Merge branch 'for-linus' into for-next

... to make easier developing HDA ext code.

23 files changed, 1485 insertions, 231 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 76e3458a5419..4450fed91ab4 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -6,45 +6,57 @@ hostprogs-y := test_verifier test_maps
 hostprogs-y += sock_example
 hostprogs-y += sockex1
 hostprogs-y += sockex2
+hostprogs-y += sockex3
 hostprogs-y += tracex1
 hostprogs-y += tracex2
 hostprogs-y += tracex3
 hostprogs-y += tracex4
+hostprogs-y += tracex5
+hostprogs-y += lathist
 
 test_verifier-objs := test_verifier.o libbpf.o
 test_maps-objs := test_maps.o libbpf.o
 sock_example-objs := sock_example.o libbpf.o
 sockex1-objs := bpf_load.o libbpf.o sockex1_user.o
 sockex2-objs := bpf_load.o libbpf.o sockex2_user.o
+sockex3-objs := bpf_load.o libbpf.o sockex3_user.o
 tracex1-objs := bpf_load.o libbpf.o tracex1_user.o
 tracex2-objs := bpf_load.o libbpf.o tracex2_user.o
 tracex3-objs := bpf_load.o libbpf.o tracex3_user.o
 tracex4-objs := bpf_load.o libbpf.o tracex4_user.o
+tracex5-objs := bpf_load.o libbpf.o tracex5_user.o
+lathist-objs := bpf_load.o libbpf.o lathist_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
 always += sockex1_kern.o
 always += sockex2_kern.o
+always += sockex3_kern.o
 always += tracex1_kern.o
 always += tracex2_kern.o
 always += tracex3_kern.o
 always += tracex4_kern.o
+always += tracex5_kern.o
 always += tcbpf1_kern.o
+always += lathist_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 
 HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
 HOSTLOADLIBES_sockex1 += -lelf
 HOSTLOADLIBES_sockex2 += -lelf
+HOSTLOADLIBES_sockex3 += -lelf
 HOSTLOADLIBES_tracex1 += -lelf
 HOSTLOADLIBES_tracex2 += -lelf
 HOSTLOADLIBES_tracex3 += -lelf
 HOSTLOADLIBES_tracex4 += -lelf -lrt
+HOSTLOADLIBES_tracex5 += -lelf
+HOSTLOADLIBES_lathist += -lelf
 
 # point this to your LLVM backend with bpf support
 LLC=$(srctree)/tools/bpf/llvm/bld/Debug+Asserts/bin/llc
 
-%.o: %.c
+$(obj)/%.o: $(src)/%.c
 	clang $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \
 		-D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \
 		-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index f960b5fb3ed8..bdf1c1607b80 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -21,6 +21,16 @@ static unsigned long long (*bpf_ktime_get_ns)(void) =
 	(void *) BPF_FUNC_ktime_get_ns;
 static int (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
 	(void *) BPF_FUNC_trace_printk;
+static void (*bpf_tail_call)(void *ctx, void *map, int index) =
+	(void *) BPF_FUNC_tail_call;
+static unsigned long long (*bpf_get_smp_processor_id)(void) =
+	(void *) BPF_FUNC_get_smp_processor_id;
+static unsigned long long (*bpf_get_current_pid_tgid)(void) =
+	(void *) BPF_FUNC_get_current_pid_tgid;
+static unsigned long long (*bpf_get_current_uid_gid)(void) =
+	(void *) BPF_FUNC_get_current_uid_gid;
+static int (*bpf_get_current_comm)(void *buf, int buf_size) =
+	(void *) BPF_FUNC_get_current_comm;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 38dac5a53b51..da86a8e0a95a 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -16,6 +16,7 @@
 #include <sys/ioctl.h>
 #include <sys/mman.h>
 #include <poll.h>
+#include <ctype.h>
 #include "libbpf.h"
 #include "bpf_helpers.h"
 #include "bpf_load.h"
@@ -29,6 +30,19 @@ int map_fd[MAX_MAPS];
 int prog_fd[MAX_PROGS];
 int event_fd[MAX_PROGS];
 int prog_cnt;
+int prog_array_fd = -1;
+
+static int populate_prog_array(const char *event, int prog_fd)
+{
+	int ind = atoi(event), err;
+
+	err = bpf_update_elem(prog_array_fd, &ind, &prog_fd, BPF_ANY);
+	if (err < 0) {
+		printf("failed to store prog_fd in prog_array\n");
+		return -1;
+	}
+	return 0;
+}
 
 static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 {
@@ -54,12 +68,40 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 		return -1;
 	}
 
+	fd = bpf_prog_load(prog_type, prog, size, license, kern_version);
+	if (fd < 0) {
+		printf("bpf_prog_load() err=%d\n%s", errno, bpf_log_buf);
+		return -1;
+	}
+
+	prog_fd[prog_cnt++] = fd;
+
+	if (is_socket) {
+		event += 6;
+		if (*event != '/')
+			return 0;
+		event++;
+		if (!isdigit(*event)) {
+			printf("invalid prog number\n");
+			return -1;
+		}
+		return populate_prog_array(event, fd);
+	}
+
 	if (is_kprobe || is_kretprobe) {
 		if (is_kprobe)
 			event += 7;
 		else
 			event += 10;
 
+		if (*event == 0) {
+			printf("event name cannot be empty\n");
+			return -1;
+		}
+
+		if (isdigit(*event))
+			return populate_prog_array(event, fd);
+
 		snprintf(buf, sizeof(buf),
 			 "echo '%c:%s %s' >> /sys/kernel/debug/tracing/kprobe_events",
 			 is_kprobe ? 'p' : 'r', event, event);
@@ -71,18 +113,6 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 		}
 	}
 
