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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-01-22

The following pull-request contains BPF updates for your *net-next* tree.

We've added 92 non-merge commits during the last 16 day(s) which contain
a total of 320 files changed, 7532 insertions(+), 1448 deletions(-).

The main changes are:

1) function by function verification and program extensions from Alexei.

2) massive cleanup of selftests/bpf from Toke and Andrii.

3) batched bpf map operations from Brian and Yonghong.

4) tcp congestion control in bpf from Martin.

5) bulking for non-map xdp_redirect form Toke.

6) bpf_send_signal_thread helper from Yonghong.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

194 files changed, 4391 insertions, 715 deletions

diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index 5535650800ab..f897eeeb0b4f 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -38,7 +38,7 @@ FEATURE_TESTS = libbfd disassembler-four-args
 FEATURE_DISPLAY = libbfd disassembler-four-args
 
 check_feat := 1
-NON_CHECK_FEAT_TARGETS := clean bpftool_clean
+NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean
 ifdef MAKECMDGOALS
 ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),)
   check_feat := 0
@@ -73,7 +73,7 @@ $(OUTPUT)%.lex.o: $(OUTPUT)%.lex.c
 
 PROGS = $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg $(OUTPUT)bpf_asm
 
-all: $(PROGS) bpftool
+all: $(PROGS) bpftool runqslower
 
 $(OUTPUT)bpf_jit_disasm: CFLAGS += -DPACKAGE='bpf_jit_disasm'
 $(OUTPUT)bpf_jit_disasm: $(OUTPUT)bpf_jit_disasm.o
@@ -89,7 +89,7 @@ $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c
 $(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c
 $(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c
 
-clean: bpftool_clean
+clean: bpftool_clean runqslower_clean
 	$(call QUIET_CLEAN, bpf-progs)
 	$(Q)$(RM) -r -- $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \
 	       $(OUTPUT)bpf_asm $(OUTPUT)bpf_exp.yacc.* $(OUTPUT)bpf_exp.lex.*
@@ -97,7 +97,7 @@ clean: bpftool_clean
 	$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf
 	$(Q)$(RM) -r -- $(OUTPUT)feature
 
-install: $(PROGS) bpftool_install
+install: $(PROGS) bpftool_install runqslower_install
 	$(call QUIET_INSTALL, bpf_jit_disasm)
 	$(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/bin
 	$(Q)$(INSTALL) $(OUTPUT)bpf_jit_disasm $(DESTDIR)$(prefix)/bin/bpf_jit_disasm
@@ -115,4 +115,14 @@ bpftool_install:
 bpftool_clean:
 	$(call descend,bpftool,clean)
 
-.PHONY: all install clean bpftool bpftool_install bpftool_clean
+runqslower:
+	$(call descend,runqslower)
+
+runqslower_install:
+	$(call descend,runqslower,install)
+
+runqslower_clean:
+	$(call descend,runqslower,clean)
+
+.PHONY: all install clean bpftool bpftool_install bpftool_clean \
+	runqslower runqslower_install runqslower_clean
diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
index 86a87da97d0b..94d91322895a 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
@@ -196,7 +196,7 @@ and global variables.
   #define __EXAMPLE_SKEL_H__
 
   #include <stdlib.h>
-  #include <libbpf.h>
+  #include <bpf/libbpf.h>
 
   struct example {
   	struct bpf_object_skeleton *skeleton;
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 39bc6f0f4f0b..c4e810335810 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -45,7 +45,7 @@ CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \
 	-I$(srctree)/kernel/bpf/ \
 	-I$(srctree)/tools/include \
 	-I$(srctree)/tools/include/uapi \
-	-I$(srctree)/tools/lib/bpf \
+	-I$(srctree)/tools/lib \
 	-I$(srctree)/tools/perf
 CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"'
 ifneq ($(EXTRA_CFLAGS),)
diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index e5bc97b71ceb..4ba90d81b6a1 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -8,15 +8,15 @@
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
 #include <linux/btf.h>
 #include <linux/hashtable.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
 
-#include "btf.h"
 #include "json_writer.h"
 #include "main.h"
 
@@ -370,6 +370,10 @@ static int dump_btf_c(const struct btf *btf,
 	if (IS_ERR(d))
 		return PTR_ERR(d);
 
+	printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n");
+	printf("#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record)\n");
+	printf("#endif\n\n");
+
 	if (root_type_cnt) {
 		for (i = 0; i < root_type_cnt; i++) {
 			err = btf_dump__dump_type(d, root_type_ids[i]);
@@ -386,6 +390,10 @@ static int dump_btf_c(const struct btf *btf,
 		}
 	}
 
+	printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n");
+	printf("#pragma clang attribute pop\n");
+	printf("#endif\n");
+
 done:
 	btf_dump__free(d);
 	return err;
@@ -524,7 +532,7 @@ static int do_dump(int argc, char **argv)
 		if (IS_ERR(btf)) {
 			err = PTR_ERR(btf);
 			btf = NULL;
-			p_err("failed to load BTF from %s: %s", 
+			p_err("failed to load BTF from %s: %s",
 			      *argv, strerror(err));
 			goto done;
 		}
diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index 397e5716ab6d..01cc52b834fa 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -8,8 +8,8 @@
 #include <linux/bitops.h>
 #include <linux/btf.h>
 #include <linux/err.h>
+#include <bpf/btf.h>
 
-#include "btf.h"
 #include "json_writer.h"
 #include "main.h"
 
diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index 2f017caa678d..62c6a1d7cd18 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -14,7 +14,7 @@
 #include <sys/types.h>
 #include <unistd.h>
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 #include "main.h"
 
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 88264abaa738..b75b8ec5469c 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -20,8 +20,8 @@
 #include <sys/stat.h>
 #include <sys/vfs.h>
 
-#include <bpf.h>
-#include <libbpf.h> /* libbpf_num_possible_cpus */
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
 
 #include "main.h"
 
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index 03bdc5b3ac49..446ba891f1e2 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -12,8 +12,8 @@
 #include <linux/filter.h>
 #include <linux/limits.h>
 
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 #include <zlib.h>
 
 #include "main.h"
@@ -572,6 +572,18 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type,
 		printf("\n");
 }
 
+static void
+probe_large_insn_limit(const char *define_prefix, __u32 ifindex)
+{
+	bool res;
+
+	res = bpf_probe_large_insn_limit(ifindex);
+	print_bool_feature("have_large_insn_limit",
+			   "Large program size limit",
+			   "HAVE_LARGE_INSN_LIMIT",
+			   res, define_prefix);
+}
+
 static int do_probe(int argc, char **argv)
 {
 	enum probe_component target = COMPONENT_UNSPEC;
@@ -724,6 +736,12 @@ static int do_probe(int argc, char **argv)
 		probe_helpers_for_progtype(i, supported_types[i],
 					   define_prefix, ifindex);
 
+	print_end_then_start_section("misc",
+				     "Scanning miscellaneous eBPF features...",
+				     "/*** eBPF misc features ***/",
+				     define_prefix);
+	probe_large_insn_limit(define_prefix, ifindex);
+
 exit_close_json:
 	if (json_output) {
 		/* End current "section" of probes */
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 7ce09a9a6999..f8113b3646f5 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -12,15 +12,15 @@
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/mman.h>
 #include <unistd.h>
+#include <bpf/btf.h>
 
-#include "btf.h"
-#include "libbpf_internal.h"
+#include "bpf/libbpf_internal.h"
 #include "json_writer.h"
 #include "main.h"
 
@@ -333,7 +333,7 @@ static int do_skeleton(int argc, char **argv)
 		#define %2$s						    \n\
 									    \n\
 		#include <stdlib.h>					    \n\
-		#include <libbpf.h>					    \n\
+		#include <bpf/libbpf.h>					    \n\
 									    \n\
 		struct %1$s {						    \n\
 			struct bpf_object_skeleton *skeleton;		    \n\
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index bfed711258ce..f7f5885aa3ba 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -24,7 +24,7 @@
 #include <dis-asm.h>
 #include <sys/stat.h>
 #include <limits.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
 
 #include "json_writer.h"
 #include "main.h"
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 1fe91c558508..6d41bbfc6459 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -9,8 +9,8 @@
 #include <stdlib.h>
 #include <string.h>
 
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 
 #include "main.h"
 
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index c01f76fa6876..e6c85680b34d 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -15,9 +15,9 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 
-#include <bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
 
-#include "btf.h"
 #include "json_writer.h"
 #include "main.h"
 
@@ -48,6 +48,7 @@ const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_QUEUE]			= "queue",
 	[BPF_MAP_TYPE_STACK]			= "stack",
 	[BPF_MAP_TYPE_SK_STORAGE]		= "sk_storage",
+	[BPF_MAP_TYPE_STRUCT_OPS]		= "struct_ops",
 };
 
 const size_t map_type_name_size = ARRAY_SIZE(map_type_name);
@@ -251,6 +252,7 @@ static int do_dump_btf(const struct btf_dumper *d,
 		       struct bpf_map_info *map_info, void *key,
 		       void *value)
 {
+	__u32 value_id;
 	int ret;
 
 	/* start of key-value pair */
@@ -264,9 +266,12 @@ static int do_dump_btf(const struct btf_dumper *d,
 			goto err_end_obj;
 	}
 
+	value_id = map_info->btf_vmlinux_value_type_id ?
+		: map_info->btf_value_type_id;
+
 	if (!map_is_per_cpu(map_info->type)) {
 		jsonw_name(d->jw, "value");
-		ret = btf_dumper_type(d, map_info->btf_value_type_id, value);
+		ret = btf_dumper_type(d, value_id, value);
 	} else {
 		unsigned int i, n, step;
 
@@ -278,8 +283,7 @@ static int do_dump_btf(const struct btf_dumper *d,
 			jsonw_start_object(d->jw);
 			jsonw_int_field(d->jw, "cpu", i);
 			jsonw_name(d->jw, "value");
-			ret = btf_dumper_type(d, map_info->btf_value_type_id,
-					      value + i * step);
+			ret = btf_dumper_type(d, value_id, value + i * step);
 			jsonw_end_object(d->jw);
 			if (ret)
 				break;
@@ -915,37 +919,63 @@ static int maps_have_btf(int *fds, int nb_fds)
 {
 	struct bpf_map_info info = {};
 	__u32 len = sizeof(info);
-	struct btf *btf = NULL;
 	int err, i;
 
 	for (i = 0; i < nb_fds; i++) {
 		err = bpf_obj_get_info_by_fd(fds[i], &info, &len);
 		if (err) {
 			p_err("can't get map info: %s", strerror(errno));
-			goto err_close;
-		}
-
-		err = btf__get_from_id(info.btf_id, &btf);
-		if (err) {
-			p_err("failed to get btf");
-			goto err_close;
+			return -1;
 		}
 
-		if (!btf)
+		if (!info.btf_id)
 			return 0;
 	}
 
 	return 1;
+}
 
-err_close:
-	for (; i < nb_fds; i++)
-		close(fds[i]);
-	return -1;
+static struct btf *btf_vmlinux;
+
+static struct btf *get_map_kv_btf(const struct bpf_map_info *info)
+{
+	struct btf *btf = NULL;
+
+	if (info->btf_vmlinux_value_type_id) {
+		if (!btf_vmlinux) {
+			btf_vmlinux = libbpf_find_kernel_btf();
+			if (IS_ERR(btf_vmlinux))
+				p_err("failed to get kernel btf");
+		}
+		return btf_vmlinux;
+	} else if (info->btf_value_type_id) {
+		int err;
+
+		err = btf__get_from_id(info->btf_id, &btf);
+		if (err || !btf) {
+			p_err("failed to get btf");
+			btf = err ? ERR_PTR(err) : ERR_PTR(-ESRCH);
+		}
+	}
+
+	return btf;
+}
+
+static void free_map_kv_btf(struct btf *btf)
+{
+	if (!IS_ERR(btf) && btf != btf_vmlinux)
+		btf__free(btf);
+}
+
+static void free_btf_vmlinux(void)
+{
+	if (!IS_ERR(btf_vmlinux))
+		btf__free(btf_vmlinux);
 }
 
 static int
 map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr,
-	 bool enable_btf, bool show_header)
+	 bool show_header)
 {
 	void *key, *value, *prev_key;
 	unsigned int num_elems = 0;
@@ -962,18 +992,13 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr,
 
 	prev_key = NULL;
 
-	if (enable_btf) {
-		err = btf__get_from_id(info->btf_id, &btf);
-		if (err || !btf) {
-			/* enable_btf is true only if we've already checked
-			 * that all maps have BTF information.
-			 */
-			p_err("failed to get btf");
+	if (wtr) {
+		btf = get_map_kv_btf(info);
+		if (IS_ERR(btf)) {
+			err = PTR_ERR(btf);
 			goto exit_free;
 		}
-	}
 
-	if (wtr) {
 		if (show_header) {
 			jsonw_start_object(wtr);	/* map object */
 			show_map_header_json(info, wtr);
@@ -1012,7 +1037,7 @@ exit_free:
 	free(key);
 	free(value);
 	close(fd);
-	btf__free(btf);
+	free_map_kv_btf(btf);
 
 	return err;
 }
@@ -1021,7 +1046,7 @@ static int do_dump(int argc, char **argv)
 {
 	json_writer_t *wtr = NULL, *btf_wtr = NULL;
 	struct bpf_map_info info = {};
-	int nb_fds, i = 0, btf = 0;
+	int nb_fds, i = 0;
 	__u32 len = sizeof(info);
 	int *fds = NULL;
 	int err = -1;
@@ -1041,17 +1066,17 @@ static int do_dump(int argc, char **argv)
 	if (json_output) {
 		wtr = json_wtr;
 	} else {
-		btf = maps_have_btf(fds, nb_fds);
-		if (btf < 0)
+		int do_plain_btf;
+
+		do_plain_btf = maps_have_btf(fds, nb_fds);
+		if (do_plain_btf < 0)
 			goto exit_close;
-		if (btf) {
+
+		if (do_plain_btf) {
 			btf_wtr = get_btf_writer();
-			if (btf_wtr) {
-				wtr = btf_wtr;
-			} else {
+			wtr = btf_wtr;
+			if (!btf_wtr)
 				p_info("failed to create json writer for btf. falling back to plain output");
-				btf = 0;
-			}
 		}
 	}
 
@@ -1062,7 +1087,7 @@ static int do_dump(int argc, char **argv)
 			p_err("can't get map info: %s", strerror(errno));
 			break;
 		}
-		err = map_dump(fds[i], &info, wtr, btf, nb_fds > 1);
+		err = map_dump(fds[i], &info, wtr, nb_fds > 1);
 		if (!wtr && i != nb_fds - 1)
 			printf("\n");
 
@@ -1073,13 +1098,14 @@ static int do_dump(int argc, char **argv)
 	if (wtr && nb_fds > 1)
 		jsonw_end_array(wtr);	/* root array */
 
-	if (btf)
+	if (btf_wtr)
 		jsonw_destroy(&btf_wtr);
 exit_close:
 	for (; i < nb_fds; i++)
 		close(fds[i]);
 exit_free:
 	free(fds);
+	free_btf_vmlinux();
 	return err;
 }
 
diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c
index 4c5531d1a450..d9b29c17fbb8 100644
--- a/tools/bpf/bpftool/map_perf_ring.c
+++ b/tools/bpf/bpftool/map_perf_ring.c
@@ -6,7 +6,7 @@
  */
 #include <errno.h>
 #include <fcntl.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
 #include <poll.h>
 #include <signal.h>
 #include <stdbool.h>
@@ -21,7 +21,7 @@
 #include <sys/mman.h>
 #include <sys/syscall.h>
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 #include <perf-sys.h>
 
 #include "main.h"
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index d93bee298e54..c5e3895b7c8b 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -7,7 +7,8 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 #include <net/if.h>
 #include <linux/if.h>
 #include <linux/rtnetlink.h>
@@ -16,9 +17,8 @@
 #include <sys/stat.h>
 #include <sys/types.h>
 
-#include <bpf.h>
-#include <nlattr.h>
-#include "libbpf_internal.h"
+#include "bpf/nlattr.h"
+#include "bpf/libbpf_internal.h"
 #include "main.h"
 #include "netlink_dumper.h"
 
diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c
index 550a0f537eed..5f65140b003b 100644
--- a/tools/bpf/bpftool/netlink_dumper.c
+++ b/tools/bpf/bpftool/netlink_dumper.c
@@ -3,11 +3,11 @@
 
 #include <stdlib.h>
 #include <string.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
 #include <linux/rtnetlink.h>
 #include <linux/tc_act/tc_bpf.h>
 
-#include <nlattr.h>
+#include "bpf/nlattr.h"
 #include "main.h"
 #include "netlink_dumper.h"
 
diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c
index b2046f33e23f..3341aa14acda 100644
--- a/tools/bpf/bpftool/perf.c
+++ b/tools/bpf/bpftool/perf.c
@@ -13,7 +13,7 @@
 #include <unistd.h>
 #include <ftw.h>
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 #include "main.h"
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 47a61ac42dc0..a3521deca869 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -17,9 +17,9 @@
 #include <linux/err.h>
 #include <linux/sizes.h>
 
-#include <bpf.h>
-#include <btf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
 
 #include "cfg.h"
 #include "main.h"
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 5b91ee65a080..8608cd68cdd0 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -7,7 +7,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
 
 #include "disasm.h"
 #include "json_writer.h"
diff --git a/tools/bpf/runqslower/.gitignore b/tools/bpf/runqslower/.gitignore
new file mode 100644
index 000000000000..90a456a2a72f
--- /dev/null
+++ b/tools/bpf/runqslower/.gitignore
@@ -0,0 +1 @@
+/.output
diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
new file mode 100644
index 000000000000..faf5418609ea
--- /dev/null
+++ b/tools/bpf/runqslower/Makefile
@@ -0,0 +1,84 @@
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+OUTPUT := .output
+CLANG := clang
+LLC := llc
+LLVM_STRIP := llvm-strip
+DEFAULT_BPFTOOL := $(OUTPUT)/sbin/bpftool
+BPFTOOL ?= $(DEFAULT_BPFTOOL)
+LIBBPF_SRC := $(abspath ../../lib/bpf)
+BPFOBJ := $(OUTPUT)/libbpf.a
+BPF_INCLUDE := $(OUTPUT)
+INCLUDES := -I$(BPF_INCLUDE) -I$(OUTPUT) -I$(abspath ../../lib)
+CFLAGS := -g -Wall
+
+# Try to detect best kernel BTF source
+KERNEL_REL := $(shell uname -r)
+VMLINUX_BTF_PATHS := /sys/kernel/btf/vmlinux /boot/vmlinux-$(KERNEL_REL)
+VMLINUX_BTF_PATH := $(or $(VMLINUX_BTF),$(firstword			       \
+					  $(wildcard $(VMLINUX_BTF_PATHS))))
+
+abs_out := $(abspath $(OUTPUT))
+ifeq ($(V),1)
+Q =
+msg =
+else
+Q = @
+msg = @printf '  %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))";
+MAKEFLAGS += --no-print-directory
+submake_extras := feature_display=0
+endif
+
+.DELETE_ON_ERROR:
+
+.PHONY: all clean runqslower
+all: runqslower
+
+runqslower: $(OUTPUT)/runqslower
+
+clean:
+	$(call msg,CLEAN)
+	$(Q)rm -rf $(OUTPUT) runqslower
+
+$(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ)
+	$(call msg,BINARY,$@)
+	$(Q)$(CC) $(CFLAGS) -lelf -lz $^ -o $@
+
+$(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h	      \
+			$(OUTPUT)/runqslower.bpf.o
+
+$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h
+
+$(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL)
+	$(call msg,GEN-SKEL,$@)
+	$(Q)$(BPFTOOL) gen skeleton $< > $@
+
+$(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT)
+	$(call msg,BPF,$@)
+	$(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES)			      \
+		 -c $(filter %.c,$^) -o $@ &&				      \
+	$(LLVM_STRIP) -g $@
+
+$(OUTPUT)/%.o: %.c | $(OUTPUT)
+	$(call msg,CC,$@)
+	$(Q)$(CC) $(CFLAGS) $(INCLUDES) -c $(filter %.c,$^) -o $@
+
+$(OUTPUT):
+	$(call msg,MKDIR,$@)
+	$(Q)mkdir -p $(OUTPUT)
+
+$(OUTPUT)/vmlinux.h: $(VMLINUX_BTF_PATH) | $(OUTPUT) $(BPFTOOL)
+	$(call msg,GEN,$@)
+	$(Q)if [ ! -e "$(VMLINUX_BTF_PATH)" ] ; then \
+		echo "Couldn't find kernel BTF; set VMLINUX_BTF to"	       \
+			"specify its location." >&2;			       \
+		exit 1;\
+	fi
+	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@
+
+$(BPFOBJ): | $(OUTPUT)
+	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC)			       \
+		    OUTPUT=$(abspath $(dir $@))/ $(abspath $@)
+
+$(DEFAULT_BPFTOOL):
+	$(Q)$(MAKE) $(submake_extras) -C ../bpftool			      \
+		    prefix= OUTPUT=$(abs_out)/ DESTDIR=$(abs_out) install
diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c
new file mode 100644
index 000000000000..48a39f72fadf
--- /dev/null
+++ b/tools/bpf/runqslower/runqslower.bpf.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "runqslower.h"
+
+#define TASK_RUNNING 0
+
+#define BPF_F_INDEX_MASK		0xffffffffULL
+#define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
+
+const volatile __u64 min_us = 0;
+const volatile pid_t targ_pid = 0;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 10240);
+	__type(key, u32);
+	__type(value, u64);
+} start SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u32));
+} events SEC(".maps");
+
+/* record enqueue timestamp */
+__always_inline
+static int trace_enqueue(u32 tgid, u32 pid)
+{
+	u64 ts;
+
+	if (!pid || (targ_pid && targ_pid != pid))
+		return 0;
+
+	ts = bpf_ktime_get_ns();
+	bpf_map_update_elem(&start, &pid, &ts, 0);
+	return 0;
+}
+
+SEC("tp_btf/sched_wakeup")
+int handle__sched_wakeup(u64 *ctx)
+{
+	/* TP_PROTO(struct task_struct *p) */
+	struct task_struct *p = (void *)ctx[0];
+
+	return trace_enqueue(p->tgid, p->pid);
+}
+
+SEC("tp_btf/sched_wakeup_new")
+int handle__sched_wakeup_new(u64 *ctx)
+{
+	/* TP_PROTO(struct task_struct *p) */
+	struct task_struct *p = (void *)ctx[0];
+
+	return trace_enqueue(p->tgid, p->pid);
+}
+
+SEC("tp_btf/sched_switch")
+int handle__sched_switch(u64 *ctx)
+{
+	/* TP_PROTO(bool preempt, struct task_struct *prev,
+	 *	    struct task_struct *next)
+	 */
+	struct task_struct *prev = (struct task_struct *)ctx[1];
+	struct task_struct *next = (struct task_struct *)ctx[2];
+	struct event event = {};
+	u64 *tsp, delta_us;
+	long state;
+	u32 pid;
+
+	/* ivcsw: treat like an enqueue event and store timestamp */
+	if (prev->state == TASK_RUNNING)
+		trace_enqueue(prev->tgid, prev->pid);
+
+	pid = next->pid;
+
+	/* fetch timestamp and calculate delta */
+	tsp = bpf_map_lookup_elem(&start, &pid);
+	if (!tsp)
+		return 0;   /* missed enqueue */
+
+	delta_us = (bpf_ktime_get_ns() - *tsp) / 1000;
+	if (min_us && delta_us <= min_us)
+		return 0;
+
+	event.pid = pid;
+	event.delta_us = delta_us;
+	bpf_get_current_comm(&event.task, sizeof(event.task));
+
+	/* output */
+	bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU,
+			      &event, sizeof(event));
+
+	bpf_map_delete_elem(&start, &pid);
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/bpf/runqslower/runqslower.c b/tools/bpf/runqslower/runqslower.c
new file mode 100644
index 000000000000..d89715844952
--- /dev/null
+++ b/tools/bpf/runqslower/runqslower.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+// Copyright (c) 2019 Facebook
+#include <argp.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/resource.h>
+#include <time.h>
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+#include "runqslower.h"
+#include "runqslower.skel.h"
+
+struct env {
+	pid_t pid;
+	__u64 min_us;
+	bool verbose;
+} env = {
+	.min_us = 10000,
+};
+
+const char *argp_program_version = "runqslower 0.1";
+const char *argp_program_bug_address = "<bpf@vger.kernel.org>";
+const char argp_program_doc[] =
+"runqslower    Trace long process scheduling delays.\n"
+"              For Linux, uses eBPF, BPF CO-RE, libbpf, BTF.\n"
+"\n"
+"This script traces high scheduling delays between tasks being\n"
+"ready to run and them running on CPU after that.\n"
+"\n"
+"USAGE: runqslower [-p PID] [min_us]\n"
+"\n"
+"EXAMPLES:\n"
+"    runqslower         # trace run queue latency higher than 10000 us (default)\n"
+"    runqslower 1000    # trace run queue latency higher than 1000 us\n"
+"    runqslower -p 123  # trace pid 123 only\n";
+
+static const struct argp_option opts[] = {
+	{ "pid", 'p', "PID", 0, "Process PID to trace"},
+	{ "verbose", 'v', NULL, 0, "Verbose debug output" },
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	static int pos_args;
+	int pid;
+	long long min_us;
+
+	switch (key) {
+	case 'v':
+		env.verbose = true;
+		break;
+	case 'p':
+		errno = 0;
+		pid = strtol(arg, NULL, 10);
+		if (errno || pid <= 0) {
+			fprintf(stderr, "Invalid PID: %s\n", arg);
+			argp_usage(state);
+		}
+		env.pid = pid;
+		break;
+	case ARGP_KEY_ARG:
+		if (pos_args++) {
+			fprintf(stderr,
+				"Unrecognized positional argument: %s\n", arg);
+			argp_usage(state);
+		}
+		errno = 0;
+		min_us = strtoll(arg, NULL, 10);
+		if (errno || min_us <= 0) {
+			fprintf(stderr, "Invalid delay (in us): %s\n", arg);
+			argp_usage(state);
+		}
+		env.min_us = min_us;
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+	return 0;
+}
+
+int libbpf_print_fn(enum libbpf_print_level level,
+		    const char *format, va_list args)
+{
+	if (level == LIBBPF_DEBUG && !env.verbose)
+		return 0;
+	return vfprintf(stderr, format, args);
+}
+
+static int bump_memlock_rlimit(void)
+{
+	struct rlimit rlim_new = {
+		.rlim_cur	= RLIM_INFINITY,
+		.rlim_max	= RLIM_INFINITY,
+	};
+
+	return setrlimit(RLIMIT_MEMLOCK, &rlim_new);
+}
+
+void handle_event(void *ctx, int cpu, void *data, __u32 data_sz)
+{
+	const struct event *e = data;
+	struct tm *tm;
+	char ts[32];
+	time_t t;
+
+	time(&t);
+	tm = localtime(&t);
+	strftime(ts, sizeof(ts), "%H:%M:%S", tm);
+	printf("%-8s %-16s %-6d %14llu\n", ts, e->task, e->pid, e->delta_us);
+}
+
+void handle_lost_events(void *ctx, int cpu, __u64 lost_cnt)
+{
+	printf("Lost %llu events on CPU #%d!\n", lost_cnt, cpu);
+}
+
+int main(int argc, char **argv)
+{
+	static const struct argp argp = {
+		.options = opts,
+		.parser = parse_arg,
+		.doc = argp_program_doc,
+	};
+	struct perf_buffer_opts pb_opts;
+	struct perf_buffer *pb = NULL;
+	struct runqslower_bpf *obj;
+	int err;
+
+	err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
+	if (err)
+		return err;
+
+	libbpf_set_print(libbpf_print_fn);
+
+	err = bump_memlock_rlimit();
+	if (err) {
+		fprintf(stderr, "failed to increase rlimit: %d", err);
+		return 1;
+	}
+
+	obj = runqslower_bpf__open();
+	if (!obj) {
+		fprintf(stderr, "failed to open and/or load BPF object\n");
+		return 1;
+	}
+
+	/* initialize global data (filtering options) */
+	obj->rodata->targ_pid = env.pid;
+	obj->rodata->min_us = env.min_us;
+
+	err = runqslower_bpf__load(obj);
+	if (err) {
+		fprintf(stderr, "failed to load BPF object: %d\n", err);
+		goto cleanup;
+	}
+
+	err = runqslower_bpf__attach(obj);
+	if (err) {
+		fprintf(stderr, "failed to attach BPF programs\n");
+		goto cleanup;
+	}
+
+	printf("Tracing run queue latency higher than %llu us\n", env.min_us);
+	printf("%-8s %-16s %-6s %14s\n", "TIME", "COMM", "PID", "LAT(us)");
+
+	pb_opts.sample_cb = handle_event;
+	pb_opts.lost_cb = handle_lost_events;
+	pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, &pb_opts);
+	err = libbpf_get_error(pb);
+	if (err) {
+		pb = NULL;
+		fprintf(stderr, "failed to open perf buffer: %d\n", err);
+		goto cleanup;
+	}
+
+	while ((err = perf_buffer__poll(pb, 100)) >= 0)
+		;
+	printf("Error polling perf buffer: %d\n", err);
+
+cleanup:
+	perf_buffer__free(pb);
+	runqslower_bpf__destroy(obj);
+
+	return err != 0;
+}
diff --git a/tools/bpf/runqslower/runqslower.h b/tools/bpf/runqslower/runqslower.h
new file mode 100644
index 000000000000..9db225425e5f
--- /dev/null
+++ b/tools/bpf/runqslower/runqslower.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __RUNQSLOWER_H
+#define __RUNQSLOWER_H
+
+#define TASK_COMM_LEN 16
+
+struct event {
+	char task[TASK_COMM_LEN];
+	__u64 delta_us;
+	pid_t pid;
+};
+
+#endif /* __RUNQSLOWER_H */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7df436da542d..f1d74a2bd234 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -107,6 +107,10 @@ enum bpf_cmd {
 	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
 	BPF_MAP_FREEZE,
 	BPF_BTF_GET_NEXT_ID,
+	BPF_MAP_LOOKUP_BATCH,
+	BPF_MAP_LOOKUP_AND_DELETE_BATCH,
+	BPF_MAP_UPDATE_BATCH,
+	BPF_MAP_DELETE_BATCH,
 };
 
 enum bpf_map_type {
@@ -136,6 +140,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_STACK,
 	BPF_MAP_TYPE_SK_STORAGE,
 	BPF_MAP_TYPE_DEVMAP_HASH,
+	BPF_MAP_TYPE_STRUCT_OPS,
 };
 
 /* Note that tracing related programs such as
@@ -174,6 +179,8 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
 	BPF_PROG_TYPE_CGROUP_SOCKOPT,
 	BPF_PROG_TYPE_TRACING,
+	BPF_PROG_TYPE_STRUCT_OPS,
+	BPF_PROG_TYPE_EXT,
 };
 
 enum bpf_attach_type {
@@ -357,7 +364,12 @@ enum bpf_attach_type {
 /* Enable memory-mapping BPF map */
 #define BPF_F_MMAPABLE		(1U << 10)
 
