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

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

1 files changed, 75 insertions, 15 deletions

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 0453bd451ce8..68014f1b6976 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -45,6 +45,7 @@
 #include "netlink.h"
 
 #define INVALID_NODE_SIG	0x10000
+#define NODE_CLEANUP_AFTER	300000
 
 /* Flags used to take different actions according to flag type
  * TIPC_NOTIFY_NODE_DOWN: notify node is down
@@ -96,6 +97,7 @@ struct tipc_bclink_entry {
  * @link_id: local and remote bearer ids of changing link, if any
  * @publ_list: list of publications
  * @rcu: rcu struct for tipc_node
+ * @delete_at: indicates the time for deleting a down node
  */
 struct tipc_node {
 	u32 addr;
@@ -121,6 +123,7 @@ struct tipc_node {
 	unsigned long keepalive_intv;
 	struct timer_list timer;
 	struct rcu_head rcu;
+	unsigned long delete_at;
 };
 
 /* Node FSM states and events:
@@ -160,6 +163,7 @@ static struct tipc_node *tipc_node_find(struct net *net, u32 addr);
 static struct tipc_node *tipc_node_find_by_id(struct net *net, u8 *id);
 static void tipc_node_put(struct tipc_node *node);
 static bool node_is_up(struct tipc_node *n);
+static void tipc_node_delete_from_list(struct tipc_node *node);
 
 struct tipc_sock_conn {
 	u32 port;
@@ -359,13 +363,24 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr,
 {
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_node *n, *temp_node;
+	struct tipc_link *l;
+	int bearer_id;
 	int i;
 
 	spin_lock_bh(&tn->node_list_lock);
 	n = tipc_node_find(net, addr);
 	if (n) {
+		if (n->capabilities == capabilities)
+			goto exit;
 		/* Same node may come back with new capabilities */
+		write_lock_bh(&n->lock);
 		n->capabilities = capabilities;
+		for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
+			l = n->links[bearer_id].link;
+			if (l)
+				tipc_link_update_caps(l, capabilities);
+		}
+		write_unlock_bh(&n->lock);
 		goto exit;
 	}
 	n = kzalloc(sizeof(*n), GFP_ATOMIC);
@@ -390,6 +405,7 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr,
 	for (i = 0; i < MAX_BEARERS; i++)
 		spin_lock_init(&n->links[i].lock);
 	n->state = SELF_DOWN_PEER_LEAVING;
+	n->delete_at = jiffies + msecs_to_jiffies(NODE_CLEANUP_AFTER);
 	n->signature = INVALID_NODE_SIG;
 	n->active_links[0] = INVALID_BEARER_ID;
 	n->active_links[1] = INVALID_BEARER_ID;
@@ -433,11 +449,16 @@ static void tipc_node_calculate_timer(struct tipc_node *n, struct tipc_link *l)
 	tipc_link_set_abort_limit(l, tol / n->keepalive_intv);
 }
 
-static void tipc_node_delete(struct tipc_node *node)
+static void tipc_node_delete_from_list(struct tipc_node *node)
 {
 	list_del_rcu(&node->list);
 	hlist_del_rcu(&node->hash);
 	tipc_node_put(node);
+}
+
+static void tipc_node_delete(struct tipc_node *node)
+{
+	tipc_node_delete_from_list(node);
 
 	del_timer_sync(&node->timer);
 	tipc_node_put(node);
@@ -544,6 +565,42 @@ void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port)
 	tipc_node_put(node);
 }
 
