Merge branch 'perf/urgent' into perf/core, to pick up latest fixes and refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

27 files changed, 960 insertions, 288 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 6c7468eb3684..87246be6feb8 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -36,6 +36,7 @@ hostprogs-y += lwt_len_hist
 hostprogs-y += xdp_tx_iptunnel
 hostprogs-y += test_map_in_map
 hostprogs-y += per_socket_stats_example
+hostprogs-y += load_sock_ops
 
 # Libbpf dependencies
 LIBBPF := ../../tools/lib/bpf/bpf.o
@@ -52,6 +53,7 @@ tracex3-objs := bpf_load.o $(LIBBPF) tracex3_user.o
 tracex4-objs := bpf_load.o $(LIBBPF) tracex4_user.o
 tracex5-objs := bpf_load.o $(LIBBPF) tracex5_user.o
 tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o
+load_sock_ops-objs := bpf_load.o $(LIBBPF) load_sock_ops.o
 test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o
 trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o
 lathist-objs := bpf_load.o $(LIBBPF) lathist_user.o
@@ -111,6 +113,12 @@ always += lwt_len_hist_kern.o
 always += xdp_tx_iptunnel_kern.o
 always += test_map_in_map_kern.o
 always += cookie_uid_helper_example.o
+always += tcp_synrto_kern.o
+always += tcp_rwnd_kern.o
+always += tcp_bufs_kern.o
+always += tcp_cong_kern.o
+always += tcp_iw_kern.o
+always += tcp_clamp_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -130,6 +138,7 @@ HOSTLOADLIBES_tracex4 += -lelf -lrt
 HOSTLOADLIBES_tracex5 += -lelf
 HOSTLOADLIBES_tracex6 += -lelf
 HOSTLOADLIBES_test_cgrp2_sock2 += -lelf
+HOSTLOADLIBES_load_sock_ops += -lelf
 HOSTLOADLIBES_test_probe_write_user += -lelf
 HOSTLOADLIBES_trace_output += -lelf -lrt
 HOSTLOADLIBES_lathist += -lelf
@@ -160,6 +169,17 @@ clean:
 	$(MAKE) -C ../../ M=$(CURDIR) clean
 	@rm -f *~
 
+$(obj)/syscall_nrs.s:	$(src)/syscall_nrs.c
+	$(call if_changed_dep,cc_s_c)
+
+$(obj)/syscall_nrs.h:	$(obj)/syscall_nrs.s FORCE
+	$(call filechk,offsets,__SYSCALL_NRS_H__)
+
+clean-files += syscall_nrs.h
+
+FORCE:
+
+
 # Verify LLVM compiler tools are available and bpf target is supported by llc
 .PHONY: verify_cmds verify_target_bpf $(CLANG) $(LLC)
 
