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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-11-26

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

The main changes are:

1) Extend BTF to support function call types and improve the BPF
   symbol handling with this info for kallsyms and bpftool program
   dump to make debugging easier, from Martin and Yonghong.

2) Optimize LPM lookups by making longest_prefix_match() handle
   multiple bytes at a time, from Eric.

3) Adds support for loading and attaching flow dissector BPF progs
   from bpftool, from Stanislav.

4) Extend the sk_lookup() helper to be supported from XDP, from Nitin.

5) Enable verifier to support narrow context loads with offset > 0
   to adapt to LLVM code generation (currently only offset of 0 was
   supported). Add test cases as well, from Andrey.

6) Simplify passing device functions for offloaded BPF progs by
   adding callbacks to bpf_prog_offload_ops instead of ndo_bpf.
   Also convert nfp and netdevsim to make use of them, from Quentin.

7) Add support for sock_ops based BPF programs to send events to
   the perf ring-buffer through perf_event_output helper, from
   Sowmini and Daniel.

8) Add read / write support for skb->tstamp from tc BPF and cg BPF
   programs to allow for supporting rate-limiting in EDT qdiscs
   like fq from BPF side, from Vlad.

9) Extend libbpf API to support map in map types and add test cases
   for it as well to BPF kselftests, from Nikita.

10) Account the maximum packet offset accessed by a BPF program in
    the verifier and use it for optimizing nfp JIT, from Jiong.

11) Fix error handling regarding kprobe_events in BPF sample loader,
    from Daniel T.

12) Add support for queue and stack map type in bpftool, from David.
====================

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

40 files changed, 3202 insertions, 331 deletions

diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index f55a2daed59b..9e827e342d9e 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -42,7 +42,8 @@ MAP COMMANDS
 |		| **percpu_array** | **stack_trace** | **cgroup_array** | **lru_hash**
 |		| **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps**
 |		| **devmap** | **sockmap** | **cpumap** | **xskmap** | **sockhash**
-|		| **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** }
+|		| **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage**
+|		| **queue** | **stack** }
 
 DESCRIPTION
 ===========
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index ac4e904b10fb..8db78ed82a71 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -15,7 +15,8 @@ SYNOPSIS
 	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } }
 
 	*COMMANDS* :=
-	{ **show** | **list** | **dump xlated** | **dump jited** | **pin** | **load** | **help** }
+	{ **show** | **list** | **dump xlated** | **dump jited** | **pin** | **load**
+	| **loadall** | **help** }
 
 MAP COMMANDS
 =============
@@ -24,9 +25,9 @@ MAP COMMANDS
 |	**bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}]
 |	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
 |	**bpftool** **prog pin** *PROG* *FILE*
-|	**bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
-|       **bpftool** **prog attach** *PROG* *ATTACH_TYPE* *MAP*
-|       **bpftool** **prog detach** *PROG* *ATTACH_TYPE* *MAP*
+|	**bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
+|       **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*]
+|       **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*]
 |	**bpftool** **prog help**
 |
 |	*MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
@@ -39,7 +40,9 @@ MAP COMMANDS
 |		**cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
 |		**cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6**
 |	}
-|       *ATTACH_TYPE* := { **msg_verdict** | **skb_verdict** | **skb_parse** }
+|       *ATTACH_TYPE* := {
+|		**msg_verdict** | **skb_verdict** | **skb_parse** | **flow_dissector**
+|	}
 
 
 DESCRIPTION
@@ -79,8 +82,11 @@ DESCRIPTION
 		  contain a dot character ('.'), which is reserved for future
 		  extensions of *bpffs*.
 
-	**bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
-		  Load bpf program from binary *OBJ* and pin as *FILE*.
+	**bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*]
+		  Load bpf program(s) from binary *OBJ* and pin as *PATH*.
+		  **bpftool prog load** pins only the first program from the
+		  *OBJ* as *PATH*. **bpftool prog loadall** pins all programs
+		  from the *OBJ* under *PATH* directory.
 		  **type** is optional, if not specified program type will be
 		  inferred from section names.
 		  By default bpftool will create new maps as declared in the ELF
@@ -92,18 +98,24 @@ DESCRIPTION
 		  use, referring to it by **id** or through a **pinned** file.
 		  If **dev** *NAME* is specified program will be loaded onto
 		  given networking device (offload).
+		  Optional **pinmaps** argument can be provided to pin all
+		  maps under *MAP_DIR* directory.
 
-		  Note: *FILE* must be located in *bpffs* mount. It must not
+		  Note: *PATH* must be located in *bpffs* mount. It must not
 		  contain a dot character ('.'), which is reserved for future
 		  extensions of *bpffs*.
 
-        **bpftool prog attach** *PROG* *ATTACH_TYPE* *MAP*
-                  Attach bpf program *PROG* (with type specified by *ATTACH_TYPE*)
-                  to the map *MAP*.
-
-        **bpftool prog detach** *PROG* *ATTACH_TYPE* *MAP*
-                  Detach bpf program *PROG* (with type specified by *ATTACH_TYPE*)
-                  from the map *MAP*.
+	**bpftool prog attach** *PROG* *ATTACH_TYPE* [*MAP*]
+		  Attach bpf program *PROG* (with type specified by
+		  *ATTACH_TYPE*). Most *ATTACH_TYPEs* require a *MAP*
+		  parameter, with the exception of *flow_dissector* which is
+		  attached to current networking name space.
+
+	**bpftool prog detach** *PROG* *ATTACH_TYPE* [*MAP*]
+		  Detach bpf program *PROG* (with type specified by
+		  *ATTACH_TYPE*). Most *ATTACH_TYPEs* require a *MAP*
+		  parameter, with the exception of *flow_dissector* which is
+		  detached from the current networking name space.
 
 	**bpftool prog help**
 		  Print short help message.
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index dac7eff4c7e5..1bea6b979082 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -53,7 +53,7 @@ ifneq ($(EXTRA_LDFLAGS),)
 LDFLAGS += $(EXTRA_LDFLAGS)
 endif
 
-LIBS = -lelf -lbfd -lopcodes $(LIBBPF)
+LIBS = -lelf $(LIBBPF)
 
 INSTALL ?= install
 RM ?= rm -f
@@ -90,7 +90,16 @@ include $(wildcard $(OUTPUT)*.d)
 
 all: $(OUTPUT)bpftool
 
-SRCS = $(wildcard *.c)
+BFD_SRCS = jit_disasm.c
+
+SRCS = $(filter-out $(BFD_SRCS),$(wildcard *.c))
+
+ifeq ($(feature-libbfd),1)
+CFLAGS += -DHAVE_LIBBFD_SUPPORT
+SRCS += $(BFD_SRCS)
+LIBS += -lbfd -lopcodes
+endif
+
 OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
 
 $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 3f78e6404589..45c2db257d2b 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -243,7 +243,7 @@ _bpftool()
     # Completion depends on object and command in use
     case $object in
         prog)
-            if [[ $command != "load" ]]; then
+            if [[ $command != "load" && $command != "loadall" ]]; then
                 case $prev in
                     id)
                         _bpftool_get_prog_ids
@@ -299,7 +299,8 @@ _bpftool()
                     fi
 
                     if [[ ${#words[@]} == 6 ]]; then
-                        COMPREPLY=( $( compgen -W "msg_verdict skb_verdict skb_parse" -- "$cur" ) )
+                        COMPREPLY=( $( compgen -W "msg_verdict skb_verdict \
+                            skb_parse flow_dissector" -- "$cur" ) )
                         return 0
                     fi
 