-/* flags for BPF_PROG_QUERY */
+/* Flags for BPF_PROG_QUERY. */
+
+/* Query effective (directly attached + inherited from ancestor cgroups)
+ * programs that will be executed for events within a cgroup.
+ * attach_flags with this flag are returned only for directly attached programs.
+ */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
 enum bpf_stack_build_id_status {
@@ -397,6 +409,10 @@ union bpf_attr {
 		__u32	btf_fd;		/* fd pointing to a BTF type data */
 		__u32	btf_key_type_id;	/* BTF type_id of the key */
 		__u32	btf_value_type_id;	/* BTF type_id of the value */
+		__u32	btf_vmlinux_value_type_id;/* BTF type_id of a kernel-
+						   * struct stored as the
+						   * map value
+						   */
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -409,6 +425,23 @@ union bpf_attr {
 		__u64		flags;
 	};
 
+	struct { /* struct used by BPF_MAP_*_BATCH commands */
+		__aligned_u64	in_batch;	/* start batch,
+						 * NULL to start from beginning
+						 */
+		__aligned_u64	out_batch;	/* output: next start batch */
+		__aligned_u64	keys;
+		__aligned_u64	values;
+		__u32		count;		/* input/output:
+						 * input: # of key/value
+						 * elements
+						 * output: # of filled elements
+						 */
+		__u32		map_fd;
+		__u64		elem_flags;
+		__u64		flags;
+	} batch;
+
 	struct { /* anonymous struct used by BPF_PROG_LOAD command */
 		__u32		prog_type;	/* one of enum bpf_prog_type */
 		__u32		insn_cnt;
@@ -2703,7 +2736,8 @@ union bpf_attr {
  *
  * int bpf_send_signal(u32 sig)
  *	Description
- *		Send signal *sig* to the current task.
+ *		Send signal *sig* to the process of the current task.
+ *		The signal may be delivered to any of this process's threads.
  *	Return
  *		0 on success or successfully queued.
  *
@@ -2831,6 +2865,33 @@ union bpf_attr {
  * 	Return
  * 		On success, the strictly positive length of the string,	including
  * 		the trailing NUL character. On error, a negative value.
+ *
+ * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
+ *	Description
+ *		Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock.
+ *		*rcv_nxt* is the ack_seq to be sent out.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_send_signal_thread(u32 sig)
+ *	Description
+ *		Send signal *sig* to the thread corresponding to the current task.
+ *	Return
+ *		0 on success or successfully queued.
+ *
+ *		**-EBUSY** if work queue under nmi is full.
+ *
+ *		**-EINVAL** if *sig* is invalid.
+ *
+ *		**-EPERM** if no permission to send the *sig*.
+ *
+ *		**-EAGAIN** if bpf program can try again.
+ *
+ * u64 bpf_jiffies64(void)
+ *	Description
+ *		Obtain the 64bit jiffies
+ *	Return
+ *		The 64 bit jiffies
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2948,7 +3009,10 @@ union bpf_attr {
 	FN(probe_read_user),		\
 	FN(probe_read_kernel),		\
 	FN(probe_read_user_str),	\
-	FN(probe_read_kernel_str),
+	FN(probe_read_kernel_str),	\
+	FN(tcp_send_ack),		\
+	FN(send_signal_thread),		\
+	FN(jiffies64),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3349,7 +3413,7 @@ struct bpf_map_info {
 	__u32 map_flags;
 	char  name[BPF_OBJ_NAME_LEN];
 	__u32 ifindex;
-	__u32 :32;
+	__u32 btf_vmlinux_value_type_id;
 	__u64 netns_dev;
 	__u64 netns_ino;
 	__u32 btf_id;
diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index 1a2898c482ee..5a667107ad2c 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -146,6 +146,12 @@ enum {
 	BTF_VAR_GLOBAL_EXTERN = 2,
 };
 
+enum btf_func_linkage {
+	BTF_FUNC_STATIC = 0,
+	BTF_FUNC_GLOBAL = 1,
+	BTF_FUNC_EXTERN = 2,
+};
+
 /* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
  * additional information related to the variable such as its linkage.
  */
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 42efdb84d189..024af2d1d0af 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -169,6 +169,7 @@ enum {
 	IFLA_MAX_MTU,
 	IFLA_PROP_LIST,
 	IFLA_ALT_IFNAME, /* Alternative ifname */
+	IFLA_PERM_ADDRESS,
 	__IFLA_MAX
 };
 
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index d87830e7ea63..aee7f1a83c77 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -183,7 +183,7 @@ $(BPF_IN_STATIC): force elfdep zdep bpfdep $(BPF_HELPER_DEFS)
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
 
 $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
-	$(Q)$(srctree)/scripts/bpf_helpers_doc.py --header 		\
+	$(QUIET_GEN)$(srctree)/scripts/bpf_helpers_doc.py --header \
 		--file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS)
 
 $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
@@ -273,10 +273,11 @@ config-clean:
 	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
 
 clean:
-	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \
-		*.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \
-		*.pc LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \
-		$(SHARED_OBJDIR) $(STATIC_OBJDIR)
+	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS)		     \
+		*~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS)		     \
+		$(SHARED_OBJDIR) $(STATIC_OBJDIR)			     \
+		$(addprefix $(OUTPUT),					     \
+			    *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc)
 	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
 
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index a787d53699c8..c6dafe563176 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -32,6 +32,9 @@
 #include "libbpf.h"
 #include "libbpf_internal.h"
 
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
  * required to be defined explicitly.
@@ -95,7 +98,11 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 	attr.btf_key_type_id = create_attr->btf_key_type_id;
 	attr.btf_value_type_id = create_attr->btf_value_type_id;
 	attr.map_ifindex = create_attr->map_ifindex;
-	attr.inner_map_fd = create_attr->inner_map_fd;
+	if (attr.map_type == BPF_MAP_TYPE_STRUCT_OPS)
+		attr.btf_vmlinux_value_type_id =
+			create_attr->btf_vmlinux_value_type_id;
+	else
+		attr.inner_map_fd = create_attr->inner_map_fd;
 
 	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
@@ -228,7 +235,10 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = load_attr->prog_type;
 	attr.expected_attach_type = load_attr->expected_attach_type;
-	if (attr.prog_type == BPF_PROG_TYPE_TRACING) {
+	if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS) {
+		attr.attach_btf_id = load_attr->attach_btf_id;
+	} else if (attr.prog_type == BPF_PROG_TYPE_TRACING ||
+		   attr.prog_type == BPF_PROG_TYPE_EXT) {
 		attr.attach_btf_id = load_attr->attach_btf_id;
 		attr.attach_prog_fd = load_attr->attach_prog_fd;
 	} else {
@@ -443,6 +453,64 @@ int bpf_map_freeze(int fd)
 	return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
 }
 
+static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
+				void *out_batch, void *keys, void *values,
+				__u32 *count,
+				const struct bpf_map_batch_opts *opts)
+{
+	union bpf_attr attr;
+	int ret;
+
+	if (!OPTS_VALID(opts, bpf_map_batch_opts))
+		return -EINVAL;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.batch.map_fd = fd;
+	attr.batch.in_batch = ptr_to_u64(in_batch);
+	attr.batch.out_batch = ptr_to_u64(out_batch);
+	attr.batch.keys = ptr_to_u64(keys);
+	attr.batch.values = ptr_to_u64(values);
+	attr.batch.count = *count;
+	attr.batch.elem_flags  = OPTS_GET(opts, elem_flags, 0);
+	attr.batch.flags = OPTS_GET(opts, flags, 0);
+
+	ret = sys_bpf(cmd, &attr, sizeof(attr));
+	*count = attr.batch.count;
+
+	return ret;
+}
+
+int bpf_map_delete_batch(int fd, void *keys, __u32 *count,
+			 const struct bpf_map_batch_opts *opts)
+{
+	return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL,
+				    NULL, keys, NULL, count, opts);
+}
+
+int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys,
+			 void *values, __u32 *count,
+			 const struct bpf_map_batch_opts *opts)
+{
+	return bpf_map_batch_common(BPF_MAP_LOOKUP_BATCH, fd, in_batch,
+				    out_batch, keys, values, count, opts);
+}
+
+int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch,
+				    void *keys, void *values, __u32 *count,
+				    const struct bpf_map_batch_opts *opts)
+{
+	return bpf_map_batch_common(BPF_MAP_LOOKUP_AND_DELETE_BATCH,
+				    fd, in_batch, out_batch, keys, values,
+				    count, opts);
+}
+
+int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count,
+			 const struct bpf_map_batch_opts *opts)
+{
+	return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL,
+				    keys, values, count, opts);
+}
+
 int bpf_obj_pin(int fd, const char *pathname)
 {
 	union bpf_attr attr;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index f0ab8519986e..b976e77316cc 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -46,7 +46,10 @@ struct bpf_create_map_attr {
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
 	__u32 map_ifindex;
-	__u32 inner_map_fd;
+	union {
+		__u32 inner_map_fd;
+		__u32 btf_vmlinux_value_type_id;
+	};
 };
 
 LIBBPF_API int
@@ -124,6 +127,28 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
 LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
 LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
 LIBBPF_API int bpf_map_freeze(int fd);
+
+struct bpf_map_batch_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u64 elem_flags;
+	__u64 flags;
+};
+#define bpf_map_batch_opts__last_field flags
+
+LIBBPF_API int bpf_map_delete_batch(int fd, void *keys,
+				    __u32 *count,
+				    const struct bpf_map_batch_opts *opts);
+LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch,
+				    void *keys, void *values, __u32 *count,
+				    const struct bpf_map_batch_opts *opts);
+LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch,
+					void *out_batch, void *keys,
+					void *values, __u32 *count,
+					const struct bpf_map_batch_opts *opts);
+LIBBPF_API int bpf_map_update_batch(int fd, void *keys, void *values,
+				    __u32 *count,
+				    const struct bpf_map_batch_opts *opts);
+
 LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
 LIBBPF_API int bpf_obj_get(const char *pathname);
 
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index 3ed1a27b5f7c..bafca49cb1e6 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -8,6 +8,9 @@
 #include "libbpf.h"
 #include "libbpf_internal.h"
 
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
 struct bpf_prog_linfo {
 	void *raw_linfo;
 	void *raw_jited_linfo;
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 5f04f56e1eb6..3d1c25fc97ae 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -8,6 +8,10 @@
 #include <fcntl.h>
 #include <unistd.h>
 #include <errno.h>
+#include <sys/utsname.h>
+#include <sys/param.h>
+#include <sys/stat.h>
+#include <linux/kernel.h>
 #include <linux/err.h>
 #include <linux/btf.h>
 #include <gelf.h>
@@ -17,8 +21,11 @@
 #include "libbpf_internal.h"
 #include "hashmap.h"
 
-#define BTF_MAX_NR_TYPES 0x7fffffff
-#define BTF_MAX_STR_OFFSET 0x7fffffff
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
+#define BTF_MAX_NR_TYPES 0x7fffffffU
+#define BTF_MAX_STR_OFFSET 0x7fffffffU
 
 static struct btf_type btf_void;
 
@@ -50,7 +57,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t)
 		if (btf->types_size == BTF_MAX_NR_TYPES)
 			return -E2BIG;
 
-		expand_by = max(btf->types_size >> 2, 16);
+		expand_by = max(btf->types_size >> 2, 16U);
 		new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by);
 
 		new_types = realloc(btf->types, sizeof(*new_types) * new_size);
@@ -286,7 +293,7 @@ int btf__align_of(const struct btf *btf, __u32 id)
 	switch (kind) {
 	case BTF_KIND_INT:
 	case BTF_KIND_ENUM:
-		return min(sizeof(void *), t->size);
+		return min(sizeof(void *), (size_t)t->size);
 	case BTF_KIND_PTR:
 		return sizeof(void *);
 	case BTF_KIND_TYPEDEF:
@@ -1398,7 +1405,7 @@ static int btf_dedup_hypot_map_add(struct btf_dedup *d,
 	if (d->hypot_cnt == d->hypot_cap) {
 		__u32 *new_list;
 
-		d->hypot_cap += max(16, d->hypot_cap / 2);
+		d->hypot_cap += max((size_t)16, d->hypot_cap / 2);
 		new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap);
 		if (!new_list)
 			return -ENOMEM;
@@ -1694,7 +1701,7 @@ static int btf_dedup_strings(struct btf_dedup *d)
 		if (strs.cnt + 1 > strs.cap) {
 			struct btf_str_ptr *new_ptrs;
 
-			strs.cap += max(strs.cnt / 2, 16);
+			strs.cap += max(strs.cnt / 2, 16U);
 			new_ptrs = realloc(strs.ptrs,
 					   sizeof(strs.ptrs[0]) * strs.cap);
 			if (!new_ptrs) {
@@ -2928,3 +2935,89 @@ static int btf_dedup_remap_types(struct btf_dedup *d)
 	}
 	return 0;
 }
+
+static struct btf *btf_load_raw(const char *path)
+{
+	struct btf *btf;
+	size_t read_cnt;
+	struct stat st;
+	void *data;
+	FILE *f;
+
+	if (stat(path, &st))
+		return ERR_PTR(-errno);
+
+	data = malloc(st.st_size);
+	if (!data)
+		return ERR_PTR(-ENOMEM);
+
+	f = fopen(path, "rb");
+	if (!f) {
+		btf = ERR_PTR(-errno);
+		goto cleanup;
+	}
+
+	read_cnt = fread(data, 1, st.st_size, f);
+	fclose(f);
+	if (read_cnt < st.st_size) {
+		btf = ERR_PTR(-EBADF);
+		goto cleanup;
+	}
+
+	btf = btf__new(data, read_cnt);
+
+cleanup:
+	free(data);
+	return btf;
+}
+
+/*
+ * Probe few well-known locations for vmlinux kernel image and try to load BTF
+ * data out of it to use for target BTF.
+ */
+struct btf *libbpf_find_kernel_btf(void)
+{
+	struct {
+		const char *path_fmt;
+		bool raw_btf;
+	} locations[] = {
+		/* try canonical vmlinux BTF through sysfs first */
+		{ "/sys/kernel/btf/vmlinux", true /* raw BTF */ },
+		/* fall back to trying to find vmlinux ELF on disk otherwise */
+		{ "/boot/vmlinux-%1$s" },
+		{ "/lib/modules/%1$s/vmlinux-%1$s" },
+		{ "/lib/modules/%1$s/build/vmlinux" },
+		{ "/usr/lib/modules/%1$s/kernel/vmlinux" },
+		{ "/usr/lib/debug/boot/vmlinux-%1$s" },
+		{ "/usr/lib/debug/boot/vmlinux-%1$s.debug" },
+		{ "/usr/lib/debug/lib/modules/%1$s/vmlinux" },
+	};
+	char path[PATH_MAX + 1];
+	struct utsname buf;
+	struct btf *btf;
+	int i;
+
+	uname(&buf);
+
+	for (i = 0; i < ARRAY_SIZE(locations); i++) {
+		snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release);
+
+		if (access(path, R_OK))
+			continue;
+
+		if (locations[i].raw_btf)
+			btf = btf_load_raw(path);
+		else
+			btf = btf__parse_elf(path, NULL);
+
+		pr_debug("loading kernel BTF '%s': %ld\n",
+			 path, IS_ERR(btf) ? PTR_ERR(btf) : 0);
+		if (IS_ERR(btf))
+			continue;
+
+		return btf;
+	}
+
+	pr_warn("failed to find valid kernel BTF\n");
+	return ERR_PTR(-ESRCH);
+}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 8d73f7f5551f..70c1b7ec2bd0 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -102,6 +102,8 @@ LIBBPF_API int btf_ext__reloc_line_info(const struct btf *btf,
 LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
 LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
 
+LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
+
 struct btf_dedup_opts {
 	unsigned int dedup_table_size;
 	bool dont_resolve_fwds;
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index e95f7710f210..bd09ed1710f1 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -18,6 +18,9 @@
 #include "libbpf.h"
 #include "libbpf_internal.h"
 
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
 static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t";
 static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1;
 
@@ -139,6 +142,7 @@ struct btf_dump *btf_dump__new(const struct btf *btf,
 	if (IS_ERR(d->type_names)) {
 		err = PTR_ERR(d->type_names);
 		d->type_names = NULL;
+		goto err;
 	}
 	d->ident_names = hashmap__new(str_hash_fn, str_equal_fn, NULL);
 	if (IS_ERR(d->ident_names)) {
diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c
index 6122272943e6..54c30c802070 100644
--- a/tools/lib/bpf/hashmap.c
+++ b/tools/lib/bpf/hashmap.c
@@ -12,6 +12,9 @@
 #include <linux/err.h>
 #include "hashmap.h"
 
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
 /* start with 4 buckets */
 #define HASHMAP_MIN_CAP_BITS 2
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7513165b104f..ae34b681ae82 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -55,6 +55,9 @@
 #include "libbpf_internal.h"
 #include "hashmap.h"
 
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
 #ifndef EM_BPF
 #define EM_BPF 247
 #endif
@@ -70,6 +73,12 @@
 
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 
+static struct bpf_map *bpf_object__add_map(struct bpf_object *obj);
+static struct bpf_program *bpf_object__find_prog_by_idx(struct bpf_object *obj,
+							int idx);
+static const struct btf_type *
+skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
+
 static int __base_pr(enum libbpf_print_level level, const char *format,
 		     va_list args)
 {
@@ -166,6 +175,8 @@ struct bpf_capabilities {
 	__u32 btf_datasec:1;
 	/* BPF_F_MMAPABLE is supported for arrays */
 	__u32 array_mmap:1;
+	/* BTF_FUNC_GLOBAL is supported */
+	__u32 btf_func_global:1;
 };
 
 enum reloc_type {
@@ -229,10 +240,32 @@ struct bpf_program {
 	__u32 prog_flags;
 };
 
+struct bpf_struct_ops {
+	const char *tname;
+	const struct btf_type *type;
+	struct bpf_program **progs;
+	__u32 *kern_func_off;
+	/* e.g. struct tcp_congestion_ops in bpf_prog's btf format */
+	void *data;
+	/* e.g. struct bpf_struct_ops_tcp_congestion_ops in
+	 *      btf_vmlinux's format.
+	 * struct bpf_struct_ops_tcp_congestion_ops {
+	 *	[... some other kernel fields ...]
+	 *	struct tcp_congestion_ops data;
+	 * }
+	 * kern_vdata-size == sizeof(struct bpf_struct_ops_tcp_congestion_ops)
+	 * bpf_map__init_kern_struct_ops() will populate the "kern_vdata"
+	 * from "data".
+	 */
+	void *kern_vdata;
+	__u32 type_id;
+};
+
 #define DATA_SEC ".data"
 #define BSS_SEC ".bss"
 #define RODATA_SEC ".rodata"
 #define KCONFIG_SEC ".kconfig"
+#define STRUCT_OPS_SEC ".struct_ops"
 
 enum libbpf_map_type {
 	LIBBPF_MAP_UNSPEC,
@@ -259,10 +292,12 @@ struct bpf_map {
 	struct bpf_map_def def;
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
+	__u32 btf_vmlinux_value_type_id;
 	void *priv;
 	bpf_map_clear_priv_t clear_priv;
 	enum libbpf_map_type libbpf_type;
 	void *mmaped;
+	struct bpf_struct_ops *st_ops;
 	char *pin_path;
 	bool pinned;
 	bool reused;
@@ -326,6 +361,7 @@ struct bpf_object {
 		Elf_Data *data;
 		Elf_Data *rodata;
 		Elf_Data *bss;
+		Elf_Data *st_ops_data;
 		size_t strtabidx;
 		struct {
 			GElf_Shdr shdr;
@@ -339,6 +375,7 @@ struct bpf_object {
 		int data_shndx;
 		int rodata_shndx;
 		int bss_shndx;
+		int st_ops_shndx;
 	} efile;
 	/*
 	 * All loaded bpf_object is linked in a list, which is
@@ -348,6 +385,10 @@ struct bpf_object {
 	struct list_head list;
 
 	struct btf *btf;
+	/* Parse and load BTF vmlinux if any of the programs in the object need
+	 * it at load time.
+	 */
+	struct btf *btf_vmlinux;
 	struct btf_ext *btf_ext;
 
 	void *priv;
@@ -566,6 +607,348 @@ static __u32 get_kernel_version(void)
 	return KERNEL_VERSION(major, minor, patch);
 }
 
+static const struct btf_member *
+find_member_by_offset(const struct btf_type *t, __u32 bit_offset)
+{
+	struct btf_member *m;
+	int i;
+
+	for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) {
+		if (btf_member_bit_offset(t, i) == bit_offset)
+			return m;
+	}
+
+	return NULL;
+}
+
+static const struct btf_member *
+find_member_by_name(const struct btf *btf, const struct btf_type *t,
+		    const char *name)
+{
+	struct btf_member *m;
+	int i;
+
+	for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) {
+		if (!strcmp(btf__name_by_offset(btf, m->name_off), name))
+			return m;
+	}
+
+	return NULL;
+}
+
+#define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_"
+static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
+				   const char *name, __u32 kind);
+
+static int
+find_struct_ops_kern_types(const struct btf *btf, const char *tname,
+			   const struct btf_type **type, __u32 *type_id,
+			   const struct btf_type **vtype, __u32 *vtype_id,
+			   const struct btf_member **data_member)
+{
+	const struct btf_type *kern_type, *kern_vtype;
+	const struct btf_member *kern_data_member;
+	__s32 kern_vtype_id, kern_type_id;
+	__u32 i;
+
+	kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+	if (kern_type_id < 0) {
+		pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n",
+			tname);
+		return kern_type_id;
+	}
+	kern_type = btf__type_by_id(btf, kern_type_id);
+
+	/* Find the corresponding "map_value" type that will be used
+	 * in map_update(BPF_MAP_TYPE_STRUCT_OPS).  For example,
+	 * find "struct bpf_struct_ops_tcp_congestion_ops" from the
+	 * btf_vmlinux.
+	 */
+	kern_vtype_id = find_btf_by_prefix_kind(btf, STRUCT_OPS_VALUE_PREFIX,
+						tname, BTF_KIND_STRUCT);
+	if (kern_vtype_id < 0) {
+		pr_warn("struct_ops init_kern: struct %s%s is not found in kernel BTF\n",
+			STRUCT_OPS_VALUE_PREFIX, tname);
+		return kern_vtype_id;
+	}
+	kern_vtype = btf__type_by_id(btf, kern_vtype_id);
+
+	/* Find "struct tcp_congestion_ops" from
+	 * struct bpf_struct_ops_tcp_congestion_ops {
+	 *	[ ... ]
+	 *	struct tcp_congestion_ops data;
+	 * }
+	 */
+	kern_data_member = btf_members(kern_vtype);
+	for (i = 0; i < btf_vlen(kern_vtype); i++, kern_data_member++) {
+		if (kern_data_member->type == kern_type_id)
+			break;
+	}
+	if (i == btf_vlen(kern_vtype)) {
+		pr_warn("struct_ops init_kern: struct %s data is not found in struct %s%s\n",
+			tname, STRUCT_OPS_VALUE_PREFIX, tname);
+		return -EINVAL;
+	}
+
+	*type = kern_type;
+	*type_id = kern_type_id;
+	*vtype = kern_vtype;
+	*vtype_id = kern_vtype_id;
+	*data_member = kern_data_member;
+
+	return 0;
+}
+
+static bool bpf_map__is_struct_ops(const struct bpf_map *map)
+{
+	return map->def.type == BPF_MAP_TYPE_STRUCT_OPS;
+}
+
+/* Init the map's fields that depend on kern_btf */
+static int bpf_map__init_kern_struct_ops(struct bpf_map *map,
+					 const struct btf *btf,
+					 const struct btf *kern_btf)
+{
+	const struct btf_member *member, *kern_member, *kern_data_member;
+	const struct btf_type *type, *kern_type, *kern_vtype;
+	__u32 i, kern_type_id, kern_vtype_id, kern_data_off;
+	struct bpf_struct_ops *st_ops;
+	void *data, *kern_data;
+	const char *tname;
+	int err;
+
+	st_ops = map->st_ops;
+	type = st_ops->type;
+	tname = st_ops->tname;
+	err = find_struct_ops_kern_types(kern_btf, tname,
+					 &kern_type, &kern_type_id,
+					 &kern_vtype, &kern_vtype_id,
+					 &kern_data_member);
+	if (err)
+		return err;
+
+	pr_debug("struct_ops init_kern %s: type_id:%u kern_type_id:%u kern_vtype_id:%u\n",
+		 map->name, st_ops->type_id, kern_type_id, kern_vtype_id);
+
+	map->def.value_size = kern_vtype->size;
+	map->btf_vmlinux_value_type_id = kern_vtype_id;
+
+	st_ops->kern_vdata = calloc(1, kern_vtype->size);
+	if (!st_ops->kern_vdata)
+		return -ENOMEM;
+
+	data = st_ops->data;
+	kern_data_off = kern_data_member->offset / 8;
+	kern_data = st_ops->kern_vdata + kern_data_off;
+
+	member = btf_members(type);
+	for (i = 0; i < btf_vlen(type); i++, member++) {
+		const struct btf_type *mtype, *kern_mtype;
+		__u32 mtype_id, kern_mtype_id;
+		void *mdata, *kern_mdata;
+		__s64 msize, kern_msize;
+		__u32 moff, kern_moff;
+		__u32 kern_member_idx;
+		const char *mname;
+
+		mname = btf__name_by_offset(btf, member->name_off);
+		kern_member = find_member_by_name(kern_btf, kern_type, mname);
+		if (!kern_member) {
+			pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n",
+				map->name, mname);
+			return -ENOTSUP;
+		}
+
+		kern_member_idx = kern_member - btf_members(kern_type);
+		if (btf_member_bitfield_size(type, i) ||
+		    btf_member_bitfield_size(kern_type, kern_member_idx)) {
+			pr_warn("struct_ops init_kern %s: bitfield %s is not supported\n",
+				map->name, mname);
+			return -ENOTSUP;
+		}
+
+		moff = member->offset / 8;
+		kern_moff = kern_member->offset / 8;
+
+		mdata = data + moff;
+		kern_mdata = kern_data + kern_moff;
+
+		mtype = skip_mods_and_typedefs(btf, member->type, &mtype_id);
+		kern_mtype = skip_mods_and_typedefs(kern_btf, kern_member->type,
+						    &kern_mtype_id);
+		if (BTF_INFO_KIND(mtype->info) !=
+		    BTF_INFO_KIND(kern_mtype->info)) {
+			pr_warn("struct_ops init_kern %s: Unmatched member type %s %u != %u(kernel)\n",
+				map->name, mname, BTF_INFO_KIND(mtype->info),
+				BTF_INFO_KIND(kern_mtype->info));
+			return -ENOTSUP;
+		}
+
+		if (btf_is_ptr(mtype)) {
+			struct bpf_program *prog;
+
+			mtype = skip_mods_and_typedefs(btf, mtype->type, &mtype_id);
+			kern_mtype = skip_mods_and_typedefs(kern_btf,
+							    kern_mtype->type,
+							    &kern_mtype_id);
+			if (!btf_is_func_proto(mtype) ||
+			    !btf_is_func_proto(kern_mtype)) {
+				pr_warn("struct_ops init_kern %s: non func ptr %s is not supported\n",
+					map->name, mname);
+				return -ENOTSUP;
+			}
+
+			prog = st_ops->progs[i];
+			if (!prog) {
+				pr_debug("struct_ops init_kern %s: func ptr %s is not set\n",
+					 map->name, mname);
+				continue;
+			}
+
+			prog->attach_btf_id = kern_type_id;
+			prog->expected_attach_type = kern_member_idx;
+
+			st_ops->kern_func_off[i] = kern_data_off + kern_moff;
+
+			pr_debug("struct_ops init_kern %s: func ptr %s is set to prog %s from data(+%u) to kern_data(+%u)\n",
+				 map->name, mname, prog->name, moff,
+				 kern_moff);
+
+			continue;
+		}
+
+		msize = btf__resolve_size(btf, mtype_id);
+		kern_msize = btf__resolve_size(kern_btf, kern_mtype_id);
+		if (msize < 0 || kern_msize < 0 || msize != kern_msize) {
+			pr_warn("struct_ops init_kern %s: Error in size of member %s: %zd != %zd(kernel)\n",
+				map->name, mname, (ssize_t)msize,
+				(ssize_t)kern_msize);
+			return -ENOTSUP;
+		}
+
+		pr_debug("struct_ops init_kern %s: copy %s %u bytes from data(+%u) to kern_data(+%u)\n",
+			 map->name, mname, (unsigned int)msize,
+			 moff, kern_moff);
+		memcpy(kern_mdata, mdata, msize);
+	}
+
+	return 0;
+}
+
+static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj)
+{
+	struct bpf_map *map;
+	size_t i;
+	int err;
+
+	for (i = 0; i < obj->nr_maps; i++) {
+		map = &obj->maps[i];
+
+		if (!bpf_map__is_struct_ops(map))
+			continue;
+
+		err = bpf_map__init_kern_struct_ops(map, obj->btf,
+						    obj->btf_vmlinux);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int bpf_object__init_struct_ops_maps(struct bpf_object *obj)
+{
+	const struct btf_type *type, *datasec;
+	const struct btf_var_secinfo *vsi;
+	struct bpf_struct_ops *st_ops;
+	const char *tname, *var_name;
+	__s32 type_id, datasec_id;
+	const struct btf *btf;
+	struct bpf_map *map;
+	__u32 i;
+
+	if (obj->efile.st_ops_shndx == -1)
+		return 0;
+
+	btf = obj->btf;
+	datasec_id = btf__find_by_name_kind(btf, STRUCT_OPS_SEC,
+					    BTF_KIND_DATASEC);
+	if (datasec_id < 0) {
+		pr_warn("struct_ops init: DATASEC %s not found\n",
+			STRUCT_OPS_SEC);
+		return -EINVAL;
+	}
+
+	datasec = btf__type_by_id(btf, datasec_id);
+	vsi = btf_var_secinfos(datasec);
+	for (i = 0; i < btf_vlen(datasec); i++, vsi++) {
+		type = btf__type_by_id(obj->btf, vsi->type);
+		var_name = btf__name_by_offset(obj->btf, type->name_off);
+
+		type_id = btf__resolve_type(obj->btf, vsi->type);
+		if (type_id < 0) {
+			pr_warn("struct_ops init: Cannot resolve var type_id %u in DATASEC %s\n",
+				vsi->type, STRUCT_OPS_SEC);
+			return -EINVAL;
+		}
+
+		type = btf__type_by_id(obj->btf, type_id);
+		tname = btf__name_by_offset(obj->btf, type->name_off);
+		if (!tname[0]) {
+			pr_warn("struct_ops init: anonymous type is not supported\n");
+			return -ENOTSUP;
+		}
+		if (!btf_is_struct(type)) {
+			pr_warn("struct_ops init: %s is not a struct\n", tname);
+			return -EINVAL;
+		}
+
+		map = bpf_object__add_map(obj);
+		if (IS_ERR(map))
+			return PTR_ERR(map);
+
+		map->sec_idx = obj->efile.st_ops_shndx;
+		map->sec_offset = vsi->offset;
+		map->name = strdup(var_name);
+		if (!map->name)
+			return -ENOMEM;
+
+		map->def.type = BPF_MAP_TYPE_STRUCT_OPS;
+		map->def.key_size = sizeof(int);
+		map->def.value_size = type->size;
+		map->def.max_entries = 1;
+
+		map->st_ops = calloc(1, sizeof(*map->st_ops));
+		if (!map->st_ops)
+			return -ENOMEM;
+		st_ops = map->st_ops;
+		st_ops->data = malloc(type->size);
+		st_ops->progs = calloc(btf_vlen(type), sizeof(*st_ops->progs));
+		st_ops->kern_func_off = malloc(btf_vlen(type) *
+					       sizeof(*st_ops->kern_func_off));
+		if (!st_ops->data || !st_ops->progs || !st_ops->kern_func_off)
+			return -ENOMEM;
+
+		if (vsi->offset + type->size > obj->efile.st_ops_data->d_size) {
+			pr_warn("struct_ops init: var %s is beyond the end of DATASEC %s\n",
+				var_name, STRUCT_OPS_SEC);
+			return -EINVAL;
+		}
+
+		memcpy(st_ops->data,
+		       obj->efile.st_ops_data->d_buf + vsi->offset,
+		       type->size);
+		st_ops->tname = tname;
+		st_ops->type = type;
+		st_ops->type_id = type_id;
+
+		pr_debug("struct_ops init: struct %s(type_id=%u) %s found at offset %u\n",
+			 tname, type_id, var_name, vsi->offset);
+	}
+
+	return 0;
+}
+
 static struct bpf_object *bpf_object__new(const char *path,
 					  const void *obj_buf,
 					  size_t obj_buf_sz,
@@ -607,6 +990,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 	obj->efile.data_shndx = -1;
 	obj->efile.rodata_shndx = -1;
 	obj->efile.bss_shndx = -1;
+	obj->efile.st_ops_shndx = -1;
 	obj->kconfig_map_idx = -1;
 
 	obj->kern_version = get_kernel_version();
@@ -630,6 +1014,7 @@ static void bpf_object__elf_finish(struct bpf_object *obj)
 	obj->efile.data = NULL;
 	obj->efile.rodata = NULL;
 	obj->efile.bss = NULL;
+	obj->efile.st_ops_data = NULL;
 
 	zfree(&obj->efile.reloc_sects);
 	obj->efile.nr_reloc_sects = 0;
@@ -735,16 +1120,6 @@ bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size)
 	return 0;
 }
 