-	fd = bpf_prog_load(prog_type, prog, size, license, kern_version);
-
-	if (fd < 0) {
-		printf("bpf_prog_load() err=%d\n%s", errno, bpf_log_buf);
-		return -1;
-	}
-
-	prog_fd[prog_cnt++] = fd;
-
-	if (is_socket)
-		return 0;
-
 	strcpy(buf, DEBUGFS);
 	strcat(buf, "events/kprobes/");
 	strcat(buf, event);
@@ -130,6 +160,9 @@ static int load_maps(struct bpf_map_def *maps, int len)
 					   maps[i].max_entries);
 		if (map_fd[i] < 0)
 			return 1;
+
+		if (maps[i].type == BPF_MAP_TYPE_PROG_ARRAY)
+			prog_array_fd = map_fd[i];
 	}
 	return 0;
 }
diff --git a/samples/bpf/lathist_kern.c b/samples/bpf/lathist_kern.c
new file mode 100644
index 000000000000..18fa088473cd
--- /dev/null
+++ b/samples/bpf/lathist_kern.c
@@ -0,0 +1,99 @@
+/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2015 BMW Car IT GmbH
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/version.h>
+#include <linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+#define MAX_ENTRIES	20
+#define MAX_CPU		4
+
+/* We need to stick to static allocated memory (an array instead of
+ * hash table) because managing dynamic memory from the
+ * trace_preempt_[on|off] tracepoints hooks is not supported.
+ */
+
+struct bpf_map_def SEC("maps") my_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(u64),
+	.max_entries = MAX_CPU,
+};
+
+SEC("kprobe/trace_preempt_off")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	int cpu = bpf_get_smp_processor_id();
+	u64 *ts = bpf_map_lookup_elem(&my_map, &cpu);
+
+	if (ts)
+		*ts = bpf_ktime_get_ns();
+
+	return 0;
+}
+
+static unsigned int log2(unsigned int v)
+{
+	unsigned int r;
+	unsigned int shift;
+
+	r = (v > 0xFFFF) << 4; v >>= r;
+	shift = (v > 0xFF) << 3; v >>= shift; r |= shift;
+	shift = (v > 0xF) << 2; v >>= shift; r |= shift;
+	shift = (v > 0x3) << 1; v >>= shift; r |= shift;
+	r |= (v >> 1);
+
+	return r;
+}
+
+static unsigned int log2l(unsigned long v)
+{
+	unsigned int hi = v >> 32;
+
+	if (hi)
+		return log2(hi) + 32;
+	else
+		return log2(v);
+}
+
+struct bpf_map_def SEC("maps") my_lat = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(long),
+	.max_entries = MAX_CPU * MAX_ENTRIES,
+};
+
+SEC("kprobe/trace_preempt_on")
+int bpf_prog2(struct pt_regs *ctx)
+{
+	u64 *ts, cur_ts, delta;
+	int key, cpu;
+	long *val;
+
+	cpu = bpf_get_smp_processor_id();
+	ts = bpf_map_lookup_elem(&my_map, &cpu);
+	if (!ts)
+		return 0;
+
+	cur_ts = bpf_ktime_get_ns();
+	delta = log2l(cur_ts - *ts);
+
+	if (delta > MAX_ENTRIES - 1)
+		delta = MAX_ENTRIES - 1;
+
+	key = cpu * MAX_ENTRIES + delta;
+	val = bpf_map_lookup_elem(&my_lat, &key);
+	if (val)
+		__sync_fetch_and_add((long *)val, 1);
+
+	return 0;
+
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/lathist_user.c b/samples/bpf/lathist_user.c
new file mode 100644
index 000000000000..65da8c1576de
--- /dev/null
+++ b/samples/bpf/lathist_user.c
@@ -0,0 +1,103 @@
+/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2015 BMW Car IT GmbH
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#define MAX_ENTRIES	20
+#define MAX_CPU		4
+#define MAX_STARS	40
+
+struct cpu_hist {
+	long data[MAX_ENTRIES];
+	long max;
+};
+
+static struct cpu_hist cpu_hist[MAX_CPU];
+
+static void stars(char *str, long val, long max, int width)
+{
+	int i;
+
+	for (i = 0; i < (width * val / max) - 1 && i < width - 1; i++)
+		str[i] = '*';
+	if (val > max)
+		str[i - 1] = '+';
+	str[i] = '\0';
+}
+
+static void print_hist(void)
+{
+	char starstr[MAX_STARS];
+	struct cpu_hist *hist;
+	int i, j;
+
+	/* clear screen */
+	printf("\033[2J");
+
+	for (j = 0; j < MAX_CPU; j++) {
+		hist = &cpu_hist[j];
+
+		/* ignore CPUs without data (maybe offline?) */
+		if (hist->max == 0)
+			continue;
+
+		printf("CPU %d\n", j);
+		printf("      latency        : count     distribution\n");
+		for (i = 1; i <= MAX_ENTRIES; i++) {
+			stars(starstr, hist->data[i - 1], hist->max, MAX_STARS);
+			printf("%8ld -> %-8ld : %-8ld |%-*s|\n",
+				(1l << i) >> 1, (1l << i) - 1,
+				hist->data[i - 1], MAX_STARS, starstr);
+		}
+	}
+}
+
+static void get_data(int fd)
+{
+	long key, value;
+	int c, i;
+
+	for (i = 0; i < MAX_CPU; i++)
+		cpu_hist[i].max = 0;
+
+	for (c = 0; c < MAX_CPU; c++) {
+		for (i = 0; i < MAX_ENTRIES; i++) {
+			key = c * MAX_ENTRIES + i;
+			bpf_lookup_elem(fd, &key, &value);
+
+			cpu_hist[c].data[i] = value;
+			if (value > cpu_hist[c].max)
+				cpu_hist[c].max = value;
+		}
+	}
+}
+
+int main(int argc, char **argv)
+{
+	char filename[256];
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	while (1) {
+		get_data(map_fd[1]);
+		print_hist();
+		sleep(5);
+	}
+
+	return 0;
+}
diff --git a/samples/bpf/sockex3_kern.c b/samples/bpf/sockex3_kern.c
new file mode 100644
index 000000000000..41ae2fd21b13
--- /dev/null
+++ b/samples/bpf/sockex3_kern.c
@@ -0,0 +1,290 @@
+/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+#include <uapi/linux/in.h>
+#include <uapi/linux/if.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/ipv6.h>
+#include <uapi/linux/if_tunnel.h>
+#include <uapi/linux/mpls.h>
+#define IP_MF		0x2000
+#define IP_OFFSET	0x1FFF
+
+#define PROG(F) SEC("socket/"__stringify(F)) int bpf_func_##F
+
+struct bpf_map_def SEC("maps") jmp_table = {
+	.type = BPF_MAP_TYPE_PROG_ARRAY,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(u32),
+	.max_entries = 8,
+};
+
+#define PARSE_VLAN 1
+#define PARSE_MPLS 2
+#define PARSE_IP 3
+#define PARSE_IPV6 4
+
+/* protocol dispatch routine.
+ * It tail-calls next BPF program depending on eth proto
+ * Note, we could have used:
+ * bpf_tail_call(skb, &jmp_table, proto);
+ * but it would need large prog_array
+ */
+static inline void parse_eth_proto(struct __sk_buff *skb, u32 proto)
+{
+	switch (proto) {
+	case ETH_P_8021Q:
+	case ETH_P_8021AD:
+		bpf_tail_call(skb, &jmp_table, PARSE_VLAN);
+		break;
+	case ETH_P_MPLS_UC:
+	case ETH_P_MPLS_MC:
+		bpf_tail_call(skb, &jmp_table, PARSE_MPLS);
+		break;
+	case ETH_P_IP:
+		bpf_tail_call(skb, &jmp_table, PARSE_IP);
+		break;
+	case ETH_P_IPV6:
+		bpf_tail_call(skb, &jmp_table, PARSE_IPV6);
+		break;
+	}
+}
+
+struct vlan_hdr {
+	__be16 h_vlan_TCI;
+	__be16 h_vlan_encapsulated_proto;
+};
+
+struct flow_keys {
+	__be32 src;
+	__be32 dst;
+	union {
+		__be32 ports;
+		__be16 port16[2];
+	};
+	__u32 ip_proto;
+};
+
+static inline int ip_is_fragment(struct __sk_buff *ctx, __u64 nhoff)
+{
+	return load_half(ctx, nhoff + offsetof(struct iphdr, frag_off))
+		& (IP_MF | IP_OFFSET);
+}
+
+static inline __u32 ipv6_addr_hash(struct __sk_buff *ctx, __u64 off)
+{
+	__u64 w0 = load_word(ctx, off);
+	__u64 w1 = load_word(ctx, off + 4);
+	__u64 w2 = load_word(ctx, off + 8);
+	__u64 w3 = load_word(ctx, off + 12);
+
+	return (__u32)(w0 ^ w1 ^ w2 ^ w3);
+}
+
+struct globals {
+	struct flow_keys flow;
+};
+
+struct bpf_map_def SEC("maps") percpu_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct globals),
+	.max_entries = 32,
+};
+
+/* user poor man's per_cpu until native support is ready */
+static struct globals *this_cpu_globals(void)
+{
+	u32 key = bpf_get_smp_processor_id();
+
+	return bpf_map_lookup_elem(&percpu_map, &key);
+}
+
+/* some simple stats for user space consumption */
+struct pair {
+	__u64 packets;
+	__u64 bytes;
+};
+
+struct bpf_map_def SEC("maps") hash_map = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(struct flow_keys),
+	.value_size = sizeof(struct pair),
+	.max_entries = 1024,
+};
+
+static void update_stats(struct __sk_buff *skb, struct globals *g)
+{
+	struct flow_keys key = g->flow;
+	struct pair *value;
+
+	value = bpf_map_lookup_elem(&hash_map, &key);
+	if (value) {
+		__sync_fetch_and_add(&value->packets, 1);
+		__sync_fetch_and_add(&value->bytes, skb->len);
+	} else {
+		struct pair val = {1, skb->len};
+
+		bpf_map_update_elem(&hash_map, &key, &val, BPF_ANY);
+	}
+}
+
+static __always_inline void parse_ip_proto(struct __sk_buff *skb,
+					   struct globals *g, __u32 ip_proto)
+{
+	__u32 nhoff = skb->cb[0];
+	int poff;
+
+	switch (ip_proto) {
+	case IPPROTO_GRE: {
+		struct gre_hdr {
+			__be16 flags;
+			__be16 proto;
+		};
+
+		__u32 gre_flags = load_half(skb,
+					    nhoff + offsetof(struct gre_hdr, flags));
+		__u32 gre_proto = load_half(skb,
+					    nhoff + offsetof(struct gre_hdr, proto));
+
+		if (gre_flags & (GRE_VERSION|GRE_ROUTING))
+			break;
+
+		nhoff += 4;
+		if (gre_flags & GRE_CSUM)
+			nhoff += 4;
+		if (gre_flags & GRE_KEY)
+			nhoff += 4;
+		if (gre_flags & GRE_SEQ)
+			nhoff += 4;
+
+		skb->cb[0] = nhoff;
+		parse_eth_proto(skb, gre_proto);
+		break;
+	}
+	case IPPROTO_IPIP:
+		parse_eth_proto(skb, ETH_P_IP);
+		break;
+	case IPPROTO_IPV6:
+		parse_eth_proto(skb, ETH_P_IPV6);
+		break;
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+		g->flow.ports = load_word(skb, nhoff);
+	case IPPROTO_ICMP:
+		g->flow.ip_proto = ip_proto;
+		update_stats(skb, g);
+		break;
+	default:
+		break;
+	}
+}
+
+PROG(PARSE_IP)(struct __sk_buff *skb)
+{
+	struct globals *g = this_cpu_globals();
+	__u32 nhoff, verlen, ip_proto;
+
+	if (!g)
+		return 0;
+
+	nhoff = skb->cb[0];
+
+	if (unlikely(ip_is_fragment(skb, nhoff)))
+		return 0;
+
+	ip_proto = load_byte(skb, nhoff + offsetof(struct iphdr, protocol));
+
+	if (ip_proto != IPPROTO_GRE) {
+		g->flow.src = load_word(skb, nhoff + offsetof(struct iphdr, saddr));
+		g->flow.dst = load_word(skb, nhoff + offsetof(struct iphdr, daddr));
+	}
+
+	verlen = load_byte(skb, nhoff + 0/*offsetof(struct iphdr, ihl)*/);
+	nhoff += (verlen & 0xF) << 2;
+
+	skb->cb[0] = nhoff;
+	parse_ip_proto(skb, g, ip_proto);
+	return 0;
+}
+
+PROG(PARSE_IPV6)(struct __sk_buff *skb)
+{
+	struct globals *g = this_cpu_globals();
+	__u32 nhoff, ip_proto;
+
+	if (!g)
+		return 0;
+
+	nhoff = skb->cb[0];
+
+	ip_proto = load_byte(skb,
+			     nhoff + offsetof(struct ipv6hdr, nexthdr));
+	g->flow.src = ipv6_addr_hash(skb,
+				     nhoff + offsetof(struct ipv6hdr, saddr));
+	g->flow.dst = ipv6_addr_hash(skb,
+				     nhoff + offsetof(struct ipv6hdr, daddr));
+	nhoff += sizeof(struct ipv6hdr);
+
+	skb->cb[0] = nhoff;
+	parse_ip_proto(skb, g, ip_proto);
+	return 0;
+}
+
+PROG(PARSE_VLAN)(struct __sk_buff *skb)
+{
+	__u32 nhoff, proto;
+
+	nhoff = skb->cb[0];
+
+	proto = load_half(skb, nhoff + offsetof(struct vlan_hdr,
+						h_vlan_encapsulated_proto));
+	nhoff += sizeof(struct vlan_hdr);
+	skb->cb[0] = nhoff;
+
+	parse_eth_proto(skb, proto);
+
+	return 0;
+}
+
+PROG(PARSE_MPLS)(struct __sk_buff *skb)
+{
+	__u32 nhoff, label;
+
+	nhoff = skb->cb[0];
+
+	label = load_word(skb, nhoff);
+	nhoff += sizeof(struct mpls_label);
+	skb->cb[0] = nhoff;
+
+	if (label & MPLS_LS_S_MASK) {
+		__u8 verlen = load_byte(skb, nhoff);
+		if ((verlen & 0xF0) == 4)
+			parse_eth_proto(skb, ETH_P_IP);
+		else
+			parse_eth_proto(skb, ETH_P_IPV6);
+	} else {
+		parse_eth_proto(skb, ETH_P_MPLS_UC);
+	}
+
+	return 0;
+}
+
+SEC("socket/0")
+int main_prog(struct __sk_buff *skb)
+{
+	__u32 nhoff = ETH_HLEN;
+	__u32 proto = load_half(skb, 12);
+
+	skb->cb[0] = nhoff;
+	parse_eth_proto(skb, proto);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c
new file mode 100644
index 000000000000..2617772d060d
--- /dev/null
+++ b/samples/bpf/sockex3_user.c
@@ -0,0 +1,66 @@
+#include <stdio.h>
+#include <assert.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+#include <unistd.h>
+#include <arpa/inet.h>
+
+struct flow_keys {
+	__be32 src;
+	__be32 dst;
+	union {
+		__be32 ports;
+		__be16 port16[2];
+	};
+	__u32 ip_proto;
+};
+
+struct pair {
+	__u64 packets;
+	__u64 bytes;
+};
+
+int main(int argc, char **argv)
+{
+	char filename[256];
+	FILE *f;
+	int i, sock;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	sock = open_raw_sock("lo");
+
+	assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd[4],
+			  sizeof(__u32)) == 0);
+
+	if (argc > 1)
+		f = popen("ping -c5 localhost", "r");
+	else
+		f = popen("netperf -l 4 localhost", "r");
+	(void) f;
+
+	for (i = 0; i < 5; i++) {
+		struct flow_keys key = {}, next_key;
+		struct pair value;
+
+		sleep(1);
+		printf("IP     src.port -> dst.port               bytes      packets\n");
+		while (bpf_get_next_key(map_fd[2], &key, &next_key) == 0) {
+			bpf_lookup_elem(map_fd[2], &next_key, &value);
+			printf("%s.%05d -> %s.%05d %12lld %12lld\n",
+			       inet_ntoa((struct in_addr){htonl(next_key.src)}),
+			       next_key.port16[0],
+			       inet_ntoa((struct in_addr){htonl(next_key.dst)}),
+			       next_key.port16[1],
+			       value.bytes, value.packets);
+			key = next_key;
+		}
+	}
+	return 0;
+}
diff --git a/samples/bpf/tcbpf1_kern.c b/samples/bpf/tcbpf1_kern.c
index 7c27710f8296..9bfb2eb34563 100644
--- a/samples/bpf/tcbpf1_kern.c
+++ b/samples/bpf/tcbpf1_kern.c
@@ -21,7 +21,7 @@ static inline void set_dst_mac(struct __sk_buff *skb, char *mac)
 
