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

Daniel Borkmann says:

====================
pull-request: bpf-next 2020-03-13

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

We've added 86 non-merge commits during the last 12 day(s) which contain
a total of 107 files changed, 5771 insertions(+), 1700 deletions(-).

The main changes are:

1) Add modify_return attach type which allows to attach to a function via
   BPF trampoline and is run after the fentry and before the fexit programs
   and can pass a return code to the original caller, from KP Singh.

2) Generalize BPF's kallsyms handling and add BPF trampoline and dispatcher
   objects to be visible in /proc/kallsyms so they can be annotated in
   stack traces, from Jiri Olsa.

3) Extend BPF sockmap to allow for UDP next to existing TCP support in order
   in order to enable this for BPF based socket dispatch, from Lorenz Bauer.

4) Introduce a new bpftool 'prog profile' command which attaches to existing
   BPF programs via fentry and fexit hooks and reads out hardware counters
   during that period, from Song Liu. Example usage:

   bpftool prog profile id 337 duration 3 cycles instructions llc_misses

        4228 run_cnt
     3403698 cycles                                              (84.08%)
     3525294 instructions   #  1.04 insn per cycle               (84.05%)
          13 llc_misses     #  3.69 LLC misses per million isns  (83.50%)

5) Batch of improvements to libbpf, bpftool and BPF selftests. Also addition
   of a new bpf_link abstraction to keep in particular BPF tracing programs
   attached even when the applicaion owning them exits, from Andrii Nakryiko.

6) New bpf_get_current_pid_tgid() helper for tracing to perform PID filtering
   and which returns the PID as seen by the init namespace, from Carlos Neira.

7) Refactor of RISC-V JIT code to move out common pieces and addition of a
   new RV32G BPF JIT compiler, from Luke Nelson.

8) Add gso_size context member to __sk_buff in order to be able to know whether
   a given skb is GSO or not, from Willem de Bruijn.

9) Add a new bpf_xdp_output() helper which reuses XDP's existing perf RB output
   implementation but can be called from tracepoint programs, from Eelco Chaudron.
====================

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

65 files changed, 2380 insertions, 472 deletions

diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore
index b13926432b84..8d6e8901ed2b 100644
--- a/tools/bpf/bpftool/.gitignore
+++ b/tools/bpf/bpftool/.gitignore
@@ -1,7 +1,9 @@
 *.d
+/_bpftool
 /bpftool
 bpftool*.8
 bpf-helpers.*
 FEATURE-DUMP.bpftool
 feature
 libbpf
+profiler.skel.h
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 46862e85fed2..9f19404f470e 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -30,6 +30,7 @@ PROG COMMANDS
 |	**bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*]
 |	**bpftool** **prog tracelog**
 |	**bpftool** **prog run** *PROG* **data_in** *FILE* [**data_out** *FILE* [**data_size_out** *L*]] [**ctx_in** *FILE* [**ctx_out** *FILE* [**ctx_size_out** *M*]]] [**repeat** *N*]
+|	**bpftool** **prog profile** *PROG* [**duration** *DURATION*] *METRICs*
 |	**bpftool** **prog help**
 |
 |	*MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
@@ -48,6 +49,9 @@ PROG COMMANDS
 |       *ATTACH_TYPE* := {
 |		**msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector**
 |	}
+|	*METRIC* := {
+|		**cycles** | **instructions** | **l1d_loads** | **llc_misses**
+|	}
 
 
 DESCRIPTION
@@ -189,6 +193,12 @@ DESCRIPTION
 		  not all of them can take the **ctx_in**/**ctx_out**
 		  arguments. bpftool does not perform checks on program types.
 
+	**bpftool prog profile** *PROG* [**duration** *DURATION*] *METRICs*
+		  Profile *METRICs* for bpf program *PROG* for *DURATION*
+		  seconds or until user hits Ctrl-C. *DURATION* is optional.
+		  If *DURATION* is not specified, the profiling will run up to
+		  UINT_MAX seconds.
+
 	**bpftool prog help**
 		  Print short help message.
 
@@ -311,6 +321,15 @@ EXAMPLES
 
 **# rm /sys/fs/bpf/xdp1**
 
+|
+| **# bpftool prog profile id 337 duration 10 cycles instructions llc_misses**
+
+::
+         51397 run_cnt
+      40176203 cycles                                                 (83.05%)
+      42518139 instructions    #   1.06 insns per cycle               (83.39%)
+           123 llc_misses      #   2.89 LLC misses per million insns  (83.15%)
+
 SEE ALSO
 ========
 	**bpf**\ (2),
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index c4e810335810..f584d1fdfc64 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -59,10 +59,12 @@ LIBS = $(LIBBPF) -lelf -lz
 
 INSTALL ?= install
 RM ?= rm -f
+CLANG ?= clang
 
 FEATURE_USER = .bpftool
-FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib
-FEATURE_DISPLAY = libbfd disassembler-four-args zlib
+FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib \
+	clang-bpf-global-var
+FEATURE_DISPLAY = libbfd disassembler-four-args zlib clang-bpf-global-var
 
 check_feat := 1
 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall
@@ -110,14 +112,39 @@ SRCS += $(BFD_SRCS)
 endif
 
 OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
+_OBJS = $(filter-out $(OUTPUT)prog.o,$(OBJS)) $(OUTPUT)_prog.o
+
+ifeq ($(feature-clang-bpf-global-var),1)
+	__OBJS = $(OBJS)
+else
+	__OBJS = $(_OBJS)
+endif
+
+$(OUTPUT)_prog.o: prog.c
+	$(QUIET_CC)$(COMPILE.c) -MMD -DBPFTOOL_WITHOUT_SKELETONS -o $@ $<
+
+$(OUTPUT)_bpftool: $(_OBJS) $(LIBBPF)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(_OBJS) $(LIBS)
+
+skeleton/profiler.bpf.o: skeleton/profiler.bpf.c $(LIBBPF)
+	$(QUIET_CLANG)$(CLANG) \
+		-I$(srctree)/tools/include/uapi/ \
+		-I$(LIBBPF_PATH) -I$(srctree)/tools/lib \
+		-g -O2 -target bpf -c $< -o $@
+
+profiler.skel.h: $(OUTPUT)_bpftool skeleton/profiler.bpf.o
+	$(QUIET_GEN)$(OUTPUT)./_bpftool gen skeleton skeleton/profiler.bpf.o > $@
+
+$(OUTPUT)prog.o: prog.c profiler.skel.h
+	$(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
 
 $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
 	$(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
 
 $(OUTPUT)feature.o: | zdep
 
-$(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
-	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJS) $(LIBS)
+$(OUTPUT)bpftool: $(__OBJS) $(LIBBPF)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(__OBJS) $(LIBS)
 
 $(OUTPUT)%.o: %.c
 	$(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
@@ -125,6 +152,7 @@ $(OUTPUT)%.o: %.c
 clean: $(LIBBPF)-clean
 	$(call QUIET_CLEAN, bpftool)
 	$(Q)$(RM) -- $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d
+	$(Q)$(RM) -- $(OUTPUT)_bpftool profiler.skel.h skeleton/profiler.bpf.o
 	$(Q)$(RM) -r -- $(OUTPUT)libbpf/
 	$(call QUIET_CLEAN, core-gen)
 	$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpftool
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index f2838a658339..9b0534f558f1 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -337,6 +337,7 @@ _bpftool()
 
             local PROG_TYPE='id pinned tag name'
             local MAP_TYPE='id pinned name'
+            local METRIC_TYPE='cycles instructions l1d_loads llc_misses'
             case $command in
                 show|list)
                     [[ $prev != "$command" ]] && return 0
@@ -388,7 +389,7 @@ _bpftool()
                                     _bpftool_get_prog_ids
                                     ;;
                                 name)
-                                    _bpftool_get_map_names
+                                    _bpftool_get_prog_names
                                     ;;
                                 pinned)
                                     _filedir
@@ -498,9 +499,51 @@ _bpftool()
                 tracelog)
                     return 0
                     ;;
+                profile)
+                    case $cword in
+                        3)
+                            COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                        4)
+                            case $prev in
+                                id)
+                                    _bpftool_get_prog_ids
+                                    ;;
+                                name)
+                                    _bpftool_get_prog_names
+                                    ;;
+                                pinned)
+                                    _filedir
+                                    ;;
+                            esac
+                            return 0
+                            ;;
+                        5)
+                            COMPREPLY=( $( compgen -W "$METRIC_TYPE duration" -- "$cur" ) )
+                            return 0
+                            ;;
+                        6)
+                            case $prev in
+                                duration)
+                                    return 0
+                                    ;;
+                                *)
+                                    COMPREPLY=( $( compgen -W "$METRIC_TYPE" -- "$cur" ) )
+                                    return 0
+                                    ;;
+                            esac
+                            return 0
+                            ;;
+                        *)
+                            COMPREPLY=( $( compgen -W "$METRIC_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                    esac
+                    ;;
                 run)
-                    if [[ ${#words[@]} -lt 5 ]]; then
-                        _filedir
+                    if [[ ${#words[@]} -eq 4 ]]; then
+                        COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
                         return 0
                     fi
                     case $prev in
@@ -508,6 +551,10 @@ _bpftool()
                             _bpftool_get_prog_ids
                             return 0
                             ;;
+                        name)
+                            _bpftool_get_prog_names
+                            return 0
+                            ;;
                         data_in|data_out|ctx_in|ctx_out)
                             _filedir
                             return 0
@@ -525,7 +572,7 @@ _bpftool()
                 *)
                     [[ $prev == $object ]] && \
                         COMPREPLY=( $( compgen -W 'dump help pin attach detach \
-                            load loadall show list tracelog run' -- "$cur" ) )
+                            load loadall show list tracelog run profile' -- "$cur" ) )
                     ;;
             esac
             ;;
@@ -713,11 +760,17 @@ _bpftool()
                     esac
                     ;;
                 pin)
-                    if [[ $prev == "$command" ]]; then
-                        COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) )
-                    else
-                        _filedir
-                    fi
+                    case $prev in
+                        $command)
+                            COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+                            ;;
+                        id)
+                            _bpftool_get_map_ids
+                            ;;
+                        name)
+                            _bpftool_get_map_names
+                            ;;
+                    esac
                     return 0
                     ;;
                 event_pipe)
@@ -844,7 +897,7 @@ _bpftool()
             case $command in
                 skeleton)
                     _filedir
-		    ;;
+                    ;;
                 *)
                     [[ $prev == $object ]] && \
                         COMPREPLY=( $( compgen -W 'skeleton help' -- "$cur" ) )
@@ -944,6 +997,9 @@ _bpftool()
                                 id)
                                     _bpftool_get_prog_ids
                                     ;;
+                                name)
+                                    _bpftool_get_prog_names
+                                    ;;
                                 pinned)
                                     _filedir
                                     ;;
diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index b3745ed711ba..bcaf55b59498 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -389,6 +389,9 @@ static int dump_btf_c(const struct btf *btf,
 	if (IS_ERR(d))
 		return PTR_ERR(d);
 
+	printf("#ifndef __VMLINUX_H__\n");
+	printf("#define __VMLINUX_H__\n");
+	printf("\n");
 	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");
@@ -412,6 +415,8 @@ 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");
+	printf("\n");
+	printf("#endif /* __VMLINUX_H__ */\n");
 
 done:
 	btf_dump__free(d);
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index b75b8ec5469c..f2223dbdfb0a 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -211,39 +211,14 @@ int do_pin_fd(int fd, const char *name)
 	return err;
 }
 
-int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
+int do_pin_any(int argc, char **argv, int (*get_fd)(int *, char ***))
 {
-	unsigned int id;
-	char *endptr;
 	int err;
 	int fd;
 
-	if (argc < 3) {
-		p_err("too few arguments, id ID and FILE path is required");
-		return -1;
-	} else if (argc > 3) {
-		p_err("too many arguments");
-		return -1;
-	}
-
-	if (!is_prefix(*argv, "id")) {
-		p_err("expected 'id' got %s", *argv);
-		return -1;
-	}
-	NEXT_ARG();
-
-	id = strtoul(*argv, &endptr, 0);
-	if (*endptr) {
-		p_err("can't parse %s as ID", *argv);
-		return -1;
-	}
-	NEXT_ARG();
-
-	fd = get_fd_by_id(id);
-	if (fd < 0) {
-		p_err("can't open object by id (%u): %s", id, strerror(errno));
-		return -1;
-	}
+	fd = get_fd(&argc, &argv);
+	if (fd < 0)
+		return fd;
 
 	err = do_pin_fd(fd, *argv);
 
@@ -597,3 +572,10 @@ int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what)
 
 	return 0;
 }
+
+int __printf(2, 0)
+print_all_levels(__maybe_unused enum libbpf_print_level level,
+		 const char *format, va_list args)
+{
+	return vfprintf(stderr, format, args);
+}
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 6d41bbfc6459..06449e846e4b 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -79,13 +79,6 @@ static int do_version(int argc, char **argv)
 	return 0;
 }
 
-static int __printf(2, 0)
-print_all_levels(__maybe_unused enum libbpf_print_level level,
-		 const char *format, va_list args)
-{
-	return vfprintf(stderr, format, args);
-}
-
 int cmd_select(const struct cmd *cmds, int argc, char **argv,
 	       int (*help)(int argc, char **argv))
 {
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 724ef9d941d3..5f6dccd43622 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -14,6 +14,8 @@
 #include <linux/hashtable.h>
 #include <tools/libc_compat.h>
 
+#include <bpf/libbpf.h>
+
 #include "json_writer.h"
 
 #define ptr_to_u64(ptr)	((__u64)(unsigned long)(ptr))
@@ -146,7 +148,7 @@ char *get_fdinfo(int fd, const char *key);
 int open_obj_pinned(char *path, bool quiet);
 int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type);
 int mount_bpffs_for_pin(const char *name);
-int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32));
+int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***));
 int do_pin_fd(int fd, const char *name);
 
 int do_prog(int argc, char **arg);
@@ -229,4 +231,7 @@ struct tcmsg;
 int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb);
 int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind,
 		   const char *devname, int ifindex);
+
+int print_all_levels(__maybe_unused enum libbpf_print_level level,
+		     const char *format, va_list args);
 #endif
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index e6c85680b34d..693a632f6813 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -1384,7 +1384,7 @@ static int do_pin(int argc, char **argv)
 {
 	int err;
 
-	err = do_pin_any(argc, argv, bpf_map_get_fd_by_id);
+	err = do_pin_any(argc, argv, map_parse_fd);
 	if (!err && json_output)
 		jsonw_null(json_wtr);
 	return err;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 1996e67a2f00..f6a5974a7b0a 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -4,6 +4,7 @@
 #define _GNU_SOURCE
 #include <errno.h>
 #include <fcntl.h>
+#include <signal.h>
 #include <stdarg.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -11,10 +12,13 @@
 #include <time.h>
 #include <unistd.h>
 #include <net/if.h>
+#include <sys/ioctl.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <sys/syscall.h>
 
 #include <linux/err.h>
+#include <linux/perf_event.h>
 #include <linux/sizes.h>
 
 #include <bpf/bpf.h>
@@ -809,7 +813,7 @@ static int do_pin(int argc, char **argv)
 {
 	int err;
 
-	err = do_pin_any(argc, argv, bpf_prog_get_fd_by_id);
+	err = do_pin_any(argc, argv, prog_parse_fd);
 	if (!err && json_output)
 		jsonw_null(json_wtr);
 	return err;
@@ -1243,6 +1247,25 @@ free_data_in:
 	return err;
 }
 
+static int
+get_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+		      enum bpf_attach_type *expected_attach_type)
+{
+	libbpf_print_fn_t print_backup;
+	int ret;
+
+	ret = libbpf_prog_type_by_name(name, prog_type, expected_attach_type);
+	if (!ret)
+		return ret;
+
+	/* libbpf_prog_type_by_name() failed, let's re-run with debug level */
+	print_backup = libbpf_set_print(print_all_levels);
+	ret = libbpf_prog_type_by_name(name, prog_type, expected_attach_type);
+	libbpf_set_print(print_backup);
+
+	return ret;
+}
+
 static int load_with_options(int argc, char **argv, bool first_prog_only)
 {
 	enum bpf_prog_type common_prog_type = BPF_PROG_TYPE_UNSPEC;
@@ -1292,8 +1315,8 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 			strcat(type, *argv);
 			strcat(type, "/");
 
-			err = libbpf_prog_type_by_name(type, &common_prog_type,
-						       &expected_attach_type);
+			err = get_prog_type_by_name(type, &common_prog_type,
+						    &expected_attach_type);
 			free(type);
 			if (err < 0)
 				goto err_free_reuse_maps;
@@ -1392,8 +1415,8 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 		if (prog_type == BPF_PROG_TYPE_UNSPEC) {
 			const char *sec_name = bpf_program__title(pos, false);
 
-			err = libbpf_prog_type_by_name(sec_name, &prog_type,
-						       &expected_attach_type);
+			err = get_prog_type_by_name(sec_name, &prog_type,
+						    &expected_attach_type);
 			if (err < 0)
 				goto err_close_obj;
 		}
@@ -1537,6 +1560,422 @@ static int do_loadall(int argc, char **argv)
 	return load_with_options(argc, argv, false);
 }
 