-static int compare_bpf_map(const void *_a, const void *_b)
-{
-	const struct bpf_map *a = _a;
-	const struct bpf_map *b = _b;
-
-	if (a->sec_idx != b->sec_idx)
-		return a->sec_idx - b->sec_idx;
-	return a->sec_offset - b->sec_offset;
-}
-
 static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
 {
 	if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
@@ -815,6 +1190,9 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name,
 	} else if (!strcmp(name, RODATA_SEC)) {
 		if (obj->efile.rodata)
 			*size = obj->efile.rodata->d_size;
+	} else if (!strcmp(name, STRUCT_OPS_SEC)) {
+		if (obj->efile.st_ops_data)
+			*size = obj->efile.st_ops_data->d_size;
 	} else {
 		ret = bpf_object_search_section_size(obj, name, &d_size);
 		if (!ret)
@@ -898,7 +1276,7 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map)
 	long page_sz = sysconf(_SC_PAGE_SIZE);
 	size_t map_sz;
 
-	map_sz = roundup(map->def.value_size, 8) * map->def.max_entries;
+	map_sz = (size_t)roundup(map->def.value_size, 8) * map->def.max_entries;
 	map_sz = roundup(map_sz, page_sz);
 	return map_sz;
 }
@@ -1440,6 +1818,20 @@ skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id)
 	return t;
 }
 
+static const struct btf_type *
+resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id)
+{
+	const struct btf_type *t;
+
+	t = skip_mods_and_typedefs(btf, id, NULL);
+	if (!btf_is_ptr(t))
+		return NULL;
+
+	t = skip_mods_and_typedefs(btf, t->type, res_id);
+
+	return btf_is_func_proto(t) ? t : NULL;
+}
+
 /*
  * Fetch integer attribute of BTF map definition. Such attributes are
  * represented using a pointer to an array, in which dimensionality of array
@@ -1787,13 +2179,10 @@ static int bpf_object__init_maps(struct bpf_object *obj,
 	err = err ?: bpf_object__init_user_btf_maps(obj, strict, pin_root_path);
 	err = err ?: bpf_object__init_global_data_maps(obj);
 	err = err ?: bpf_object__init_kconfig_map(obj);
+	err = err ?: bpf_object__init_struct_ops_maps(obj);
 	if (err)
 		return err;
 
-	if (obj->nr_maps) {
-		qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
-		      compare_bpf_map);
-	}
 	return 0;
 }
 
@@ -1817,13 +2206,14 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx)
 
 static void bpf_object__sanitize_btf(struct bpf_object *obj)
 {
+	bool has_func_global = obj->caps.btf_func_global;
 	bool has_datasec = obj->caps.btf_datasec;
 	bool has_func = obj->caps.btf_func;
 	struct btf *btf = obj->btf;
 	struct btf_type *t;
 	int i, j, vlen;
 
-	if (!obj->btf || (has_func && has_datasec))
+	if (!obj->btf || (has_func && has_datasec && has_func_global))
 		return;
 
 	for (i = 1; i <= btf__get_nr_types(btf); i++) {
@@ -1871,6 +2261,9 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj)
 		} else if (!has_func && btf_is_func(t)) {
 			/* replace FUNC with TYPEDEF */
 			t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0);
+		} else if (!has_func_global && btf_is_func(t)) {
+			/* replace BTF_FUNC_GLOBAL with BTF_FUNC_STATIC */
+			t->info = BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0);
 		}
 	}
 }
@@ -1889,23 +2282,26 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj)
 static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj)
 {
 	return obj->efile.btf_maps_shndx >= 0 ||
-	       obj->nr_extern > 0;
+		obj->efile.st_ops_shndx >= 0 ||
+		obj->nr_extern > 0;
 }
 
 static int bpf_object__init_btf(struct bpf_object *obj,
 				Elf_Data *btf_data,
 				Elf_Data *btf_ext_data)
 {
-	bool btf_required = bpf_object__is_btf_mandatory(obj);
-	int err = 0;
+	int err = -ENOENT;
 
 	if (btf_data) {
 		obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
 		if (IS_ERR(obj->btf)) {
+			err = PTR_ERR(obj->btf);
+			obj->btf = NULL;
 			pr_warn("Error loading ELF section %s: %d.\n",
 				BTF_ELF_SEC, err);
 			goto out;
 		}
+		err = 0;
 	}
 	if (btf_ext_data) {
 		if (!obj->btf) {
@@ -1923,18 +2319,9 @@ static int bpf_object__init_btf(struct bpf_object *obj,
 		}
 	}
 out:
-	if (err || IS_ERR(obj->btf)) {
-		if (btf_required)
-			err = err ? : PTR_ERR(obj->btf);
-		else
-			err = 0;
-		if (!IS_ERR_OR_NULL(obj->btf))
-			btf__free(obj->btf);
-		obj->btf = NULL;
-	}
-	if (btf_required && !obj->btf) {
+	if (err && bpf_object__is_btf_mandatory(obj)) {
 		pr_warn("BTF is required, but is missing or corrupted.\n");
-		return err == 0 ? -ENOENT : err;
+		return err;
 	}
 	return 0;
 }
@@ -1963,6 +2350,41 @@ static int bpf_object__finalize_btf(struct bpf_object *obj)
 	return 0;
 }
 
+static inline bool libbpf_prog_needs_vmlinux_btf(struct bpf_program *prog)
+{
+	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
+		return true;
+
+	/* BPF_PROG_TYPE_TRACING programs which do not attach to other programs
+	 * also need vmlinux BTF
+	 */
+	if (prog->type == BPF_PROG_TYPE_TRACING && !prog->attach_prog_fd)
+		return true;
+
+	return false;
+}
+
+static int bpf_object__load_vmlinux_btf(struct bpf_object *obj)
+{
+	struct bpf_program *prog;
+	int err;
+
+	bpf_object__for_each_program(prog, obj) {
+		if (libbpf_prog_needs_vmlinux_btf(prog)) {
+			obj->btf_vmlinux = libbpf_find_kernel_btf();
+			if (IS_ERR(obj->btf_vmlinux)) {
+				err = PTR_ERR(obj->btf_vmlinux);
+				pr_warn("Error loading vmlinux BTF: %d\n", err);
+				obj->btf_vmlinux = NULL;
+				return err;
+			}
+			return 0;
+		}
+	}
+
+	return 0;
+}
+
 static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 {
 	int err = 0;
@@ -2088,6 +2510,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			} else if (strcmp(name, RODATA_SEC) == 0) {
 				obj->efile.rodata = data;
 				obj->efile.rodata_shndx = idx;
+			} else if (strcmp(name, STRUCT_OPS_SEC) == 0) {
+				obj->efile.st_ops_data = data;
+				obj->efile.st_ops_shndx = idx;
 			} else {
 				pr_debug("skip section(%d) %s\n", idx, name);
 			}
@@ -2097,7 +2522,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			int sec = sh.sh_info; /* points to other section */
 
 			/* Only do relo for section with exec instructions */
-			if (!section_have_execinstr(obj, sec)) {
+			if (!section_have_execinstr(obj, sec) &&
+			    strcmp(name, ".rel" STRUCT_OPS_SEC)) {
 				pr_debug("skip relo %s(%d) for section(%d)\n",
 					 name, idx, sec);
 				continue;
@@ -2599,8 +3025,12 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
 	__u32 key_type_id = 0, value_type_id = 0;
 	int ret;
 
-	/* if it's BTF-defined map, we don't need to search for type IDs */
-	if (map->sec_idx == obj->efile.btf_maps_shndx)
+	/* if it's BTF-defined map, we don't need to search for type IDs.
+	 * For struct_ops map, it does not need btf_key_type_id and
+	 * btf_value_type_id.
+	 */
+	if (map->sec_idx == obj->efile.btf_maps_shndx ||
+	    bpf_map__is_struct_ops(map))
 		return 0;
 
 	if (!bpf_map__is_internal(map)) {
@@ -2804,6 +3234,32 @@ static int bpf_object__probe_btf_func(struct bpf_object *obj)
 	return 0;
 }
 
+static int bpf_object__probe_btf_func_global(struct bpf_object *obj)
+{
+	static const char strs[] = "\0int\0x\0a";
+	/* static void x(int a) {} */
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* FUNC_PROTO */                                /* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
+		BTF_PARAM_ENC(7, 1),
+		/* FUNC x BTF_FUNC_GLOBAL */                    /* [3] */
+		BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2),
+	};
+	int btf_fd;
+
+	btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types),
+				      strs, sizeof(strs));
+	if (btf_fd >= 0) {
+		obj->caps.btf_func_global = 1;
+		close(btf_fd);
+		return 1;
+	}
+
+	return 0;
+}
+
 static int bpf_object__probe_btf_datasec(struct bpf_object *obj)
 {
 	static const char strs[] = "\0x\0.data";
@@ -2859,6 +3315,7 @@ bpf_object__probe_caps(struct bpf_object *obj)
 		bpf_object__probe_name,
 		bpf_object__probe_global_data,
 		bpf_object__probe_btf_func,
+		bpf_object__probe_btf_func_global,
 		bpf_object__probe_btf_datasec,
 		bpf_object__probe_array_mmap,
 	};
@@ -3025,6 +3482,9 @@ bpf_object__create_maps(struct bpf_object *obj)
 		if (bpf_map_type__is_map_in_map(def->type) &&
 		    map->inner_map_fd >= 0)
 			create_attr.inner_map_fd = map->inner_map_fd;
+		if (bpf_map__is_struct_ops(map))
+			create_attr.btf_vmlinux_value_type_id =
+				map->btf_vmlinux_value_type_id;
 
 		if (obj->btf && !bpf_map_find_btf_info(obj, map)) {
 			create_attr.btf_fd = btf__fd(obj->btf);
@@ -3860,92 +4320,6 @@ static int bpf_core_reloc_insn(struct bpf_program *prog,
 	return 0;
 }
 
-static struct btf *btf_load_raw(const char *path)
-{
-	struct btf *btf;
-	size_t read_cnt;
-	struct stat st;
-	void *data;
-	FILE *f;
-
-	if (stat(path, &st))
-		return ERR_PTR(-errno);
-
-	data = malloc(st.st_size);
-	if (!data)
-		return ERR_PTR(-ENOMEM);
-
-	f = fopen(path, "rb");
-	if (!f) {
-		btf = ERR_PTR(-errno);
-		goto cleanup;
-	}
-
-	read_cnt = fread(data, 1, st.st_size, f);
-	fclose(f);
-	if (read_cnt < st.st_size) {
-		btf = ERR_PTR(-EBADF);
-		goto cleanup;
-	}
-
-	btf = btf__new(data, read_cnt);
-
-cleanup:
-	free(data);
-	return btf;
-}
-
-/*
- * Probe few well-known locations for vmlinux kernel image and try to load BTF
- * data out of it to use for target BTF.
- */
-static struct btf *bpf_core_find_kernel_btf(void)
-{
-	struct {
-		const char *path_fmt;
-		bool raw_btf;
-	} locations[] = {
-		/* try canonical vmlinux BTF through sysfs first */
-		{ "/sys/kernel/btf/vmlinux", true /* raw BTF */ },
-		/* fall back to trying to find vmlinux ELF on disk otherwise */
-		{ "/boot/vmlinux-%1$s" },
-		{ "/lib/modules/%1$s/vmlinux-%1$s" },
-		{ "/lib/modules/%1$s/build/vmlinux" },
-		{ "/usr/lib/modules/%1$s/kernel/vmlinux" },
-		{ "/usr/lib/debug/boot/vmlinux-%1$s" },
-		{ "/usr/lib/debug/boot/vmlinux-%1$s.debug" },
-		{ "/usr/lib/debug/lib/modules/%1$s/vmlinux" },
-	};
-	char path[PATH_MAX + 1];
-	struct utsname buf;
-	struct btf *btf;
-	int i;
-
-	uname(&buf);
-
-	for (i = 0; i < ARRAY_SIZE(locations); i++) {
-		snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release);
-
-		if (access(path, R_OK))
-			continue;
-
-		if (locations[i].raw_btf)
-			btf = btf_load_raw(path);
-		else
-			btf = btf__parse_elf(path, NULL);
-
-		pr_debug("loading kernel BTF '%s': %ld\n",
-			 path, IS_ERR(btf) ? PTR_ERR(btf) : 0);
-		if (IS_ERR(btf))
-			continue;
-
-		return btf;
-	}
-
-	pr_warn("failed to find valid kernel BTF\n");
-	return ERR_PTR(-ESRCH);
-}
-
 /* Output spec definition in the format:
  * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>,
  * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b
@@ -4180,7 +4554,7 @@ bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path)
 	if (targ_btf_path)
 		targ_btf = btf__parse_elf(targ_btf_path, NULL);
 	else
-		targ_btf = bpf_core_find_kernel_btf();
+		targ_btf = libbpf_find_kernel_btf();
 	if (IS_ERR(targ_btf)) {
 		pr_warn("failed to get target BTF: %ld\n", PTR_ERR(targ_btf));
 		return PTR_ERR(targ_btf);
@@ -4252,13 +4626,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 	size_t new_cnt;
 	int err;
 
-	if (prog->idx == obj->efile.text_shndx) {
-		pr_warn("relo in .text insn %d into off %d (insn #%d)\n",
-			relo->insn_idx, relo->sym_off, relo->sym_off / 8);
-		return -LIBBPF_ERRNO__RELOC;
-	}
-
-	if (prog->main_prog_cnt == 0) {
+	if (prog->idx != obj->efile.text_shndx && prog->main_prog_cnt == 0) {
 		text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx);
 		if (!text) {
 			pr_warn("no .text section found yet relo into text exist\n");
@@ -4288,6 +4656,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			 text->insns_cnt, text->section_name,
 			 prog->section_name);
 	}
+
 	insn = &prog->insns[relo->insn_idx];
 	insn->imm += relo->sym_off / 8 + prog->main_prog_cnt - relo->insn_idx;
 	return 0;
@@ -4367,8 +4736,28 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 			return err;
 		}
 	}
+	/* ensure .text is relocated first, as it's going to be copied as-is
+	 * later for sub-program calls
+	 */
+	for (i = 0; i < obj->nr_programs; i++) {
+		prog = &obj->programs[i];
+		if (prog->idx != obj->efile.text_shndx)
+			continue;
+
+		err = bpf_program__relocate(prog, obj);
+		if (err) {
+			pr_warn("failed to relocate '%s'\n", prog->section_name);
+			return err;
+		}
+		break;
+	}
+	/* now relocate everything but .text, which by now is relocated
+	 * properly, so we can copy raw sub-program instructions as is safely
+	 */
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
+		if (prog->idx == obj->efile.text_shndx)
+			continue;
 
 		err = bpf_program__relocate(prog, obj);
 		if (err) {
@@ -4379,6 +4768,10 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 	return 0;
 }
 
+static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj,
+						    GElf_Shdr *shdr,
+						    Elf_Data *data);
+
 static int bpf_object__collect_reloc(struct bpf_object *obj)
 {
 	int i, err;
@@ -4399,6 +4792,15 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 			return -LIBBPF_ERRNO__INTERNAL;
 		}
 
+		if (idx == obj->efile.st_ops_shndx) {
+			err = bpf_object__collect_struct_ops_map_reloc(obj,
+								       shdr,
+								       data);
+			if (err)
+				return err;
+			continue;
+		}
+
 		prog = bpf_object__find_prog_by_idx(obj, idx);
 		if (!prog) {
 			pr_warn("relocation failed: no section(%d)\n", idx);
@@ -4433,7 +4835,10 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.insns = insns;
 	load_attr.insns_cnt = insns_cnt;
 	load_attr.license = license;
-	if (prog->type == BPF_PROG_TYPE_TRACING) {
+	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) {
+		load_attr.attach_btf_id = prog->attach_btf_id;
+	} else if (prog->type == BPF_PROG_TYPE_TRACING ||
+		   prog->type == BPF_PROG_TYPE_EXT) {
 		load_attr.attach_prog_fd = prog->attach_prog_fd;
 		load_attr.attach_btf_id = prog->attach_btf_id;
 	} else {
@@ -4508,18 +4913,15 @@ out:
 	return ret;
 }
 
-static int libbpf_find_attach_btf_id(const char *name,
-				     enum bpf_attach_type attach_type,
-				     __u32 attach_prog_fd);
+static int libbpf_find_attach_btf_id(struct bpf_program *prog);
 
 int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 {
 	int err = 0, fd, i, btf_id;
 
-	if (prog->type == BPF_PROG_TYPE_TRACING) {
-		btf_id = libbpf_find_attach_btf_id(prog->section_name,
-						   prog->expected_attach_type,
-						   prog->attach_prog_fd);
+	if (prog->type == BPF_PROG_TYPE_TRACING ||
+	    prog->type == BPF_PROG_TYPE_EXT) {
+		btf_id = libbpf_find_attach_btf_id(prog);
 		if (btf_id <= 0)
 			return btf_id;
 		prog->attach_btf_id = btf_id;
@@ -4679,6 +5081,9 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 		enum bpf_prog_type prog_type;
 		enum bpf_attach_type attach_type;
 
+		if (prog->type != BPF_PROG_TYPE_UNSPEC)
+			continue;
+
 		err = libbpf_prog_type_by_name(prog->section_name, &prog_type,
 					       &attach_type);
 		if (err == -ESRCH)
@@ -4689,7 +5094,8 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 
 		bpf_program__set_type(prog, prog_type);
 		bpf_program__set_expected_attach_type(prog, attach_type);
-		if (prog_type == BPF_PROG_TYPE_TRACING)
+		if (prog_type == BPF_PROG_TYPE_TRACING ||
+		    prog_type == BPF_PROG_TYPE_EXT)
 			prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
 	}
 
@@ -4774,8 +5180,11 @@ int bpf_object__unload(struct bpf_object *obj)
 	if (!obj)
 		return -EINVAL;
 
-	for (i = 0; i < obj->nr_maps; i++)
+	for (i = 0; i < obj->nr_maps; i++) {
 		zclose(obj->maps[i].fd);
+		if (obj->maps[i].st_ops)
+			zfree(&obj->maps[i].st_ops->kern_vdata);
+	}
 
 	for (i = 0; i < obj->nr_programs; i++)
 		bpf_program__unload(&obj->programs[i]);
@@ -4891,9 +5300,15 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 	err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
 	err = err ? : bpf_object__sanitize_and_load_btf(obj);
 	err = err ? : bpf_object__sanitize_maps(obj);
+	err = err ? : bpf_object__load_vmlinux_btf(obj);
+	err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
 	err = err ? : bpf_object__create_maps(obj);
 	err = err ? : bpf_object__relocate(obj, attr->target_btf_path);
 	err = err ? : bpf_object__load_progs(obj, attr->log_level);
+
+	btf__free(obj->btf_vmlinux);
+	obj->btf_vmlinux = NULL;
+
 	if (err)
 		goto out;
 
@@ -5478,6 +5893,13 @@ void bpf_object__close(struct bpf_object *obj)
 			map->mmaped = NULL;
 		}
 
+		if (map->st_ops) {
+			zfree(&map->st_ops->data);
+			zfree(&map->st_ops->progs);
+			zfree(&map->st_ops->kern_func_off);
+			zfree(&map->st_ops);
+		}
+
 		zfree(&map->name);
 		zfree(&map->pin_path);
 	}
@@ -5746,6 +6168,8 @@ BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT);
 BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
 BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
 BPF_PROG_TYPE_FNS(tracing, BPF_PROG_TYPE_TRACING);
+BPF_PROG_TYPE_FNS(struct_ops, BPF_PROG_TYPE_STRUCT_OPS);
+BPF_PROG_TYPE_FNS(extension, BPF_PROG_TYPE_EXT);
 
 enum bpf_attach_type
 bpf_program__get_expected_attach_type(struct bpf_program *prog)
@@ -5845,6 +6269,9 @@ static const struct bpf_sec_def section_defs[] = {
 		.expected_attach_type = BPF_TRACE_FEXIT,
 		.is_attach_btf = true,
 		.attach_fn = attach_trace),
+	SEC_DEF("freplace/", EXT,
+		.is_attach_btf = true,
+		.attach_fn = attach_trace),
 	BPF_PROG_SEC("xdp",			BPF_PROG_TYPE_XDP),
 	BPF_PROG_SEC("perf_event",		BPF_PROG_TYPE_PERF_EVENT),
 	BPF_PROG_SEC("lwt_in",			BPF_PROG_TYPE_LWT_IN),
@@ -5899,6 +6326,7 @@ static const struct bpf_sec_def section_defs[] = {
 						BPF_CGROUP_GETSOCKOPT),
 	BPF_EAPROG_SEC("cgroup/setsockopt",	BPF_PROG_TYPE_CGROUP_SOCKOPT,
 						BPF_CGROUP_SETSOCKOPT),
+	BPF_PROG_SEC("struct_ops",		BPF_PROG_TYPE_STRUCT_OPS),
 };
 
 #undef BPF_PROG_SEC_IMPL
@@ -5975,34 +6403,182 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 	return -ESRCH;
 }
 
-#define BTF_PREFIX "btf_trace_"
+static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
+						     size_t offset)
+{
+	struct bpf_map *map;
+	size_t i;
+
+	for (i = 0; i < obj->nr_maps; i++) {
+		map = &obj->maps[i];
+		if (!bpf_map__is_struct_ops(map))
+			continue;
+		if (map->sec_offset <= offset &&
+		    offset - map->sec_offset < map->def.value_size)
+			return map;
+	}
+
+	return NULL;
+}
+
+/* Collect the reloc from ELF and populate the st_ops->progs[] */
+static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj,
+						    GElf_Shdr *shdr,
+						    Elf_Data *data)
+{
+	const struct btf_member *member;
+	struct bpf_struct_ops *st_ops;
+	struct bpf_program *prog;
+	unsigned int shdr_idx;
+	const struct btf *btf;
+	struct bpf_map *map;
+	Elf_Data *symbols;
+	unsigned int moff;
+	const char *name;
+	__u32 member_idx;
+	GElf_Sym sym;
+	GElf_Rel rel;
+	int i, nrels;
+
+	symbols = obj->efile.symbols;
+	btf = obj->btf;
+	nrels = shdr->sh_size / shdr->sh_entsize;
+	for (i = 0; i < nrels; i++) {
+		if (!gelf_getrel(data, i, &rel)) {
+			pr_warn("struct_ops reloc: failed to get %d reloc\n", i);
+			return -LIBBPF_ERRNO__FORMAT;
+		}
+
+		if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
+			pr_warn("struct_ops reloc: symbol %zx not found\n",
+				(size_t)GELF_R_SYM(rel.r_info));
+			return -LIBBPF_ERRNO__FORMAT;
+		}
+
+		name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
+				  sym.st_name) ? : "<?>";
+		map = find_struct_ops_map_by_offset(obj, rel.r_offset);
+		if (!map) {
+			pr_warn("struct_ops reloc: cannot find map at rel.r_offset %zu\n",
+				(size_t)rel.r_offset);
+			return -EINVAL;
+		}
+
+		moff = rel.r_offset - map->sec_offset;
+		shdr_idx = sym.st_shndx;
+		st_ops = map->st_ops;
+		pr_debug("struct_ops reloc %s: for %lld value %lld shdr_idx %u rel.r_offset %zu map->sec_offset %zu name %d (\'%s\')\n",
+			 map->name,
+			 (long long)(rel.r_info >> 32),
+			 (long long)sym.st_value,
+			 shdr_idx, (size_t)rel.r_offset,
+			 map->sec_offset, sym.st_name, name);
+
+		if (shdr_idx >= SHN_LORESERVE) {
+			pr_warn("struct_ops reloc %s: rel.r_offset %zu shdr_idx %u unsupported non-static function\n",
+				map->name, (size_t)rel.r_offset, shdr_idx);
+			return -LIBBPF_ERRNO__RELOC;
+		}
+
+		member = find_member_by_offset(st_ops->type, moff * 8);
+		if (!member) {
+			pr_warn("struct_ops reloc %s: cannot find member at moff %u\n",
+				map->name, moff);
+			return -EINVAL;
+		}
+		member_idx = member - btf_members(st_ops->type);
+		name = btf__name_by_offset(btf, member->name_off);
+
+		if (!resolve_func_ptr(btf, member->type, NULL)) {
+			pr_warn("struct_ops reloc %s: cannot relocate non func ptr %s\n",
+				map->name, name);
+			return -EINVAL;
+		}
+
+		prog = bpf_object__find_prog_by_idx(obj, shdr_idx);
+		if (!prog) {
+			pr_warn("struct_ops reloc %s: cannot find prog at shdr_idx %u to relocate func ptr %s\n",
+				map->name, shdr_idx, name);
+			return -EINVAL;
+		}
+
+		if (prog->type == BPF_PROG_TYPE_UNSPEC) {
+			const struct bpf_sec_def *sec_def;
+
+			sec_def = find_sec_def(prog->section_name);
+			if (sec_def &&
+			    sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) {
+				/* for pr_warn */
+				prog->type = sec_def->prog_type;
+				goto invalid_prog;
+			}
+
+			prog->type = BPF_PROG_TYPE_STRUCT_OPS;
+			prog->attach_btf_id = st_ops->type_id;
+			prog->expected_attach_type = member_idx;
+		} else if (prog->type != BPF_PROG_TYPE_STRUCT_OPS ||
+			   prog->attach_btf_id != st_ops->type_id ||
+			   prog->expected_attach_type != member_idx) {
+			goto invalid_prog;
+		}
+		st_ops->progs[member_idx] = prog;
+	}
+
+	return 0;
+
+invalid_prog:
+	pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n",
+		map->name, prog->name, prog->section_name, prog->type,
+		prog->attach_btf_id, prog->expected_attach_type, name);
+	return -EINVAL;
+}
+
+#define BTF_TRACE_PREFIX "btf_trace_"
+#define BTF_MAX_NAME_SIZE 128
+
+static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
+				   const char *name, __u32 kind)
+{
+	char btf_type_name[BTF_MAX_NAME_SIZE];
+	int ret;
+
+	ret = snprintf(btf_type_name, sizeof(btf_type_name),
+		       "%s%s", prefix, name);
+	/* snprintf returns the number of characters written excluding the
+	 * the terminating null. So, if >= BTF_MAX_NAME_SIZE are written, it
+	 * indicates truncation.
+	 */
+	if (ret < 0 || ret >= sizeof(btf_type_name))
+		return -ENAMETOOLONG;
+	return btf__find_by_name_kind(btf, btf_type_name, kind);
+}
+
+static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name,
+					enum bpf_attach_type attach_type)
+{
+	int err;
+
+	if (attach_type == BPF_TRACE_RAW_TP)
+		err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name,
+					      BTF_KIND_TYPEDEF);
+	else
+		err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
+
+	return err;
+}
+
 int libbpf_find_vmlinux_btf_id(const char *name,
 			       enum bpf_attach_type attach_type)
 {
-	struct btf *btf = bpf_core_find_kernel_btf();
-	char raw_tp_btf[128] = BTF_PREFIX;
-	char *dst = raw_tp_btf + sizeof(BTF_PREFIX) - 1;
-	const char *btf_name;
-	int err = -EINVAL;
-	__u32 kind;
+	struct btf *btf;
 
+	btf = libbpf_find_kernel_btf();
 	if (IS_ERR(btf)) {
 		pr_warn("vmlinux BTF is not found\n");
 		return -EINVAL;
 	}
 
-	if (attach_type == BPF_TRACE_RAW_TP) {
-		/* prepend "btf_trace_" prefix per kernel convention */
-		strncat(dst, name, sizeof(raw_tp_btf) - sizeof(BTF_PREFIX));
-		btf_name = raw_tp_btf;
-		kind = BTF_KIND_TYPEDEF;
-	} else {
-		btf_name = name;
-		kind = BTF_KIND_FUNC;
-	}
-	err = btf__find_by_name_kind(btf, btf_name, kind);
-	btf__free(btf);
-	return err;
+	return __find_vmlinux_btf_id(btf, name, attach_type);
 }
 
 static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
@@ -6038,10 +6614,11 @@ out:
 	return err;
 }
 
-static int libbpf_find_attach_btf_id(const char *name,
-				     enum bpf_attach_type attach_type,
-				     __u32 attach_prog_fd)
+static int libbpf_find_attach_btf_id(struct bpf_program *prog)
 {
+	enum bpf_attach_type attach_type = prog->expected_attach_type;
+	__u32 attach_prog_fd = prog->attach_prog_fd;
+	const char *name = prog->section_name;
 	int i, err;
 
 	if (!name)
@@ -6056,8 +6633,9 @@ static int libbpf_find_attach_btf_id(const char *name,
 			err = libbpf_find_prog_btf_id(name + section_defs[i].len,
 						      attach_prog_fd);
 		else
-			err = libbpf_find_vmlinux_btf_id(name + section_defs[i].len,
-							 attach_type);
+			err = __find_vmlinux_btf_id(prog->obj->btf_vmlinux,
+						    name + section_defs[i].len,
+						    attach_type);
 		if (err <= 0)
 			pr_warn("%s is not found in vmlinux BTF\n", name);
 		return err;
@@ -6805,6 +7383,58 @@ struct bpf_link *bpf_program__attach(struct bpf_program *prog)
 	return sec_def->attach_fn(sec_def, prog);
 }
 