 static inline void set_ip_tos(struct __sk_buff *skb, __u8 new_tos)
 {
-	__u8 old_tos = load_byte(skb, BPF_LL_OFF + TOS_OFF);
+	__u8 old_tos = load_byte(skb, TOS_OFF);
 
 	bpf_l3_csum_replace(skb, IP_CSUM_OFF, htons(old_tos), htons(new_tos), 2);
 	bpf_skb_store_bytes(skb, TOS_OFF, &new_tos, sizeof(new_tos), 0);
@@ -34,7 +34,7 @@ static inline void set_ip_tos(struct __sk_buff *skb, __u8 new_tos)
 
 static inline void set_tcp_ip_src(struct __sk_buff *skb, __u32 new_ip)
 {
-	__u32 old_ip = _htonl(load_word(skb, BPF_LL_OFF + IP_SRC_OFF));
+	__u32 old_ip = _htonl(load_word(skb, IP_SRC_OFF));
 
 	bpf_l4_csum_replace(skb, TCP_CSUM_OFF, old_ip, new_ip, IS_PSEUDO | sizeof(new_ip));
 	bpf_l3_csum_replace(skb, IP_CSUM_OFF, old_ip, new_ip, sizeof(new_ip));
@@ -44,7 +44,7 @@ static inline void set_tcp_ip_src(struct __sk_buff *skb, __u32 new_ip)
 #define TCP_DPORT_OFF (ETH_HLEN + sizeof(struct iphdr) + offsetof(struct tcphdr, dest))
 static inline void set_tcp_dest_port(struct __sk_buff *skb, __u16 new_port)
 {
-	__u16 old_port = htons(load_half(skb, BPF_LL_OFF + TCP_DPORT_OFF));
+	__u16 old_port = htons(load_half(skb, TCP_DPORT_OFF));
 
