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

Pull networking update from David Miller:

 1) Checkpoint/restarted TCP sockets now can properly propagate the TCP
    timestamp offset.  From Andrey Vagin.

 2) VMWARE VM VSOCK layer, from Andy King.

 3) Much improved support for virtual functions and SR-IOV in bnx2x,
    from Ariel ELior.

 4) All protocols on ipv4 and ipv6 are now network namespace aware, and
    all the compatability checks for initial-namespace-only protocols is
    removed.  Thanks to Tom Parkin for helping deal with the last major
    holdout, L2TP.

 5) IPV6 support in netpoll and network namespace support in pktgen,
    from Cong Wang.

 6) Multiple Registration Protocol (MRP) and Multiple VLAN Registration
    Protocol (MVRP) support, from David Ward.

 7) Compute packet lengths more accurately in the packet scheduler, from
    Eric Dumazet.

 8) Use per-task page fragment allocator in skb_append_datato_frags(),
    also from Eric Dumazet.

 9) Add support for connection tracking labels in netfilter, from
    Florian Westphal.

10) Fix default multicast group joining on ipv6, and add anti-spoofing
    checks to 6to4 and 6rd.  From Hannes Frederic Sowa.

11) Make ipv4/ipv6 fragmentation memory limits more reasonable in modern
    times, rearrange inet frag datastructures for better cacheline
    locality, and move more operations outside of locking.  From Jesper
    Dangaard Brouer.

12) Instead of strict master <--> slave relationships, allow arbitrary
    scenerios with "upper device lists".  From Jiri Pirko.

13) Improve rate limiting accuracy in TBF and act_police, also from Jiri
    Pirko.

14) Add a BPF filter netfilter match target, from Willem de Bruijn.

15) Orphan and delete a bunch of pre-historic networking drivers from
    Paul Gortmaker.

16) Add TSO support for GRE tunnels, from Pravin B SHelar.  Although
    this still needs some minor bug fixing before it's %100 correct in
    all cases.

17) Handle unresolved IPSEC states like ARP, with a resolution packet
    queue.  From Steffen Klassert.

18) Remove TCP Appropriate Byte Count support (ABC), from Stephen
    Hemminger.  This was long overdue.

19) Support SO_REUSEPORT, from Tom Herbert.

20) Allow locking a socket BPF filter, so that it cannot change after a
    process drops capabilities.

21) Add VLAN filtering to bridge, from Vlad Yasevich.

22) Bring ipv6 on-par with ipv4 and do not cache neighbour entries in
    the ipv6 routes, from YOSHIFUJI Hideaki.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1538 commits)
  ipv6: fix race condition regarding dst->expires and dst->from.
  net: fix a wrong assignment in skb_split()
  ip_gre: remove an extra dst_release()
  ppp: set qdisc_tx_busylock to avoid LOCKDEP splat
  atl1c: restore buffer state
  net: fix a build failure when !CONFIG_PROC_FS
  net: ipv4: fix waring -Wunused-variable
  net: proc: fix build failed when procfs is not configured
  Revert "xen: netback: remove redundant xenvif_put"
  net: move procfs code to net/core/net-procfs.c
  qmi_wwan, cdc-ether: add ADU960S
  bonding: set sysfs device_type to 'bond'
  bonding: fix bond_release_all inconsistencies
  b44: use netdev_alloc_skb_ip_align()
  xen: netback: remove redundant xenvif_put
  net: fec: Do a sanity check on the gpio number
  ip_gre: propogate target device GSO capability to the tunnel device
  ip_gre: allow CSUM capable devices to handle packets
  bonding: Fix initialize after use for 3ad machine state spinlock
  bonding: Fix race condition between bond_enslave() and bond_3ad_update_lacp_rate()
  ...

