bpf: sockmap, support for msg_peek in sk_msg with redirect ingress

This adds support for the MSG_PEEK flag when doing redirect to ingress
and receiving on the sk_msg psock queue. Previously the flag was
being ignored which could confuse applications if they expected the
flag to work as normal.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

include/net/tcp.h

@@ -2089,7 +2089,7 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes,
 int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		    int nonblock, int flags, int *addr_len);
 int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
-		      struct msghdr *msg, int len);
+		      struct msghdr *msg, int len, int flags);
 
 /* Call BPF_SOCK_OPS program that returns an int. If the return value
  * is < 0, then the BPF op failed (for example if the loaded BPF

net/ipv4/tcp_bpf.c

@@ -39,17 +39,19 @@ static int tcp_bpf_wait_data(struct sock *sk, struct sk_psock *psock,
 }
 
 int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
-		      struct msghdr *msg, int len)
+		      struct msghdr *msg, int len, int flags)
 {
 	struct iov_iter *iter = &msg->msg_iter;
+	int peek = flags & MSG_PEEK;
 	int i, ret, copied = 0;
+	struct sk_msg *msg_rx;
+
+	msg_rx = list_first_entry_or_null(&psock->ingress_msg,
+					  struct sk_msg, list);
 
 	while (copied != len) {
 		struct scatterlist *sge;
-		struct sk_msg *msg_rx;
 
-		msg_rx = list_first_entry_or_null(&psock->ingress_msg,
-						  struct sk_msg, list);
 		if (unlikely(!msg_rx))
 			break;
 
@@ -70,22 +72,30 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 			}
 
 			copied += copy;
-			sge->offset += copy;
-			sge->length -= copy;
-			sk_mem_uncharge(sk, copy);
-			msg_rx->sg.size -= copy;
-			if (!sge->length) {
-				i++;
-				if (i == MAX_SKB_FRAGS)
-					i = 0;
-				if (!msg_rx->skb)
-					put_page(page);
+			if (likely(!peek)) {
+				sge->offset += copy;
+				sge->length -= copy;
+				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 {
+				sk_msg_iter_var_next(i);
 			}
 
 			if (copied == len)
 				break;
 		} while (i != msg_rx->sg.end);
 
+		if (unlikely(peek)) {
+			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);
@@ -93,6 +103,8 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 				consume_skb(msg_rx->skb);
 			kfree(msg_rx);
 		}
+		msg_rx = list_first_entry_or_null(&psock->ingress_msg,
+						  struct sk_msg, list);
 	}
 
 	return copied;
@@ -115,7 +127,7 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 	lock_sock(sk);
 msg_bytes_ready:
-	copied = __tcp_bpf_recvmsg(sk, psock, msg, len);
+	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
 	if (!copied) {
 		int data, err = 0;
 		long timeo;

net/tls/tls_sw.c

@@ -1478,7 +1478,8 @@ int tls_sw_recvmsg(struct sock *sk,
 		skb = tls_wait_data(sk, psock, flags, timeo, &err);
 		if (!skb) {
 			if (psock) {
-				int ret = __tcp_bpf_recvmsg(sk, psock, msg, len);
+				int ret = __tcp_bpf_recvmsg(sk, psock,
+							    msg, len, flags);
 
 				if (ret > 0) {
 					copied += ret;