 	bpf_l4_csum_replace(skb, TCP_CSUM_OFF, old_port, new_port, sizeof(new_port));
 	bpf_skb_store_bytes(skb, TCP_DPORT_OFF, &new_port, sizeof(new_port), 0);
@@ -53,7 +53,7 @@ static inline void set_tcp_dest_port(struct __sk_buff *skb, __u16 new_port)
 SEC("classifier")
 int bpf_prog1(struct __sk_buff *skb)
 {
-	__u8 proto = load_byte(skb, BPF_LL_OFF + ETH_HLEN + offsetof(struct iphdr, protocol));
+	__u8 proto = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol));
 	long *value;
 
 	if (proto == IPPROTO_TCP) {
diff --git a/samples/bpf/test_verifier.c b/samples/bpf/test_verifier.c
index 12f3780af73f..693605997abc 100644
--- a/samples/bpf/test_verifier.c
+++ b/samples/bpf/test_verifier.c
@@ -29,6 +29,7 @@ struct bpf_test {
 		ACCEPT,
 		REJECT
 	} result;
+	enum bpf_prog_type prog_type;
 };
 
 static struct bpf_test tests[] = {
@@ -743,6 +744,84 @@ static struct bpf_test tests[] = {
 		.errstr = "different pointers",
 		.result = REJECT,
 	},
+	{
+		"check skb->mark is not writeable by sockets",
+		.insns = {
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "invalid bpf_context access",
+		.result = REJECT,
+	},
+	{
+		"check skb->tc_index is not writeable by sockets",
+		.insns = {
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+				    offsetof(struct __sk_buff, tc_index)),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "invalid bpf_context access",
+		.result = REJECT,
+	},
+	{
+		"check non-u32 access to cb",
+		.insns = {
+			BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[0])),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "invalid bpf_context access",
+		.result = REJECT,
+	},
+	{
+		"check out of range skb->cb access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[60])),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "invalid bpf_context access",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_SCHED_ACT,
+	},
+	{
+		"write skb fields from socket prog",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[4])),
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, tc_index)),
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[0])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[2])),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+	},
+	{
+		"write skb fields from tc_cls_act prog",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[0])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, tc_index)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+				    offsetof(struct __sk_buff, tc_index)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+				    offsetof(struct __sk_buff, cb[3])),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
 };
 
 static int probe_filter_length(struct bpf_insn *fp)
@@ -775,6 +854,7 @@ static int test(void)
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		struct bpf_insn *prog = tests[i].insns;
+		int prog_type = tests[i].prog_type;
 		int prog_len = probe_filter_length(prog);
 		int *fixup = tests[i].fixup;
 		int map_fd = -1;
@@ -789,8 +869,8 @@ static int test(void)
 		}
 		printf("#%d %s ", i, tests[i].descr);
 
-		prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, prog,
-					prog_len * sizeof(struct bpf_insn),
+		prog_fd = bpf_prog_load(prog_type ?: BPF_PROG_TYPE_SOCKET_FILTER,
+					prog, prog_len * sizeof(struct bpf_insn),
 					"GPL", 0);
 
 		if (tests[i].result == ACCEPT) {
diff --git a/samples/bpf/tracex2_kern.c b/samples/bpf/tracex2_kern.c
index 19ec1cfc45db..dc50f4f2943f 100644
--- a/samples/bpf/tracex2_kern.c
+++ b/samples/bpf/tracex2_kern.c
@@ -62,11 +62,18 @@ static unsigned int log2l(unsigned long v)
 		return log2(v);
 }
 
+struct hist_key {
+	char comm[16];
+	u64 pid_tgid;
+	u64 uid_gid;
+	u32 index;
+};
+
 struct bpf_map_def SEC("maps") my_hist_map = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(u32),
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(struct hist_key),
 	.value_size = sizeof(long),
-	.max_entries = 64,
+	.max_entries = 1024,
 };
 
 SEC("kprobe/sys_write")
@@ -75,11 +82,18 @@ int bpf_prog3(struct pt_regs *ctx)
 	long write_size = ctx->dx; /* arg3 */
 	long init_val = 1;
 	long *value;
-	u32 index = log2l(write_size);
+	struct hist_key key = {};
+
+	key.index = log2l(write_size);
+	key.pid_tgid = bpf_get_current_pid_tgid();
+	key.uid_gid = bpf_get_current_uid_gid();
+	bpf_get_current_comm(&key.comm, sizeof(key.comm));
 
-	value = bpf_map_lookup_elem(&my_hist_map, &index);
+	value = bpf_map_lookup_elem(&my_hist_map, &key);
 	if (value)
 		__sync_fetch_and_add(value, 1);
+	else
+		bpf_map_update_elem(&my_hist_map, &key, &init_val, BPF_ANY);
 	return 0;
 }
 char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c
index 91b8d0896fbb..cd0241c1447a 100644
--- a/samples/bpf/tracex2_user.c
+++ b/samples/bpf/tracex2_user.c
@@ -3,6 +3,7 @@
 #include <stdlib.h>
 #include <signal.h>
 #include <linux/bpf.h>
+#include <string.h>
 #include "libbpf.h"
 #include "bpf_load.h"
 
@@ -20,23 +21,42 @@ static void stars(char *str, long val, long max, int width)
 	str[i] = '\0';
 }
 
-static void print_hist(int fd)
+struct task {
+	char comm[16];
+	__u64 pid_tgid;
+	__u64 uid_gid;
+};
+
+struct hist_key {
+	struct task t;
+	__u32 index;
+};
+
+#define SIZE sizeof(struct task)
+
+static void print_hist_for_pid(int fd, void *task)
 {
-	int key;
+	struct hist_key key = {}, next_key;
+	char starstr[MAX_STARS];
 	long value;
 	long data[MAX_INDEX] = {};
-	char starstr[MAX_STARS];
-	int i;
 	int max_ind = -1;
 	long max_value = 0;
+	int i, ind;
 
-	for (key = 0; key < MAX_INDEX; key++) {
-		bpf_lookup_elem(fd, &key, &value);
-		data[key] = value;
-		if (value && key > max_ind)
-			max_ind = key;
+	while (bpf_get_next_key(fd, &key, &next_key) == 0) {
+		if (memcmp(&next_key, task, SIZE)) {
+			key = next_key;
+			continue;
+		}
+		bpf_lookup_elem(fd, &next_key, &value);
+		ind = next_key.index;
+		data[ind] = value;
+		if (value && ind > max_ind)
+			max_ind = ind;
 		if (value > max_value)
 			max_value = value;
+		key = next_key;
 	}
 
