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

Pull networking updates from David Miller:

 1) New ipset extensions for matching on destination MAC addresses, from
    Stefano Brivio.

 2) Add ipv4 ttl and tos, plus ipv6 flow label and hop limit offloads to
    nfp driver. From Stefano Brivio.

 3) Implement GRO for plain UDP sockets, from Paolo Abeni.

 4) Lots of work from Michał Mirosław to eliminate the VLAN_TAG_PRESENT
    bit so that we could support the entire vlan_tci value.

 5) Rework the IPSEC policy lookups to better optimize more usecases,
    from Florian Westphal.

 6) Infrastructure changes eliminating direct manipulation of SKB lists
    wherever possible, and to always use the appropriate SKB list
    helpers. This work is still ongoing...

 7) Lots of PHY driver and state machine improvements and
    simplifications, from Heiner Kallweit.

 8) Various TSO deferral refinements, from Eric Dumazet.

 9) Add ntuple filter support to aquantia driver, from Dmitry Bogdanov.

10) Batch dropping of XDP packets in tuntap, from Jason Wang.

11) Lots of cleanups and improvements to the r8169 driver from Heiner
    Kallweit, including support for ->xmit_more. This driver has been
    getting some much needed love since he started working on it.

12) Lots of new forwarding selftests from Petr Machata.

13) Enable VXLAN learning in mlxsw driver, from Ido Schimmel.

14) Packed ring support for virtio, from Tiwei Bie.

15) Add new Aquantia AQtion USB driver, from Dmitry Bezrukov.

16) Add XDP support to dpaa2-eth driver, from Ioana Ciocoi Radulescu.

17) Implement coalescing on TCP backlog queue, from Eric Dumazet.

18) Implement carrier change in tun driver, from Nicolas Dichtel.

19) Support msg_zerocopy in UDP, from Willem de Bruijn.

20) Significantly improve garbage collection of neighbor objects when
    the table has many PERMANENT entries, from David Ahern.

21) Remove egdev usage from nfp and mlx5, and remove the facility
    completely from the tree as it no longer has any users. From Oz
    Shlomo and others.

22) Add a NETDEV_PRE_CHANGEADDR so that drivers can veto the change and
    therefore abort the operation before the commit phase (which is the
    NETDEV_CHANGEADDR event). From Petr Machata.

23) Add indirect call wrappers to avoid retpoline overhead, and use them
    in the GRO code paths. From Paolo Abeni.

24) Add support for netlink FDB get operations, from Roopa Prabhu.

25) Support bloom filter in mlxsw driver, from Nir Dotan.

26) Add SKB extension infrastructure. This consolidates the handling of
    the auxiliary SKB data used by IPSEC and bridge netfilter, and is
    designed to support the needs to MPTCP which could be integrated in
    the future.

27) Lots of XDP TX optimizations in mlx5 from Tariq Toukan.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1845 commits)
  net: dccp: fix kernel crash on module load
  drivers/net: appletalk/cops: remove redundant if statement and mask
  bnx2x: Fix NULL pointer dereference in bnx2x_del_all_vlans() on some hw
  net/net_namespace: Check the return value of register_pernet_subsys()
  net/netlink_compat: Fix a missing check of nla_parse_nested
  ieee802154: lowpan_header_create check must check daddr
  net/mlx4_core: drop useless LIST_HEAD
  mlxsw: spectrum: drop useless LIST_HEAD
  net/mlx5e: drop useless LIST_HEAD
  iptunnel: Set tun_flags in the iptunnel_metadata_reply from src
  net/mlx5e: fix semicolon.cocci warnings
  staging: octeon: fix build failure with XFRM enabled
  net: Revert recent Spectre-v1 patches.
  can: af_can: Fix Spectre v1 vulnerability
  packet: validate address length if non-zero
  nfc: af_nfc: Fix Spectre v1 vulnerability
  phonet: af_phonet: Fix Spectre v1 vulnerability
  net: core: Fix Spectre v1 vulnerability
  net: minor cleanup in skb_ext_add()
  net: drop the unused helper skb_ext_get()
  ...

