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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 76 insertions, 48 deletions

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 2050fd386642..66d3a07bc571 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -107,7 +107,6 @@ struct tipc_stats {
  * @backlogq: queue for messages waiting to be sent
  * @snt_nxt: next sequence number to use for outbound messages
  * @prev_from: sequence number of most previous retransmission request
- * @stale_cnt: counter for number of identical retransmit attempts
  * @stale_limit: time when repeated identical retransmits must force link reset
  * @ackers: # of peers that needs to ack each packet before it can be released
  * @acked: # last packet acked by a certain peer. Used for broadcast.
@@ -167,7 +166,6 @@ struct tipc_link {
 	u16 snd_nxt;
 	u16 prev_from;
 	u16 window;
-	u16 stale_cnt;
 	unsigned long stale_limit;
 
 	/* Reception */
@@ -209,7 +207,7 @@ enum {
 	BC_NACK_SND_SUPPRESS,
 };
 
-#define TIPC_BC_RETR_LIM msecs_to_jiffies(10)   /* [ms] */
+#define TIPC_BC_RETR_LIM  (jiffies + msecs_to_jiffies(10))
 #define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1))
 
 /*
@@ -249,9 +247,9 @@ static void tipc_link_build_bc_init_msg(struct tipc_link *l,
 					struct sk_buff_head *xmitq);
 static bool tipc_link_release_pkts(struct tipc_link *l, u16 to);
 static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data);
-static void tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap,
-				      struct tipc_gap_ack_blks *ga,
-				      struct sk_buff_head *xmitq);
+static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap,
+				     struct tipc_gap_ack_blks *ga,
+				     struct sk_buff_head *xmitq);
 
 /*
  *  Simple non-static link routines (i.e. referenced outside this file)
@@ -734,7 +732,7 @@ static void link_profile_stats(struct tipc_link *l)
 	if (msg_user(msg) == MSG_FRAGMENTER) {
 		if (msg_type(msg) != FIRST_FRAGMENT)
 			return;
-		length = msg_size(msg_get_wrapped(msg));
+		length = msg_size(msg_inner_hdr(msg));
 	}
 	l->stats.msg_lengths_total += length;
 	l->stats.msg_length_counts++;
@@ -910,7 +908,6 @@ void tipc_link_reset(struct tipc_link *l)
 	l->acked = 0;
 	l->silent_intv_cnt = 0;
 	l->rst_cnt = 0;
-	l->stale_cnt = 0;
 	l->bc_peer_is_up = false;
 	memset(&l->mon_state, 0, sizeof(l->mon_state));
 	tipc_link_reset_stats(l);
@@ -979,8 +976,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 			__skb_queue_tail(transmq, skb);
 			/* next retransmit attempt */
 			if (link_is_bc_sndlink(l))
-				TIPC_SKB_CB(skb)->nxt_retr =
-					jiffies + TIPC_BC_RETR_LIM;
+				TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
 			__skb_queue_tail(xmitq, _skb);
 			TIPC_SKB_CB(skb)->ackers = l->ackers;
 			l->rcv_unacked = 0;
@@ -1030,7 +1026,7 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
 		__skb_queue_tail(&l->transmq, skb);
 		/* next retransmit attempt */
 		if (link_is_bc_sndlink(l))
-			TIPC_SKB_CB(skb)->nxt_retr = jiffies + TIPC_BC_RETR_LIM;
+			TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
 
 		__skb_queue_tail(xmitq, _skb);
 		TIPC_SKB_CB(skb)->ackers = l->ackers;
@@ -1044,32 +1040,68 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
 	l->snd_nxt = seqno;
 }
 
