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

Pull networking updates from David Miller:
 "Highlights:

   1) Support TX_RING in AF_PACKET TPACKET_V3 mode, from Sowmini
      Varadhan.

   2) Simplify classifier state on sk_buff in order to shrink it a bit.
      From Willem de Bruijn.

   3) Introduce SIPHASH and it's usage for secure sequence numbers and
      syncookies. From Jason A. Donenfeld.

   4) Reduce CPU usage for ICMP replies we are going to limit or
      suppress, from Jesper Dangaard Brouer.

   5) Introduce Shared Memory Communications socket layer, from Ursula
      Braun.

   6) Add RACK loss detection and allow it to actually trigger fast
      recovery instead of just assisting after other algorithms have
      triggered it. From Yuchung Cheng.

   7) Add xmit_more and BQL support to mvneta driver, from Simon Guinot.

   8) skb_cow_data avoidance in esp4 and esp6, from Steffen Klassert.

   9) Export MPLS packet stats via netlink, from Robert Shearman.

  10) Significantly improve inet port bind conflict handling, especially
      when an application is restarted and changes it's setting of
      reuseport. From Josef Bacik.

  11) Implement TX batching in vhost_net, from Jason Wang.

  12) Extend the dummy device so that VF (virtual function) features,
      such as configuration, can be more easily tested. From Phil
      Sutter.

  13) Avoid two atomic ops per page on x86 in bnx2x driver, from Eric
      Dumazet.

  14) Add new bpf MAP, implementing a longest prefix match trie. From
      Daniel Mack.

  15) Packet sample offloading support in mlxsw driver, from Yotam Gigi.

  16) Add new aquantia driver, from David VomLehn.

  17) Add bpf tracepoints, from Daniel Borkmann.

  18) Add support for port mirroring to b53 and bcm_sf2 drivers, from
      Florian Fainelli.

  19) Remove custom busy polling in many drivers, it is done in the core
      networking since 4.5 times. From Eric Dumazet.

  20) Support XDP adjust_head in virtio_net, from John Fastabend.

  21) Fix several major holes in neighbour entry confirmation, from
      Julian Anastasov.

  22) Add XDP support to bnxt_en driver, from Michael Chan.

  23) VXLAN offloads for enic driver, from Govindarajulu Varadarajan.

  24) Add IPVTAP driver (IP-VLAN based tap driver) from Sainath Grandhi.

  25) Support GRO in IPSEC protocols, from Steffen Klassert"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1764 commits)
  Revert "ath10k: Search SMBIOS for OEM board file extension"
  net: socket: fix recvmmsg not returning error from sock_error
  bnxt_en: use eth_hw_addr_random()
  bpf: fix unlocking of jited image when module ronx not set
  arch: add ARCH_HAS_SET_MEMORY config
  net: napi_watchdog() can use napi_schedule_irqoff()
  tcp: Revert "tcp: tcp_probe: use spin_lock_bh()"
  net/hsr: use eth_hw_addr_random()
  net: mvpp2: enable building on 64-bit platforms
  net: mvpp2: switch to build_skb() in the RX path
  net: mvpp2: simplify MVPP2_PRS_RI_* definitions
  net: mvpp2: fix indentation of MVPP2_EXT_GLOBAL_CTRL_DEFAULT
  net: mvpp2: remove unused register definitions
  net: mvpp2: simplify mvpp2_bm_bufs_add()
  net: mvpp2: drop useless fields in mvpp2_bm_pool and related code
  net: mvpp2: remove unused 'tx_skb' field of 'struct mvpp2_tx_queue'
  net: mvpp2: release reference to txq_cpu[] entry after unmapping
  net: mvpp2: handle too large value in mvpp2_rx_time_coal_set()
  net: mvpp2: handle too large value handling in mvpp2_rx_pkts_coal_set()
  net: mvpp2: remove useless arguments in mvpp2_rx_{pkts, time}_coal_set
  ...

1 files changed, 43 insertions, 44 deletions

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 4e8647aef01c..ddd2dd6f77aa 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -515,6 +515,10 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer,
 	if (link_is_bc_sndlink(l))
 		l->state = LINK_ESTABLISHED;
 
+	/* Disable replicast if even a single peer doesn't support it */
+	if (link_is_bc_rcvlink(l) && !(peer_caps & TIPC_BCAST_RCAST))
+		tipc_bcast_disable_rcast(net);
+
 	return true;
 }
 
@@ -776,60 +780,47 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
 
 /**
  * link_schedule_user - schedule a message sender for wakeup after congestion
- * @link: congested link
- * @list: message that was attempted sent
+ * @l: congested link
+ * @hdr: header of message that is being sent
  * Create pseudo msg to send back to user when congestion abates
- * Does not consume buffer list
  */
-static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list)
+static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr)
 {
-	struct tipc_msg *msg = buf_msg(skb_peek(list));
-	int imp = msg_importance(msg);
-	u32 oport = msg_origport(msg);
-	u32 addr = tipc_own_addr(link->net);
+	u32 dnode = tipc_own_addr(l->net);
+	u32 dport = msg_origport(hdr);
 	struct sk_buff *skb;
 