@@ -180,11 +200,14 @@ verify_target_bpf: verify_cmds
 
 $(src)/*.c: verify_target_bpf
 
+$(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h
+
 # asm/sysreg.h - inline assembly used by it is incompatible with llvm.
 # But, there is no easy way to fix it, so just exclude it since it is
 # useless for BPF samples.
 $(obj)/%.o: $(src)/%.c
-	$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \
+	$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
+		-I$(srctree)/tools/testing/selftests/bpf/ \
 		-D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
 		-Wno-compare-distinct-pointer-types \
 		-Wno-gnu-variable-sized-type-not-at-end \
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
deleted file mode 100644
index 9a9c95f2c9fb..000000000000
--- a/samples/bpf/bpf_helpers.h
+++ /dev/null
@@ -1,181 +0,0 @@
-#ifndef __BPF_HELPERS_H
-#define __BPF_HELPERS_H
-
-/* helper macro to place programs, maps, license in
- * different sections in elf_bpf file. Section names
- * are interpreted by elf_bpf loader
- */
-#define SEC(NAME) __attribute__((section(NAME), used))
-
-/* helper functions called from eBPF programs written in C */
-static void *(*bpf_map_lookup_elem)(void *map, void *key) =
-	(void *) BPF_FUNC_map_lookup_elem;
-static int (*bpf_map_update_elem)(void *map, void *key, void *value,
-				  unsigned long long flags) =
-	(void *) BPF_FUNC_map_update_elem;
-static int (*bpf_map_delete_elem)(void *map, void *key) =
-	(void *) BPF_FUNC_map_delete_elem;
-static int (*bpf_probe_read)(void *dst, int size, void *unsafe_ptr) =
-	(void *) BPF_FUNC_probe_read;
-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;
-static int (*bpf_perf_event_read)(void *map, int index) =
-	(void *) BPF_FUNC_perf_event_read;
-static int (*bpf_clone_redirect)(void *ctx, int ifindex, int flags) =
-	(void *) BPF_FUNC_clone_redirect;
-static int (*bpf_redirect)(int ifindex, int flags) =
-	(void *) BPF_FUNC_redirect;
-static int (*bpf_perf_event_output)(void *ctx, void *map,
-				    unsigned long long flags, void *data,
-				    int size) =
-	(void *) BPF_FUNC_perf_event_output;
-static int (*bpf_get_stackid)(void *ctx, void *map, int flags) =
-	(void *) BPF_FUNC_get_stackid;
-static int (*bpf_probe_write_user)(void *dst, void *src, int size) =
-	(void *) BPF_FUNC_probe_write_user;
-static int (*bpf_current_task_under_cgroup)(void *map, int index) =
-	(void *) BPF_FUNC_current_task_under_cgroup;
-static int (*bpf_skb_get_tunnel_key)(void *ctx, void *key, int size, int flags) =
-	(void *) BPF_FUNC_skb_get_tunnel_key;
-static int (*bpf_skb_set_tunnel_key)(void *ctx, void *key, int size, int flags) =
-	(void *) BPF_FUNC_skb_set_tunnel_key;
-static int (*bpf_skb_get_tunnel_opt)(void *ctx, void *md, int size) =
-	(void *) BPF_FUNC_skb_get_tunnel_opt;
-static int (*bpf_skb_set_tunnel_opt)(void *ctx, void *md, int size) =
-	(void *) BPF_FUNC_skb_set_tunnel_opt;
-static unsigned long long (*bpf_get_prandom_u32)(void) =
-	(void *) BPF_FUNC_get_prandom_u32;
-static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
-	(void *) BPF_FUNC_xdp_adjust_head;
-
-/* llvm builtin functions that eBPF C program may use to
- * emit BPF_LD_ABS and BPF_LD_IND instructions
- */
-struct sk_buff;
-unsigned long long load_byte(void *skb,
-			     unsigned long long off) asm("llvm.bpf.load.byte");
-unsigned long long load_half(void *skb,
-			     unsigned long long off) asm("llvm.bpf.load.half");
-unsigned long long load_word(void *skb,
-			     unsigned long long off) asm("llvm.bpf.load.word");
-
-/* a helper structure used by eBPF C program
- * to describe map attributes to elf_bpf loader
- */
-struct bpf_map_def {
-	unsigned int type;
-	unsigned int key_size;
-	unsigned int value_size;
-	unsigned int max_entries;
-	unsigned int map_flags;
-	unsigned int inner_map_idx;
-};
-
-static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
-	(void *) BPF_FUNC_skb_load_bytes;
-static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) =
-	(void *) BPF_FUNC_skb_store_bytes;
