Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Support ipv6 checksum offload in sunvnet driver, from Shannon
    Nelson.

 2) Move to RB-tree instead of custom AVL code in inetpeer, from Eric
    Dumazet.

 3) Allow generic XDP to work on virtual devices, from John Fastabend.

 4) Add bpf device maps and XDP_REDIRECT, which can be used to build
    arbitrary switching frameworks using XDP. From John Fastabend.

 5) Remove UFO offloads from the tree, gave us little other than bugs.

 6) Remove the IPSEC flow cache, from Florian Westphal.

 7) Support ipv6 route offload in mlxsw driver.

 8) Support VF representors in bnxt_en, from Sathya Perla.

 9) Add support for forward error correction modes to ethtool, from
    Vidya Sagar Ravipati.

10) Add time filter for packet scheduler action dumping, from Jamal Hadi
    Salim.

11) Extend the zerocopy sendmsg() used by virtio and tap to regular
    sockets via MSG_ZEROCOPY. From Willem de Bruijn.

12) Significantly rework value tracking in the BPF verifier, from Edward
    Cree.

13) Add new jump instructions to eBPF, from Daniel Borkmann.

14) Rework rtnetlink plumbing so that operations can be run without
    taking the RTNL semaphore. From Florian Westphal.

15) Support XDP in tap driver, from Jason Wang.

16) Add 32-bit eBPF JIT for ARM, from Shubham Bansal.

17) Add Huawei hinic ethernet driver.

18) Allow to report MD5 keys in TCP inet_diag dumps, from Ivan
    Delalande.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1780 commits)
  i40e: point wb_desc at the nvm_wb_desc during i40e_read_nvm_aq
  i40e: avoid NVM acquire deadlock during NVM update
  drivers: net: xgene: Remove return statement from void function
  drivers: net: xgene: Configure tx/rx delay for ACPI
  drivers: net: xgene: Read tx/rx delay for ACPI
  rocker: fix kcalloc parameter order
  rds: Fix non-atomic operation on shared flag variable
  net: sched: don't use GFP_KERNEL under spin lock
  vhost_net: correctly check tx avail during rx busy polling
  net: mdio-mux: add mdio_mux parameter to mdio_mux_init()
  rxrpc: Make service connection lookup always check for retry
  net: stmmac: Delete dead code for MDIO registration
  gianfar: Fix Tx flow control deactivation
  cxgb4: Ignore MPS_TX_INT_CAUSE[Bubble] for T6
  cxgb4: Fix pause frame count in t4_get_port_stats
  cxgb4: fix memory leak
  tun: rename generic_xdp to skb_xdp
  tun: reserve extra headroom only when XDP is set
  net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
  net: dsa: bcm_sf2: Advertise number of egress queues
  ...

1 files changed, 65 insertions, 105 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bab7f0493098..c5d7656beeee 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1952,6 +1952,7 @@ void tcp_enter_loss(struct sock *sk)
 	    !after(tp->high_seq, tp->snd_una) ||
 	    (icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) {
 		tp->prior_ssthresh = tcp_current_ssthresh(sk);
+		tp->prior_cwnd = tp->snd_cwnd;
 		tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
 		tcp_ca_event(sk, CA_EVENT_LOSS);
 		tcp_init_undo(tp);
@@ -4267,9 +4268,15 @@ static void tcp_sack_remove(struct tcp_sock *tp)
 	tp->rx_opt.num_sacks = num_sacks;
 }
 
+enum tcp_queue {
+	OOO_QUEUE,
+	RCV_QUEUE,
+};
+
 /**
  * tcp_try_coalesce - try to merge skb to prior one
  * @sk: socket
+ * @dest: destination queue
  * @to: prior buffer
  * @from: buffer to add in queue
  * @fragstolen: pointer to boolean
@@ -4281,6 +4288,7 @@ static void tcp_sack_remove(struct tcp_sock *tp)
  * Returns true if caller should free @from instead of queueing it
  */
 static bool tcp_try_coalesce(struct sock *sk,
+			     enum tcp_queue dest,
 			     struct sk_buff *to,
 			     struct sk_buff *from,
 			     bool *fragstolen)
@@ -4302,6 +4310,15 @@ static bool tcp_try_coalesce(struct sock *sk,
 	TCP_SKB_CB(to)->end_seq = TCP_SKB_CB(from)->end_seq;
 	TCP_SKB_CB(to)->ack_seq = TCP_SKB_CB(from)->ack_seq;
 	TCP_SKB_CB(to)->tcp_flags |= TCP_SKB_CB(from)->tcp_flags;
+
+	if (TCP_SKB_CB(from)->has_rxtstamp) {
+		TCP_SKB_CB(to)->has_rxtstamp = true;
+		if (dest == OOO_QUEUE)
+			TCP_SKB_CB(to)->swtstamp = TCP_SKB_CB(from)->swtstamp;
+		else
+			to->tstamp = from->tstamp;
+	}
+
 	return true;
 }
 