@@ -309,7 +310,7 @@ _bpftool()
                     fi
                     return 0
                     ;;
-                load)
+                load|loadall)
                     local obj
 
                     if [[ ${#words[@]} -lt 6 ]]; then
@@ -338,7 +339,16 @@ _bpftool()
 
                     case $prev in
                         type)
-                            COMPREPLY=( $( compgen -W "socket kprobe kretprobe classifier action tracepoint raw_tracepoint xdp perf_event cgroup/skb cgroup/sock cgroup/dev lwt_in lwt_out lwt_xmit lwt_seg6local sockops sk_skb sk_msg lirc_mode2 cgroup/bind4 cgroup/bind6 cgroup/connect4 cgroup/connect6 cgroup/sendmsg4 cgroup/sendmsg6 cgroup/post_bind4 cgroup/post_bind6" -- \
+                            COMPREPLY=( $( compgen -W "socket kprobe \
+                                kretprobe classifier flow_dissector \
+                                action tracepoint raw_tracepoint \
+                                xdp perf_event cgroup/skb cgroup/sock \
+                                cgroup/dev lwt_in lwt_out lwt_xmit \
+                                lwt_seg6local sockops sk_skb sk_msg \
+                                lirc_mode2 cgroup/bind4 cgroup/bind6 \
+                                cgroup/connect4 cgroup/connect6 \
+                                cgroup/sendmsg4 cgroup/sendmsg6 \
+                                cgroup/post_bind4 cgroup/post_bind6" -- \
                                                    "$cur" ) )
                             return 0
                             ;;
@@ -346,7 +356,7 @@ _bpftool()
                             _bpftool_get_map_ids
                             return 0
                             ;;
-                        pinned)
+                        pinned|pinmaps)
                             _filedir
                             return 0
                             ;;
@@ -358,6 +368,7 @@ _bpftool()
                             COMPREPLY=( $( compgen -W "map" -- "$cur" ) )
                             _bpftool_once_attr 'type'
                             _bpftool_once_attr 'dev'
+                            _bpftool_once_attr 'pinmaps'
                             return 0
                             ;;
                     esac
diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index 55bc512a1831..c3fd3a7cb787 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -249,3 +249,139 @@ int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
 {
 	return btf_dumper_do_type(d, type_id, 0, data);
 }
+
+#define BTF_PRINT_ARG(...)						\
+	do {								\
+		pos += snprintf(func_sig + pos, size - pos,		\
+				__VA_ARGS__);				\
+		if (pos >= size)					\
+			return -1;					\
+	} while (0)
+#define BTF_PRINT_TYPE(type)					\
+	do {								\
+		pos = __btf_dumper_type_only(btf, type, func_sig,	\
+					     pos, size);		\
+		if (pos == -1)						\
+			return -1;					\
+	} while (0)
+
+static int btf_dump_func(const struct btf *btf, char *func_sig,
+			 const struct btf_type *func_proto,
+			 const struct btf_type *func, int pos, int size);
+
+static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id,
+				  char *func_sig, int pos, int size)
+{
+	const struct btf_type *proto_type;
+	const struct btf_array *array;
+	const struct btf_type *t;
+
+	if (!type_id) {
+		BTF_PRINT_ARG("void ");
+		return pos;
+	}
+
+	t = btf__type_by_id(btf, type_id);
+
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_INT:
+		BTF_PRINT_ARG("%s ", btf__name_by_offset(btf, t->name_off));
+		break;
+	case BTF_KIND_STRUCT:
+		BTF_PRINT_ARG("struct %s ",
+			      btf__name_by_offset(btf, t->name_off));
+		break;
+	case BTF_KIND_UNION:
+		BTF_PRINT_ARG("union %s ",
+			      btf__name_by_offset(btf, t->name_off));
+		break;
+	case BTF_KIND_ENUM:
+		BTF_PRINT_ARG("enum %s ",
+			      btf__name_by_offset(btf, t->name_off));
+		break;
+	case BTF_KIND_ARRAY:
+		array = (struct btf_array *)(t + 1);
+		BTF_PRINT_TYPE(array->type);
+		BTF_PRINT_ARG("[%d]", array->nelems);
+		break;
+	case BTF_KIND_PTR:
+		BTF_PRINT_TYPE(t->type);
+		BTF_PRINT_ARG("* ");
+		break;
+	case BTF_KIND_UNKN:
+	case BTF_KIND_FWD:
+	case BTF_KIND_TYPEDEF:
+		return -1;
+	case BTF_KIND_VOLATILE:
+		BTF_PRINT_ARG("volatile ");
+		BTF_PRINT_TYPE(t->type);
+		break;
+	case BTF_KIND_CONST:
+		BTF_PRINT_ARG("const ");
+		BTF_PRINT_TYPE(t->type);
+		break;
+	case BTF_KIND_RESTRICT:
+		BTF_PRINT_ARG("restrict ");
+		BTF_PRINT_TYPE(t->type);
+		break;
+	case BTF_KIND_FUNC_PROTO:
+		pos = btf_dump_func(btf, func_sig, t, NULL, pos, size);
+		if (pos == -1)
+			return -1;
+		break;
+	case BTF_KIND_FUNC:
+		proto_type = btf__type_by_id(btf, t->type);
+		pos = btf_dump_func(btf, func_sig, proto_type, t, pos, size);
+		if (pos == -1)
+			return -1;
+		break;
+	default:
+		return -1;
+	}
+
+	return pos;
+}
+
+static int btf_dump_func(const struct btf *btf, char *func_sig,
+			 const struct btf_type *func_proto,
+			 const struct btf_type *func, int pos, int size)
+{
+	int i, vlen;
+
+	BTF_PRINT_TYPE(func_proto->type);
+	if (func)
+		BTF_PRINT_ARG("%s(", btf__name_by_offset(btf, func->name_off));
+	else
+		BTF_PRINT_ARG("(");
+	vlen = BTF_INFO_VLEN(func_proto->info);
+	for (i = 0; i < vlen; i++) {
+		struct btf_param *arg = &((struct btf_param *)(func_proto + 1))[i];
+
+		if (i)
+			BTF_PRINT_ARG(", ");
+		if (arg->type) {
+			BTF_PRINT_TYPE(arg->type);
+			BTF_PRINT_ARG("%s",
+				      btf__name_by_offset(btf, arg->name_off));
+		} else {
+			BTF_PRINT_ARG("...");
+		}
+	}
+	BTF_PRINT_ARG(")");
+
+	return pos;
+}
+
+void btf_dumper_type_only(const struct btf *btf, __u32 type_id, char *func_sig,
+			  int size)
+{
+	int err;
+
+	func_sig[0] = '\0';
+	if (!btf)
+		return;
+
+	err = __btf_dumper_type_only(btf, type_id, func_sig, 0, size);
+	if (err < 0)
+		func_sig[0] = '\0';
+}
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 25af85304ebe..cb06a5b6e016 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -46,6 +46,7 @@
 #include <linux/magic.h>
 #include <net/if.h>
 #include <sys/mount.h>
+#include <sys/resource.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/vfs.h>
@@ -99,6 +100,13 @@ static bool is_bpffs(char *path)
 	return (unsigned long)st_fs.f_type == BPF_FS_MAGIC;
 }
 
+void set_max_rlimit(void)
+{
+	struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
+
+	setrlimit(RLIMIT_MEMLOCK, &rinf);
+}
+
 static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
 {
 	bool bind_done = false;
@@ -169,34 +177,23 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
 	return fd;
 }
 