-static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flags) =
-	(void *) BPF_FUNC_l3_csum_replace;
-static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) =
-	(void *) BPF_FUNC_l4_csum_replace;
-static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
-	(void *) BPF_FUNC_skb_under_cgroup;
-static int (*bpf_skb_change_head)(void *, int len, int flags) =
-	(void *) BPF_FUNC_skb_change_head;
-
-#if defined(__x86_64__)
-
-#define PT_REGS_PARM1(x) ((x)->di)
-#define PT_REGS_PARM2(x) ((x)->si)
-#define PT_REGS_PARM3(x) ((x)->dx)
-#define PT_REGS_PARM4(x) ((x)->cx)
-#define PT_REGS_PARM5(x) ((x)->r8)
-#define PT_REGS_RET(x) ((x)->sp)
-#define PT_REGS_FP(x) ((x)->bp)
-#define PT_REGS_RC(x) ((x)->ax)
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->ip)
-
-#elif defined(__s390x__)
-
-#define PT_REGS_PARM1(x) ((x)->gprs[2])
-#define PT_REGS_PARM2(x) ((x)->gprs[3])
-#define PT_REGS_PARM3(x) ((x)->gprs[4])
-#define PT_REGS_PARM4(x) ((x)->gprs[5])
-#define PT_REGS_PARM5(x) ((x)->gprs[6])
-#define PT_REGS_RET(x) ((x)->gprs[14])
-#define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->gprs[2])
-#define PT_REGS_SP(x) ((x)->gprs[15])
-#define PT_REGS_IP(x) ((x)->psw.addr)
-
-#elif defined(__aarch64__)
-
-#define PT_REGS_PARM1(x) ((x)->regs[0])
-#define PT_REGS_PARM2(x) ((x)->regs[1])
-#define PT_REGS_PARM3(x) ((x)->regs[2])
-#define PT_REGS_PARM4(x) ((x)->regs[3])
-#define PT_REGS_PARM5(x) ((x)->regs[4])
-#define PT_REGS_RET(x) ((x)->regs[30])
-#define PT_REGS_FP(x) ((x)->regs[29]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->regs[0])
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->pc)
-
-#elif defined(__powerpc__)
-
-#define PT_REGS_PARM1(x) ((x)->gpr[3])
-#define PT_REGS_PARM2(x) ((x)->gpr[4])
-#define PT_REGS_PARM3(x) ((x)->gpr[5])
-#define PT_REGS_PARM4(x) ((x)->gpr[6])
-#define PT_REGS_PARM5(x) ((x)->gpr[7])
-#define PT_REGS_RC(x) ((x)->gpr[3])
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->nip)
-
-#elif defined(__sparc__)
-
-#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
-#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2])
-#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3])
-#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4])
-#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
-#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
-#if defined(__arch64__)
-#define PT_REGS_IP(x) ((x)->tpc)
-#else
-#define PT_REGS_IP(x) ((x)->pc)
-#endif
-
-#endif
-
-#ifdef __powerpc__
-#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
-#define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
-#elif defined(__sparc__)
-#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
-#define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
-#else
-#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({				\
-		bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
-#define BPF_KRETPROBE_READ_RET_IP(ip, ctx)	({				\
-		bpf_probe_read(&(ip), sizeof(ip),				\
-				(void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
-#endif
-
-#endif
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 74456b3eb89a..899f40310bc3 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -64,6 +64,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 	bool is_perf_event = strncmp(event, "perf_event", 10) == 0;
 	bool is_cgroup_skb = strncmp(event, "cgroup/skb", 10) == 0;
 	bool is_cgroup_sk = strncmp(event, "cgroup/sock", 11) == 0;
+	bool is_sockops = strncmp(event, "sockops", 7) == 0;
 	size_t insns_cnt = size / sizeof(struct bpf_insn);
 	enum bpf_prog_type prog_type;
 	char buf[256];
@@ -89,6 +90,8 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 		prog_type = BPF_PROG_TYPE_CGROUP_SKB;
 	} else if (is_cgroup_sk) {
 		prog_type = BPF_PROG_TYPE_CGROUP_SOCK;
+	} else if (is_sockops) {
+		prog_type = BPF_PROG_TYPE_SOCK_OPS;
 	} else {
 		printf("Unknown event '%s'\n", event);
 		return -1;
@@ -106,8 +109,11 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 	if (is_xdp || is_perf_event || is_cgroup_skb || is_cgroup_sk)
 		return 0;
 