1 files changed, 173 insertions, 47 deletions

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 836727e363c4..2792a3cae682 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -43,6 +43,7 @@
 #include "discover.h"
 #include "netlink.h"
 #include "monitor.h"
+#include "trace.h"
 
 #include <linux/pkt_sched.h>
 
@@ -105,7 +106,7 @@ struct tipc_stats {
  * @transmitq: queue for sent, non-acked messages
  * @backlogq: queue for messages waiting to be sent
  * @snt_nxt: next sequence number to use for outbound messages
- * @last_retransmitted: sequence number of most recently retransmitted message
+ * @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
@@ -163,7 +164,7 @@ struct tipc_link {
 		u16 limit;
 	} backlog[5];
 	u16 snd_nxt;
-	u16 last_retransm;
+	u16 prev_from;
 	u16 window;
 	u16 stale_cnt;
 	unsigned long stale_limit;
@@ -186,9 +187,6 @@ struct tipc_link {
 	u16 acked;
 	struct tipc_link *bc_rcvlink;
 	struct tipc_link *bc_sndlink;
-	unsigned long prev_retr;
-	u16 prev_from;
-	u16 prev_to;
 	u8 nack_state;
 	bool bc_peer_is_up;
 
@@ -210,7 +208,7 @@ enum {
 	BC_NACK_SND_SUPPRESS,
 };
 
-#define TIPC_BC_RETR_LIMIT 10   /* [ms] */
+#define TIPC_BC_RETR_LIM msecs_to_jiffies(10)   /* [ms] */
 
 /*
  * Interval between NACKs when packets arrive out of order
@@ -359,9 +357,11 @@ void tipc_link_remove_bc_peer(struct tipc_link *snd_l,
 	rcv_l->bc_peer_is_up = true;
 	rcv_l->state = LINK_ESTABLISHED;
 	tipc_link_bc_ack_rcv(rcv_l, ack, xmitq);
+	trace_tipc_link_reset(rcv_l, TIPC_DUMP_ALL, "bclink removed!");
 	tipc_link_reset(rcv_l);
 	rcv_l->state = LINK_RESET;
 	if (!snd_l->ackers) {
+		trace_tipc_link_reset(snd_l, TIPC_DUMP_ALL, "zero ackers!");
 		tipc_link_reset(snd_l);
 		snd_l->state = LINK_RESET;
 		__skb_queue_purge(xmitq);
@@ -525,6 +525,7 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer,
 
 	l = *link;
 	strcpy(l->name, tipc_bclink_name);
+	trace_tipc_link_reset(l, TIPC_DUMP_ALL, "bclink created!");
 	tipc_link_reset(l);
 	l->state = LINK_RESET;
 	l->ackers = 0;
@@ -549,6 +550,7 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer,
 int tipc_link_fsm_evt(struct tipc_link *l, int evt)
 {
 	int rc = 0;
+	int old_state = l->state;
 
 	switch (l->state) {
 	case LINK_RESETTING:
@@ -695,10 +697,12 @@ int tipc_link_fsm_evt(struct tipc_link *l, int evt)
 	default:
 		pr_err("Unknown FSM state %x in %s\n", l->state, l->name);
 	}
+	trace_tipc_link_fsm(l->name, old_state, l->state, evt);
 	return rc;
 illegal_evt:
 	pr_err("Illegal FSM event %x in state %x on link %s\n",
 	       evt, l->state, l->name);
+	trace_tipc_link_fsm(l->name, old_state, l->state, evt);
 	return rc;
 }
 
@@ -743,6 +747,18 @@ static void link_profile_stats(struct tipc_link *l)
 		l->stats.msg_length_profile[6]++;
 }
 
