5 files changed, 33 insertions, 20 deletions

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index e8bc939b56dd..dde77f72e03e 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -124,7 +124,8 @@ struct fib_table *fib_get_table(struct net *net, u32 id)
 	h = id & (FIB_TABLE_HASHSZ - 1);
 
 	head = &net->ipv4.fib_table_hash[h];
-	hlist_for_each_entry_rcu(tb, head, tb_hlist) {
+	hlist_for_each_entry_rcu(tb, head, tb_hlist,
+				 lockdep_rtnl_is_held()) {
 		if (tb->tb_id == id)
 			return tb;
 	}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 2db089e10ba0..0913a090b2bf 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1582,7 +1582,7 @@ failure:
 }
 
 int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc,
-		     unsigned char *flags, bool skip_oif)
+		     u8 rt_family, unsigned char *flags, bool skip_oif)
 {
 	if (nhc->nhc_flags & RTNH_F_DEAD)
 		*flags |= RTNH_F_DEAD;
@@ -1613,7 +1613,7 @@ int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc,
 		/* if gateway family does not match nexthop family
 		 * gateway is encoded as RTA_VIA
 		 */
-		if (nhc->nhc_gw_family != nhc->nhc_family) {
+		if (rt_family != nhc->nhc_gw_family) {
 			int alen = sizeof(struct in6_addr);
 			struct nlattr *nla;
 			struct rtvia *via;
@@ -1654,7 +1654,7 @@ EXPORT_SYMBOL_GPL(fib_nexthop_info);
 
 #if IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) || IS_ENABLED(CONFIG_IPV6)
 int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc,
-		    int nh_weight)
+		    int nh_weight, u8 rt_family)
 {
 	const struct net_device *dev = nhc->nhc_dev;
 	struct rtnexthop *rtnh;
@@ -1667,7 +1667,7 @@ int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc,
 	rtnh->rtnh_hops = nh_weight - 1;
 	rtnh->rtnh_ifindex = dev ? dev->ifindex : 0;
 
-	if (fib_nexthop_info(skb, nhc, &flags, true) < 0)
+	if (fib_nexthop_info(skb, nhc, rt_family, &flags, true) < 0)
 		goto nla_put_failure;
 
 	rtnh->rtnh_flags = flags;
@@ -1693,13 +1693,14 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi)
 		goto nla_put_failure;
 
 	if (unlikely(fi->nh)) {
-		if (nexthop_mpath_fill_node(skb, fi->nh) < 0)
+		if (nexthop_mpath_fill_node(skb, fi->nh, AF_INET) < 0)
 			goto nla_put_failure;
 		goto mp_end;
 	}
 
 	for_nexthops(fi) {
-		if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight) < 0)
+		if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight,
+				    AF_INET) < 0)
 			goto nla_put_failure;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		if (nh->nh_tclassid &&
@@ -1775,7 +1776,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		const struct fib_nh_common *nhc = fib_info_nhc(fi, 0);
 		unsigned char flags = 0;
 
-		if (fib_nexthop_info(skb, nhc, &flags, false) < 0)
+		if (fib_nexthop_info(skb, nhc, AF_INET, &flags, false) < 0)
 			goto nla_put_failure;
 
 		rtm->rtm_flags = flags;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 77b485d60b9d..61082065b26a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -935,6 +935,22 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
 	return mss_now;
 }
 
+/* In some cases, both sendpage() and sendmsg() could have added
+ * an skb to the write queue, but failed adding payload on it.
+ * We need to remove it to consume less memory, but more
+ * importantly be able to generate EPOLLOUT for Edge Trigger epoll()
+ * users.
+ */
+static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
+{
+	if (skb && !skb->len) {
+		tcp_unlink_write_queue(skb, sk);
+		if (tcp_write_queue_empty(sk))
+			tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
+		sk_wmem_free_skb(sk, skb);
+	}
+}
+
 ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 			 size_t size, int flags)
 {
@@ -1064,6 +1080,7 @@ out:
 	return copied;
 
 do_error:
+	tcp_remove_empty_skb(sk, tcp_write_queue_tail(sk));
 	if (copied)
 		goto out;
 out_err:
@@ -1388,18 +1405,11 @@ out_nopush:
 	sock_zerocopy_put(uarg);
 	return copied + copied_syn;
 
+do_error:
+	skb = tcp_write_queue_tail(sk);
 do_fault:
-	if (!skb->len) {
-		tcp_unlink_write_queue(skb, sk);
-		/* It is the one place in all of TCP, except connection
-		 * reset, where we can be unlinking the send_head.
-		 */
-		if (tcp_write_queue_empty(sk))
-			tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
-		sk_wmem_free_skb(sk, skb);
-	}
+	tcp_remove_empty_skb(sk, skb);
 
-do_error:
 	if (copied + copied_syn)
 		goto out;
 out_err:
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c21e8a22fb3b..8a1cd93dbb09 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -266,7 +266,7 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb)
 
 static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
 {
-	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+	tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR;
 }
 
 static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 979520e46e33..8a645f304e6c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2053,7 +2053,7 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
 		if (len <= skb->len)
 			break;
 
-		if (unlikely(TCP_SKB_CB(skb)->eor))
+		if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb))
 			return false;
 
 		len -= skb->len;
@@ -2170,6 +2170,7 @@ static int tcp_mtu_probe(struct sock *sk)
 			 * we need to propagate it to the new skb.
 			 */
 			TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor;
+			tcp_skb_collapse_tstamp(nskb, skb);
 			tcp_unlink_write_queue(skb, sk);
 			sk_wmem_free_skb(sk, skb);
 		} else {