Merge branch 'bpf-samples-improvements'

Jakub Kicinski says:

====================
This set is next part of a quest to get rid of the bpf_load
ELF loader.  It fixes some minor issues with the samples and
starts the conversion.

First patch fixes ping invocations, ping localhost defaults
to IPv6 on modern setups. Next load_sock_ops sample is removed
and users are directed towards using bpftool directly.

Patch 4 removes the use of bpf_load from samples which don't
need the auto-attachment functionality at all.

Patch 5 improves symbol counting in libbpf, it's not currently
an issue but it will be when anyone adds a symbol with a long
name. Let's make sure that person doesn't have to spend time
scratching their head and wondering why .a and .so symbol
counts don't match.

v2: - specify prog_type where possible (Andrii).
====================

Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

samples/bpf/.gitignore

@@ -1,7 +1,6 @@
 cpustat
 fds_example
 lathist
-load_sock_ops
 lwt_len_hist
 map_perf_test
 offwaketime

samples/bpf/Makefile

@@ -40,7 +40,6 @@ 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
 hostprogs-y += xdp_redirect
 hostprogs-y += xdp_redirect_map
 hostprogs-y += xdp_redirect_cpu
@@ -60,9 +59,9 @@ LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a
 CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o
 TRACE_HELPERS := ../../tools/testing/selftests/bpf/trace_helpers.o
 
-fds_example-objs := bpf_load.o fds_example.o
+fds_example-objs := fds_example.o
-sockex1-objs := bpf_load.o sockex1_user.o
+sockex1-objs := sockex1_user.o
-sockex2-objs := bpf_load.o sockex2_user.o
+sockex2-objs := sockex2_user.o
 sockex3-objs := bpf_load.o sockex3_user.o
 tracex1-objs := bpf_load.o tracex1_user.o
 tracex2-objs := bpf_load.o tracex2_user.o
@@ -71,7 +70,6 @@ tracex4-objs := bpf_load.o tracex4_user.o
 tracex5-objs := bpf_load.o tracex5_user.o
 tracex6-objs := bpf_load.o tracex6_user.o
 tracex7-objs := bpf_load.o tracex7_user.o
-load_sock_ops-objs := bpf_load.o load_sock_ops.o
 test_probe_write_user-objs := bpf_load.o test_probe_write_user_user.o
 trace_output-objs := bpf_load.o trace_output_user.o $(TRACE_HELPERS)
 lathist-objs := bpf_load.o lathist_user.o

samples/bpf/fds_example.c

@@ -14,8 +14,8 @@
 
 #include <bpf/bpf.h>
 
+#include "bpf/libbpf.h"
 #include "bpf_insn.h"
-#include "bpf_load.h"
 #include "sock_example.h"
 
 #define BPF_F_PIN	(1 << 0)
@@ -57,10 +57,14 @@ static int bpf_prog_create(const char *object)
 		BPF_EXIT_INSN(),
 	};
 	size_t insns_cnt = sizeof(insns) / sizeof(struct bpf_insn);
+	char bpf_log_buf[BPF_LOG_BUF_SIZE];
+	struct bpf_object *obj;
+	int prog_fd;
 
 	if (object) {
-		assert(!load_bpf_file((char *)object));
+		assert(!bpf_prog_load(object, BPF_PROG_TYPE_UNSPEC,
-		return prog_fd[0];
+				      &obj, &prog_fd));
+		return prog_fd;
 	} else {
 		return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER,
 					insns, insns_cnt, "GPL", 0,

samples/bpf/load_sock_ops.c

@@ -1,97 +0,0 @@
-/* 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 <bpf/bpf.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;
-}

samples/bpf/sock_example.c

@@ -99,7 +99,7 @@ int main(void)
 {
 	FILE *f;
 
-	f = popen("ping -c5 localhost", "r");
+	f = popen("ping -4 -c5 localhost", "r");
 	(void)f;
 
 	return test_sock();

samples/bpf/sockex1_user.c

@@ -3,30 +3,33 @@
 #include <assert.h>
 #include <linux/bpf.h>
 #include <bpf/bpf.h>
-#include "bpf_load.h"
+#include "bpf/libbpf.h"
 #include "sock_example.h"
 #include <unistd.h>
 #include <arpa/inet.h>
 
 int main(int ac, char **argv)
 {
+	struct bpf_object *obj;
+	int map_fd, prog_fd;
 	char filename[256];
-	FILE *f;
 	int i, sock;
+	FILE *f;
 