 	printf("           syscall write() stats\n");
@@ -48,6 +68,35 @@ static void print_hist(int fd)
 		       MAX_STARS, starstr);
 	}
 }
+
+static void print_hist(int fd)
+{
+	struct hist_key key = {}, next_key;
+	static struct task tasks[1024];
+	int task_cnt = 0;
+	int i;
+
+	while (bpf_get_next_key(fd, &key, &next_key) == 0) {
+		int found = 0;
+
+		for (i = 0; i < task_cnt; i++)
+			if (memcmp(&tasks[i], &next_key, SIZE) == 0)
+				found = 1;
+		if (!found)
+			memcpy(&tasks[task_cnt++], &next_key, SIZE);
+		key = next_key;
+	}
+
+	for (i = 0; i < task_cnt; i++) {
+		printf("\npid %d cmd %s uid %d\n",
+		       (__u32) tasks[i].pid_tgid,
+		       tasks[i].comm,
+		       (__u32) tasks[i].uid_gid);
+		print_hist_for_pid(fd, &tasks[i]);
+	}
+
+}
+
 static void int_exit(int sig)
 {
 	print_hist(map_fd[1]);
diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c
new file mode 100644
index 000000000000..b71fe07a7a7a
--- /dev/null
+++ b/samples/bpf/tracex5_kern.c
@@ -0,0 +1,75 @@
+/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/seccomp.h>
+#include "bpf_helpers.h"
+
+#define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F
+
+struct bpf_map_def SEC("maps") progs = {
+	.type = BPF_MAP_TYPE_PROG_ARRAY,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(u32),
+	.max_entries = 1024,
+};
+
+SEC("kprobe/seccomp_phase1")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	struct seccomp_data sd = {};
+
+	bpf_probe_read(&sd, sizeof(sd), (void *)ctx->di);
+
+	/* dispatch into next BPF program depending on syscall number */
+	bpf_tail_call(ctx, &progs, sd.nr);
+
+	/* fall through -> unknown syscall */
+	if (sd.nr >= __NR_getuid && sd.nr <= __NR_getsid) {
+		char fmt[] = "syscall=%d (one of get/set uid/pid/gid)\n";
+		bpf_trace_printk(fmt, sizeof(fmt), sd.nr);
+	}
+	return 0;
+}
+
+/* we jump here when syscall number == __NR_write */
+PROG(__NR_write)(struct pt_regs *ctx)
+{
+	struct seccomp_data sd = {};
+
+	bpf_probe_read(&sd, sizeof(sd), (void *)ctx->di);
+	if (sd.args[2] == 512) {
+		char fmt[] = "write(fd=%d, buf=%p, size=%d)\n";
+		bpf_trace_printk(fmt, sizeof(fmt),
+				 sd.args[0], sd.args[1], sd.args[2]);
+	}
+	return 0;
+}
+
+PROG(__NR_read)(struct pt_regs *ctx)
+{
+	struct seccomp_data sd = {};
+
+	bpf_probe_read(&sd, sizeof(sd), (void *)ctx->di);
+	if (sd.args[2] > 128 && sd.args[2] <= 1024) {
+		char fmt[] = "read(fd=%d, buf=%p, size=%d)\n";
+		bpf_trace_printk(fmt, sizeof(fmt),
+				 sd.args[0], sd.args[1], sd.args[2]);
+	}
+	return 0;
+}
+
+PROG(__NR_mmap)(struct pt_regs *ctx)
+{
+	char fmt[] = "mmap\n";
+	bpf_trace_printk(fmt, sizeof(fmt));
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/tracex5_user.c b/samples/bpf/tracex5_user.c
new file mode 100644
index 000000000000..a04dd3cd4358
--- /dev/null
+++ b/samples/bpf/tracex5_user.c
@@ -0,0 +1,46 @@
+#include <stdio.h>
+#include <linux/bpf.h>
+#include <unistd.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <sys/prctl.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+/* install fake seccomp program to enable seccomp code path inside the kernel,
+ * so that our kprobe attached to seccomp_phase1() can be triggered
+ */
+static void install_accept_all_seccomp(void)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog = {
+		.len = (unsigned short)(sizeof(filter)/sizeof(filter[0])),
+		.filter = filter,
+	};
+	if (prctl(PR_SET_SECCOMP, 2, &prog))
+		perror("prctl");
+}
+
+int main(int ac, char **argv)
+{
+	FILE *f;
+	char filename[256];
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	install_accept_all_seccomp();
+
+	f = popen("dd if=/dev/zero of=/dev/null count=5", "r");
+	(void) f;
+
+	read_trace_pipe();
+
+	return 0;
+}
diff --git a/samples/pktgen/README.rst b/samples/pktgen/README.rst
new file mode 100644
index 000000000000..8365c4e5c513
--- /dev/null
+++ b/samples/pktgen/README.rst
@@ -0,0 +1,43 @@
+Sample and benchmark scripts for pktgen (packet generator)
+==========================================================
+This directory contains some pktgen sample and benchmark scripts, that
+can easily be copied and adjusted for your own use-case.
+
+General doc is located in kernel: Documentation/networking/pktgen.txt
+
+Helper include files
+====================
+This directory contains two helper shell files, that can be "included"
+by shell source'ing.  Namely "functions.sh" and "parameters.sh".
+
+Common parameters
+-----------------
+The parameters.sh file support easy and consistant parameter parsing
+across the sample scripts.  Usage example is printed on errors::
+
+ Usage: ./pktgen_sample01_simple.sh [-vx] -i ethX
+  -i : ($DEV)       output interface/device (required)
+  -s : ($PKT_SIZE)  packet size
+  -d : ($DEST_IP)   destination IP
+  -m : ($DST_MAC)   destination MAC-addr
+  -t : ($THREADS)   threads to start
+  -c : ($SKB_CLONE) SKB clones send before alloc new SKB
+  -b : ($BURST)     HW level bursting of SKBs
+  -v : ($VERBOSE)   verbose
+  -x : ($DEBUG)     debug
+
+The global variable being set is also listed.  E.g. the required
+interface/device parameter "-i" sets variable $DEV.
+
+Common functions
+----------------
+The functions.sh file provides; Three different shell functions for
+configuring the different components of pktgen: pg_ctrl(), pg_thread()
+and pg_set().
+
+These functions correspond to pktgens different components.
+ * pg_ctrl()   control "pgctrl" (/proc/net/pktgen/pgctrl)
+ * pg_thread() control the kernel threads and binding to devices
+ * pg_set()    control setup of individual devices
+
+See sample scripts for usage examples.
diff --git a/samples/pktgen/functions.sh b/samples/pktgen/functions.sh
new file mode 100644
index 000000000000..205e4cde4601
--- /dev/null
+++ b/samples/pktgen/functions.sh
@@ -0,0 +1,121 @@
+#
+# Common functions used by pktgen scripts
+#  - Depending on bash 3 (or higher) syntax
+#
+# Author: Jesper Dangaaard Brouer
+# License: GPL
+
+## -- General shell logging cmds --
+function err() {
+    local exitcode=$1
+    shift
+    echo "ERROR: $@" >&2
+    exit $exitcode
+}
+
+function warn() {
+    echo "WARN : $@" >&2
+}
+
+function info() {
+    if [[ -n "$VERBOSE" ]]; then
+	echo "INFO : $@" >&2
+    fi
+}
+
+## -- Pktgen proc config commands -- ##
+export PROC_DIR=/proc/net/pktgen
+#
+# Three different shell functions for configuring the different
+# components of pktgen:
+#   pg_ctrl(), pg_thread() and pg_set().
+#
+# These functions correspond to pktgens different components.
+# * pg_ctrl()   control "pgctrl" (/proc/net/pktgen/pgctrl)
+# * pg_thread() control the kernel threads and binding to devices
+# * pg_set()    control setup of individual devices
+function pg_ctrl() {
+    local proc_file="pgctrl"