+static int bpf_link__detach_struct_ops(struct bpf_link *link)
+{
+	struct bpf_link_fd *l = (void *)link;
+	__u32 zero = 0;
+
+	if (bpf_map_delete_elem(l->fd, &zero))
+		return -errno;
+
+	return 0;
+}
+
+struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
+{
+	struct bpf_struct_ops *st_ops;
+	struct bpf_link_fd *link;
+	__u32 i, zero = 0;
+	int err;
+
+	if (!bpf_map__is_struct_ops(map) || map->fd == -1)
+		return ERR_PTR(-EINVAL);
+
+	link = calloc(1, sizeof(*link));
+	if (!link)
+		return ERR_PTR(-EINVAL);
+
+	st_ops = map->st_ops;
+	for (i = 0; i < btf_vlen(st_ops->type); i++) {
+		struct bpf_program *prog = st_ops->progs[i];
+		void *kern_data;
+		int prog_fd;
+
+		if (!prog)
+			continue;
+
+		prog_fd = bpf_program__fd(prog);
+		kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i];
+		*(unsigned long *)kern_data = prog_fd;
+	}
+
+	err = bpf_map_update_elem(map->fd, &zero, st_ops->kern_vdata, 0);
+	if (err) {
+		err = -errno;
+		free(link);
+		return ERR_PTR(err);
+	}
+
+	link->link.detach = bpf_link__detach_struct_ops;
+	link->fd = map->fd;
+
+	return (struct bpf_link *)link;
+}
+
 enum bpf_perf_event_ret
 bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
 			   void **copy_mem, size_t *copy_size,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index fe592ef48f1b..2a5e3b087002 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -239,6 +239,8 @@ bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 
 LIBBPF_API struct bpf_link *
 bpf_program__attach_trace(struct bpf_program *prog);
+struct bpf_map;
+LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map);
 struct bpf_insn;
 
 /*
@@ -315,6 +317,8 @@ LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_extension(struct bpf_program *prog);
 
 LIBBPF_API enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog);
 LIBBPF_API void bpf_program__set_type(struct bpf_program *prog,
@@ -335,6 +339,8 @@ LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_extension(const struct bpf_program *prog);
 
 /*
  * No need for __attribute__((packed)), all members of 'bpf_map_def'
@@ -354,7 +360,6 @@ struct bpf_map_def {
  * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel,
  * so no need to worry about a name clash.
  */
-struct bpf_map;
 LIBBPF_API struct bpf_map *
 bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name);
 
@@ -521,6 +526,7 @@ LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type,
 LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex);
 LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id,
 				 enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex);
 
 /*
  * Get bpf_prog_info in continuous memory
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index e9713a574243..b035122142bb 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -213,14 +213,25 @@ LIBBPF_0.0.7 {
 	global:
 		btf_dump__emit_type_decl;
 		bpf_link__disconnect;
+		bpf_map__attach_struct_ops;
+		bpf_map_delete_batch;
+		bpf_map_lookup_and_delete_batch;
+		bpf_map_lookup_batch;
+		bpf_map_update_batch;
 		bpf_object__find_program_by_name;
 		bpf_object__attach_skeleton;
 		bpf_object__destroy_skeleton;
 		bpf_object__detach_skeleton;
 		bpf_object__load_skeleton;
 		bpf_object__open_skeleton;
+		bpf_probe_large_insn_limit;
 		bpf_prog_attach_xattr;
 		bpf_program__attach;
 		bpf_program__name;
+		bpf_program__is_extension;
+		bpf_program__is_struct_ops;
+		bpf_program__set_extension;
+		bpf_program__set_struct_ops;
 		btf__align_of;
+		libbpf_find_kernel_btf;
 } LIBBPF_0.0.6;
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index 4343e40588c6..0afb51f7a919 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -13,6 +13,9 @@
 
 #include "libbpf.h"
 
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
 #define ERRNO_OFFSET(e)		((e) - __LIBBPF_ERRNO__START)
 #define ERRCODE_OFFSET(c)	ERRNO_OFFSET(LIBBPF_ERRNO__##c)
 #define NR_ERRNO	(__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index a9eb8b322671..b782ebef6ac9 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -17,6 +17,9 @@
 #include "libbpf.h"
 #include "libbpf_internal.h"
 
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
 static bool grep(const char *buffer, const char *pattern)
 {
 	return !!strstr(buffer, pattern);
@@ -103,6 +106,8 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_STRUCT_OPS:
+	case BPF_PROG_TYPE_EXT:
 	default:
 		break;
 	}
@@ -251,6 +256,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_XSKMAP:
 	case BPF_MAP_TYPE_SOCKHASH:
 	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
+	case BPF_MAP_TYPE_STRUCT_OPS:
 	default:
 		break;
 	}
@@ -321,3 +327,24 @@ bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
 
 	return res;
 }
+
+/*
+ * Probe for availability of kernel commit (5.3):
+ *
+ * c04c0d2b968a ("bpf: increase complexity limit and maximum program size")
+ */
+bool bpf_probe_large_insn_limit(__u32 ifindex)
+{
+	struct bpf_insn insns[BPF_MAXINSNS + 1];
+	int i;
+
+	for (i = 0; i < BPF_MAXINSNS; i++)
+		insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1);
+	insns[BPF_MAXINSNS] = BPF_EXIT_INSN();
+
+	errno = 0;
+	probe_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
+		   ifindex);
+
+	return errno != E2BIG && errno != EINVAL;
+}
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 5065c1aa1061..431bd25c6cdb 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -15,6 +15,9 @@
 #include "libbpf_internal.h"
 #include "nlattr.h"
 
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
 #ifndef SOL_NETLINK
 #define SOL_NETLINK 270
 #endif
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index 8db44bbfc66d..0ad41dfea8eb 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -13,6 +13,9 @@
 #include <string.h>
 #include <stdio.h>
 
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
 static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = {
 	[LIBBPF_NLA_U8]		= sizeof(uint8_t),
 	[LIBBPF_NLA_U16]	= sizeof(uint16_t),
diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c
index b8064eedc177..146da01979c7 100644
--- a/tools/lib/bpf/str_error.c
+++ b/tools/lib/bpf/str_error.c
@@ -4,6 +4,9 @@
 #include <stdio.h>
 #include "str_error.h"
 
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
 /*
  * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl
  * libc, while checking strerror_r() return to avoid having to check this in
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 8e0ffa800a71..9807903f121e 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -32,6 +32,9 @@
 #include "libbpf_internal.h"
 #include "xsk.h"
 
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
 #ifndef SOL_XDP
  #define SOL_XDP 283
 #endif
diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c
index b9c203219691..49f4f84da485 100644
--- a/tools/perf/examples/bpf/5sec.c
+++ b/tools/perf/examples/bpf/5sec.c
@@ -39,7 +39,7 @@
    Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
 */
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
 {
diff --git a/tools/perf/examples/bpf/empty.c b/tools/perf/examples/bpf/empty.c
index 3776d26db9e7..7d7fb0c9fe76 100644
--- a/tools/perf/examples/bpf/empty.c
+++ b/tools/perf/examples/bpf/empty.c
@@ -1,3 +1,3 @@
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 license(GPL);
diff --git a/tools/perf/examples/bpf/sys_enter_openat.c b/tools/perf/examples/bpf/sys_enter_openat.c
index 9cd124b09392..c4481c390d23 100644
--- a/tools/perf/examples/bpf/sys_enter_openat.c
+++ b/tools/perf/examples/bpf/sys_enter_openat.c
@@ -14,7 +14,7 @@
  * the return value.
  */
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 struct syscall_enter_openat_args {
 	unsigned long long unused;
diff --git a/tools/perf/include/bpf/pid_filter.h b/tools/perf/include/bpf/pid_filter.h
index 6e61c4bdf548..607189a315b2 100644
--- a/tools/perf/include/bpf/pid_filter.h
+++ b/tools/perf/include/bpf/pid_filter.h
@@ -3,7 +3,7 @@
 #ifndef _PERF_BPF_PID_FILTER_
 #define _PERF_BPF_PID_FILTER_
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 #define pid_filter(name) pid_map(name, bool)
 
diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h
index 316af5b2ff35..7ca6fa5463ee 100644
--- a/tools/perf/include/bpf/stdio.h
+++ b/tools/perf/include/bpf/stdio.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 struct bpf_map SEC("maps") __bpf_stdout__ = {
        .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
diff --git a/tools/perf/include/bpf/unistd.h b/tools/perf/include/bpf/unistd.h
index ca7877f9a976..d1a35b6c649d 100644
--- a/tools/perf/include/bpf/unistd.h
+++ b/tools/perf/include/bpf/unistd.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: LGPL-2.1
 
-#include <bpf.h>
+#include <bpf/bpf.h>
 
 static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid;
 
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 301ac12d5d69..ec464859c6b6 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -22,17 +22,13 @@ get_cgroup_id_user
 test_skb_cgroup_id_user
 test_socket_cookie
 test_cgroup_storage
-test_select_reuseport
 test_flow_dissector
 flow_dissector_load
 test_netcnt
-test_section_names
 test_tcpnotify_user
 test_libbpf
 test_tcp_check_syncookie_user
 test_sysctl
-libbpf.pc
-libbpf.so.*
 test_hashmap
 test_btf_dump
 xdping
@@ -41,4 +37,4 @@ test_cpp
 /no_alu32
 /bpf_gcc
 /tools
-bpf_helper_defs.h
+
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f1f949cd8ed9..5f41f5bd8033 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -20,8 +20,8 @@ CLANG		?= clang
 LLC		?= llc
 LLVM_OBJCOPY	?= llvm-objcopy
 BPF_GCC		?= $(shell command -v bpf-gcc;)
-CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR)	\
-	  -I$(GENDIR) -I$(TOOLSINCDIR) -I$(CURDIR)			\
+CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(CURDIR) -I$(APIDIR)		\
+	  -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) -I$(TOOLSINCDIR)	\
 	  -Dbpf_prog_load=bpf_prog_test_load				\
 	  -Dbpf_load_program=bpf_test_load_program
 LDLIBS += -lcap -lelf -lz -lrt -lpthread
@@ -73,7 +73,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \
 # Compile but not part of 'make run_tests'
 TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
 	flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
-	test_lirc_mode2_user xdping test_cpp
+	test_lirc_mode2_user xdping test_cpp runqslower
 
 TEST_CUSTOM_PROGS = urandom_read
 
@@ -83,20 +83,29 @@ TEST_CUSTOM_PROGS = urandom_read
 # $3 - target (assumed to be file); only file name will be emitted;
 # $4 - optional extra arg, emitted as-is, if provided.
 ifeq ($(V),1)
+Q =
 msg =
 else
-msg = @$(info $(1)$(if $(2), [$(2)]) $(notdir $(3)))$(if $(4), $(4))
+Q = @
+msg = @printf '  %-8s%s %s%s\n' "$(1)" "$(if $(2), [$(2)])" "$(notdir $(3))" "$(if $(4), $(4))";
+MAKEFLAGS += --no-print-directory
+submake_extras := feature_display=0
 endif
 
 # override lib.mk's default rules
 OVERRIDE_TARGETS := 1
 override define CLEAN
-	$(call msg,    CLEAN)
+	$(call msg,CLEAN)
 	$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
 endef
 
 include ../lib.mk
 
+SCRATCH_DIR := $(OUTPUT)/tools
+BUILD_DIR := $(SCRATCH_DIR)/build
+INCLUDE_DIR := $(SCRATCH_DIR)/include
+BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a
+
 # Define simple and short `make test_progs`, `make test_sysctl`, etc targets
 # to build individual tests.
 # NOTE: Semicolon at the end is critical to override lib.mk's default static
@@ -108,18 +117,25 @@ $(notdir $(TEST_GEN_PROGS)						\
 	 $(TEST_CUSTOM_PROGS)): %: $(OUTPUT)/% ;
 
 $(OUTPUT)/%:%.c
-	$(call msg,     BINARY,,$@)
+	$(call msg,BINARY,,$@)
 	$(LINK.c) $^ $(LDLIBS) -o $@
 
 $(OUTPUT)/urandom_read: urandom_read.c
-	$(call msg,     BINARY,,$@)
-	$(CC) -o $@ $< -Wl,--build-id
+	$(call msg,BINARY,,$@)
+	$(CC) $(LDFLAGS) -o $@ $< $(LDLIBS) -Wl,--build-id
 
-$(OUTPUT)/test_stub.o: test_stub.c
-	$(call msg,         CC,,$@)
+$(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ)
+	$(call msg,CC,,$@)
 	$(CC) -c $(CFLAGS) -o $@ $<
 
-BPFOBJ := $(OUTPUT)/libbpf.a
+VMLINUX_BTF_PATHS := $(abspath ../../../../vmlinux)			\
+			       /sys/kernel/btf/vmlinux			\
+			       /boot/vmlinux-$(shell uname -r)
+VMLINUX_BTF:= $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))
+$(OUTPUT)/runqslower: $(BPFOBJ)
+	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower	\
+		    OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF)   \
+		    BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR)
 
 $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ)
 
@@ -137,23 +153,22 @@ $(OUTPUT)/test_netcnt: cgroup_helpers.c
 $(OUTPUT)/test_sock_fields: cgroup_helpers.c
 $(OUTPUT)/test_sysctl: cgroup_helpers.c
 
-.PHONY: force
-
-# force a rebuild of BPFOBJ when its dependencies are updated
-force:
-
-DEFAULT_BPFTOOL := $(OUTPUT)/tools/usr/local/sbin/bpftool
+DEFAULT_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool
 BPFTOOL ?= $(DEFAULT_BPFTOOL)
+$(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BUILD_DIR)/bpftool
+	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)			\
+		    OUTPUT=$(BUILD_DIR)/bpftool/			\
+		    prefix= DESTDIR=$(SCRATCH_DIR)/ install
 
-$(DEFAULT_BPFTOOL): force
-	$(MAKE) -C $(BPFTOOLDIR) DESTDIR=$(OUTPUT)/tools install
-
-$(BPFOBJ): force
-	$(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/
+$(BPFOBJ): $(wildcard $(BPFDIR)/*.c $(BPFDIR)/*.h $(BPFDIR)/Makefile)          \
+	   ../../../include/uapi/linux/bpf.h                                   \
+	   | $(INCLUDE_DIR) $(BUILD_DIR)/libbpf
+	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
+		DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
 
-BPF_HELPERS := $(OUTPUT)/bpf_helper_defs.h $(wildcard $(BPFDIR)/bpf_*.h)
-$(OUTPUT)/bpf_helper_defs.h:
-	$(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ $(OUTPUT)/bpf_helper_defs.h
+$(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(INCLUDE_DIR):
+	$(call msg,MKDIR,,$@)
+	mkdir -p $@
 
 # Get Clang's default includes on this system, as opposed to those seen by
 # '-target bpf'. This fixes "missing" files on some architectures/distros,
@@ -173,8 +188,8 @@ MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian)
 
 CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG))
 BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) 			\
-	     -I. -I./include/uapi -I$(APIDIR)				\
-	     -I$(BPFDIR) -I$(abspath $(OUTPUT)/../usr/include)
+	     -I$(INCLUDE_DIR) -I$(CURDIR) -I$(CURDIR)/include/uapi	\
+	     -I$(APIDIR) -I$(abspath $(OUTPUT)/../usr/include)
 
 CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
 	       -Wno-compare-distinct-pointer-types
@@ -190,28 +205,28 @@ $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h
 # $3 - CFLAGS
 # $4 - LDFLAGS
 define CLANG_BPF_BUILD_RULE
-	$(call msg,  CLANG-LLC,$(TRUNNER_BINARY),$2)
+	$(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2)
 	($(CLANG) $3 -O2 -target bpf -emit-llvm				\
 		-c $1 -o - || echo "BPF obj compilation failed") | 	\
 	$(LLC) -mattr=dwarfris -march=bpf -mcpu=probe $4 -filetype=obj -o $2
 endef
 # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
 define CLANG_NOALU32_BPF_BUILD_RULE
-	$(call msg,  CLANG-LLC,$(TRUNNER_BINARY),$2)
+	$(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2)
 	($(CLANG) $3 -O2 -target bpf -emit-llvm				\
 		-c $1 -o - || echo "BPF obj compilation failed") | 	\
 	$(LLC) -march=bpf -mcpu=v2 $4 -filetype=obj -o $2
 endef
 # Similar to CLANG_BPF_BUILD_RULE, but using native Clang and bpf LLC
 define CLANG_NATIVE_BPF_BUILD_RULE
-	$(call msg,  CLANG-BPF,$(TRUNNER_BINARY),$2)
+	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
 	($(CLANG) $3 -O2 -emit-llvm					\
 		-c $1 -o - || echo "BPF obj compilation failed") | 	\
 	$(LLC) -march=bpf -mcpu=probe $4 -filetype=obj -o $2
 endef
 # Build BPF object using GCC
 define GCC_BPF_BUILD_RULE
-	$(call msg,    GCC-BPF,$(TRUNNER_BINARY),$2)
+	$(call msg,GCC-BPF,$(TRUNNER_BINARY),$2)
 	$(BPF_GCC) $3 $4 -O2 -c $1 -o $2
 endef
 
@@ -252,6 +267,7 @@ define DEFINE_TEST_RUNNER_RULES
 ifeq ($($(TRUNNER_OUTPUT)-dir),)
 $(TRUNNER_OUTPUT)-dir := y
 $(TRUNNER_OUTPUT):
+	$$(call msg,MKDIR,,$$@)
 	mkdir -p $$@
 endif
 
@@ -262,7 +278,7 @@ $(TRUNNER_BPF_PROGS_DIR)$(if $2,-)$2-bpfobjs := y
 $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 		     $(TRUNNER_BPF_PROGS_DIR)/%.c			\
 		     $(TRUNNER_BPF_PROGS_DIR)/*.h			\
-		     $$(BPF_HELPERS) | $(TRUNNER_OUTPUT)
+		     $$(BPFOBJ) | $(TRUNNER_OUTPUT)
 	$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@,			\
 					  $(TRUNNER_BPF_CFLAGS),	\
 					  $(TRUNNER_BPF_LDFLAGS))
@@ -270,7 +286,7 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 $(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h:			\
 		      $(TRUNNER_OUTPUT)/%.o				\
 		      | $(BPFTOOL) $(TRUNNER_OUTPUT)
-	$$(call msg,   GEN-SKEL,$(TRUNNER_BINARY),$$@)
+	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
 	$$(BPFTOOL) gen skeleton $$< > $$@
 endif
 
@@ -278,7 +294,7 @@ endif
 ifeq ($($(TRUNNER_TESTS_DIR)-tests-hdr),)
 $(TRUNNER_TESTS_DIR)-tests-hdr := y
 $(TRUNNER_TESTS_HDR): $(TRUNNER_TESTS_DIR)/*.c
-	$$(call msg,   TEST-HDR,$(TRUNNER_BINARY),$$@)
+	$$(call msg,TEST-HDR,$(TRUNNER_BINARY),$$@)
 	$$(shell ( cd $(TRUNNER_TESTS_DIR);				\
 		  echo '/* Generated header, do not edit */';		\
 		  ls *.c 2> /dev/null |					\
@@ -294,7 +310,7 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o:			\
 		      $(TRUNNER_BPF_OBJS)				\
 		      $(TRUNNER_BPF_SKELS)				\
 		      $$(BPFOBJ) | $(TRUNNER_OUTPUT)
-	$$(call msg,   TEST-OBJ,$(TRUNNER_BINARY),$$@)
+	$$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@)
 	cd $$(@D) && $$(CC) $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
 
 $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
@@ -302,20 +318,20 @@ $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 		       $(TRUNNER_EXTRA_HDRS)				\
 		       $(TRUNNER_TESTS_HDR)				\
 		       $$(BPFOBJ) | $(TRUNNER_OUTPUT)
-	$$(call msg,  EXTRA-OBJ,$(TRUNNER_BINARY),$$@)
+	$$(call msg,EXT-OBJ,$(TRUNNER_BINARY),$$@)
 	$$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@
 
 # only copy extra resources if in flavored build
 $(TRUNNER_BINARY)-extras: $(TRUNNER_EXTRA_FILES) | $(TRUNNER_OUTPUT)
 ifneq ($2,)
-	$$(call msg,  EXTRAS-CP,$(TRUNNER_BINARY),$(TRUNNER_EXTRA_FILES))
+	$$(call msg,EXT-COPY,$(TRUNNER_BINARY),$(TRUNNER_EXTRA_FILES))
 	cp -a $$^ $(TRUNNER_OUTPUT)/
 endif
 
 $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS)			\
 			     $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ)		\
 			     | $(TRUNNER_BINARY)-extras
-	$$(call msg,     BINARY,,$$@)
+	$$(call msg,BINARY,,$$@)
 	$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@
 
 endef
@@ -328,7 +344,7 @@ TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c	\
 TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read				\
 		       $(wildcard progs/btf_dump_test_case_*.c)
 TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE
-TRUNNER_BPF_CFLAGS := -I. -I$(OUTPUT) $(BPF_CFLAGS) $(CLANG_CFLAGS)
+TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS)
 TRUNNER_BPF_LDFLAGS := -mattr=+alu32
 $(eval $(call DEFINE_TEST_RUNNER,test_progs))
 
@@ -367,15 +383,15 @@ verifier/tests.h: verifier/*.c
 		  echo '#endif' \
 		) > verifier/tests.h)
 $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT)
-	$(call msg,     BINARY,,$@)
+	$(call msg,BINARY,,$@)
 	$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
 
 # Make sure we are able to include and link libbpf against c++.
 $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
-	$(call msg,        CXX,,$@)
+	$(call msg,CXX,,$@)
 	$(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@
 
-EXTRA_CLEAN := $(TEST_CUSTOM_PROGS)					\
+EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR)			\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
-	feature $(OUTPUT)/*.o $(OUTPUT)/no_alu32 $(OUTPUT)/bpf_gcc	\
-	tools *.skel.h
+	feature								\
+	$(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc)
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
new file mode 100644
index 000000000000..8f21965ffc6c
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -0,0 +1,235 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BPF_TCP_HELPERS_H
+#define __BPF_TCP_HELPERS_H
+
+#include <stdbool.h>
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_trace_helpers.h"
+
+#define BPF_STRUCT_OPS(name, args...) \
+SEC("struct_ops/"#name) \
+BPF_PROG(name, args)
+
+#define tcp_jiffies32 ((__u32)bpf_jiffies64())
+
+struct sock_common {
+	unsigned char	skc_state;
+} __attribute__((preserve_access_index));
+
+enum sk_pacing {
+	SK_PACING_NONE		= 0,
+	SK_PACING_NEEDED	= 1,
+	SK_PACING_FQ		= 2,
+};
+
+struct sock {
+	struct sock_common	__sk_common;
+	unsigned long		sk_pacing_rate;
+	__u32			sk_pacing_status; /* see enum sk_pacing */
+} __attribute__((preserve_access_index));
+
+struct inet_sock {
+	struct sock		sk;
+} __attribute__((preserve_access_index));
+
+struct inet_connection_sock {
+	struct inet_sock	  icsk_inet;
+	__u8			  icsk_ca_state:6,
+				  icsk_ca_setsockopt:1,
+				  icsk_ca_dst_locked:1;
+	struct {
+		__u8		  pending;
+	} icsk_ack;
+	__u64			  icsk_ca_priv[104 / sizeof(__u64)];
+} __attribute__((preserve_access_index));
+
+struct tcp_sock {
+	struct inet_connection_sock	inet_conn;
+
+	__u32	rcv_nxt;
+	__u32	snd_nxt;
+	__u32	snd_una;
+	__u8	ecn_flags;
+	__u32	delivered;
+	__u32	delivered_ce;
+	__u32	snd_cwnd;
+	__u32	snd_cwnd_cnt;
+	__u32	snd_cwnd_clamp;
+	__u32	snd_ssthresh;
+	__u8	syn_data:1,	/* SYN includes data */
+		syn_fastopen:1,	/* SYN includes Fast Open option */
+		syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
+		syn_fastopen_ch:1, /* Active TFO re-enabling probe */
+		syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
+		save_syn:1,	/* Save headers of SYN packet */
+		is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
+		syn_smc:1;	/* SYN includes SMC */
+	__u32	max_packets_out;
+	__u32	lsndtime;
+	__u32	prior_cwnd;
+	__u64	tcp_mstamp;	/* most recent packet received/sent */
+} __attribute__((preserve_access_index));
+
+static __always_inline struct inet_connection_sock *inet_csk(const struct sock *sk)
+{
+	return (struct inet_connection_sock *)sk;
+}
+
+static __always_inline void *inet_csk_ca(const struct sock *sk)
+{
+	return (void *)inet_csk(sk)->icsk_ca_priv;
+}
+
+static __always_inline struct tcp_sock *tcp_sk(const struct sock *sk)
+{
+	return (struct tcp_sock *)sk;
+}
+
+static __always_inline bool before(__u32 seq1, __u32 seq2)
+{
+	return (__s32)(seq1-seq2) < 0;
+}
+#define after(seq2, seq1) 	before(seq1, seq2)
+
+#define	TCP_ECN_OK		1
+#define	TCP_ECN_QUEUE_CWR	2
+#define	TCP_ECN_DEMAND_CWR	4
+#define	TCP_ECN_SEEN		8
+
+enum inet_csk_ack_state_t {
+	ICSK_ACK_SCHED	= 1,
+	ICSK_ACK_TIMER  = 2,
+	ICSK_ACK_PUSHED = 4,
+	ICSK_ACK_PUSHED2 = 8,
+	ICSK_ACK_NOW = 16	/* Send the next ACK immediately (once) */
+};
+
+enum tcp_ca_event {
+	CA_EVENT_TX_START = 0,
+	CA_EVENT_CWND_RESTART = 1,
+	CA_EVENT_COMPLETE_CWR = 2,
+	CA_EVENT_LOSS = 3,
+	CA_EVENT_ECN_NO_CE = 4,
+	CA_EVENT_ECN_IS_CE = 5,
+};
+
+enum tcp_ca_state {
+	TCP_CA_Open = 0,
+	TCP_CA_Disorder = 1,
+	TCP_CA_CWR = 2,
+	TCP_CA_Recovery = 3,
+	TCP_CA_Loss = 4
+};
+
+struct ack_sample {
+	__u32 pkts_acked;
+	__s32 rtt_us;
+	__u32 in_flight;
+} __attribute__((preserve_access_index));
+
+struct rate_sample {
+	__u64  prior_mstamp; /* starting timestamp for interval */
+	__u32  prior_delivered;	/* tp->delivered at "prior_mstamp" */
+	__s32  delivered;		/* number of packets delivered over interval */
+	long interval_us;	/* time for tp->delivered to incr "delivered" */
+	__u32 snd_interval_us;	/* snd interval for delivered packets */
+	__u32 rcv_interval_us;	/* rcv interval for delivered packets */
+	long rtt_us;		/* RTT of last (S)ACKed packet (or -1) */
+	int  losses;		/* number of packets marked lost upon ACK */
+	__u32  acked_sacked;	/* number of packets newly (S)ACKed upon ACK */
+	__u32  prior_in_flight;	/* in flight before this ACK */
+	bool is_app_limited;	/* is sample from packet with bubble in pipe? */
+	bool is_retrans;	/* is sample from retransmission? */
+	bool is_ack_delayed;	/* is this (likely) a delayed ACK? */
+} __attribute__((preserve_access_index));
+
+#define TCP_CA_NAME_MAX		16
+#define TCP_CONG_NEEDS_ECN	0x2
+
+struct tcp_congestion_ops {
+	char name[TCP_CA_NAME_MAX];
+	__u32 flags;
+
+	/* initialize private data (optional) */
+	void (*init)(struct sock *sk);
+	/* cleanup private data  (optional) */
+	void (*release)(struct sock *sk);
+
+	/* return slow start threshold (required) */
+	__u32 (*ssthresh)(struct sock *sk);
+	/* do new cwnd calculation (required) */
+	void (*cong_avoid)(struct sock *sk, __u32 ack, __u32 acked);
+	/* call before changing ca_state (optional) */
+	void (*set_state)(struct sock *sk, __u8 new_state);
+	/* call when cwnd event occurs (optional) */
+	void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
+	/* call when ack arrives (optional) */
+	void (*in_ack_event)(struct sock *sk, __u32 flags);
+	/* new value of cwnd after loss (required) */
+	__u32  (*undo_cwnd)(struct sock *sk);
+	/* hook for packet ack accounting (optional) */
+	void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
+	/* override sysctl_tcp_min_tso_segs */
+	__u32 (*min_tso_segs)(struct sock *sk);
+	/* returns the multiplier used in tcp_sndbuf_expand (optional) */
+	__u32 (*sndbuf_expand)(struct sock *sk);
+	/* call when packets are delivered to update cwnd and pacing rate,
+	 * after all the ca_state processing. (optional)
+	 */
+	void (*cong_control)(struct sock *sk, const struct rate_sample *rs);
+};
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+#define max(a, b) ((a) > (b) ? (a) : (b))
+#define min_not_zero(x, y) ({			\
+	typeof(x) __x = (x);			\
+	typeof(y) __y = (y);			\
+	__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
+
+static __always_inline __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked)
+{
+	__u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh);
+
+	acked -= cwnd - tp->snd_cwnd;
+	tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
+
+	return acked;
+}
+
+static __always_inline bool tcp_in_slow_start(const struct tcp_sock *tp)
+{
+	return tp->snd_cwnd < tp->snd_ssthresh;
+}
+
+static __always_inline bool tcp_is_cwnd_limited(const struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+
+	/* If in slow start, ensure cwnd grows to twice what was ACKed. */
+	if (tcp_in_slow_start(tp))
+		return tp->snd_cwnd < 2 * tp->max_packets_out;
+
+	return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited);
+}
+
+static __always_inline void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked)
+{
+	/* If credits accumulated at a higher w, apply them gently now. */
+	if (tp->snd_cwnd_cnt >= w) {
+		tp->snd_cwnd_cnt = 0;
+		tp->snd_cwnd++;
+	}
+
+	tp->snd_cwnd_cnt += acked;
+	if (tp->snd_cwnd_cnt >= w) {
+		__u32 delta = tp->snd_cwnd_cnt / w;
+
+		tp->snd_cwnd_cnt -= delta * w;
+		tp->snd_cwnd += delta;
+	}
+	tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp);
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/bpf_trace_helpers.h b/tools/testing/selftests/bpf/bpf_trace_helpers.h
index c76a214a53b0..c6f1354d93fb 100644
--- a/tools/testing/selftests/bpf/bpf_trace_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_trace_helpers.h
@@ -1,58 +1,120 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 #ifndef __BPF_TRACE_HELPERS_H
 #define __BPF_TRACE_HELPERS_H
 