-	if (is_socket) {
-		event += 6;
+	if (is_socket || is_sockops) {
+		if (is_socket)
+			event += 6;
+		else
+			event += 7;
 		if (*event != '/')
 			return 0;
 		event++;
@@ -516,16 +522,18 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map)
 		processed_sec[maps_shndx] = true;
 	}
 
-	/* load programs that need map fixup (relocations) */
+	/* process all relo sections, and rewrite bpf insns for maps */
 	for (i = 1; i < ehdr.e_shnum; i++) {
 		if (processed_sec[i])
 			continue;
 
 		if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
 			continue;
+
 		if (shdr.sh_type == SHT_REL) {
 			struct bpf_insn *insns;
 
+			/* locate prog sec that need map fixup (relocations) */
 			if (get_sec(elf, shdr.sh_info, &ehdr, &shname_prog,
 				    &shdr_prog, &data_prog))
 				continue;
@@ -535,26 +543,15 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map)
 				continue;
 
 			insns = (struct bpf_insn *) data_prog->d_buf;
-
-			processed_sec[shdr.sh_info] = true;
-			processed_sec[i] = true;
+			processed_sec[i] = true; /* relo section */
 
 			if (parse_relo_and_apply(data, symbols, &shdr, insns,
 						 map_data, nr_maps))
 				continue;
-
-			if (memcmp(shname_prog, "kprobe/", 7) == 0 ||
-			    memcmp(shname_prog, "kretprobe/", 10) == 0 ||
-			    memcmp(shname_prog, "tracepoint/", 11) == 0 ||
-			    memcmp(shname_prog, "xdp", 3) == 0 ||
-			    memcmp(shname_prog, "perf_event", 10) == 0 ||
-			    memcmp(shname_prog, "socket", 6) == 0 ||
-			    memcmp(shname_prog, "cgroup/", 7) == 0)
-				load_and_attach(shname_prog, insns, data_prog->d_size);
 		}
 	}
 