-int do_pin_fd(int fd, const char *name)
+int mount_bpffs_for_pin(const char *name)
 {
 	char err_str[ERR_MAX_LEN];
 	char *file;
 	char *dir;
 	int err = 0;
 
-	err = bpf_obj_pin(fd, name);
-	if (!err)
-		goto out;
-
 	file = malloc(strlen(name) + 1);
 	strcpy(file, name);
 	dir = dirname(file);
 
-	if (errno != EPERM || is_bpffs(dir)) {
-		p_err("can't pin the object (%s): %s", name, strerror(errno));
+	if (is_bpffs(dir))
+		/* nothing to do if already mounted */
 		goto out_free;
-	}
 
-	/* Attempt to mount bpffs, then retry pinning. */
 	err = mnt_bpffs(dir, err_str, ERR_MAX_LEN);
-	if (!err) {
-		err = bpf_obj_pin(fd, name);
-		if (err)
-			p_err("can't pin the object (%s): %s", name,
-			      strerror(errno));
-	} else {
+	if (err) {
 		err_str[ERR_MAX_LEN - 1] = '\0';
 		p_err("can't mount BPF file system to pin the object (%s): %s",
 		      name, err_str);
@@ -204,10 +201,20 @@ int do_pin_fd(int fd, const char *name)
 
 out_free:
 	free(file);
-out:
 	return err;
 }
 
+int do_pin_fd(int fd, const char *name)
+{
+	int err;
+
+	err = mount_bpffs_for_pin(name);
+	if (err)
+		return err;
+
+	return bpf_obj_pin(fd, name);
+}
+
 int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 {
 	unsigned int id;
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index c75ffd9ce2bb..b2ed5ee1af5f 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -109,7 +109,7 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 		if (inf) {
 			bfdf->arch_info = inf;
 		} else {
-			p_err("No libfd support for %s", arch);
+			p_err("No libbfd support for %s", arch);
 			return;
 		}
 	}
@@ -183,3 +183,9 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 
 	bfd_close(bfdf);
 }
+
+int disasm_init(void)
+{
+	bfd_init();
+	return 0;
+}
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 75a3296dc0bc..5c4c1cd5a7ba 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -31,7 +31,6 @@
  * SOFTWARE.
  */
 
-#include <bfd.h>
 #include <ctype.h>
 #include <errno.h>
 #include <getopt.h>
@@ -399,8 +398,6 @@ int main(int argc, char **argv)
 	if (argc < 0)
 		usage();
 
-	bfd_init();
-
 	ret = cmd_select(cmds, argc, argv, do_help);
 
 	if (json_output)
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 28322ace2856..3e8979567cf1 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -100,6 +100,8 @@ bool is_prefix(const char *pfx, const char *str);
 void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep);
 void usage(void) __noreturn;
 
+void set_max_rlimit(void);
+
 struct pinned_obj_table {
 	DECLARE_HASHTABLE(table, 16);
 };
@@ -129,6 +131,7 @@ const char *get_fd_type_name(enum bpf_obj_type type);
 char *get_fdinfo(int fd, const char *key);
 int open_obj_pinned(char *path);
 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_fd(int fd, const char *name);
 
@@ -144,8 +147,22 @@ int prog_parse_fd(int *argc, char ***argv);
 int map_parse_fd(int *argc, char ***argv);
 int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
 
+#ifdef HAVE_LIBBFD_SUPPORT
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 		       const char *arch, const char *disassembler_options);
+int disasm_init(void);
+#else
+static inline
+void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
+		       const char *arch, const char *disassembler_options)
+{
+}
+static inline int disasm_init(void)
+{
+	p_err("No libbfd support");
+	return -1;
+}
+#endif
 void print_data_json(uint8_t *data, size_t len);
 void print_hex_data_json(uint8_t *data, size_t len);
 
@@ -170,6 +187,8 @@ struct btf_dumper {
  */
 int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
 		    const void *data);
+void btf_dumper_type_only(const struct btf *btf, __u32 func_type_id,
+			  char *func_only, int size);
 
 struct nlattr;
 struct ifinfomsg;
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 7bf38f0e152e..cbd3080e72c7 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -52,28 +52,30 @@
 #include "main.h"
 
 static const char * const map_type_name[] = {
-	[BPF_MAP_TYPE_UNSPEC]		= "unspec",
-	[BPF_MAP_TYPE_HASH]		= "hash",
-	[BPF_MAP_TYPE_ARRAY]		= "array",
-	[BPF_MAP_TYPE_PROG_ARRAY]	= "prog_array",
-	[BPF_MAP_TYPE_PERF_EVENT_ARRAY]	= "perf_event_array",
-	[BPF_MAP_TYPE_PERCPU_HASH]	= "percpu_hash",
-	[BPF_MAP_TYPE_PERCPU_ARRAY]	= "percpu_array",
-	[BPF_MAP_TYPE_STACK_TRACE]	= "stack_trace",
-	[BPF_MAP_TYPE_CGROUP_ARRAY]	= "cgroup_array",
-	[BPF_MAP_TYPE_LRU_HASH]		= "lru_hash",
-	[BPF_MAP_TYPE_LRU_PERCPU_HASH]	= "lru_percpu_hash",
-	[BPF_MAP_TYPE_LPM_TRIE]		= "lpm_trie",
-	[BPF_MAP_TYPE_ARRAY_OF_MAPS]	= "array_of_maps",
-	[BPF_MAP_TYPE_HASH_OF_MAPS]	= "hash_of_maps",
-	[BPF_MAP_TYPE_DEVMAP]		= "devmap",
-	[BPF_MAP_TYPE_SOCKMAP]		= "sockmap",
-	[BPF_MAP_TYPE_CPUMAP]		= "cpumap",
-	[BPF_MAP_TYPE_XSKMAP]           = "xskmap",
-	[BPF_MAP_TYPE_SOCKHASH]		= "sockhash",
-	[BPF_MAP_TYPE_CGROUP_STORAGE]	= "cgroup_storage",
-	[BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray",
+	[BPF_MAP_TYPE_UNSPEC]			= "unspec",
+	[BPF_MAP_TYPE_HASH]			= "hash",
+	[BPF_MAP_TYPE_ARRAY]			= "array",
+	[BPF_MAP_TYPE_PROG_ARRAY]		= "prog_array",
+	[BPF_MAP_TYPE_PERF_EVENT_ARRAY]		= "perf_event_array",
+	[BPF_MAP_TYPE_PERCPU_HASH]		= "percpu_hash",
+	[BPF_MAP_TYPE_PERCPU_ARRAY]		= "percpu_array",
+	[BPF_MAP_TYPE_STACK_TRACE]		= "stack_trace",
+	[BPF_MAP_TYPE_CGROUP_ARRAY]		= "cgroup_array",
+	[BPF_MAP_TYPE_LRU_HASH]			= "lru_hash",
+	[BPF_MAP_TYPE_LRU_PERCPU_HASH]		= "lru_percpu_hash",
+	[BPF_MAP_TYPE_LPM_TRIE]			= "lpm_trie",
+	[BPF_MAP_TYPE_ARRAY_OF_MAPS]		= "array_of_maps",
+	[BPF_MAP_TYPE_HASH_OF_MAPS]		= "hash_of_maps",
+	[BPF_MAP_TYPE_DEVMAP]			= "devmap",
+	[BPF_MAP_TYPE_SOCKMAP]			= "sockmap",
+	[BPF_MAP_TYPE_CPUMAP]			= "cpumap",
+	[BPF_MAP_TYPE_XSKMAP]			= "xskmap",
+	[BPF_MAP_TYPE_SOCKHASH]			= "sockhash",
+	[BPF_MAP_TYPE_CGROUP_STORAGE]		= "cgroup_storage",
+	[BPF_MAP_TYPE_REUSEPORT_SOCKARRAY]	= "reuseport_sockarray",
 	[BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE]	= "percpu_cgroup_storage",
+	[BPF_MAP_TYPE_QUEUE]			= "queue",
+	[BPF_MAP_TYPE_STACK]			= "stack",
 };
 
 static bool map_is_per_cpu(__u32 type)
@@ -215,70 +217,6 @@ err_end_obj:
 	return ret;
 }
 
