diff --git a/include/linux/if_addr.h b/include/linux/if_addr.h
index 58b39f4..9ce823d 100644
--- a/include/linux/if_addr.h
+++ b/include/linux/if_addr.h
@@ -18,6 +18,9 @@
  * It makes no difference for normally configured broadcast interfaces,
  * but for point-to-point IFA_ADDRESS is DESTINATION address,
  * local address is supplied in IFA_LOCAL attribute.
+ *
+ * IFA_FLAGS is a u32 attribute that extends the u8 field ifa_flags.
+ * If present, the value from struct ifaddrmsg will be ignored.
  */
 enum {
 	IFA_UNSPEC,
@@ -28,6 +31,7 @@
 	IFA_ANYCAST,
 	IFA_CACHEINFO,
 	IFA_MULTICAST,
+	IFA_FLAGS,
 	__IFA_MAX,
 };
 
@@ -44,6 +48,7 @@
 #define IFA_F_DEPRECATED	0x20
 #define IFA_F_TENTATIVE		0x40
 #define IFA_F_PERMANENT		0x80
+#define IFA_F_MANAGETEMPADDR	0x100
 
 struct ifa_cacheinfo {
 	__u32	ifa_prefered;
diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index 4b727a5..7d8f543 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -329,11 +329,43 @@
 	IFLA_BOND_UNSPEC,
 	IFLA_BOND_MODE,
 	IFLA_BOND_ACTIVE_SLAVE,
+	IFLA_BOND_MIIMON,
+	IFLA_BOND_UPDELAY,
+	IFLA_BOND_DOWNDELAY,
+	IFLA_BOND_USE_CARRIER,
+	IFLA_BOND_ARP_INTERVAL,
+	IFLA_BOND_ARP_IP_TARGET,
+	IFLA_BOND_ARP_VALIDATE,
+	IFLA_BOND_ARP_ALL_TARGETS,
+	IFLA_BOND_PRIMARY,
+	IFLA_BOND_PRIMARY_RESELECT,
+	IFLA_BOND_FAIL_OVER_MAC,
+	IFLA_BOND_XMIT_HASH_POLICY,
+	IFLA_BOND_RESEND_IGMP,
+	IFLA_BOND_NUM_PEER_NOTIF,
+	IFLA_BOND_ALL_SLAVES_ACTIVE,
+	IFLA_BOND_MIN_LINKS,
+	IFLA_BOND_LP_INTERVAL,
+	IFLA_BOND_PACKETS_PER_SLAVE,
+	IFLA_BOND_AD_LACP_RATE,
+	IFLA_BOND_AD_SELECT,
+	IFLA_BOND_AD_INFO,
 	__IFLA_BOND_MAX,
 };
 
 #define IFLA_BOND_MAX	(__IFLA_BOND_MAX - 1)
 
+enum {
+	IFLA_BOND_AD_INFO_AGGREGATOR,
+	IFLA_BOND_AD_INFO_NUM_PORTS,
+	IFLA_BOND_AD_INFO_ACTOR_KEY,
+	IFLA_BOND_AD_INFO_PARTNER_KEY,
+	IFLA_BOND_AD_INFO_PARTNER_MAC,
+	__IFLA_BOND_AD_INFO_MAX,
+};
+
+#define IFLA_BOND_AD_INFO_MAX	(__IFLA_BOND_AD_INFO_MAX - 1)
+
 /* SR-IOV virtual function management section */
 
 enum {
diff --git a/include/linux/netconf.h b/include/linux/netconf.h
index 52c4424..6ceb170 100644
--- a/include/linux/netconf.h
+++ b/include/linux/netconf.h
@@ -14,6 +14,7 @@
 	NETCONFA_FORWARDING,
 	NETCONFA_RP_FILTER,
 	NETCONFA_MC_FORWARDING,
+	NETCONFA_PROXY_NEIGH,
 	__NETCONFA_MAX
 };
 #define NETCONFA_MAX	(__NETCONFA_MAX - 1)
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index f05c3d9..be0bc18 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -51,6 +51,7 @@
 
 enum {
 	NFPROTO_UNSPEC =  0,
+	NFPROTO_INET   =  1,
 	NFPROTO_IPV4   =  2,
 	NFPROTO_ARP    =  3,
 	NFPROTO_BRIDGE =  7,
diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h
index a806687..d62316b 100644
--- a/include/linux/pkt_sched.h
+++ b/include/linux/pkt_sched.h
@@ -173,6 +173,8 @@
 	TCA_TBF_PTAB,
 	TCA_TBF_RATE64,
 	TCA_TBF_PRATE64,
+	TCA_TBF_BURST,
+	TCA_TBF_PBURST,
 	__TCA_TBF_MAX,
 };
 
@@ -523,6 +525,7 @@
 	TCA_NETEM_LOSS,
 	TCA_NETEM_RATE,
 	TCA_NETEM_ECN,
+	TCA_NETEM_RATE64,
 	__TCA_NETEM_MAX,
 };
 