-	/* load programs that don't use maps */
+	/* load programs */
 	for (i = 1; i < ehdr.e_shnum; i++) {
 
 		if (processed_sec[i])
@@ -569,8 +566,13 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map)
 		    memcmp(shname, "xdp", 3) == 0 ||
 		    memcmp(shname, "perf_event", 10) == 0 ||
 		    memcmp(shname, "socket", 6) == 0 ||
-		    memcmp(shname, "cgroup/", 7) == 0)
-			load_and_attach(shname, data->d_buf, data->d_size);
+		    memcmp(shname, "cgroup/", 7) == 0 ||
+		    memcmp(shname, "sockops", 7) == 0) {
+			ret = load_and_attach(shname, data->d_buf,
+					      data->d_size);
+			if (ret != 0)
+				goto done;
+		}
 	}
 
 	ret = 0;
diff --git a/samples/bpf/load_sock_ops.c b/samples/bpf/load_sock_ops.c
new file mode 100644
index 000000000000..e5da6cf71a3e
--- /dev/null
+++ b/samples/bpf/load_sock_ops.c
@@ -0,0 +1,97 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * 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 <stdlib.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+#include <unistd.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/unistd.h>
+
+static void usage(char *pname)
+{
+	printf("USAGE:\n  %s [-l] <cg-path> <prog filename>\n", pname);
+	printf("\tLoad and attach a sock_ops program to the specified "
+	       "cgroup\n");
+	printf("\tIf \"-l\" is used, the program will continue to run\n");
+	printf("\tprinting the BPF log buffer\n");
+	printf("\tIf the specified filename does not end in \".o\", it\n");
+	printf("\tappends \"_kern.o\" to the name\n");
+	printf("\n");
+	printf("  %s -r <cg-path>\n", pname);
+	printf("\tDetaches the currently attached sock_ops program\n");
+	printf("\tfrom the specified cgroup\n");
+	printf("\n");
+	exit(1);
+}
+
+int main(int argc, char **argv)
+{
+	int logFlag = 0;
+	int error = 0;
+	char *cg_path;
+	char fn[500];
+	char *prog;
+	int cg_fd;
+
+	if (argc < 3)
+		usage(argv[0]);
+
+	if (!strcmp(argv[1], "-r")) {
+		cg_path = argv[2];
+		cg_fd = open(cg_path, O_DIRECTORY, O_RDONLY);
+		error = bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+		if (error) {
+			printf("ERROR: bpf_prog_detach: %d (%s)\n",
+			       error, strerror(errno));
+			return 2;
+		}
+		return 0;
+	} else if (!strcmp(argv[1], "-h")) {
+		usage(argv[0]);
+	} else if (!strcmp(argv[1], "-l")) {
+		logFlag = 1;
+		if (argc < 4)
+			usage(argv[0]);
+	}
+
+	prog = argv[argc - 1];
+	cg_path = argv[argc - 2];
+	if (strlen(prog) > 480) {
+		fprintf(stderr, "ERROR: program name too long (> 480 chars)\n");
+		return 3;
+	}
+	cg_fd = open(cg_path, O_DIRECTORY, O_RDONLY);
+
+	if (!strcmp(prog + strlen(prog)-2, ".o"))
+		strcpy(fn, prog);
+	else
+		sprintf(fn, "%s_kern.o", prog);
+	if (logFlag)
+		printf("loading bpf file:%s\n", fn);
+	if (load_bpf_file(fn)) {
+		printf("ERROR: load_bpf_file failed for: %s\n", fn);
+		printf("%s", bpf_log_buf);
+		return 4;
+	}
+	if (logFlag)
+		printf("TCP BPF Loaded %s\n", fn);
+
+	error = bpf_prog_attach(prog_fd[0], cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+	if (error) {
+		printf("ERROR: bpf_prog_attach: %d (%s)\n",
+		       error, strerror(errno));
+		return 5;
+	} else if (logFlag) {
+		read_trace_pipe();
+	}
+
+	return error;
+}
diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c
index b5524d417eb5..877ecf8fc5ac 100644
--- a/samples/bpf/sockex3_user.c
+++ b/samples/bpf/sockex3_user.c
@@ -8,6 +8,10 @@
 #include <arpa/inet.h>
 #include <sys/resource.h>
 
