1 files changed, 60 insertions, 15 deletions

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index d3e9386b493e..f70aa0932bd6 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)
 {
@@ -185,6 +172,41 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
 	return ret;
 }
 
+static int tcp_bpf_recvmsg_parser(struct sock *sk,
+				  struct msghdr *msg,
+				  size_t len,
+				  int nonblock,
+				  int flags,
+				  int *addr_len)
+{
+	struct sk_psock *psock;
+	int copied;
+
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return inet_recv_error(sk, msg, len, addr_len);
+
+	psock = sk_psock_get(sk);
+	if (unlikely(!psock))
+		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+
+	lock_sock(sk);
+msg_bytes_ready:
+	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
+	if (!copied) {
+		long timeo;
+		int data;
+
+		timeo = sock_rcvtimeo(sk, nonblock);
+		data = tcp_msg_wait_data(sk, psock, timeo);
+		if (data && !sk_psock_queue_empty(psock))
+			goto msg_bytes_ready;
+		copied = -EAGAIN;
+	}
+	release_sock(sk);
+	sk_psock_put(sk, psock);
+	return copied;
+}
+
 static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		    int nonblock, int flags, int *addr_len)
 {
@@ -232,6 +254,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 	bool cork = false, enospc = sk_msg_full(msg);
 	struct sock *sk_redir;
 	u32 tosend, delta = 0;
+	u32 eval = __SK_NONE;
 	int ret;
 
 more_data:
@@ -275,13 +298,24 @@ more_data:
 	case __SK_REDIRECT:
 		sk_redir = psock->sk_redir;
 		sk_msg_apply_bytes(psock, tosend);
+		if (!psock->apply_bytes) {
+			/* Clean up before releasing the sock lock. */
+			eval = psock->eval;
+			psock->eval = __SK_NONE;
+			psock->sk_redir = NULL;
+		}
 		if (psock->cork) {
 			cork = true;
 			psock->cork = NULL;
 		}
 		sk_msg_return(sk, msg, tosend);
 		release_sock(sk);
+
 		ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
+
+		if (eval == __SK_REDIRECT)
+			sock_put(sk_redir);
+
 		lock_sock(sk);
 		if (unlikely(ret < 0)) {
 			int free = sk_msg_free_nocharge(sk, msg);
@@ -465,6 +499,8 @@ enum {
 enum {
 	TCP_BPF_BASE,
 	TCP_BPF_TX,
+	TCP_BPF_RX,
+	TCP_BPF_TXRX,
 	TCP_BPF_NUM_CFGS,
 };
 
@@ -476,14 +512,19 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
 				   struct proto *base)
 {
 	prot[TCP_BPF_BASE]			= *base;
-	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;
 	prot[TCP_BPF_TX].sendpage		= tcp_bpf_sendpage;
+
+	prot[TCP_BPF_RX]			= prot[TCP_BPF_BASE];
+	prot[TCP_BPF_RX].recvmsg		= tcp_bpf_recvmsg_parser;
+
+	prot[TCP_BPF_TXRX]			= prot[TCP_BPF_TX];
+	prot[TCP_BPF_TXRX].recvmsg		= tcp_bpf_recvmsg_parser;
 }
 
 static void tcp_bpf_check_v6_needs_rebuild(struct proto *ops)
@@ -521,6 +562,10 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 	int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
 	int config = psock->progs.msg_parser   ? TCP_BPF_TX   : TCP_BPF_BASE;
 
+	if (psock->progs.stream_verdict || psock->progs.skb_verdict) {
+		config = (config == TCP_BPF_TX) ? TCP_BPF_TXRX : TCP_BPF_RX;
+	}
+
 	if (restore) {
 		if (inet_csk_has_ulp(sk)) {
 			/* TLS does not have an unhash proto in SW cases,