+#ifdef BPFTOOL_WITHOUT_SKELETONS
+
+static int do_profile(int argc, char **argv)
+{
+	p_err("bpftool prog profile command is not supported. Please build bpftool with clang >= 10.0.0");
+	return 0;
+}
+
+#else /* BPFTOOL_WITHOUT_SKELETONS */
+
+#include "profiler.skel.h"
+
+struct profile_metric {
+	const char *name;
+	struct bpf_perf_event_value val;
+	struct perf_event_attr attr;
+	bool selected;
+
+	/* calculate ratios like instructions per cycle */
+	const int ratio_metric; /* 0 for N/A, 1 for index 0 (cycles) */
+	const char *ratio_desc;
+	const float ratio_mul;
+} metrics[] = {
+	{
+		.name = "cycles",
+		.attr = {
+			.type = PERF_TYPE_HARDWARE,
+			.config = PERF_COUNT_HW_CPU_CYCLES,
+			.exclude_user = 1,
+		},
+	},
+	{
+		.name = "instructions",
+		.attr = {
+			.type = PERF_TYPE_HARDWARE,
+			.config = PERF_COUNT_HW_INSTRUCTIONS,
+			.exclude_user = 1,
+		},
+		.ratio_metric = 1,
+		.ratio_desc = "insns per cycle",
+		.ratio_mul = 1.0,
+	},
+	{
+		.name = "l1d_loads",
+		.attr = {
+			.type = PERF_TYPE_HW_CACHE,
+			.config =
+				PERF_COUNT_HW_CACHE_L1D |
+				(PERF_COUNT_HW_CACHE_OP_READ << 8) |
+				(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16),
+			.exclude_user = 1,
+		},
+	},
+	{
+		.name = "llc_misses",
+		.attr = {
+			.type = PERF_TYPE_HW_CACHE,
+			.config =
+				PERF_COUNT_HW_CACHE_LL |
+				(PERF_COUNT_HW_CACHE_OP_READ << 8) |
+				(PERF_COUNT_HW_CACHE_RESULT_MISS << 16),
+			.exclude_user = 1
+		},
+		.ratio_metric = 2,
+		.ratio_desc = "LLC misses per million insns",
+		.ratio_mul = 1e6,
+	},
+};
+
+static __u64 profile_total_count;
+
+#define MAX_NUM_PROFILE_METRICS 4
+
+static int profile_parse_metrics(int argc, char **argv)
+{
+	unsigned int metric_cnt;
+	int selected_cnt = 0;
+	unsigned int i;
+
+	metric_cnt = sizeof(metrics) / sizeof(struct profile_metric);
+
+	while (argc > 0) {
+		for (i = 0; i < metric_cnt; i++) {
+			if (is_prefix(argv[0], metrics[i].name)) {
+				if (!metrics[i].selected)
+					selected_cnt++;
+				metrics[i].selected = true;
+				break;
+			}
+		}
+		if (i == metric_cnt) {
+			p_err("unknown metric %s", argv[0]);
+			return -1;
+		}
+		NEXT_ARG();
+	}
+	if (selected_cnt > MAX_NUM_PROFILE_METRICS) {
+		p_err("too many (%d) metrics, please specify no more than %d metrics at at time",
+		      selected_cnt, MAX_NUM_PROFILE_METRICS);
+		return -1;
+	}
+	return selected_cnt;
+}
+
+static void profile_read_values(struct profiler_bpf *obj)
+{
+	__u32 m, cpu, num_cpu = obj->rodata->num_cpu;
+	int reading_map_fd, count_map_fd;
+	__u64 counts[num_cpu];
+	__u32 key = 0;
+	int err;
+
+	reading_map_fd = bpf_map__fd(obj->maps.accum_readings);
+	count_map_fd = bpf_map__fd(obj->maps.counts);
+	if (reading_map_fd < 0 || count_map_fd < 0) {
+		p_err("failed to get fd for map");
+		return;
+	}
+
+	err = bpf_map_lookup_elem(count_map_fd, &key, counts);
+	if (err) {
+		p_err("failed to read count_map: %s", strerror(errno));
+		return;
+	}
+
+	profile_total_count = 0;
+	for (cpu = 0; cpu < num_cpu; cpu++)
+		profile_total_count += counts[cpu];
+
+	for (m = 0; m < ARRAY_SIZE(metrics); m++) {
+		struct bpf_perf_event_value values[num_cpu];
+
+		if (!metrics[m].selected)
+			continue;
+
+		err = bpf_map_lookup_elem(reading_map_fd, &key, values);
+		if (err) {
+			p_err("failed to read reading_map: %s",
+			      strerror(errno));
+			return;
+		}
+		for (cpu = 0; cpu < num_cpu; cpu++) {
+			metrics[m].val.counter += values[cpu].counter;
+			metrics[m].val.enabled += values[cpu].enabled;
+			metrics[m].val.running += values[cpu].running;
+		}
+		key++;
+	}
+}
+
+static void profile_print_readings_json(void)
+{
+	__u32 m;
+
+	jsonw_start_array(json_wtr);
+	for (m = 0; m < ARRAY_SIZE(metrics); m++) {
+		if (!metrics[m].selected)
+			continue;
+		jsonw_start_object(json_wtr);
+		jsonw_string_field(json_wtr, "metric", metrics[m].name);
+		jsonw_lluint_field(json_wtr, "run_cnt", profile_total_count);
+		jsonw_lluint_field(json_wtr, "value", metrics[m].val.counter);
+		jsonw_lluint_field(json_wtr, "enabled", metrics[m].val.enabled);
+		jsonw_lluint_field(json_wtr, "running", metrics[m].val.running);
+
+		jsonw_end_object(json_wtr);
+	}
+	jsonw_end_array(json_wtr);
+}
+
+static void profile_print_readings_plain(void)
+{
+	__u32 m;
+
+	printf("\n%18llu %-20s\n", profile_total_count, "run_cnt");
+	for (m = 0; m < ARRAY_SIZE(metrics); m++) {
+		struct bpf_perf_event_value *val = &metrics[m].val;
+		int r;
+
+		if (!metrics[m].selected)
+			continue;
+		printf("%18llu %-20s", val->counter, metrics[m].name);
+
+		r = metrics[m].ratio_metric - 1;
+		if (r >= 0 && metrics[r].selected &&
+		    metrics[r].val.counter > 0) {
+			printf("# %8.2f %-30s",
+			       val->counter * metrics[m].ratio_mul /
+			       metrics[r].val.counter,
+			       metrics[m].ratio_desc);
+		} else {
+			printf("%-41s", "");
+		}
+
+		if (val->enabled > val->running)
+			printf("(%4.2f%%)",
+			       val->running * 100.0 / val->enabled);
+		printf("\n");
+	}
+}
+
+static void profile_print_readings(void)
+{
+	if (json_output)
+		profile_print_readings_json();
+	else
+		profile_print_readings_plain();
+}
+
+static char *profile_target_name(int tgt_fd)
+{
+	struct bpf_prog_info_linear *info_linear;
+	struct bpf_func_info *func_info;
+	const struct btf_type *t;
+	char *name = NULL;
+	struct btf *btf;
+
+	info_linear = bpf_program__get_prog_info_linear(
+		tgt_fd, 1UL << BPF_PROG_INFO_FUNC_INFO);
+	if (IS_ERR_OR_NULL(info_linear)) {
+		p_err("failed to get info_linear for prog FD %d", tgt_fd);
+		return NULL;
+	}
+
+	if (info_linear->info.btf_id == 0 ||
+	    btf__get_from_id(info_linear->info.btf_id, &btf)) {
+		p_err("prog FD %d doesn't have valid btf", tgt_fd);
+		goto out;
+	}
+
+	func_info = (struct bpf_func_info *)(info_linear->info.func_info);
+	t = btf__type_by_id(btf, func_info[0].type_id);
+	if (!t) {
+		p_err("btf %d doesn't have type %d",
+		      info_linear->info.btf_id, func_info[0].type_id);
+		goto out;
+	}
+	name = strdup(btf__name_by_offset(btf, t->name_off));
+out:
+	free(info_linear);
+	return name;
+}
+
+static struct profiler_bpf *profile_obj;
+static int profile_tgt_fd = -1;
+static char *profile_tgt_name;
+static int *profile_perf_events;
+static int profile_perf_event_cnt;
+
+static void profile_close_perf_events(struct profiler_bpf *obj)
+{
+	int i;
+
+	for (i = profile_perf_event_cnt - 1; i >= 0; i--)
+		close(profile_perf_events[i]);
+
+	free(profile_perf_events);
+	profile_perf_event_cnt = 0;
+}
+
+static int profile_open_perf_events(struct profiler_bpf *obj)
+{
+	unsigned int cpu, m;
+	int map_fd, pmu_fd;
+
+	profile_perf_events = calloc(
+		sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric);
+	if (!profile_perf_events) {
+		p_err("failed to allocate memory for perf_event array: %s",
+		      strerror(errno));
+		return -1;
+	}
+	map_fd = bpf_map__fd(obj->maps.events);
+	if (map_fd < 0) {
+		p_err("failed to get fd for events map");
+		return -1;
+	}
+
+	for (m = 0; m < ARRAY_SIZE(metrics); m++) {
+		if (!metrics[m].selected)
+			continue;
+		for (cpu = 0; cpu < obj->rodata->num_cpu; cpu++) {
+			pmu_fd = syscall(__NR_perf_event_open, &metrics[m].attr,
+					 -1/*pid*/, cpu, -1/*group_fd*/, 0);
+			if (pmu_fd < 0 ||
+			    bpf_map_update_elem(map_fd, &profile_perf_event_cnt,
+						&pmu_fd, BPF_ANY) ||
+			    ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) {
+				p_err("failed to create event %s on cpu %d",
+				      metrics[m].name, cpu);
+				return -1;
+			}
+			profile_perf_events[profile_perf_event_cnt++] = pmu_fd;
+		}
+	}
+	return 0;
+}
+
+static void profile_print_and_cleanup(void)
+{
+	profile_close_perf_events(profile_obj);
+	profile_read_values(profile_obj);
+	profile_print_readings();
+	profiler_bpf__destroy(profile_obj);
+
+	close(profile_tgt_fd);
+	free(profile_tgt_name);
+}
+
+static void int_exit(int signo)
+{
+	profile_print_and_cleanup();
+	exit(0);
+}
+
+static int do_profile(int argc, char **argv)
+{
+	int num_metric, num_cpu, err = -1;
+	struct bpf_program *prog;
+	unsigned long duration;
+	char *endptr;
+
+	/* we at least need two args for the prog and one metric */
+	if (!REQ_ARGS(3))
+		return -EINVAL;
+
+	/* parse target fd */
+	profile_tgt_fd = prog_parse_fd(&argc, &argv);
+	if (profile_tgt_fd < 0) {
+		p_err("failed to parse fd");
+		return -1;
+	}
+
+	/* parse profiling optional duration */
+	if (argc > 2 && is_prefix(argv[0], "duration")) {
+		NEXT_ARG();
+		duration = strtoul(*argv, &endptr, 0);
+		if (*endptr)
+			usage();
+		NEXT_ARG();
+	} else {
+		duration = UINT_MAX;
+	}
+
+	num_metric = profile_parse_metrics(argc, argv);
+	if (num_metric <= 0)
+		goto out;
+
+	num_cpu = libbpf_num_possible_cpus();
+	if (num_cpu <= 0) {
+		p_err("failed to identify number of CPUs");
+		goto out;
+	}
+
+	profile_obj = profiler_bpf__open();
+	if (!profile_obj) {
+		p_err("failed to open and/or load BPF object");
+		goto out;
+	}
+
+	profile_obj->rodata->num_cpu = num_cpu;
+	profile_obj->rodata->num_metric = num_metric;
+
+	/* adjust map sizes */
+	bpf_map__resize(profile_obj->maps.events, num_metric * num_cpu);
+	bpf_map__resize(profile_obj->maps.fentry_readings, num_metric);
+	bpf_map__resize(profile_obj->maps.accum_readings, num_metric);
+	bpf_map__resize(profile_obj->maps.counts, 1);
+
+	/* change target name */
+	profile_tgt_name = profile_target_name(profile_tgt_fd);
+	if (!profile_tgt_name)
+		goto out;
+
+	bpf_object__for_each_program(prog, profile_obj->obj) {
+		err = bpf_program__set_attach_target(prog, profile_tgt_fd,
+						     profile_tgt_name);
+		if (err) {
+			p_err("failed to set attach target\n");
+			goto out;
+		}
+	}
+
+	set_max_rlimit();
+	err = profiler_bpf__load(profile_obj);
+	if (err) {
+		p_err("failed to load profile_obj");
+		goto out;
+	}
+
+	err = profile_open_perf_events(profile_obj);
+	if (err)
+		goto out;
+
+	err = profiler_bpf__attach(profile_obj);
+	if (err) {
+		p_err("failed to attach profile_obj");
+		goto out;
+	}
+	signal(SIGINT, int_exit);
+
+	sleep(duration);
+	profile_print_and_cleanup();
+	return 0;
+
+out:
+	profile_close_perf_events(profile_obj);
+	if (profile_obj)
+		profiler_bpf__destroy(profile_obj);
+	close(profile_tgt_fd);
+	free(profile_tgt_name);
+	return err;
+}
+
+#endif /* BPFTOOL_WITHOUT_SKELETONS */
+
 static int do_help(int argc, char **argv)
 {
 	if (json_output) {
@@ -1560,6 +1999,7 @@ static int do_help(int argc, char **argv)
 		"                         [data_out FILE [data_size_out L]] \\\n"
 		"                         [ctx_in FILE [ctx_out FILE [ctx_size_out M]]] \\\n"
 		"                         [repeat N]\n"
+		"       %s %s profile PROG [duration DURATION] METRICs\n"
 		"       %s %s tracelog\n"
 		"       %s %s help\n"
 		"\n"
@@ -1577,12 +2017,13 @@ static int do_help(int argc, char **argv)
 		"                 struct_ops | fentry | fexit | freplace }\n"
 		"       ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n"
 		"                        flow_dissector }\n"
+		"       METRIC := { cycles | instructions | l1d_loads | llc_misses }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
-		bin_name, argv[-2]);
+		bin_name, argv[-2], bin_name, argv[-2]);
 
 	return 0;
 }
@@ -1599,6 +2040,7 @@ static const struct cmd cmds[] = {
 	{ "detach",	do_detach },
 	{ "tracelog",	do_tracelog },
 	{ "run",	do_run },
+	{ "profile",	do_profile },
 	{ 0 }
 };
 
diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c
new file mode 100644
index 000000000000..20034c12f7c5
--- /dev/null
+++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+#include "profiler.h"
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+/* map of perf event fds, num_cpu * num_metric entries */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(int));
+} events SEC(".maps");
+
+/* readings at fentry */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+} fentry_readings SEC(".maps");
+
+/* accumulated readings */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+} accum_readings SEC(".maps");
+
+/* sample counts, one per cpu */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u64));
+} counts SEC(".maps");
+
+const volatile __u32 num_cpu = 1;
+const volatile __u32 num_metric = 1;
+#define MAX_NUM_MATRICS 4
+
+SEC("fentry/XXX")
+int BPF_PROG(fentry_XXX)
+{
+	struct bpf_perf_event_value *ptrs[MAX_NUM_MATRICS];
+	u32 key = bpf_get_smp_processor_id();
+	u32 i;
+
+	/* look up before reading, to reduce error */
+	for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
+		u32 flag = i;
+
+		ptrs[i] = bpf_map_lookup_elem(&fentry_readings, &flag);
+		if (!ptrs[i])
+			return 0;
+	}
+
+	for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
+		struct bpf_perf_event_value reading;
+		int err;
+
+		err = bpf_perf_event_read_value(&events, key, &reading,
+						sizeof(reading));
+		if (err)
+			return 0;
+		*(ptrs[i]) = reading;
+		key += num_cpu;
+	}
+
+	return 0;
+}
+
+static inline void
+fexit_update_maps(u32 id, struct bpf_perf_event_value *after)
+{
+	struct bpf_perf_event_value *before, diff, *accum;
+
+	before = bpf_map_lookup_elem(&fentry_readings, &id);
+	/* only account samples with a valid fentry_reading */
+	if (before && before->counter) {
+		struct bpf_perf_event_value *accum;
+
+		diff.counter = after->counter - before->counter;
+		diff.enabled = after->enabled - before->enabled;
+		diff.running = after->running - before->running;
+
+		accum = bpf_map_lookup_elem(&accum_readings, &id);
+		if (accum) {
+			accum->counter += diff.counter;
+			accum->enabled += diff.enabled;
+			accum->running += diff.running;
+		}
+	}
+}
+
+SEC("fexit/XXX")
+int BPF_PROG(fexit_XXX)
+{
+	struct bpf_perf_event_value readings[MAX_NUM_MATRICS];
+	u32 cpu = bpf_get_smp_processor_id();
+	u32 i, one = 1, zero = 0;
+	int err;
+	u64 *count;
+
+	/* read all events before updating the maps, to reduce error */
+	for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
+		err = bpf_perf_event_read_value(&events, cpu + i * num_cpu,
+						readings + i, sizeof(*readings));
+		if (err)
+			return 0;
+	}
+	count = bpf_map_lookup_elem(&counts, &zero);
+	if (count) {
+		*count += 1;
+		for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++)
+			fexit_update_maps(i, &readings[i]);
+	}
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/bpf/bpftool/skeleton/profiler.h b/tools/bpf/bpftool/skeleton/profiler.h
new file mode 100644
index 000000000000..1f767e9510f7
--- /dev/null
+++ b/tools/bpf/bpftool/skeleton/profiler.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __PROFILER_H
+#define __PROFILER_H
+
+/* useful typedefs from vmlinux.h */
+
+typedef signed char __s8;
+typedef unsigned char __u8;
+typedef short int __s16;
+typedef short unsigned int __u16;
+typedef int __s32;
+typedef unsigned int __u32;
+typedef long long int __s64;
+typedef long long unsigned int __u64;
+
+typedef __s8 s8;
+typedef __u8 u8;
+typedef __s16 s16;
+typedef __u16 u16;
+typedef __s32 s32;
+typedef __u32 u32;
+typedef __s64 s64;
+typedef __u64 u64;
+
+enum {
+	false = 0,
+	true = 1,
+};
+
+#ifdef __CHECKER__
+#define __bitwise__ __attribute__((bitwise))
+#else
+#define __bitwise__
+#endif
+
+typedef __u16 __bitwise__ __le16;
+typedef __u16 __bitwise__ __be16;
+typedef __u32 __bitwise__ __le32;
+typedef __u32 __bitwise__ __be32;
+typedef __u64 __bitwise__ __le64;
+typedef __u64 __bitwise__ __be64;
+
+typedef __u16 __bitwise__ __sum16;
+typedef __u32 __bitwise__ __wsum;
+
+#endif /* __PROFILER_H */
diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c
index 48a39f72fadf..1f18a409f044 100644
--- a/tools/bpf/runqslower/runqslower.bpf.c
+++ b/tools/bpf/runqslower/runqslower.bpf.c
@@ -5,9 +5,7 @@
 #include "runqslower.h"
 