+#define PARSE_IP 3
+#define PARSE_IP_PROG_FD (prog_fd[0])
+#define PROG_ARRAY_FD (map_fd[0])
+
 struct bpf_flow_keys {
 	__be32 src;
 	__be32 dst;
@@ -28,7 +32,9 @@ int main(int argc, char **argv)
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	char filename[256];
 	FILE *f;
-	int i, sock;
+	int i, sock, err, id, key = PARSE_IP;
+	struct bpf_prog_info info = {};
+	uint32_t info_len = sizeof(info);
 
 	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
 	setrlimit(RLIMIT_MEMLOCK, &r);
@@ -38,6 +44,13 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
+	/* Test fd array lookup which returns the id of the bpf_prog */
+	err = bpf_obj_get_info_by_fd(PARSE_IP_PROG_FD, &info, &info_len);
+	assert(!err);
+	err = bpf_map_lookup_elem(PROG_ARRAY_FD, &key, &id);
+	assert(!err);
+	assert(id == info.id);
+
 	sock = open_raw_sock("lo");
 
 	assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd[4],
diff --git a/samples/bpf/syscall_nrs.c b/samples/bpf/syscall_nrs.c
new file mode 100644
index 000000000000..ce2a30b11248
--- /dev/null
+++ b/samples/bpf/syscall_nrs.c
@@ -0,0 +1,12 @@
+#include <uapi/linux/unistd.h>
+#include <linux/kbuild.h>
+
+#define SYSNR(_NR) DEFINE(SYS ## _NR, _NR)
+
+void syscall_defines(void)
+{
+	COMMENT("Linux system call numbers.");
+	SYSNR(__NR_write);
+	SYSNR(__NR_read);
+	SYSNR(__NR_mmap);
+}
diff --git a/samples/bpf/tcp_bufs_kern.c b/samples/bpf/tcp_bufs_kern.c
new file mode 100644
index 000000000000..ee83bbabd17c
--- /dev/null
+++ b/samples/bpf/tcp_bufs_kern.c
@@ -0,0 +1,86 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * 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.
+ *
+ * BPF program to set initial receive window to 40 packets and send
+ * and receive buffers to 1.5MB. This would usually be done after
+ * doing appropriate checks that indicate the hosts are far enough
+ * away (i.e. large RTT).
+ *
+ * Use load_sock_ops to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define DEBUG 1
+
+#define bpf_printk(fmt, ...)					\
+({								\
+	       char ____fmt[] = fmt;				\
+	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				##__VA_ARGS__);			\
+})
+
+SEC("sockops")
+int bpf_bufs(struct bpf_sock_ops *skops)
+{
+	int bufsize = 1500000;
+	int rwnd_init = 40;
+	int rv = 0;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) != 55601 &&
+	    skops->local_port != 55601)
+		return -1;
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+
+	/* Usually there would be a check to insure the hosts are far
+	 * from each other so it makes sense to increase buffer sizes
+	 */
+	switch (op) {
+	case BPF_SOCK_OPS_RWND_INIT:
+		rv = rwnd_init;
+		break;
+	case BPF_SOCK_OPS_TCP_CONNECT_CB:
+		/* Set sndbuf and rcvbuf of active connections */
+		rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize,
+				    sizeof(bufsize));
+		rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF,
+					     &bufsize, sizeof(bufsize));
+		break;
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+		/* Nothing to do */
+		break;
+	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		/* Set sndbuf and rcvbuf of passive connections */
+		rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize,
+				    sizeof(bufsize));
+		rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF,
+					     &bufsize, sizeof(bufsize));
+		break;
+	default:
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/tcp_clamp_kern.c b/samples/bpf/tcp_clamp_kern.c
new file mode 100644
index 000000000000..d68eadd9ca2d
--- /dev/null
+++ b/samples/bpf/tcp_clamp_kern.c
@@ -0,0 +1,102 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * 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.
+ *
+ * Sample BPF program to set send and receive buffers to 150KB, sndcwnd clamp
+ * to 100 packets and SYN and SYN_ACK RTOs to 10ms when both hosts are within
+ * the same datacenter. For his example, we assume they are within the same
+ * datacenter when the first 5.5 bytes of their IPv6 addresses are the same.
+ *
+ * Use load_sock_ops to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define DEBUG 1
+
+#define bpf_printk(fmt, ...)					\
+({								\
+	       char ____fmt[] = fmt;				\
+	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				##__VA_ARGS__);			\
+})
+
+SEC("sockops")
+int bpf_clamp(struct bpf_sock_ops *skops)
+{
+	int bufsize = 150000;
+	int to_init = 10;
+	int clamp = 100;
+	int rv = 0;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) != 55601 && skops->local_port != 55601)
+		return -1;
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Check that both hosts are within same datacenter. For this example
+	 * it is the case when the first 5.5 bytes of their IPv6 addresses are
+	 * the same.
+	 */
+	if (skops->family == AF_INET6 &&
+	    skops->local_ip6[0] == skops->remote_ip6[0] &&
+	    (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) ==
+	    (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000)) {
+		switch (op) {
+		case BPF_SOCK_OPS_TIMEOUT_INIT:
+			rv = to_init;
+			break;
+		case BPF_SOCK_OPS_TCP_CONNECT_CB:
+			/* Set sndbuf and rcvbuf of active connections */
+			rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF,
+					    &bufsize, sizeof(bufsize));
+			rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET,
+						      SO_RCVBUF, &bufsize,
+						      sizeof(bufsize));
+			break;
+		case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+			rv = bpf_setsockopt(skops, SOL_TCP,
+					    TCP_BPF_SNDCWND_CLAMP,
+					    &clamp, sizeof(clamp));
+			break;
+		case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+			/* Set sndbuf and rcvbuf of passive connections */
+			rv = bpf_setsockopt(skops, SOL_TCP,
+					    TCP_BPF_SNDCWND_CLAMP,
+					    &clamp, sizeof(clamp));
+			rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET,
+						      SO_SNDBUF, &bufsize,
+						      sizeof(bufsize));
+			rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET,
+						      SO_RCVBUF, &bufsize,
+						      sizeof(bufsize));
+			break;
+		default:
+			rv = -1;
+		}
+	} else {
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/tcp_cong_kern.c b/samples/bpf/tcp_cong_kern.c
new file mode 100644
index 000000000000..dac15bce1fa9
--- /dev/null
+++ b/samples/bpf/tcp_cong_kern.c
@@ -0,0 +1,83 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * 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.
+ *
+ * BPF program to set congestion control to dctcp when both hosts are
+ * in the same datacenter (as deteremined by IPv6 prefix).
+ *
+ * Use load_sock_ops to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define DEBUG 1
+
+#define bpf_printk(fmt, ...)					\
+({								\
+	       char ____fmt[] = fmt;				\
+	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				##__VA_ARGS__);			\
+})
+
+SEC("sockops")
+int bpf_cong(struct bpf_sock_ops *skops)
+{
+	char cong[] = "dctcp";
+	int rv = 0;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) != 55601 &&
+	    skops->local_port != 55601)
+		return -1;
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Check if both hosts are in the same datacenter. For this
+	 * example they are if the 1st 5.5 bytes in the IPv6 address
+	 * are the same.
+	 */
+	if (skops->family == AF_INET6 &&
+	    skops->local_ip6[0] == skops->remote_ip6[0] &&
+	    (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) ==
+	    (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000)) {
+		switch (op) {
+		case BPF_SOCK_OPS_NEEDS_ECN:
+			rv = 1;
+			break;
+		case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+			rv = bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION,
+					    cong, sizeof(cong));
+			break;
+		case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+			rv = bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION,
+					    cong, sizeof(cong));
+			break;
+		default:
+			rv = -1;
+		}
+	} else {
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/tcp_iw_kern.c b/samples/bpf/tcp_iw_kern.c
new file mode 100644
index 000000000000..23c5122ef819
--- /dev/null
+++ b/samples/bpf/tcp_iw_kern.c
@@ -0,0 +1,88 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * 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.
+ *
+ * BPF program to set initial congestion window and initial receive
+ * window to 40 packets and send and receive buffers to 1.5MB. This
+ * would usually be done after doing appropriate checks that indicate
+ * the hosts are far enough away (i.e. large RTT).
+ *</