BackMerge tag 'v6.6-rc7' into drm-next

This is needed to add the msm pr which is based on a higher base.

Signed-off-by: Dave Airlie <airlied@redhat.com>

13 files changed, 102 insertions, 53 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 3d2e30e20473..2713c9b06c4c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -597,7 +597,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
 
 	add_wait_queue(sk_sleep(sk), &wait);
 	sk->sk_write_pending += writebias;
-	sk->sk_wait_pending++;
 
 	/* Basic assumption: if someone sets sk->sk_err, he _must_
 	 * change state of the socket from TCP_SYN_*.
@@ -613,7 +612,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
 	}
 	remove_wait_queue(sk_sleep(sk), &wait);
 	sk->sk_write_pending -= writebias;
-	sk->sk_wait_pending--;
 	return timeo;
 }
 
@@ -642,6 +640,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 			return -EINVAL;
 
 		if (uaddr->sa_family == AF_UNSPEC) {
+			sk->sk_disconnects++;
 			err = sk->sk_prot->disconnect(sk, flags);
 			sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
 			goto out;
@@ -696,6 +695,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		int writebias = (sk->sk_protocol == IPPROTO_TCP) &&
 				tcp_sk(sk)->fastopen_req &&
 				tcp_sk(sk)->fastopen_req->data ? 1 : 0;
+		int dis = sk->sk_disconnects;
 
 		/* Error code is set above */
 		if (!timeo || !inet_wait_for_connect(sk, timeo, writebias))
@@ -704,6 +704,11 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		err = sock_intr_errno(timeo);
 		if (signal_pending(current))
 			goto out;
+
+		if (dis != sk->sk_disconnects) {
+			err = -EPIPE;
+			goto out;
+		}
 	}
 
 	/* Connection was closed by RST, timeout, ICMP error
@@ -725,6 +730,7 @@ out:
 sock_error:
 	err = sock_error(sk) ? : -ECONNABORTED;
 	sock->state = SS_UNCONNECTED;
+	sk->sk_disconnects++;
 	if (sk->sk_prot->disconnect(sk, flags))
 		sock->state = SS_DISCONNECTING;
 	goto out;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 2be2d4922557..d18f0f092fe7 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -732,7 +732,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb)
 		skb->csum = csum_block_sub(skb->csum, csumdiff,
 					   skb->len - trimlen);
 	}
-	pskb_trim(skb, skb->len - trimlen);
+	ret = pskb_trim(skb, skb->len - trimlen);
+	if (unlikely(ret))
+		return ret;
 
 	ret = nexthdr[1];
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index eafa4a033515..5eb1b8d302bb 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1325,15 +1325,18 @@ __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc,
 				 unsigned char scope)
 {
 	struct fib_nh *nh;
+	__be32 saddr;
 
 	if (nhc->nhc_family != AF_INET)
 		return inet_select_addr(nhc->nhc_dev, 0, scope);
 
 	nh = container_of(nhc, struct fib_nh, nh_common);
-	nh->nh_saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope);
-	nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid);
+	saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope);
 
-	return nh->nh_saddr;
+	WRITE_ONCE(nh->nh_saddr, saddr);
+	WRITE_ONCE(nh->nh_saddr_genid, atomic_read(&net->ipv4.dev_addr_genid));
+
+	return saddr;
 }
 
 __be32 fib_result_prefsrc(struct net *net, struct fib_result *res)
@@ -1347,8 +1350,9 @@ __be32 fib_result_prefsrc(struct net *net, struct fib_result *res)
 		struct fib_nh *nh;
 
 		nh = container_of(nhc, struct fib_nh, nh_common);
-		if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid))
-			return nh->nh_saddr;
+		if (READ_ONCE(nh->nh_saddr_genid) ==
+		    atomic_read(&net->ipv4.dev_addr_genid))
+			return READ_ONCE(nh->nh_saddr);
 	}
 
 	return fib_info_update_nhc_saddr(net, nhc, res->fi->fib_scope);
@@ -1887,6 +1891,7 @@ 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/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index aeebe8816689..394a498c2823 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1145,7 +1145,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 	if (newsk) {
 		struct inet_connection_sock *newicsk = inet_csk(newsk);
 