+    proc_cmd ${proc_file} "$@"
+}
+
+function pg_thread() {
+    local thread=$1
+    local proc_file="kpktgend_${thread}"
+    shift
+    proc_cmd ${proc_file} "$@"
+}
+
+function pg_set() {
+    local dev=$1
+    local proc_file="$dev"
+    shift
+    proc_cmd ${proc_file} "$@"
+}
+
+# More generic replacement for pgset(), that does not depend on global
+# variable for proc file.
+function proc_cmd() {
+    local result
+    local proc_file=$1
+    # after shift, the remaining args are contained in $@
+    shift
+    local proc_ctrl=${PROC_DIR}/$proc_file
+    if [[ ! -e "$proc_ctrl" ]]; then
+	err 3 "proc file:$proc_ctrl does not exists (dev added to thread?)"
+    else
+	if [[ ! -w "$proc_ctrl" ]]; then
+	    err 4 "proc file:$proc_ctrl not writable, not root?!"
+	fi
+    fi
+
+    if [[ "$DEBUG" == "yes" ]]; then
+	echo "cmd: $@ > $proc_ctrl"
+    fi
+    # Quoting of "$@" is important for space expansion
+    echo "$@" > "$proc_ctrl"
+    local status=$?
+
+    result=$(grep "Result: OK:" $proc_ctrl)
+    # Due to pgctrl, cannot use exit code $? from grep
+    if [[ "$result" == "" ]]; then
+	grep "Result:" $proc_ctrl >&2
+    fi
+    if (( $status != 0 )); then
+	err 5 "Write error($status) occurred cmd: \"$@ > $proc_ctrl\""
+    fi
+}
+
+# Old obsolete "pgset" function, with slightly improved err handling
+function pgset() {
+    local result
+
+    if [[ "$DEBUG" == "yes" ]]; then
+	echo "cmd: $1 > $PGDEV"
+    fi
+    echo $1 > $PGDEV
+    local status=$?
+
+    result=`cat $PGDEV | fgrep "Result: OK:"`
+    if [[ "$result" == "" ]]; then
+         cat $PGDEV | fgrep Result:
+    fi
+    if (( $status != 0 )); then
+	err 5 "Write error($status) occurred cmd: \"$1 > $PGDEV\""
+    fi
+}
+
+## -- General shell tricks --
+
+function root_check_run_with_sudo() {
+    # Trick so, program can be run as normal user, will just use "sudo"
+    #  call as root_check_run_as_sudo "$@"
+    if [ "$EUID" -ne 0 ]; then
+	if [ -x $0 ]; then # Directly executable use sudo
+	    info "Not root, running with sudo"
+            sudo "$0" "$@"
+            exit $?
+	fi
+	err 4 "cannot perform sudo run of $0"
+    fi
+}
diff --git a/samples/pktgen/parameters.sh b/samples/pktgen/parameters.sh
new file mode 100644
index 000000000000..33b70fdd5a4a
--- /dev/null
+++ b/samples/pktgen/parameters.sh
@@ -0,0 +1,97 @@
+#
+# Common parameter parsing for pktgen scripts
+#
+
+function usage() {
+    echo ""
+    echo "Usage: $0 [-vx] -i ethX"
+    echo "  -i : (\$DEV)       output interface/device (required)"
+    echo "  -s : (\$PKT_SIZE)  packet size"
+    echo "  -d : (\$DEST_IP)   destination IP"
+    echo "  -m : (\$DST_MAC)   destination MAC-addr"
+    echo "  -t : (\$THREADS)   threads to start"
+    echo "  -c : (\$SKB_CLONE) SKB clones send before alloc new SKB"
+    echo "  -b : (\$BURST)     HW level bursting of SKBs"
+    echo "  -v : (\$VERBOSE)   verbose"
+    echo "  -x : (\$DEBUG)     debug"
+    echo ""
+}
+
+##  --- Parse command line arguments / parameters ---
+## echo "Commandline options:"
+while getopts "s:i:d:m:t:c:b:vxh" option; do
+    case $option in
+        i) # interface
+          export DEV=$OPTARG
+	  info "Output device set to: DEV=$DEV"
+          ;;
+        s)
+          export PKT_SIZE=$OPTARG
+	  info "Packet size set to: PKT_SIZE=$PKT_SIZE bytes"
+          ;;
+        d) # destination IP
+          export DEST_IP=$OPTARG
+	  info "Destination IP set to: DEST_IP=$DEST_IP"
+          ;;
+        m) # MAC
+          export DST_MAC=$OPTARG
+	  info "Destination MAC set to: DST_MAC=$DST_MAC"
+          ;;
+        t)
+	  export THREADS=$OPTARG
+          export CPU_THREADS=$OPTARG
+	  let "CPU_THREADS -= 1"
+	  info "Number of threads to start: $THREADS (0 to $CPU_THREADS)"
+          ;;
+        c)
+	  export CLONE_SKB=$OPTARG
+	  info "CLONE_SKB=$CLONE_SKB"
+          ;;
+        b)
+	  export BURST=$OPTARG
+	  info "SKB bursting: BURST=$BURST"
+          ;;
+        v)
+          export VERBOSE=yes
+          info "Verbose mode: VERBOSE=$VERBOSE"
+          ;;
+        x)
+          export DEBUG=yes
+          info "Debug mode: DEBUG=$DEBUG"
+          ;;
+        h|?|*)
+          usage;
+          err 2 "[ERROR] Unknown parameters!!!"
+    esac
+done
+shift $(( $OPTIND - 1 ))
+
+if [ -z "$PKT_SIZE" ]; then
+    # NIC adds 4 bytes CRC
+    export PKT_SIZE=60
+    info "Default packet size set to: set to: $PKT_SIZE bytes"
+fi
+
+if [ -z "$THREADS" ]; then
+    # Zero CPU threads means one thread, because CPU numbers are zero indexed
+    export CPU_THREADS=0
+    export THREADS=1
+fi
+
+if [ -z "$DEV" ]; then
+    usage
+    err 2 "Please specify output device"
+fi
+
+if [ -z "$DST_MAC" ]; then
+    warn "Missing destination MAC address"
+fi
+
+if [ -z "$DEST_IP" ]; then
+    warn "Missing destination IP address"
+fi
+
+if [ ! -d /proc/net/pktgen ]; then
+    info "Loading kernel module: pktgen"
+    modprobe pktgen
+fi
diff --git a/samples/pktgen/pktgen.conf-1-1 b/samples/pktgen/pktgen.conf-1-1
deleted file mode 100755
index f91daad9e916..000000000000
--- a/samples/pktgen/pktgen.conf-1-1
+++ /dev/null
@@ -1,59 +0,0 @@
-#!/bin/bash
-
-#modprobe pktgen
-
-
-function pgset() {
-    local result
-
-    echo $1 > $PGDEV
-
-    result=`cat $PGDEV | fgrep "Result: OK:"`
-    if [ "$result" = "" ]; then
-         cat $PGDEV | fgrep Result:
-    fi
-}
-
-# Config Start Here -----------------------------------------------------------
-
-
-# thread config
-# Each CPU has its own thread. One CPU example. We add eth1.
-
-PGDEV=/proc/net/pktgen/kpktgend_0
-  echo "Removing all devices"
- pgset "rem_device_all"
-  echo "Adding eth1"
- pgset "add_device eth1"
-
-
-# device config
-# delay 0 means maximum speed.
-
-CLONE_SKB="clone_skb 1000000"
-# NIC adds 4 bytes CRC
-PKT_SIZE="pkt_size 60"
-
-# COUNT 0 means forever
-#COUNT="count 0"
-COUNT="count 10000000"
-DELAY="delay 0"
-
-PGDEV=/proc/net/pktgen/eth1
-  echo "Configuring $PGDEV"
- pgset "$COUNT"
- pgset "$CLONE_SKB"
- pgset "$PKT_SIZE"
- pgset "$DELAY"
- pgset "dst 10.10.11.2"
- pgset "dst_mac  00:04:23:08:91:dc"
-
-
-# Time to run
-PGDEV=/proc/net/pktgen/pgctrl
-
- echo "Running... ctrl^C to stop"
- trap true INT
- pgset "start"
- echo "Done"
- cat /proc/net/pktgen/eth1
diff --git a/samples/pktgen/pktgen.conf-2-1 b/samples/pktgen/pktgen.conf-2-1
deleted file mode 100755
index e108e97d6d89..000000000000
--- a/samples/pktgen/pktgen.conf-2-1
+++ /dev/null
@@ -1,66 +0,0 @@
-#!/bin/bash
-
-#modprobe pktgen
-
-
-function pgset() {
-    local result
-
-    echo $1 > $PGDEV
-
-    result=`cat $PGDEV | fgrep "Result: OK:"`
-    if [ "$result" = "" ]; then
-         cat $PGDEV | fgrep Result:
-    fi
-}
-
