg;
-	prot[TLS_BASE][TLS_SW].stream_memory_read = tls_sw_stream_read;
+	prot[TLS_BASE][TLS_SW].sock_is_readable   = tls_sw_sock_is_readable;
 	prot[TLS_BASE][TLS_SW].close		  = tls_sk_proto_close;
 
 	prot[TLS_SW][TLS_SW] = prot[TLS_SW][TLS_BASE];
 	prot[TLS_SW][TLS_SW].recvmsg		= tls_sw_recvmsg;
-	prot[TLS_SW][TLS_SW].stream_memory_read	= tls_sw_stream_read;
+	prot[TLS_SW][TLS_SW].sock_is_readable   = tls_sw_sock_is_readable;
 	prot[TLS_SW][TLS_SW].close		= tls_sk_proto_close;
 
 #ifdef CONFIG_TLS_DEVICE
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 4feb95e34b64..d5d09bd817b7 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2026,7 +2026,7 @@ splice_read_end:
 	return copied ? : err;
 }
 
-bool tls_sw_stream_read(const struct sock *sk)
+bool tls_sw_sock_is_readable(struct sock *sk)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 89f9e85ae970..78e08e82c08c 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -3052,6 +3052,8 @@ 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) &&
@@ -3091,6 +3093,8 @@ 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;
 }