-static int get_btf(struct bpf_map_info *map_info, struct btf **btf)
-{
-	struct bpf_btf_info btf_info = { 0 };
-	__u32 len = sizeof(btf_info);
-	__u32 last_size;
-	int btf_fd;
-	void *ptr;
-	int err;
-
-	err = 0;
-	*btf = NULL;
-	btf_fd = bpf_btf_get_fd_by_id(map_info->btf_id);
-	if (btf_fd < 0)
-		return 0;
-
-	/* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so
-	 * let's start with a sane default - 4KiB here - and resize it only if
-	 * bpf_obj_get_info_by_fd() needs a bigger buffer.
-	 */
-	btf_info.btf_size = 4096;
-	last_size = btf_info.btf_size;
-	ptr = malloc(last_size);
-	if (!ptr) {
-		err = -ENOMEM;
-		goto exit_free;
-	}
-
-	bzero(ptr, last_size);
-	btf_info.btf = ptr_to_u64(ptr);
-	err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
-
-	if (!err && btf_info.btf_size > last_size) {
-		void *temp_ptr;
-
-		last_size = btf_info.btf_size;
-		temp_ptr = realloc(ptr, last_size);
-		if (!temp_ptr) {
-			err = -ENOMEM;
-			goto exit_free;
-		}
-		ptr = temp_ptr;
-		bzero(ptr, last_size);
-		btf_info.btf = ptr_to_u64(ptr);
-		err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
-	}
-
-	if (err || btf_info.btf_size > last_size) {
-		err = errno;
-		goto exit_free;
-	}
-
-	*btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL);
-	if (IS_ERR(*btf)) {
-		err = PTR_ERR(*btf);
-		*btf = NULL;
-	}
-
-exit_free:
-	close(btf_fd);
-	free(ptr);
-
-	return err;
-}
-
 static json_writer_t *get_btf_writer(void)
 {
 	json_writer_t *jw = jsonw_new(stdout);
@@ -383,7 +321,10 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
 		printf(single_line ? "  " : "\n");
 
 		printf("value:%c", break_names ? '\n' : ' ');
-		fprint_hex(stdout, value, info->value_size, " ");
+		if (value)
+			fprint_hex(stdout, value, info->value_size, " ");
+		else
+			printf("<no entry>");
 
 		printf("\n");
 	} else {
@@ -398,8 +339,11 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
 		for (i = 0; i < n; i++) {
 			printf("value (CPU %02d):%c",
 			       i, info->value_size > 16 ? '\n' : ' ');
-			fprint_hex(stdout, value + i * step,
-				   info->value_size, " ");
+			if (value)
+				fprint_hex(stdout, value + i * step,
+					   info->value_size, " ");
+			else
+				printf("<no entry>");
 			printf("\n");
 		}
 	}
@@ -731,7 +675,11 @@ static int dump_map_elem(int fd, void *key, void *value,
 		jsonw_string_field(json_wtr, "error", strerror(lookup_errno));
 		jsonw_end_object(json_wtr);
 	} else {
-		print_entry_error(map_info, key, strerror(lookup_errno));
+		if (errno == ENOENT)
+			print_entry_plain(map_info, key, NULL);
+		else
+			print_entry_error(map_info, key,
+					  strerror(lookup_errno));
 	}
 
 	return 0;
@@ -765,7 +713,7 @@ static int do_dump(int argc, char **argv)
 
 	prev_key = NULL;
 
-	err = get_btf(&info, &btf);
+	err = btf_get_from_id(info.btf_id, &btf);
 	if (err) {
 		p_err("failed to get btf");
 		goto exit_free;
@@ -909,7 +857,7 @@ static int do_lookup(int argc, char **argv)
 	}
 
 	/* here means bpf_map_lookup_elem() succeeded */
-	err = get_btf(&info, &btf);
+	err = btf_get_from_id(info.btf_id, &btf);
 	if (err) {
 		p_err("failed to get btf");
 		goto exit_free;
@@ -1140,6 +1088,8 @@ static int do_create(int argc, char **argv)
 		return -1;
 	}
 
+	set_max_rlimit();
+
 	fd = bpf_create_map_xattr(&attr);
 	if (fd < 0) {
 		p_err("map create failed: %s", strerror(errno));
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 5302ee282409..37b1daf19da6 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -47,6 +47,7 @@
 #include <linux/err.h>
 
 #include <bpf.h>
+#include <btf.h>
 #include <libbpf.h>
 
 #include "cfg.h"
@@ -81,6 +82,7 @@ static const char * const attach_type_strings[] = {
 	[BPF_SK_SKB_STREAM_PARSER] = "stream_parser",
 	[BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict",
 	[BPF_SK_MSG_VERDICT] = "msg_verdict",
+	[BPF_FLOW_DISSECTOR] = "flow_dissector",
 	[__MAX_BPF_ATTACH_TYPE] = NULL,
 };
 
@@ -450,14 +452,19 @@ static int do_dump(int argc, char **argv)
 	struct bpf_prog_info info = {};
 	unsigned int *func_lens = NULL;
 	const char *disasm_opt = NULL;
+	unsigned int finfo_rec_size;
 	unsigned int nr_func_ksyms;
 	unsigned int nr_func_lens;
 	struct dump_data dd = {};
 	__u32 len = sizeof(info);
+	struct btf *btf = NULL;
+	void *func_info = NULL;
+	unsigned int finfo_cnt;
 	unsigned int buf_size;
 	char *filepath = NULL;
 	bool opcodes = false;
 	bool visual = false;
+	char func_sig[1024];
 	unsigned char *buf;
 	__u32 *member_len;
 	__u64 *member_ptr;
@@ -466,6 +473,9 @@ static int do_dump(int argc, char **argv)
 	int fd;
 
 	if (is_prefix(*argv, "jited")) {
+		if (disasm_init())
+			return -1;
+
 		member_len = &info.jited_prog_len;
 		member_ptr = &info.jited_prog_insns;
 	} else if (is_prefix(*argv, "xlated")) {
@@ -547,6 +557,17 @@ static int do_dump(int argc, char **argv)
 		}
 	}
 
+	finfo_cnt = info.func_info_cnt;
+	finfo_rec_size = info.func_info_rec_size;
+	if (finfo_cnt && finfo_rec_size) {
+		func_info = malloc(finfo_cnt * finfo_rec_size);
+		if (!func_info) {
+			p_err("mem alloc failed");
+			close(fd);
+			goto err_free;
+		}
+	}
+
 	memset(&info, 0, sizeof(info));
 