-		newsk->sk_wait_pending = 0;
 		inet_sk_set_state(newsk, TCP_SYN_RECV);
 		newicsk->icsk_bind_hash = NULL;
 		newicsk->icsk_bind2_hash = NULL;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index c32f5e28758b..598c1b114d2c 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -149,8 +149,14 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2,
 					 const struct sock *sk)
 {
 #if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family != tb2->family)
-		return false;
+	if (sk->sk_family != tb2->family) {
+		if (sk->sk_family == AF_INET)
+			return ipv6_addr_v4mapped(&tb2->v6_rcv_saddr) &&
+				tb2->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr;
+
+		return ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr) &&
+			sk->sk_v6_rcv_saddr.s6_addr32[3] == tb2->rcv_saddr;
+	}
 
 	if (sk->sk_family == AF_INET6)
 		return ipv6_addr_equal(&tb2->v6_rcv_saddr,
@@ -819,19 +825,7 @@ static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb,
 	    tb->l3mdev != l3mdev)
 		return false;
 
-#if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family != tb->family) {
-		if (sk->sk_family == AF_INET)
-			return ipv6_addr_v4mapped(&tb->v6_rcv_saddr) &&
-				tb->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr;
-
-		return false;
-	}
-
-	if (sk->sk_family == AF_INET6)
-		return ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr);
-#endif
-	return tb->rcv_saddr == sk->sk_rcv_saddr;
+	return inet_bind2_bucket_addr_match(tb, sk);
 }
 
 bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 66f419e7f9a7..b214b5a2e045 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1213,6 +1213,7 @@ EXPORT_INDIRECT_CALLABLE(ipv4_dst_check);
 
 static void ipv4_send_dest_unreach(struct sk_buff *skb)
 {
+	struct net_device *dev;
 	struct ip_options opt;
 	int res;
 
@@ -1230,7 +1231,8 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb)
 		opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr);
 
 		rcu_read_lock();
-		res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+		dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev;
+		res = __ip_options_compile(dev_net(dev), &opt, skb, NULL);
 		rcu_read_unlock();
 
 		if (res)
@@ -3415,6 +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 0c3040a63ebd..d3456cf840de 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -831,7 +831,9 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 			 */
 			if (!skb_queue_empty(&sk->sk_receive_queue))
 				break;
-			sk_wait_data(sk, &timeo, NULL);
+			ret = sk_wait_data(sk, &timeo, NULL);
+			if (ret < 0)
+				break;
 			if (signal_pending(current)) {
 				ret = sock_intr_errno(timeo);
 				break;
@@ -1621,16 +1623,13 @@ 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 +1642,10 @@ 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;
 }
@@ -2448,7 +2444,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 			__sk_flush_backlog(sk);
 		} else {
 			tcp_cleanup_rbuf(sk, copied);
-			sk_wait_data(sk, &timeo, last);
+			err = sk_wait_data(sk, &timeo, last);
+			if (err < 0) {
+				err = copied ? : err;
+				goto out;
+			}
 		}
 
 		if ((flags & MSG_PEEK) &&
@@ -2972,12 +2972,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	int old_state = sk->sk_state;
 	u32 seq;
 
-	/* Deny disconnect if other threads are blocked in sk_wait_event()
-	 * or inet_wait_for_connect().
-	 */
-	if (sk->sk_wait_pending)
-		return -EBUSY;
-
 	if (old_state != TCP_CLOSE)
 		tcp_set_state(sk, TCP_CLOSE);
 
