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

Pull networking updates from David Miller:

 1) Seccomp BPF filters can now be JIT'd, from Alexei Starovoitov.

 2) Multiqueue support in xen-netback and xen-netfront, from Andrew J
    Benniston.

 3) Allow tweaking of aggregation settings in cdc_ncm driver, from Bjørn
    Mork.

 4) BPF now has a "random" opcode, from Chema Gonzalez.

 5) Add more BPF documentation and improve test framework, from Daniel
    Borkmann.

 6) Support TCP fastopen over ipv6, from Daniel Lee.

 7) Add software TSO helper functions and use them to support software
    TSO in mvneta and mv643xx_eth drivers.  From Ezequiel Garcia.

 8) Support software TSO in fec driver too, from Nimrod Andy.

 9) Add Broadcom SYSTEMPORT driver, from Florian Fainelli.

10) Handle broadcasts more gracefully over macvlan when there are large
    numbers of interfaces configured, from Herbert Xu.

11) Allow more control over fwmark used for non-socket based responses,
    from Lorenzo Colitti.

12) Do TCP congestion window limiting based upon measurements, from Neal
    Cardwell.

13) Support busy polling in SCTP, from Neal Horman.

14) Allow RSS key to be configured via ethtool, from Venkata Duvvuru.

15) Bridge promisc mode handling improvements from Vlad Yasevich.

16) Don't use inetpeer entries to implement ID generation any more, it
    performs poorly, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits)
  rtnetlink: fix userspace API breakage for iproute2 < v3.9.0
  tcp: fixing TLP's FIN recovery
  net: fec: Add software TSO support
  net: fec: Add Scatter/gather support
  net: fec: Increase buffer descriptor entry number
  net: fec: Factorize feature setting
  net: fec: Enable IP header hardware checksum
  net: fec: Factorize the .xmit transmit function
  bridge: fix compile error when compiling without IPv6 support
  bridge: fix smatch warning / potential null pointer dereference
  via-rhine: fix full-duplex with autoneg disable
  bnx2x: Enlarge the dorq threshold for VFs
  bnx2x: Check for UNDI in uncommon branch
  bnx2x: Fix 1G-baseT link
  bnx2x: Fix link for KR with swapped polarity lane
  sctp: Fix sk_ack_backlog wrap-around problem
  net/core: Add VF link state control policy
  net/fsl: xgmac_mdio is dependent on OF_MDIO
  net/fsl: Make xgmac_mdio read error message useful
  net_sched: drr: warn when qdisc is not work conserving
  ...

1 files changed, 107 insertions, 63 deletions

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 39579c3e0d1..9de23a222d3 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -55,6 +55,7 @@
 #include <net/sctp/sm.h>
 
 /* Forward declarations for internal functions. */
+static void sctp_select_active_and_retran_path(struct sctp_association *asoc);
 static void sctp_assoc_bh_rcv(struct work_struct *work);
 static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc);
 static void sctp_assoc_free_asconf_queue(struct sctp_association *asoc);
@@ -330,7 +331,7 @@ void sctp_association_free(struct sctp_association *asoc)
 	/* Only real associations count against the endpoint, so
 	 * don't bother for if this is a temporary association.
 	 */
-	if (!asoc->temp) {
+	if (!list_empty(&asoc->asocs)) {
 		list_del(&asoc->asocs);
 
 		/* Decrement the backlog value for a TCP-style listening
@@ -774,9 +775,6 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 				  sctp_transport_cmd_t command,
 				  sctp_sn_error_t error)
 {
-	struct sctp_transport *t = NULL;
-	struct sctp_transport *first;
-	struct sctp_transport *second;
 	struct sctp_ulpevent *event;
 	struct sockaddr_storage addr;
 	int spc_state = 0;
@@ -829,13 +827,14 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 		return;
 	}
 