-static void link_retransmit_failure(struct tipc_link *l, struct sk_buff *skb)
+/**
+ * link_retransmit_failure() - Detect repeated retransmit failures
+ * @l: tipc link sender
+ * @r: tipc link receiver (= l in case of unicast)
+ * @from: seqno of the 1st packet in retransmit request
+ * @rc: returned code
+ *
+ * Return: true if the repeated retransmit failures happens, otherwise
+ * false
+ */
+static bool link_retransmit_failure(struct tipc_link *l, struct tipc_link *r,
+				    u16 from, int *rc)
 {
-	struct tipc_msg *hdr = buf_msg(skb);
+	struct sk_buff *skb = skb_peek(&l->transmq);
+	struct tipc_msg *hdr;
+
+	if (!skb)
+		return false;
+	hdr = buf_msg(skb);
+
+	/* Detect repeated retransmit failures on same packet */
+	if (r->prev_from != from) {
+		r->prev_from = from;
+		r->stale_limit = jiffies + msecs_to_jiffies(r->tolerance);
+	} else if (time_after(jiffies, r->stale_limit)) {
+		pr_warn("Retransmission failure on link <%s>\n", l->name);
+		link_print(l, "State of link ");
+		pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n",
+			msg_user(hdr), msg_type(hdr), msg_size(hdr),
+			msg_errcode(hdr));
+		pr_info("sqno %u, prev: %x, src: %x\n",
+			msg_seqno(hdr), msg_prevnode(hdr), msg_orignode(hdr));
+
+		trace_tipc_list_dump(&l->transmq, true, "retrans failure!");
+		trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!");
+		trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!");
+
+		if (link_is_bc_sndlink(l))
+			*rc = TIPC_LINK_DOWN_EVT;
+
+		*rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
+		return true;
+	}
 
-	pr_warn("Retransmission failure on link <%s>\n", l->name);
-	link_print(l, "State of link ");
-	pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n",
-		msg_user(hdr), msg_type(hdr), msg_size(hdr), msg_errcode(hdr));
-	pr_info("sqno %u, prev: %x, src: %x\n",
-		msg_seqno(hdr), msg_prevnode(hdr), msg_orignode(hdr));
+	return false;
 }
 
-/* tipc_link_retrans() - retransmit one or more packets
+/* tipc_link_bc_retrans() - retransmit zero or more packets
  * @l: the link to transmit on
  * @r: the receiving link ordering the retransmit. Same as l if unicast
  * @from: retransmit from (inclusive) this sequence number
  * @to: retransmit to (inclusive) this sequence number
  * xmitq: queue for accumulating the retransmitted packets
  */
-static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
-			     u16 from, u16 to, struct sk_buff_head *xmitq)
+static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r,
+				u16 from, u16 to, struct sk_buff_head *xmitq)
 {
 	struct sk_buff *_skb, *skb = skb_peek(&l->transmq);
 	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
 	u16 ack = l->rcv_nxt - 1;
 	struct tipc_msg *hdr;
+	int rc = 0;
 
 	if (!skb)
 		return 0;
@@ -1077,20 +1109,9 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
 		return 0;
 
 	trace_tipc_link_retrans(r, from, to, &l->transmq);
-	/* Detect repeated retransmit failures on same packet */
-	if (r->prev_from != from) {
-		r->prev_from = from;
-		r->stale_limit = jiffies + msecs_to_jiffies(r->tolerance);
-		r->stale_cnt = 0;
-	} else if (++r->stale_cnt > 99 && time_after(jiffies, r->stale_limit)) {
-		link_retransmit_failure(l, skb);
-		trace_tipc_list_dump(&l->transmq, true, "retrans failure!");
-		trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!");
-		trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!");
-		if (link_is_bc_sndlink(l))
-			return TIPC_LINK_DOWN_EVT;
-		return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
-	}
+
+	if (link_retransmit_failure(l, r, from, &rc))
+		return rc;
 
