Merge tag 'v5.7-rc6' into rdma.git for-next

Linux 5.7-rc6

Conflict in drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
resolved by deleting dr_cq_event, matching how netdev resolved it.

Required for dependencies in the following patches.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

9 files changed, 48 insertions, 34 deletions

diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 0bd10a1f477f..a23094b050f8 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1258,7 +1258,8 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def,
 			return ret_val;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	return 0;
@@ -1439,7 +1440,8 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def,
 			return ret_val;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	return 0;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 30fa42f5997d..c0dd561aa190 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -614,12 +614,15 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
 	return NULL;
 }
 
-static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
+static int ip_mc_autojoin_config(struct net *net, bool join,
+				 const struct in_ifaddr *ifa)
 {
+#if defined(CONFIG_IP_MULTICAST)
 	struct ip_mreqn mreq = {
 		.imr_multiaddr.s_addr = ifa->ifa_address,
 		.imr_ifindex = ifa->ifa_dev->dev->ifindex,
 	};
+	struct sock *sk = net->ipv4.mc_autojoin_sk;
 	int ret;
 
 	ASSERT_RTNL();
@@ -632,6 +635,9 @@ static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
 	release_sock(sk);
 
 	return ret;
+#else
+	return -EOPNOTSUPP;
+#endif
 }
 
 static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -675,7 +681,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 			continue;
 
 		if (ipv4_is_multicast(ifa->ifa_address))
-			ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa);
+			ip_mc_autojoin_config(net, false, ifa);
 		__inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid);
 		return 0;
 	}
@@ -940,8 +946,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		 */
 		set_ifa_lifetime(ifa, valid_lft, prefered_lft);
 		if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) {
-			int ret = ip_mc_config(net->ipv4.mc_autojoin_sk,
-					       true, ifa);
+			int ret = ip_mc_autojoin_config(net, true, ifa);
 
 			if (ret < 0) {
 				inet_free_ifa(ifa);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 6ed8c9317179..55ca2e521828 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -2014,7 +2014,7 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 
 	hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
 		struct fib_info *next_fi = fa->fa_info;
-		struct fib_nh *nh;
+		struct fib_nh_common *nhc;
 
 		if (fa->fa_slen != slen)
 			continue;
@@ -2037,8 +2037,8 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 		    fa->fa_type != RTN_UNICAST)
 			continue;
 
-		nh = fib_info_nh(next_fi, 0);
-		if (!nh->fib_nh_gw4 || nh->fib_nh_scope != RT_SCOPE_LINK)
+		nhc = fib_info_nhc(next_fi, 0);
+		if (!nhc->nhc_gw_family || nhc->nhc_scope != RT_SCOPE_LINK)
 			continue;
 
 		fib_alias_accessed(fa);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9cf83cc85e4a..5c218db2dede 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -109,8 +109,10 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags);
 static void ipmr_expire_process(struct timer_list *t);
 
 #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
-#define ipmr_for_each_table(mrt, net) \
-	list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list)
+#define ipmr_for_each_table(mrt, net)					\
+	list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list,	\
+				lockdep_rtnl_is_held() ||		\
+				list_empty(&net->ipv4.mr_tables))
 
 static struct mr_table *ipmr_mr_table_iter(struct net *net,
 					   struct mr_table *mrt)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 788c69d9bfe0..fa829f31a3f5 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -915,7 +915,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	/* Check for load limit; set rate_last to the latest sent
 	 * redirect.
 	 */
-	if (peer->rate_tokens == 0 ||
+	if (peer->n_redirects == 0 ||
 	    time_after(jiffies,
 		       (peer->rate_last +
 			(ip_rt_redirect_load << peer->n_redirects)))) {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6d87de434377..dd401757eea1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -476,9 +476,17 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
 static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 					  int target, struct sock *sk)
 {
-	return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) ||
-		(sk->sk_prot->stream_memory_read ?
-		sk->sk_prot->stream_memory_read(sk) : false);
+	int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);
+
+	if (avail > 0) {
+		if (avail >= target)
+			return true;
+		if (tcp_rmem_pressure(sk))
+			return true;
+	}
+	if (sk->sk_prot->stream_memory_read)
+		return sk->sk_prot->stream_memory_read(sk);
+	return false;
 }
 
 /*
@@ -1756,10 +1764,11 @@ static int tcp_zerocopy_receive(struct sock *sk,
 
 	down_read(&current->mm->mmap_sem);
 
-	ret = -EINVAL;
 	vma = find_vma(current->mm, address);
-	if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops)
-		goto out;
+	if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) {
+		up_read(&current->mm->mmap_sem);
+		return -EINVAL;
+	}
 	zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);
 
 	tp = tcp_sk(sk);
@@ -2154,13 +2163,15 @@ skip_copy:
 			tp->urg_data = 0;
 			tcp_fast_path_check(sk);
 		}
-		if (used + offset < skb->len)
-			continue;
 
 		if (TCP_SKB_CB(skb)->has_rxtstamp) {
 			tcp_update_recv_tstamps(skb, &tss);
 			cmsg_flags |= 2;
 		}
+
+		if (used + offset < skb->len)
+			continue;
+
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			goto found_fin_ok;
 		if (!(flags & MSG_PEEK))
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 5a05327f97c1..629aaa9a1eb9 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -125,7 +125,6 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
 
 	if (!ret) {
 		msg->sg.start = i;
-		msg->sg.size -= apply_bytes;
 		sk_psock_queue_msg(psock, tmp);
 		sk_psock_data_ready(sk, psock);
 	} else {
@@ -262,14 +261,17 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	struct sk_psock *psock;
 	int copied, ret;
 
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return inet_recv_error(sk, msg, len, addr_len);
+
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
-	if (unlikely(flags & MSG_ERRQUEUE))
-		return inet_recv_error(sk, msg, len, addr_len);
 	if (!skb_queue_empty(&sk->sk_receive_queue) &&
-	    sk_psock_queue_empty(psock))
+	    sk_psock_queue_empty(psock)) {
+		sk_psock_put(sk, psock);
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+	}
 	lock_sock(sk);
 msg_bytes_ready:
 	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bf4ced9273e8..29c6fc8c7716 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3926,10 +3926,6 @@ void tcp_parse_options(const struct net *net,
 				 */
 				break;
 #endif
-			case TCPOPT_MPTCP:
-				mptcp_parse_option(skb, ptr, opsize, opt_rx);
-				break;
-
 			case TCPOPT_FASTOPEN:
 				tcp_parse_fastopen_option(
 					opsize - TCPOLEN_FASTOPEN_BASE,
@@ -4761,7 +4757,8 @@ void tcp_data_ready(struct sock *sk)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	int avail = tp->rcv_nxt - tp->copied_seq;
 
-	if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
+	if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&
+	    !sock_flag(sk, SOCK_DONE))
 		return;
 
 	sk->sk_data_ready(sk);
@@ -5990,9 +5987,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		tcp_initialize_rcv_mss(sk);
 
-		if (sk_is_mptcp(sk))
-			mptcp_rcv_synsent(sk);
-
 		/* Remember, tcp_poll() does not lock socket!
 		 * Change state from SYN-SENT only after copied_seq
 		 * is initialized. */
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 89ba7c87de5d..30ddb9dc9398 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -58,9 +58,7 @@ int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb)
 {
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 
-#ifdef CONFIG_NETFILTER
 	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
-#endif
 
 	return xfrm_output(sk, skb);
 }