@@ -4336,6 +4353,9 @@ static void tcp_ofo_queue(struct sock *sk)
 		}
 		p = rb_next(p);
 		rb_erase(&skb->rbnode, &tp->out_of_order_queue);
+		/* Replace tstamp which was stomped by rbnode */
+		if (TCP_SKB_CB(skb)->has_rxtstamp)
+			skb->tstamp = TCP_SKB_CB(skb)->swtstamp;
 
 		if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) {
 			SOCK_DEBUG(sk, "ofo packet was already received\n");
@@ -4347,7 +4367,8 @@ static void tcp_ofo_queue(struct sock *sk)
 			   TCP_SKB_CB(skb)->end_seq);
 
 		tail = skb_peek_tail(&sk->sk_receive_queue);
-		eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
+		eaten = tail && tcp_try_coalesce(sk, RCV_QUEUE,
+						 tail, skb, &fragstolen);
 		tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
 		fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
 		if (!eaten)
@@ -4401,6 +4422,10 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		return;
 	}
 
+	/* Stash tstamp to avoid being stomped on by rbnode */
+	if (TCP_SKB_CB(skb)->has_rxtstamp)
+		TCP_SKB_CB(skb)->swtstamp = skb->tstamp;
+
 	/* Disable header prediction. */
 	tp->pred_flags = 0;
 	inet_csk_schedule_ack(sk);
@@ -4428,7 +4453,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	/* In the typical case, we are adding an skb to the end of the list.
 	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
 	 */
-	if (tcp_try_coalesce(sk, tp->ooo_last_skb, skb, &fragstolen)) {
+	if (tcp_try_coalesce(sk, OOO_QUEUE, tp->ooo_last_skb,
+			     skb, &fragstolen)) {
 coalesce_done:
 		tcp_grow_window(sk, skb);
 		kfree_skb_partial(skb, fragstolen);
@@ -4478,7 +4504,8 @@ coalesce_done:
 				__kfree_skb(skb1);
 				goto merge_right;
 			}
-		} else if (tcp_try_coalesce(sk, skb1, skb, &fragstolen)) {
+		} else if (tcp_try_coalesce(sk, OOO_QUEUE, skb1,
+					    skb, &fragstolen)) {
 			goto coalesce_done;
 		}
 		p = &parent->rb_right;
@@ -4529,7 +4556,8 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
 
 	__skb_pull(skb, hdrlen);
 	eaten = (tail &&
-		 tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0;
+		 tcp_try_coalesce(sk, RCV_QUEUE, tail,
+				  skb, fragstolen)) ? 1 : 0;
 	tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
 	if (!eaten) {
 		__skb_queue_tail(&sk->sk_receive_queue, skb);
@@ -4591,8 +4619,8 @@ err:
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	bool fragstolen = false;
-	int eaten = -1;
+	bool fragstolen;
+	int eaten;
 
 	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
 		__kfree_skb(skb);
@@ -4614,32 +4642,13 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 			goto out_of_window;
 
 		/* Ok. In sequence. In window. */
-		if (tp->ucopy.task == current &&
-		    tp->copied_seq == tp->rcv_nxt && tp->ucopy.len &&
-		    sock_owned_by_user(sk) && !tp->urg_data) {
-			int chunk = min_t(unsigned int, skb->len,
-					  tp->ucopy.len);
-
-			__set_current_state(TASK_RUNNING);
-
-			if (!skb_copy_datagram_msg(skb, 0, tp->ucopy.msg, chunk)) {
-				tp->ucopy.len -= chunk;
-				tp->copied_seq += chunk;
-				eaten = (chunk == skb->len);
-				tcp_rcv_space_adjust(sk);
-			}
-		}
-
-		if (eaten <= 0) {
 queue_and_out:
-			if (eaten < 0) {
-				if (skb_queue_len(&sk->sk_receive_queue) == 0)
-					sk_forced_mem_schedule(sk, skb->truesize);
-				else if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
-					goto drop;
-			}
-			eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
-		}
+		if (skb_queue_len(&sk->sk_receive_queue) == 0)
+			sk_forced_mem_schedule(sk, skb->truesize);
+		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
+			goto drop;
+
+		eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
 		tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
 		if (skb->len)
 			tcp_event_data_recv(sk, skb);
@@ -5189,26 +5198,6 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t
 	}
 }
 