 	skb_queue_walk(&l->transmq, skb) {
 		hdr = buf_msg(skb);
@@ -1101,9 +1122,9 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
 		if (link_is_bc_sndlink(l)) {
 			if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
 				continue;
-			TIPC_SKB_CB(skb)->nxt_retr = jiffies + TIPC_BC_RETR_LIM;
+			TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
 		}
-		_skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC);
+		_skb = __pskb_copy(skb, LL_MAX_HEADER + MIN_H_SIZE, GFP_ATOMIC);
 		if (!_skb)
 			return 0;
 		hdr = buf_msg(_skb);
@@ -1324,17 +1345,23 @@ exit:
  * @gap: # of gap packets
  * @ga: buffer pointer to Gap ACK blocks from peer
  * @xmitq: queue for accumulating the retransmitted packets if any
+ *
+ * In case of a repeated retransmit failures, the call will return shortly
+ * with a returned code (e.g. TIPC_LINK_DOWN_EVT)
  */
-static void tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap,
-				      struct tipc_gap_ack_blks *ga,
-				      struct sk_buff_head *xmitq)
+static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap,
+				     struct tipc_gap_ack_blks *ga,
+				     struct sk_buff_head *xmitq)
 {
 	struct sk_buff *skb, *_skb, *tmp;
 	struct tipc_msg *hdr;
 	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
 	u16 ack = l->rcv_nxt - 1;
-	u16 seqno;
-	u16 n = 0;
+	u16 seqno, n = 0;
+	int rc = 0;
+
+	if (gap && link_retransmit_failure(l, l, acked + 1, &rc))
+		return rc;
 
 	skb_queue_walk_safe(&l->transmq, skb, tmp) {
 		seqno = buf_seqno(skb);
@@ -1369,6 +1396,8 @@ next_gap_ack:
 			goto next_gap_ack;
 		}
 	}
+
+	return 0;
 }
 
 /* tipc_link_build_state_msg: prepare link state message for transmission
@@ -1481,7 +1510,6 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
 
 		/* Forward queues and wake up waiting users */
 		if (likely(tipc_link_release_pkts(l, msg_ack(hdr)))) {
-			l->stale_cnt = 0;
 			tipc_link_advance_backlog(l, xmitq);
 			if (unlikely(!skb_queue_empty(&l->wakeupq)))
 				link_prepare_wakeup(l);
@@ -1918,7 +1946,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 			tipc_link_build_proto_msg(l, STATE_MSG, 0, reply,
 						  rcvgap, 0, 0, xmitq);
 
-		tipc_link_advance_transmq(l, ack, gap, ga, xmitq);
+		rc |= tipc_link_advance_transmq(l, ack, gap, ga, xmitq);
 
 		/* If NACK, retransmit will now start at right position */
 		if (gap)
@@ -2035,7 +2063,7 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr,
 	if (more(peers_snd_nxt, l->rcv_nxt + l->window))
 		return rc;
 
-	rc = tipc_link_retrans(snd_l, l, from, to, xmitq);
+	rc = tipc_link_bc_retrans(snd_l, l, from, to, xmitq);
 
 	l->snd_nxt = peers_snd_nxt;
 	if (link_bc_rcv_gap(l))
@@ -2131,7 +2159,7 @@ int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb,
 
 	if (dnode == tipc_own_addr(l->net)) {
 		tipc_link_bc_ack_rcv(l, acked, xmitq);
-		rc = tipc_link_retrans(l->bc_sndlink, l, from, to, xmitq);
+		rc = tipc_link_bc_retrans(l->bc_sndlink, l, from, to, xmitq);
 		l->stats.recv_nacks++;
 		return rc;
 	}
@@ -2550,7 +2578,7 @@ int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf)
 	i += scnprintf(buf + i, sz - i, " %u", l->silent_intv_cnt);
 	i += scnprintf(buf + i, sz - i, " %u", l->rst_cnt);
 	i += scnprintf(buf + i, sz - i, " %u", l->prev_from);
-	i += scnprintf(buf + i, sz - i, " %u", l->stale_cnt);
+	i += scnprintf(buf + i, sz - i, " %u", 0);
 	i += scnprintf(buf + i, sz - i, " %u", l->acked);
 
 	list = &l->transmq;