 	*member_ptr = ptr_to_u64(buf);
@@ -555,6 +576,9 @@ static int do_dump(int argc, char **argv)
 	info.nr_jited_ksyms = nr_func_ksyms;
 	info.jited_func_lens = ptr_to_u64(func_lens);
 	info.nr_jited_func_lens = nr_func_lens;
+	info.func_info_cnt = finfo_cnt;
+	info.func_info_rec_size = finfo_rec_size;
+	info.func_info = ptr_to_u64(func_info);
 
 	err = bpf_obj_get_info_by_fd(fd, &info, &len);
 	close(fd);
@@ -578,6 +602,18 @@ static int do_dump(int argc, char **argv)
 		goto err_free;
 	}
 
+	if (info.func_info_cnt != finfo_cnt) {
+		p_err("incorrect func_info_cnt %d vs. expected %d",
+		      info.func_info_cnt, finfo_cnt);
+		goto err_free;
+	}
+
+	if (info.func_info_rec_size != finfo_rec_size) {
+		p_err("incorrect func_info_rec_size %d vs. expected %d",
+		      info.func_info_rec_size, finfo_rec_size);
+		goto err_free;
+	}
+
 	if ((member_len == &info.jited_prog_len &&
 	     info.jited_prog_insns == 0) ||
 	    (member_len == &info.xlated_prog_len &&
@@ -586,6 +622,11 @@ static int do_dump(int argc, char **argv)
 		goto err_free;
 	}
 
+	if (info.btf_id && btf_get_from_id(info.btf_id, &btf)) {
+		p_err("failed to get btf");
+		goto err_free;
+	}
+
 	if (filepath) {
 		fd = open(filepath, O_WRONLY | O_CREAT | O_TRUNC, 0600);
 		if (fd < 0) {
@@ -618,6 +659,7 @@ static int do_dump(int argc, char **argv)
 
 		if (info.nr_jited_func_lens && info.jited_func_lens) {
 			struct kernel_sym *sym = NULL;
+			struct bpf_func_info *record;
 			char sym_name[SYM_MAX_NAME];
 			unsigned char *img = buf;
 			__u64 *ksyms = NULL;
@@ -644,12 +686,25 @@ static int do_dump(int argc, char **argv)
 					strcpy(sym_name, "unknown");
 				}
 
+				if (func_info) {
+					record = func_info + i * finfo_rec_size;
+					btf_dumper_type_only(btf, record->type_id,
+							     func_sig,
+							     sizeof(func_sig));
+				}
+
 				if (json_output) {
 					jsonw_start_object(json_wtr);
+					if (func_info && func_sig[0] != '\0') {
+						jsonw_name(json_wtr, "proto");
+						jsonw_string(json_wtr, func_sig);
+					}
 					jsonw_name(json_wtr, "name");
 					jsonw_string(json_wtr, sym_name);
 					jsonw_name(json_wtr, "insns");
 				} else {
+					if (func_info && func_sig[0] != '\0')
+						printf("%s:\n", func_sig);
 					printf("%s:\n", sym_name);
 				}
 
@@ -678,6 +733,9 @@ static int do_dump(int argc, char **argv)
 		kernel_syms_load(&dd);
 		dd.nr_jited_ksyms = info.nr_jited_ksyms;
 		dd.jited_ksyms = (__u64 *) info.jited_ksyms;
+		dd.btf = btf;
+		dd.func_info = func_info;
+		dd.finfo_rec_size = finfo_rec_size;
 
 		if (json_output)
 			dump_xlated_json(&dd, buf, *member_len, opcodes);
@@ -689,12 +747,14 @@ static int do_dump(int argc, char **argv)
 	free(buf);
 	free(func_ksyms);
 	free(func_lens);
+	free(func_info);
 	return 0;
 
 err_free:
 	free(buf);
 	free(func_ksyms);
 	free(func_lens);
+	free(func_info);
 	return -1;
 }
 
@@ -721,30 +781,49 @@ int map_replace_compar(const void *p1, const void *p2)
 	return a->idx - b->idx;
 }
 
-static int do_attach(int argc, char **argv)
+static int parse_attach_detach_args(int argc, char **argv, int *progfd,
+				    enum bpf_attach_type *attach_type,
+				    int *mapfd)
 {
-	enum bpf_attach_type attach_type;
-	int err, mapfd, progfd;
-
-	if (!REQ_ARGS(5)) {
-		p_err("too few parameters for map attach");
+	if (!REQ_ARGS(3))
 		return -EINVAL;
-	}
 
-	progfd = prog_parse_fd(&argc, &argv);
-	if (progfd < 0)
-		return progfd;
+	*progfd = prog_parse_fd(&argc, &argv);
+	if (*progfd < 0)
+		return *progfd;
 
-	attach_type = parse_attach_type(*argv);
-	if (attach_type == __MAX_BPF_ATTACH_TYPE) {
-		p_err("invalid attach type");
+	*attach_type = parse_attach_type(*argv);
+	if (*attach_type == __MAX_BPF_ATTACH_TYPE) {
+		p_err("invalid attach/detach type");
 		return -EINVAL;
 	}
+
+	if (*attach_type == BPF_FLOW_DISSECTOR) {
+		*mapfd = -1;
+		return 0;
+	}
+
 	NEXT_ARG();
+	if (!REQ_ARGS(2))
+		return -EINVAL;
 
-	mapfd = map_parse_fd(&argc, &argv);
-	if (mapfd < 0)
-		return mapfd;
+	*mapfd = map_parse_fd(&argc, &argv);
+	if (*mapfd < 0)
+		return *mapfd;
+
+	return 0;
+}
+
+static int do_attach(int argc, char **argv)
+{
+	enum bpf_attach_type attach_type;
+	int err, progfd;
+	int mapfd;
+
+	err = parse_attach_detach_args(argc, argv,
+				       &progfd, &attach_type, &mapfd);
+	if (err)
+		return err;
 
 	err = bpf_prog_attach(progfd, mapfd, attach_type, 0);
 	if (err) {
@@ -760,27 +839,13 @@ static int do_attach(int argc, char **argv)
 static int do_detach(int argc, char **argv)
 {
 	enum bpf_attach_type attach_type;
-	int err, mapfd, progfd;
-
-	if (!REQ_ARGS(5)) {
-		p_err("too few parameters for map detach");
-		return -EINVAL;
-	}
+	int err, progfd;
+	int mapfd;
 
-	progfd = prog_parse_fd(&argc, &argv);
-	if (progfd < 0)
-		return progfd;
-
-	attach_type = parse_attach_type(*argv);
-	if (attach_type == __MAX_BPF_ATTACH_TYPE) {
-		p_err("invalid attach type");
-		return -EINVAL;
-	}
-	NEXT_ARG();
-
-	mapfd = map_parse_fd(&argc, &argv);
-	if (mapfd < 0)
-		return mapfd;
+	err = parse_attach_detach_args(argc, argv,
+				       &progfd, &attach_type, &mapfd);
+	if (err)
+		return err;
 
 	err = bpf_prog_detach2(progfd, mapfd, attach_type);
 	if (err) {
@@ -792,15 +857,17 @@ static int do_detach(int argc, char **argv)
 		jsonw_null(json_wtr);
 	return 0;
 }
-static int do_load(int argc, char **argv)
+
+static int load_with_options(int argc, char **argv, bool first_prog_only)
 {
 	enum bpf_attach_type expected_attach_type;
 	struct bpf_object_open_attr attr = {
 		.prog_type	= BPF_PROG_TYPE_UNSPEC,
 	};
 	struct map_replace *map_replace = NULL;
+	struct bpf_program *prog = NULL, *pos;
 	unsigned int old_map_fds = 0;
-	struct bpf_program *prog;
+	const char *pinmaps = NULL;
 	struct bpf_object *obj;
 	struct bpf_map *map;
 	const char *pinfile;
@@ -905,6 +972,13 @@ static int do_load(int argc, char **argv)
 				goto err_free_reuse_maps;
 			}
 			NEXT_ARG();
+		} else if (is_prefix(*argv, "pinmaps")) {
+			NEXT_ARG();
+
+			if (!REQ_ARGS(1))
+				goto err_free_reuse_maps;
+
+			pinmaps = GET_ARG();
 		} else {
 			p_err("expected no more arguments, 'type', 'map' or 'dev', got: '%s'?",
 			      *argv);
@@ -918,26 +992,25 @@ static int do_load(int argc, char **argv)
 		goto err_free_reuse_maps;
 	}
 
