Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

Conflicts:

net/ipv4/raw.c
  3632679d9e4f ("ipv{4,6}/raw: fix output xfrm lookup wrt protocol")
  c85be08fc4fa ("raw: Stop using RTO_ONLINK.")
https://lore.kernel.org/all/20230525110037.2b532b83@canb.auug.org.au/

Adjacent changes:

drivers/net/ethernet/freescale/fec_main.c
  9025944fddfe ("net: fec: add dma_wmb to ensure correct descriptor values")
  144470c88c5d ("net: fec: using the standard return codes when xdp xmit errors")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 98 insertions, 18 deletions

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index b511ff0adc0a..8e97d8d4cc9d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 			ipc->tos = val;
 			ipc->priority = rt_tos2priority(ipc->tos);
 			break;
-
+		case IP_PROTOCOL:
+			if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+				return -EINVAL;
+			val = *(int *)CMSG_DATA(cmsg);
+			if (val < 1 || val > 255)
+				return -EINVAL;
+			ipc->protocol = val;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_LOCAL_PORT_RANGE:
 		val = inet->local_port_range.hi << 16 | inet->local_port_range.lo;
 		break;
+	case IP_PROTOCOL:
+		val = inet_sk(sk)->inet_num;
+		break;
 	default:
 		sockopt_release_sock(sk);
 		return -ENOPROTOOPT;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8b7b5c842bdd..9aacce9db7b9 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -532,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 
 	ipcm_init_sk(&ipc, inet);
+	/* Keep backward compat */
+	if (hdrincl)
+		ipc.protocol = IPPROTO_RAW;
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sk, msg, &ipc, false);
@@ -597,7 +600,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 
 	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope,
-			   hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+			   hdrincl ? ipc.protocol : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk) |
 			    (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
 			   daddr, saddr, 0, 0, sk->sk_uid);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e9506cebecce..f1b4ec67cbd7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1451,7 +1451,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
  * calculation of whether or not we must ACK for the sake of
  * a window update.
  */
-static void __tcp_cleanup_rbuf(struct sock *sk, int copied)
+void __tcp_cleanup_rbuf(struct sock *sk, int copied)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool time_to_ack = false;
@@ -1653,7 +1653,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 		WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk));
 		tcp_flags = TCP_SKB_CB(skb)->tcp_flags;
 		used = recv_actor(sk, skb);
-		consume_skb(skb);
 		if (used < 0) {
 			if (!copied)
 				copied = used;
@@ -1667,14 +1666,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 			break;
 		}
 	}
-	WRITE_ONCE(tp->copied_seq, seq);
-
-	tcp_rcv_space_adjust(sk);
-
-	/* Clean up data we have read: This will do ACK frames. */
-	if (copied > 0)
-		__tcp_cleanup_rbuf(sk, copied);
-
 	return copied;
 }
 EXPORT_SYMBOL(tcp_read_skb);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 0291d15acd19..e75023ea052f 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -11,6 +11,24 @@
 #include <net/inet_common.h>
 #include <net/tls.h>
 
+void tcp_eat_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcp_sock *tcp;
+	int copied;
+
+	if (!skb || !skb->len || !sk_is_tcp(sk))
+		return;
+
+	if (skb_bpf_strparser(skb))
+		return;
+
+	tcp = tcp_sk(sk);
+	copied = tcp->copied_seq + skb->len;
+	WRITE_ONCE(tcp->copied_seq, copied);
+	tcp_rcv_space_adjust(sk);
+	__tcp_cleanup_rbuf(sk, skb->len);
+}
+
 static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
 			   struct sk_msg *msg, u32 apply_bytes, int flags)
 {
@@ -178,14 +196,34 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
 	return ret;
 }
 
+static bool is_next_msg_fin(struct sk_psock *psock)
+{
+	struct scatterlist *sge;
+	struct sk_msg *msg_rx;
+	int i;
+
+	msg_rx = sk_psock_peek_msg(psock);
+	i = msg_rx->sg.start;
+	sge = sk_msg_elem(msg_rx, i);
+	if (!sge->length) {
+		struct sk_buff *skb = msg_rx->skb;
+
+		if (skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+			return true;
+	}
+	return false;
+}
+
 static int tcp_bpf_recvmsg_parser(struct sock *sk,
 				  struct msghdr *msg,
 				  size_t len,
 				  int flags,
 				  int *addr_len)
 {
+	struct tcp_sock *tcp = tcp_sk(sk);
+	u32 seq = tcp->copied_seq;
 	struct sk_psock *psock;
-	int copied;
+	int copied = 0;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
@@ -198,8 +236,43 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
 		return tcp_recvmsg(sk, msg, len, flags, addr_len);
 
 	lock_sock(sk);
+
+	/* We may have received data on the sk_receive_queue pre-accept and
+	 * then we can not use read_skb in this context because we haven't
+	 * assigned a sk_socket yet so have no link to the ops. The work-around
+	 * is to check the sk_receive_queue and in these cases read skbs off
+	 * queue again. The read_skb hook is not running at this point because
+	 * of lock_sock so we avoid having multiple runners in read_skb.
+	 */
+	if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) {
+		tcp_data_ready(sk);
+		/* This handles the ENOMEM errors if we both receive data
+		 * pre accept and are already under memory pressure. At least
+		 * let user know to retry.
+		 */
+		if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) {
+			copied = -EAGAIN;
+			goto out;
+		}
+	}
+
 msg_bytes_ready:
 	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
+	/* The typical case for EFAULT is the socket was gracefully
+	 * shutdown with a FIN pkt. So check here the other case is
+	 * some error on copy_page_to_iter which would be unexpected.
+	 * On fin return correct return code to zero.
+	 */
+	if (copied == -EFAULT) {
+		bool is_fin = is_next_msg_fin(psock);
+
+		if (is_fin) {
+			copied = 0;
+			seq++;
+			goto out;
+		}
+	}
+	seq += copied;
 	if (!copied) {
 		long timeo;
 		int data;
@@ -237,6 +310,10 @@ msg_bytes_ready:
 		copied = -EAGAIN;
 	}
 out:
+	WRITE_ONCE(tcp->copied_seq, seq);
+	tcp_rcv_space_adjust(sk);
+	if (copied > 0)
+		__tcp_cleanup_rbuf(sk, copied);
 	release_sock(sk);
 	sk_psock_put(sk, psock);
 	return copied;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e992dd5392e3..514ebd4aff74 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1774,7 +1774,7 @@ EXPORT_SYMBOL(__skb_recv_udp);
 int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 {
 	struct sk_buff *skb;
-	int err, copied;
+	int err;
 
 try_again:
 	skb = skb_recv_udp(sk, MSG_DONTWAIT, &err);
@@ -1793,10 +1793,7 @@ try_again:
 	}
 
 	WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk));
-	copied = recv_actor(sk, skb);
-	kfree_skb(skb);
-
-	return copied;
+	return recv_actor(sk, skb);
 }
 EXPORT_SYMBOL(udp_read_skb);
 
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index e0c9cc39b81e..56d94d23b9e0 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -64,6 +64,8 @@ struct proto 	udplite_prot = {
 	.per_cpu_fw_alloc  = &udp_memory_per_cpu_fw_alloc,
 
 	.sysctl_mem	   = sysctl_udp_mem,
+	.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
+	.sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
 	.obj_size	   = sizeof(struct udp_sock),
 	.h.udp_table	   = &udplite_table,
 };