-# Config Start Here -----------------------------------------------------------
-
-
-# thread config
-# Each CPU has its own thread. Two CPU example. We add eth1 to the first
-# and leave the second idle.
-
-PGDEV=/proc/net/pktgen/kpktgend_0
-  echo "Removing all devices"
- pgset "rem_device_all"
-  echo "Adding eth1"
- pgset "add_device eth1"
-
-# We need to remove old config since we dont use this thread. We can only
-# one NIC on one CPU due to affinity reasons.
-
-PGDEV=/proc/net/pktgen/kpktgend_1
-  echo "Removing all devices"
- pgset "rem_device_all"
-
-# device config
-# delay 0 means maximum speed.
-
-CLONE_SKB="clone_skb 1000000"
-# NIC adds 4 bytes CRC
-PKT_SIZE="pkt_size 60"
-
-# COUNT 0 means forever
-#COUNT="count 0"
-COUNT="count 10000000"
-DELAY="delay 0"
-
-PGDEV=/proc/net/pktgen/eth1
-  echo "Configuring $PGDEV"
- pgset "$COUNT"
- pgset "$CLONE_SKB"
- pgset "$PKT_SIZE"
- pgset "$DELAY"
- pgset "dst 10.10.11.2"
- pgset "dst_mac  00:04:23:08:91:dc"
-
-
-# Time to run
-PGDEV=/proc/net/pktgen/pgctrl
-
- echo "Running... ctrl^C to stop"
- trap true INT
- pgset "start"
- echo "Done"
- cat /proc/net/pktgen/eth1
diff --git a/samples/pktgen/pktgen.conf-2-2 b/samples/pktgen/pktgen.conf-2-2
deleted file mode 100755
index acea15503e71..000000000000
--- a/samples/pktgen/pktgen.conf-2-2
+++ /dev/null
@@ -1,73 +0,0 @@
-#!/bin/bash
-
-#modprobe pktgen
-
-
-function pgset() {
-    local result
-
-    echo $1 > $PGDEV
-
-    result=`cat $PGDEV | fgrep "Result: OK:"`
-    if [ "$result" = "" ]; then
-         cat $PGDEV | fgrep Result:
-    fi
-}
-
-# Config Start Here -----------------------------------------------------------
-
-
-# thread config
-# Each CPU has its own thread. Two CPU example. We add eth1, eth2 respectively.
-
-PGDEV=/proc/net/pktgen/kpktgend_0
-  echo "Removing all devices"
- pgset "rem_device_all"
-  echo "Adding eth1"
- pgset "add_device eth1"
-
-PGDEV=/proc/net/pktgen/kpktgend_1
-  echo "Removing all devices"
- pgset "rem_device_all"
-  echo "Adding eth2"
- pgset "add_device eth2"
-
-
-# device config
-# delay 0 means maximum speed.
-
-CLONE_SKB="clone_skb 1000000"
-# NIC adds 4 bytes CRC
-PKT_SIZE="pkt_size 60"
-
-# COUNT 0 means forever
-#COUNT="count 0"
-COUNT="count 10000000"
-DELAY="delay 0"
-
-PGDEV=/proc/net/pktgen/eth1
-  echo "Configuring $PGDEV"
- pgset "$COUNT"
- pgset "$CLONE_SKB"
- pgset "$PKT_SIZE"
- pgset "$DELAY"
- pgset "dst 10.10.11.2"
- pgset "dst_mac  00:04:23:08:91:dc"
-
-PGDEV=/proc/net/pktgen/eth2
-  echo "Configuring $PGDEV"
- pgset "$COUNT"
- pgset "$CLONE_SKB"
- pgset "$PKT_SIZE"
- pgset "$DELAY"
- pgset "dst 192.168.2.2"
- pgset "dst_mac  00:04:23:08:91:de"
-
-# Time to run
-PGDEV=/proc/net/pktgen/pgctrl
-
- echo "Running... ctrl^C to stop"
- trap true INT
- pgset "start"
- echo "Done"
- cat /proc/net/pktgen/eth1 /proc/net/pktgen/eth2
diff --git a/samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh b/samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh
new file mode 100755
index 000000000000..cb1590331b47
--- /dev/null
+++ b/samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh
@@ -0,0 +1,86 @@
+#!/bin/bash
+#
+# Benchmark script:
+#  - developed for benchmarking ingress qdisc path
+#
+# Script for injecting packets into RX path of the stack with pktgen
+# "xmit_mode netif_receive".  With an invalid dst_mac this will only
+# measure the ingress code path as packets gets dropped in ip_rcv().
+#
+# This script don't really need any hardware.  It benchmarks software
+# RX path just after NIC driver level.  With bursting is also
+# "removes" the SKB alloc/free overhead.
+#
+# Setup scenarios for measuring ingress qdisc (with invalid dst_mac):
+# ------------------------------------------------------------------
+# (1) no ingress (uses static_key_false(&ingress_needed))
+#
+# (2) ingress on other dev (change ingress_needed and calls
+#     handle_ing() but exit early)
+#
+#  config:  tc qdisc add dev $SOMEDEV handle ffff: ingress
+#
+# (3) ingress on this dev, handle_ing() -> tc_classify()
+#
+#  config:  tc qdisc add dev $DEV handle ffff: ingress
+#
+# (4) ingress on this dev + drop at u32 classifier/action.
+#
+basedir=`dirname $0`
+source ${basedir}/functions.sh
+root_check_run_with_sudo "$@"
+
+# Parameter parsing via include
+source ${basedir}/parameters.sh
+# Using invalid DST_MAC will cause the packets to get dropped in
+# ip_rcv() which is part of the test
+[ -z "$DEST_IP" ] && DEST_IP="198.18.0.42"
+[ -z "$DST_MAC" ] && DST_MAC="90:e2:ba:ff:ff:ff"
+[ -z "$BURST" ] && BURST=1024
+
+# Base Config
+DELAY="0"        # Zero means max speed
+COUNT="10000000" # Zero means indefinitely
+
+# General cleanup everything since last run
+pg_ctrl "reset"
+
+# Threads are specified with parameter -t value in $THREADS
+for ((thread = 0; thread < $THREADS; thread++)); do
+    # The device name is extended with @name, using thread number to
+    # make then unique, but any name will do.
+    dev=${DEV}@${thread}
+
+    # Add remove all other devices and add_device $dev to thread
+    pg_thread $thread "rem_device_all"
+    pg_thread $thread "add_device" $dev
+
+    # Base config of dev
+    pg_set $dev "flag QUEUE_MAP_CPU"
+    pg_set $dev "count $COUNT"
+    pg_set $dev "pkt_size $PKT_SIZE"
+    pg_set $dev "delay $DELAY"
+    pg_set $dev "flag NO_TIMESTAMP"
+
+    # Destination
+    pg_set $dev "dst_mac $DST_MAC"
+    pg_set $dev "dst $DEST_IP"
+
+    # Inject packet into RX path of stack
+    pg_set $dev "xmit_mode netif_receive"
+
+    # Burst allow us to avoid measuring SKB alloc/free overhead
+    pg_set $dev "burst $BURST"
+done
+
+# start_run
+echo "Running... ctrl^C to stop" >&2
+pg_ctrl "start"
+echo "Done" >&2
+
+# Print results
+for ((thread = 0; thread < $THREADS; thread++)); do
+    dev=${DEV}@${thread}
+    echo "Device: $dev"
+    cat /proc/net/pktgen/$dev | grep -A2 "Result:"
+done
diff --git a/samples/pktgen/pktgen_sample01_simple.sh b/samples/pktgen/pktgen_sample01_simple.sh
new file mode 100755
index 000000000000..8c9d318c221b
--- /dev/null
+++ b/samples/pktgen/pktgen_sample01_simple.sh
@@ -0,0 +1,71 @@
+#!/bin/bash
+#
+# Simple example:
+#  * pktgen sending with single thread and single interface
+#  * flow variation via random UDP source port
+#
+basedir=`dirname $0`
+source ${basedir}/functions.sh
+root_check_run_with_sudo "$@"
+
+# Parameter parsing via include
+# - go look in parameters.sh to see which setting are avail
+# - required param is the interface "-i" stored in $DEV
+source ${basedir}/parameters.sh
+#
+# Set some default params, if they didn't get set
+[ -z "$DEST_IP" ] && DEST_IP="198.18.0.42"
+[ -z "$CLONE_SKB" ] && CLONE_SKB="0"
+# Example enforce param "-m" for dst_mac