 #define TASK_RUNNING 0
-
-#define BPF_F_INDEX_MASK		0xffffffffULL
-#define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
+#define BPF_F_CURRENT_CPU 0xffffffffULL
 
 const volatile __u64 min_us = 0;
 const volatile pid_t targ_pid = 0;
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 7ac0d8088565..ab8e89a7009c 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -67,7 +67,8 @@ FILES=                                          \
          test-llvm.bin				\
          test-llvm-version.bin			\
          test-libaio.bin			\
-         test-libzstd.bin
+         test-libzstd.bin			\
+         test-clang-bpf-global-var.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
@@ -75,6 +76,7 @@ CC ?= $(CROSS_COMPILE)gcc
 CXX ?= $(CROSS_COMPILE)g++
 PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config
 LLVM_CONFIG ?= llvm-config
+CLANG ?= clang
 
 all: $(FILES)
 
@@ -321,6 +323,11 @@ $(OUTPUT)test-libaio.bin:
 $(OUTPUT)test-libzstd.bin:
 	$(BUILD) -lzstd
 
+$(OUTPUT)test-clang-bpf-global-var.bin:
+	$(CLANG) -S -g -target bpf -o - $(patsubst %.bin,%.c,$(@F)) |	\
+		grep BTF_KIND_VAR
+
+
 ###############################
 
 clean:
diff --git a/tools/build/feature/test-clang-bpf-global-var.c b/tools/build/feature/test-clang-bpf-global-var.c
new file mode 100644
index 000000000000..221f1481d52e
--- /dev/null
+++ b/tools/build/feature/test-clang-bpf-global-var.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+volatile int global_value_for_test = 1;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 906e9f2752db..5d01c5c7e598 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -73,7 +73,7 @@ struct bpf_insn {
 /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
 struct bpf_lpm_trie_key {
 	__u32	prefixlen;	/* up to 32 for AF_INET, 128 for AF_INET6 */
-	__u8	data[0];	/* Arbitrary size */
+	__u8	data[];	/* Arbitrary size */
 };
 
 struct bpf_cgroup_storage_key {
@@ -210,6 +210,7 @@ enum bpf_attach_type {
 	BPF_TRACE_RAW_TP,
 	BPF_TRACE_FENTRY,
 	BPF_TRACE_FEXIT,
+	BPF_MODIFY_RETURN,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -325,44 +326,46 @@ enum bpf_attach_type {
 #define BPF_PSEUDO_CALL		1
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
-#define BPF_ANY		0 /* create new element or update existing */
-#define BPF_NOEXIST	1 /* create new element if it didn't exist */
-#define BPF_EXIST	2 /* update existing element */
-#define BPF_F_LOCK	4 /* spin_lock-ed map_lookup/map_update */
+enum {
+	BPF_ANY		= 0, /* create new element or update existing */
+	BPF_NOEXIST	= 1, /* create new element if it didn't exist */
+	BPF_EXIST	= 2, /* update existing element */
+	BPF_F_LOCK	= 4, /* spin_lock-ed map_lookup/map_update */
+};
 
 /* flags for BPF_MAP_CREATE command */
-#define BPF_F_NO_PREALLOC	(1U << 0)
+enum {
+	BPF_F_NO_PREALLOC	= (1U << 0),
 /* Instead of having one common LRU list in the
  * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
  * which can scale and perform better.
  * Note, the LRU nodes (including free nodes) cannot be moved
  * across different LRU lists.
  */
-#define BPF_F_NO_COMMON_LRU	(1U << 1)
+	BPF_F_NO_COMMON_LRU	= (1U << 1),
 /* Specify numa node during map creation */
-#define BPF_F_NUMA_NODE		(1U << 2)
-
-#define BPF_OBJ_NAME_LEN 16U
+	BPF_F_NUMA_NODE		= (1U << 2),
 
 /* Flags for accessing BPF object from syscall side. */
-#define BPF_F_RDONLY		(1U << 3)
-#define BPF_F_WRONLY		(1U << 4)
+	BPF_F_RDONLY		= (1U << 3),
+	BPF_F_WRONLY		= (1U << 4),
 
 /* Flag for stack_map, store build_id+offset instead of pointer */
-#define BPF_F_STACK_BUILD_ID	(1U << 5)
+	BPF_F_STACK_BUILD_ID	= (1U << 5),
 
 /* Zero-initialize hash function seed. This should only be used for testing. */
-#define BPF_F_ZERO_SEED		(1U << 6)
+	BPF_F_ZERO_SEED		= (1U << 6),
 
 /* Flags for accessing BPF object from program side. */
-#define BPF_F_RDONLY_PROG	(1U << 7)
-#define BPF_F_WRONLY_PROG	(1U << 8)
+	BPF_F_RDONLY_PROG	= (1U << 7),
+	BPF_F_WRONLY_PROG	= (1U << 8),
 
 /* Clone map from listener for newly accepted socket */
-#define BPF_F_CLONE		(1U << 9)
+	BPF_F_CLONE		= (1U << 9),
 
 /* Enable memory-mapping BPF map */
-#define BPF_F_MMAPABLE		(1U << 10)
+	BPF_F_MMAPABLE		= (1U << 10),
+};
 
 /* Flags for BPF_PROG_QUERY. */
 
@@ -391,6 +394,8 @@ struct bpf_stack_build_id {
 	};
 };
 
+#define BPF_OBJ_NAME_LEN 16U
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -2909,6 +2914,42 @@ union bpf_attr {
  *		of sizeof(struct perf_branch_entry).
  *
  *		**-ENOENT** if architecture does not support branch records.
+ *
+ * int bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size)
+ *	Description
+ *		Returns 0 on success, values for *pid* and *tgid* as seen from the current
+ *		*namespace* will be returned in *nsdata*.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EINVAL** if dev and inum supplied don't match dev_t and inode number
+ *              with nsfs of current task, or if dev conversion to dev_t lost high bits.
+ *
+ *		**-ENOENT** if pidns does not exists for the current task.
+ *
+ * int bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ *	Description
+ *		Write raw *data* blob into a special BPF perf event held by
+ *		*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ *		event must have the following attributes: **PERF_SAMPLE_RAW**
+ *		as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ *		**PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ *		The *flags* are used to indicate the index in *map* for which
+ *		the value must be put, masked with **BPF_F_INDEX_MASK**.
+ *		Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ *		to indicate that the index of the current CPU core should be
+ *		used.
+ *
+ *		The value to write, of *size*, is passed through eBPF stack and
+ *		pointed by *data*.
+ *
+ *		*ctx* is a pointer to in-kernel struct xdp_buff.
+ *
+ *		This helper is similar to **bpf_perf_eventoutput**\ () but
+ *		restricted to raw_tracepoint bpf programs.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3030,7 +3071,9 @@ union bpf_attr {
 	FN(tcp_send_ack),		\
 	FN(send_signal_thread),		\
 	FN(jiffies64),			\
-	FN(read_branch_records),
+	FN(read_branch_records),	\
+	FN(get_ns_current_pid_tgid),	\
+	FN(xdp_output),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3045,72 +3088,100 @@ enum bpf_func_id {
 /* All flags used by eBPF helper functions, placed here. */
 
 /* BPF_FUNC_skb_store_bytes flags. */
-#define BPF_F_RECOMPUTE_CSUM		(1ULL << 0)
-#define BPF_F_INVALIDATE_HASH		(1ULL << 1)
+enum {
+	BPF_F_RECOMPUTE_CSUM		= (1ULL << 0),
+	BPF_F_INVALIDATE_HASH		= (1ULL << 1),
+};
 
 /* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags.
  * First 4 bits are for passing the header field size.
  */
-#define BPF_F_HDR_FIELD_MASK		0xfULL
+enum {
+	BPF_F_HDR_FIELD_MASK		= 0xfULL,
+};
 
 /* BPF_FUNC_l4_csum_replace flags. */
-#define BPF_F_PSEUDO_HDR		(1ULL << 4)
-#define BPF_F_MARK_MANGLED_0		(1ULL << 5)
-#define BPF_F_MARK_ENFORCE		(1ULL << 6)
+enum {
+	BPF_F_PSEUDO_HDR		= (1ULL << 4),
+	BPF_F_MARK_MANGLED_0		= (1ULL << 5),
+	BPF_F_MARK_ENFORCE		= (1ULL << 6),
+};
 
 /* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
-#define BPF_F_INGRESS			(1ULL << 0)
+enum {
+	BPF_F_INGRESS			= (1ULL << 0),
+};
 
 /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
-#define BPF_F_TUNINFO_IPV6		(1ULL << 0)
+enum {
+	BPF_F_TUNINFO_IPV6		= (1ULL << 0),
+};
 
 /* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */
-#define BPF_F_SKIP_FIELD_MASK		0xffULL
-#define BPF_F_USER_STACK		(1ULL << 8)
+enum {
+	BPF_F_SKIP_FIELD_MASK		= 0xffULL,
+	BPF_F_USER_STACK		= (1ULL << 8),
 /* flags used by BPF_FUNC_get_stackid only. */
-#define BPF_F_FAST_STACK_CMP		(1ULL << 9)
-#define BPF_F_REUSE_STACKID		(1ULL << 10)
+	BPF_F_FAST_STACK_CMP		= (1ULL << 9),
+	BPF_F_REUSE_STACKID		= (1ULL << 10),
 /* flags used by BPF_FUNC_get_stack only. */
-#define BPF_F_USER_BUILD_ID		(1ULL << 11)
+	BPF_F_USER_BUILD_ID		= (1ULL << 11),
+};
 
 /* BPF_FUNC_skb_set_tunnel_key flags. */
-#define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
-#define BPF_F_DONT_FRAGMENT		(1ULL << 2)
-#define BPF_F_SEQ_NUMBER		(1ULL << 3)
+enum {
+	BPF_F_ZERO_CSUM_TX		= (1ULL << 1),
+	BPF_F_DONT_FRAGMENT		= (1ULL << 2),
+	BPF_F_SEQ_NUMBER		= (1ULL << 3),
+};
 
 /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
  * BPF_FUNC_perf_event_read_value flags.
  */
-#define BPF_F_INDEX_MASK		0xffffffffULL
-#define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
+enum {
+	BPF_F_INDEX_MASK		= 0xffffffffULL,
+	BPF_F_CURRENT_CPU		= BPF_F_INDEX_MASK,
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
-#define BPF_F_CTXLEN_MASK		(0xfffffULL << 32)
+	BPF_F_CTXLEN_MASK		= (0xfffffULL << 32),
+};
 
 /* Current network namespace */
-#define BPF_F_CURRENT_NETNS		(-1L)
+enum {
+	BPF_F_CURRENT_NETNS		= (-1L),
+};
 
 /* BPF_FUNC_skb_adjust_room flags. */
-#define BPF_F_ADJ_ROOM_FIXED_GSO	(1ULL << 0)
+enum {
+	BPF_F_ADJ_ROOM_FIXED_GSO	= (1ULL << 0),
+	BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	= (1ULL << 1),
+	BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	= (1ULL << 2),
+	BPF_F_ADJ_ROOM_ENCAP_L4_GRE	= (1ULL << 3),
+	BPF_F_ADJ_ROOM_ENCAP_L4_UDP	= (1ULL << 4),
+};
 
-#define BPF_ADJ_ROOM_ENCAP_L2_MASK	0xff
-#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT	56
+enum {
+	BPF_ADJ_ROOM_ENCAP_L2_MASK	= 0xff,
+	BPF_ADJ_ROOM_ENCAP_L2_SHIFT	= 56,
+};
 
-#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	(1ULL << 1)
-#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	(1ULL << 2)
-#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE	(1ULL << 3)
-#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP	(1ULL << 4)
 #define BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
 					  BPF_ADJ_ROOM_ENCAP_L2_MASK) \
 					 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
 
 /* BPF_FUNC_sysctl_get_name flags. */
-#define BPF_F_SYSCTL_BASE_NAME		(1ULL << 0)
+enum {
+	BPF_F_SYSCTL_BASE_NAME		= (1ULL << 0),
+};
 
 /* BPF_FUNC_sk_storage_get flags */
-#define BPF_SK_STORAGE_GET_F_CREATE	(1ULL << 0)
+enum {
+	BPF_SK_STORAGE_GET_F_CREATE	= (1ULL << 0),
+};
 
 /* BPF_FUNC_read_branch_records flags. */
-#define BPF_F_GET_BRANCH_RECORDS_SIZE	(1ULL << 0)
+enum {
+	BPF_F_GET_BRANCH_RECORDS_SIZE	= (1ULL << 0),
+};
 
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
@@ -3176,6 +3247,7 @@ struct __sk_buff {
 	__u32 wire_len;
 	__u32 gso_segs;
 	__bpf_md_ptr(struct bpf_sock *, sk);
+	__u32 gso_size;
 };
 
 struct bpf_tunnel_key {
@@ -3528,13 +3600,14 @@ struct bpf_sock_ops {
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */
-#define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
-#define BPF_SOCK_OPS_RETRANS_CB_FLAG	(1<<1)
-#define BPF_SOCK_OPS_STATE_CB_FLAG	(1<<2)
-#define BPF_SOCK_OPS_RTT_CB_FLAG	(1<<3)
-#define BPF_SOCK_OPS_ALL_CB_FLAGS       0xF		/* Mask of all currently
-							 * supported cb flags
-							 */
+enum {
+	BPF_SOCK_OPS_RTO_CB_FLAG	= (1<<0),
+	BPF_SOCK_OPS_RETRANS_CB_FLAG	= (1<<1),
+	BPF_SOCK_OPS_STATE_CB_FLAG	= (1<<2),
+	BPF_SOCK_OPS_RTT_CB_FLAG	= (1<<3),
+/* Mask of all currently supported cb flags */
+	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0xF,
+};
 
 /* List of known BPF sock_ops operators.
  * New entries can only be added at the end
@@ -3613,8 +3686,10 @@ enum {
 	BPF_TCP_MAX_STATES	/* Leave at the end! */
 };
 
-#define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
-#define TCP_BPF_SNDCWND_CLAMP	1002	/* Set sndcwnd_clamp */
+enum {
+	TCP_BPF_IW		= 1001,	/* Set TCP initial congestion window */
+	TCP_BPF_SNDCWND_CLAMP	= 1002,	/* Set sndcwnd_clamp */
+};
 
 struct bpf_perf_event_value {
 	__u64 counter;
@@ -3622,12 +3697,16 @@ struct bpf_perf_event_value {
 	__u64 running;
 };
 
-#define BPF_DEVCG_ACC_MKNOD	(1ULL << 0)
-#define BPF_DEVCG_ACC_READ	(1ULL << 1)
-#define BPF_DEVCG_ACC_WRITE	(1ULL << 2)
+enum {
+	BPF_DEVCG_ACC_MKNOD	= (1ULL << 0),
+	BPF_DEVCG_ACC_READ	= (1ULL << 1),
+	BPF_DEVCG_ACC_WRITE	= (1ULL << 2),
+};
 