-#include "bpf_helpers.h"
-
-#define __BPF_MAP_0(i, m, v, ...) v
-#define __BPF_MAP_1(i, m, v, t, a, ...) m(t, a, ctx[i])
-#define __BPF_MAP_2(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_1(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_3(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_2(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_4(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_3(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_5(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_4(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_6(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_5(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_7(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_6(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_8(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_7(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_9(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_8(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_10(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_9(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_11(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_10(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_12(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_11(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP(n, ...) __BPF_MAP_##n(0, __VA_ARGS__)
-
-/* BPF sizeof(void *) is always 8, so no need to cast to long first
- * for ptr to avoid compiler warning.
+#include <bpf/bpf_helpers.h>
+
+#define ___bpf_concat(a, b) a ## b
+#define ___bpf_apply(fn, n) ___bpf_concat(fn, n)
+#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
+#define ___bpf_narg(...) \
+	___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#define ___bpf_empty(...) \
+	___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0)
+
+#define ___bpf_ctx_cast0() ctx
+#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0]
+#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1]
+#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2]
+#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3]
+#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4]
+#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5]
+#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6]
+#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7]
+#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8]
+#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9]
+#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10]
+#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11]
+#define ___bpf_ctx_cast(args...) \
+	___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
+
+/*
+ * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
+ * similar kinds of BPF programs, that accept input arguments as a single
+ * pointer to untyped u64 array, where each u64 can actually be a typed
+ * pointer or integer of different size. Instead of requring user to write
+ * manual casts and work with array elements by index, BPF_PROG macro
+ * allows user to declare a list of named and typed input arguments in the
+ * same syntax as for normal C function. All the casting is hidden and
+ * performed transparently, while user code can just assume working with
+ * function arguments of specified type and name.
+ *
+ * Original raw context argument is preserved as well as 'ctx' argument.
+ * This is useful when using BPF helpers that expect original context
+ * as one of the parameters (e.g., for bpf_perf_event_output()).
  */
-#define __BPF_CAST(t, a, ctx) (t) ctx
-#define __BPF_V void
-#define __BPF_N
-
-#define __BPF_DECL_ARGS(t, a, ctx) t a
-
-#define BPF_TRACE_x(x, sec_name, fname, ret_type, ...)			\
-static __always_inline ret_type						\
-____##fname(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__));	\
-									\
-SEC(sec_name)								\
-ret_type fname(__u64 *ctx)						\
-{									\
-	return ____##fname(__BPF_MAP(x, __BPF_CAST, __BPF_N, __VA_ARGS__));\
-}									\
-									\
-static __always_inline							\
-ret_type ____##fname(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__))
-
-#define BPF_TRACE_0(sec, fname, ...)  BPF_TRACE_x(0, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_1(sec, fname, ...)  BPF_TRACE_x(1, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_2(sec, fname, ...)  BPF_TRACE_x(2, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_3(sec, fname, ...)  BPF_TRACE_x(3, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_4(sec, fname, ...)  BPF_TRACE_x(4, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_5(sec, fname, ...)  BPF_TRACE_x(5, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_6(sec, fname, ...)  BPF_TRACE_x(6, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_7(sec, fname, ...)  BPF_TRACE_x(7, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_8(sec, fname, ...)  BPF_TRACE_x(8, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_9(sec, fname, ...)  BPF_TRACE_x(9, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_10(sec, fname, ...)  BPF_TRACE_x(10, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_11(sec, fname, ...)  BPF_TRACE_x(11, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_12(sec, fname, ...)  BPF_TRACE_x(12, sec, fname, int, __VA_ARGS__)
+#define BPF_PROG(name, args...)						    \
+name(unsigned long long *ctx);						    \
+static __always_inline typeof(name(0))					    \
+____##name(unsigned long long *ctx, ##args);				    \
+typeof(name(0)) name(unsigned long long *ctx)				    \
+{									    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_ctx_cast(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __always_inline typeof(name(0))					    \
+____##name(unsigned long long *ctx, ##args)
+
+struct pt_regs;
+
+#define ___bpf_kprobe_args0() ctx
+#define ___bpf_kprobe_args1(x) \
+	___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
+#define ___bpf_kprobe_args2(x, args...) \
+	___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
+#define ___bpf_kprobe_args3(x, args...) \
+	___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
+#define ___bpf_kprobe_args4(x, args...) \
+	___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
+#define ___bpf_kprobe_args5(x, args...) \
+	___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args(args...) \
+	___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
 
+/*
+ * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for
+ * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific
+ * low-level way of getting kprobe input arguments from struct pt_regs, and
+ * provides a familiar typed and named function arguments syntax and
+ * semantics of accessing kprobe input paremeters.
+ *
+ * Original struct pt_regs* context is preserved as 'ctx' argument. This might
+ * be necessary when using BPF helpers like bpf_perf_event_output().
+ */
+#define BPF_KPROBE(name, args...)					    \
+name(struct pt_regs *ctx);						    \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\
+typeof(name(0)) name(struct pt_regs *ctx)				    \
+{									    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_kprobe_args(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
+
+#define ___bpf_kretprobe_args0() ctx
+#define ___bpf_kretprobe_argsN(x, args...) \
+	___bpf_kprobe_args(args), (void *)PT_REGS_RET(ctx)
+#define ___bpf_kretprobe_args(args...) \
+	___bpf_apply(___bpf_kretprobe_args, ___bpf_empty(args))(args)
+
+/*
+ * BPF_KRETPROBE is similar to BPF_KPROBE, except, in addition to listing all
+ * input kprobe arguments, one last extra argument has to be specified, which
+ * captures kprobe return value.
+ */
+#define BPF_KRETPROBE(name, args...)					    \
+name(struct pt_regs *ctx);						    \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\
+typeof(name(0)) name(struct pt_regs *ctx)				    \
+{									    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_kretprobe_args(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 #endif
diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index ec219f84e041..a3352a64c067 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -6,7 +6,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <errno.h>
-#include <libbpf.h> /* libbpf_num_possible_cpus */
+#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
 
 static inline unsigned int bpf_num_possible_cpus(void)
 {
diff --git a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
new file mode 100644
index 000000000000..f0a64d8ac59a
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <test_maps.h>
+
+static void map_batch_update(int map_fd, __u32 max_entries, int *keys,
+			     int *values)
+{
+	int i, err;
+	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+		.elem_flags = 0,
+		.flags = 0,
+	);
+
+	for (i = 0; i < max_entries; i++) {
+		keys[i] = i;
+		values[i] = i + 1;
+	}
+
+	err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts);
+	CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno));
+}
+
+static void map_batch_verify(int *visited, __u32 max_entries,
+			     int *keys, int *values)
+{
+	int i;
+
+	memset(visited, 0, max_entries * sizeof(*visited));
+	for (i = 0; i < max_entries; i++) {
+		CHECK(keys[i] + 1 != values[i], "key/value checking",
+		      "error: i %d key %d value %d\n", i, keys[i], values[i]);
+		visited[i] = 1;
+	}
+	for (i = 0; i < max_entries; i++) {
+		CHECK(visited[i] != 1, "visited checking",
+		      "error: keys array at index %d missing\n", i);
+	}
+}
+
+void test_array_map_batch_ops(void)
+{
+	struct bpf_create_map_attr xattr = {
+		.name = "array_map",
+		.map_type = BPF_MAP_TYPE_ARRAY,
+		.key_size = sizeof(int),
+		.value_size = sizeof(int),
+	};
+	int map_fd, *keys, *values, *visited;
+	__u32 count, total, total_success;
+	const __u32 max_entries = 10;
+	bool nospace_err;
+	__u64 batch = 0;
+	int err, step;
+	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+		.elem_flags = 0,
+		.flags = 0,
+	);
+
+	xattr.max_entries = max_entries;
+	map_fd = bpf_create_map_xattr(&xattr);
+	CHECK(map_fd == -1,
+	      "bpf_create_map_xattr()", "error:%s\n", strerror(errno));
+
+	keys = malloc(max_entries * sizeof(int));
+	values = malloc(max_entries * sizeof(int));
+	visited = malloc(max_entries * sizeof(int));
+	CHECK(!keys || !values || !visited, "malloc()", "error:%s\n",
+	      strerror(errno));
+
+	/* populate elements to the map */
+	map_batch_update(map_fd, max_entries, keys, values);
+
+	/* test 1: lookup in a loop with various steps. */
+	total_success = 0;
+	for (step = 1; step < max_entries; step++) {
+		map_batch_update(map_fd, max_entries, keys, values);
+		map_batch_verify(visited, max_entries, keys, values);
+		memset(keys, 0, max_entries * sizeof(*keys));
+		memset(values, 0, max_entries * sizeof(*values));
+		batch = 0;
+		total = 0;
+		/* iteratively lookup/delete elements with 'step'
+		 * elements each.
+		 */
+		count = step;
+		nospace_err = false;
+		while (true) {
+			err = bpf_map_lookup_batch(map_fd,
+						total ? &batch : NULL, &batch,
+						keys + total,
+						values + total,
+						&count, &opts);
+
+			CHECK((err && errno != ENOENT), "lookup with steps",
+			      "error: %s\n", strerror(errno));
+
+			total += count;
+			if (err)
+				break;
+
+		}
+
+		if (nospace_err == true)
+			continue;
+
+		CHECK(total != max_entries, "lookup with steps",
+		      "total = %u, max_entries = %u\n", total, max_entries);
+
+		map_batch_verify(visited, max_entries, keys, values);
+
+		total_success++;
+	}
+
+	CHECK(total_success == 0, "check total_success",
+	      "unexpected failure\n");
+
+	printf("%s:PASS\n", __func__);
+
+	free(keys);
+	free(values);
+	free(visited);
+}
diff --git a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c
new file mode 100644
index 000000000000..976bf415fbdd
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook  */
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <bpf_util.h>
+#include <test_maps.h>
+
+static void map_batch_update(int map_fd, __u32 max_entries, int *keys,
+			     void *values, bool is_pcpu)
+{
+	typedef BPF_DECLARE_PERCPU(int, value);
+	value *v = NULL;
+	int i, j, err;
+	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+		.elem_flags = 0,
+		.flags = 0,
+	);
+
+	if (is_pcpu)
+		v = (value *)values;
+
+	for (i = 0; i < max_entries; i++) {
+		keys[i] = i + 1;
+		if (is_pcpu)
+			for (j = 0; j < bpf_num_possible_cpus(); j++)
+				bpf_percpu(v[i], j) = i + 2 + j;
+		else
+			((int *)values)[i] = i + 2;
+	}
+
+	err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts);
+	CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno));
+}
+
+static void map_batch_verify(int *visited, __u32 max_entries,
+			     int *keys, void *values, bool is_pcpu)
+{
+	typedef BPF_DECLARE_PERCPU(int, value);
+	value *v = NULL;
+	int i, j;
+
+	if (is_pcpu)
+		v = (value *)values;
+
+	memset(visited, 0, max_entries * sizeof(*visited));
+	for (i = 0; i < max_entries; i++) {
+
+		if (is_pcpu) {
+			for (j = 0; j < bpf_num_possible_cpus(); j++) {
+				CHECK(keys[i] + 1 + j != bpf_percpu(v[i], j),
+				      "key/value checking",
+				      "error: i %d j %d key %d value %d\n",
+				      i, j, keys[i], bpf_percpu(v[i],  j));
+			}
+		} else {
+			CHECK(keys[i] + 1 != ((int *)values)[i],
+			      "key/value checking",
+			      "error: i %d key %d value %d\n", i, keys[i],
+			      ((int *)values)[i]);
+		}
+
+		visited[i] = 1;
+
+	}
+	for (i = 0; i < max_entries; i++) {
+		CHECK(visited[i] != 1, "visited checking",
+		      "error: keys array at index %d missing\n", i);
+	}
+}
+
+void __test_map_lookup_and_delete_batch(bool is_pcpu)
+{
+	__u32 batch, count, total, total_success;
+	typedef BPF_DECLARE_PERCPU(int, value);
+	int map_fd, *keys, *visited, key;
+	const __u32 max_entries = 10;
+	value pcpu_values[max_entries];
+	int err, step, value_size;
+	bool nospace_err;
+	void *values;
+	struct bpf_create_map_attr xattr = {
+		.name = "hash_map",
+		.map_type = is_pcpu ? BPF_MAP_TYPE_PERCPU_HASH :
+			    BPF_MAP_TYPE_HASH,
+		.key_size = sizeof(int),
+		.value_size = sizeof(int),
+	};
+	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+		.elem_flags = 0,
+		.flags = 0,
+	);
+
+	xattr.max_entries = max_entries;
+	map_fd = bpf_create_map_xattr(&xattr);
+	CHECK(map_fd == -1,
+	      "bpf_create_map_xattr()", "error:%s\n", strerror(errno));
+
+	value_size = is_pcpu ? sizeof(value) : sizeof(int);
+	keys = malloc(max_entries * sizeof(int));
+	if (is_pcpu)
+		values = pcpu_values;
+	else
+		values = malloc(max_entries * sizeof(int));
+	visited = malloc(max_entries * sizeof(int));
+	CHECK(!keys || !values || !visited, "malloc()",
+	      "error:%s\n", strerror(errno));
+
+	/* test 1: lookup/delete an empty hash table, -ENOENT */
+	count = max_entries;
+	err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys,
+					      values, &count, &opts);
+	CHECK((err && errno != ENOENT), "empty map",
+	      "error: %s\n", strerror(errno));
+
+	/* populate elements to the map */
+	map_batch_update(map_fd, max_entries, keys, values, is_pcpu);
+
+	/* test 2: lookup/delete with count = 0, success */
+	count = 0;
+	err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys,
+					      values, &count, &opts);
+	CHECK(err, "count = 0", "error: %s\n", strerror(errno));
+
+	/* test 3: lookup/delete with count = max_entries, success */
+	memset(keys, 0, max_entries * sizeof(*keys));
+	memset(values, 0, max_entries * value_size);
+	count = max_entries;
+	err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys,
+					      values, &count, &opts);
+	CHECK((err && errno != ENOENT), "count = max_entries",
+	       "error: %s\n", strerror(errno));
+	CHECK(count != max_entries, "count = max_entries",
+	      "count = %u, max_entries = %u\n", count, max_entries);
+	map_batch_verify(visited, max_entries, keys, values, is_pcpu);
+
+	/* bpf_map_get_next_key() should return -ENOENT for an empty map. */
+	err = bpf_map_get_next_key(map_fd, NULL, &key);
+	CHECK(!err, "bpf_map_get_next_key()", "error: %s\n", strerror(errno));
+
+	/* test 4: lookup/delete in a loop with various steps. */
+	total_success = 0;
+	for (step = 1; step < max_entries; step++) {
+		map_batch_update(map_fd, max_entries, keys, values, is_pcpu);
+		memset(keys, 0, max_entries * sizeof(*keys));
+		memset(values, 0, max_entries * value_size);
+		total = 0;
+		/* iteratively lookup/delete elements with 'step'
+		 * elements each
+		 */
+		count = step;
+		nospace_err = false;
+		while (true) {
+			err = bpf_map_lookup_batch(map_fd,
+						   total ? &batch : NULL,
+						   &batch, keys + total,
+						   values +
+						   total * value_size,
+						   &count, &opts);
+			/* It is possible that we are failing due to buffer size
+			 * not big enough. In such cases, let us just exit and
+			 * go with large steps. Not that a buffer size with
+			 * max_entries should always work.
+			 */
+			if (err && errno == ENOSPC) {
+				nospace_err = true;
+				break;
+			}
+
+			CHECK((err && errno != ENOENT), "lookup with steps",
+			      "error: %s\n", strerror(errno));
+
+			total += count;
+			if (err)
+				break;
+
+		}
+		if (nospace_err == true)
+			continue;
+
+		CHECK(total != max_entries, "lookup with steps",
+		      "total = %u, max_entries = %u\n", total, max_entries);
+		map_batch_verify(visited, max_entries, keys, values, is_pcpu);
+
+		total = 0;
+		count = step;
+		while (total < max_entries) {
+			if (max_entries - total < step)
+				count = max_entries - total;
+			err = bpf_map_delete_batch(map_fd,
+						   keys + total,
+						   &count, &opts);
+			CHECK((err && errno != ENOENT), "delete batch",
+			      "error: %s\n", strerror(errno));
+			total += count;
+			if (err)
+				break;
+		}
+		CHECK(total != max_entries, "delete with steps",
+		      "total = %u, max_entries = %u\n", total, max_entries);
+
+		/* check map is empty, errono == ENOENT */
+		err = bpf_map_get_next_key(map_fd, NULL, &key);
+		CHECK(!err || errno != ENOENT, "bpf_map_get_next_key()",
+		      "error: %s\n", strerror(errno));
+
+		/* iteratively lookup/delete elements with 'step'
+		 * elements each
+		 */
+		map_batch_update(map_fd, max_entries, keys, values, is_pcpu);
+		memset(keys, 0, max_entries * sizeof(*keys));
+		memset(values, 0, max_entries * value_size);
+		total = 0;
+		count = step;
+		nospace_err = false;
+		while (true) {
+			err = bpf_map_lookup_and_delete_batch(map_fd,
+							total ? &batch : NULL,
+							&batch, keys + total,
+							values +
+							total * value_size,
+							&count, &opts);
+			/* It is possible that we are failing due to buffer size
+			 * not big enough. In such cases, let us just exit and
+			 * go with large steps. Not that a buffer size with
+			 * max_entries should always work.
+			 */
+			if (err && errno == ENOSPC) {
+				nospace_err = true;
+				break;
+			}
+
+			CHECK((err && errno != ENOENT), "lookup with steps",
+			      "error: %s\n", strerror(errno));
+
+			total += count;
+			if (err)
+				break;
+		}
+
+		if (nospace_err == true)
+			continue;
+
+		CHECK(total != max_entries, "lookup/delete with steps",
+		      "total = %u, max_entries = %u\n", total, max_entries);
+
+		map_batch_verify(visited, max_entries, keys, values, is_pcpu);
+		err = bpf_map_get_next_key(map_fd, NULL, &key);
+		CHECK(!err, "bpf_map_get_next_key()", "error: %s\n",
+		      strerror(errno));
+
+		total_success++;
+	}
+
+	CHECK(total_success == 0, "check total_success",
+	      "unexpected failure\n");
+	free(keys);
+	free(visited);
+	if (!is_pcpu)
+		free(values);
+}
+
+void htab_map_batch_ops(void)
+{
+	__test_map_lookup_and_delete_batch(false);
+	printf("test_%s:PASS\n", __func__);
+}
+
+void htab_percpu_map_batch_ops(void)
+{
+	__test_map_lookup_and_delete_batch(true);
+	printf("test_%s:PASS\n", __func__);
+}
+
+void test_htab_map_batch_ops(void)
+{
+	htab_map_batch_ops();
+	htab_percpu_map_batch_ops();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
new file mode 100644
index 000000000000..8482bbc67eec
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <linux/err.h>
+#include <test_progs.h>
+#include "bpf_dctcp.skel.h"
+#include "bpf_cubic.skel.h"
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+
+static const unsigned int total_bytes = 10 * 1024 * 1024;
+static const struct timeval timeo_sec = { .tv_sec = 10 };
+static const size_t timeo_optlen = sizeof(timeo_sec);
+static int stop, duration;
+
+static int settimeo(int fd)
+{
+	int err;
+
+	err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec,
+			 timeo_optlen);
+	if (CHECK(err == -1, "setsockopt(fd, SO_RCVTIMEO)", "errno:%d\n",
+		  errno))
+		return -1;
+
+	err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo_sec,
+			 timeo_optlen);
+	if (CHECK(err == -1, "setsockopt(fd, SO_SNDTIMEO)", "errno:%d\n",
+		  errno))
+		return -1;
+
+	return 0;
+}
+
+static int settcpca(int fd, const char *tcp_ca)
+{
+	int err;
+
+	err = setsockopt(fd, IPPROTO_TCP, TCP_CONGESTION, tcp_ca, strlen(tcp_ca));
+	if (CHECK(err == -1, "setsockopt(fd, TCP_CONGESTION)", "errno:%d\n",
+		  errno))
+		return -1;
+
+	return 0;
+}
+
+static void *server(void *arg)
+{
+	int lfd = (int)(long)arg, err = 0, fd;
+	ssize_t nr_sent = 0, bytes = 0;
+	char batch[1500];
+
+	fd = accept(lfd, NULL, NULL);
+	while (fd == -1) {
+		if (errno == EINTR)
+			continue;
+		err = -errno;
+		goto done;
+	}
+
+	if (settimeo(fd)) {
+		err = -errno;
+		goto done;
+	}
+
+	while (bytes < total_bytes && !READ_ONCE(stop)) {
+		nr_sent = send(fd, &batch,
+			       min(total_bytes - bytes, sizeof(batch)), 0);
+		if (nr_sent == -1 && errno == EINTR)
+			continue;
+		if (nr_sent == -1) {
+			err = -errno;
+			break;
+		}
+		bytes += nr_sent;
+	}
+
+	CHECK(bytes != total_bytes, "send", "%zd != %u nr_sent:%zd errno:%d\n",
+	      bytes, total_bytes, nr_sent, errno);
+
+done:
+	if (fd != -1)
+		close(fd);
+	if (err) {
+		WRITE_ONCE(stop, 1);
+		return ERR_PTR(err);
+	}
+	return NULL;
+}
+
+static void do_test(const char *tcp_ca)
+{
+	struct sockaddr_in6 sa6 = {};
+	ssize_t nr_recv = 0, bytes = 0;
+	int lfd = -1, fd = -1;
+	pthread_t srv_thread;
+	socklen_t addrlen = sizeof(sa6);
+	void *thread_ret;
+	char batch[1500];
+	int err;
+
+	WRITE_ONCE(stop, 0);
+
+	lfd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (CHECK(lfd == -1, "socket", "errno:%d\n", errno))
+		return;
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (CHECK(fd == -1, "socket", "errno:%d\n", errno)) {
+		close(lfd);
+		return;
+	}
+
+	if (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca) ||
+	    settimeo(lfd) || settimeo(fd))
+		goto done;
+
+	/* bind, listen and start server thread to accept */
+	sa6.sin6_family = AF_INET6;
+	sa6.sin6_addr = in6addr_loopback;
+	err = bind(lfd, (struct sockaddr *)&sa6, addrlen);
+	if (CHECK(err == -1, "bind", "errno:%d\n", errno))
+		goto done;
+	err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen);
+	if (CHECK(err == -1, "getsockname", "errno:%d\n", errno))
+		goto done;
+	err = listen(lfd, 1);
+	if (CHECK(err == -1, "listen", "errno:%d\n", errno))
+		goto done;
+	err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd);
+	if (CHECK(err != 0, "pthread_create", "err:%d\n", err))
+		goto done;
+
+	/* connect to server */
+	err = connect(fd, (struct sockaddr *)&sa6, addrlen);
+	if (CHECK(err == -1, "connect", "errno:%d\n", errno))
+		goto wait_thread;
+
+	/* recv total_bytes */
+	while (bytes < total_bytes && !READ_ONCE(stop)) {
+		nr_recv = recv(fd, &batch,
+			       min(total_bytes - bytes, sizeof(batch)), 0);
+		if (nr_recv == -1 && errno == EINTR)
+			continue;
+		if (nr_recv == -1)
+			break;
+		bytes += nr_recv;
+	}
+
+	CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n",
+	      bytes, total_bytes, nr_recv, errno);
+
+wait_thread:
+	WRITE_ONCE(stop, 1);
+	pthread_join(srv_thread, &thread_ret);
+	CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld",
+	      PTR_ERR(thread_ret));
+done:
+	close(lfd);
+	close(fd);
+}
+
+static void test_cubic(void)
+{
+	struct bpf_cubic *cubic_skel;
+	struct bpf_link *link;
+
+	cubic_skel = bpf_cubic__open_and_load();
+	if (CHECK(!cubic_skel, "bpf_cubic__open_and_load", "failed\n"))
+		return;
+
+	link = bpf_map__attach_struct_ops(cubic_skel->maps.cubic);
+	if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n",
+		  PTR_ERR(link))) {
+		bpf_cubic__destroy(cubic_skel);
+		return;
+	}
+
+	do_test("bpf_cubic");
+
+	bpf_link__destroy(link);
+	bpf_cubic__destroy(cubic_skel);
+}
+
+static void test_dctcp(void)
+{
+	struct bpf_dctcp *dctcp_skel;
+	struct bpf_link *link;
+
+	dctcp_skel = bpf_dctcp__open_and_load();
+	if (CHECK(!dctcp_skel, "bpf_dctcp__open_and_load", "failed\n"))
+		return;
+
+	link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp);
+	if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n",
+		  PTR_ERR(link))) {
+		bpf_dctcp__destroy(dctcp_skel);
+		return;
+	}
+
+	do_test("bpf_dctcp");
+
+	bpf_link__destroy(link);
+	bpf_dctcp__destroy(dctcp_skel);
+}
+
+void test_bpf_tcp_ca(void)
+{
+	if (test__start_subtest("dctcp"))
+		test_dctcp();
+	if (test__start_subtest("cubic"))
+		test_cubic();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index 9486c13af6b2..e9f2f12ba06b 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -48,6 +48,8 @@ void test_bpf_verif_scale(void)
 		{ "test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS },
 		{ "test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS },
 
+		{ "pyperf_global.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
+
 		/* full unroll by llvm */
 		{ "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
 		{ "pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
diff --git a/tools/testing/selftests/bpf/prog_tests/cpu_mask.c b/tools/testing/selftests/bpf/prog_tests/cpu_mask.c
index 1fa1bdbaffa9..f7c7e25232be 100644
--- a/tools/testing/selftests/bpf/prog_tests/cpu_mask.c
+++ b/tools/testing/selftests/bpf/prog_tests/cpu_mask.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include <bpf/btf.h>
-#include "libbpf_internal.h"
+#include "bpf/libbpf_internal.h"
 
 static int duration = 0;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index b426bf2f97e4..db5c74d2ce6d 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -26,7 +26,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 
 	link = calloc(sizeof(struct bpf_link *), prog_cnt);
 	prog = calloc(sizeof(struct bpf_program *), prog_cnt);
-	result = malloc(prog_cnt * sizeof(u64));
+	result = malloc((prog_cnt + 32 /* spare */) * sizeof(u64));
 	if (CHECK(!link || !prog || !result, "alloc_memory",
 		  "failed to alloc memory"))
 		goto close_prog;
@@ -98,6 +98,24 @@ static void test_target_yes_callees(void)
 		"fexit/test_pkt_access",
 		"fexit/test_pkt_access_subprog1",
 		"fexit/test_pkt_access_subprog2",
+		"fexit/test_pkt_access_subprog3",
+	};
+	test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
+				  "./test_pkt_access.o",
+				  ARRAY_SIZE(prog_name),
+				  prog_name);
+}
+
+static void test_func_replace(void)
+{
+	const char *prog_name[] = {
+		"fexit/test_pkt_access",
+		"fexit/test_pkt_access_subprog1",
+		"fexit/test_pkt_access_subprog2",
+		"fexit/test_pkt_access_subprog3",
+		"freplace/get_skb_len",
+		"freplace/get_skb_ifindex",
+		"freplace/get_constant",
 	};
 	test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
 				  "./test_pkt_access.o",
@@ -109,4 +127,5 @@ void test_fexit_bpf2bpf(void)
 {
 	test_target_no_callees();
 	test_target_yes_callees();
+	test_func_replace();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index cf6c87936c69..1450ea2dd4cc 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -4,7 +4,7 @@
 #include <sched.h>
 #include <sys/socket.h>
 #include <test_progs.h>
-#include "libbpf_internal.h"
+#include "bpf/libbpf_internal.h"
 
 static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 {
diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c
index b607112c64e7..504abb7bfb95 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include "test_send_signal_kern.skel.h"
 
 static volatile int sigusr1_received = 0;
 
@@ -9,17 +10,15 @@ static void sigusr1_handler(int signum)
 }
 
 static void test_send_signal_common(struct perf_event_attr *attr,
-				    int prog_type,
+				    bool signal_thread,
 				    const char *test_name)
 {
-	int err = -1, pmu_fd, prog_fd, info_map_fd, status_map_fd;
-	const char *file = "./test_send_signal_kern.o";
-	struct bpf_object *obj = NULL;
+	struct test_send_signal_kern *skel;
 	int pipe_c2p[2], pipe_p2c[2];
-	__u32 key = 0, duration = 0;
+	int err = -1, pmu_fd = -1;
+	__u32 duration = 0;
 	char buf[256];
 	pid_t pid;
-	__u64 val;
 
 	if (CHECK(pipe(pipe_c2p), test_name,
 		  "pipe pipe_c2p error: %s\n", strerror(errno)))
@@ -73,45 +72,39 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 	close(pipe_c2p[1]); /* close write */
 	close(pipe_p2c[0]); /* close read */
 
-	err = bpf_prog_load(file, prog_type, &obj, &prog_fd);
-	if (CHECK(err < 0, test_name, "bpf_prog_load error: %s\n",
-		  strerror(errno)))
-		goto prog_load_failure;
-
-	pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1,
-			 -1 /* group id */, 0 /* flags */);
-	if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n",
-		  strerror(errno))) {
-		err = -1;
-		goto close_prog;
-	}
+	skel = test_send_signal_kern__open_and_load();
+	if (CHECK(!skel, "skel_open_and_load", "skeleton open_and_load failed\n"))
+		goto skel_open_load_failure;
 
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
-	if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_enable error: %s\n",
-		  strerror(errno)))
-		goto disable_pmu;
-
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
-	if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_set_bpf error: %s\n",
-		  strerror(errno)))
-		goto disable_pmu;
-
-	err = -1;
-	info_map_fd = bpf_object__find_map_fd_by_name(obj, "info_map");
-	if (CHECK(info_map_fd < 0, test_name, "find map %s error\n", "info_map"))
-		goto disable_pmu;
+	if (!attr) {
+		err = test_send_signal_kern__attach(skel);
+		if (CHECK(err, "skel_attach", "skeleton attach failed\n")) {
+			err = -1;
+			goto destroy_skel;
+		}
+	} else {
+		pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1,
+				 -1 /* group id */, 0 /* flags */);
+		if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n",
+			strerror(errno))) {
+			err = -1;
+			goto destroy_skel;
+		}
 
-	status_map_fd = bpf_object__find_map_fd_by_name(obj, "status_map");
-	if (CHECK(status_map_fd < 0, test_name, "find map %s error\n", "status_map"))
-		goto disable_pmu;
+		skel->links.send_signal_perf =
+			bpf_program__attach_perf_event(skel->progs.send_signal_perf, pmu_fd);
+		if (CHECK(IS_ERR(skel->links.send_signal_perf), "attach_perf_event",
+			  "err %ld\n", PTR_ERR(skel->links.send_signal_perf)))
+			goto disable_pmu;
+	}
 
 	/* wait until child signal handler installed */
 	read(pipe_c2p[0], buf, 1);
 
 	/* trigger the bpf send_signal */
-	key = 0;
-	val = (((__u64)(SIGUSR1)) << 32) | pid;
-	bpf_map_update_elem(info_map_fd, &key, &val, 0);
+	skel->bss->pid = pid;
+	skel->bss->sig = SIGUSR1;
+	skel->bss->signal_thread = signal_thread;
 