-	prog = bpf_program__next(NULL, obj);
-	if (!prog) {
-		p_err("object file doesn't contain any bpf program");
-		goto err_close_obj;
-	}
+	bpf_object__for_each_program(pos, obj) {
+		enum bpf_prog_type prog_type = attr.prog_type;
 
-	bpf_program__set_ifindex(prog, ifindex);
-	if (attr.prog_type == BPF_PROG_TYPE_UNSPEC) {
-		const char *sec_name = bpf_program__title(prog, false);
+		if (attr.prog_type == BPF_PROG_TYPE_UNSPEC) {
+			const char *sec_name = bpf_program__title(pos, false);
 
-		err = libbpf_prog_type_by_name(sec_name, &attr.prog_type,
-					       &expected_attach_type);
-		if (err < 0) {
-			p_err("failed to guess program type based on section name %s\n",
-			      sec_name);
-			goto err_close_obj;
+			err = libbpf_prog_type_by_name(sec_name, &prog_type,
+						       &expected_attach_type);
+			if (err < 0) {
+				p_err("failed to guess program type based on section name %s\n",
+				      sec_name);
+				goto err_close_obj;
+			}
 		}
+
+		bpf_program__set_ifindex(pos, ifindex);
+		bpf_program__set_type(pos, prog_type);
+		bpf_program__set_expected_attach_type(pos, expected_attach_type);
 	}
-	bpf_program__set_type(prog, attr.prog_type);
-	bpf_program__set_expected_attach_type(prog, expected_attach_type);
 
 	qsort(map_replace, old_map_fds, sizeof(*map_replace),
 	      map_replace_compar);
@@ -995,15 +1068,47 @@ static int do_load(int argc, char **argv)
 		goto err_close_obj;
 	}
 
+	set_max_rlimit();
+
 	err = bpf_object__load(obj);
 	if (err) {
 		p_err("failed to load object file");
 		goto err_close_obj;
 	}
 
-	if (do_pin_fd(bpf_program__fd(prog), pinfile))
+	err = mount_bpffs_for_pin(pinfile);
+	if (err)
 		goto err_close_obj;
 
+	if (first_prog_only) {
+		prog = bpf_program__next(NULL, obj);
+		if (!prog) {
+			p_err("object file doesn't contain any bpf program");
+			goto err_close_obj;
+		}
+
+		err = bpf_obj_pin(bpf_program__fd(prog), pinfile);
+		if (err) {
+			p_err("failed to pin program %s",
+			      bpf_program__title(prog, false));
+			goto err_close_obj;
+		}
+	} else {
+		err = bpf_object__pin_programs(obj, pinfile);
+		if (err) {
+			p_err("failed to pin all programs");
+			goto err_close_obj;
+		}
+	}
+
+	if (pinmaps) {
+		err = bpf_object__pin_maps(obj, pinmaps);
+		if (err) {
+			p_err("failed to pin all maps");
+			goto err_unpin;
+		}
+	}
+
 	if (json_output)
 		jsonw_null(json_wtr);
 
@@ -1014,6 +1119,11 @@ static int do_load(int argc, char **argv)
 
 	return 0;
 
+err_unpin:
+	if (first_prog_only)
+		unlink(pinfile);
+	else
+		bpf_object__unpin_programs(obj, pinfile);
 err_close_obj:
 	bpf_object__close(obj);
 err_free_reuse_maps:
@@ -1023,6 +1133,16 @@ err_free_reuse_maps:
 	return -1;
 }
 
+static int do_load(int argc, char **argv)
+{
+	return load_with_options(argc, argv, true);
+}
+
+static int do_loadall(int argc, char **argv)
+{
+	return load_with_options(argc, argv, false);
+}
+
 static int do_help(int argc, char **argv)
 {
 	if (json_output) {
@@ -1035,10 +1155,12 @@ static int do_help(int argc, char **argv)
 		"       %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n"
 		"       %s %s dump jited  PROG [{ file FILE | opcodes }]\n"
 		"       %s %s pin   PROG FILE\n"
-		"       %s %s load  OBJ  FILE [type TYPE] [dev NAME] \\\n"
-		"                         [map { idx IDX | name NAME } MAP]\n"
-		"       %s %s attach PROG ATTACH_TYPE MAP\n"
-		"       %s %s detach PROG ATTACH_TYPE MAP\n"
+		"       %s %s { load | loadall } OBJ  PATH \\\n"
+		"                         [type TYPE] [dev NAME] \\\n"
+		"                         [map { idx IDX | name NAME } MAP]\\\n"
+		"                         [pinmaps MAP_DIR]\n"
+		"       %s %s attach PROG ATTACH_TYPE [MAP]\n"
+		"       %s %s detach PROG ATTACH_TYPE [MAP]\n"
 		"       %s %s help\n"
 		"\n"
 		"       " HELP_SPEC_MAP "\n"
@@ -1050,7 +1172,8 @@ static int do_help(int argc, char **argv)
 		"                 cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
 		"                 cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
 		"                 cgroup/sendmsg4 | cgroup/sendmsg6 }\n"
-		"       ATTACH_TYPE := { msg_verdict | skb_verdict | skb_parse }\n"
+		"       ATTACH_TYPE := { msg_verdict | skb_verdict | skb_parse |\n"
+		"                        flow_dissector }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
@@ -1067,6 +1190,7 @@ static const struct cmd cmds[] = {
 	{ "dump",	do_dump },
 	{ "pin",	do_pin },
 	{ "load",	do_load },
+	{ "loadall",	do_loadall },
 	{ "attach",	do_attach },
 	{ "detach",	do_detach },
 	{ 0 }
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 3284759df98a..e06ac0286a75 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -242,11 +242,15 @@ void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len,
 		.cb_imm		= print_imm,
 		.private_data	= dd,
 	};
+	struct bpf_func_info *record;
 	struct bpf_insn *insn = buf;
+	struct btf *btf = dd->btf;
 	bool double_insn = false;
+	char func_sig[1024];
 	unsigned int i;
 
 	jsonw_start_array(json_wtr);
+	record = dd->func_info;
 	for (i = 0; i < len / sizeof(*insn); i++) {
 		if (double_insn) {
 			double_insn = false;
@@ -255,6 +259,20 @@ void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len,
 		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
 
 		jsonw_start_object(json_wtr);
+
+		if (btf && record) {
+			if (record->insn_offset == i) {
+				btf_dumper_type_only(btf, record->type_id,
+						     func_sig,
+						     sizeof(func_sig));
+				if (func_sig[0] != '\0') {
+					jsonw_name(json_wtr, "proto");
+					jsonw_string(json_wtr, func_sig);
+				}
+				record = (void *)record + dd->finfo_rec_size;
+			}
+		}
+
 		jsonw_name(json_wtr, "disasm");
 		print_bpf_insn(&cbs, insn + i, true);
 