@@ -790,4 +793,54 @@
 	__u32	throttled_flows;
 	__u32	pad;
 };
+
+/* Heavy-Hitter Filter */
+
+enum {
+	TCA_HHF_UNSPEC,
+	TCA_HHF_BACKLOG_LIMIT,
+	TCA_HHF_QUANTUM,
+	TCA_HHF_HH_FLOWS_LIMIT,
+	TCA_HHF_RESET_TIMEOUT,
+	TCA_HHF_ADMIT_BYTES,
+	TCA_HHF_EVICT_TIMEOUT,
+	TCA_HHF_NON_HH_WEIGHT,
+	__TCA_HHF_MAX
+};
+
+#define TCA_HHF_MAX	(__TCA_HHF_MAX - 1)
+
+struct tc_hhf_xstats {
+	__u32	drop_overlimit; /* number of times max qdisc packet limit
+				 * was hit
+				 */
+	__u32	hh_overlimit;   /* number of times max heavy-hitters was hit */
+	__u32	hh_tot_count;   /* number of captured heavy-hitters so far */
+	__u32	hh_cur_count;   /* number of current heavy-hitters */
+};
+
+/* PIE */
+enum {
+	TCA_PIE_UNSPEC,
+	TCA_PIE_TARGET,
+	TCA_PIE_LIMIT,
+	TCA_PIE_TUPDATE,
+	TCA_PIE_ALPHA,
+	TCA_PIE_BETA,
+	TCA_PIE_ECN,
+	TCA_PIE_BYTEMODE,
+	__TCA_PIE_MAX
+};
+#define TCA_PIE_MAX   (__TCA_PIE_MAX - 1)
+
+struct tc_pie_xstats {
+	__u32 prob;             /* current probability */
+	__u32 delay;            /* current delay in ms */
+	__u32 avg_dq_rate;      /* current average dq_rate in bits/pie_time */
+	__u32 packets_in;       /* total number of packets enqueued */
+	__u32 dropped;          /* packets dropped due to pie_action */
+	__u32 overlimit;        /* dropped due to lack of space in queue */
+	__u32 maxq;             /* maximum queue size */
+	__u32 ecn_mark;         /* packets marked with ecn*/
+};
 #endif
diff --git a/ip/ipaddress.c b/ip/ipaddress.c
index d02eaaf..1e3f22c 100644
--- a/ip/ipaddress.c
+++ b/ip/ipaddress.c
@@ -541,6 +541,13 @@
 	return 0;
 }
 
+static unsigned int get_ifa_flags(struct ifaddrmsg *ifa,
+				  struct rtattr *ifa_flags_attr)
+{
+	return ifa_flags_attr ? rta_getattr_u32(ifa_flags_attr) :
+				ifa->ifa_flags;
+}
+
 int print_addrinfo(const struct sockaddr_nl *who, struct nlmsghdr *n,
 		   void *arg)
 {
@@ -567,6 +574,8 @@
 
 	parse_rtattr(rta_tb, IFA_MAX, IFA_RTA(ifa), n->nlmsg_len - NLMSG_LENGTH(sizeof(*ifa)));
 
+	ifa_flags = get_ifa_flags(ifa, rta_tb[IFA_FLAGS]);
+
 	if (!rta_tb[IFA_LOCAL])
 		rta_tb[IFA_LOCAL] = rta_tb[IFA_ADDRESS];
 	if (!rta_tb[IFA_ADDRESS])
@@ -576,7 +585,7 @@
 		return 0;
 	if ((filter.scope^ifa->ifa_scope)&filter.scopemask)
 		return 0;
-	if ((filter.flags^ifa->ifa_flags)&filter.flagmask)
+	if ((filter.flags ^ ifa_flags) & filter.flagmask)
 		return 0;
 	if (filter.label) {
 		SPRINT_BUF(b1);
@@ -670,36 +679,35 @@
 				    abuf, sizeof(abuf)));
 	}
 	fprintf(fp, "scope %s ", rtnl_rtscope_n2a(ifa->ifa_scope, b1, sizeof(b1)));
-	ifa_flags = ifa->ifa_flags;
-	if (ifa->ifa_flags&IFA_F_SECONDARY) {
+	if (ifa_flags & IFA_F_SECONDARY) {
 		ifa_flags &= ~IFA_F_SECONDARY;
 		if (ifa->ifa_family == AF_INET6)
 			fprintf(fp, "temporary ");
 		else
 			fprintf(fp, "secondary ");
 	}
-	if (ifa->ifa_flags&IFA_F_TENTATIVE) {
+	if (ifa_flags & IFA_F_TENTATIVE) {
 		ifa_flags &= ~IFA_F_TENTATIVE;
 		fprintf(fp, "tentative ");
 	}
-	if (ifa->ifa_flags&IFA_F_DEPRECATED) {
+	if (ifa_flags & IFA_F_DEPRECATED) {
 		ifa_flags &= ~IFA_F_DEPRECATED;
 		deprecated = 1;
 		fprintf(fp, "deprecated ");
 	}
-	if (ifa->ifa_flags&IFA_F_HOMEADDRESS) {
+	if (ifa_flags & IFA_F_HOMEADDRESS) {
 		ifa_flags &= ~IFA_F_HOMEADDRESS;
 		fprintf(fp, "home ");
 	}
-	if (ifa->ifa_flags&IFA_F_NODAD) {
+	if (ifa_flags & IFA_F_NODAD) {
 		ifa_flags &= ~IFA_F_NODAD;
 		fprintf(fp, "nodad ");
 	}
-	if (!(ifa->ifa_flags&IFA_F_PERMANENT)) {
+	if (!(ifa_flags & IFA_F_PERMANENT)) {
 		fprintf(fp, "dynamic ");
 	} else
 		ifa_flags &= ~IFA_F_PERMANENT;
-	if (ifa->ifa_flags&IFA_F_DADFAILED) {
+	if (ifa_flags & IFA_F_DADFAILED) {
 		ifa_flags &= ~IFA_F_DADFAILED;
 		fprintf(fp, "dadfailed ");
 	}
@@ -926,6 +934,8 @@
 		for (a = ainfo->head; a; a = a->next) {
 			struct nlmsghdr *n = &a->h;
 			struct ifaddrmsg *ifa = NLMSG_DATA(n);
+			struct rtattr *tb[IFA_MAX + 1];
+			unsigned int ifa_flags;
 