 	/* notify child that bpf program can send_signal now */
 	write(pipe_p2c[1], buf, 1);
@@ -132,46 +125,20 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 
 disable_pmu:
 	close(pmu_fd);
-close_prog:
-	bpf_object__close(obj);
-prog_load_failure:
+destroy_skel:
+	test_send_signal_kern__destroy(skel);
+skel_open_load_failure:
 	close(pipe_c2p[0]);
 	close(pipe_p2c[1]);
 	wait(NULL);
 }
 
-static void test_send_signal_tracepoint(void)
+static void test_send_signal_tracepoint(bool signal_thread)
 {
-	const char *id_path = "/sys/kernel/debug/tracing/events/syscalls/sys_enter_nanosleep/id";
-	struct perf_event_attr attr = {
-		.type = PERF_TYPE_TRACEPOINT,
-		.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN,
-		.sample_period = 1,
-		.wakeup_events = 1,
-	};
-	__u32 duration = 0;
-	int bytes, efd;
-	char buf[256];
-
-	efd = open(id_path, O_RDONLY, 0);
-	if (CHECK(efd < 0, "tracepoint",
-		  "open syscalls/sys_enter_nanosleep/id failure: %s\n",
-		  strerror(errno)))
-		return;
-
-	bytes = read(efd, buf, sizeof(buf));
-	close(efd);
-	if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "tracepoint",
-		  "read syscalls/sys_enter_nanosleep/id failure: %s\n",
-		  strerror(errno)))
-		return;
-
-	attr.config = strtol(buf, NULL, 0);
-
-	test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint");
+	test_send_signal_common(NULL, signal_thread, "tracepoint");
 }
 
-static void test_send_signal_perf(void)
+static void test_send_signal_perf(bool signal_thread)
 {
 	struct perf_event_attr attr = {
 		.sample_period = 1,
@@ -179,15 +146,13 @@ static void test_send_signal_perf(void)
 		.config = PERF_COUNT_SW_CPU_CLOCK,
 	};
 
-	test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
-				"perf_sw_event");
+	test_send_signal_common(&attr, signal_thread, "perf_sw_event");
 }
 
-static void test_send_signal_nmi(void)
+static void test_send_signal_nmi(bool signal_thread)
 {
 	struct perf_event_attr attr = {
-		.sample_freq = 50,
-		.freq = 1,
+		.sample_period = 1,
 		.type = PERF_TYPE_HARDWARE,
 		.config = PERF_COUNT_HW_CPU_CYCLES,
 	};
@@ -210,16 +175,21 @@ static void test_send_signal_nmi(void)
 		close(pmu_fd);
 	}
 
-	test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
-				"perf_hw_event");
+	test_send_signal_common(&attr, signal_thread, "perf_hw_event");
 }
 
 void test_send_signal(void)
 {
 	if (test__start_subtest("send_signal_tracepoint"))
-		test_send_signal_tracepoint();
+		test_send_signal_tracepoint(false);
 	if (test__start_subtest("send_signal_perf"))
-		test_send_signal_perf();
+		test_send_signal_perf(false);
 	if (test__start_subtest("send_signal_nmi"))
-		test_send_signal_nmi();
+		test_send_signal_nmi(false);
+	if (test__start_subtest("send_signal_tracepoint_thread"))
+		test_send_signal_tracepoint(true);
+	if (test__start_subtest("send_signal_perf_thread"))
+		test_send_signal_perf(true);
+	if (test__start_subtest("send_signal_nmi_thread"))
+		test_send_signal_nmi(true);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
index 8974450a4bdb..f002e3090d92 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
@@ -49,8 +49,12 @@ retry:
 	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
 			 0 /* cpu 0 */, -1 /* group id */,
 			 0 /* flags */);
-	if (CHECK(pmu_fd < 0, "perf_event_open",
-		  "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n",
+	if (pmu_fd < 0 && errno == ENOENT) {
+		printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__);
+		test__skip();
+		goto cleanup;
+	}
+	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
 		  pmu_fd, errno))
 		goto cleanup;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
new file mode 100644
index 000000000000..25b068591e9a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+
+const char *err_str;
+bool found;
+
+static int libbpf_debug_print(enum libbpf_print_level level,
+			      const char *format, va_list args)
+{
+	char *log_buf;
+
+	if (level != LIBBPF_WARN ||
+	    strcmp(format, "libbpf: \n%s\n")) {
+		vprintf(format, args);
+		return 0;
+	}
+
+	log_buf = va_arg(args, char *);
+	if (!log_buf)
+		goto out;
+	if (strstr(log_buf, err_str) == 0)
+		found = true;
+out:
+	printf(format, log_buf);
+	return 0;
+}
+
+extern int extra_prog_load_log_flags;
+
+static int check_load(const char *file)
+{
+	struct bpf_prog_load_attr attr;
+	struct bpf_object *obj = NULL;
+	int err, prog_fd;
+
+	memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
+	attr.file = file;
+	attr.prog_type = BPF_PROG_TYPE_UNSPEC;
+	attr.log_level = extra_prog_load_log_flags;
+	attr.prog_flags = BPF_F_TEST_RND_HI32;
+	found = false;
+	err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+	bpf_object__close(obj);
+	return err;
+}
+
+struct test_def {
+	const char *file;
+	const char *err_str;
+};
+
+void test_test_global_funcs(void)
+{
+	struct test_def tests[] = {
+		{ "test_global_func1.o", "combined stack size of 4 calls is 544" },
+		{ "test_global_func2.o" },
+		{ "test_global_func3.o" , "the call stack of 8 frames" },
+		{ "test_global_func4.o" },
+		{ "test_global_func5.o" , "expected pointer to ctx, but got PTR" },
+		{ "test_global_func6.o" , "modified ctx ptr R2" },
+		{ "test_global_func7.o" , "foo() doesn't return scalar" },
+	};
+	libbpf_print_fn_t old_print_fn = NULL;
+	int err, i, duration = 0;
+
+	old_print_fn = libbpf_set_print(libbpf_debug_print);
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		const struct test_def *test = &tests[i];
+
+		if (!test__start_subtest(test->file))
+			continue;
+
+		err_str = test->err_str;
+		err = check_load(test->file);
+		CHECK_FAIL(!!err ^ !!err_str);
+		if (err_str)
+			CHECK(found, "", "expected string '%s'", err_str);
+	}
+	libbpf_set_print(old_print_fn);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
index c32aa28bd93f..465b371a561d 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019 Facebook */
 #define _GNU_SOURCE
 #include <sched.h>
+#include <sys/prctl.h>
 #include <test_progs.h>
 
 #define MAX_CNT 100000
@@ -17,7 +18,7 @@ static __u64 time_get_ns(void)
 static int test_task_rename(const char *prog)
 {
 	int i, fd, duration = 0, err;
-	char buf[] = "test\n";
+	char buf[] = "test_overhead";
 	__u64 start_time;
 
 	fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
@@ -66,6 +67,10 @@ void test_test_overhead(void)
 	struct bpf_object *obj;
 	struct bpf_link *link;
 	int err, duration = 0;
+	char comm[16] = {};
+
+	if (CHECK_FAIL(prctl(PR_GET_NAME, comm, 0L, 0L, 0L)))
+		return;
 
 	obj = bpf_object__open_file("./test_overhead.o", NULL);
 	if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj)))
@@ -138,5 +143,6 @@ void test_test_overhead(void)
 	test_run("fexit");
 	bpf_link__destroy(link);
 cleanup:
+	prctl(PR_SET_NAME, comm, 0L, 0L, 0L);
 	bpf_object__close(obj);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
new file mode 100644
index 000000000000..6b56bdc73ebc
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <net/if.h>
+#include "test_xdp.skel.h"
+#include "test_xdp_bpf2bpf.skel.h"
+
+void test_xdp_bpf2bpf(void)
+{
+	__u32 duration = 0, retval, size;
+	char buf[128];
+	int err, pkt_fd, map_fd;
+	struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
+	struct iptnl_info value4 = {.family = AF_INET};
+	struct test_xdp *pkt_skel = NULL;
+	struct test_xdp_bpf2bpf *ftrace_skel = NULL;
+	struct vip key4 = {.protocol = 6, .family = AF_INET};
+	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
+
+	/* Load XDP program to introspect */
+	pkt_skel = test_xdp__open_and_load();
+	if (CHECK(!pkt_skel, "pkt_skel_load", "test_xdp skeleton failed\n"))
+		return;
+
+	pkt_fd = bpf_program__fd(pkt_skel->progs._xdp_tx_iptunnel);
+
+	map_fd = bpf_map__fd(pkt_skel->maps.vip2tnl);
+	bpf_map_update_elem(map_fd, &key4, &value4, 0);
+
+	/* Load trace program */
+	opts.attach_prog_fd = pkt_fd,
+	ftrace_skel = test_xdp_bpf2bpf__open_opts(&opts);
+	if (CHECK(!ftrace_skel, "__open", "ftrace skeleton failed\n"))
+		goto out;
+
+	err = test_xdp_bpf2bpf__load(ftrace_skel);
+	if (CHECK(err, "__load", "ftrace skeleton failed\n"))
+		goto out;
+
+	err = test_xdp_bpf2bpf__attach(ftrace_skel);
+	if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err))
+		goto out;
+
+	/* Run test program */
+	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				buf, &size, &retval, &duration);
+
+	if (CHECK(err || retval != XDP_TX || size != 74 ||
+		  iph->protocol != IPPROTO_IPIP, "ipv4",
+		  "err %d errno %d retval %d size %d\n",
+		  err, errno, retval, size))
+		goto out;
+
+	/* Verify test results */
+	if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"),
+		  "result", "fentry failed err %llu\n",
+		  ftrace_skel->bss->test_result_fentry))
+		goto out;
+
+	CHECK(ftrace_skel->bss->test_result_fexit != XDP_TX, "result",
+	      "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit);
+
+out:
+	test_xdp__destroy(pkt_skel);
+	test_xdp_bpf2bpf__destroy(ftrace_skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c
new file mode 100644
index 000000000000..7897c8f4d363
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c
@@ -0,0 +1,544 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/* WARNING: This implemenation is not necessarily the same
+ * as the tcp_cubic.c.  The purpose is mainly for testing
+ * the kernel BPF logic.
+ *
+ * Highlights:
+ * 1. CONFIG_HZ .kconfig map is used.
+ * 2. In bictcp_update(), calculation is changed to use usec
+ *    resolution (i.e. USEC_PER_JIFFY) instead of using jiffies.
+ *    Thus, usecs_to_jiffies() is not used in the bpf_cubic.c.
+ * 3. In bitctcp_update() [under tcp_friendliness], the original
+ *    "while (ca->ack_cnt > delta)" loop is changed to the equivalent
+ *    "ca->ack_cnt / delta" operation.
+ */
+
+#include <linux/bpf.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
+
+#define BICTCP_BETA_SCALE    1024	/* Scale factor beta calculation
+					 * max_cwnd = snd_cwnd * beta
+					 */
+#define	BICTCP_HZ		10	/* BIC HZ 2^10 = 1024 */
+
+/* Two methods of hybrid slow start */
+#define HYSTART_ACK_TRAIN	0x1
+#define HYSTART_DELAY		0x2
+
+/* Number of delay samples for detecting the increase of delay */
+#define HYSTART_MIN_SAMPLES	8
+#define HYSTART_DELAY_MIN	(4000U)	/* 4ms */
+#define HYSTART_DELAY_MAX	(16000U)	/* 16 ms */
+#define HYSTART_DELAY_THRESH(x)	clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX)
+
+static int fast_convergence = 1;
+static const int beta = 717;	/* = 717/1024 (BICTCP_BETA_SCALE) */
+static int initial_ssthresh;
+static const int bic_scale = 41;
+static int tcp_friendliness = 1;
+
+static int hystart = 1;
+static int hystart_detect = HYSTART_ACK_TRAIN | HYSTART_DELAY;
+static int hystart_low_window = 16;
+static int hystart_ack_delta_us = 2000;
+
+static const __u32 cube_rtt_scale = (bic_scale * 10);	/* 1024*c/rtt */
+static const __u32 beta_scale = 8*(BICTCP_BETA_SCALE+beta) / 3
+				/ (BICTCP_BETA_SCALE - beta);
+/* calculate the "K" for (wmax-cwnd) = c/rtt * K^3
+ *  so K = cubic_root( (wmax-cwnd)*rtt/c )
+ * the unit of K is bictcp_HZ=2^10, not HZ
+ *
+ *  c = bic_scale >> 10
+ *  rtt = 100ms
+ *
+ * the following code has been designed and tested for
+ * cwnd < 1 million packets
+ * RTT < 100 seconds
+ * HZ < 1,000,00  (corresponding to 10 nano-second)
+ */
+
+/* 1/c * 2^2*bictcp_HZ * srtt, 2^40 */
+static const __u64 cube_factor = (__u64)(1ull << (10+3*BICTCP_HZ))
+				/ (bic_scale * 10);
+
+/* BIC TCP Parameters */
+struct bictcp {
+	__u32	cnt;		/* increase cwnd by 1 after ACKs */
+	__u32	last_max_cwnd;	/* last maximum snd_cwnd */
+	__u32	last_cwnd;	/* the last snd_cwnd */
+	__u32	last_time;	/* time when updated last_cwnd */
+	__u32	bic_origin_point;/* origin point of bic function */
+	__u32	bic_K;		/* time to origin point
+				   from the beginning of the current epoch */
+	__u32	delay_min;	/* min delay (usec) */
+	__u32	epoch_start;	/* beginning of an epoch */
+	__u32	ack_cnt;	/* number of acks */
+	__u32	tcp_cwnd;	/* estimated tcp cwnd */
+	__u16	unused;
+	__u8	sample_cnt;	/* number of samples to decide curr_rtt */
+	__u8	found;		/* the exit point is found? */
+	__u32	round_start;	/* beginning of each round */
+	__u32	end_seq;	/* end_seq of the round */
+	__u32	last_ack;	/* last time when the ACK spacing is close */
+	__u32	curr_rtt;	/* the minimum rtt of current round */
+};
+
+static inline void bictcp_reset(struct bictcp *ca)
+{
+	ca->cnt = 0;
+	ca->last_max_cwnd = 0;
+	ca->last_cwnd = 0;
+	ca->last_time = 0;
+	ca->bic_origin_point = 0;
+	ca->bic_K = 0;
+	ca->delay_min = 0;
+	ca->epoch_start = 0;
+	ca->ack_cnt = 0;
+	ca->tcp_cwnd = 0;
+	ca->found = 0;
+}
+
+extern unsigned long CONFIG_HZ __kconfig;
+#define HZ CONFIG_HZ
+#define USEC_PER_MSEC	1000UL
+#define USEC_PER_SEC	1000000UL
+#define USEC_PER_JIFFY	(USEC_PER_SEC / HZ)
+
+static __always_inline __u64 div64_u64(__u64 dividend, __u64 divisor)
+{
+	return dividend / divisor;
+}
+
+#define div64_ul div64_u64
+
+#define BITS_PER_U64 (sizeof(__u64) * 8)
+static __always_inline int fls64(__u64 x)
+{
+	int num = BITS_PER_U64 - 1;
+
+	if (x == 0)
+		return 0;
+
+	if (!(x & (~0ull << (BITS_PER_U64-32)))) {
+		num -= 32;
+		x <<= 32;
+	}
+	if (!(x & (~0ull << (BITS_PER_U64-16)))) {
+		num -= 16;
+		x <<= 16;
+	}
+	if (!(x & (~0ull << (BITS_PER_U64-8)))) {
+		num -= 8;
+		x <<= 8;
+	}
+	if (!(x & (~0ull << (BITS_PER_U64-4)))) {
+		num -= 4;
+		x <<= 4;
+	}
+	if (!(x & (~0ull << (BITS_PER_U64-2)))) {
+		num -= 2;
+		x <<= 2;
+	}
+	if (!(x & (~0ull << (BITS_PER_U64-1))))
+		num -= 1;
+
+	return num + 1;
+}
+
+static __always_inline __u32 bictcp_clock_us(const struct sock *sk)
+{
+	return tcp_sk(sk)->tcp_mstamp;
+}
+
+static __always_inline void bictcp_hystart_reset(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bictcp *ca = inet_csk_ca(sk);
+
+	ca->round_start = ca->last_ack = bictcp_clock_us(sk);
+	ca->end_seq = tp->snd_nxt;
+	ca->curr_rtt = ~0U;
+	ca->sample_cnt = 0;
+}
+
+/* "struct_ops/" prefix is not a requirement
+ * It will be recognized as BPF_PROG_TYPE_STRUCT_OPS
+ * as long as it is used in one of the func ptr
+ * under SEC(".struct_ops").
+ */
+SEC("struct_ops/bictcp_init")
+void BPF_PROG(bictcp_init, struct sock *sk)
+{
+	struct bictcp *ca = inet_csk_ca(sk);
+
+	bictcp_reset(ca);
+
+	if (hystart)
+		bictcp_hystart_reset(sk);
+
+	if (!hystart && initial_ssthresh)
+		tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
+}
+
+/* No prefix in SEC will also work.
+ * The remaining tcp-cubic functions have an easier way.
+ */
+SEC("no-sec-prefix-bictcp_cwnd_event")
+void BPF_PROG(bictcp_cwnd_event, struct sock *sk, enum tcp_ca_event event)
+{
+	if (event == CA_EVENT_TX_START) {
+		struct bictcp *ca = inet_csk_ca(sk);
+		__u32 now = tcp_jiffies32;
+		__s32 delta;
+
+		delta = now - tcp_sk(sk)->lsndtime;
+
+		/* We were application limited (idle) for a while.
+		 * Shift epoch_start to keep cwnd growth to cubic curve.
+		 */
+		if (ca->epoch_start && delta > 0) {
+			ca->epoch_start += delta;
+			if (after(ca->epoch_start, now))
+				ca->epoch_start = now;
+		}
+		return;
+	}
+}
+
+/*
+ * cbrt(x) MSB values for x MSB values in [0..63].
+ * Precomputed then refined by hand - Willy Tarreau
+ *
+ * For x in [0..63],
+ *   v = cbrt(x << 18) - 1
+ *   cbrt(x) = (v[x] + 10) >> 6
+ */
+static const __u8 v[] = {
+	/* 0x00 */    0,   54,   54,   54,  118,  118,  118,  118,
+	/* 0x08 */  123,  129,  134,  138,  143,  147,  151,  156,
+	/* 0x10 */  157,  161,  164,  168,  170,  173,  176,  179,
+	/* 0x18 */  181,  185,  187,  190,  192,  194,  197,  199,
+	/* 0x20 */  200,  202,  204,  206,  209,  211,  213,  215,
+	/* 0x28 */  217,  219,  221,  222,  224,  225,  227,  229,
+	/* 0x30 */  231,  232,  234,  236,  237,  239,  240,  242,
+	/* 0x38 */  244,  245,  246,  248,  250,  251,  252,  254,
+};
+
+/* calculate the cubic root of x using a table lookup followed by one
+ * Newton-Raphson iteration.
+ * Avg err ~= 0.195%
+ */
+static __always_inline __u32 cubic_root(__u64 a)
+{
+	__u32 x, b, shift;
+
+	if (a < 64) {
+		/* a in [0..63] */
+		return ((__u32)v[(__u32)a] + 35) >> 6;
+	}
+
+	b = fls64(a);
+	b = ((b * 84) >> 8) - 1;
+	shift = (a >> (b * 3));
+
+	/* it is needed for verifier's bound check on v */
+	if (shift >= 64)
+		return 0;
+
+	x = ((__u32)(((__u32)v[shift] + 10) << b)) >> 6;
+
+	/*
+	 * Newton-Raphson iteration
+	 *                         2
+	 * x    = ( 2 * x  +  a / x  ) / 3
+	 *  k+1          k         k
+	 */
+	x = (2 * x + (__u32)div64_u64(a, (__u64)x * (__u64)(x - 1)));
+	x = ((x * 341) >> 10);
+	return x;
+}
+
+/*
+ * Compute congestion window to use.
+ */
+static __always_inline void bictcp_update(struct bictcp *ca, __u32 cwnd,
+					  __u32 acked)
+{
+	__u32 delta, bic_target, max_cnt;
+	__u64 offs, t;
+
+	ca->ack_cnt += acked;	/* count the number of ACKed packets */
+
+	if (ca->last_cwnd == cwnd &&
+	    (__s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32)
+		return;
+
+	/* The CUBIC function can update ca->cnt at most once per jiffy.
+	 * On all cwnd reduction events, ca->epoch_start is set to 0,
+	 * which will force a recalculation of ca->cnt.
+	 */
+	if (ca->epoch_start && tcp_jiffies32 == ca->last_time)
+		goto tcp_friendliness;
+
+	ca->last_cwnd = cwnd;
+	ca->last_time = tcp_jiffies32;
+
+	if (ca->epoch_start == 0) {
+		ca->epoch_start = tcp_jiffies32;	/* record beginning */
+		ca->ack_cnt = acked;			/* start counting */
+		ca->tcp_cwnd = cwnd;			/* syn with cubic */
+
+		if (ca->last_max_cwnd <= cwnd) {
+			ca->bic_K = 0;
+			ca->bic_origin_point = cwnd;
+		} else {
+			/* Compute new K based on
+			 * (wmax-cwnd) * (srtt>>3 / HZ) / c * 2^(3*bictcp_HZ)
+			 */
+			ca->bic_K = cubic_root(cube_factor
+					       * (ca->last_max_cwnd - cwnd));
+			ca->bic_origin_point = ca->last_max_cwnd;
+		}
+	}
+
+	/* cubic function - calc*/
+	/* calculate c * time^3 / rtt,
+	 *  while considering overflow in calculation of time^3
+	 * (so time^3 is done by using 64 bit)
+	 * and without the support of division of 64bit numbers
+	 * (so all divisions are done by using 32 bit)
+	 *  also NOTE the unit of those veriables
+	 *	  time  = (t - K) / 2^bictcp_HZ
+	 *	  c = bic_scale >> 10
+	 * rtt  = (srtt >> 3) / HZ
+	 * !!! The following code does not have overflow problems,
+	 * if the cwnd < 1 million packets !!!
+	 */
+
+	t = (__s32)(tcp_jiffies32 - ca->epoch_start) * USEC_PER_JIFFY;
+	t += ca->delay_min;
+	/* change the unit from usec to bictcp_HZ */
+	t <<= BICTCP_HZ;
+	t /= USEC_PER_SEC;
+
+	if (t < ca->bic_K)		/* t - K */
+		offs = ca->bic_K - t;
+	else
+		offs = t - ca->bic_K;
+
+	/* c/rtt * (t-K)^3 */
+	delta = (cube_rtt_scale * offs * offs * offs) >> (10+3*BICTCP_HZ);
+	if (t < ca->bic_K)                            /* below origin*/
+		bic_target = ca->bic_origin_point - delta;
+	else                                          /* above origin*/
+		bic_target = ca->bic_origin_point + delta;
+
+	/* cubic function - calc bictcp_cnt*/
+	if (bic_target > cwnd) {
+		ca->cnt = cwnd / (bic_target - cwnd);
+	} else {
+		ca->cnt = 100 * cwnd;              /* very small increment*/
+	}
+
+	/*
+	 * The initial growth of cubic function may be too conservative
+	 * when the available bandwidth is still unknown.
+	 */
+	if (ca->last_max_cwnd == 0 && ca->cnt > 20)
+		ca->cnt = 20;	/* increase cwnd 5% per RTT */
+
+tcp_friendliness:
+	/* TCP Friendly */
+	if (tcp_friendliness) {
+		__u32 scale = beta_scale;
+		__u32 n;
+
+		/* update tcp cwnd */
+		delta = (cwnd * scale) >> 3;
+		if (ca->ack_cnt > delta && delta) {
+			n = ca->ack_cnt / delta;
+			ca->ack_cnt -= n * delta;
+			ca->tcp_cwnd += n;
+		}
+
+		if (ca->tcp_cwnd > cwnd) {	/* if bic is slower than tcp */
+			delta = ca->tcp_cwnd - cwnd;
+			max_cnt = cwnd / delta;
+			if (ca->cnt > max_cnt)
+				ca->cnt = max_cnt;
+		}
+	}
+
+	/* The maximum rate of cwnd increase CUBIC allows is 1 packet per
+	 * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT.
+	 */
+	ca->cnt = max(ca->cnt, 2U);
+}
+
+/* Or simply use the BPF_STRUCT_OPS to avoid the SEC boiler plate. */
+void BPF_STRUCT_OPS(bictcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bictcp *ca = inet_csk_ca(sk);
+
+	if (!tcp_is_cwnd_limited(sk))
+		return;
+
+	if (tcp_in_slow_start(tp)) {
+		if (hystart && after(ack, ca->end_seq))
+			bictcp_hystart_reset(sk);
+		acked = tcp_slow_start(tp, acked);
+		if (!acked)
+			return;
+	}
+	bictcp_update(ca, tp->snd_cwnd, acked);
+	tcp_cong_avoid_ai(tp, ca->cnt, acked);
+}
+
+__u32 BPF_STRUCT_OPS(bictcp_recalc_ssthresh, struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	struct bictcp *ca = inet_csk_ca(sk);
+
+	ca->epoch_start = 0;	/* end of epoch */
+
+	/* Wmax and fast convergence */
+	if (tp->snd_cwnd < ca->last_max_cwnd && fast_convergence)
+		ca->last_max_cwnd = (tp->snd_cwnd * (BICTCP_BETA_SCALE + beta))
+			/ (2 * BICTCP_BETA_SCALE);
+	else
+		ca->last_max_cwnd = tp->snd_cwnd;
+
+	return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
+}
+
+void BPF_STRUCT_OPS(bictcp_state, struct sock *sk, __u8 new_state)
+{
+	if (new_state == TCP_CA_Loss) {
+		bictcp_reset(inet_csk_ca(sk));
+		bictcp_hystart_reset(sk);
+	}
+}
+
+#define GSO_MAX_SIZE		65536
+
+/* Account for TSO/GRO delays.
+ * Otherwise short RTT flows could get too small ssthresh, since during
+ * slow start we begin with small TSO packets and ca->delay_min would
+ * not account for long aggregation delay when TSO packets get bigger.
+ * Ideally even with a very small RTT we would like to have at least one
+ * TSO packet being sent and received by GRO, and another one in qdisc layer.
+ * We apply another 100% factor because @rate is doubled at this point.
+ * We cap the cushion to 1ms.
+ */
+static __always_inline __u32 hystart_ack_delay(struct sock *sk)
+{
+	unsigned long rate;
+
+	rate = sk->sk_pacing_rate;
+	if (!rate)
+		return 0;
+	return min((__u64)USEC_PER_MSEC,
+		   div64_ul((__u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate));
+}
+
+static __always_inline void hystart_update(struct sock *sk, __u32 delay)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bictcp *ca = inet_csk_ca(sk);
+	__u32 threshold;
+
+	if (hystart_detect & HYSTART_ACK_TRAIN) {
+		__u32 now = bictcp_clock_us(sk);
+
+		/* first detection parameter - ack-train detection */
+		if ((__s32)(now - ca->last_ack) <= hystart_ack_delta_us) {
+			ca->last_ack = now;
+
+			threshold = ca->delay_min + hystart_ack_delay(sk);
+
+			/* Hystart ack train triggers if we get ack past
+			 * ca->delay_min/2.
+			 * Pacing might have delayed packets up to RTT/2
+			 * during slow start.
+			 */
+			if (sk->sk_pacing_status == SK_PACING_NONE)
+				threshold >>= 1;
+
+			if ((__s32)(now - ca->round_start) > threshold) {
+				ca->found = 1;
+				tp->snd_ssthresh = tp->snd_cwnd;
+			}
+		}
+	}
+
+	if (hystart_detect & HYSTART_DELAY) {
+		/* obtain the minimum delay of more than sampling packets */
+		if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
+			if (ca->curr_rtt > delay)
+				ca->curr_rtt = delay;
+
+			ca->sample_cnt++;
+		} else {
+			if (ca->curr_rtt > ca->delay_min +
+			    HYSTART_DELAY_THRESH(ca->delay_min >> 3)) {
+				ca->found = 1;
+				tp->snd_ssthresh = tp->snd_cwnd;
+			}
+		}
+	}
+}
+
+void BPF_STRUCT_OPS(bictcp_acked, struct sock *sk,
+		    const struct ack_sample *sample)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	struct bictcp *ca = inet_csk_ca(sk);
+	__u32 delay;
+
+	/* Some calls are for duplicates without timetamps */
+	if (sample->rtt_us < 0)
+		return;
+
+	/* Discard delay samples right after fast recovery */
+	if (ca->epoch_start && (__s32)(tcp_jiffies32 - ca->epoch_start) < HZ)
+		return;
+
+	delay = sample->rtt_us;
+	if (delay == 0)
+		delay = 1;
+
+	/* first time call or link delay decreases */
+	if (ca->delay_min == 0 || ca->delay_min > delay)
+		ca->delay_min = delay;
+
+	/* hystart triggers when cwnd is larger than some threshold */
+	if (!ca->found && tcp_in_slow_start(tp) && hystart &&
+	    tp->snd_cwnd >= hystart_low_window)
+		hystart_update(sk, delay);
+}
+
+__u32 BPF_STRUCT_OPS(tcp_reno_undo_cwnd, struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+
+	return max(tp->snd_cwnd, tp->prior_cwnd);
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops cubic = {
+	.init		= (void *)bictcp_init,
+	.ssthresh	= (void *)bictcp_recalc_ssthresh,
+	.cong_avoid	= (void *)bictcp_cong_avoid,
+	.set_state	= (void *)bictcp_state,
+	.undo_cwnd	= (void *)tcp_reno_undo_cwnd,
+	.cwnd_event	= (void *)bictcp_cwnd_event,
+	.pkts_acked     = (void *)bictcp_acked,
+	.name		= "bpf_cubic",
+};
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
new file mode 100644
index 000000000000..b631fb5032d2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+/* WARNING: This implemenation is not necessarily the same
+ * as the tcp_dctcp.c.  The purpose is mainly for testing
+ * the kernel BPF logic.
+ */
+
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_trace_helpers.h"
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define DCTCP_MAX_ALPHA	1024U
+
+struct dctcp {
+	__u32 old_delivered;
+	__u32 old_delivered_ce;
+	__u32 prior_rcv_nxt;
+	__u32 dctcp_alpha;
+	__u32 next_seq;
+	__u32 ce_state;
+	__u32 loss_cwnd;
+};
+
+static unsigned int dctcp_shift_g = 4; /* g = 1/2^4 */
+static unsigned int dctcp_alpha_on_init = DCTCP_MAX_ALPHA;
+
+static __always_inline void dctcp_reset(const struct tcp_sock *tp,
+					struct dctcp *ca)
+{
+	ca->next_seq = tp->snd_nxt;
+
+	ca->old_delivered = tp->delivered;
+	ca->old_delivered_ce = tp->delivered_ce;
+}
+
+SEC("struct_ops/dctcp_init")
+void BPF_PROG(dctcp_init, struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	struct dctcp *ca = inet_csk_ca(sk);
+
+	ca->prior_rcv_nxt = tp->rcv_nxt;
+	ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
+	ca->loss_cwnd = 0;
+	ca->ce_state = 0;
+
+	dctcp_reset(tp, ca);
+}
+
+SEC("struct_ops/dctcp_ssthresh")
+__u32 BPF_PROG(dctcp_ssthresh, struct sock *sk)
+{
+	struct dctcp *ca = inet_csk_ca(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	ca->loss_cwnd = tp->snd_cwnd;
+	return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
+}
+
+SEC("struct_ops/dctcp_update_alpha")
+void BPF_PROG(dctcp_update_alpha, struct sock *sk, __u32 flags)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	struct dctcp *ca = inet_csk_ca(sk);
+
+	/* Expired RTT */
+	if (!before(tp->snd_una, ca->next_seq)) {
+		__u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce;
+		__u32 alpha = ca->dctcp_alpha;
+
+		/* alpha = (1 - g) * alpha + g * F */
+
+		alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g);
+		if (delivered_ce) {
+			__u32 delivered = tp->delivered - ca->old_delivered;
+
+			/* If dctcp_shift_g == 1, a 32bit value would overflow
+			 * after 8 M packets.
+			 */
+			delivered_ce <<= (10 - dctcp_shift_g);
+			delivered_ce /= max(1U, delivered);
+
+			alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA);
+		}
+		ca->dctcp_alpha = alpha;
+		dctcp_reset(tp, ca);
+	}
+}
+
+static __always_inline void dctcp_react_to_loss(struct sock *sk)
+{
+	struct dctcp *ca = inet_csk_ca(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	ca->loss_cwnd = tp->snd_cwnd;
+	tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
+SEC("struct_ops/dctcp_state")
+void BPF_PROG(dctcp_state, struct sock *sk, __u8 new_state)
+{
+	if (new_state == TCP_CA_Recovery &&
+	    new_state != BPF_CORE_READ_BITFIELD(inet_csk(sk), icsk_ca_state))
+		dctcp_react_to_loss(sk);
+	/* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+	 * one loss-adjustment per RTT.
+	 */
+}
+
+static __always_inline void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (ce_state == 1)
+		tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+	else
+		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+}
+
+/* Minimal DCTP CE state machine:
+ *
+ * S:	0 <- last pkt was non-CE
+ *	1 <- last pkt was CE
+ */
+static __always_inline
+void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt,
+			  __u32 *prior_rcv_nxt, __u32 *ce_state)
+{
+	__u32 new_ce_state = (evt == CA_EVENT_ECN_IS_CE) ? 1 : 0;
+
+	if (*ce_state != new_ce_state) {
+		/* CE state has changed, force an immediate ACK to
+		 * reflect the new CE state. If an ACK was delayed,
+		 * send that first to reflect the prior CE state.
+		 */
+		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
+			dctcp_ece_ack_cwr(sk, *ce_state);
+			bpf_tcp_send_ack(sk, *prior_rcv_nxt);
+		}
+		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
+	}
+	*prior_rcv_nxt = tcp_sk(sk)->rcv_nxt;
+	*ce_state = new_ce_state;
+	dctcp_ece_ack_cwr(sk, new_ce_state);
+}
+
+SEC("struct_ops/dctcp_cwnd_event")
+void BPF_PROG(dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev)
+{
+	struct dctcp *ca = inet_csk_ca(sk);
+
+	switch (ev) {
+	case CA_EVENT_ECN_IS_CE:
+	case CA_EVENT_ECN_NO_CE:
+		dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state);
+		break;
+	case CA_EVENT_LOSS:
+		dctcp_react_to_loss(sk);
+		break;
+	default:
+		/* Don't care for the rest. */
+		break;
+	}
+}
+
+SEC("struct_ops/dctcp_cwnd_undo")
+__u32 BPF_PROG(dctcp_cwnd_undo, struct sock *sk)
+{
+	const struct dctcp *ca = inet_csk_ca(sk);
+
+	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
+}
+
+SEC("struct_ops/tcp_reno_cong_avoid")
+void BPF_PROG(tcp_reno_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (!tcp_is_cwnd_limited(sk))
+		return;
+
+	/* In "safe" area, increase. */
+	if (tcp_in_slow_start(tp)) {
+		acked = tcp_slow_start(tp, acked);
+		if (!acked)
+			return;
+	}
+	/* In dangerous area, increase slowly. */
+	tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops dctcp_nouse = {
+	.init		= (void *)dctcp_init,
+	.set_state	= (void *)dctcp_state,
+	.flags		= TCP_CONG_NEEDS_ECN,
+	.name		= "bpf_dctcp_nouse",
+};
+
+SEC(".struct_ops")
+struct tcp_congestion_ops dctcp = {
+	.init		= (void *)dctcp_init,
+	.in_ack_event   = (void *)dctcp_update_alpha,
+	.cwnd_event	= (void *)dctcp_cwnd_event,
+	.ssthresh	= (void *)dctcp_ssthresh,
+	.cong_avoid	= (void *)tcp_reno_cong_avoid,
+	.undo_cwnd	= (void *)dctcp_cwnd_undo,
+	.set_state	= (void *)dctcp_state,
+	.flags		= TCP_CONG_NEEDS_ECN,
+	.name		= "bpf_dctcp",
+};
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index 040a44206f29..9941f0ba471e 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@@ -16,8 +16,8 @@
 #include <sys/socket.h>
 #include <linux/if_tunnel.h>
 #include <linux/mpls.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 int _version SEC("version") = 1;
 #define PROG(F) SEC(#F) int bpf_func_##F
diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c
index 1fd244d35ba9..75085119c5bb 100644
--- a/tools/testing/selftests/bpf/progs/connect4_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect4_prog.c
@@ -9,8 +9,8 @@
 #include <linux/in6.h>
 #include <sys/socket.h>
 