-#define BPF_DEVCG_DEV_BLOCK	(1ULL << 0)
-#define BPF_DEVCG_DEV_CHAR	(1ULL << 1)
+enum {
+	BPF_DEVCG_DEV_BLOCK	= (1ULL << 0),
+	BPF_DEVCG_DEV_CHAR	= (1ULL << 1),
+};
 
 struct bpf_cgroup_dev_ctx {
 	/* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */
@@ -3643,8 +3722,10 @@ struct bpf_raw_tracepoint_args {
 /* DIRECT:  Skip the FIB rules and go to FIB table associated with device
  * OUTPUT:  Do lookup from egress perspective; default is ingress
  */
-#define BPF_FIB_LOOKUP_DIRECT  (1U << 0)
-#define BPF_FIB_LOOKUP_OUTPUT  (1U << 1)
+enum {
+	BPF_FIB_LOOKUP_DIRECT  = (1U << 0),
+	BPF_FIB_LOOKUP_OUTPUT  = (1U << 1),
+};
 
 enum {
 	BPF_FIB_LKUP_RET_SUCCESS,      /* lookup successful */
@@ -3716,9 +3797,11 @@ enum bpf_task_fd_type {
 	BPF_FD_TYPE_URETPROBE,		/* filename + offset */
 };
 
-#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG		(1U << 0)
-#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL		(1U << 1)
-#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP		(1U << 2)
+enum {
+	BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG		= (1U << 0),
+	BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL		= (1U << 1),
+	BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP		= (1U << 2),
+};
 
 struct bpf_flow_keys {
 	__u16	nhoff;
@@ -3784,4 +3867,8 @@ struct bpf_sockopt {
 	__s32	retval;
 };
 
+struct bpf_pidns_info {
+	__u32 pid;
+	__u32 tgid;
+};
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/testing/selftests/bpf/include/uapi/linux/types.h b/tools/include/uapi/linux/types.h
index 91fa51a9c31d..91fa51a9c31d 100644
--- a/tools/testing/selftests/bpf/include/uapi/linux/types.h
+++ b/tools/include/uapi/linux/types.h
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index b0dafe8b4ebc..b0c9ae5c73b5 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -49,7 +49,8 @@
 
 #if defined(bpf_target_x86)
 
-#ifdef __KERNEL__
+#if defined(__KERNEL__) || defined(__VMLINUX_H__)
+
 #define PT_REGS_PARM1(x) ((x)->di)
 #define PT_REGS_PARM2(x) ((x)->si)
 #define PT_REGS_PARM3(x) ((x)->dx)
@@ -60,7 +61,20 @@
 #define PT_REGS_RC(x) ((x)->ax)
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->ip)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), di)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), si)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), dx)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), cx)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), sp)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), bp)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), ax)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), ip)
+
 #else
+
 #ifdef __i386__
 /* i386 kernel is built with -mregparm=3 */
 #define PT_REGS_PARM1(x) ((x)->eax)
@@ -73,7 +87,20 @@
 #define PT_REGS_RC(x) ((x)->eax)
 #define PT_REGS_SP(x) ((x)->esp)
 #define PT_REGS_IP(x) ((x)->eip)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), eax)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), edx)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), ecx)
+#define PT_REGS_PARM4_CORE(x) 0
+#define PT_REGS_PARM5_CORE(x) 0
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), esp)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), ebp)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), eax)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), esp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), eip)
+
 #else
+
 #define PT_REGS_PARM1(x) ((x)->rdi)
 #define PT_REGS_PARM2(x) ((x)->rsi)
 #define PT_REGS_PARM3(x) ((x)->rdx)
@@ -84,6 +111,18 @@
 #define PT_REGS_RC(x) ((x)->rax)
 #define PT_REGS_SP(x) ((x)->rsp)
 #define PT_REGS_IP(x) ((x)->rip)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), rdi)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), rsi)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), rdx)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), rcx)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), rsp)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), rbp)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), rax)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), rsp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), rip)
+
 #endif
 #endif
 
@@ -104,6 +143,17 @@ struct pt_regs;
 #define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15])
 #define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr)
 
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[3])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), grps[14])
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15])
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), pdw.addr)
+
 #elif defined(bpf_target_arm)
 
 #define PT_REGS_PARM1(x) ((x)->uregs[0])
@@ -117,6 +167,17 @@ struct pt_regs;
 #define PT_REGS_SP(x) ((x)->uregs[13])
 #define PT_REGS_IP(x) ((x)->uregs[12])
 
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), uregs[0])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), uregs[1])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), uregs[2])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), uregs[3])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), uregs[4])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), uregs[14])
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), uregs[11])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), uregs[0])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), uregs[13])
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), uregs[12])
+
 #elif defined(bpf_target_arm64)
 
 /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
@@ -134,6 +195,17 @@ struct pt_regs;
 #define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp)
 #define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc)
 
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[1])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[2])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[3])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[4])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[30])
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[29])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), sp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), pc)
+
 #elif defined(bpf_target_mips)
 
 #define PT_REGS_PARM1(x) ((x)->regs[4])
@@ -147,6 +219,17 @@ struct pt_regs;
 #define PT_REGS_SP(x) ((x)->regs[29])
 #define PT_REGS_IP(x) ((x)->cp0_epc)
 
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), regs[4])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), regs[5])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), regs[6])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), regs[7])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), regs[8])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), regs[31])
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), regs[30])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), regs[1])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), regs[29])
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), cp0_epc)
+
 #elif defined(bpf_target_powerpc)
 
 #define PT_REGS_PARM1(x) ((x)->gpr[3])
@@ -158,6 +241,15 @@ struct pt_regs;
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->nip)
 
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), gpr[3])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), gpr[4])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), gpr[5])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), gpr[6])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), gpr[7])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), gpr[3])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), nip)
+
 #elif defined(bpf_target_sparc)
 
 #define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
@@ -169,11 +261,22 @@ struct pt_regs;
 #define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
 #define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
 
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I1])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I2])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I3])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I4])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I7])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), u_regs[UREG_FP])
+
 /* Should this also be a bpf_target check for the sparc case? */
 #if defined(__arch64__)
 #define PT_REGS_IP(x) ((x)->tpc)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), tpc)
 #else
 #define PT_REGS_IP(x) ((x)->pc)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), pc)
 #endif
 
 #endif
@@ -192,4 +295,122 @@ struct pt_regs;
 			  (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
 #endif
 
+#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_PROG(name, args...)						    \
+name(unsigned long long *ctx);						    \
+static __attribute__((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 __attribute__((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 __attribute__((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 __attribute__((always_inline)) typeof(name(0))			    \
+____##name(struct pt_regs *ctx, ##args)
+
+#define ___bpf_kretprobe_args0() ctx
+#define ___bpf_kretprobe_args1(x) \
+	___bpf_kretprobe_args0(), (void *)PT_REGS_RET(ctx)
+#define ___bpf_kretprobe_args(args...) \
+	___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
+
+/*
+ * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional
+ * return value (in addition to `struct pt_regs *ctx`), but no input
+ * arguments, because they will be clobbered by the time probed function
+ * returns.
+ */
+#define BPF_KRETPROBE(name, args...)					    \
+name(struct pt_regs *ctx);						    \
+static __attribute__((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/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index bd09ed1710f1..0c28ee82834b 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -916,13 +916,13 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id,
 			/* enumerators share namespace with typedef idents */
 			dup_cnt = btf_dump_name_dups(d, d->ident_names, name);
 			if (dup_cnt > 1) {
-				btf_dump_printf(d, "\n%s%s___%zu = %d,",
+				btf_dump_printf(d, "\n%s%s___%zu = %u,",
 						pfx(lvl + 1), name, dup_cnt,
-						(__s32)v->val);
+						(__u32)v->val);
 			} else {
-				btf_dump_printf(d, "\n%s%s = %d,",
+				btf_dump_printf(d, "\n%s%s = %u,",
 						pfx(lvl + 1), name,
-						(__s32)v->val);
+						(__u32)v->val);
 			}
 		}
 		btf_dump_printf(d, "\n%s}", pfx(lvl));
@@ -1030,7 +1030,7 @@ int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id,
 	if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts))
 		return -EINVAL;
 
-	fname = OPTS_GET(opts, field_name, NULL);
+	fname = OPTS_GET(opts, field_name, "");
 	lvl = OPTS_GET(opts, indent_level, 0);
 	btf_dump_emit_type_decl(d, id, fname, lvl);
 	return 0;
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 996162801f7a..085e41f9b68e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2284,9 +2284,16 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj)
 	}
 }
 
-static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj)
+static bool libbpf_needs_btf(const struct bpf_object *obj)
 {
-	return obj->efile.st_ops_shndx >= 0 || obj->nr_extern > 0;
+	return obj->efile.btf_maps_shndx >= 0 ||
+	       obj->efile.st_ops_shndx >= 0 ||
+	       obj->nr_extern > 0;
+}
+
+static bool kernel_needs_btf(const struct bpf_object *obj)
+{
+	return obj->efile.st_ops_shndx >= 0;
 }
 
 static int bpf_object__init_btf(struct bpf_object *obj,
@@ -2322,7 +2329,7 @@ static int bpf_object__init_btf(struct bpf_object *obj,
 		}
 	}
 out:
-	if (err && bpf_object__is_btf_mandatory(obj)) {
+	if (err && libbpf_needs_btf(obj)) {
 		pr_warn("BTF is required, but is missing or corrupted.\n");
 		return err;
 	}
@@ -2346,7 +2353,7 @@ static int bpf_object__finalize_btf(struct bpf_object *obj)
 	btf_ext__free(obj->btf_ext);
 	obj->btf_ext = NULL;
 
-	if (bpf_object__is_btf_mandatory(obj)) {
+	if (libbpf_needs_btf(obj)) {
 		pr_warn("BTF is required, but is missing or corrupted.\n");
 		return -ENOENT;
 	}
@@ -2410,7 +2417,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 			obj->btf_ext = NULL;
 		}
 
-		if (bpf_object__is_btf_mandatory(obj))
+		if (kernel_needs_btf(obj))
 			return err;
 	}
 	return 0;
@@ -3866,6 +3873,10 @@ static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf,
 		if (str_is_empty(targ_name))
 			continue;
 
+		t = skip_mods_and_typedefs(targ_btf, i, NULL);
+		if (!btf_is_composite(t) && !btf_is_array(t))
+			continue;
+
 		targ_essent_len = bpf_core_essential_name_len(targ_name);
 		if (targ_essent_len != local_essent_len)
 			continue;
@@ -6288,6 +6299,10 @@ static const struct bpf_sec_def section_defs[] = {
 		.expected_attach_type = BPF_TRACE_FENTRY,
 		.is_attach_btf = true,
 		.attach_fn = attach_trace),
+	SEC_DEF("fmod_ret/", TRACING,
+		.expected_attach_type = BPF_MODIFY_RETURN,
+		.is_attach_btf = true,
+		.attach_fn = attach_trace),
 	SEC_DEF("fexit/", TRACING,
 		.expected_attach_type = BPF_TRACE_FEXIT,
 		.is_attach_btf = true,
@@ -6931,6 +6946,8 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 struct bpf_link {
 	int (*detach)(struct bpf_link *link);
 	int (*destroy)(struct bpf_link *link);
+	char *pin_path;		/* NULL, if not pinned */
+	int fd;			/* hook FD, -1 if not applicable */
 	bool disconnected;
 };
 
@@ -6960,26 +6977,109 @@ int bpf_link__destroy(struct bpf_link *link)
 		err = link->detach(link);
 	if (link->destroy)
 		link->destroy(link);
+	if (link->pin_path)
+		free(link->pin_path);
 	free(link);
 
 	return err;
 }
 
-struct bpf_link_fd {
-	struct bpf_link link; /* has to be at the top of struct */
-	int fd; /* hook FD */
-};
+int bpf_link__fd(const struct bpf_link *link)
+{
+	return link->fd;
+}
+
+const char *bpf_link__pin_path(const struct bpf_link *link)
+{
+	return link->pin_path;
+}
+
+static int bpf_link__detach_fd(struct bpf_link *link)
+{
+	return close(link->fd);
+}
+
+struct bpf_link *bpf_link__open(const char *path)
+{
+	struct bpf_link *link;
+	int fd;
+
+	fd = bpf_obj_get(path);
+	if (fd < 0) {
+		fd = -errno;
+		pr_warn("failed to open link at %s: %d\n", path, fd);
+		return ERR_PTR(fd);
+	}
+
+	link = calloc(1, sizeof(*link));
+	if (!link) {
+		close(fd);
+		return ERR_PTR(-ENOMEM);
+	}
+	link->detach = &bpf_link__detach_fd;
+	link->fd = fd;
+
+	link->pin_path = strdup(path);
+	if (!link->pin_path) {
+		bpf_link__destroy(link);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return link;
+}
+
+int bpf_link__pin(struct bpf_link *link, const char *path)
+{
+	int err;
+
+	if (link->pin_path)
+		return -EBUSY;
+	err = make_parent_dir(path);
+	if (err)
+		return err;
+	err = check_path(path);
+	if (err)
+		return err;
+
+	link->pin_path = strdup(path);
+	if (!link->pin_path)
+		return -ENOMEM;
+
+	if (bpf_obj_pin(link->fd, link->pin_path)) {
+		err = -errno;
+		zfree(&link->pin_path);
+		return err;
+	}
+
+	pr_debug("link fd=%d: pinned at %s\n", link->fd, link->pin_path);
+	return 0;
+}
+
+int bpf_link__unpin(struct bpf_link *link)
+{
+	int err;
+
+	if (!link->pin_path)
+		return -EINVAL;
+
+	err = unlink(link->pin_path);
+	if (err != 0)
+		return -errno;
+
+	pr_debug("link fd=%d: unpinned from %s\n", link->fd, link->pin_path);
+	zfree(&link->pin_path);
+	return 0;
+}
 
 static int bpf_link__detach_perf_event(struct bpf_link *link)
 {
-	struct bpf_link_fd *l = (void *)link;
 	int err;
 
-	err = ioctl(l->fd, PERF_EVENT_IOC_DISABLE, 0);
+	err = ioctl(link->fd, PERF_EVENT_IOC_DISABLE, 0);
 	if (err)
 		err = -errno;
 
-	close(l->fd);
+	close(link->fd);
 	return err;
 }
 
@@ -6987,7 +7087,7 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
 						int pfd)
 {
 	char errmsg[STRERR_BUFSIZE];
-	struct bpf_link_fd *link;
+	struct bpf_link *link;
 	int prog_fd, err;
 
 	if (pfd < 0) {
@@ -7005,7 +7105,7 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
 	link = calloc(1, sizeof(*link));
 	if (!link)
 		return ERR_PTR(-ENOMEM);
-	link->link.detach = &bpf_link__detach_perf_event;
+	link->detach = &bpf_link__detach_perf_event;
 	link->fd = pfd;
 
 	if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) {
@@ -7024,7 +7124,7 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
 			   libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
 		return ERR_PTR(err);
 	}
-	return (struct bpf_link *)link;
+	return link;
 }
 
 /*
@@ -7312,18 +7412,11 @@ out:
 	return link;
 }
 
-static int bpf_link__detach_fd(struct bpf_link *link)
-{
-	struct bpf_link_fd *l = (void *)link;
-
-	return close(l->fd);
-}
-
 struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 						    const char *tp_name)
 {
 	char errmsg[STRERR_BUFSIZE];
-	struct bpf_link_fd *link;
+	struct bpf_link *link;
 	int prog_fd, pfd;
 
 	prog_fd = bpf_program__fd(prog);
@@ -7336,7 +7429,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 	link = calloc(1, sizeof(*link));
 	if (!link)
 		return ERR_PTR(-ENOMEM);
-	link->link.detach = &bpf_link__detach_fd;
+	link->detach = &bpf_link__detach_fd;
 
 	pfd = bpf_raw_tracepoint_open(tp_name, prog_fd);
 	if (pfd < 0) {
@@ -7348,7 +7441,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 		return ERR_PTR(pfd);
 	}
 	link->fd = pfd;
-	return (struct bpf_link *)link;
+	return link;
 }
 
 static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
@@ -7362,7 +7455,7 @@ static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
 struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
 {
 	char errmsg[STRERR_BUFSIZE];
-	struct bpf_link_fd *link;
+	struct bpf_link *link;
 	int prog_fd, pfd;
 
 	prog_fd = bpf_program__fd(prog);
@@ -7375,7 +7468,7 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
 	link = calloc(1, sizeof(*link));
 	if (!link)
 		return ERR_PTR(-ENOMEM);
-	link->link.detach = &bpf_link__detach_fd;
+	link->detach = &bpf_link__detach_fd;
 
 	pfd = bpf_raw_tracepoint_open(NULL, prog_fd);
 	if (pfd < 0) {
@@ -7409,10 +7502,9 @@ struct bpf_link *bpf_program__attach(struct bpf_program *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))
+	if (bpf_map_delete_elem(link->fd, &zero))
 		return -errno;
 
 	return 0;
@@ -7421,7 +7513,7 @@ static int bpf_link__detach_struct_ops(struct bpf_link *link)
 struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
 {
 	struct bpf_struct_ops *st_ops;
-	struct bpf_link_fd *link;
+	struct bpf_link *link;
 	__u32 i, zero = 0;
 	int err;
 
@@ -7453,10 +7545,10 @@ struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
 		return ERR_PTR(err);
 	}
 
-	link->link.detach = bpf_link__detach_struct_ops;
+	link->detach = bpf_link__detach_struct_ops;
 	link->fd = map->fd;
 
-	return (struct bpf_link *)link;
+	return link;
 }
 
 enum bpf_perf_event_ret
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 02fc58a21a7f..d38d7a629417 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -219,6 +219,11 @@ LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
 
 struct bpf_link;
 