 	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
 
-	if (load_bpf_file(filename)) {
+	if (bpf_prog_load(filename, BPF_PROG_TYPE_SOCKET_FILTER,
-		printf("%s", bpf_log_buf);
+			  &obj, &prog_fd))
 		return 1;
-	}
+
+	map_fd = bpf_object__find_map_fd_by_name(obj, "my_map");
 
 	sock = open_raw_sock("lo");
 
-	assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, prog_fd,
+	assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd,
-			  sizeof(prog_fd[0])) == 0);
+			  sizeof(prog_fd)) == 0);
 
-	f = popen("ping -c5 localhost", "r");
+	f = popen("ping -4 -c5 localhost", "r");
 	(void) f;
 
 	for (i = 0; i < 5; i++) {
@@ -34,13 +37,13 @@ int main(int ac, char **argv)
 		int key;
 
 		key = IPPROTO_TCP;
-		assert(bpf_map_lookup_elem(map_fd[0], &key, &tcp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd, &key, &tcp_cnt) == 0);
 
 		key = IPPROTO_UDP;
-		assert(bpf_map_lookup_elem(map_fd[0], &key, &udp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd, &key, &udp_cnt) == 0);
 
 		key = IPPROTO_ICMP;
-		assert(bpf_map_lookup_elem(map_fd[0], &key, &icmp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd, &key, &icmp_cnt) == 0);
 
 		printf("TCP %lld UDP %lld ICMP %lld bytes\n",
 		       tcp_cnt, udp_cnt, icmp_cnt);

samples/bpf/sockex2_user.c

@@ -3,7 +3,7 @@
 #include <assert.h>
 #include <linux/bpf.h>
 #include <bpf/bpf.h>
-#include "bpf_load.h"
+#include "bpf/libbpf.h"
 #include "sock_example.h"
 #include <unistd.h>
 #include <arpa/inet.h>
@@ -17,32 +17,35 @@ struct pair {
 int main(int ac, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	struct bpf_object *obj;
+	int map_fd, prog_fd;
 	char filename[256];
-	FILE *f;
 	int i, sock;
+	FILE *f;
 
 	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
 	setrlimit(RLIMIT_MEMLOCK, &r);
 
-	if (load_bpf_file(filename)) {
+	if (bpf_prog_load(filename, BPF_PROG_TYPE_SOCKET_FILTER,
-		printf("%s", bpf_log_buf);
+			  &obj, &prog_fd))
 		return 1;
-	}
+
+	map_fd = bpf_object__find_map_fd_by_name(obj, "hash_map");
 
 	sock = open_raw_sock("lo");
 
-	assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, prog_fd,
+	assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd,
-			  sizeof(prog_fd[0])) == 0);
+			  sizeof(prog_fd)) == 0);
 
-	f = popen("ping -c5 localhost", "r");
+	f = popen("ping -4 -c5 localhost", "r");
 	(void) f;
 
 	for (i = 0; i < 5; i++) {
 		int key = 0, next_key;
 		struct pair value;
 
-		while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) {
+		while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) {
-			bpf_map_lookup_elem(map_fd[0], &next_key, &value);
+			bpf_map_lookup_elem(map_fd, &next_key, &value);
 			printf("ip %s bytes %lld packets %lld\n",
 			       inet_ntoa((struct in_addr){htonl(next_key)}),
 			       value.bytes, value.packets);

samples/bpf/sockex3_user.c

@@ -58,7 +58,7 @@ int main(int argc, char **argv)
 			  sizeof(__u32)) == 0);
 
 	if (argc > 1)
-		f = popen("ping -c5 localhost", "r");
+		f = popen("ping -4 -c5 localhost", "r");
 	else
 		f = popen("netperf -l 4 localhost", "r");
 	(void) f;

samples/bpf/tcp_basertt_kern.c

@@ -7,7 +7,7 @@
  * BPF program to set base_rtt to 80us when host is running TCP-NV and
  * both hosts are in the same datacenter (as determined by IPv6 prefix).
  *
- * Use load_sock_ops to load this BPF program.
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
  */
 