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define SRC_REWRITE_IP4		0x7f000004U
 #define DST_REWRITE_IP4		0x7f000001U
diff --git a/tools/testing/selftests/bpf/progs/connect6_prog.c b/tools/testing/selftests/bpf/progs/connect6_prog.c
index 26397ab7b3c7..506d0f81a375 100644
--- a/tools/testing/selftests/bpf/progs/connect6_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect6_prog.c
@@ -9,8 +9,8 @@
 #include <linux/in6.h>
 #include <sys/socket.h>
 
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define SRC_REWRITE_IP6_0	0
 #define SRC_REWRITE_IP6_1	0
diff --git a/tools/testing/selftests/bpf/progs/dev_cgroup.c b/tools/testing/selftests/bpf/progs/dev_cgroup.c
index ce41a3475f27..8924e06bdef0 100644
--- a/tools/testing/selftests/bpf/progs/dev_cgroup.c
+++ b/tools/testing/selftests/bpf/progs/dev_cgroup.c
@@ -7,7 +7,7 @@
 
 #include <linux/bpf.h>
 #include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 SEC("cgroup/dev")
 int bpf_prog1(struct bpf_cgroup_dev_ctx *ctx)
diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c
index 615f7c6bca77..38d3a82144ca 100644
--- a/tools/testing/selftests/bpf/progs/fentry_test.c
+++ b/tools/testing/selftests/bpf/progs/fentry_test.c
@@ -1,43 +1,46 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "bpf_trace_helpers.h"
 
 char _license[] SEC("license") = "GPL";
 
 __u64 test1_result = 0;
-BPF_TRACE_1("fentry/bpf_fentry_test1", test1, int, a)
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test1, int a)
 {
 	test1_result = a == 1;
 	return 0;
 }
 
 __u64 test2_result = 0;
-BPF_TRACE_2("fentry/bpf_fentry_test2", test2, int, a, __u64, b)
+SEC("fentry/bpf_fentry_test2")
+int BPF_PROG(test2, int a, __u64 b)
 {
 	test2_result = a == 2 && b == 3;
 	return 0;
 }
 
 __u64 test3_result = 0;
-BPF_TRACE_3("fentry/bpf_fentry_test3", test3, char, a, int, b, __u64, c)
+SEC("fentry/bpf_fentry_test3")
+int BPF_PROG(test3, char a, int b, __u64 c)
 {
 	test3_result = a == 4 && b == 5 && c == 6;
 	return 0;
 }
 
 __u64 test4_result = 0;
-BPF_TRACE_4("fentry/bpf_fentry_test4", test4,
-	    void *, a, char, b, int, c, __u64, d)
+SEC("fentry/bpf_fentry_test4")
+int BPF_PROG(test4, void *a, char b, int c, __u64 d)
 {
 	test4_result = a == (void *)7 && b == 8 && c == 9 && d == 10;
 	return 0;
 }
 
 __u64 test5_result = 0;
-BPF_TRACE_5("fentry/bpf_fentry_test5", test5,
-	    __u64, a, void *, b, short, c, int, d, __u64, e)
+SEC("fentry/bpf_fentry_test5")
+int BPF_PROG(test5, __u64 a, void *b, short c, int d, __u64 e)
 {
 	test5_result = a == 11 && b == (void *)12 && c == 13 && d == 14 &&
 		e == 15;
@@ -45,8 +48,8 @@ BPF_TRACE_5("fentry/bpf_fentry_test5", test5,
 }
 
 __u64 test6_result = 0;
-BPF_TRACE_6("fentry/bpf_fentry_test6", test6,
-	    __u64, a, void *, b, short, c, int, d, void *, e, __u64, f)
+SEC("fentry/bpf_fentry_test6")
+int BPF_PROG(test6, __u64 a, void *b, short c, int d, void * e, __u64 f)
 {
 	test6_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
 		e == (void *)20 && f == 21;
diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
index 2d211ee98a1c..c329fccf9842 100644
--- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
@@ -1,7 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
+#include <linux/stddef.h>
+#include <linux/ipv6.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 #include "bpf_trace_helpers.h"
 
 struct sk_buff {
@@ -9,8 +12,8 @@ struct sk_buff {
 };
 
 __u64 test_result = 0;
-BPF_TRACE_2("fexit/test_pkt_access", test_main,
-	    struct sk_buff *, skb, int, ret)
+SEC("fexit/test_pkt_access")
+int BPF_PROG(test_main, struct sk_buff *skb, int ret)
 {
 	int len;
 
@@ -24,8 +27,8 @@ BPF_TRACE_2("fexit/test_pkt_access", test_main,
 }
 
 __u64 test_result_subprog1 = 0;
-BPF_TRACE_2("fexit/test_pkt_access_subprog1", test_subprog1,
-	    struct sk_buff *, skb, int, ret)
+SEC("fexit/test_pkt_access_subprog1")
+int BPF_PROG(test_subprog1, struct sk_buff *skb, int ret)
 {
 	int len;
 
@@ -79,4 +82,73 @@ int test_subprog2(struct args_subprog2 *ctx)
 	test_result_subprog2 = 1;
 	return 0;
 }
+
+__u64 test_result_subprog3 = 0;
+SEC("fexit/test_pkt_access_subprog3")
+int BPF_PROG(test_subprog3, int val, struct sk_buff *skb, int ret)
+{
+	int len;
+
+	__builtin_preserve_access_index(({
+		len = skb->len;
+	}));
+	if (len != 74 || ret != 74 * val || val != 3)
+		return 0;
+	test_result_subprog3 = 1;
+	return 0;
+}
+
+__u64 test_get_skb_len = 0;
+SEC("freplace/get_skb_len")
+int new_get_skb_len(struct __sk_buff *skb)
+{
+	int len = skb->len;
+
+	if (len != 74)
+		return 0;
+	test_get_skb_len = 1;
+	return 74; /* original get_skb_len() returns skb->len */
+}
+
+__u64 test_get_skb_ifindex = 0;
+SEC("freplace/get_skb_ifindex")
+int new_get_skb_ifindex(int val, struct __sk_buff *skb, int var)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ipv6hdr ip6, *ip6p;
+	int ifindex = skb->ifindex;
+	__u32 eth_proto;
+	__u32 nh_off;
+
+	/* check that BPF extension can read packet via direct packet access */
+	if (data + 14 + sizeof(ip6) > data_end)
+		return 0;
+	ip6p = data + 14;
+
+	if (ip6p->nexthdr != 6 || ip6p->payload_len != __bpf_constant_htons(123))
+		return 0;
+
+	/* check that legacy packet access helper works too */
+	if (bpf_skb_load_bytes(skb, 14, &ip6, sizeof(ip6)) < 0)
+		return 0;
+	ip6p = &ip6;
+	if (ip6p->nexthdr != 6 || ip6p->payload_len != __bpf_constant_htons(123))
+		return 0;
+
+	if (ifindex != 1 || val != 3 || var != 1)
+		return 0;
+	test_get_skb_ifindex = 1;
+	return 3; /* original get_skb_ifindex() returns val * ifindex * var */
+}
+
+volatile __u64 test_get_constant = 0;
+SEC("freplace/get_constant")
+int new_get_constant(long val)
+{
+	if (val != 123)
+		return 0;
+	test_get_constant = 1;
+	return test_get_constant; /* original get_constant() returns val - 122 */
+}
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
index ebc0ab7f0f5c..92f3fa47cf40 100644
--- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
+++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "bpf_trace_helpers.h"
 
 struct sk_buff {
@@ -9,8 +9,9 @@ struct sk_buff {
 };
 
 __u64 test_result = 0;
-BPF_TRACE_2("fexit/test_pkt_md_access", test_main2,
-	    struct sk_buff *, skb, int, ret)
+
+SEC("fexit/test_pkt_md_access")
+int BPF_PROG(test_main2, struct sk_buff *skb, int ret)
 {
 	int len;
 
diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c
index 86db0d60fb6e..348109b9ea07 100644
--- a/tools/testing/selftests/bpf/progs/fexit_test.c
+++ b/tools/testing/selftests/bpf/progs/fexit_test.c
@@ -1,45 +1,47 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "bpf_trace_helpers.h"
 
 char _license[] SEC("license") = "GPL";
 
 __u64 test1_result = 0;
-BPF_TRACE_2("fexit/bpf_fentry_test1", test1, int, a, int, ret)
+SEC("fexit/bpf_fentry_test1")
+int BPF_PROG(test1, int a, int ret)
 {
 	test1_result = a == 1 && ret == 2;
 	return 0;
 }
 
 __u64 test2_result = 0;
-BPF_TRACE_3("fexit/bpf_fentry_test2", test2, int, a, __u64, b, int, ret)
+SEC("fexit/bpf_fentry_test2")
+int BPF_PROG(test2, int a, __u64 b, int ret)
 {
 	test2_result = a == 2 && b == 3 && ret == 5;
 	return 0;
 }
 
 __u64 test3_result = 0;
-BPF_TRACE_4("fexit/bpf_fentry_test3", test3, char, a, int, b, __u64, c, int, ret)
+SEC("fexit/bpf_fentry_test3")
+int BPF_PROG(test3, char a, int b, __u64 c, int ret)
 {
 	test3_result = a == 4 && b == 5 && c == 6 && ret == 15;
 	return 0;
 }
 
 __u64 test4_result = 0;
-BPF_TRACE_5("fexit/bpf_fentry_test4", test4,
-	    void *, a, char, b, int, c, __u64, d, int, ret)
+SEC("fexit/bpf_fentry_test4")
+int BPF_PROG(test4, void *a, char b, int c, __u64 d, int ret)
 {
-
 	test4_result = a == (void *)7 && b == 8 && c == 9 && d == 10 &&
 		ret == 34;
 	return 0;
 }
 
 __u64 test5_result = 0;
-BPF_TRACE_6("fexit/bpf_fentry_test5", test5,
-	    __u64, a, void *, b, short, c, int, d, __u64, e, int, ret)
+SEC("fexit/bpf_fentry_test5")
+int BPF_PROG(test5, __u64 a, void *b, short c, int d, __u64 e, int ret)
 {
 	test5_result = a == 11 && b == (void *)12 && c == 13 && d == 14 &&
 		e == 15 && ret == 65;
@@ -47,9 +49,8 @@ BPF_TRACE_6("fexit/bpf_fentry_test5", test5,
 }
 
 __u64 test6_result = 0;
-BPF_TRACE_7("fexit/bpf_fentry_test6", test6,
-	    __u64, a, void *, b, short, c, int, d, void *, e, __u64, f,
-	    int, ret)
+SEC("fexit/bpf_fentry_test6")
+int BPF_PROG(test6, __u64 a, void *b, short c, int d, void *e, __u64 f, int ret)
 {
 	test6_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
 		e == (void *)20 && f == 21 && ret == 111;
diff --git a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
index 16c54ade6888..6b42db2fe391 100644
--- a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
+++ b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
@@ -2,7 +2,7 @@
 // Copyright (c) 2018 Facebook
 
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c
index 974d6f3bb319..8f48a909f079 100644
--- a/tools/testing/selftests/bpf/progs/kfree_skb.c
+++ b/tools/testing/selftests/bpf/progs/kfree_skb.c
@@ -2,8 +2,8 @@
 // Copyright (c) 2019 Facebook
 #include <linux/bpf.h>
 #include <stdbool.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 #include "bpf_trace_helpers.h"
 
 char _license[] SEC("license") = "GPL";
@@ -57,8 +57,8 @@ struct meta {
 /* TRACE_EVENT(kfree_skb,
  *         TP_PROTO(struct sk_buff *skb, void *location),
  */
-BPF_TRACE_2("tp_btf/kfree_skb", trace_kfree_skb,
-	    struct sk_buff *, skb, void *, location)
+SEC("tp_btf/kfree_skb")
+int BPF_PROG(trace_kfree_skb, struct sk_buff *skb, void *location)
 {
 	struct net_device *dev;
 	struct callback_head *ptr;
@@ -114,9 +114,9 @@ static volatile struct {
 	bool fexit_test_ok;
 } result;
 
-BPF_TRACE_3("fentry/eth_type_trans", fentry_eth_type_trans,
-	    struct sk_buff *, skb, struct net_device *, dev,
-	    unsigned short, protocol)
+SEC("fentry/eth_type_trans")
+int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb, struct net_device *dev,
+	     unsigned short protocol)
 {
 	int len, ifindex;
 
@@ -132,9 +132,9 @@ BPF_TRACE_3("fentry/eth_type_trans", fentry_eth_type_trans,
 	return 0;
 }
 
-BPF_TRACE_3("fexit/eth_type_trans", fexit_eth_type_trans,
-	    struct sk_buff *, skb, struct net_device *, dev,
-	    unsigned short, protocol)
+SEC("fexit/eth_type_trans")
+int BPF_PROG(fexit_eth_type_trans, struct sk_buff *skb, struct net_device *dev,
+	     unsigned short protocol)
 {
 	int len, ifindex;
 
diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c
index 40ac722a9da5..50e66772c046 100644
--- a/tools/testing/selftests/bpf/progs/loop1.c
+++ b/tools/testing/selftests/bpf/progs/loop1.c
@@ -6,8 +6,8 @@
 #include <stddef.h>
 #include <stdbool.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c
index bb80f29aa7f7..947bb7e988c2 100644
--- a/tools/testing/selftests/bpf/progs/loop2.c
+++ b/tools/testing/selftests/bpf/progs/loop2.c
@@ -6,8 +6,8 @@
 #include <stddef.h>
 #include <stdbool.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c
index 2b9165a7afe1..76e93b31c14b 100644
--- a/tools/testing/selftests/bpf/progs/loop3.c
+++ b/tools/testing/selftests/bpf/progs/loop3.c
@@ -6,8 +6,8 @@
 #include <stddef.h>
 #include <stdbool.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/loop4.c b/tools/testing/selftests/bpf/progs/loop4.c
index 650859022771..b35337926d66 100644
--- a/tools/testing/selftests/bpf/progs/loop4.c
+++ b/tools/testing/selftests/bpf/progs/loop4.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/loop5.c b/tools/testing/selftests/bpf/progs/loop5.c
index 28d1d668f07c..913791923fa3 100644
--- a/tools/testing/selftests/bpf/progs/loop5.c
+++ b/tools/testing/selftests/bpf/progs/loop5.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #define barrier() __asm__ __volatile__("": : :"memory")
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c
index 38a997852cad..d071adf178bd 100644
--- a/tools/testing/selftests/bpf/progs/netcnt_prog.c
+++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c
@@ -2,7 +2,7 @@
 #include <linux/bpf.h>
 #include <linux/version.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "netcnt_common.h"
 
 #define MAX_BPS	(3 * 1024 * 1024)
diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h
index 71d383cc9b85..cc615b82b56e 100644
--- a/tools/testing/selftests/bpf/progs/pyperf.h
+++ b/tools/testing/selftests/bpf/progs/pyperf.h
@@ -6,7 +6,7 @@
 #include <stddef.h>
 #include <stdbool.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #define FUNCTION_NAME_LEN 64
 #define FILE_NAME_LEN 128
@@ -154,7 +154,12 @@ struct {
 	__uint(value_size, sizeof(long long) * 127);
 } stackmap SEC(".maps");
 
-static __always_inline int __on_event(struct pt_regs *ctx)
+#ifdef GLOBAL_FUNC
+__attribute__((noinline))
+#else
+static __always_inline
+#endif
+int __on_event(struct bpf_raw_tracepoint_args *ctx)
 {
 	uint64_t pid_tgid = bpf_get_current_pid_tgid();
 	pid_t pid = (pid_t)(pid_tgid >> 32);
@@ -254,7 +259,7 @@ static __always_inline int __on_event(struct pt_regs *ctx)
 }
 
 SEC("raw_tracepoint/kfree_skb")
-int on_event(struct pt_regs* ctx)
+int on_event(struct bpf_raw_tracepoint_args* ctx)
 {
 	int i, ret = 0;
 	ret |= __on_event(ctx);
diff --git a/tools/testing/selftests/bpf/progs/pyperf_global.c b/tools/testing/selftests/bpf/progs/pyperf_global.c
new file mode 100644
index 000000000000..079e78a7562b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/pyperf_global.c
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define STACK_MAX_LEN 50
+#define GLOBAL_FUNC
+#include "pyperf.h"
diff --git a/tools/testing/selftests/bpf/progs/sample_map_ret0.c b/tools/testing/selftests/bpf/progs/sample_map_ret0.c
index 0756303676ac..1612a32007b6 100644
--- a/tools/testing/selftests/bpf/progs/sample_map_ret0.c
+++ b/tools/testing/selftests/bpf/progs/sample_map_ret0.c
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct bpf_map_def SEC("maps") htab = {
 	.type = BPF_MAP_TYPE_HASH,
diff --git a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
index a91536b1c47e..092d9da536f3 100644
--- a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
@@ -5,8 +5,8 @@
 #include <linux/bpf.h>
 #include <sys/socket.h>
 
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define SRC1_IP4		0xAC100001U /* 172.16.0.1 */
 #define SRC2_IP4		0x00000000U
diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
index a68062820410..255a432bc163 100644
--- a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
@@ -5,8 +5,8 @@
 #include <linux/bpf.h>
 #include <sys/socket.h>
 
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define SRC_REWRITE_IP6_0	0
 #define SRC_REWRITE_IP6_1	0
diff --git a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c
index e4440fdd94cb..0cb5656a22b0 100644
--- a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c
+++ b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c
@@ -4,8 +4,8 @@
 #include <linux/bpf.h>
 #include <sys/socket.h>
 
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 struct socket_cookie {
 	__u64 cookie_key;
diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
index 9390e0244259..a5c6d5903b22 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
@@ -1,6 +1,6 @@
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
index e80484d98a1a..fdb4bf4408fa 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
@@ -1,7 +1,7 @@
 #include <linux/bpf.h>
 
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
index 433e23918a62..4797dc985064 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
@@ -1,6 +1,6 @@
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
index dede0fcd6102..c6d428a8d785 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
 __u32 _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c
index 4afd2595c08e..9d8c212dde9f 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_multi.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <netinet/in.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
 __u32 _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c
index 1bafbb944e37..d5a5eeb5fb52 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c
@@ -3,7 +3,7 @@
 #include <netinet/in.h>
 #include <netinet/tcp.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
 __u32 _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index 4bf16e0a1b0e..ad61b722a9de 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -8,7 +8,7 @@
 #include <linux/ptrace.h>
 #include <linux/sched.h>
 #include <linux/types.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 typedef uint32_t pid_t;
 struct task_struct {};
diff --git a/tools/testing/selftests/bpf/progs/tailcall1.c b/tools/testing/selftests/bpf/progs/tailcall1.c
index 63531e1a9fa4..1f407e65ae52 100644
--- a/tools/testing/selftests/bpf/progs/tailcall1.c
+++ b/tools/testing/selftests/bpf/progs/tailcall1.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/tailcall2.c b/tools/testing/selftests/bpf/progs/tailcall2.c
index 21c85c477210..a093e739cf0e 100644
--- a/tools/testing/selftests/bpf/progs/tailcall2.c
+++ b/tools/testing/selftests/bpf/progs/tailcall2.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c
index 1ecae198b8c1..cabda877cf0a 100644
--- a/tools/testing/selftests/bpf/progs/tailcall3.c
+++ b/tools/testing/selftests/bpf/progs/tailcall3.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/tailcall4.c b/tools/testing/selftests/bpf/progs/tailcall4.c
index 499388758119..f82075b47d7d 100644
--- a/tools/testing/selftests/bpf/progs/tailcall4.c
+++ b/tools/testing/selftests/bpf/progs/tailcall4.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/tailcall5.c b/tools/testing/selftests/bpf/progs/tailcall5.c
index 49c64eb53f19..ce5450744fd4 100644
--- a/tools/testing/selftests/bpf/progs/tailcall5.c
+++ b/tools/testing/selftests/bpf/progs/tailcall5.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/tcp_rtt.c b/tools/testing/selftests/bpf/progs/tcp_rtt.c
index 2cf813a06b83..0cb3204ddb18 100644
--- a/tools/testing/selftests/bpf/progs/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/progs/tcp_rtt.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
 __u32 _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_adjust_tail.c b/tools/testing/selftests/bpf/progs/test_adjust_tail.c
index 4cd5e860c903..b7fc85769bdc 100644
--- a/tools/testing/selftests/bpf/progs/test_adjust_tail.c
+++ b/tools/testing/selftests/bpf/progs/test_adjust_tail.c
@@ -7,7 +7,7 @@
  */
 #include <linux/bpf.h>
 #include <linux/if_ether.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c
index 221b69700625..dd8fae6660ab 100644
--- a/tools/testing/selftests/bpf/progs/test_attach_probe.c
+++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c
@@ -3,7 +3,7 @@
 
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 int kprobe_res = 0;
 int kretprobe_res = 0;
diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
index 62ad7e22105e..88b0566da13d 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright (c) 2018 Facebook */
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "bpf_legacy.h"
 
 int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
index fb8d91a1dbe0..a924e53c8e9d 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright (c) 2018 Facebook */
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "bpf_legacy.h"
 
 int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
index 3f4422044759..983aedd1c072 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright (c) 2018 Facebook */
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_extern.c b/tools/testing/selftests/bpf/progs/test_core_extern.c
index 9bfc91d9d004..3ac3603ad53d 100644
--- a/tools/testing/selftests/bpf/progs/test_core_extern.c
+++ b/tools/testing/selftests/bpf/progs/test_core_extern.c
@@ -5,7 +5,7 @@
 #include <stdbool.h>
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 /* non-existing BPF helper, to test dead code elimination */
 static int (*bpf_missing_helper)(const void *arg1, int arg2) = (void *) 999;
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
index 053b86f6b53f..51b3f79df523 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
@@ -3,8 +3,8 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c
index edc0f7c9e56d..56aec20212b5 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c
@@ -3,8 +3,8 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
index 6c20e433558b..ab1e647aeb31 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
@@ -3,8 +3,8 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c b/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c
index 1b7f0ae49cfb..7e45e2bdf6cd 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c
@@ -3,8 +3,8 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c
index b5dbeef540fd..525acc2f841b 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c
@@ -3,8 +3,8 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c
index c78ab6d28a14..6b5290739806 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c
@@ -3,8 +3,8 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
index 270de441b60a..aba928fd60d3 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
@@ -3,8 +3,8 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c
index 292a5c4ee76a..d5756dbdef82 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c
@@ -3,8 +3,8 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c
index 0b28bfacc8fd..8b533db4a7a5 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c
@@ -3,8 +3,8 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c
index 39279bf0c9db..2b4b6d49c677 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c
@@ -3,8 +3,8 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c
index ea57973cdd19..2a8975678aa6 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c
@@ -3,8 +3,8 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c
index d1eb59d4ea64..ca61a5183b88 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c
@@ -3,8 +3,8 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_size.c b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c
index 9e091124d3bd..d7fb6cfc7891 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_size.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c
@@ -3,8 +3,8 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
index 6a4a8f57f174..29817a703984 100644
--- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
+++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 /* Permit pretty deep stack traces */
 #define MAX_STACK_RAWTP 100
diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c
index 32a6073acb99..dd7a4d3dbc0d 100644
--- a/tools/testing/selftests/bpf/progs/test_global_data.c
+++ b/tools/testing/selftests/bpf/progs/test_global_data.c
@@ -5,7 +5,7 @@
 #include <linux/pkt_cls.h>
 #include <string.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c
new file mode 100644
index 000000000000..880260f6d536
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func1.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#ifndef MAX_STACK
+#define MAX_STACK (512 - 3 * 32 + 8)
+#endif
+
+static __attribute__ ((noinline))
+int f0(int var, struct __sk_buff *skb)
+{
+	return skb->len;
+}
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+	volatile char buf[MAX_STACK] = {};
+
+	return f0(0, skb) + skb->len;
+}
+
+int f3(int, struct __sk_buff *skb, int);
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+	return f1(skb) + f3(val, skb, 1);
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb, int var)
+{
+	volatile char buf[MAX_STACK] = {};
+
+	return skb->ifindex * val * var;
+}
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+	return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func2.c b/tools/testing/selftests/bpf/progs/test_global_func2.c
new file mode 100644
index 000000000000..2c18d82923a2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func2.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#define MAX_STACK (512 - 3 * 32)
+#include "test_global_func1.c"
diff --git a/tools/testing/selftests/bpf/progs/test_global_func3.c b/tools/testing/selftests/bpf/progs/test_global_func3.c
new file mode 100644
index 000000000000..86f0ecb304fc
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func3.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+	return skb->len;
+}
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+	return f1(skb) + val;
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb, int var)
+{
+	return f2(var, skb) + val;
+}
+
+__attribute__ ((noinline))
+int f4(struct __sk_buff *skb)
+{
+	return f3(1, skb, 2);
+}
+
+__attribute__ ((noinline))
+int f5(struct __sk_buff *skb)
+{
+	return f4(skb);
+}
+
+__attribute__ ((noinline))
+int f6(struct __sk_buff *skb)
+{
+	return f5(skb);
+}
+
+__attribute__ ((noinline))
+int f7(struct __sk_buff *skb)
+{
+	return f6(skb);
+}
+
+#ifndef NO_FN8
+__attribute__ ((noinline))
+int f8(struct __sk_buff *skb)
+{
+	return f7(skb);
+}
+#endif
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+#ifndef NO_FN8
+	return f8(skb);
+#else
+	return f7(skb);
+#endif
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func4.c b/tools/testing/selftests/bpf/progs/test_global_func4.c
new file mode 100644
index 000000000000..610f75edf276
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func4.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#define NO_FN8
+#include "test_global_func3.c"
diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c
new file mode 100644
index 000000000000..260c25b827ef
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func5.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+	return skb->len;
+}
+
+int f3(int, struct __sk_buff *skb);
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+	return f1(skb) + f3(val, (void *)&val); /* type mismatch */
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb)
+{
+	return skb->ifindex * val;
+}
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+	return f1(skb) + f2(2, skb) + f3(3, skb);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func6.c b/tools/testing/selftests/bpf/progs/test_global_func6.c
new file mode 100644
index 000000000000..69e19c64e10b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func6.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+	return skb->len;
+}
+
+int f3(int, struct __sk_buff *skb);
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+	return f1(skb) + f3(val, skb + 1); /* type mismatch */
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb)
+{
+	return skb->ifindex * val;
+}
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+	return f1(skb) + f2(2, skb) + f3(3, skb);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func7.c b/tools/testing/selftests/bpf/progs/test_global_func7.c
new file mode 100644
index 000000000000..309b3f6136bd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func7.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__attribute__ ((noinline))
+void foo(struct __sk_buff *skb)
+{
+	skb->tc_index = 0;
+}
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+	foo(skb);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_l4lb.c b/tools/testing/selftests/bpf/progs/test_l4lb.c
index 1d652ee8e73d..33493911d87a 100644
--- a/tools/testing/selftests/bpf/progs/test_l4lb.c
+++ b/tools/testing/selftests/bpf/progs/test_l4lb.c
@@ -17,9 +17,9 @@
 #include <linux/icmpv6.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "test_iptunnel_common.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
index 2e4efe70b1e5..28351936a438 100644
--- a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
@@ -13,9 +13,9 @@
 #include <linux/icmpv6.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "test_iptunnel_common.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c
index 4147130cc3b7..7a6620671a83 100644
--- a/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c
@@ -5,7 +5,7 @@
 
