1 files changed, 30 insertions, 109 deletions

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index bc7d2a586e18..ad9d17923fc5 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -10,86 +10,6 @@
 #include <net/inet_common.h>
 #include <net/tls.h>
 
-int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
-		      struct msghdr *msg, int len, int flags)
-{
-	struct iov_iter *iter = &msg->msg_iter;
-	int peek = flags & MSG_PEEK;
-	struct sk_msg *msg_rx;
-	int i, copied = 0;
-
-	msg_rx = list_first_entry_or_null(&psock->ingress_msg,
-					  struct sk_msg, list);
-
-	while (copied != len) {
-		struct scatterlist *sge;
-
-		if (unlikely(!msg_rx))
-			break;
-
-		i = msg_rx->sg.start;
-		do {
-			struct page *page;
-			int copy;
-
-			sge = sk_msg_elem(msg_rx, i);
-			copy = sge->length;
-			page = sg_page(sge);
-			if (copied + copy > len)
-				copy = len - copied;
-			copy = copy_page_to_iter(page, sge->offset, copy, iter);
-			if (!copy)
-				return copied ? copied : -EFAULT;
-
-			copied += copy;
-			if (likely(!peek)) {
-				sge->offset += copy;
-				sge->length -= copy;
-				if (!msg_rx->skb)
-					sk_mem_uncharge(sk, copy);
-				msg_rx->sg.size -= copy;
-
-				if (!sge->length) {
-					sk_msg_iter_var_next(i);
-					if (!msg_rx->skb)
-						put_page(page);
-				}
-			} else {
-				/* Lets not optimize peek case if copy_page_to_iter
-				 * didn't copy the entire length lets just break.
-				 */
-				if (copy != sge->length)
-					return copied;
-				sk_msg_iter_var_next(i);
-			}
-
-			if (copied == len)
-				break;
-		} while (i != msg_rx->sg.end);
-
-		if (unlikely(peek)) {
-			if (msg_rx == list_last_entry(&psock->ingress_msg,
-						      struct sk_msg, list))
-				break;
-			msg_rx = list_next_entry(msg_rx, list);
-			continue;
-		}
-
-		msg_rx->sg.start = i;
-		if (!sge->length && msg_rx->sg.start == msg_rx->sg.end) {
-			list_del(&msg_rx->list);
-			if (msg_rx->skb)
-				consume_skb(msg_rx->skb);
-			kfree(msg_rx);
-		}
-		msg_rx = list_first_entry_or_null(&psock->ingress_msg,
-						  struct sk_msg, list);
-	}
-
-	return copied;
-}
-EXPORT_SYMBOL_GPL(__tcp_bpf_recvmsg);
-
 static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
 			   struct sk_msg *msg, u32 apply_bytes, int flags)
 {
@@ -229,7 +149,7 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg,
 }
 EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir);
 
-#ifdef CONFIG_BPF_STREAM_PARSER
+#ifdef CONFIG_BPF_SYSCALL
 static bool tcp_bpf_stream_read(const struct sock *sk)
 {
 	struct sk_psock *psock;
@@ -243,28 +163,6 @@ static bool tcp_bpf_stream_read(const struct sock *sk)
 	return !empty;
 }
 
-static int tcp_bpf_wait_data(struct sock *sk, struct sk_psock *psock,
-			     int flags, long timeo, int *err)
-{
-	DEFINE_WAIT_FUNC(wait, woken_wake_function);
-	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);
-	ret = sk_wait_event(sk, &timeo,
-			    !list_empty(&psock->ingress_msg) ||
-			    !skb_queue_empty(&sk->sk_receive_queue), &wait);
-	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
-	remove_wait_queue(sk_sleep(sk), &wait);
-	return ret;
-}
-
 static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		    int nonblock, int flags, int *addr_len)
 {
@@ -284,13 +182,13 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	}
 	lock_sock(sk);
 msg_bytes_ready:
-	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
+	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
 	if (!copied) {
 		int data, err = 0;
 		long timeo;
 
 		timeo = sock_rcvtimeo(sk, nonblock);
-		data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
+		data = sk_msg_wait_data(sk, psock, flags, timeo, &err);
 		if (data) {
 			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
@@ -601,20 +499,43 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops)
 	       ops->sendpage == tcp_sendpage ? 0 : -ENOTSUPP;
 }
 
-struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
+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 (restore) {
+		if (inet_csk_has_ulp(sk)) {
+			/* TLS does not have an unhash proto in SW cases,
+			 * but we need to ensure we stop using the sock_map
+			 * unhash routine because the associated psock is being
+			 * removed. So use the original unhash handler.
+			 */
+			WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash);
+			tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space);
+		} else {
+			sk->sk_write_space = psock->saved_write_space;
+			/* Pairs with lockless read in sk_clone_lock() */
+			WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+		}
+		return 0;
+	}
+
+	if (inet_csk_has_ulp(sk))
+		return -EINVAL;
+
 	if (sk->sk_family == AF_INET6) {
 		if (tcp_bpf_assert_proto_ops(psock->sk_proto))
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 
 		tcp_bpf_check_v6_needs_rebuild(psock->sk_proto);
 	}
 
-	return &tcp_bpf_prots[family][config];
+	/* Pairs with lockless read in sk_clone_lock() */
+	WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]);
+	return 0;
 }
+EXPORT_SYMBOL_GPL(tcp_bpf_update_proto);
 
 /* If a child got cloned from a listening socket that had tcp_bpf
  * protocol callbacks installed, we need to restore the callbacks to
@@ -629,4 +550,4 @@ void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
 	if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE])
 		newsk->sk_prot = sk->sk_prot_creator;
 }
-#endif /* CONFIG_BPF_STREAM_PARSER */
+#endif /* CONFIG_BPF_SYSCALL */