-	/* Generate and send a SCTP_PEER_ADDR_CHANGE notification to the
-	 * user.
+	/* Generate and send a SCTP_PEER_ADDR_CHANGE notification
+	 * to the user.
 	 */
 	if (ulp_notify) {
 		memset(&addr, 0, sizeof(struct sockaddr_storage));
 		memcpy(&addr, &transport->ipaddr,
 		       transport->af_specific->sockaddr_len);
+
 		event = sctp_ulpevent_make_peer_addr_change(asoc, &addr,
 					0, spc_state, error, GFP_ATOMIC);
 		if (event)
@@ -843,60 +842,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 	}
 
 	/* Select new active and retran paths. */
-
-	/* Look for the two most recently used active transports.
-	 *
-	 * This code produces the wrong ordering whenever jiffies
-	 * rolls over, but we still get usable transports, so we don't
-	 * worry about it.
-	 */
-	first = NULL; second = NULL;
-
-	list_for_each_entry(t, &asoc->peer.transport_addr_list,
-			transports) {
-
-		if ((t->state == SCTP_INACTIVE) ||
-		    (t->state == SCTP_UNCONFIRMED) ||
-		    (t->state == SCTP_PF))
-			continue;
-		if (!first || t->last_time_heard > first->last_time_heard) {
-			second = first;
-			first = t;
-		} else if (!second ||
-			   t->last_time_heard > second->last_time_heard)
-			second = t;
-	}
-
-	/* RFC 2960 6.4 Multi-Homed SCTP Endpoints
-	 *
-	 * By default, an endpoint should always transmit to the
-	 * primary path, unless the SCTP user explicitly specifies the
-	 * destination transport address (and possibly source
-	 * transport address) to use.
-	 *
-	 * [If the primary is active but not most recent, bump the most
-	 * recently used transport.]
-	 */
-	if (((asoc->peer.primary_path->state == SCTP_ACTIVE) ||
-	     (asoc->peer.primary_path->state == SCTP_UNKNOWN)) &&
-	    first != asoc->peer.primary_path) {
-		second = first;
-		first = asoc->peer.primary_path;
-	}
-
-	if (!second)
-		second = first;
-	/* If we failed to find a usable transport, just camp on the
-	 * primary, even if it is inactive.
-	 */
-	if (!first) {
-		first = asoc->peer.primary_path;
-		second = asoc->peer.primary_path;
-	}
-
-	/* Set the active and retran transports.  */
-	asoc->peer.active_path = first;
-	asoc->peer.retran_path = second;
+	sctp_select_active_and_retran_path(asoc);
 }
 
 /* Hold a reference to an association. */
@@ -1090,7 +1036,7 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
 		}
 
 		if (chunk->transport)
-			chunk->transport->last_time_heard = jiffies;
+			chunk->transport->last_time_heard = ktime_get();
 
 		/* Run through the state machine. */
 		error = sctp_do_sm(net, SCTP_EVENT_T_CHUNK, subtype,
@@ -1278,13 +1224,41 @@ static u8 sctp_trans_score(const struct sctp_transport *trans)
 	return sctp_trans_state_to_prio_map[trans->state];
 }
 
+static struct sctp_transport *sctp_trans_elect_tie(struct sctp_transport *trans1,
+						   struct sctp_transport *trans2)
+{
+	if (trans1->error_count > trans2->error_count) {
+		return trans2;
+	} else if (trans1->error_count == trans2->error_count &&
+		   ktime_after(trans2->last_time_heard,
+			       trans1->last_time_heard)) {
+		return trans2;
+	} else {
+		return trans1;
+	}
+}
+
 static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr,
 						    struct sctp_transport *best)
 {
+	u8 score_curr, score_best;
+
 	if (best == NULL)
 		return curr;
 