+/**
+ * tipc_link_too_silent - check if link is "too silent"
+ * @l: tipc link to be checked
+ *
+ * Returns true if the link 'silent_intv_cnt' is about to reach the
+ * 'abort_limit' value, otherwise false
+ */
+bool tipc_link_too_silent(struct tipc_link *l)
+{
+	return (l->silent_intv_cnt + 2 > l->abort_limit);
+}
+
 /* tipc_link_timeout - perform periodic task as instructed from node timeout
  */
 int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
@@ -756,6 +772,8 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
 	u16 bc_acked = l->bc_rcvlink->acked;
 	struct tipc_mon_state *mstate = &l->mon_state;
 
+	trace_tipc_link_timeout(l, TIPC_DUMP_NONE, " ");
+	trace_tipc_link_too_silent(l, TIPC_DUMP_ALL, " ");
 	switch (l->state) {
 	case LINK_ESTABLISHED:
 	case LINK_SYNCHING:
@@ -818,6 +836,7 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr)
 	TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr);
 	skb_queue_tail(&l->wakeupq, skb);
 	l->stats.link_congs++;
+	trace_tipc_link_conges(l, TIPC_DUMP_ALL, "wakeup scheduled!");
 	return -ELINKCONG;
 }
 
@@ -948,6 +967,10 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 			}
 			__skb_dequeue(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;
 			__skb_queue_tail(xmitq, _skb);
 			TIPC_SKB_CB(skb)->ackers = l->ackers;
 			l->rcv_unacked = 0;
@@ -995,6 +1018,10 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
 		hdr = buf_msg(skb);
 		l->backlog[msg_importance(hdr)].len--;
 		__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;
+
 		__skb_queue_tail(xmitq, _skb);
 		TIPC_SKB_CB(skb)->ackers = l->ackers;
 		msg_set_seqno(hdr, seqno);
@@ -1036,14 +1063,20 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
 
 	if (!skb)
 		return 0;
+	if (less(to, from))
+		return 0;
 
+	trace_tipc_link_retrans(r, from, to, &l->transmq);
 	/* Detect repeated retransmit failures on same packet */
-	if (r->last_retransm != buf_seqno(skb)) {
-		r->last_retransm = buf_seqno(skb);
+	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);
@@ -1055,6 +1088,11 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
 			continue;
 		if (more(msg_seqno(hdr), to))
 			break;
+		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;
+		}
 		_skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC);
 		if (!_skb)
 			return 0;
@@ -1398,6 +1436,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
 		l->stats.sent_nacks++;
 	skb->priority = TC_PRIO_CONTROL;
 	__skb_queue_tail(xmitq, skb);
+	trace_tipc_proto_build(skb, false, l->name);
 }
 
 void tipc_link_create_dummy_tnl_msg(struct tipc_link *l,
@@ -1561,6 +1600,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 	char *if_name;
 	int rc = 0;
 
+	trace_tipc_proto_rcv(skb, false, l->name);
 	if (tipc_link_is_blocked(l) || !xmitq)
 		goto exit;
 
@@ -1571,8 +1611,11 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 	hdr = buf_msg(skb);
 	data = msg_data(hdr);
 
-	if (!tipc_link_validate_msg(l, hdr))
+	if (!tipc_link_validate_msg(l, hdr)) {
+		trace_tipc_skb_dump(skb, false, "PROTO invalid (1)!");
+		trace_tipc_link_dump(l, TIPC_DUMP_NONE, "PROTO invalid (1)!");
 		goto exit;
+	}
 
 	switch (mtyp) {
 	case RESET_MSG:
@@ -1737,42 +1780,6 @@ void tipc_link_bc_init_rcv(struct tipc_link *l, struct tipc_msg *hdr)
 		l->rcv_nxt = peers_snd_nxt;
 }
 