 			if (ifa->ifa_index != ifi->ifi_index)
 				continue;
@@ -934,11 +944,13 @@
 				continue;
 			if ((filter.scope^ifa->ifa_scope)&filter.scopemask)
 				continue;
-			if ((filter.flags^ifa->ifa_flags)&filter.flagmask)
+
+			parse_rtattr(tb, IFA_MAX, IFA_RTA(ifa), IFA_PAYLOAD(n));
+			ifa_flags = get_ifa_flags(ifa, tb[IFA_FLAGS]);
+
+			if ((filter.flags ^ ifa_flags) & filter.flagmask)
 				continue;
 			if (filter.pfx.family || filter.label) {
-				struct rtattr *tb[IFA_MAX+1];
-				parse_rtattr(tb, IFA_MAX, IFA_RTA(ifa), IFA_PAYLOAD(n));
 				if (!tb[IFA_LOCAL])
 					tb[IFA_LOCAL] = tb[IFA_ADDRESS];
 
@@ -1252,6 +1264,7 @@
 	__u32 preferred_lft = INFINITY_LIFE_TIME;
 	__u32 valid_lft = INFINITY_LIFE_TIME;
 	struct ifa_cacheinfo cinfo;
+	unsigned int ifa_flags = 0;
 
 	memset(&req, 0, sizeof(req));
 
@@ -1329,9 +1342,9 @@
 			if (set_lifetime(&preferred_lft, *argv))
 				invarg("preferred_lft value", *argv);
 		} else if (strcmp(*argv, "home") == 0) {
-			req.ifa.ifa_flags |= IFA_F_HOMEADDRESS;
+			ifa_flags |= IFA_F_HOMEADDRESS;
 		} else if (strcmp(*argv, "nodad") == 0) {
-			req.ifa.ifa_flags |= IFA_F_NODAD;
+			ifa_flags |= IFA_F_NODAD;
 		} else {
 			if (strcmp(*argv, "local") == 0) {
 				NEXT_ARG();
@@ -1349,6 +1362,9 @@
 		}
 		argc--; argv++;
 	}
+	req.ifa.ifa_flags = ifa_flags;
+	addattr32(&req.n, sizeof(req), IFA_FLAGS, ifa_flags);
+
 	if (d == NULL) {
 		fprintf(stderr, "Not enough information: \"dev\" argument is required.\n");
 		return -1;
diff --git a/ip/ipnetconf.c b/ip/ipnetconf.c
index 37aaf45..0e44cc8 100644
--- a/ip/ipnetconf.c
+++ b/ip/ipnetconf.c
@@ -114,6 +114,10 @@
 		fprintf(fp, "mc_forwarding %d ",
 			*(int *)RTA_DATA(tb[NETCONFA_MC_FORWARDING]));
 
+	if (tb[NETCONFA_PROXY_NEIGH])
+		fprintf(fp, "proxy_neigh %s ",
+			*(int *)RTA_DATA(tb[NETCONFA_PROXY_NEIGH])?"on":"off");
+
 	fprintf(fp, "\n");
 	fflush(fp);
 	return 0;
diff --git a/tc/Makefile b/tc/Makefile
index 84215c0..b633771 100644
--- a/tc/Makefile
+++ b/tc/Makefile
@@ -53,6 +53,7 @@
 TCMODULES += q_codel.o
 TCMODULES += q_fq_codel.o
 TCMODULES += q_fq.o
+TCMODULES += q_pie.o
 
 ifeq ($(TC_CONFIG_IPSET), y)
   ifeq ($(TC_CONFIG_XT), y)
diff --git a/tc/q_htb.c b/tc/q_htb.c
index e108857..1d8c56f 100644
--- a/tc/q_htb.c
+++ b/tc/q_htb.c
@@ -113,6 +113,7 @@
 	unsigned int direct_qlen = ~0U;
 	unsigned int linklayer  = LINKLAYER_ETHERNET; /* Assume ethernet */
 	struct rtattr *tail;
+	__u64 ceil64 = 0, rate64 = 0;
 