1 files changed, 64 insertions, 41 deletions

diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index a9de23297d47..823463adbd21 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -22,8 +22,23 @@
 #include <net/act_api.h>
 #include <net/netlink.h>
 
-#define L2T(p, L)   qdisc_l2t((p)->tcfp_R_tab, L)
-#define L2T_P(p, L) qdisc_l2t((p)->tcfp_P_tab, L)
+struct tcf_police {
+	struct tcf_common	common;
+	int			tcfp_result;
+	u32			tcfp_ewma_rate;
+	s64			tcfp_burst;
+	u32			tcfp_mtu;
+	s64			tcfp_toks;
+	s64			tcfp_ptoks;
+	s64			tcfp_mtu_ptoks;
+	s64			tcfp_t_c;
+	struct psched_ratecfg	rate;
+	bool			rate_present;
+	struct psched_ratecfg	peak;
+	bool			peak_present;
+};
+#define to_police(pc)	\
+	container_of(pc, struct tcf_police, common)
 
 #define POL_TAB_MASK     15
 static struct tcf_common *tcf_police_ht[POL_TAB_MASK + 1];
@@ -108,10 +123,6 @@ static void tcf_police_destroy(struct tcf_police *p)
 			write_unlock_bh(&police_lock);
 			gen_kill_estimator(&p->tcf_bstats,
 					   &p->tcf_rate_est);
-			if (p->tcfp_R_tab)
-				qdisc_put_rtab(p->tcfp_R_tab);
-			if (p->tcfp_P_tab)
-				qdisc_put_rtab(p->tcfp_P_tab);
 			/*
 			 * gen_estimator est_timer() might access p->tcf_lock
 			 * or bstats, wait a RCU grace period before freeing p
@@ -130,8 +141,9 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = {
 	[TCA_POLICE_RESULT]	= { .type = NLA_U32 },
 };
 
-static int tcf_act_police_locate(struct nlattr *nla, struct nlattr *est,
-				 struct tc_action *a, int ovr, int bind)
+static int tcf_act_police_locate(struct net *net, struct nlattr *nla,
+				 struct nlattr *est, struct tc_action *a,
+				 int ovr, int bind)
 {
 	unsigned int h;
 	int ret = 0, err;
@@ -211,26 +223,36 @@ override:
 	}
 
 	/* No failure allowed after this point */
-	if (R_tab != NULL) {
-		qdisc_put_rtab(police->tcfp_R_tab);
-		police->tcfp_R_tab = R_tab;
+	police->tcfp_mtu = parm->mtu;
+	if (police->tcfp_mtu == 0) {
+		police->tcfp_mtu = ~0;
+		if (R_tab)
+			police->tcfp_mtu = 255 << R_tab->rate.cell_log;
+	}
+	if (R_tab) {
+		police->rate_present = true;
+		psched_ratecfg_precompute(&police->rate, R_tab->rate.rate);
+		qdisc_put_rtab(R_tab);
+	} else {
+		police->rate_present = false;
 	}
-	if (P_tab != NULL) {
-		qdisc_put_rtab(police->tcfp_P_tab);
-		police->tcfp_P_tab = P_tab;
+	if (P_tab) {
+		police->peak_present = true;
+		psched_ratecfg_precompute(&police->peak, P_tab->rate.rate);
+		qdisc_put_rtab(P_tab);
+	} else {
+		police->peak_present = false;
 	}
 
 	if (tb[TCA_POLICE_RESULT])
 		police->tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]);
-	police->tcfp_toks = police->tcfp_burst = parm->burst;
-	police->tcfp_mtu = parm->mtu;
-	if (police->tcfp_mtu == 0) {
-		police->tcfp_mtu = ~0;
-		if (police->tcfp_R_tab)
-			police->tcfp_mtu = 255<<police->tcfp_R_tab->rate.cell_log;
+	police->tcfp_burst = PSCHED_TICKS2NS(parm->burst);
+	police->tcfp_toks = police->tcfp_burst;
+	if (police->peak_present) {
+		police->tcfp_mtu_ptoks = (s64) psched_l2t_ns(&police->peak,
+							     police->tcfp_mtu);
+		police->tcfp_ptoks = police->tcfp_mtu_ptoks;
 	}
-	if (police->tcfp_P_tab)
-		police->tcfp_ptoks = L2T_P(police, police->tcfp_mtu);
 	police->tcf_action = parm->action;
 
 	if (tb[TCA_POLICE_AVRATE])
@@ -240,7 +262,7 @@ override:
 	if (ret != ACT_P_CREATED)
 		return ret;
 