-static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	int chunk = skb->len - hlen;
-	int err;
-
-	if (skb_csum_unnecessary(skb))
-		err = skb_copy_datagram_msg(skb, hlen, tp->ucopy.msg, chunk);
-	else
-		err = skb_copy_and_csum_datagram_msg(skb, hlen, tp->ucopy.msg);
-
-	if (!err) {
-		tp->ucopy.len -= chunk;
-		tp->copied_seq += chunk;
-		tcp_rcv_space_adjust(sk);
-	}
-
-	return err;
-}
-
 /* Accept RST for rcv_nxt - 1 after a FIN.
  * When tcp connections are abruptly terminated from Mac OSX (via ^C), a
  * FIN is sent followed by a RST packet. The RST is sent with the same
@@ -5361,8 +5350,9 @@ discard:
  *	tcp_data_queue when everything is OK.
  */
 void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
-			 const struct tcphdr *th, unsigned int len)
+			 const struct tcphdr *th)
 {
+	unsigned int len = skb->len;
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	tcp_mstamp_refresh(tp);
@@ -5448,56 +5438,28 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 			int eaten = 0;
 			bool fragstolen = false;
 
-			if (tp->ucopy.task == current &&
-			    tp->copied_seq == tp->rcv_nxt &&
-			    len - tcp_header_len <= tp->ucopy.len &&
-			    sock_owned_by_user(sk)) {
-				__set_current_state(TASK_RUNNING);
-
-				if (!tcp_copy_to_iovec(sk, skb, tcp_header_len)) {
-					/* Predicted packet is in window by definition.
-					 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
-					 * Hence, check seq<=rcv_wup reduces to:
-					 */
-					if (tcp_header_len ==
-					    (sizeof(struct tcphdr) +
-					     TCPOLEN_TSTAMP_ALIGNED) &&
-					    tp->rcv_nxt == tp->rcv_wup)
-						tcp_store_ts_recent(tp);
-
-					tcp_rcv_rtt_measure_ts(sk, skb);
-
-					__skb_pull(skb, tcp_header_len);
-					tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
-					NET_INC_STATS(sock_net(sk),
-							LINUX_MIB_TCPHPHITSTOUSER);
-					eaten = 1;
-				}
-			}
-			if (!eaten) {
-				if (tcp_checksum_complete(skb))
-					goto csum_error;
+			if (tcp_checksum_complete(skb))
+				goto csum_error;
 
-				if ((int)skb->truesize > sk->sk_forward_alloc)
-					goto step5;
+			if ((int)skb->truesize > sk->sk_forward_alloc)
+				goto step5;
 
-				/* Predicted packet is in window by definition.
-				 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
-				 * Hence, check seq<=rcv_wup reduces to:
-				 */
-				if (tcp_header_len ==
-				    (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
-				    tp->rcv_nxt == tp->rcv_wup)
-					tcp_store_ts_recent(tp);
+			/* Predicted packet is in window by definition.
+			 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
+			 * Hence, check seq<=rcv_wup reduces to:
+			 */
+			if (tcp_header_len ==
+			    (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
+			    tp->rcv_nxt == tp->rcv_wup)
+				tcp_store_ts_recent(tp);
 
-				tcp_rcv_rtt_measure_ts(sk, skb);
+			tcp_rcv_rtt_measure_ts(sk, skb);
 
-				NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS);
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS);
 
-				/* Bulk data transfer: receiver */
-				eaten = tcp_queue_rcv(sk, skb, tcp_header_len,
-						      &fragstolen);
-			}
+			/* Bulk data transfer: receiver */
+			eaten = tcp_queue_rcv(sk, skb, tcp_header_len,
+					      &fragstolen);
 
 			tcp_event_data_recv(sk, skb);
 
@@ -5591,7 +5553,6 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 		__tcp_fast_path_on(tp, tp->snd_wnd);
 	else
 		tp->pred_flags = 0;
-
 }
 
 static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
@@ -6306,9 +6267,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	struct sock *fastopen_sk = NULL;
-	struct dst_entry *dst = NULL;
 	struct request_sock *req;
 	bool want_cookie = false;
+	struct dst_entry *dst;
 	struct flowi fl;
 
 	/* TW buckets are converted to open requests without
@@ -6358,6 +6319,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if (tmp_opt.tstamp_ok)
 		tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb);
 
+	dst = af_ops->route_req(sk, &fl, req);
+	if (!dst)
+		goto drop_and_free;
+
 	if (!want_cookie && !isn) {
 		/* Kill the following clause, if you dislike this way. */
 		if (!net->ipv4.sysctl_tcp_syncookies &&
@@ -6378,11 +6343,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 
 		isn = af_ops->init_seq(skb);
 	}
-	if (!dst) {
-		dst = af_ops->route_req(sk, &fl, req);
-		if (!dst)
-			goto drop_and_free;
-	}
 
 	tcp_ecn_create_request(req, skb, sk, dst);
 
@@ -6398,7 +6358,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	tcp_openreq_init_rwin(req, sk, dst);
 	if (!want_cookie) {
 		tcp_reqsk_record_syn(sk, req, skb);
-		fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst);
+		fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc);
 	}
 	if (fastopen_sk) {
 		af_ops->send_synack(fastopen_sk, dst, &fl, req,