 	memset(&opt, 0, sizeof(opt)); mtu = 1600; /* eth packet len */
 
@@ -173,22 +174,22 @@
 			ok++;
 		} else if (strcmp(*argv, "ceil") == 0) {
 			NEXT_ARG();
-			if (opt.ceil.rate) {
+			if (ceil64) {
 				fprintf(stderr, "Double \"ceil\" spec\n");
 				return -1;
 			}
-			if (get_rate(&opt.ceil.rate, *argv)) {
+			if (get_rate64(&ceil64, *argv)) {
 				explain1("ceil");
 				return -1;
 			}
 			ok++;
 		} else if (strcmp(*argv, "rate") == 0) {
 			NEXT_ARG();
-			if (opt.rate.rate) {
+			if (rate64) {
 				fprintf(stderr, "Double \"rate\" spec\n");
 				return -1;
 			}
-			if (get_rate(&opt.rate.rate, *argv)) {
+			if (get_rate64(&rate64, *argv)) {
 				explain1("rate");
 				return -1;
 			}
@@ -207,17 +208,23 @@
 	/*	if (!ok)
 		return 0;*/
 
-	if (opt.rate.rate == 0) {
+	if (!rate64) {
 		fprintf(stderr, "\"rate\" is required.\n");
 		return -1;
 	}
 	/* if ceil params are missing, use the same as rate */
-	if (!opt.ceil.rate) opt.ceil = opt.rate;
+	if (!ceil64)
+		ceil64 = rate64;
+
+	opt.rate.rate = (rate64 >= (1ULL << 32)) ? ~0U : rate64;
+	opt.ceil.rate = (ceil64 >= (1ULL << 32)) ? ~0U : ceil64;
 
 	/* compute minimal allowed burst from rate; mtu is added here to make
 	   sute that buffer is larger than mtu and to have some safeguard space */
-	if (!buffer) buffer = opt.rate.rate / get_hz() + mtu;
-	if (!cbuffer) cbuffer = opt.ceil.rate / get_hz() + mtu;
+	if (!buffer)
+		buffer = rate64 / get_hz() + mtu;
+	if (!cbuffer)
+		cbuffer = ceil64 / get_hz() + mtu;
 
 	opt.ceil.overhead = overhead;
 	opt.rate.overhead = overhead;
@@ -229,19 +236,26 @@
 		fprintf(stderr, "htb: failed to calculate rate table.\n");
 		return -1;
 	}
-	opt.buffer = tc_calc_xmittime(opt.rate.rate, buffer);
+	opt.buffer = tc_calc_xmittime(rate64, buffer);
 
 	if (tc_calc_rtable(&opt.ceil, ctab, ccell_log, mtu, linklayer) < 0) {
 		fprintf(stderr, "htb: failed to calculate ceil rate table.\n");
 		return -1;
 	}
-	opt.cbuffer = tc_calc_xmittime(opt.ceil.rate, cbuffer);
+	opt.cbuffer = tc_calc_xmittime(ceil64, cbuffer);
 