@@ -297,16 +315,31 @@ void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len,
 		.cb_imm		= print_imm,
 		.private_data	= dd,
 	};
+	struct bpf_func_info *record;
 	struct bpf_insn *insn = buf;
+	struct btf *btf = dd->btf;
 	bool double_insn = false;
+	char func_sig[1024];
 	unsigned int i;
 
+	record = dd->func_info;
 	for (i = 0; i < len / sizeof(*insn); i++) {
 		if (double_insn) {
 			double_insn = false;
 			continue;
 		}
 
+		if (btf && record) {
+			if (record->insn_offset == i) {
+				btf_dumper_type_only(btf, record->type_id,
+						     func_sig,
+						     sizeof(func_sig));
+				if (func_sig[0] != '\0')
+					printf("%s:\n", func_sig);
+				record = (void *)record + dd->finfo_rec_size;
+			}
+		}
+
 		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
 
 		printf("% 4d: ", i);
diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h
index 33d86e2b369b..aec31723e1e5 100644
--- a/tools/bpf/bpftool/xlated_dumper.h
+++ b/tools/bpf/bpftool/xlated_dumper.h
@@ -51,6 +51,9 @@ struct dump_data {
 	__u32 sym_count;
 	__u64 *jited_ksyms;
 	__u32 nr_jited_ksyms;
+	struct btf *btf;
+	void *func_info;
+	__u32 finfo_rec_size;
 	char scratch_buff[SYM_MAX_NAME + 8];
 };
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 852dc17ab47a..23e2031a43d4 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -257,9 +257,6 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE		(1U << 2)
 
-/* flags for BPF_PROG_QUERY */
-#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
-
 #define BPF_OBJ_NAME_LEN 16U
 
 /* Flags for accessing BPF object */
@@ -269,6 +266,12 @@ enum bpf_attach_type {
 /* Flag for stack_map, store build_id+offset instead of pointer */
 #define 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)
+
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
+
 enum bpf_stack_build_id_status {
 	/* user space need an empty entry to identify end of a trace */
 	BPF_STACK_BUILD_ID_EMPTY = 0,
@@ -335,6 +338,10 @@ union bpf_attr {
 		 * (context accesses, allowed helpers, etc).
 		 */
 		__u32		expected_attach_type;
+		__u32		prog_btf_fd;	/* fd pointing to BTF type data */
+		__u32		func_info_rec_size;	/* userspace bpf_func_info size */
+		__aligned_u64	func_info;	/* func info */
+		__u32		func_info_cnt;	/* number of bpf_func_info records */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -2201,6 +2208,8 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, *struct bpf_sock*
+ *		return is from reuse->socks[] using hash of the packet.
  *
  * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
  *	Description
@@ -2233,6 +2242,8 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, *struct bpf_sock*
+ *		return is from reuse->socks[] using hash of the packet.
  *
  * int bpf_sk_release(struct bpf_sock *sk)
  *	Description
@@ -2457,6 +2468,7 @@ struct __sk_buff {
 
 	__u32 data_meta;
 	struct bpf_flow_keys *flow_keys;
+	__u64 tstamp;
 };
 
 struct bpf_tunnel_key {
@@ -2631,6 +2643,10 @@ struct bpf_prog_info {
 	__u32 nr_jited_func_lens;
 	__aligned_u64 jited_ksyms;
 	__aligned_u64 jited_func_lens;
+	__u32 btf_id;
+	__u32 func_info_rec_size;
+	__aligned_u64 func_info;
+	__u32 func_info_cnt;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -2942,4 +2958,9 @@ struct bpf_flow_keys {
 	};
 };
 
+struct bpf_func_info {
+	__u32	insn_offset;
+	__u32	type_id;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index 972265f32871..14f66948fc95 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -40,7 +40,8 @@ struct btf_type {
 	/* "size" is used by INT, ENUM, STRUCT and UNION.
 	 * "size" tells the size of the type it is describing.
 	 *
-	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT.
+	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
+	 * FUNC and FUNC_PROTO.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -64,8 +65,10 @@ struct btf_type {
 #define BTF_KIND_VOLATILE	9	/* Volatile	*/
 #define BTF_KIND_CONST		10	/* Const	*/
 #define BTF_KIND_RESTRICT	11	/* Restrict	*/
-#define BTF_KIND_MAX		11
-#define NR_BTF_KINDS		12
+#define BTF_KIND_FUNC		12	/* Function	*/
+#define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
+#define BTF_KIND_MAX		13
+#define NR_BTF_KINDS		14
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
@@ -110,4 +113,13 @@ struct btf_member {
 	__u32	offset;	/* offset in bits */
 };
 
+/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param".
+ * The exact number of btf_param is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_param {
+	__u32	name_off;
+	__u32	type;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 425b480bda75..1b4a683a00fc 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -66,7 +66,7 @@ ifndef VERBOSE
 endif
 
 FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf libelf-mmap bpf reallocarray
+FEATURE_TESTS = libelf libelf-mmap bpf reallocarray cxx
 FEATURE_DISPLAY = libelf bpf
 
 INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
@@ -148,6 +148,12 @@ LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
 
 CMD_TARGETS = $(LIB_FILE)
 
+CXX_TEST_TARGET = $(OUTPUT)test_libbpf
+
+ifeq ($(feature-cxx), 1)
+	CMD_TARGETS += $(CXX_TEST_TARGET)
+endif
+
 TARGETS = $(CMD_TARGETS)
 
 all: fixdep all_cmd
@@ -175,6 +181,9 @@ $(OUTPUT)libbpf.so: $(BPF_IN)
 $(OUTPUT)libbpf.a: $(BPF_IN)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
 
+$(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a
+	$(QUIET_LINK)$(CXX) $^ -lelf -o $@
+
 define do_install
 	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
@@ -201,8 +210,8 @@ config-clean:
 	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
 
 clean:
-	$(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so .*.d .*.cmd \
-		$(RM) LIBBPF-CFLAGS
+	$(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \
+		*.o *~ *.a *.so .*.d .*.cmd LIBBPF-CFLAGS
 	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
 
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 03f9bcc4ef50..ce1822194590 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -177,6 +177,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 			   char *log_buf, size_t log_buf_sz)
 {
 	union bpf_attr attr;
+	void *finfo = NULL;
 	__u32 name_len;
 	int fd;
 
@@ -196,6 +197,10 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	attr.log_level = 0;
 	attr.kern_version = load_attr->kern_version;
 	attr.prog_ifindex = load_attr->prog_ifindex;
+	attr.prog_btf_fd = load_attr->prog_btf_fd;
+	attr.func_info_rec_size = load_attr->func_info_rec_size;
+	attr.func_info_cnt = load_attr->func_info_cnt;
+	attr.func_info = ptr_to_u64(load_attr->func_info);
 	memcpy(attr.prog_name, load_attr->name,
 	       min(name_len, BPF_OBJ_NAME_LEN - 1));
 
@@ -203,12 +208,55 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	if (fd >= 0 || !log_buf || !log_buf_sz)
 		return fd;
 