 #include <uapi/linux/bpf.h>

samples/bpf/tcp_bpf.readme

@@ -8,14 +8,16 @@ a cgroupv2 and attach a bash shell to the group.
   bash
   echo $$ >> /tmp/cgroupv2/foo/cgroup.procs
 
-Anything that runs under this shell belongs to the foo cgroupv2 To load
+Anything that runs under this shell belongs to the foo cgroupv2. To load
 (attach) one of the tcp_*_kern.o programs:
 
-  ./load_sock_ops -l /tmp/cgroupv2/foo tcp_basertt_kern.o
+  bpftool prog load tcp_basertt_kern.o /sys/fs/bpf/tcp_prog
+  bpftool cgroup attach /tmp/cgroupv2/foo sock_ops pinned /sys/fs/bpf/tcp_prog
+  bpftool prog tracelog
 
-If the "-l" flag is used, the load_sock_ops program will continue to run
+"bpftool prog tracelog" will continue to run printing the BPF log buffer.
-printing the BPF log buffer. The tcp_*_kern.o programs use special print
+The tcp_*_kern.o programs use special print functions to print logging
-functions to print logging information (if enabled by the ifdef).
+information (if enabled by the ifdef).
 
 If using netperf/netserver to create traffic, you need to run them under the
 cgroupv2 to which the BPF programs are attached (i.e. under bash shell
@@ -23,4 +25,4 @@ attached to the cgroupv2).
 
 To remove (unattach) a socket_ops BPF program from a cgroupv2:
 
-  ./load_sock_ops -r /tmp/cgroupv2/foo
+  bpftool cgroup attach /tmp/cgroupv2/foo sock_ops pinned /sys/fs/bpf/tcp_prog

samples/bpf/tcp_bufs_kern.c

@@ -9,7 +9,7 @@
  * doing appropriate checks that indicate the hosts are far enough
  * away (i.e. large RTT).
  *
- * Use load_sock_ops to load this BPF program.
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
  */
 
 #include <uapi/linux/bpf.h>

samples/bpf/tcp_clamp_kern.c

@@ -9,7 +9,7 @@
  * 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.
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
  */
 
 #include <uapi/linux/bpf.h>

samples/bpf/tcp_cong_kern.c

@@ -7,7 +7,7 @@
  * 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.
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
  */
 
 #include <uapi/linux/bpf.h>

samples/bpf/tcp_iw_kern.c

@@ -9,7 +9,7 @@
  * 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.
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
  */
 
 #include <uapi/linux/bpf.h>

samples/bpf/tcp_rwnd_kern.c

@@ -8,7 +8,7 @@
  * and the first 5.5 bytes of the IPv6 addresses are not the same (in this
  * example that means both hosts are not the same datacenter).
  *
- * Use load_sock_ops to load this BPF program.
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
  */
 
 #include <uapi/linux/bpf.h>

samples/bpf/tcp_synrto_kern.c

@@ -8,7 +8,7 @@
  * and the first 5.5 bytes of the IPv6 addresses are the same (in this example
  * that means both hosts are in the same datacenter).
  *
- * Use load_sock_ops to load this BPF program.
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
  */
 
 #include <uapi/linux/bpf.h>

samples/bpf/tcp_tos_reflect_kern.c

@@ -4,7 +4,7 @@
  *
  * BPF program to automatically reflect TOS option from received syn packet
  *
- * Use load_sock_ops to load this BPF program.
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
  */
 
 #include <uapi/linux/bpf.h>

samples/bpf/tracex2_user.c

@@ -131,7 +131,7 @@ int main(int ac, char **argv)
 	signal(SIGTERM, int_exit);
 
 	/* start 'ping' in the background to have some kfree_skb events */
-	f = popen("ping -c5 localhost", "r");
+	f = popen("ping -4 -c5 localhost", "r");
 	(void) f;
 