-	/* This really cannot happen...  */
-	if (unlikely(imp > TIPC_CRITICAL_IMPORTANCE)) {
-		pr_warn("%s<%s>, send queue full", link_rst_msg, link->name);
-		return -ENOBUFS;
-	}
-	/* Non-blocking sender: */
-	if (TIPC_SKB_CB(skb_peek(list))->wakeup_pending)
-		return -ELINKCONG;
-
 	/* Create and schedule wakeup pseudo message */
 	skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0,
-			      addr, addr, oport, 0, 0);
+			      dnode, l->addr, dport, 0, 0);
 	if (!skb)
 		return -ENOBUFS;
-	TIPC_SKB_CB(skb)->chain_sz = skb_queue_len(list);
-	TIPC_SKB_CB(skb)->chain_imp = imp;
-	skb_queue_tail(&link->wakeupq, skb);
-	link->stats.link_congs++;
+	msg_set_dest_droppable(buf_msg(skb), true);
+	TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr);
+	skb_queue_tail(&l->wakeupq, skb);
+	l->stats.link_congs++;
 	return -ELINKCONG;
 }
 
 /**
  * link_prepare_wakeup - prepare users for wakeup after congestion
- * @link: congested link
- * Move a number of waiting users, as permitted by available space in
- * the send queue, from link wait queue to node wait queue for wakeup
+ * @l: congested link
+ * Wake up a number of waiting users, as permitted by available space
+ * in the send queue
  */
 void link_prepare_wakeup(struct tipc_link *l)
 {
-	int pnd[TIPC_SYSTEM_IMPORTANCE + 1] = {0,};
-	int imp, lim;
 	struct sk_buff *skb, *tmp;
+	int imp, i = 0;
 
 	skb_queue_walk_safe(&l->wakeupq, skb, tmp) {
 		imp = TIPC_SKB_CB(skb)->chain_imp;
-		lim = l->backlog[imp].limit;
-		pnd[imp] += TIPC_SKB_CB(skb)->chain_sz;
-		if ((pnd[imp] + l->backlog[imp].len) >= lim)
+		if (l->backlog[imp].len < l->backlog[imp].limit) {
+			skb_unlink(skb, &l->wakeupq);
+			skb_queue_tail(l->inputq, skb);
+		} else if (i++ > 10) {
 			break;
-		skb_unlink(skb, &l->wakeupq);
-		skb_queue_tail(l->inputq, skb);
+		}
 	}
 }
 
@@ -869,8 +860,7 @@ void tipc_link_reset(struct tipc_link *l)
  * @list: chain of buffers containing message
  * @xmitq: returned list of packets to be sent by caller
  *
- * Consumes the buffer chain, except when returning -ELINKCONG,
- * since the caller then may want to make more send attempts.
+ * Consumes the buffer chain.
  * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS
  * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted
  */
@@ -879,7 +869,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 {
 	struct tipc_msg *hdr = buf_msg(skb_peek(list));
 	unsigned int maxwin = l->window;
-	unsigned int i, imp = msg_importance(hdr);
+	int imp = msg_importance(hdr);
 	unsigned int mtu = l->mtu;
 	u16 ack = l->rcv_nxt - 1;
 	u16 seqno = l->snd_nxt;
@@ -888,19 +878,22 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 	struct sk_buff_head *backlogq = &l->backlogq;
 	struct sk_buff *skb, *_skb, *bskb;
 	int pkt_cnt = skb_queue_len(list);
+	int rc = 0;
 
-	/* Match msg importance against this and all higher backlog limits: */
-	if (!skb_queue_empty(backlogq)) {
-		for (i = imp; i <= TIPC_SYSTEM_IMPORTANCE; i++) {
-			if (unlikely(l->backlog[i].len >= l->backlog[i].limit))
-				return link_schedule_user(l, list);
-		}
-	}
 	if (unlikely(msg_size(hdr) > mtu)) {
 		skb_queue_purge(list);
 		return -EMSGSIZE;
 	}
 
+	/* Allow oversubscription of one data msg per source at congestion */
+	if (unlikely(l->backlog[imp].len >= l->backlog[imp].limit)) {
+		if (imp == TIPC_SYSTEM_IMPORTANCE) {
+			pr_warn("%s<%s>, link overflow", link_rst_msg, l->name);
+			return -ENOBUFS;
+		}
+		rc = link_schedule_user(l, hdr);
+	}
+
 	if (pkt_cnt > 1) {
 		l->stats.sent_fragmented++;
 		l->stats.sent_fragments += pkt_cnt;
@@ -946,7 +939,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 		skb_queue_splice_tail_init(list, backlogq);
 	}
 	l->snd_nxt = seqno;
-	return 0;
+	return rc;
 }
 
 void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq)
@@ -1043,11 +1036,17 @@ int tipc_link_retrans(struct tipc_link *l, u16 from, u16 to,
 static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
 			    struct sk_buff_head *inputq)
 {
-	switch (msg_user(buf_msg(skb))) {
+	struct tipc_msg *hdr = buf_msg(skb);
+
+	switch (msg_user(hdr)) {
 	case TIPC_LOW_IMPORTANCE:
 	case TIPC_MEDIUM_IMPORTANCE:
 	case TIPC_HIGH_IMPORTANCE:
 	case TIPC_CRITICAL_IMPORTANCE:
+		if (unlikely(msg_type(hdr) == TIPC_MCAST_MSG)) {
+			skb_queue_tail(l->bc_rcvlink->inputq, skb);
+			return true;
+		}
 	case CONN_MANAGER:
 		skb_queue_tail(inputq, skb);
 		return true;