 #include <linux/bpf.h>
 #include <linux/lirc.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 SEC("lirc_mode2")
 int bpf_decoder(unsigned int *sample)
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
index c957d6dfe6d7..d6cb986e7533 100644
--- a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
+++ b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
@@ -4,8 +4,8 @@
 #include <linux/bpf.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 struct grehdr {
 	__be16 flags;
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
index 41a3ebcd593d..48ff2b2ad5e7 100644
--- a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
+++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
@@ -3,8 +3,8 @@
 #include <errno.h>
 #include <linux/seg6_local.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 /* Packet parsing state machine helpers. */
 #define cursor_advance(_cursor, _len) \
diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c
index 113226115365..1cfeb940cf9f 100644
--- a/tools/testing/selftests/bpf/progs/test_map_in_map.c
+++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c
@@ -3,7 +3,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <linux/types.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
diff --git a/tools/testing/selftests/bpf/progs/test_map_lock.c b/tools/testing/selftests/bpf/progs/test_map_lock.c
index bb7ce35f691b..b5c07ae7b68f 100644
--- a/tools/testing/selftests/bpf/progs/test_map_lock.c
+++ b/tools/testing/selftests/bpf/progs/test_map_lock.c
@@ -2,7 +2,7 @@
 // Copyright (c) 2019 Facebook
 #include <linux/bpf.h>
 #include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #define VAR_NUM 16
 
diff --git a/tools/testing/selftests/bpf/progs/test_mmap.c b/tools/testing/selftests/bpf/progs/test_mmap.c
index e808791b7047..6239596cd14e 100644
--- a/tools/testing/selftests/bpf/progs/test_mmap.c
+++ b/tools/testing/selftests/bpf/progs/test_mmap.c
@@ -3,7 +3,7 @@
 
 #include <linux/bpf.h>
 #include <stdint.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/test_obj_id.c b/tools/testing/selftests/bpf/progs/test_obj_id.c
index 3d30c02bdae9..98b9de2fafd0 100644
--- a/tools/testing/selftests/bpf/progs/test_obj_id.c
+++ b/tools/testing/selftests/bpf/progs/test_obj_id.c
@@ -4,7 +4,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 /* It is a dumb bpf program such that it must have no
  * issue to be loaded since testing the verifier is
diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c
index 96c0124a04ba..bfe9fbcb9684 100644
--- a/tools/testing/selftests/bpf/progs/test_overhead.c
+++ b/tools/testing/selftests/bpf/progs/test_overhead.c
@@ -1,39 +1,45 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
+#include <stdbool.h>
+#include <stddef.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <linux/ptrace.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 #include "bpf_trace_helpers.h"
 
+struct task_struct;
+
 SEC("kprobe/__set_task_comm")
-int prog1(struct pt_regs *ctx)
+int BPF_KPROBE(prog1, struct task_struct *tsk, const char *buf, bool exec)
 {
-	return 0;
+	return !tsk;
 }
 
 SEC("kretprobe/__set_task_comm")
-int prog2(struct pt_regs *ctx)
+int BPF_KRETPROBE(prog2,
+		  struct task_struct *tsk, const char *buf, bool exec,
+		  int ret)
 {
-	return 0;
+	return !PT_REGS_PARM1(ctx) && ret;
 }
 
 SEC("raw_tp/task_rename")
 int prog3(struct bpf_raw_tracepoint_args *ctx)
 {
-	return 0;
+	return !ctx->args[0];
 }
 
-struct task_struct;
-BPF_TRACE_3("fentry/__set_task_comm", prog4,
-	    struct task_struct *, tsk, const char *, buf, __u8, exec)
+SEC("fentry/__set_task_comm")
+int BPF_PROG(prog4, struct task_struct *tsk, const char *buf, bool exec)
 {
-	return 0;
+	return !tsk;
 }
 
-BPF_TRACE_3("fexit/__set_task_comm", prog5,
-	    struct task_struct *, tsk, const char *, buf, __u8, exec)
+SEC("fexit/__set_task_comm")
+int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec)
 {
-	return 0;
+	return !tsk;
 }
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
index 07c09ca5546a..ebfcc9f50c35 100644
--- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
@@ -3,7 +3,8 @@
 
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_trace_helpers.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
@@ -12,7 +13,7 @@ struct {
 } perf_buf_map SEC(".maps");
 
 SEC("kprobe/sys_nanosleep")
-int handle_sys_nanosleep_entry(struct pt_regs *ctx)
+int BPF_KPROBE(handle_sys_nanosleep_entry)
 {
 	int cpu = bpf_get_smp_processor_id();
 
diff --git a/tools/testing/selftests/bpf/progs/test_pinning.c b/tools/testing/selftests/bpf/progs/test_pinning.c
index f20e7e00373f..4ef2630292b2 100644
--- a/tools/testing/selftests/bpf/progs/test_pinning.c
+++ b/tools/testing/selftests/bpf/progs/test_pinning.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c
index 51b38abe7ba1..5412e0c732c7 100644
--- a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c
+++ b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c
index 3a7b4b607ed3..e72eba4a93d2 100644
--- a/tools/testing/selftests/bpf/progs/test_pkt_access.c
+++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c
@@ -11,8 +11,8 @@
 #include <linux/in.h>
 #include <linux/tcp.h>
 #include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define barrier() __asm__ __volatile__("": : :"memory")
 int _version SEC("version") = 1;
@@ -47,6 +47,38 @@ int test_pkt_access_subprog2(int val, volatile struct __sk_buff *skb)
 	return skb->len * val;
 }
 
+#define MAX_STACK (512 - 2 * 32)
+
+__attribute__ ((noinline))
+int get_skb_len(struct __sk_buff *skb)
+{
+	volatile char buf[MAX_STACK] = {};
+
+	return skb->len;
+}
+
+__attribute__ ((noinline))
+int get_constant(long val)
+{
+	return val - 122;
+}
+
+int get_skb_ifindex(int, struct __sk_buff *skb, int);
+
+__attribute__ ((noinline))
+int test_pkt_access_subprog3(int val, struct __sk_buff *skb)
+{
+	return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123));
+}
+
+__attribute__ ((noinline))
+int get_skb_ifindex(int val, struct __sk_buff *skb, int var)
+{
+	volatile char buf[MAX_STACK] = {};
+
+	return skb->ifindex * val * var;
+}
+
 SEC("classifier/test_pkt_access")
 int test_pkt_access(struct __sk_buff *skb)
 {
@@ -82,6 +114,8 @@ int test_pkt_access(struct __sk_buff *skb)
 		return TC_ACT_SHOT;
 	if (test_pkt_access_subprog2(2, skb) != skb->len * 2)
 		return TC_ACT_SHOT;
+	if (test_pkt_access_subprog3(3, skb) != skb->len * 3 * skb->ifindex)
+		return TC_ACT_SHOT;
 	if (tcp) {
 		if (((void *)(tcp) + 20) > data_end || proto != 6)
 			return TC_ACT_SHOT;
diff --git a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c
index 1db2623021ad..610c74ea9f64 100644
--- a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c
+++ b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c
@@ -5,7 +5,7 @@
 #include <string.h>
 #include <linux/bpf.h>
 #include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c
index 1871e2ece0c4..d556b1572cc6 100644
--- a/tools/testing/selftests/bpf/progs/test_probe_user.c
+++ b/tools/testing/selftests/bpf/progs/test_probe_user.c
@@ -5,13 +5,14 @@
 
 #include <netinet/in.h>
 
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_trace_helpers.h"
 
 static struct sockaddr_in old;
 
 SEC("kprobe/__sys_connect")
-int handle_sys_connect(struct pt_regs *ctx)
+int BPF_KPROBE(handle_sys_connect)
 {
 	void *ptr = (void *)PT_REGS_PARM2(ctx);
 	struct sockaddr_in new;
diff --git a/tools/testing/selftests/bpf/progs/test_queue_stack_map.h b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h
index 0e014d3b2b36..4dd9806ad73b 100644
--- a/tools/testing/selftests/bpf/progs/test_queue_stack_map.h
+++ b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h
@@ -6,7 +6,7 @@
 #include <linux/if_ether.h>
 #include <linux/ip.h>
 #include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
index 52d94e8b214d..ecbeea2df259 100644
--- a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
+++ b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
@@ -3,7 +3,7 @@
 
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 static volatile const struct {
 	unsigned a[4];
diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c
index 69880c1e7700..a7278f064368 100644
--- a/tools/testing/selftests/bpf/progs/test_seg6_loop.c
+++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c
@@ -3,8 +3,8 @@
 #include <errno.h>
 #include <linux/seg6_local.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 /* Packet parsing state machine helpers. */
 #define cursor_advance(_cursor, _len) \
diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
index b1f09f5bb1cf..d69a1f2bbbfd 100644
--- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
@@ -11,8 +11,8 @@
 #include <linux/types.h>
 #include <linux/if_ether.h>
 
-#include "bpf_endian.h"
-#include "bpf_helpers.h"
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
 #include "test_select_reuseport_common.h"
 
 int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
index 0e6be01157e6..1acc91e87bfc 100644
--- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
@@ -2,46 +2,39 @@
 // Copyright (c) 2019 Facebook
 #include <linux/bpf.h>
 #include <linux/version.h>
-#include "bpf_helpers.h"
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 1);
-	__type(key, __u32);
-	__type(value, __u64);
-} info_map SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 1);
-	__type(key, __u32);
-	__type(value, __u64);
-} status_map SEC(".maps");
-
-SEC("send_signal_demo")
-int bpf_send_signal_test(void *ctx)
+#include <bpf/bpf_helpers.h>
+
+__u32 sig = 0, pid = 0, status = 0, signal_thread = 0;
+
+static __always_inline int bpf_send_signal_test(void *ctx)
 {
-	__u64 *info_val, *status_val;
-	__u32 key = 0, pid, sig;
 	int ret;
 
-	status_val = bpf_map_lookup_elem(&status_map, &key);
-	if (!status_val || *status_val != 0)
-		return 0;
-
-	info_val = bpf_map_lookup_elem(&info_map, &key);
-	if (!info_val || *info_val == 0)
+	if (status != 0 || sig == 0 || pid == 0)
 		return 0;
 
-	sig = *info_val >> 32;
-	pid = *info_val & 0xffffFFFF;
-
 	if ((bpf_get_current_pid_tgid() >> 32) == pid) {
-		ret = bpf_send_signal(sig);
+		if (signal_thread)
+			ret = bpf_send_signal_thread(sig);
+		else
+			ret = bpf_send_signal(sig);
 		if (ret == 0)
-			*status_val = 1;
+			status = 1;
 	}
 
 	return 0;
 }
+
+SEC("tracepoint/syscalls/sys_enter_nanosleep")
+int send_signal_tp(void *ctx)
+{
+	return bpf_send_signal_test(ctx);
+}
+
+SEC("perf_event")
+int send_signal_perf(void *ctx)
+{
+	return bpf_send_signal_test(ctx);
+}
+
 char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
index cb49ccb707d1..d2b38fa6a5b0 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
@@ -12,8 +12,8 @@
 #include <linux/pkt_cls.h>
 #include <linux/tcp.h>
 #include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 int _version SEC("version") = 1;
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
index 68cf9829f5a7..552f2090665c 100644
--- a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
@@ -6,7 +6,7 @@
 
 #include <string.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #define NUM_CGROUP_LEVELS	4
 
diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
index e18da87fe84f..202de3938494 100644
--- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 int _version SEC("version") = 1;
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c
index 4f69aac5635f..de03a90f78ca 100644
--- a/tools/testing/selftests/bpf/progs/test_skeleton.c
+++ b/tools/testing/selftests/bpf/progs/test_skeleton.c
@@ -3,7 +3,7 @@
 
 #include <stdbool.h>
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct s {
 	int a;
diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
index a47b003623ef..9bcaa37f476a 100644
--- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
@@ -5,8 +5,8 @@
 #include <netinet/in.h>
 #include <stdbool.h>
 
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 enum bpf_addr_array_idx {
 	ADDR_SRV_IDX,
diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c
index a43b999c8da2..0d31a3b3505f 100644
--- a/tools/testing/selftests/bpf/progs/test_spin_lock.c
+++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c
@@ -2,7 +2,7 @@
 // Copyright (c) 2019 Facebook
 #include <linux/bpf.h>
 #include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct hmap_elem {
 	volatile int cnt;
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
index f5638e26865d..0cf0134631b4 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
@@ -2,7 +2,7 @@
 // Copyright (c) 2018 Facebook
 
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #ifndef PERF_MAX_STACK_DEPTH
 #define PERF_MAX_STACK_DEPTH         127
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
index 3b7e1dca8829..00ed48672620 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
@@ -2,7 +2,7 @@
 // Copyright (c) 2018 Facebook
 
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #ifndef PERF_MAX_STACK_DEPTH
 #define PERF_MAX_STACK_DEPTH         127
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
index d22e438198cf..458b0d69133e 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
@@ -7,7 +7,7 @@
 #include <linux/stddef.h>
 #include <linux/bpf.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #ifndef ARRAY_SIZE
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
index cb201cbe11e7..b2e6f9b0894d 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
@@ -7,7 +7,7 @@
 #include <linux/stddef.h>
 #include <linux/bpf.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #ifndef ARRAY_SIZE
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
index 5cbbff416998..2d0b0b82a78a 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
@@ -7,7 +7,7 @@
 #include <linux/stddef.h>
 #include <linux/bpf.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 /* Max supported length of a string with unsigned long in base 10 (pow2 - 1). */
 #define MAX_ULONG_STR_LEN 0xF
diff --git a/tools/testing/selftests/bpf/progs/test_tc_edt.c b/tools/testing/selftests/bpf/progs/test_tc_edt.c
index 0961415ba477..bf28814bfde5 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_edt.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_edt.c
@@ -7,8 +7,8 @@
 #include <linux/ip.h>
 #include <linux/pkt_cls.h>
 #include <linux/tcp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 /* the maximum delay we are willing to add (drop packets beyond that) */
 #define TIME_HORIZON_NS (2000 * 1000 * 1000)
diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
index 74370e7e286d..37bce7a7c394 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
@@ -17,8 +17,8 @@
 #include <linux/pkt_cls.h>
 #include <linux/types.h>
 
-#include "bpf_endian.h"
-#include "bpf_helpers.h"
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
 
 static const int cfg_port = 8000;
 
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
index d8803dfa8d32..47cbe2eeae43 100644
--- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
@@ -13,8 +13,8 @@
 #include <sys/socket.h>
 #include <linux/tcp.h>
 
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 struct bpf_map_def SEC("maps") results = {
 	.type = BPF_MAP_TYPE_ARRAY,
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c
index 87b7d934ce73..adc83a54c352 100644
--- a/tools/testing/selftests/bpf/progs/test_tcp_estats.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c
@@ -36,7 +36,7 @@
 #include <linux/ipv6.h>
 #include <linux/version.h>
 #include <sys/socket.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #define _(P) ({typeof(P) val = 0; bpf_probe_read_kernel(&val, sizeof(val), &P); val;})
 #define TCP_ESTATS_MAGIC 0xBAADBEEF
diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
index 7fa4595d2b66..1f1966e86e9f 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
@@ -10,8 +10,8 @@
 #include <linux/types.h>
 #include <linux/socket.h>
 #include <linux/tcp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 #include "test_tcpbpf.h"
 
 struct {
diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
index 08346e7765d5..ac63410bb541 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
@@ -10,8 +10,8 @@
 #include <linux/types.h>
 #include <linux/socket.h>
 #include <linux/tcp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 #include "test_tcpnotify.h"
 
 struct {
diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c
index 04bf084517e0..4b825ee122cf 100644
--- a/tools/testing/selftests/bpf/progs/test_tracepoint.c
+++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c
@@ -2,7 +2,7 @@
 // Copyright (c) 2017 Facebook
 
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
 struct sched_switch_args {
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index 504df69c83df..f48dbfe24ddc 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -19,8 +19,8 @@
 #include <linux/socket.h>
 #include <linux/pkt_cls.h>
 #include <linux/erspan.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define ERROR(ret) do {\
 		char fmt[] = "ERROR line:%d ret:%d\n";\
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale1.c b/tools/testing/selftests/bpf/progs/test_verif_scale1.c
index f3236ce35f31..d38153dab3dd 100644
--- a/tools/testing/selftests/bpf/progs/test_verif_scale1.c
+++ b/tools/testing/selftests/bpf/progs/test_verif_scale1.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #define ATTR __attribute__((noinline))
 #include "test_jhash.h"
 
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale2.c b/tools/testing/selftests/bpf/progs/test_verif_scale2.c
index 9897150ed516..f024154c7be7 100644
--- a/tools/testing/selftests/bpf/progs/test_verif_scale2.c
+++ b/tools/testing/selftests/bpf/progs/test_verif_scale2.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #define ATTR __always_inline
 #include "test_jhash.h"
 
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale3.c b/tools/testing/selftests/bpf/progs/test_verif_scale3.c
index 1848da04ea41..9beb5bf80373 100644
--- a/tools/testing/selftests/bpf/progs/test_verif_scale3.c
+++ b/tools/testing/selftests/bpf/progs/test_verif_scale3.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #define ATTR __attribute__((noinline))
 #include "test_jhash.h"
 
diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c
index 0941c655b07b..31f9bce37491 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp.c
@@ -16,8 +16,8 @@
 #include <linux/tcp.h>
 #include <linux/pkt_cls.h>
 #include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 #include "test_iptunnel_common.h"
 
 int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
new file mode 100644
index 000000000000..cb8a04ab7a78
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_trace_helpers.h"
+
+struct net_device {
+	/* Structure does not need to contain all entries,
+	 * as "preserve_access_index" will use BTF to fix this...
+	 */
+	int ifindex;
+} __attribute__((preserve_access_index));
+
+struct xdp_rxq_info {
+	/* Structure does not need to contain all entries,
+	 * as "preserve_access_index" will use BTF to fix this...
+	 */
+	struct net_device *dev;
+	__u32 queue_index;
+} __attribute__((preserve_access_index));
+
+struct xdp_buff {
+	void *data;
+	void *data_end;
+	void *data_meta;
+	void *data_hard_start;
+	unsigned long handle;
+	struct xdp_rxq_info *rxq;
+} __attribute__((preserve_access_index));
+
+__u64 test_result_fentry = 0;
+SEC("fentry/_xdp_tx_iptunnel")
+int BPF_PROG(trace_on_entry, struct xdp_buff *xdp)
+{
+	test_result_fentry = xdp->rxq->dev->ifindex;
+	return 0;
+}
+
+__u64 test_result_fexit = 0;
+SEC("fexit/_xdp_tx_iptunnel")
+int BPF_PROG(trace_on_exit, struct xdp_buff *xdp, int ret)
+{
+	test_result_fexit = ret;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
index 97175f73c3fe..fcabcda30ba3 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
@@ -12,8 +12,8 @@
 #include <linux/tcp.h>
 #include <linux/pkt_cls.h>
 #include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 #include "test_iptunnel_common.h"
 
 int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
index 8d0182650653..a7c4a7d49fe6 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
@@ -2,7 +2,7 @@
 #include <linux/if_ether.h>
 #include <linux/pkt_cls.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #define __round_mask(x, y) ((__typeof__(x))((y) - 1))
 #define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1)
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
index e88d7b9d65ab..8beecec166d9 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
@@ -13,8 +13,8 @@
 #include <linux/icmpv6.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 static __u32 rol32(__u32 word, unsigned int shift)
 {
@@ -86,7 +86,7 @@ u32 jhash(const void *key, u32 length, u32 initval)
 	return c;
 }
 
-static __attribute__ ((noinline))
+__attribute__ ((noinline))
 u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
 {
 	a += initval;
@@ -96,7 +96,7 @@ u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
 	return c;
 }
 
-static __attribute__ ((noinline))
+__attribute__ ((noinline))
 u32 jhash_2words(u32 a, u32 b, u32 initval)
 {
 	return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c
index ef9e704be140..a5337cd9400b 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c
@@ -10,7 +10,7 @@
  * General Public License for more details.
  */
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
index 365a7d2d9f5c..134768f6b788 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
@@ -22,8 +22,8 @@
 #include <linux/in.h>
 #include <linux/pkt_cls.h>
 
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 /* linux/if_vlan.h have not exposed this as UAPI, thus mirror some here
  *
diff --git a/tools/testing/selftests/bpf/progs/xdp_dummy.c b/tools/testing/selftests/bpf/progs/xdp_dummy.c
index 43b0ef1001ed..ea25e8881992 100644
--- a/tools/testing/selftests/bpf/progs/xdp_dummy.c
+++ b/tools/testing/selftests/bpf/progs/xdp_dummy.c
@@ -2,7 +2,7 @@
 
 #define KBUILD_MODNAME "xdp_dummy"
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 SEC("xdp_dummy")
 int xdp_dummy_prog(struct xdp_md *ctx)
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
index 1c5f298d7196..d037262c8937 100644
--- a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_DEVMAP);
diff --git a/tools/testing/selftests/bpf/progs/xdp_tx.c b/tools/testing/selftests/bpf/progs/xdp_tx.c
index 57912e7c94b0..94e6c2b281cb 100644
--- a/tools/testing/selftests/bpf/progs/xdp_tx.c
+++ b/tools/testing/selftests/bpf/progs/xdp_tx.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 SEC("tx")
 int xdp_tx(struct xdp_md *xdp)
diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c
index 112a2857f4e2..6b9ca40bd1f4 100644
--- a/tools/testing/selftests/bpf/progs/xdping_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdping_kern.c
@@ -12,8 +12,8 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #include "xdping.h"
 
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 3d617e806054..93040ca83e60 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -4148,10 +4148,6 @@ static int do_test_file(unsigned int test_num)
 	if (CHECK(IS_ERR(obj), "obj: %ld", PTR_ERR(obj)))
 		return PTR_ERR(obj);
 
-	err = bpf_object__btf_fd(obj);
-	if (CHECK(err == -1, "bpf_object__btf_fd: -1"))
-		goto done;
-
 	prog = bpf_program__next(NULL, obj);
 	if (CHECK(!prog, "Cannot find bpf_prog")) {
 		err = -1;
diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp
index 6fe23a10d48a..a8d2e9a87fbf 100644
--- a/tools/testing/selftests/bpf/test_cpp.cpp
+++ b/tools/testing/selftests/bpf/test_cpp.cpp
@@ -1,8 +1,8 @@
 /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 #include <iostream>
-#include "libbpf.h"
-#include "bpf.h"
-#include "btf.h"
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
 #include "test_core_extern.skel.h"
 
 /* do nothing, just make sure we can link successfully */
diff --git a/tools/testing/selftests/bpf/test_hashmap.c b/tools/testing/selftests/bpf/test_hashmap.c
index b64094c981e3..c490e012c23f 100644
--- a/tools/testing/selftests/bpf/test_hashmap.c
+++ b/tools/testing/selftests/bpf/test_hashmap.c
@@ -8,7 +8,7 @@
 #include <stdio.h>
 #include <errno.h>
 #include <linux/err.h>
-#include "hashmap.h"
+#include "bpf/hashmap.h"
 
 #define CHECK(condition, format...) ({					\
 	int __ret = !!(condition);					\
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 7fa7d08a8104..bab1e6f1d8f1 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -8,7 +8,7 @@
 #include <string.h>
 
 /* defined in test_progs.h */
-struct test_env env;
+struct test_env env = {};
 
 struct prog_test_def {
 	const char *test_name;
@@ -29,10 +29,19 @@ struct prog_test_def {
 
 static bool should_run(struct test_selector *sel, int num, const char *name)
 {
-	if (sel->name && sel->name[0] && !strstr(name, sel->name))
-		return false;
+	int i;
+
+	for (i = 0; i < sel->blacklist.cnt; i++) {
+		if (strstr(name, sel->blacklist.strs[i]))
+			return false;
+	}
 
-	if (!sel->num_set)
+	for (i = 0; i < sel->whitelist.cnt; i++) {
+		if (strstr(name, sel->whitelist.strs[i]))
+			return true;
+	}
+
+	if (!sel->whitelist.cnt && !sel->num_set)
 		return true;
 
 	return num < sel->num_set_len && sel->num_set[num];
@@ -334,6 +343,7 @@ const char argp_program_doc[] = "BPF selftests test runner";
 enum ARG_KEYS {
 	ARG_TEST_NUM = 'n',
 	ARG_TEST_NAME = 't',
+	ARG_TEST_NAME_BLACKLIST = 'b',
 	ARG_VERIFIER_STATS = 's',
 	ARG_VERBOSE = 'v',
 };
@@ -341,8 +351,10 @@ enum ARG_KEYS {
 static const struct argp_option opts[] = {
 	{ "num", ARG_TEST_NUM, "NUM", 0,
 	  "Run test number NUM only " },
-	{ "name", ARG_TEST_NAME, "NAME", 0,
-	  "Run tests with names containing NAME" },
+	{ "name", ARG_TEST_NAME, "NAMES", 0,
+	  "Run tests with names containing any string from NAMES list" },
+	{ "name-blacklist", ARG_TEST_NAME_BLACKLIST, "NAMES", 0,
+	  "Don't run tests with names containing any string from NAMES list" },
 	{ "verifier-stats", ARG_VERIFIER_STATS, NULL, 0,
 	  "Output verifier statistics", },
 	{ "verbose", ARG_VERBOSE, "LEVEL", OPTION_ARG_OPTIONAL,
@@ -359,6 +371,41 @@ static int libbpf_print_fn(enum libbpf_print_level level,
 	return 0;
 }
 
+static int parse_str_list(const char *s, struct str_set *set)
+{
+	char *input, *state = NULL, *next, **tmp, **strs = NULL;
+	int cnt = 0;
+
+	input = strdup(s);
+	if (!input)
+		return -ENOMEM;
+
+	set->cnt = 0;
+	set->strs = NULL;
+
+	while ((next = strtok_r(state ? NULL : input, ",", &state))) {
+		tmp = realloc(strs, sizeof(*strs) * (cnt + 1));
+		if (!tmp)
+			goto err;
+		strs = tmp;
+
+		strs[cnt] = strdup(next);
+		if (!strs[cnt])
+			goto err;
+
+		cnt++;
+	}
+
+	set->cnt = cnt;
+	set->strs = (const char **)strs;
+	free(input);
+	return 0;
+err:
+	free(strs);
+	free(input);
+	return -ENOMEM;
+}
+
 int parse_num_list(const char *s, struct test_selector *sel)
 {
 	int i, set_len = 0, num, start = 0, end = -1;
@@ -449,12 +496,24 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 
 		if (subtest_str) {
 			*subtest_str = '\0';
-			env->subtest_selector.name = strdup(subtest_str + 1);
-			if (!env->subtest_selector.name)
+			if (parse_str_list(subtest_str + 1,
+					   &env->subtest_selector.whitelist))
+				return -ENOMEM;
+		}
+		if (parse_str_list(arg, &env->test_selector.whitelist))
+			return -ENOMEM;
+		break;
+	}
+	case ARG_TEST_NAME_BLACKLIST: {
+		char *subtest_str = strchr(arg, '/');
+
+		if (subtest_str) {
+			*subtest_str = '\0';
+			if (parse_str_list(subtest_str + 1,
+					   &env->subtest_selector.blacklist))
 				return -ENOMEM;
 		}
-		env->test_selector.name = strdup(arg);
-		if (!env->test_selector.name)
+		if (parse_str_list(arg, &env->test_selector.blacklist))
 			return -ENOMEM;
 		break;
 	}
@@ -617,7 +676,11 @@ int main(int argc, char **argv)
 	printf("Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n",
 	       env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt);
 
+	free(env.test_selector.blacklist.strs);
+	free(env.test_selector.whitelist.strs);
 	free(env.test_selector.num_set);
+	free(env.subtest_selector.blacklist.strs);
+	free(env.subtest_selector.whitelist.strs);
 	free(env.subtest_selector.num_set);
 
 	return env.fail_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index de1fdaa4e7b4..bcfa9ef23fda 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -35,7 +35,7 @@ typedef __u16 __sum16;
 
 #include "test_iptunnel_common.h"
 #include "bpf_util.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
 #include "trace_helpers.h"
 #include "flow_dissector_load.h"
 
@@ -46,8 +46,14 @@ enum verbosity {
 	VERBOSE_SUPER,
 };
 
+struct str_set {
+	const char **strs;
+	int cnt;
+};
+
 struct test_selector {
-	const char *name;
+	struct str_set whitelist;
+	struct str_set blacklist;
 	bool *num_set;
 	int num_set_len;
 };
diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c
index 0e6652733462..52bf14955797 100644
--- a/tools/testing/selftests/bpf/test_sock.c
+++ b/tools/testing/selftests/bpf/test_sock.c
@@ -13,7 +13,7 @@
 #include <bpf/bpf.h>
 
 #include "cgroup_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
 #include "bpf_rlimit.h"
 #include "bpf_util.h"
 
diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/test_sockmap_kern.h
index d008b41b7d8d..9b4d3a68a91a 100644
--- a/tools/testing/selftests/bpf/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/test_sockmap_kern.h
@@ -12,8 +12,8 @@
 #include <linux/tcp.h>
 #include <linux/pkt_cls.h>
 #include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 /* Sockmap sample program connects a client and a backend together
  * using cgroups.
diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c
index 40bd93a6e7ae..d196e2a4a6e0 100644
--- a/tools/testing/selftests/bpf/test_sysctl.c
+++ b/tools/testing/selftests/bpf/test_sysctl.c
@@ -13,7 +13,7 @@
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
 
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
 #include "bpf_rlimit.h"
 #include "bpf_util.h"
 #include "cgroup_helpers.h"
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index aa4dcfe18050..0383c9b8adc1 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -2,7 +2,7 @@
 #ifndef __TRACE_HELPER_H
 #define __TRACE_HELPER_H
 
-#include <libbpf.h>
+#include <bpf/libbpf.h>
 
 struct ksym {
 	long addr;