-/* link_bc_retr eval()- check if the indicated range can be retransmitted now
- * - Adjust permitted range if there is overlap with previous retransmission
- */
-static bool link_bc_retr_eval(struct tipc_link *l, u16 *from, u16 *to)
-{
-	unsigned long elapsed = jiffies_to_msecs(jiffies - l->prev_retr);
-
-	if (less(*to, *from))
-		return false;
-
-	/* New retransmission request */
-	if ((elapsed > TIPC_BC_RETR_LIMIT) ||
-	    less(*to, l->prev_from) || more(*from, l->prev_to)) {
-		l->prev_from = *from;
-		l->prev_to = *to;
-		l->prev_retr = jiffies;
-		return true;
-	}
-
-	/* Inside range of previous retransmit */
-	if (!less(*from, l->prev_from) && !more(*to, l->prev_to))
-		return false;
-
-	/* Fully or partially outside previous range => exclude overlap */
-	if (less(*from, l->prev_from)) {
-		*to = l->prev_from - 1;
-		l->prev_from = *from;
-	}
-	if (more(*to, l->prev_to)) {
-		*from = l->prev_to + 1;
-		l->prev_to = *to;
-	}
-	l->prev_retr = jiffies;
-	return true;
-}
-
 /* tipc_link_bc_sync_rcv - update rcv link according to peer's send state
  */
 int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr,
@@ -1803,8 +1810,7 @@ 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;
 
-	if (link_bc_retr_eval(snd_l, &from, &to))
-		rc = tipc_link_retrans(snd_l, l, from, to, xmitq);
+	rc = tipc_link_retrans(snd_l, l, from, to, xmitq);
 
 	l->snd_nxt = peers_snd_nxt;
 	if (link_bc_rcv_gap(l))
@@ -1852,6 +1858,7 @@ void tipc_link_bc_ack_rcv(struct tipc_link *l, u16 acked,
 	if (!more(acked, l->acked))
 		return;
 
