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

Cross-merge networking fixes after downstream PR.

No conflicts (or adjacent changes of note).

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

7 files changed, 28 insertions, 13 deletions

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index eafa4a033515..1ea82bc33ef1 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1887,6 +1887,7 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local)
 			continue;
 		if (fi->fib_prefsrc == local) {
 			fi->fib_flags |= RTNH_F_DEAD;
+			fi->pfsrc_removed = true;
 			ret++;
 		}
 	}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index d13fb9e76b97..9bdfdab906fe 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2027,6 +2027,7 @@ void fib_table_flush_external(struct fib_table *tb)
 int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all)
 {
 	struct trie *t = (struct trie *)tb->tb_data;
+	struct nl_info info = { .nl_net = net };
 	struct key_vector *pn = t->kv;
 	unsigned long cindex = 1;
 	struct hlist_node *tmp;
@@ -2089,6 +2090,9 @@ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all)
 
 			fib_notify_alias_delete(net, n->key, &n->leaf, fa,
 						NULL);
+			if (fi->pfsrc_removed)
+				rtmsg_fib(RTM_DELROUTE, htonl(n->key), fa,
+					  KEYLENGTH - fa->fa_slen, tb->tb_id, &info, 0);
 			hlist_del_rcu(&fa->fa_list);
 			fib_release_info(fa->fa_info);
 			alias_free_mem_rcu(fa);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ac332e2e4fff..e2bf4602b559 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3417,6 +3417,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 				    fa->fa_type == fri.type) {
 					fri.offload = READ_ONCE(fa->offload);
 					fri.trap = READ_ONCE(fa->trap);
+					fri.offload_failed =
+						READ_ONCE(fa->offload_failed);
 					break;
 				}
 			}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e54f91eb943b..9a8b134d8ada 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1621,16 +1621,13 @@ EXPORT_SYMBOL(tcp_read_sock);
 
 int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
-	u32 seq = tp->copied_seq;
 	struct sk_buff *skb;
 	int copied = 0;
-	u32 offset;
 
 	if (sk->sk_state == TCP_LISTEN)
 		return -ENOTCONN;
 
-	while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
+	while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
 		u8 tcp_flags;
 		int used;
 
@@ -1643,13 +1640,10 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 				copied = used;
 			break;
 		}
-		seq += used;
 		copied += used;
 
-		if (tcp_flags & TCPHDR_FIN) {
-			++seq;
+		if (tcp_flags & TCPHDR_FIN)
 			break;
-		}
 	}
 	return copied;
 }
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 81f0dff69e0b..327268203001 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -222,6 +222,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
 				  int *addr_len)
 {
 	struct tcp_sock *tcp = tcp_sk(sk);
+	int peek = flags & MSG_PEEK;
 	u32 seq = tcp->copied_seq;
 	struct sk_psock *psock;
 	int copied = 0;
@@ -311,7 +312,8 @@ msg_bytes_ready:
 		copied = -EAGAIN;
 	}
 out:
-	WRITE_ONCE(tcp->copied_seq, seq);
+	if (!peek)
+		WRITE_ONCE(tcp->copied_seq, seq);
 	tcp_rcv_space_adjust(sk);
 	if (copied > 0)
 		__tcp_cleanup_rbuf(sk, copied);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 22c2a7c2e65e..4b8f2e74d71d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -253,6 +253,19 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 		if (unlikely(len > icsk->icsk_ack.rcv_mss +
 				   MAX_TCP_OPTION_SPACE))
 			tcp_gro_dev_warn(sk, skb, len);
+		/* If the skb has a len of exactly 1*MSS and has the PSH bit
+		 * set then it is likely the end of an application write. So
+		 * more data may not be arriving soon, and yet the data sender
+		 * may be waiting for an ACK if cwnd-bound or using TX zero
+		 * copy. So we set ICSK_ACK_PUSHED here so that
+		 * tcp_cleanup_rbuf() will send an ACK immediately if the app
+		 * reads all of the data and is not ping-pong. If len > MSS
+		 * then this logic does not matter (and does not hurt) because
+		 * tcp_cleanup_rbuf() will always ACK immediately if the app
+		 * reads data and there is more than an MSS of unACKed data.
+		 */
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_PSH)
+			icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
 	} else {
 		/* Otherwise, we make more careful check taking into account,
 		 * that SACKs block is variable.
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8885552dff8e..f207712eece1 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -177,8 +177,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 }
 
 /* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
-				      u32 rcv_nxt)
+static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -192,7 +191,7 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
 
 	if (unlikely(rcv_nxt != tp->rcv_nxt))
 		return;  /* Special ACK sent by DCTCP to reflect ECN */
-	tcp_dec_quickack_mode(sk, pkts);
+	tcp_dec_quickack_mode(sk);
 	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
 }
 
@@ -1380,7 +1379,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 			   sk, skb);
 
 	if (likely(tcb->tcp_flags & TCPHDR_ACK))
-		tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
+		tcp_event_ack_sent(sk, rcv_nxt);
 
 	if (skb->len != tcp_header_size) {
 		tcp_event_data_sent(tp, sk);