 	tail = NLMSG_TAIL(n);
 	if (direct_qlen != ~0U)
 		addattr_l(n, 1024, TCA_HTB_DIRECT_QLEN,
 			  &direct_qlen, sizeof(direct_qlen));
 	addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+
+	if (rate64 >= (1ULL << 32))
+		addattr_l(n, 1124, TCA_HTB_RATE64, &rate64, sizeof(rate64));
+
+	if (ceil64 >= (1ULL << 32))
+		addattr_l(n, 1224, TCA_HTB_CEIL64, &ceil64, sizeof(ceil64));
+
 	addattr_l(n, 2024, TCA_HTB_PARMS, &opt, sizeof(opt));
 	addattr_l(n, 3024, TCA_HTB_RTAB, rtab, 1024);
 	addattr_l(n, 4024, TCA_HTB_CTAB, ctab, 1024);
@@ -256,6 +270,7 @@
 	struct tc_htb_glob *gopt;
 	double buffer,cbuffer;
 	unsigned int linklayer;
+	__u64 rate64, ceil64;
 	SPRINT_BUF(b1);
 	SPRINT_BUF(b2);
 	SPRINT_BUF(b3);
@@ -275,12 +290,25 @@
 			if (show_details)
 				fprintf(f, "quantum %d ", (int)hopt->quantum);
 		}
-		fprintf(f, "rate %s ", sprint_rate(hopt->rate.rate, b1));
+
+		rate64 = hopt->rate.rate;
+		if (tb[TCA_HTB_RATE64] &&
+		    RTA_PAYLOAD(tb[TCA_HTB_RATE64]) >= sizeof(rate64)) {
+			rate64 = rta_getattr_u64(tb[TCA_HTB_RATE64]);
+		}
+
+		ceil64 = hopt->ceil.rate;
+		if (tb[TCA_HTB_CEIL64] &&
+		    RTA_PAYLOAD(tb[TCA_HTB_CEIL64]) >= sizeof(ceil64))
+			ceil64 = rta_getattr_u64(tb[TCA_HTB_CEIL64]);
+
+		fprintf(f, "rate %s ", sprint_rate(rate64, b1));
 		if (hopt->rate.overhead)
 			fprintf(f, "overhead %u ", hopt->rate.overhead);
-		buffer = tc_calc_xmitsize(hopt->rate.rate, hopt->buffer);
-		fprintf(f, "ceil %s ", sprint_rate(hopt->ceil.rate, b1));
-		cbuffer = tc_calc_xmitsize(hopt->ceil.rate, hopt->cbuffer);
+		buffer = tc_calc_xmitsize(rate64, hopt->buffer);
+
+		fprintf(f, "ceil %s ", sprint_rate(ceil64, b1));
+		cbuffer = tc_calc_xmitsize(ceil64, hopt->cbuffer);
 		linklayer = (hopt->rate.linklayer & TC_LINKLAYER_MASK);
 		if (linklayer > TC_LINKLAYER_ETHERNET || show_details)
 			fprintf(f, "linklayer %s ", sprint_linklayer(linklayer, b4));
diff --git a/tc/q_pie.c b/tc/q_pie.c
new file mode 100644
index 0000000..193b05d
--- /dev/null
+++ b/tc/q_pie.c
@@ -0,0 +1,218 @@
+/* Copyright (C) 2013 Cisco Systems, Inc, 2013.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Author: Vijay Subramanian <vijaynsu@cisco.com>
+ * Author: Mythili Prabhu <mysuryan@cisco.com>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <math.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+	fprintf(stderr, "Usage: ... pie [ limit PACKETS ][ target TIME us]\n");
+	fprintf(stderr, "              [ tupdate TIME us][ alpha ALPHA ]");
+	fprintf(stderr, "[beta BETA ][bytemode | nobytemode][ecn | noecn ]\n");
+}
+
+#define ALPHA_MAX 32
+#define ALPHA_MIN 0
+#define BETA_MAX 32
+#define BETA_MIN 0
+
+static int pie_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+			 struct nlmsghdr *n)
+{
+	unsigned int limit   = 0;
+	unsigned int target  = 0;
+	unsigned int tupdate = 0;
+	unsigned int alpha   = 0;
+	unsigned int beta    = 0;
+	int ecn = -1;
+	int bytemode = -1;
+	struct rtattr *tail;
+
+	while (argc > 0) {
+		if (strcmp(*argv, "limit") == 0) {
+			NEXT_ARG();
+			if (get_unsigned(&limit, *argv, 0)) {
+				fprintf(stderr, "Illegal \"limit\"\n");
+				return -1;
+			}
+		} else if (strcmp(*argv, "target") == 0) {
+			NEXT_ARG();
+			if (get_time(&target, *argv)) {
+				fprintf(stderr, "Illegal \"target\"\n");
+				return -1;
+			}
+		} else if (strcmp(*argv, "tupdate") == 0) {
+			NEXT_ARG();
+			if (get_time(&tupdate, *argv)) {
+				fprintf(stderr, "Illegal \"tupdate\"\n");
+				return -1;
+			}
+		} else if (strcmp(*argv, "alpha") == 0) {
+			NEXT_ARG();
+			if (get_unsigned(&alpha, *argv, 0) ||
+			    (alpha > ALPHA_MAX) || (alpha < ALPHA_MIN)) {
+				fprintf(stderr, "Illegal \"alpha\"\n");
+				return -1;
+			}
+		} else if (strcmp(*argv, "beta") == 0) {
+			NEXT_ARG();
+			if (get_unsigned(&beta, *argv, 0) ||
+			    (beta > BETA_MAX) || (beta < BETA_MIN)) {
+				fprintf(stderr, "Illegal \"beta\"\n");