+LIBBPF_API struct bpf_link *bpf_link__open(const char *path);
+LIBBPF_API int bpf_link__fd(const struct bpf_link *link);
+LIBBPF_API const char *bpf_link__pin_path(const struct bpf_link *link);
+LIBBPF_API int bpf_link__pin(struct bpf_link *link, const char *path);
+LIBBPF_API int bpf_link__unpin(struct bpf_link *link);
 LIBBPF_API void bpf_link__disconnect(struct bpf_link *link);
 LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
 
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 7b014c8cdece..5129283c0284 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -238,5 +238,10 @@ LIBBPF_0.0.7 {
 
 LIBBPF_0.0.8 {
 	global:
+		bpf_link__fd;
+		bpf_link__open;
+		bpf_link__pin;
+		bpf_link__pin_path;
+		bpf_link__unpin;
 		bpf_program__set_attach_target;
 } LIBBPF_0.0.7;
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index ded7a950dc40..59f31f01cb93 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -106,6 +106,7 @@ ifneq ($(silent),1)
   ifneq ($(V),1)
 	QUIET_CC       = @echo '  CC       '$@;
 	QUIET_CC_FPIC  = @echo '  CC FPIC  '$@;
+	QUIET_CLANG    = @echo '  CLANG    '$@;
 	QUIET_AR       = @echo '  AR       '$@;
 	QUIET_LINK     = @echo '  LINK     '$@;
 	QUIET_MKDIR    = @echo '  MKDIR    '$@;
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index ec464859c6b6..2198cd876675 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -31,6 +31,7 @@ test_tcp_check_syncookie_user
 test_sysctl
 test_hashmap
 test_btf_dump
+test_current_pid_tgid_new_ns
 xdping
 test_cpp
 *.skel.h
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 2d7f5df33f04..7729892e0b04 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -20,8 +20,9 @@ CLANG		?= clang
 LLC		?= llc
 LLVM_OBJCOPY	?= llvm-objcopy
 BPF_GCC		?= $(shell command -v bpf-gcc;)
-CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) -I$(CURDIR) -I$(APIDIR)	\
+CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) -I$(CURDIR)		\
 	  -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) -I$(TOOLSINCDIR)	\
+	  -I$(APIDIR)							\
 	  -Dbpf_prog_load=bpf_prog_test_load				\
 	  -Dbpf_load_program=bpf_test_load_program
 LDLIBS += -lcap -lelf -lz -lrt -lpthread
@@ -32,7 +33,8 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \
 	test_cgroup_storage \
 	test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \
-	test_progs-no_alu32
+	test_progs-no_alu32 \
+	test_current_pid_tgid_new_ns
 
 # Also test bpf-gcc, if present
 ifneq ($(BPF_GCC),)
@@ -129,10 +131,13 @@ $(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ)
 	$(call msg,CC,,$@)
 	$(CC) -c $(CFLAGS) -o $@ $<
 
-VMLINUX_BTF_PATHS := $(abspath ../../../../vmlinux)			\
-			       /sys/kernel/btf/vmlinux			\
-			       /boot/vmlinux-$(shell uname -r)
-VMLINUX_BTF:= $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))
+VMLINUX_BTF_PATHS := $(if $(O),$(O)/vmlinux)				\
+		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)	\
+		     ../../../../vmlinux				\
+		     /sys/kernel/btf/vmlinux				\
+		     /boot/vmlinux-$(shell uname -r)
+VMLINUX_BTF := $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+
 $(OUTPUT)/runqslower: $(BPFOBJ)
 	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower	\
 		    OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF)   \
@@ -172,6 +177,10 @@ $(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(INCLUDE_DIR):
 	$(call msg,MKDIR,,$@)
 	mkdir -p $@
 
+$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) | $(BPFTOOL) $(INCLUDE_DIR)
+	$(call msg,GEN,,$@)
+	$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
+
 # Get Clang's default includes on this system, as opposed to those seen by
 # '-target bpf'. This fixes "missing" files on some architectures/distros,
 # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
@@ -190,8 +199,8 @@ MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian)
 
 CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG))
 BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) 			\
-	     -I$(INCLUDE_DIR) -I$(CURDIR) -I$(CURDIR)/include/uapi	\
-	     -I$(APIDIR) -I$(abspath $(OUTPUT)/../usr/include)
+	     -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR)			\
+	     -I$(abspath $(OUTPUT)/../usr/include)
 
 CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
 	       -Wno-compare-distinct-pointer-types
@@ -280,6 +289,7 @@ $(TRUNNER_BPF_PROGS_DIR)$(if $2,-)$2-bpfobjs := y
 $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 		     $(TRUNNER_BPF_PROGS_DIR)/%.c			\
 		     $(TRUNNER_BPF_PROGS_DIR)/*.h			\
+		     $$(INCLUDE_DIR)/vmlinux.h				\
 		     $$(BPFOBJ) | $(TRUNNER_OUTPUT)
 	$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@,			\
 					  $(TRUNNER_BPF_CFLAGS),	\
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 8f21965ffc6c..5bf2fe9b1efa 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -6,7 +6,7 @@
 #include <linux/types.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_core_read.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 #define BPF_STRUCT_OPS(name, args...) \
 SEC("struct_ops/"#name) \
diff --git a/tools/testing/selftests/bpf/bpf_trace_helpers.h b/tools/testing/selftests/bpf/bpf_trace_helpers.h
deleted file mode 100644
index c6f1354d93fb..000000000000
--- a/tools/testing/selftests/bpf/bpf_trace_helpers.h
+++ /dev/null
@@ -1,120 +0,0 @@
-/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
-#ifndef __BPF_TRACE_HELPERS_H
-#define __BPF_TRACE_HELPERS_H
-
-#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_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/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
index 5b13f2c6c402..70e94e783070 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
@@ -6,7 +6,7 @@
 
 #define PING_CMD	"ping -q -c1 -w1 127.0.0.1 > /dev/null"
 
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
+static char bpf_log_buf[BPF_LOG_BUF_SIZE];
 
 static int prog_load(void)
 {
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
index 2ff21dbce179..139f8e82c7c6 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
@@ -6,7 +6,7 @@
 
 #define PING_CMD	"ping -q -c1 -w1 127.0.0.1 > /dev/null"
 
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
+static char bpf_log_buf[BPF_LOG_BUF_SIZE];
 
 static int map_fd = -1;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
index 9d8cb48b99de..9e96f8d87fea 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
@@ -8,7 +8,7 @@
 #define BAR		"/foo/bar/"
 #define PING_CMD	"ping -q -c1 -w1 127.0.0.1 > /dev/null"
 
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
+static char bpf_log_buf[BPF_LOG_BUF_SIZE];
 
 static int prog_load(int verdict)
 {
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
index 235ac4f67f5b..83493bd5745c 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
@@ -1,22 +1,17 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
-#include "test_pkt_access.skel.h"
 #include "fentry_test.skel.h"
 #include "fexit_test.skel.h"
 
 void test_fentry_fexit(void)
 {
-	struct test_pkt_access *pkt_skel = NULL;
 	struct fentry_test *fentry_skel = NULL;
 	struct fexit_test *fexit_skel = NULL;
 	__u64 *fentry_res, *fexit_res;
 	__u32 duration = 0, retval;
-	int err, pkt_fd, i;
+	int err, prog_fd, i;
 
-	pkt_skel = test_pkt_access__open_and_load();
-	if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n"))
-		return;
 	fentry_skel = fentry_test__open_and_load();
 	if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n"))
 		goto close_prog;
@@ -31,8 +26,8 @@ void test_fentry_fexit(void)
 	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
 		goto close_prog;
 
-	pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access);
-	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
+	prog_fd = bpf_program__fd(fexit_skel->progs.test1);
+	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
 	CHECK(err || retval, "ipv6",
 	      "err %d errno %d retval %d duration %d\n",
@@ -49,7 +44,6 @@ void test_fentry_fexit(void)
 	}
 
 close_prog:
-	test_pkt_access__destroy(pkt_skel);
 	fentry_test__destroy(fentry_skel);
 	fexit_test__destroy(fexit_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
index 5cc06021f27d..04ebbf1cb390 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
@@ -1,20 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
-#include "test_pkt_access.skel.h"
 #include "fentry_test.skel.h"
 
 void test_fentry_test(void)
 {
-	struct test_pkt_access *pkt_skel = NULL;
 	struct fentry_test *fentry_skel = NULL;
-	int err, pkt_fd, i;
+	int err, prog_fd, i;
 	__u32 duration = 0, retval;
 	__u64 *result;
 
-	pkt_skel = test_pkt_access__open_and_load();
-	if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n"))
-		return;
 	fentry_skel = fentry_test__open_and_load();
 	if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n"))
 		goto cleanup;
@@ -23,10 +18,10 @@ void test_fentry_test(void)
 	if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err))
 		goto cleanup;
 
-	pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access);
-	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
+	prog_fd = bpf_program__fd(fentry_skel->progs.test1);
+	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
-	CHECK(err || retval, "ipv6",
+	CHECK(err || retval, "test_run",
 	      "err %d errno %d retval %d duration %d\n",
 	      err, errno, retval, duration);
 
@@ -39,5 +34,4 @@ void test_fentry_test(void)
 
 cleanup:
 	fentry_test__destroy(fentry_skel);
-	test_pkt_access__destroy(pkt_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
index d2c3655dd7a3..78d7a2765c27 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
@@ -1,64 +1,37 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
+#include "fexit_test.skel.h"
 
 void test_fexit_test(void)
 {
-	struct bpf_prog_load_attr attr = {
-		.file = "./fexit_test.o",
-	};
-
-	char prog_name[] = "fexit/bpf_fentry_testX";
-	struct bpf_object *obj = NULL, *pkt_obj;
-	int err, pkt_fd, kfree_skb_fd, i;
-	struct bpf_link *link[6] = {};
-	struct bpf_program *prog[6];
+	struct fexit_test *fexit_skel = NULL;
+	int err, prog_fd, i;
 	__u32 duration = 0, retval;
-	struct bpf_map *data_map;
-	const int zero = 0;
-	u64 result[6];
+	__u64 *result;
 
-	err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS,
-			    &pkt_obj, &pkt_fd);
-	if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno))
-		return;
-	err = bpf_prog_load_xattr(&attr, &obj, &kfree_skb_fd);
-	if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno))
-		goto close_prog;
+	fexit_skel = fexit_test__open_and_load();
+	if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n"))
+		goto cleanup;
 
-	for (i = 0; i < 6; i++) {
-		prog_name[sizeof(prog_name) - 2] = '1' + i;
-		prog[i] = bpf_object__find_program_by_title(obj, prog_name);
-		if (CHECK(!prog[i], "find_prog", "prog %s not found\n", prog_name))
-			goto close_prog;
-		link[i] = bpf_program__attach_trace(prog[i]);
-		if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
-			goto close_prog;
-	}
-	data_map = bpf_object__find_map_by_name(obj, "fexit_te.bss");
-	if (CHECK(!data_map, "find_data_map", "data map not found\n"))
-		goto close_prog;
+	err = fexit_test__attach(fexit_skel);
+	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
+		goto cleanup;
 
-	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
+	prog_fd = bpf_program__fd(fexit_skel->progs.test1);
+	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
-	CHECK(err || retval, "ipv6",
+	CHECK(err || retval, "test_run",
 	      "err %d errno %d retval %d duration %d\n",
 	      err, errno, retval, duration);
 
-	err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &result);
-	if (CHECK(err, "get_result",
-		  "failed to get output data: %d\n", err))
-		goto close_prog;
-
-	for (i = 0; i < 6; i++)
-		if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n",
-			  i + 1, result[i]))
-			goto close_prog;
+	result = (__u64 *)fexit_skel->bss;
+	for (i = 0; i < 6; i++) {
+		if (CHECK(result[i] != 1, "result",
+			  "fexit_test%d failed err %lld\n", i + 1, result[i]))
+			goto cleanup;
+	}
 
-close_prog:
-	for (i = 0; i < 6; i++)
-		if (!IS_ERR_OR_NULL(link[i]))
-			bpf_link__destroy(link[i]);
-	bpf_object__close(obj);
-	bpf_object__close(pkt_obj);
+cleanup:
+	fexit_test__destroy(fexit_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/link_pinning.c b/tools/testing/selftests/bpf/prog_tests/link_pinning.c
new file mode 100644
index 000000000000..a743288cf384
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/link_pinning.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <test_progs.h>
+#include <sys/stat.h>
+
+#include "test_link_pinning.skel.h"
+
+static int duration = 0;
+
+void test_link_pinning_subtest(struct bpf_program *prog,
+			       struct test_link_pinning__bss *bss)
+{
+	const char *link_pin_path = "/sys/fs/bpf/pinned_link_test";
+	struct stat statbuf = {};
+	struct bpf_link *link;
+	int err, i;
+
+	link = bpf_program__attach(prog);
+	if (CHECK(IS_ERR(link), "link_attach", "err: %ld\n", PTR_ERR(link)))
+		goto cleanup;
+
+	bss->in = 1;
+	usleep(1);
+	CHECK(bss->out != 1, "res_check1", "exp %d, got %d\n", 1, bss->out);
+
+	/* pin link */
+	err = bpf_link__pin(link, link_pin_path);
+	if (CHECK(err, "link_pin", "err: %d\n", err))
+		goto cleanup;
+
+	CHECK(strcmp(link_pin_path, bpf_link__pin_path(link)), "pin_path1",
+	      "exp %s, got %s\n", link_pin_path, bpf_link__pin_path(link));
+
+	/* check that link was pinned */
+	err = stat(link_pin_path, &statbuf);
+	if (CHECK(err, "stat_link", "err %d errno %d\n", err, errno))
+		goto cleanup;
+
+	bss->in = 2;
+	usleep(1);
+	CHECK(bss->out != 2, "res_check2", "exp %d, got %d\n", 2, bss->out);
+
+	/* destroy link, pinned link should keep program attached */
+	bpf_link__destroy(link);
+	link = NULL;
+
+	bss->in = 3;
+	usleep(1);
+	CHECK(bss->out != 3, "res_check3", "exp %d, got %d\n", 3, bss->out);
+
+	/* re-open link from BPFFS */
+	link = bpf_link__open(link_pin_path);
+	if (CHECK(IS_ERR(link), "link_open", "err: %ld\n", PTR_ERR(link)))
+		goto cleanup;
+
+	CHECK(strcmp(link_pin_path, bpf_link__pin_path(link)), "pin_path2",
+	      "exp %s, got %s\n", link_pin_path, bpf_link__pin_path(link));
+
+	/* unpin link from BPFFS, program still attached */
+	err = bpf_link__unpin(link);
+	if (CHECK(err, "link_unpin", "err: %d\n", err))
+		goto cleanup;
+
+	/* still active, as we have FD open now */
+	bss->in = 4;
+	usleep(1);
+	CHECK(bss->out != 4, "res_check4", "exp %d, got %d\n", 4, bss->out);
+
+	bpf_link__destroy(link);
+	link = NULL;
+
+	/* Validate it's finally detached.
+	 * Actual detachment might get delayed a bit, so there is no reliable
+	 * way to validate it immediately here, let's count up for long enough
+	 * and see if eventually output stops being updated
+	 */
+	for (i = 5; i < 10000; i++) {
+		bss->in = i;
+		usleep(1);
+		if (bss->out == i - 1)
+			break;
+	}
+	CHECK(i == 10000, "link_attached", "got to iteration #%d\n", i);
+
+cleanup:
+	if (!IS_ERR(link))
+		bpf_link__destroy(link);
+}
+
+void test_link_pinning(void)
+{
+	struct test_link_pinning* skel;
+
+	skel = test_link_pinning__open_and_load();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+		return;
+
+	if (test__start_subtest("pin_raw_tp"))
+		test_link_pinning_subtest(skel->progs.raw_tp_prog, skel->bss);
+	if (test__start_subtest("pin_tp_btf"))
+		test_link_pinning_subtest(skel->progs.tp_btf_prog, skel->bss);
+
+	test_link_pinning__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c
new file mode 100644
index 000000000000..97fec70c600b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include <test_progs.h>
+#include "modify_return.skel.h"
+
+#define LOWER(x) ((x) & 0xffff)
+#define UPPER(x) ((x) >> 16)
+
+
+static void run_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret)
+{
+	struct modify_return *skel = NULL;
+	int err, prog_fd;
+	__u32 duration = 0, retval;
+	__u16 side_effect;
+	__s16 ret;
+
+	skel = modify_return__open_and_load();
+	if (CHECK(!skel, "skel_load", "modify_return skeleton failed\n"))
+		goto cleanup;
+
+	err = modify_return__attach(skel);
+	if (CHECK(err, "modify_return", "attach failed: %d\n", err))
+		goto cleanup;
+
+	skel->bss->input_retval = input_retval;
+	prog_fd = bpf_program__fd(skel->progs.fmod_ret_test);
+	err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, 0,
+				&retval, &duration);
+
+	CHECK(err, "test_run", "err %d errno %d\n", err, errno);
+
+	side_effect = UPPER(retval);
+	ret  = LOWER(retval);
+
+	CHECK(ret != want_ret, "test_run",
+	      "unexpected ret: %d, expected: %d\n", ret, want_ret);
+	CHECK(side_effect != want_side_effect, "modify_return",
+	      "unexpected side_effect: %d\n", side_effect);
+
+	CHECK(skel->bss->fentry_result != 1, "modify_return",
+	      "fentry failed\n");
+	CHECK(skel->bss->fexit_result != 1, "modify_return",
+	      "fexit failed\n");
+	CHECK(skel->bss->fmod_ret_result != 1, "modify_return",
+	      "fmod_ret failed\n");
+
+cleanup:
+	modify_return__destroy(skel);
+}
+
+void test_modify_return(void)
+{
+	run_test(0 /* input_retval */,
+		 1 /* want_side_effect */,
+		 4 /* want_ret */);
+	run_test(-EINVAL /* input_retval */,
+		 0 /* want_side_effect */,
+		 -EINVAL /* want_ret */);
+}
+
diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
new file mode 100644
index 000000000000..542240e16564
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Carlos Neira cneirabustos@gmail.com */
+#include <test_progs.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+
+struct bss {
+	__u64 dev;
+	__u64 ino;
+	__u64 pid_tgid;
+	__u64 user_pid_tgid;
+};
+
+void test_ns_current_pid_tgid(void)
+{
+	const char *probe_name = "raw_tracepoint/sys_enter";
+	const char *file = "test_ns_current_pid_tgid.o";
+	int err, key = 0, duration = 0;
+	struct bpf_link *link = NULL;
+	struct bpf_program *prog;
+	struct bpf_map *bss_map;
+	struct bpf_object *obj;
+	struct bss bss;
+	struct stat st;
+	__u64 id;
+
+	obj = bpf_object__open_file(file, NULL);
+	if (CHECK(IS_ERR(obj), "obj_open", "err %ld\n", PTR_ERR(obj)))
+		return;
+
+	err = bpf_object__load(obj);
+	if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno))
+		goto cleanup;
+
+	bss_map = bpf_object__find_map_by_name(obj, "test_ns_.bss");
+	if (CHECK(!bss_map, "find_bss_map", "failed\n"))
+		goto cleanup;
+
+	prog = bpf_object__find_program_by_title(obj, probe_name);
+	if (CHECK(!prog, "find_prog", "prog '%s' not found\n",
+		  probe_name))
+		goto cleanup;
+
+	memset(&bss, 0, sizeof(bss));
+	pid_t tid = syscall(SYS_gettid);
+	pid_t pid = getpid();
+
+	id = (__u64) tid << 32 | pid;
+	bss.user_pid_tgid = id;
+
+	if (CHECK_FAIL(stat("/proc/self/ns/pid", &st))) {
+		perror("Failed to stat /proc/self/ns/pid");
+		goto cleanup;
+	}
+
+	bss.dev = st.st_dev;
+	bss.ino = st.st_ino;
+
+	err = bpf_map_update_elem(bpf_map__fd(bss_map), &key, &bss, 0);
+	if (CHECK(err, "setting_bss", "failed to set bss : %d\n", err))
+		goto cleanup;
+
+	link = bpf_program__attach_raw_tracepoint(prog, "sys_enter");
+	if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n",
+		  PTR_ERR(link))) {
+		link = NULL;
+		goto cleanup;
+	}
+
+	/* trigger some syscalls */
+	usleep(1);
+
+	err = bpf_map_lookup_elem(bpf_map__fd(bss_map), &key, &bss);
+	if (CHECK(err, "set_bss", "failed to get bss : %d\n", err))
+		goto cleanup;
+
+	if (CHECK(id != bss.pid_tgid, "Compare user pid/tgid vs. bpf pid/tgid",
+		  "User pid/tgid %llu BPF pid/tgid %llu\n", id, bss.pid_tgid))
+		goto cleanup;
+cleanup:
+	if (!link) {
+		bpf_link__destroy(link);
+		link = NULL;
+	}
+	bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
index a1dd13b34d4b..821b4146b7b6 100644
--- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
@@ -805,12 +805,6 @@ static void test_config(int sotype, sa_family_t family, bool inany)
 	char s[MAX_TEST_NAME];
 	const struct test *t;
 