-	police->tcfp_t_c = psched_get_time();
+	police->tcfp_t_c = ktime_to_ns(ktime_get());
 	police->tcf_index = parm->index ? parm->index :
 		tcf_hash_new_index(&police_idx_gen, &police_hash_info);
 	h = tcf_hash(police->tcf_index, POL_TAB_MASK);
@@ -286,9 +308,9 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a,
 			  struct tcf_result *res)
 {
 	struct tcf_police *police = a->priv;
-	psched_time_t now;
-	long toks;
-	long ptoks = 0;
+	s64 now;
+	s64 toks;
+	s64 ptoks = 0;
 
 	spin_lock(&police->tcf_lock);
 
@@ -304,24 +326,25 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a,
 	}
 
 	if (qdisc_pkt_len(skb) <= police->tcfp_mtu) {
-		if (police->tcfp_R_tab == NULL) {
+		if (!police->rate_present) {
 			spin_unlock(&police->tcf_lock);
 			return police->tcfp_result;
 		}
 
-		now = psched_get_time();
-		toks = psched_tdiff_bounded(now, police->tcfp_t_c,
-					    police->tcfp_burst);
-		if (police->tcfp_P_tab) {
+		now = ktime_to_ns(ktime_get());
+		toks = min_t(s64, now - police->tcfp_t_c,
+			     police->tcfp_burst);
+		if (police->peak_present) {
 			ptoks = toks + police->tcfp_ptoks;
-			if (ptoks > (long)L2T_P(police, police->tcfp_mtu))
-				ptoks = (long)L2T_P(police, police->tcfp_mtu);
-			ptoks -= L2T_P(police, qdisc_pkt_len(skb));
+			if (ptoks > police->tcfp_mtu_ptoks)
+				ptoks = police->tcfp_mtu_ptoks;
+			ptoks -= (s64) psched_l2t_ns(&police->peak,
+						     qdisc_pkt_len(skb));
 		}
 		toks += police->tcfp_toks;
-		if (toks > (long)police->tcfp_burst)
+		if (toks > police->tcfp_burst)
 			toks = police->tcfp_burst;
-		toks -= L2T(police, qdisc_pkt_len(skb));
+		toks -= (s64) psched_l2t_ns(&police->rate, qdisc_pkt_len(skb));
 		if ((toks|ptoks) >= 0) {
 			police->tcfp_t_c = now;
 			police->tcfp_toks = toks;
@@ -347,15 +370,15 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 		.index = police->tcf_index,
 		.action = police->tcf_action,
 		.mtu = police->tcfp_mtu,
-		.burst = police->tcfp_burst,
+		.burst = PSCHED_NS2TICKS(police->tcfp_burst),
 		.refcnt = police->tcf_refcnt - ref,
 		.bindcnt = police->tcf_bindcnt - bind,
 	};
 
-	if (police->tcfp_R_tab)
-		opt.rate = police->tcfp_R_tab->rate;
-	if (police->tcfp_P_tab)
-		opt.peakrate = police->tcfp_P_tab->rate;
+	if (police->rate_present)
+		opt.rate.rate = psched_ratecfg_getrate(&police->rate);
+	if (police->peak_present)
+		opt.peakrate.rate = psched_ratecfg_getrate(&police->peak);
 	if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt))
 		goto nla_put_failure;
 	if (police->tcfp_result &&