+				return -1;
+			}
+		} else if (strcmp(*argv, "ecn") == 0) {
+			ecn = 1;
+		} else if (strcmp(*argv, "noecn") == 0) {
+			ecn = 0;
+		} else if (strcmp(*argv, "bytemode") == 0) {
+			bytemode = 1;
+		} else if (strcmp(*argv, "nobytemode") == 0) {
+			bytemode = 0;
+		} else if (strcmp(*argv, "help") == 0) {
+			explain();
+			return -1;
+		} else {
+			fprintf(stderr, "What is \"%s\"?\n", *argv);
+			explain();
+			return -1;
+		}
+		argc--;
+		argv++;
+	}
+
+	tail = NLMSG_TAIL(n);
+	addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+	if (limit)
+		addattr_l(n, 1024, TCA_PIE_LIMIT, &limit, sizeof(limit));
+	if (tupdate)
+		addattr_l(n, 1024, TCA_PIE_TUPDATE, &tupdate, sizeof(tupdate));
+	if (target)
+		addattr_l(n, 1024, TCA_PIE_TARGET, &target, sizeof(target));
+	if (alpha)
+		addattr_l(n, 1024, TCA_PIE_ALPHA, &alpha, sizeof(alpha));
+	if (beta)
+		addattr_l(n, 1024, TCA_PIE_BETA, &beta, sizeof(beta));
+	if (ecn != -1)
+		addattr_l(n, 1024, TCA_PIE_ECN, &ecn, sizeof(ecn));
+	if (bytemode != -1)
+		addattr_l(n, 1024, TCA_PIE_BYTEMODE, &bytemode,
+			  sizeof(bytemode));
+
+	tail->rta_len = (void *)NLMSG_TAIL(n) - (void *)tail;
+	return 0;
+}
+
+static int pie_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+	struct rtattr *tb[TCA_PIE_MAX + 1];
+	unsigned int limit;
+	unsigned int tupdate;
+	unsigned int target;
+	unsigned int alpha;
+	unsigned int beta;
+	unsigned ecn;
+	unsigned bytemode;
+	SPRINT_BUF(b1);
+
+	if (opt == NULL)
+		return 0;
+
+	parse_rtattr_nested(tb, TCA_PIE_MAX, opt);
+
+	if (tb[TCA_PIE_LIMIT] &&
+	    RTA_PAYLOAD(tb[TCA_PIE_LIMIT]) >= sizeof(__u32)) {
+		limit = rta_getattr_u32(tb[TCA_PIE_LIMIT]);
+		fprintf(f, "limit %up ", limit);
+	}
+	if (tb[TCA_PIE_TARGET] &&
+	    RTA_PAYLOAD(tb[TCA_PIE_TARGET]) >= sizeof(__u32)) {
+		target = rta_getattr_u32(tb[TCA_PIE_TARGET]);
+		fprintf(f, "target %s ", sprint_time(target, b1));
+	}
+	if (tb[TCA_PIE_TUPDATE] &&
+	    RTA_PAYLOAD(tb[TCA_PIE_TUPDATE]) >= sizeof(__u32)) {
+		tupdate = rta_getattr_u32(tb[TCA_PIE_TUPDATE]);
+		fprintf(f, "tupdate %s ", sprint_time(tupdate, b1));
+	}
+	if (tb[TCA_PIE_ALPHA] &&
+	    RTA_PAYLOAD(tb[TCA_PIE_ALPHA]) >= sizeof(__u32)) {
+		alpha = rta_getattr_u32(tb[TCA_PIE_ALPHA]);
+		fprintf(f, "alpha %u ", alpha);
+	}
+	if (tb[TCA_PIE_BETA] &&
+	    RTA_PAYLOAD(tb[TCA_PIE_BETA]) >= sizeof(__u32)) {
+		beta = rta_getattr_u32(tb[TCA_PIE_BETA]);
+		fprintf(f, "beta %u ", beta);
+	}
+
+	if (tb[TCA_PIE_ECN] && RTA_PAYLOAD(tb[TCA_PIE_ECN]) >= sizeof(__u32)) {
+		ecn = rta_getattr_u32(tb[TCA_PIE_ECN]);
+		if (ecn)
+			fprintf(f, "ecn ");
+	}
+
+	if (tb[TCA_PIE_BYTEMODE] &&
+	    RTA_PAYLOAD(tb[TCA_PIE_BYTEMODE]) >= sizeof(__u32)) {
+		bytemode = rta_getattr_u32(tb[TCA_PIE_BYTEMODE]);
+		if (bytemode)
+			fprintf(f, "bytemode ");
+	}
+
+	return 0;
+}
+
+static int pie_print_xstats(struct qdisc_util *qu, FILE *f,
+			    struct rtattr *xstats)
+{
+	struct tc_pie_xstats *st;
+
+	if (xstats == NULL)
+		return 0;
+
+	if (RTA_PAYLOAD(xstats) < sizeof(*st))
+		return -1;
+
+	st = RTA_DATA(xstats);
+	/*prob is returned as a fracion of maximum integer value */
+	fprintf(f, "prob %f delay %uus avg_dq_rate %u\n",
+		(double)st->prob / (double)0xffffffff, st->delay,
+		st->avg_dq_rate);
+	fprintf(f, "pkts_in %u overlimit %u dropped %u maxq %u ecn_mark %u\n",
+		st->packets_in, st->overlimit, st->dropped, st->maxq,
+		st->ecn_mark);
+	return 0;
+
+}
+
+struct qdisc_util pie_qdisc_util = {
+	.id = "pie",
+	.parse_qopt	= pie_parse_opt,
+	.print_qopt	= pie_print_opt,
+	.print_xstats	= pie_print_xstats,
+};
diff --git a/tc/q_tbf.c b/tc/q_tbf.c
index 34784a4..2fbfd3b 100644
--- a/tc/q_tbf.c
+++ b/tc/q_tbf.c
@@ -47,6 +47,7 @@
 	unsigned short overhead=0;
 	unsigned int linklayer = LINKLAYER_ETHERNET; /* Assume ethernet */
 	struct rtattr *tail;
+	__u64 rate64 = 0, prate64 = 0;
 