-	return sctp_trans_score(curr) > sctp_trans_score(best) ? curr : best;
+	score_curr = sctp_trans_score(curr);
+	score_best = sctp_trans_score(best);
+
+	/* First, try a score-based selection if both transport states
+	 * differ. If we're in a tie, lets try to make a more clever
+	 * decision here based on error counts and last time heard.
+	 */
+	if (score_curr > score_best)
+		return curr;
+	else if (score_curr == score_best)
+		return sctp_trans_elect_tie(curr, best);
+	else
+		return best;
 }
 
 void sctp_assoc_update_retran_path(struct sctp_association *asoc)
@@ -1325,6 +1299,76 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc)
 		 __func__, asoc, &asoc->peer.retran_path->ipaddr.sa);
 }
 
+static void sctp_select_active_and_retran_path(struct sctp_association *asoc)
+{
+	struct sctp_transport *trans, *trans_pri = NULL, *trans_sec = NULL;
+	struct sctp_transport *trans_pf = NULL;
+
+	/* Look for the two most recently used active transports. */
+	list_for_each_entry(trans, &asoc->peer.transport_addr_list,
+			    transports) {
+		/* Skip uninteresting transports. */
+		if (trans->state == SCTP_INACTIVE ||
+		    trans->state == SCTP_UNCONFIRMED)
+			continue;
+		/* Keep track of the best PF transport from our
+		 * list in case we don't find an active one.
+		 */
+		if (trans->state == SCTP_PF) {
+			trans_pf = sctp_trans_elect_best(trans, trans_pf);
+			continue;
+		}
+		/* For active transports, pick the most recent ones. */
+		if (trans_pri == NULL ||
+		    ktime_after(trans->last_time_heard,
+				trans_pri->last_time_heard)) {
+			trans_sec = trans_pri;
+			trans_pri = trans;
+		} else if (trans_sec == NULL ||
+			   ktime_after(trans->last_time_heard,
+				       trans_sec->last_time_heard)) {
+			trans_sec = trans;
+		}
+	}
+
+	/* RFC 2960 6.4 Multi-Homed SCTP Endpoints
+	 *
+	 * By default, an endpoint should always transmit to the primary
+	 * path, unless the SCTP user explicitly specifies the
+	 * destination transport address (and possibly source transport
+	 * address) to use. [If the primary is active but not most recent,
+	 * bump the most recently used transport.]
+	 */
+	if ((asoc->peer.primary_path->state == SCTP_ACTIVE ||
+	     asoc->peer.primary_path->state == SCTP_UNKNOWN) &&
+	     asoc->peer.primary_path != trans_pri) {
+		trans_sec = trans_pri;
+		trans_pri = asoc->peer.primary_path;
+	}
+
+	/* We did not find anything useful for a possible retransmission
+	 * path; either primary path that we found is the the same as
+	 * the current one, or we didn't generally find an active one.
+	 */
+	if (trans_sec == NULL)
+		trans_sec = trans_pri;
+
+	/* If we failed to find a usable transport, just camp on the
+	 * primary or retran, even if they are inactive, if possible
+	 * pick a PF iff it's the better choice.
+	 */
+	if (trans_pri == NULL) {
+		trans_pri = sctp_trans_elect_best(asoc->peer.primary_path,
+						  asoc->peer.retran_path);
+		trans_pri = sctp_trans_elect_best(trans_pri, trans_pf);
+		trans_sec = asoc->peer.primary_path;
+	}
+
+	/* Set the active and retran transports. */
+	asoc->peer.active_path = trans_pri;
+	asoc->peer.retran_path = trans_sec;
+}
+
 struct sctp_transport *
 sctp_assoc_choose_alter_transport(struct sctp_association *asoc,
 				  struct sctp_transport *last_sent_to)
@@ -1547,7 +1591,7 @@ int sctp_assoc_lookup_laddr(struct sctp_association *asoc,
 /* Set an association id for a given association */
 int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp)
 {
-	bool preload = gfp & __GFP_WAIT;
+	bool preload = !!(gfp & __GFP_WAIT);
 	int ret;
 
 	/* If the id is already assigned, keep it. */