+static void  tipc_node_clear_links(struct tipc_node *node)
+{
+	int i;
+
+	for (i = 0; i < MAX_BEARERS; i++) {
+		struct tipc_link_entry *le = &node->links[i];
+
+		if (le->link) {
+			kfree(le->link);
+			le->link = NULL;
+			node->link_cnt--;
+		}
+	}
+}
+
+/* tipc_node_cleanup - delete nodes that does not
+ * have active links for NODE_CLEANUP_AFTER time
+ */
+static int tipc_node_cleanup(struct tipc_node *peer)
+{
+	struct tipc_net *tn = tipc_net(peer->net);
+	bool deleted = false;
+
+	spin_lock_bh(&tn->node_list_lock);
+	tipc_node_write_lock(peer);
+
+	if (!node_is_up(peer) && time_after(jiffies, peer->delete_at)) {
+		tipc_node_clear_links(peer);
+		tipc_node_delete_from_list(peer);
+		deleted = true;
+	}
+	tipc_node_write_unlock(peer);
+	spin_unlock_bh(&tn->node_list_lock);
+	return deleted;
+}
+
 /* tipc_node_timeout - handle expiration of node timer
  */
 static void tipc_node_timeout(struct timer_list *t)
@@ -551,21 +608,29 @@ static void tipc_node_timeout(struct timer_list *t)
 	struct tipc_node *n = from_timer(n, t, timer);
 	struct tipc_link_entry *le;
 	struct sk_buff_head xmitq;
+	int remains = n->link_cnt;
 	int bearer_id;
 	int rc = 0;
 
+	if (!node_is_up(n) && tipc_node_cleanup(n)) {
+		/*Removing the reference of Timer*/
+		tipc_node_put(n);
+		return;
+	}
+
 	__skb_queue_head_init(&xmitq);
 
-	for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
+	for (bearer_id = 0; remains && (bearer_id < MAX_BEARERS); bearer_id++) {
 		tipc_node_read_lock(n);
 		le = &n->links[bearer_id];
-		spin_lock_bh(&le->lock);
 		if (le->link) {
+			spin_lock_bh(&le->lock);
 			/* Link tolerance may change asynchronously: */
 			tipc_node_calculate_timer(n, le->link);
 			rc = tipc_link_timeout(le->link, &xmitq);
+			spin_unlock_bh(&le->lock);
+			remains--;
 		}
-		spin_unlock_bh(&le->lock);
 		tipc_node_read_unlock(n);
 		tipc_bearer_xmit(n->net, bearer_id, &xmitq, &le->maddr);
 		if (rc & TIPC_LINK_DOWN_EVT)
@@ -1174,6 +1239,7 @@ static void node_lost_contact(struct tipc_node *n,
 	uint i;
 
 	pr_debug("Lost contact with %x\n", n->addr);
+	n->delete_at = jiffies + msecs_to_jiffies(NODE_CLEANUP_AFTER);
 
 	/* Clean up broadcast state */
 	tipc_bcast_remove_peer(n->net, n->bc_entry.link);
@@ -1481,7 +1547,7 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id
  * tipc_node_check_state - check and if necessary update node state
  * @skb: TIPC packet
  * @bearer_id: identity of bearer delivering the packet
- * Returns true if state is ok, otherwise consumes buffer and returns false
+ * Returns true if state and msg are ok, otherwise false
  */
 static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
 				  int bearer_id, struct sk_buff_head *xmitq)
@@ -1515,6 +1581,9 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
 		}
 	}
 
+	if (!tipc_link_validate_msg(l, hdr))
+		return false;
+
 	/* Check and update node accesibility if applicable */
 	if (state == SELF_UP_PEER_COMING) {
 		if (!tipc_link_is_up(l))
@@ -1743,7 +1812,6 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info)
 	struct tipc_node *peer;
 	u32 addr;
 	int err;
-	int i;
 
 	/* We identify the peer by its net */
 	if (!info->attrs[TIPC_NLA_NET])
@@ -1778,15 +1846,7 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info)
 		goto err_out;
 	}
 
-	for (i = 0; i < MAX_BEARERS; i++) {
-		struct tipc_link_entry *le = &peer->links[i];
-
-		if (le->link) {
-			kfree(le->link);
-			le->link = NULL;
-			peer->link_cnt--;
-		}
-	}
+	tipc_node_clear_links(peer);
 	tipc_node_write_unlock(peer);
 	tipc_node_delete(peer);