 	memset(&opt, 0, sizeof(opt));
 
@@ -121,22 +122,22 @@
 			ok++;
 		} else if (strcmp(*argv, "rate") == 0) {
 			NEXT_ARG();
-			if (opt.rate.rate) {
+			if (rate64) {
 				fprintf(stderr, "tbf: duplicate \"rate\" specification\n");
 				return -1;
 			}
-			if (get_rate(&opt.rate.rate, *argv)) {
+			if (get_rate64(&rate64, *argv)) {
 				explain1("rate", *argv);
 				return -1;
 			}
 			ok++;
 		} else if (matches(*argv, "peakrate") == 0) {
 			NEXT_ARG();
-			if (opt.peakrate.rate) {
+			if (prate64) {
 				fprintf(stderr, "tbf: duplicate \"peakrate\" specification\n");
 				return -1;
 			}
-			if (get_rate(&opt.peakrate.rate, *argv)) {
+			if (get_rate64(&prate64, *argv)) {
 				explain1("peakrate", *argv);
 				return -1;
 			}
@@ -172,7 +173,7 @@
          * one go rather than reveal one more problem when a
          * previous one has been fixed.
          */
-	if (opt.rate.rate == 0) {
+	if (rate64 == 0) {
 		fprintf(stderr, "tbf: the \"rate\" parameter is mandatory.\n");
 		verdict = -1;
 	}
@@ -180,7 +181,7 @@
 		fprintf(stderr, "tbf: the \"burst\" parameter is mandatory.\n");
 		verdict = -1;
 	}
-	if (opt.peakrate.rate) {
+	if (prate64) {
 		if (!mtu) {
 			fprintf(stderr, "tbf: when \"peakrate\" is specified, \"mtu\" must also be specified.\n");
 			verdict = -1;
@@ -197,10 +198,13 @@
                 return verdict;
         }
 
+	opt.rate.rate = (rate64 >= (1ULL << 32)) ? ~0U : rate64;
+	opt.peakrate.rate = (prate64 >= (1ULL << 32)) ? ~0U : prate64;
+
 	if (opt.limit == 0) {
-		double lim = opt.rate.rate*(double)latency/TIME_UNITS_PER_SEC + buffer;
-		if (opt.peakrate.rate) {
-			double lim2 = opt.peakrate.rate*(double)latency/TIME_UNITS_PER_SEC + mtu;
+		double lim = rate64*(double)latency/TIME_UNITS_PER_SEC + buffer;
+		if (prate64) {
+			double lim2 = prate64*(double)latency/TIME_UNITS_PER_SEC + mtu;
 			if (lim2 < lim)
 				lim = lim2;
 		}
@@ -228,20 +232,26 @@
 	tail = NLMSG_TAIL(n);
 	addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
 	addattr_l(n, 2024, TCA_TBF_PARMS, &opt, sizeof(opt));
+	if (rate64 >= (1ULL << 32))
+		addattr_l(n, 2124, TCA_TBF_RATE64, &rate64, sizeof(rate64));
 	addattr_l(n, 3024, TCA_TBF_RTAB, rtab, 1024);
-	if (opt.peakrate.rate)
+	if (opt.peakrate.rate) {
+		if (prate64 >= (1ULL << 32))
+			addattr_l(n, 3124, TCA_TBF_PRATE64, &prate64, sizeof(prate64));
 		addattr_l(n, 4096, TCA_TBF_PTAB, ptab, 1024);
+	}
 	tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
 	return 0;
 }
 
 static int tbf_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
 {
-	struct rtattr *tb[TCA_TBF_PTAB+1];
+	struct rtattr *tb[TCA_TBF_MAX+1];
 	struct tc_tbf_qopt *qopt;
 	unsigned int linklayer;
 	double buffer, mtu;
 	double latency;
+	__u64 rate64 = 0, prate64 = 0;
 	SPRINT_BUF(b1);
 	SPRINT_BUF(b2);
 	SPRINT_BUF(b3);
@@ -249,7 +259,7 @@
 	if (opt == NULL)
 		return 0;
 
-	parse_rtattr_nested(tb, TCA_TBF_PTAB, opt);
+	parse_rtattr_nested(tb, TCA_TBF_MAX, opt);
 
 	if (tb[TCA_TBF_PARMS] == NULL)
 		return -1;
@@ -257,8 +267,12 @@
 	qopt = RTA_DATA(tb[TCA_TBF_PARMS]);
 	if (RTA_PAYLOAD(tb[TCA_TBF_PARMS])  < sizeof(*qopt))
 		return -1;
-	fprintf(f, "rate %s ", sprint_rate(qopt->rate.rate, b1));
-	buffer = tc_calc_xmitsize(qopt->rate.rate, qopt->buffer);
+	rate64 = qopt->rate.rate;
+	if (tb[TCA_TBF_RATE64] &&
+	    RTA_PAYLOAD(tb[TCA_TBF_RATE64]) >= sizeof(rate64))
+		rate64 = rta_getattr_u64(tb[TCA_TBF_RATE64]);
+	fprintf(f, "rate %s ", sprint_rate(rate64, b1));
+	buffer = tc_calc_xmitsize(rate64, qopt->buffer);
 	if (show_details) {
 		fprintf(f, "burst %s/%u mpu %s ", sprint_size(buffer, b1),
 			1<<qopt->rate.cell_log, sprint_size(qopt->rate.mpu, b2));
@@ -267,10 +281,14 @@
 	}
 	if (show_raw)
 		fprintf(f, "[%08x] ", qopt->buffer);
-	if (qopt->peakrate.rate) {
-		fprintf(f, "peakrate %s ", sprint_rate(qopt->peakrate.rate, b1));
+	prate64 = qopt->peakrate.rate;
+	if (tb[TCA_TBF_PRATE64] &&
+	    RTA_PAYLOAD(tb[TCA_TBF_PRATE64]) >= sizeof(prate64))
+		prate64 = rta_getattr_u64(tb[TCA_TBF_PRATE64]);
+	if (prate64) {
+		fprintf(f, "peakrate %s ", sprint_rate(prate64, b1));
 		if (qopt->mtu || qopt->peakrate.mpu) {
-			mtu = tc_calc_xmitsize(qopt->peakrate.rate, qopt->mtu);
+			mtu = tc_calc_xmitsize(prate64, qopt->mtu);
 			if (show_details) {
 				fprintf(f, "mtu %s/%u mpu %s ", sprint_size(mtu, b1),
 					1<<qopt->peakrate.cell_log, sprint_size(qopt->peakrate.mpu, b2));
@@ -285,9 +303,9 @@
 	if (show_raw)
 		fprintf(f, "limit %s ", sprint_size(qopt->limit, b1));
 