-	/* SOCKMAP/SOCKHASH don't support UDP yet */
-	if (sotype == SOCK_DGRAM &&
-	    (inner_map_type == BPF_MAP_TYPE_SOCKMAP ||
-	     inner_map_type == BPF_MAP_TYPE_SOCKHASH))
-		return;
-
 	for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
 		if (t->need_sotype && t->need_sotype != sotype)
 			continue; /* test not compatible with socket type */
diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
index c6d6b685a946..4538bd08203f 100644
--- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
+++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
@@ -14,6 +14,7 @@ void test_skb_ctx(void)
 		.wire_len = 100,
 		.gso_segs = 8,
 		.mark = 9,
+		.gso_size = 10,
 	};
 	struct bpf_prog_test_run_attr tattr = {
 		.data_in = &pkt_v4,
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index b1b2acea0638..d7d65a700799 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -16,6 +16,7 @@
 #include <pthread.h>
 #include <stdlib.h>
 #include <string.h>
+#include <sys/select.h>
 #include <unistd.h>
 
 #include <bpf/bpf.h>
@@ -25,6 +26,7 @@
 #include "test_progs.h"
 #include "test_sockmap_listen.skel.h"
 
+#define IO_TIMEOUT_SEC 30
 #define MAX_STRERR_LEN 256
 #define MAX_TEST_NAME 80
 
@@ -44,9 +46,10 @@
 
 /* Wrappers that fail the test on error and report it. */
 
-#define xaccept(fd, addr, len)                                                 \
+#define xaccept_nonblock(fd, addr, len)                                        \
 	({                                                                     \
-		int __ret = accept((fd), (addr), (len));                       \
+		int __ret =                                                    \
+			accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC);   \
 		if (__ret == -1)                                               \
 			FAIL_ERRNO("accept");                                  \
 		__ret;                                                         \
@@ -108,6 +111,23 @@
 		__ret;                                                         \
 	})
 
+#define xsend(fd, buf, len, flags)                                             \
+	({                                                                     \
+		ssize_t __ret = send((fd), (buf), (len), (flags));             \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("send");                                    \
+		__ret;                                                         \
+	})
+
+#define xrecv_nonblock(fd, buf, len, flags)                                    \
+	({                                                                     \
+		ssize_t __ret = recv_timeout((fd), (buf), (len), (flags),      \
+					     IO_TIMEOUT_SEC);                  \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("recv");                                    \
+		__ret;                                                         \
+	})
+
 #define xsocket(family, sotype, flags)                                         \
 	({                                                                     \
 		int __ret = socket(family, sotype, flags);                     \
@@ -175,6 +195,40 @@
 		__ret;                                                         \
 	})
 
+static int poll_read(int fd, unsigned int timeout_sec)
+{
+	struct timeval timeout = { .tv_sec = timeout_sec };
+	fd_set rfds;
+	int r;
+
+	FD_ZERO(&rfds);
+	FD_SET(fd, &rfds);
+
+	r = select(fd + 1, &rfds, NULL, NULL, &timeout);
+	if (r == 0)
+		errno = ETIME;
+
+	return r == 1 ? 0 : -1;
+}
+
+static int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len,
+			  unsigned int timeout_sec)
+{
+	if (poll_read(fd, timeout_sec))
+		return -1;
+
+	return accept(fd, addr, len);
+}
+
+static int recv_timeout(int fd, void *buf, size_t len, int flags,
+			unsigned int timeout_sec)
+{
+	if (poll_read(fd, timeout_sec))
+		return -1;
+
+	return recv(fd, buf, len, flags);
+}
+
 static void init_addr_loopback4(struct sockaddr_storage *ss, socklen_t *len)
 {
 	struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss));
@@ -230,7 +284,7 @@ static int enable_reuseport(int s, int progfd)
 	return 0;
 }
 
-static int listen_loopback_reuseport(int family, int sotype, int progfd)
+static int socket_loopback_reuseport(int family, int sotype, int progfd)
 {
 	struct sockaddr_storage addr;
 	socklen_t len;
@@ -249,6 +303,9 @@ static int listen_loopback_reuseport(int family, int sotype, int progfd)
 	if (err)
 		goto close;
 
+	if (sotype & SOCK_DGRAM)
+		return s;
+
 	err = xlisten(s, SOMAXCONN);
 	if (err)
 		goto close;
@@ -259,9 +316,9 @@ close:
 	return -1;
 }
 
-static int listen_loopback(int family, int sotype)
+static int socket_loopback(int family, int sotype)
 {
-	return listen_loopback_reuseport(family, sotype, -1);
+	return socket_loopback_reuseport(family, sotype, -1);
 }
 
 static void test_insert_invalid(int family, int sotype, int mapfd)
@@ -327,13 +384,13 @@ close:
 	xclose(s);
 }
 
-static void test_insert_listening(int family, int sotype, int mapfd)
+static void test_insert(int family, int sotype, int mapfd)
 {
 	u64 value;
 	u32 key;
 	int s;
 
-	s = listen_loopback(family, sotype);
+	s = socket_loopback(family, sotype);
 	if (s < 0)
 		return;
 
@@ -349,7 +406,7 @@ static void test_delete_after_insert(int family, int sotype, int mapfd)
 	u32 key;
 	int s;
 
-	s = listen_loopback(family, sotype);
+	s = socket_loopback(family, sotype);
 	if (s < 0)
 		return;
 
@@ -366,7 +423,7 @@ static void test_delete_after_close(int family, int sotype, int mapfd)
 	u64 value;
 	u32 key;
 
-	s = listen_loopback(family, sotype);
+	s = socket_loopback(family, sotype);
 	if (s < 0)
 		return;
 
@@ -390,7 +447,7 @@ static void test_lookup_after_insert(int family, int sotype, int mapfd)
 	u32 key;
 	int s;
 
-	s = listen_loopback(family, sotype);
+	s = socket_loopback(family, sotype);
 	if (s < 0)
 		return;
 
@@ -417,7 +474,7 @@ static void test_lookup_after_delete(int family, int sotype, int mapfd)
 	u64 value;
 	u32 key;
 
-	s = listen_loopback(family, sotype);
+	s = socket_loopback(family, sotype);
 	if (s < 0)
 		return;
 
@@ -439,7 +496,7 @@ static void test_lookup_32_bit_value(int family, int sotype, int mapfd)
 	u32 key, value32;
 	int err, s;
 
-	s = listen_loopback(family, sotype);
+	s = socket_loopback(family, sotype);
 	if (s < 0)
 		return;
 
@@ -464,17 +521,17 @@ close:
 	xclose(s);
 }
 
-static void test_update_listening(int family, int sotype, int mapfd)
+static void test_update_existing(int family, int sotype, int mapfd)
 {
 	int s1, s2;
 	u64 value;
 	u32 key;
 
-	s1 = listen_loopback(family, sotype);
+	s1 = socket_loopback(family, sotype);
 	if (s1 < 0)
 		return;
 
-	s2 = listen_loopback(family, sotype);
+	s2 = socket_loopback(family, sotype);
 	if (s2 < 0)
 		goto close_s1;
 
@@ -500,7 +557,7 @@ static void test_destroy_orphan_child(int family, int sotype, int mapfd)
 	u64 value;
 	u32 key;
 
-	s = listen_loopback(family, sotype);
+	s = socket_loopback(family, sotype);
 	if (s < 0)
 		return;
 
@@ -534,7 +591,7 @@ static void test_clone_after_delete(int family, int sotype, int mapfd)
 	u64 value;
 	u32 key;
 
-	s = listen_loopback(family, sotype);
+	s = socket_loopback(family, sotype);
 	if (s < 0)
 		return;
 
@@ -570,7 +627,7 @@ static void test_accept_after_delete(int family, int sotype, int mapfd)
 	socklen_t len;
 	u64 value;
 
-	s = listen_loopback(family, sotype);
+	s = socket_loopback(family, sotype | SOCK_NONBLOCK);
 	if (s == -1)
 		return;
 
@@ -598,7 +655,7 @@ static void test_accept_after_delete(int family, int sotype, int mapfd)
 	if (err)
 		goto close_cli;
 
-	p = xaccept(s, NULL, NULL);
+	p = xaccept_nonblock(s, NULL, NULL);
 	if (p == -1)
 		goto close_cli;
 
@@ -624,7 +681,7 @@ static void test_accept_before_delete(int family, int sotype, int mapfd)
 	socklen_t len;
 	u64 value;
 
-	s = listen_loopback(family, sotype);
+	s = socket_loopback(family, sotype | SOCK_NONBLOCK);
 	if (s == -1)
 		return;
 
@@ -647,7 +704,7 @@ static void test_accept_before_delete(int family, int sotype, int mapfd)
 	if (err)
 		goto close_cli;
 
-	p = xaccept(s, NULL, NULL);
+	p = xaccept_nonblock(s, NULL, NULL);
 	if (p == -1)
 		goto close_cli;
 
@@ -711,7 +768,7 @@ static void *connect_accept_thread(void *arg)
 			break;
 		}
 
-		p = xaccept(s, NULL, NULL);
+		p = xaccept_nonblock(s, NULL, NULL);
 		if (p < 0) {
 			xclose(c);
 			break;
@@ -735,7 +792,7 @@ static void test_syn_recv_insert_delete(int family, int sotype, int mapfd)
 	int err, s;
 	u64 value;
 
-	s = listen_loopback(family, sotype | SOCK_NONBLOCK);
+	s = socket_loopback(family, sotype | SOCK_NONBLOCK);
 	if (s < 0)
 		return;
 
@@ -877,7 +934,7 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
 
 	zero_verdict_count(verd_mapfd);
 
-	s = listen_loopback(family, sotype | SOCK_NONBLOCK);
+	s = socket_loopback(family, sotype | SOCK_NONBLOCK);
 	if (s < 0)
 		return;
 
@@ -893,7 +950,7 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
 	if (err)
 		goto close_cli0;
 
-	p0 = xaccept(s, NULL, NULL);
+	p0 = xaccept_nonblock(s, NULL, NULL);
 	if (p0 < 0)
 		goto close_cli0;
 
@@ -904,7 +961,7 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
 	if (err)
 		goto close_cli1;
 
-	p1 = xaccept(s, NULL, NULL);
+	p1 = xaccept_nonblock(s, NULL, NULL);
 	if (p1 < 0)
 		goto close_cli1;
 
@@ -1009,7 +1066,7 @@ static void redir_to_listening(int family, int sotype, int sock_mapfd,
 
 	zero_verdict_count(verd_mapfd);
 
-	s = listen_loopback(family, sotype | SOCK_NONBLOCK);
+	s = socket_loopback(family, sotype | SOCK_NONBLOCK);
 	if (s < 0)
 		return;
 
@@ -1025,7 +1082,7 @@ static void redir_to_listening(int family, int sotype, int sock_mapfd,
 	if (err)
 		goto close_cli;
 
-	p = xaccept(s, NULL, NULL);
+	p = xaccept_nonblock(s, NULL, NULL);
 	if (p < 0)
 		goto close_cli;
 
@@ -1113,14 +1170,15 @@ static void test_reuseport_select_listening(int family, int sotype,
 {
 	struct sockaddr_storage addr;
 	unsigned int pass;
-	int s, c, p, err;
+	int s, c, err;
 	socklen_t len;
 	u64 value;
 	u32 key;
 
 	zero_verdict_count(verd_map);
 
-	s = listen_loopback_reuseport(family, sotype, reuseport_prog);
+	s = socket_loopback_reuseport(family, sotype | SOCK_NONBLOCK,
+				      reuseport_prog);
 	if (s < 0)
 		return;
 
@@ -1142,19 +1200,33 @@ static void test_reuseport_select_listening(int family, int sotype,
 	if (err)
 		goto close_cli;
 
-	p = xaccept(s, NULL, NULL);
-	if (p < 0)
-		goto close_cli;
+	if (sotype == SOCK_STREAM) {
+		int p;
+
+		p = xaccept_nonblock(s, NULL, NULL);
+		if (p < 0)
+			goto close_cli;
+		xclose(p);
+	} else {
+		char b = 'a';
+		ssize_t n;
+
+		n = xsend(c, &b, sizeof(b), 0);
+		if (n == -1)
+			goto close_cli;
+
+		n = xrecv_nonblock(s, &b, sizeof(b), 0);
+		if (n == -1)
+			goto close_cli;
+	}
 
 	key = SK_PASS;
 	err = xbpf_map_lookup_elem(verd_map, &key, &pass);
 	if (err)
-		goto close_peer;
+		goto close_cli;
 	if (pass != 1)
 		FAIL("want pass count 1, have %d", pass);
 
-close_peer:
-	xclose(p);
 close_cli:
 	xclose(c);
 close_srv:
@@ -1174,7 +1246,7 @@ static void test_reuseport_select_connected(int family, int sotype,
 
 	zero_verdict_count(verd_map);
 
-	s = listen_loopback_reuseport(family, sotype, reuseport_prog);
+	s = socket_loopback_reuseport(family, sotype, reuseport_prog);
 	if (s < 0)
 		return;
 
@@ -1198,9 +1270,24 @@ static void test_reuseport_select_connected(int family, int sotype,
 	if (err)
 		goto close_cli0;
 