+[ -z "$DST_MAC" ] && usage && err 2 "Must specify -m dst_mac"
+
+# Base Config
+DELAY="0"        # Zero means max speed
+COUNT="100000"   # Zero means indefinitely
+
+# Flow variation random source port between min and max
+UDP_MIN=9
+UDP_MAX=109
+
+# General cleanup everything since last run
+# (especially important if other threads were configured by other scripts)
+pg_ctrl "reset"
+
+# Add remove all other devices and add_device $DEV to thread 0
+thread=0
+pg_thread $thread "rem_device_all"
+pg_thread $thread "add_device" $DEV
+
+# How many packets to send (zero means indefinitely)
+pg_set $DEV "count $COUNT"
+
+# Reduce alloc cost by sending same SKB many times
+# - this obviously affects the randomness within the packet
+pg_set $DEV "clone_skb $CLONE_SKB"
+
+# Set packet size
+pg_set $DEV "pkt_size $PKT_SIZE"
+
+# Delay between packets (zero means max speed)
+pg_set $DEV "delay $DELAY"
+
+# Flag example disabling timestamping
+pg_set $DEV "flag NO_TIMESTAMP"
+
+# Destination
+pg_set $DEV "dst_mac $DST_MAC"
+pg_set $DEV "dst $DEST_IP"
+
+# Setup random UDP port src range
+pg_set $DEV "flag UDPSRC_RND"
+pg_set $DEV "udp_src_min $UDP_MIN"
+pg_set $DEV "udp_src_max $UDP_MAX"
+
+# start_run
+echo "Running... ctrl^C to stop" >&2
+pg_ctrl "start"
+echo "Done" >&2
+
+# Print results
+echo "Result device: $DEV"
+cat /proc/net/pktgen/$DEV
diff --git a/samples/pktgen/pktgen_sample02_multiqueue.sh b/samples/pktgen/pktgen_sample02_multiqueue.sh
new file mode 100755
index 000000000000..32467aea8e47
--- /dev/null
+++ b/samples/pktgen/pktgen_sample02_multiqueue.sh
@@ -0,0 +1,75 @@
+#!/bin/bash
+#
+# Multiqueue: Using pktgen threads for sending on multiple CPUs
+#  * adding devices to kernel threads
+#  * notice the naming scheme for keeping device names unique
+#  * nameing scheme: dev@thread_number
+#  * flow variation via random UDP source port
+#
+basedir=`dirname $0`
+source ${basedir}/functions.sh
+root_check_run_with_sudo "$@"
+#
+# Required param: -i dev in $DEV
+source ${basedir}/parameters.sh
+
+# Base Config
+DELAY="0"        # Zero means max speed
+COUNT="100000"   # Zero means indefinitely
+[ -z "$CLONE_SKB" ] && CLONE_SKB="0"
+
+# Flow variation random source port between min and max
+UDP_MIN=9
+UDP_MAX=109
+
+# (example of setting default params in your script)
+[ -z "$DEST_IP" ] && DEST_IP="198.18.0.42"
+[ -z "$DST_MAC" ] && DST_MAC="90:e2:ba:ff:ff:ff"
+
+# General cleanup everything since last run
+pg_ctrl "reset"
+
+# Threads are specified with parameter -t value in $THREADS
+for ((thread = 0; thread < $THREADS; thread++)); do
+    # The device name is extended with @name, using thread number to
+    # make then unique, but any name will do.
+    dev=${DEV}@${thread}
+
+    # Add remove all other devices and add_device $dev to thread
+    pg_thread $thread "rem_device_all"
+    pg_thread $thread "add_device" $dev
+
+    # Notice config queue to map to cpu (mirrors smp_processor_id())
+    # It is beneficial to map IRQ /proc/irq/*/smp_affinity 1:1 to CPU number
+    pg_set $dev "flag QUEUE_MAP_CPU"
+
+    # Base config of dev
+    pg_set $dev "count $COUNT"
+    pg_set $dev "clone_skb $CLONE_SKB"
+    pg_set $dev "pkt_size $PKT_SIZE"
+    pg_set $dev "delay $DELAY"
+
+    # Flag example disabling timestamping
+    pg_set $dev "flag NO_TIMESTAMP"
+
+    # Destination
+    pg_set $dev "dst_mac $DST_MAC"
+    pg_set $dev "dst $DEST_IP"
+
+    # Setup random UDP port src range
+    pg_set $dev "flag UDPSRC_RND"
+    pg_set $dev "udp_src_min $UDP_MIN"
+    pg_set $dev "udp_src_max $UDP_MAX"
+done
+
+# start_run
+echo "Running... ctrl^C to stop" >&2
+pg_ctrl "start"
+echo "Done" >&2
+
+# Print results
+for ((thread = 0; thread < $THREADS; thread++)); do
+    dev=${DEV}@${thread}
+    echo "Device: $dev"
+    cat /proc/net/pktgen/$dev | grep -A2 "Result:"
+done
diff --git a/samples/pktgen/pktgen_sample03_burst_single_flow.sh b/samples/pktgen/pktgen_sample03_burst_single_flow.sh
new file mode 100755
index 000000000000..775f5d0a1e53
--- /dev/null
+++ b/samples/pktgen/pktgen_sample03_burst_single_flow.sh
@@ -0,0 +1,82 @@
+#!/bin/bash
+#
+# Script for max single flow performance
+#  - If correctly tuned[1], single CPU 10G wirespeed small pkts is possible[2]
+#
+# Using pktgen "burst" option (use -b $N)
+#  - To boost max performance
+#  - Avail since: kernel v3.18
+#   * commit 38b2cf2982dc73 ("net: pktgen: packet bursting via skb->xmit_more")
+#  - This avoids writing the HW tailptr on every driver xmit
+#  - The performance boost is impressive, see commit and blog [2]
+#
+# Notice: On purpose generates a single (UDP) flow towards target,
+#   reason behind this is to only overload/activate a single CPU on
+#   target host.  And no randomness for pktgen also makes it faster.
+#
+# Tuning see:
+#  [1] http://netoptimizer.blogspot.dk/2014/06/pktgen-for-network-overload-testing.html
+#  [2] http://netoptimizer.blogspot.dk/2014/10/unlocked-10gbps-tx-wirespeed-smallest.html
+#
+basedir=`dirname $0`
+source ${basedir}/functions.sh
+root_check_run_with_sudo "$@"
+
+# Parameter parsing via include
+source ${basedir}/parameters.sh
+# Set some default params, if they didn't get set
+[ -z "$DEST_IP" ]   && DEST_IP="198.18.0.42"
+[ -z "$DST_MAC" ]   && DST_MAC="90:e2:ba:ff:ff:ff"
+[ -z "$BURST" ]     && BURST=32
+[ -z "$CLONE_SKB" ] && CLONE_SKB="100000"
+
+# Base Config
+DELAY="0"  # Zero means max speed
+COUNT="0"  # Zero means indefinitely
+
+# General cleanup everything since last run
+pg_ctrl "reset"
+
+# Threads are specified with parameter -t value in $THREADS
+for ((thread = 0; thread < $THREADS; thread++)); do
+    dev=${DEV}@${thread}
+
+    # Add remove all other devices and add_device $dev to thread
+    pg_thread $thread "rem_device_all"
+    pg_thread $thread "add_device" $dev
+
+    # Base config
+    pg_set $dev "flag QUEUE_MAP_CPU"
+    pg_set $dev "count $COUNT"
+    pg_set $dev "clone_skb $CLONE_SKB"
+    pg_set $dev "pkt_size $PKT_SIZE"
+    pg_set $dev "delay $DELAY"
+    pg_set $dev "flag NO_TIMESTAMP"
+
+    # Destination
+    pg_set $dev "dst_mac $DST_MAC"
+    pg_set $dev "dst $DEST_IP"
+
+    # Setup burst, for easy testing -b 0 disable bursting
+    # (internally in pktgen default and minimum burst=1)
+    if [[ ${BURST} -ne 0 ]]; then
+	pg_set $dev "burst $BURST"
+    else
+	info "$dev: Not using burst"
+    fi
+done
+
+# Run if user hits control-c
+function control_c() {
+    # Print results
+    for ((thread = 0; thread < $THREADS; thread++)); do
+	dev=${DEV}@${thread}
+	echo "Device: $dev"
+	cat /proc/net/pktgen/$dev | grep -A2 "Result:"
+    done
+}
+# trap keyboard interrupt (Ctrl-C)
+trap control_c SIGINT
+
+echo "Running... ctrl^C to stop" >&2
+pg_ctrl "start"