-	latency = TIME_UNITS_PER_SEC*(qopt->limit/(double)qopt->rate.rate) - tc_core_tick2time(qopt->buffer);
-	if (qopt->peakrate.rate) {
-		double lat2 = TIME_UNITS_PER_SEC*(qopt->limit/(double)qopt->peakrate.rate) - tc_core_tick2time(qopt->mtu);
+	latency = TIME_UNITS_PER_SEC*(qopt->limit/(double)rate64) - tc_core_tick2time(qopt->buffer);
+	if (prate64) {
+		double lat2 = TIME_UNITS_PER_SEC*(qopt->limit/(double)prate64) - tc_core_tick2time(qopt->mtu);
 		if (lat2 > latency)
 			latency = lat2;
 	}
diff --git a/tc/tc_core.c b/tc/tc_core.c
index a524337..46eaefb 100644
--- a/tc/tc_core.c
+++ b/tc/tc_core.c
@@ -56,12 +56,12 @@
 	return ktime / clock_factor;
 }
 
-unsigned tc_calc_xmittime(unsigned rate, unsigned size)
+unsigned tc_calc_xmittime(__u64 rate, unsigned size)
 {
-	return tc_core_time2tick(TIME_UNITS_PER_SEC*((double)size/rate));
+	return tc_core_time2tick(TIME_UNITS_PER_SEC*((double)size/(double)rate));
 }
 
-unsigned tc_calc_xmitsize(unsigned rate, unsigned ticks)
+unsigned tc_calc_xmitsize(__u64 rate, unsigned ticks)
 {
 	return ((double)rate*tc_core_tick2time(ticks))/TIME_UNITS_PER_SEC;
 }
diff --git a/tc/tc_core.h b/tc/tc_core.h
index 5a693ba..8a63b79 100644
--- a/tc/tc_core.h
+++ b/tc/tc_core.h
@@ -18,8 +18,8 @@
 unsigned tc_core_tick2time(unsigned tick);
 unsigned tc_core_time2ktime(unsigned time);
 unsigned tc_core_ktime2time(unsigned ktime);
-unsigned tc_calc_xmittime(unsigned rate, unsigned size);
-unsigned tc_calc_xmitsize(unsigned rate, unsigned ticks);
+unsigned tc_calc_xmittime(__u64 rate, unsigned size);
+unsigned tc_calc_xmitsize(__u64 rate, unsigned ticks);
 int tc_calc_rtable(struct tc_ratespec *r, __u32 *rtab,
 		   int cell_log, unsigned mtu, enum link_layer link_layer);
 int tc_calc_size_table(struct tc_sizespec *s, __u16 **stab);
diff --git a/tc/tc_util.c b/tc/tc_util.c
index 67f6948..15fb053 100644
--- a/tc/tc_util.c
+++ b/tc/tc_util.c
@@ -171,6 +171,31 @@
 	return 0;
 }
 
+int get_rate64(__u64 *rate, const char *str)
+{
+	char *p;
+	double bps = strtod(str, &p);
+	const struct rate_suffix *s;
+
+	if (p == str)
+		return -1;
+
+	for (s = suffixes; s->name; ++s) {
+		if (strcasecmp(s->name, p) == 0) {
+			bps *= s->scale;
+			p += strlen(p);
+			break;
+		}
+	}
+
+	if (*p)
+		return -1; /* unknown suffix */
+
+	bps /= 8; /* -> bytes per second */
+	*rate = bps;
+	return 0;
+}
+
 void print_rate(char *buf, int len, __u64 rate)
 {
 	extern int use_iec;
diff --git a/tc/tc_util.h b/tc/tc_util.h
index 7c3709f..d418367 100644
--- a/tc/tc_util.h
+++ b/tc/tc_util.h
@@ -58,6 +58,7 @@
 
 extern int get_qdisc_handle(__u32 *h, const char *str);
 extern int get_rate(unsigned *rate, const char *str);
+extern int get_rate64(__u64 *rate, const char *str);
 extern int get_size(unsigned *size, const char *str);
 extern int get_size_and_cell(unsigned *size, int *cell_log, char *str);
 extern int get_time(unsigned *time, const char *str);