-	p0 = xaccept(s, NULL, NULL);
-	if (err)
-		goto close_cli0;
+	if (sotype == SOCK_STREAM) {
+		p0 = xaccept_nonblock(s, NULL, NULL);
+		if (p0 < 0)
+			goto close_cli0;
+	} else {
+		p0 = xsocket(family, sotype, 0);
+		if (p0 < 0)
+			goto close_cli0;
+
+		len = sizeof(addr);
+		err = xgetsockname(c0, sockaddr(&addr), &len);
+		if (err)
+			goto close_cli0;
+
+		err = xconnect(p0, sockaddr(&addr), len);
+		if (err)
+			goto close_cli0;
+	}
 
 	/* Update sock_map[0] to redirect to a connected socket */
 	key = 0;
@@ -1213,8 +1300,24 @@ static void test_reuseport_select_connected(int family, int sotype,
 	if (c1 < 0)
 		goto close_peer0;
 
+	len = sizeof(addr);
+	err = xgetsockname(s, sockaddr(&addr), &len);
+	if (err)
+		goto close_srv;
+
 	errno = 0;
 	err = connect(c1, sockaddr(&addr), len);
+	if (sotype == SOCK_DGRAM) {
+		char b = 'a';
+		ssize_t n;
+
+		n = xsend(c1, &b, sizeof(b), 0);
+		if (n == -1)
+			goto close_cli1;
+
+		n = recv_timeout(c1, &b, sizeof(b), 0, IO_TIMEOUT_SEC);
+		err = n == -1;
+	}
 	if (!err || errno != ECONNREFUSED)
 		FAIL_ERRNO("connect: expected ECONNREFUSED");
 
@@ -1249,11 +1352,11 @@ static void test_reuseport_mixed_groups(int family, int sotype, int sock_map,
 	zero_verdict_count(verd_map);
 
 	/* Create two listeners, each in its own reuseport group */
-	s1 = listen_loopback_reuseport(family, sotype, reuseport_prog);
+	s1 = socket_loopback_reuseport(family, sotype, reuseport_prog);
 	if (s1 < 0)
 		return;
 
-	s2 = listen_loopback_reuseport(family, sotype, reuseport_prog);
+	s2 = socket_loopback_reuseport(family, sotype, reuseport_prog);
 	if (s2 < 0)
 		goto close_srv1;
 
@@ -1278,7 +1381,18 @@ static void test_reuseport_mixed_groups(int family, int sotype, int sock_map,
 		goto close_srv2;
 
 	err = connect(c, sockaddr(&addr), len);
-	if (err && errno != ECONNREFUSED) {
+	if (sotype == SOCK_DGRAM) {
+		char b = 'a';
+		ssize_t n;
+
+		n = xsend(c, &b, sizeof(b), 0);
+		if (n == -1)
+			goto close_cli;
+
+		n = recv_timeout(c, &b, sizeof(b), 0, IO_TIMEOUT_SEC);
+		err = n == -1;
+	}
+	if (!err || errno != ECONNREFUSED) {
 		FAIL_ERRNO("connect: expected ECONNREFUSED");
 		goto close_cli;
 	}
@@ -1299,9 +1413,9 @@ close_srv1:
 	xclose(s1);
 }
 
-#define TEST(fn)                                                               \
+#define TEST(fn, ...)                                                          \
 	{                                                                      \
-		fn, #fn                                                        \
+		fn, #fn, __VA_ARGS__                                           \
 	}
 
 static void test_ops_cleanup(const struct bpf_map *map)
@@ -1350,18 +1464,31 @@ static const char *map_type_str(const struct bpf_map *map)
 	}
 }
 
+static const char *sotype_str(int sotype)
+{
+	switch (sotype) {
+	case SOCK_DGRAM:
+		return "UDP";
+	case SOCK_STREAM:
+		return "TCP";
+	default:
+		return "unknown";
+	}
+}
+
 static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map,
 		     int family, int sotype)
 {
 	const struct op_test {
 		void (*fn)(int family, int sotype, int mapfd);
 		const char *name;
+		int sotype;
 	} tests[] = {
 		/* insert */
 		TEST(test_insert_invalid),
 		TEST(test_insert_opened),
-		TEST(test_insert_bound),
-		TEST(test_insert_listening),
+		TEST(test_insert_bound, SOCK_STREAM),
+		TEST(test_insert),
 		/* delete */
 		TEST(test_delete_after_insert),
 		TEST(test_delete_after_close),
@@ -1370,28 +1497,32 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map,
 		TEST(test_lookup_after_delete),
 		TEST(test_lookup_32_bit_value),
 		/* update */
-		TEST(test_update_listening),
+		TEST(test_update_existing),
 		/* races with insert/delete */
-		TEST(test_destroy_orphan_child),
-		TEST(test_syn_recv_insert_delete),
-		TEST(test_race_insert_listen),
+		TEST(test_destroy_orphan_child, SOCK_STREAM),
+		TEST(test_syn_recv_insert_delete, SOCK_STREAM),
+		TEST(test_race_insert_listen, SOCK_STREAM),
 		/* child clone */
-		TEST(test_clone_after_delete),
-		TEST(test_accept_after_delete),
-		TEST(test_accept_before_delete),
+		TEST(test_clone_after_delete, SOCK_STREAM),
+		TEST(test_accept_after_delete, SOCK_STREAM),
+		TEST(test_accept_before_delete, SOCK_STREAM),
 	};
-	const char *family_name, *map_name;
+	const char *family_name, *map_name, *sotype_name;
 	const struct op_test *t;
 	char s[MAX_TEST_NAME];
 	int map_fd;
 
 	family_name = family_str(family);
 	map_name = map_type_str(map);
+	sotype_name = sotype_str(sotype);
 	map_fd = bpf_map__fd(map);
 
 	for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
-		snprintf(s, sizeof(s), "%s %s %s", map_name, family_name,
-			 t->name);
+		snprintf(s, sizeof(s), "%s %s %s %s", map_name, family_name,
+			 sotype_name, t->name);
+
+		if (t->sotype != 0 && t->sotype != sotype)
+			continue;
 
 		if (!test__start_subtest(s))
 			continue;
@@ -1424,6 +1555,7 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
 	for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
 		snprintf(s, sizeof(s), "%s %s %s", map_name, family_name,
 			 t->name);
+
 		if (!test__start_subtest(s))
 			continue;
 
@@ -1438,26 +1570,31 @@ static void test_reuseport(struct test_sockmap_listen *skel,
 		void (*fn)(int family, int sotype, int socket_map,
 			   int verdict_map, int reuseport_prog);
 		const char *name;
+		int sotype;
 	} tests[] = {
 		TEST(test_reuseport_select_listening),
 		TEST(test_reuseport_select_connected),
 		TEST(test_reuseport_mixed_groups),
 	};
 	int socket_map, verdict_map, reuseport_prog;
-	const char *family_name, *map_name;
+	const char *family_name, *map_name, *sotype_name;
 	const struct reuseport_test *t;
 	char s[MAX_TEST_NAME];
 
 	family_name = family_str(family);
 	map_name = map_type_str(map);
+	sotype_name = sotype_str(sotype);
 
 	socket_map = bpf_map__fd(map);
 	verdict_map = bpf_map__fd(skel->maps.verdict_map);
 	reuseport_prog = bpf_program__fd(skel->progs.prog_reuseport);
 
 	for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
-		snprintf(s, sizeof(s), "%s %s %s", map_name, family_name,
-			 t->name);
+		snprintf(s, sizeof(s), "%s %s %s %s", map_name, family_name,
+			 sotype_name, t->name);
+
+		if (t->sotype != 0 && t->sotype != sotype)
+			continue;
 
 		if (!test__start_subtest(s))
 			continue;
@@ -1470,8 +1607,10 @@ static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
 		      int family)
 {
 	test_ops(skel, map, family, SOCK_STREAM);
+	test_ops(skel, map, family, SOCK_DGRAM);
 	test_redir(skel, map, family, SOCK_STREAM);
 	test_reuseport(skel, map, family, SOCK_STREAM);
+	test_reuseport(skel, map, family, SOCK_DGRAM);
 }
 
 void test_sockmap_listen(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
index f4cd60d6fba2..e08f6bb17700 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
@@ -188,7 +188,7 @@ static int start_server(void)
 	};
 	int fd;
 
-	fd = socket(AF_INET, SOCK_STREAM, 0);
+	fd = socket(AF_INET, SOCK_STREAM | SOCK_NONBLOCK, 0);
 	if (fd < 0) {
 		log_err("Failed to create server socket");
 		return -1;
@@ -205,6 +205,7 @@ static int start_server(void)
 
 static pthread_mutex_t server_started_mtx = PTHREAD_MUTEX_INITIALIZER;
 static pthread_cond_t server_started = PTHREAD_COND_INITIALIZER;
+static volatile bool server_done = false;
 
 static void *server_thread(void *arg)
 {
@@ -222,23 +223,24 @@ static void *server_thread(void *arg)
 
 	if (CHECK_FAIL(err < 0)) {
 		perror("Failed to listed on socket");
-		return NULL;
+		return ERR_PTR(err);
 	}
 
-	client_fd = accept(fd, (struct sockaddr *)&addr, &len);
+	while (!server_done) {
+		client_fd = accept(fd, (struct sockaddr *)&addr, &len);
+		if (client_fd == -1 && errno == EAGAIN) {
+			usleep(50);
+			continue;
+		}
+		break;
+	}
 	if (CHECK_FAIL(client_fd < 0)) {
 		perror("Failed to accept client");
-		return NULL;
+		return ERR_PTR(err);
 	}
 
-	/* Wait for the next connection (that never arrives)
-	 * to keep this thread alive to prevent calling
-	 * close() on client_fd.
-	 */
-	if (CHECK_FAIL(accept(fd, (struct sockaddr *)&addr, &len) >= 0)) {
-		perror("Unexpected success in second accept");
-		return NULL;
-	}
+	while (!server_done)
+		usleep(50);
 
 	close(client_fd);
 
@@ -249,6 +251,7 @@ void test_tcp_rtt(void)
 {
 	int server_fd, cgroup_fd;
 	pthread_t tid;
+	void *server_res;
 
 	cgroup_fd = test__join_cgroup("/tcp_rtt");
 	if (CHECK_FAIL(cgroup_fd < 0))
@@ -267,6 +270,11 @@ void test_tcp_rtt(void)
 	pthread_mutex_unlock(&server_started_mtx);
 
 	CHECK_FAIL(run_test(cgroup_fd, server_fd));
+
+	server_done = true;
+	pthread_join(tid, &server_res);
+	CHECK_FAIL(IS_ERR(server_res));
+
 close_server_fd:
 	close(server_fd);
 close_cgroup_fd:
diff --git a/tools/testing/selftests/bpf/prog_tests/vmlinux.c b/tools/testing/selftests/bpf/prog_tests/vmlinux.c
new file mode 100644
index 000000000000..04939eda1325
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/vmlinux.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <test_progs.h>
+#include <time.h>
+#include "test_vmlinux.skel.h"
+
+#define MY_TV_NSEC 1337
+
+static void nsleep()
+{
+	struct timespec ts = { .tv_nsec = MY_TV_NSEC };
+
+	(void)nanosleep(&ts, NULL);
+}
+
+void test_vmlinux(void)
+{
+	int duration = 0, err;
+	struct test_vmlinux* skel;
+	struct test_vmlinux__bss *bss;
+
+	skel = test_vmlinux__open_and_load();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+		return;
+	bss = skel->bss;
+
+	err = test_vmlinux__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+		goto cleanup;
+
+	/* trigger everything */
+	nsleep();
+
+	CHECK(!bss->tp_called, "tp", "not called\n");
+	CHECK(!bss->raw_tp_called, "raw_tp", "not called\n");
+	CHECK(!bss->tp_btf_called, "tp_btf", "not called\n");
+	CHECK(!bss->kprobe_called, "kprobe", "not called\n");
+	CHECK(!bss->fentry_called, "fentry", "not called\n");
+
+cleanup:
+	test_vmlinux__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
index 4ba011031d4c..a0f688c37023 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
@@ -4,17 +4,51 @@
 #include "test_xdp.skel.h"
 #include "test_xdp_bpf2bpf.skel.h"
 
+struct meta {
+	int ifindex;
+	int pkt_len;
+};
+
+static void on_sample(void *ctx, int cpu, void *data, __u32 size)
+{
+	int duration = 0;
+	struct meta *meta = (struct meta *)data;
+	struct ipv4_packet *trace_pkt_v4 = data + sizeof(*meta);
+
+	if (CHECK(size < sizeof(pkt_v4) + sizeof(*meta),
+		  "check_size", "size %u < %zu\n",
+		  size, sizeof(pkt_v4) + sizeof(*meta)))
+		return;
+
+	if (CHECK(meta->ifindex != if_nametoindex("lo"), "check_meta_ifindex",
+		  "meta->ifindex = %d\n", meta->ifindex))
+		return;
+
+	if (CHECK(meta->pkt_len != sizeof(pkt_v4), "check_meta_pkt_len",
+		  "meta->pkt_len = %zd\n", sizeof(pkt_v4)))
+		return;
+
+	if (CHECK(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)),
+		  "check_packet_content", "content not the same\n"))
+		return;
+
+	*(bool *)ctx = true;
+}
+
 void test_xdp_bpf2bpf(void)
 {
 	__u32 duration = 0, retval, size;
 	char buf[128];
 	int err, pkt_fd, map_fd;
+	bool passed = false;
 	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};
 	struct bpf_program *prog;
+	struct perf_buffer *pb = NULL;
+	struct perf_buffer_opts pb_opts = {};
 
 	/* Load XDP program to introspect */
 	pkt_skel = test_xdp__open_and_load();
@@ -50,6 +84,14 @@ void test_xdp_bpf2bpf(void)
 	if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err))
 		goto out;
 
+	/* Set up perf buffer */
+	pb_opts.sample_cb = on_sample;
+	pb_opts.ctx = &passed;
+	pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map),
+			      1, &pb_opts);
+	if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb)))
+		goto out;
+
 	/* Run test program */
 	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4),
 				buf, &size, &retval, &duration);
@@ -60,6 +102,15 @@ void test_xdp_bpf2bpf(void)
 		  err, errno, retval, size))
 		goto out;
 
+	/* Make sure bpf_xdp_output() was triggered and it sent the expected
+	 * data to the perf ring buffer.
+	 */
+	err = perf_buffer__poll(pb, 100);
+	if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err))
+		goto out;
+
+	CHECK_FAIL(!passed);
+
 	/* Verify test results */
 	if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"),
 		  "result", "fentry failed err %llu\n",
@@ -70,6 +121,8 @@ void test_xdp_bpf2bpf(void)
 	      "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit);
 
 out:
+	if (pb)
+		perf_buffer__free(pb);
 	test_xdp__destroy(pkt_skel);
 	test_xdp_bpf2bpf__destroy(ftrace_skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
index b631fb5032d2..127ea762a062 100644
--- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -9,7 +9,7 @@
 #include <linux/bpf.h>
 #include <linux/types.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 #include "bpf_tcp_helpers.h"
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
index d4a02fe44a12..31975c96e2c9 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
@@ -13,7 +13,7 @@ enum e1 {
 
 enum e2 {
 	C = 100,
-	D = -100,
+	D = 4294967295,
 	E = 0,
 };
 
diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c
index 38d3a82144ca..9365b686f84b 100644
--- a/tools/testing/selftests/bpf/progs/fentry_test.c
+++ b/tools/testing/selftests/bpf/progs/fentry_test.c
@@ -2,7 +2,7 @@
 /* Copyright (c) 2019 Facebook */
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
index c329fccf9842..98e1efe14549 100644
--- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
@@ -5,7 +5,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 struct sk_buff {
 	unsigned int len;
diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
index 92f3fa47cf40..85c0b516d6ee 100644
--- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
+++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
@@ -2,7 +2,7 @@
 /* Copyright (c) 2019 Facebook */
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 struct sk_buff {
 	unsigned int len;
diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c
index 348109b9ea07..bd1e17d8024c 100644
--- a/tools/testing/selftests/bpf/progs/fexit_test.c
+++ b/tools/testing/selftests/bpf/progs/fexit_test.c
@@ -2,7 +2,7 @@
 /* Copyright (c) 2019 Facebook */
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c
index 8f48a909f079..a46a264ce24e 100644
--- a/tools/testing/selftests/bpf/progs/kfree_skb.c
+++ b/tools/testing/selftests/bpf/progs/kfree_skb.c
@@ -4,7 +4,7 @@
 #include <stdbool.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 struct {
diff --git a/tools/testing/selftests/bpf/progs/modify_return.c b/tools/testing/selftests/bpf/progs/modify_return.c
new file mode 100644
index 000000000000..8b7466a15c6b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/modify_return.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+static int sequence = 0;
+__s32 input_retval = 0;
+
+__u64 fentry_result = 0;
+SEC("fentry/bpf_modify_return_test")
+int BPF_PROG(fentry_test, int a, __u64 b)
+{
+	sequence++;
+	fentry_result = (sequence == 1);
+	return 0;
+}
+
+__u64 fmod_ret_result = 0;
+SEC("fmod_ret/bpf_modify_return_test")
+int BPF_PROG(fmod_ret_test, int a, int *b, int ret)
+{
+	sequence++;
+	/* This is the first fmod_ret program, the ret passed should be 0 */
+	fmod_ret_result = (sequence == 2 && ret == 0);
+	return input_retval;
+}
+
+__u64 fexit_result = 0;
+SEC("fexit/bpf_modify_return_test")
+int BPF_PROG(fexit_test, int a, __u64 b, int ret)
+{
+	sequence++;
+	/* If the input_reval is non-zero a successful modification should have
+	 * occurred.
+	 */
+	if (input_retval)
+		fexit_result = (sequence == 3 && ret == input_retval);
+	else
+		fexit_result = (sequence == 3 && ret == 4);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c
index dd8fae6660ab..8056a4c6d918 100644
--- a/tools/testing/selftests/bpf/progs/test_attach_probe.c
+++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c
@@ -4,6 +4,7 @@
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 int kprobe_res = 0;
 int kretprobe_res = 0;
@@ -18,7 +19,7 @@ int handle_kprobe(struct pt_regs *ctx)
 }
 