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 81f0dff69e0b..53b0d62fd2c2 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;
@@ -306,15 +307,22 @@ msg_bytes_ready:
 		}
 
 		data = tcp_msg_wait_data(sk, psock, timeo);
+		if (data < 0) {
+			copied = data;
+			goto unlock;
+		}
 		if (data && !sk_psock_queue_empty(psock))
 			goto 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);
+
+unlock:
 	release_sock(sk);
 	sk_psock_put(sk, psock);
 	return copied;
@@ -349,6 +357,10 @@ msg_bytes_ready:
 
 		timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 		data = tcp_msg_wait_data(sk, psock, timeo);
+		if (data < 0) {
+			ret = data;
+			goto unlock;
+		}
 		if (data) {
 			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
@@ -359,6 +371,8 @@ msg_bytes_ready:
 		copied = -EAGAIN;
 	}
 	ret = copied;
+
+unlock:
 	release_sock(sk);
 	sk_psock_put(sk, psock);
 	return ret;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 06fe1cf645d5..8afb0950a697 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_ipv4.c b/net/ipv4/tcp_ipv4.c
index 27140e5cdc06..4167e8a48b60 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1869,6 +1869,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
 #ifdef CONFIG_TLS_DEVICE
 	    tail->decrypted != skb->decrypted ||
 #endif
+	    !mptcp_skb_can_collapse(tail, skb) ||
 	    thtail->doff != th->doff ||
 	    memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th)))
 		goto no_coalesce;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ccfc8bbf7455..f0723460753c 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);
 }
 
@@ -1387,7 +1386,7 @@ 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);
@@ -2457,6 +2456,7 @@ static int tcp_mtu_probe(struct sock *sk)
 
 	/* build the payload, and be prepared to abort if this fails. */
 	if (tcp_clone_payload(sk, nskb, probe_size)) {
+		tcp_skb_tsorted_anchor_cleanup(nskb);
 		consume_skb(nskb);
 		return -1;
 	}
@@ -2542,6 +2542,18 @@ static bool tcp_pacing_check(struct sock *sk)
 	return true;
 }
 
+static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk)
+{
+	const struct rb_node *node = sk->tcp_rtx_queue.rb_node;
+
+	/* No skb in the rtx queue. */
+	if (!node)
+		return true;
+
+	/* Only one skb in rtx queue. */
+	return !node->rb_left && !node->rb_right;
+}
+
 /* TCP Small Queues :
  * Control number of packets in qdisc/devices to two packets / or ~1 ms.
  * (These limits are doubled for retransmits)
@@ -2579,12 +2591,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 		limit += extra_bytes;
 	}
 	if (refcount_read(&sk->sk_wmem_alloc) > limit) {
-		/* Always send skb if rtx queue is empty.
+		/* Always send skb if rtx queue is empty or has one skb.
 		 * No need to wait for TX completion to call us back,
 		 * after softirq/tasklet schedule.
 		 * This helps when TX completions are delayed too much.
 		 */
-		if (tcp_rtx_queue_empty(sk))
+		if (tcp_rtx_queue_empty_or_single_skb(sk))
 			return false;
 
 		set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
@@ -2788,7 +2800,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 timeout, rto_delta_us;
+	u32 timeout, timeout_us, rto_delta_us;
 	int early_retrans;
 
 	/* Don't do any loss probe on a Fast Open connection before 3WHS
@@ -2812,11 +2824,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
 	 * sample is available then probe after TCP_TIMEOUT_INIT.
 	 */
 	if (tp->srtt_us) {
-		timeout = usecs_to_jiffies(tp->srtt_us >> 2);
+		timeout_us = tp->srtt_us >> 2;
 		if (tp->packets_out == 1)
-			timeout += TCP_RTO_MIN;
+			timeout_us += tcp_rto_min_us(sk);
 		else
-			timeout += TCP_TIMEOUT_MIN;
+			timeout_us += TCP_TIMEOUT_MIN_US;
+		timeout = usecs_to_jiffies(timeout_us);
 	} else {
 		timeout = TCP_TIMEOUT_INIT;
 	}
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index acf4869c5d3b..bba10110fbbc 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -104,7 +104,7 @@ bool tcp_rack_mark_lost(struct sock *sk)
 	tp->rack.advanced = 0;
 	tcp_rack_detect_loss(sk, &timeout);
 	if (timeout) {
-		timeout = usecs_to_jiffies(timeout) + TCP_TIMEOUT_MIN;
+		timeout = usecs_to_jiffies(timeout + TCP_TIMEOUT_MIN_US);
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT,
 					  timeout, inet_csk(sk)->icsk_rto);
 	}