 	/* start 'dd' in the background to have plenty of 'write' syscalls */

tools/bpf/bpftool/prog.c

@@ -1053,7 +1053,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 	j = 0;
 	while (j < old_map_fds && map_replace[j].name) {
 		i = 0;
-		bpf_map__for_each(map, obj) {
+		bpf_object__for_each_map(map, obj) {
 			if (!strcmp(bpf_map__name(map), map_replace[j].name)) {
 				map_replace[j].idx = i;
 				break;
@@ -1074,7 +1074,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 	/* Set ifindex and name reuse */
 	j = 0;
 	idx = 0;
-	bpf_map__for_each(map, obj) {
+	bpf_object__for_each_map(map, obj) {
 		if (!bpf_map__is_offload_neutral(map))
 			bpf_map__set_ifindex(map, ifindex);
 

tools/lib/bpf/Makefile

@@ -132,9 +132,9 @@ BPF_IN    := $(OUTPUT)libbpf-in.o
 LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
 VERSION_SCRIPT := libbpf.map
 
-GLOBAL_SYM_COUNT = $(shell readelf -s $(BPF_IN) | \
+GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \
 			   awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}')
-VERSIONED_SYM_COUNT = $(shell readelf -s $(OUTPUT)libbpf.so | \
+VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \
 			      grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
 
 CMD_TARGETS = $(LIB_FILE)

tools/lib/bpf/libbpf.c

@@ -2100,7 +2100,7 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
 	if (err)
 		return err;
 
-	bpf_map__for_each(map, obj) {
+	bpf_object__for_each_map(map, obj) {
 		char buf[PATH_MAX];
 		int len;
 
@@ -2147,7 +2147,7 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
 	if (!obj)
 		return -ENOENT;
 
-	bpf_map__for_each(map, obj) {
+	bpf_object__for_each_map(map, obj) {
 		char buf[PATH_MAX];
 		int len;
 
@@ -2835,7 +2835,7 @@ bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
 {
 	struct bpf_map *pos;
 
-	bpf_map__for_each(pos, obj) {
+	bpf_object__for_each_map(pos, obj) {
 		if (pos->name && !strcmp(pos->name, name))
 			return pos;
 	}
@@ -2928,7 +2928,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 			first_prog = prog;
 	}
 
-	bpf_map__for_each(map, obj) {
+	bpf_object__for_each_map(map, obj) {
 		if (!bpf_map__is_offload_neutral(map))
 			map->map_ifindex = attr->ifindex;
 	}

tools/lib/bpf/libbpf.h

@@ -278,10 +278,11 @@ bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset);
 
 LIBBPF_API struct bpf_map *
 bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
-#define bpf_map__for_each(pos, obj)		\
+#define bpf_object__for_each_map(pos, obj)		\
 	for ((pos) = bpf_map__next(NULL, (obj));	\
 	     (pos) != NULL;				\
 	     (pos) = bpf_map__next((pos), (obj)))
+#define bpf_map__for_each bpf_object__for_each_map
 
 LIBBPF_API struct bpf_map *
 bpf_map__prev(struct bpf_map *map, struct bpf_object *obj);

tools/perf/util/bpf-loader.c

@@ -1489,7 +1489,7 @@ apply_obj_config_object(struct bpf_object *obj)
 	struct bpf_map *map;
 	int err;
 
-	bpf_map__for_each(map, obj) {
+	bpf_object__for_each_map(map, obj) {
 		err = apply_obj_config_map(map);
 		if (err)
 			return err;
@@ -1513,7 +1513,7 @@ int bpf__apply_obj_config(void)
 
 #define bpf__for_each_map(pos, obj, objtmp)	\
 	bpf_object__for_each_safe(obj, objtmp)	\
-		bpf_map__for_each(pos, obj)
+		bpf_object__for_each_map(pos, obj)
 
 #define bpf__for_each_map_named(pos, obj, objtmp, name)	\
 	bpf__for_each_map(pos, obj, objtmp) 		\

tools/testing/selftests/bpf/test_libbpf_open.c

@@ -67,7 +67,7 @@ int test_walk_maps(struct bpf_object *obj, bool verbose)
 	struct bpf_map *map;
 	int cnt = 0;
 
-	bpf_map__for_each(map, obj) {
+	bpf_object__for_each_map(map, obj) {
 		cnt++;
 		if (verbose)
 			printf("Map (count:%d) name: %s\n", cnt,