 SEC("kretprobe/sys_nanosleep")
-int handle_kretprobe(struct pt_regs *ctx)
+int BPF_KRETPROBE(handle_kretprobe)
 {
 	kretprobe_res = 2;
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_link_pinning.c b/tools/testing/selftests/bpf/progs/test_link_pinning.c
new file mode 100644
index 000000000000..bbf2a5264dc0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_link_pinning.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+int in = 0;
+int out = 0;
+
+SEC("raw_tp/sys_enter")
+int raw_tp_prog(const void *ctx)
+{
+	out = in;
+	return 0;
+}
+
+SEC("tp_btf/sys_enter")
+int tp_btf_prog(const void *ctx)
+{
+	out = in;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c
new file mode 100644
index 000000000000..1dca70a6de2f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Carlos Neira cneirabustos@gmail.com */
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include <bpf/bpf_helpers.h>
+
+static volatile struct {
+	__u64 dev;
+	__u64 ino;
+	__u64 pid_tgid;
+	__u64 user_pid_tgid;
+} res;
+
+SEC("raw_tracepoint/sys_enter")
+int trace(void *ctx)
+{
+	__u64  ns_pid_tgid, expected_pid;
+	struct bpf_pidns_info nsdata;
+	__u32 key = 0;
+
+	if (bpf_get_ns_current_pid_tgid(res.dev, res.ino, &nsdata,
+		   sizeof(struct bpf_pidns_info)))
+		return 0;
+
+	ns_pid_tgid = (__u64)nsdata.tgid << 32 | nsdata.pid;
+	expected_pid = res.user_pid_tgid;
+
+	if (expected_pid != ns_pid_tgid)
+		return 0;
+
+	res.pid_tgid = ns_pid_tgid;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c
index bfe9fbcb9684..56a50b25cd33 100644
--- a/tools/testing/selftests/bpf/progs/test_overhead.c
+++ b/tools/testing/selftests/bpf/progs/test_overhead.c
@@ -6,7 +6,6 @@
 #include <linux/ptrace.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include "bpf_trace_helpers.h"
 
 struct task_struct;
 
@@ -17,11 +16,9 @@ int BPF_KPROBE(prog1, struct task_struct *tsk, const char *buf, bool exec)
 }
 
 SEC("kretprobe/__set_task_comm")
-int BPF_KRETPROBE(prog2,
-		  struct task_struct *tsk, const char *buf, bool exec,
-		  int ret)
+int BPF_KRETPROBE(prog2, int ret)
 {
-	return !PT_REGS_PARM1(ctx) && ret;
+	return ret;
 }
 
 SEC("raw_tp/task_rename")
diff --git a/tools/testing/selftests/bpf/progs/test_perf_branches.c b/tools/testing/selftests/bpf/progs/test_perf_branches.c
index 0f7e27d97567..a1ccc831c882 100644
--- a/tools/testing/selftests/bpf/progs/test_perf_branches.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_branches.c
@@ -5,7 +5,7 @@
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 int valid = 0;
 int required_size_out = 0;
diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
index ebfcc9f50c35..ad59c4c9aba8 100644
--- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
@@ -4,7 +4,7 @@
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c
index d556b1572cc6..89b3532ccc75 100644
--- a/tools/testing/selftests/bpf/progs/test_probe_user.c
+++ b/tools/testing/selftests/bpf/progs/test_probe_user.c
@@ -7,7 +7,6 @@
 
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include "bpf_trace_helpers.h"
 
 static struct sockaddr_in old;
 
diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
index 202de3938494..b02ea589ce7e 100644
--- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
@@ -23,6 +23,8 @@ int process(struct __sk_buff *skb)
 		return 1;
 	if (skb->gso_segs != 8)
 		return 1;
+	if (skb->gso_size != 10)
+		return 1;
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_trampoline_count.c b/tools/testing/selftests/bpf/progs/test_trampoline_count.c
index e51e6e3a81c2..f030e469d05b 100644
--- a/tools/testing/selftests/bpf/progs/test_trampoline_count.c
+++ b/tools/testing/selftests/bpf/progs/test_trampoline_count.c
@@ -2,7 +2,8 @@
 #include <stdbool.h>
 #include <stddef.h>
 #include <linux/bpf.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 struct task_struct;
 
diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c
new file mode 100644
index 000000000000..5611b564d3b1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include "vmlinux.h"
+#include <asm/unistd.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+#define MY_TV_NSEC 1337
+
+bool tp_called = false;
+bool raw_tp_called = false;
+bool tp_btf_called = false;
+bool kprobe_called = false;
+bool fentry_called = false;
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int handle__tp(struct trace_event_raw_sys_enter *args)
+{
+	struct __kernel_timespec *ts;
+
+	if (args->id != __NR_nanosleep)
+		return 0;
+
+	ts = (void *)args->args[0];
+	if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC)
+		return 0;
+
+	tp_called = true;
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handle__raw_tp, struct pt_regs *regs, long id)
+{
+	struct __kernel_timespec *ts;
+
+	if (id != __NR_nanosleep)
+		return 0;
+
+	ts = (void *)PT_REGS_PARM1_CORE(regs);
+	if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC)
+		return 0;
+
+	raw_tp_called = true;
+	return 0;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(handle__tp_btf, struct pt_regs *regs, long id)
+{
+	struct __kernel_timespec *ts;
+
+	if (id != __NR_nanosleep)
+		return 0;
+
+	ts = (void *)PT_REGS_PARM1_CORE(regs);
+	if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC)
+		return 0;
+
+	tp_btf_called = true;
+	return 0;
+}
+
+SEC("kprobe/hrtimer_nanosleep")
+int BPF_KPROBE(handle__kprobe,
+	       ktime_t rqtp, enum hrtimer_mode mode, clockid_t clockid)
+{
+	if (rqtp == MY_TV_NSEC)
+		kprobe_called = true;
+	return 0;
+}
+
+SEC("fentry/hrtimer_nanosleep")
+int BPF_PROG(handle__fentry,
+	     ktime_t rqtp, enum hrtimer_mode mode, clockid_t clockid)
+{
+	if (rqtp == MY_TV_NSEC)
+		fentry_called = true;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
index b840fc9e3ed5..a038e827f850 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
@@ -1,7 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
+#include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+
+char _license[] SEC("license") = "GPL";
 
 struct net_device {
 	/* Structure does not need to contain all entries,
@@ -27,10 +29,32 @@ struct xdp_buff {
 	struct xdp_rxq_info *rxq;
 } __attribute__((preserve_access_index));
 
+struct meta {
+	int ifindex;
+	int pkt_len;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} perf_buf_map SEC(".maps");
+
 __u64 test_result_fentry = 0;
 SEC("fentry/FUNC")
 int BPF_PROG(trace_on_entry, struct xdp_buff *xdp)
 {
+	struct meta meta;
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+
+	meta.ifindex = xdp->rxq->dev->ifindex;
+	meta.pkt_len = data_end - data;
+	bpf_xdp_output(xdp, &perf_buf_map,
+		       ((__u64) meta.pkt_len << 32) |
+		       BPF_F_CURRENT_CPU,
+		       &meta, sizeof(meta));
+
 	test_result_fentry = xdp->rxq->dev->ifindex;
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c b/tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c
new file mode 100644
index 000000000000..ed253f252cd0
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Carlos Neira cneirabustos@gmail.com */
+#define _GNU_SOURCE
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sched.h>
+#include <sys/wait.h>
+#include <sys/mount.h>
+#include "test_progs.h"
+
+#define CHECK_NEWNS(condition, tag, format...) ({		\
+	int __ret = !!(condition);			\
+	if (__ret) {					\
+		printf("%s:FAIL:%s ", __func__, tag);	\
+		printf(format);				\
+	} else {					\
+		printf("%s:PASS:%s\n", __func__, tag);	\
+	}						\
+	__ret;						\
+})
+
+struct bss {
+	__u64 dev;
+	__u64 ino;
+	__u64 pid_tgid;
+	__u64 user_pid_tgid;
+};
+
+int main(int argc, char **argv)
+{
+	pid_t pid;
+	int exit_code = 1;
+	struct stat st;
+
+	printf("Testing bpf_get_ns_current_pid_tgid helper in new ns\n");
+
+	if (stat("/proc/self/ns/pid", &st)) {
+		perror("stat failed on /proc/self/ns/pid ns\n");
+		printf("%s:FAILED\n", argv[0]);
+		return exit_code;
+	}
+
+	if (CHECK_NEWNS(unshare(CLONE_NEWPID | CLONE_NEWNS),
+			"unshare CLONE_NEWPID | CLONE_NEWNS", "error errno=%d\n", errno))
+		return exit_code;
+
+	pid = fork();
+	if (pid == -1) {
+		perror("Fork() failed\n");
+		printf("%s:FAILED\n", argv[0]);
+		return exit_code;
+	}
+
+	if (pid > 0) {
+		int status;
+
+		usleep(5);
+		waitpid(pid, &status, 0);
+		return 0;
+	} else {
+
+		pid = fork();
+		if (pid == -1) {
+			perror("Fork() failed\n");
+			printf("%s:FAILED\n", argv[0]);
+			return exit_code;
+		}
+
+		if (pid > 0) {
+			int status;
+			waitpid(pid, &status, 0);
+			return 0;
+		} else {
+			if (CHECK_NEWNS(mount("none", "/proc", NULL, MS_PRIVATE|MS_REC, NULL),
+				"Unmounting proc", "Cannot umount proc! errno=%d\n", errno))
+				return exit_code;
+
+			if (CHECK_NEWNS(mount("proc", "/proc", "proc", MS_NOSUID|MS_NOEXEC|MS_NODEV, NULL),
+				"Mounting proc", "Cannot mount proc! errno=%d\n", errno))
+				return exit_code;
+
+			const char *probe_name = "raw_tracepoint/sys_enter";
+			const char *file = "test_ns_current_pid_tgid.o";
+			struct bpf_link *link = NULL;
+			struct bpf_program *prog;
+			struct bpf_map *bss_map;
+			struct bpf_object *obj;
+			int exit_code = 1;
+			int err, key = 0;
+			struct bss bss;
+			struct stat st;
+			__u64 id;
+
+			obj = bpf_object__open_file(file, NULL);
+			if (CHECK_NEWNS(IS_ERR(obj), "obj_open", "err %ld\n", PTR_ERR(obj)))
+				return exit_code;
+
+			err = bpf_object__load(obj);
+			if (CHECK_NEWNS(err, "obj_load", "err %d errno %d\n", err, errno))
+				goto cleanup;
+
+			bss_map = bpf_object__find_map_by_name(obj, "test_ns_.bss");
+			if (CHECK_NEWNS(!bss_map, "find_bss_map", "failed\n"))
+				goto cleanup;
+
+			prog = bpf_object__find_program_by_title(obj, probe_name);
+			if (CHECK_NEWNS(!prog, "find_prog", "prog '%s' not found\n",
+						probe_name))
+				goto cleanup;
+
+			memset(&bss, 0, sizeof(bss));
+			pid_t tid = syscall(SYS_gettid);
+			pid_t pid = getpid();
+
+			id = (__u64) tid << 32 | pid;
+			bss.user_pid_tgid = id;
+
+			if (CHECK_NEWNS(stat("/proc/self/ns/pid", &st),
+				"stat new ns", "Failed to stat /proc/self/ns/pid errno=%d\n", errno))
+				goto cleanup;
+
+			bss.dev = st.st_dev;
+			bss.ino = st.st_ino;
+
+			err = bpf_map_update_elem(bpf_map__fd(bss_map), &key, &bss, 0);
+			if (CHECK_NEWNS(err, "setting_bss", "failed to set bss : %d\n", err))
+				goto cleanup;
+
+			link = bpf_program__attach_raw_tracepoint(prog, "sys_enter");
+			if (CHECK_NEWNS(IS_ERR(link), "attach_raw_tp", "err %ld\n",
+						PTR_ERR(link))) {
+				link = NULL;
+				goto cleanup;
+			}
+
+			/* trigger some syscalls */
+			usleep(1);
+
+			err = bpf_map_lookup_elem(bpf_map__fd(bss_map), &key, &bss);
+			if (CHECK_NEWNS(err, "set_bss", "failed to get bss : %d\n", err))
+				goto cleanup;
+
+			if (CHECK_NEWNS(id != bss.pid_tgid, "Compare user pid/tgid vs. bpf pid/tgid",
+						"User pid/tgid %llu BPF pid/tgid %llu\n", id, bss.pid_tgid))
+				goto cleanup;
+
+			exit_code = 0;
+			printf("%s:PASS\n", argv[0]);
+cleanup:
+			if (!link) {
+				bpf_link__destroy(link);
+				link = NULL;
+			}
+			bpf_object__close(obj);
+		}
+	}
+}
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index a969c77e9456..f85a06512541 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -29,6 +29,24 @@ struct prog_test_def {
 	int old_error_cnt;
 };
 
+/* Override C runtime library's usleep() implementation to ensure nanosleep()
+ * is always called. Usleep is frequently used in selftests as a way to
+ * trigger kprobe and tracepoints.
+ */
+int usleep(useconds_t usec)
+{
+	struct timespec ts;
+
+	if (usec > 999999) {
+		ts.tv_sec = usec / 1000000;
+		ts.tv_nsec = usec % 1000000;
+	} else {
+		ts.tv_sec = 0;
+		ts.tv_nsec = usec;
+	}
+	return nanosleep(&ts, NULL);
+}
+
 static bool should_run(struct test_selector *sel, int num, const char *name)
 {
 	int i;
@@ -198,7 +216,7 @@ int bpf_find_map(const char *test, struct bpf_object *obj, const char *name)
 
 	map = bpf_object__find_map_by_name(obj, name);
 	if (!map) {
-		printf("%s:FAIL:map '%s' not found\n", test, name);
+		fprintf(stdout, "%s:FAIL:map '%s' not found\n", test, name);
 		test__fail();
 		return -1;
 	}
@@ -369,7 +387,7 @@ static int libbpf_print_fn(enum libbpf_print_level level,
 {
 	if (env.verbosity < VERBOSE_VERY && level == LIBBPF_DEBUG)
 		return 0;
-	vprintf(format, args);
+	vfprintf(stdout, format, args);
 	return 0;
 }
 
@@ -615,7 +633,7 @@ int cd_flavor_subdir(const char *exec_name)
 	if (!flavor)
 		return 0;
 	flavor++;
-	printf("Switching to flavor '%s' subdirectory...\n", flavor);
+	fprintf(stdout, "Switching to flavor '%s' subdirectory...\n", flavor);
 	return chdir(flavor);
 }
 
@@ -698,8 +716,8 @@ int main(int argc, char **argv)
 			cleanup_cgroup_environment();
 	}
 	stdio_restore();
-	printf("Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n",
-	       env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt);
+	fprintf(stdout, "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);
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index bcfa9ef23fda..fd85fa61dbf7 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -109,10 +109,10 @@ extern struct ipv6_packet pkt_v6;
 	int __save_errno = errno;					\
 	if (__ret) {							\
 		test__fail();						\
-		printf("%s:FAIL:%s ", __func__, tag);			\
-		printf(format);						\
+		fprintf(stdout, "%s:FAIL:%s ", __func__, tag);		\
+		fprintf(stdout, ##format);				\
 	} else {							\
-		printf("%s:PASS:%s %d nsec\n",				\
+		fprintf(stdout, "%s:PASS:%s %d nsec\n",			\
 		       __func__, tag, duration);			\
 	}								\
 	errno = __save_errno;						\
@@ -124,7 +124,7 @@ extern struct ipv6_packet pkt_v6;
 	int __save_errno = errno;					\
 	if (__ret) {							\
 		test__fail();						\
-		printf("%s:FAIL:%d\n", __func__, __LINE__);		\
+		fprintf(stdout, "%s:FAIL:%d\n", __func__, __LINE__);	\
 	}								\
 	errno = __save_errno;						\
 	__ret;								\
diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c
index d438193804b2..2e16b8e268f2 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_skb.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c
@@ -1011,6 +1011,53 @@
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 },
 {
+	"read gso_size from CGROUP_SKB",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+		    offsetof(struct __sk_buff, gso_size)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+},
+{
+	"read gso_size from CGROUP_SKB",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+		    offsetof(struct __sk_buff, gso_size)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+},
+{
+	"write gso_size from CGROUP_SKB",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+		    offsetof(struct __sk_buff, gso_size)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.result_unpriv = REJECT,
+	.errstr = "invalid bpf_context access off=176 size=4",
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+},
+{
+	"read gso_size from CLS",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+		    offsetof(struct __sk_buff, gso_size)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
+{
 	"check wire_len is not readable by sockets",
 	.insns = {
 		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,