+	trace_tipc_link_bc_ack(l, l->acked, acked, &snd_l->transmq);
 	/* Skip over packets peer has already acked */
 	skb_queue_walk(&snd_l->transmq, skb) {
 		if (more(buf_seqno(skb), l->acked))
@@ -2255,3 +2262,122 @@ void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit)
 {
 	l->abort_limit = limit;
 }
+
+char *tipc_link_name_ext(struct tipc_link *l, char *buf)
+{
+	if (!l)
+		scnprintf(buf, TIPC_MAX_LINK_NAME, "null");
+	else if (link_is_bc_sndlink(l))
+		scnprintf(buf, TIPC_MAX_LINK_NAME, "broadcast-sender");
+	else if (link_is_bc_rcvlink(l))
+		scnprintf(buf, TIPC_MAX_LINK_NAME,
+			  "broadcast-receiver, peer %x", l->addr);
+	else
+		memcpy(buf, l->name, TIPC_MAX_LINK_NAME);
+
+	return buf;
+}
+
+/**
+ * tipc_link_dump - dump TIPC link data
+ * @l: tipc link to be dumped
+ * @dqueues: bitmask to decide if any link queue to be dumped?
+ *           - TIPC_DUMP_NONE: don't dump link queues
+ *           - TIPC_DUMP_TRANSMQ: dump link transmq queue
+ *           - TIPC_DUMP_BACKLOGQ: dump link backlog queue
+ *           - TIPC_DUMP_DEFERDQ: dump link deferd queue
+ *           - TIPC_DUMP_INPUTQ: dump link input queue
+ *           - TIPC_DUMP_WAKEUP: dump link wakeup queue
+ *           - TIPC_DUMP_ALL: dump all the link queues above
+ * @buf: returned buffer of dump data in format
+ */
+int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf)
+{
+	int i = 0;
+	size_t sz = (dqueues) ? LINK_LMAX : LINK_LMIN;
+	struct sk_buff_head *list;
+	struct sk_buff *hskb, *tskb;
+	u32 len;
+
+	if (!l) {
+		i += scnprintf(buf, sz, "link data: (null)\n");
+		return i;
+	}
+
+	i += scnprintf(buf, sz, "link data: %x", l->addr);
+	i += scnprintf(buf + i, sz - i, " %x", l->state);
+	i += scnprintf(buf + i, sz - i, " %u", l->in_session);
+	i += scnprintf(buf + i, sz - i, " %u", l->session);
+	i += scnprintf(buf + i, sz - i, " %u", l->peer_session);
+	i += scnprintf(buf + i, sz - i, " %u", l->snd_nxt);
+	i += scnprintf(buf + i, sz - i, " %u", l->rcv_nxt);
+	i += scnprintf(buf + i, sz - i, " %u", l->snd_nxt_state);
+	i += scnprintf(buf + i, sz - i, " %u", l->rcv_nxt_state);
+	i += scnprintf(buf + i, sz - i, " %x", l->peer_caps);
+	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", l->acked);
+
+	list = &l->transmq;
+	len = skb_queue_len(list);
+	hskb = skb_peek(list);
+	tskb = skb_peek_tail(list);
+	i += scnprintf(buf + i, sz - i, " | %u %u %u", len,
+		       (hskb) ? msg_seqno(buf_msg(hskb)) : 0,
+		       (tskb) ? msg_seqno(buf_msg(tskb)) : 0);
+
+	list = &l->deferdq;
+	len = skb_queue_len(list);
+	hskb = skb_peek(list);
+	tskb = skb_peek_tail(list);
+	i += scnprintf(buf + i, sz - i, " | %u %u %u", len,
+		       (hskb) ? msg_seqno(buf_msg(hskb)) : 0,
+		       (tskb) ? msg_seqno(buf_msg(tskb)) : 0);
+
+	list = &l->backlogq;
+	len = skb_queue_len(list);
+	hskb = skb_peek(list);
+	tskb = skb_peek_tail(list);
+	i += scnprintf(buf + i, sz - i, " | %u %u %u", len,
+		       (hskb) ? msg_seqno(buf_msg(hskb)) : 0,
+		       (tskb) ? msg_seqno(buf_msg(tskb)) : 0);
+
+	list = l->inputq;
+	len = skb_queue_len(list);
+	hskb = skb_peek(list);
+	tskb = skb_peek_tail(list);
+	i += scnprintf(buf + i, sz - i, " | %u %u %u\n", len,
+		       (hskb) ? msg_seqno(buf_msg(hskb)) : 0,
+		       (tskb) ? msg_seqno(buf_msg(tskb)) : 0);
+
+	if (dqueues & TIPC_DUMP_TRANSMQ) {
+		i += scnprintf(buf + i, sz - i, "transmq: ");
+		i += tipc_list_dump(&l->transmq, false, buf + i);
+	}
+	if (dqueues & TIPC_DUMP_BACKLOGQ) {
+		i += scnprintf(buf + i, sz - i,
+			       "backlogq: <%u %u %u %u %u>, ",
+			       l->backlog[TIPC_LOW_IMPORTANCE].len,
+			       l->backlog[TIPC_MEDIUM_IMPORTANCE].len,
+			       l->backlog[TIPC_HIGH_IMPORTANCE].len,
+			       l->backlog[TIPC_CRITICAL_IMPORTANCE].len,
+			       l->backlog[TIPC_SYSTEM_IMPORTANCE].len);
+		i += tipc_list_dump(&l->backlogq, false, buf + i);
+	}
+	if (dqueues & TIPC_DUMP_DEFERDQ) {
+		i += scnprintf(buf + i, sz - i, "deferdq: ");
+		i += tipc_list_dump(&l->deferdq, false, buf + i);
+	}
+	if (dqueues & TIPC_DUMP_INPUTQ) {
+		i += scnprintf(buf + i, sz - i, "inputq: ");
+		i += tipc_list_dump(l->inputq, false, buf + i);
+	}
+	if (dqueues & TIPC_DUMP_WAKEUP) {
+		i += scnprintf(buf + i, sz - i, "wakeup: ");
+		i += tipc_list_dump(&l->wakeupq, false, buf + i);
+	}
+
+	return i;
+}