+	/* After bpf_prog_load, the kernel may modify certain attributes
+	 * to give user space a hint how to deal with loading failure.
+	 * Check to see whether we can make some changes and load again.
+	 */
+	if (errno == E2BIG && attr.func_info_cnt &&
+	    attr.func_info_rec_size < load_attr->func_info_rec_size) {
+		__u32 actual_rec_size = load_attr->func_info_rec_size;
+		__u32 expected_rec_size = attr.func_info_rec_size;
+		__u32 finfo_cnt = load_attr->func_info_cnt;
+		__u64 finfo_len = actual_rec_size * finfo_cnt;
+		const void *orecord;
+		void *nrecord;
+		int i;
+
+		finfo = malloc(finfo_len);
+		if (!finfo)
+			/* further try with log buffer won't help */
+			return fd;
+
+		/* zero out bytes kernel does not understand */
+		orecord = load_attr->func_info;
+		nrecord = finfo;
+		for (i = 0; i < load_attr->func_info_cnt; i++) {
+			memcpy(nrecord, orecord, expected_rec_size);
+			memset(nrecord + expected_rec_size, 0,
+			       actual_rec_size - expected_rec_size);
+			orecord += actual_rec_size;
+			nrecord += actual_rec_size;
+		}
+
+		/* try with corrected func info records */
+		attr.func_info = ptr_to_u64(finfo);
+		attr.func_info_rec_size = load_attr->func_info_rec_size;
+
+		fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+
+		if (fd >= 0 || !log_buf || !log_buf_sz)
+			goto done;
+	}
+
 	/* Try again with log */
 	attr.log_buf = ptr_to_u64(log_buf);
 	attr.log_size = log_buf_sz;
 	attr.log_level = 1;
 	log_buf[0] = 0;
-	return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+done:
+	free(finfo);
+	return fd;
 }
 
 int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 26a51538213c..09e8bbe111d4 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -27,6 +27,10 @@
 #include <stdbool.h>
 #include <stddef.h>
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 #ifndef LIBBPF_API
 #define LIBBPF_API __attribute__((visibility("default")))
 #endif
@@ -74,6 +78,10 @@ struct bpf_load_program_attr {
 	const char *license;
 	__u32 kern_version;
 	__u32 prog_ifindex;
+	__u32 prog_btf_fd;
+	__u32 func_info_rec_size;
+	const void *func_info;
+	__u32 func_info_cnt;
 };
 
 /* Flags to direct loading requirements */
@@ -128,4 +136,9 @@ LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf,
 LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
 				 __u64 *probe_offset, __u64 *probe_addr);
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
 #endif /* __LIBBPF_BPF_H */
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 449591aa9900..13ddc4bd24ee 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -37,6 +37,23 @@ struct btf {
 	int fd;
 };
 
+struct btf_ext {
+	void *func_info;
+	__u32 func_info_rec_size;
+	__u32 func_info_len;
+};
+
+/* The minimum bpf_func_info checked by the loader */
+struct bpf_func_info_min {
+	__u32   insn_offset;
+	__u32   type_id;
+};
+
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
 static int btf_add_type(struct btf *btf, struct btf_type *t)
 {
 	if (btf->types_size - btf->nr_types < 2) {
@@ -165,6 +182,10 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
 		case BTF_KIND_ENUM:
 			next_type += vlen * sizeof(struct btf_enum);
 			break;
+		case BTF_KIND_FUNC_PROTO:
+			next_type += vlen * sizeof(struct btf_param);
+			break;
+		case BTF_KIND_FUNC:
 		case BTF_KIND_TYPEDEF:
 		case BTF_KIND_PTR:
 		case BTF_KIND_FWD:
@@ -393,3 +414,329 @@ const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
 	else
 		return NULL;
 }
+
+int btf_get_from_id(__u32 id, struct btf **btf)
+{
+	struct bpf_btf_info btf_info = { 0 };
+	__u32 len = sizeof(btf_info);
+	__u32 last_size;
+	int btf_fd;
+	void *ptr;
+	int err;
+
+	err = 0;
+	*btf = NULL;
+	btf_fd = bpf_btf_get_fd_by_id(id);
+	if (btf_fd < 0)
+		return 0;
+
+	/* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so
+	 * let's start with a sane default - 4KiB here - and resize it only if
+	 * bpf_obj_get_info_by_fd() needs a bigger buffer.
+	 */
+	btf_info.btf_size = 4096;
+	last_size = btf_info.btf_size;
+	ptr = malloc(last_size);
+	if (!ptr) {
+		err = -ENOMEM;
+		goto exit_free;
+	}
+
+	bzero(ptr, last_size);
+	btf_info.btf = ptr_to_u64(ptr);
+	err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+
+	if (!err && btf_info.btf_size > last_size) {
+		void *temp_ptr;
+
+		last_size = btf_info.btf_size;
+		temp_ptr = realloc(ptr, last_size);
+		if (!temp_ptr) {
+			err = -ENOMEM;
+			goto exit_free;
+		}
+		ptr = temp_ptr;
+		bzero(ptr, last_size);
+		btf_info.btf = ptr_to_u64(ptr);
+		err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+	}
+
+	if (err || btf_info.btf_size > last_size) {
+		err = errno;
+		goto exit_free;
+	}
+
+	*btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL);
+	if (IS_ERR(*btf)) {
+		err = PTR_ERR(*btf);
+		*btf = NULL;
+	}
+
+exit_free:
+	close(btf_fd);
+	free(ptr);
+
+	return err;
+}
+
+static int btf_ext_validate_func_info(const void *finfo, __u32 size,
+				      btf_print_fn_t err_log)
+{
+	int sec_hdrlen = sizeof(struct btf_sec_func_info);
+	__u32 size_left, num_records, record_size;
+	const struct btf_sec_func_info *sinfo;
+	__u64 total_record_size;
+
+	/* At least a func_info record size */
+	if (size < sizeof(__u32)) {
+		elog("BTF.ext func_info record size not found");
+		return -EINVAL;
+	}
+
+	/* The record size needs to meet below minimum standard */
+	record_size = *(__u32 *)finfo;
+	if (record_size < sizeof(struct bpf_func_info_min) ||
+	    record_size % sizeof(__u32)) {
+		elog("BTF.ext func_info invalid record size");
+		return -EINVAL;
+	}
+
+	sinfo = finfo + sizeof(__u32);
+	size_left = size - sizeof(__u32);
+
+	/* If no func_info records, return failure now so .BTF.ext
+	 * won't be used.
+	 */
+	if (!size_left) {
+		elog("BTF.ext no func info records");
+		return -EINVAL;
+	}
+
+	while (size_left) {
+		if (size_left < sec_hdrlen) {
+			elog("BTF.ext func_info header not found");
+			return -EINVAL;
+		}
+
+		num_records = sinfo->num_func_info;
+		if (num_records == 0) {
+			elog("incorrect BTF.ext num_func_info");
+			return -EINVAL;
+		}
+
+		total_record_size = sec_hdrlen +
+				    (__u64)num_records * record_size;
+		if (size_left < total_record_size) {
+			elog("incorrect BTF.ext num_func_info");
+			return -EINVAL;
+		}
+
+		size_left -= total_record_size;
+		sinfo = (void *)sinfo + total_record_size;
+	}
+
+	return 0;
+}
+
+static int btf_ext_parse_hdr(__u8 *data, __u32 data_size,
+			     btf_print_fn_t err_log)
+{
+	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
+	__u32 meta_left, last_func_info_pos;
+	void *finfo;
+
+	if (data_size < offsetof(struct btf_ext_header, func_info_off) ||
+	    data_size < hdr->hdr_len) {
+		elog("BTF.ext header not found");
+		return -EINVAL;
+	}
+
+	if (hdr->magic != BTF_MAGIC) {
+		elog("Invalid BTF.ext magic:%x\n", hdr->magic);
+		return -EINVAL;
+	}
+
+	if (hdr->version != BTF_VERSION) {
+		elog("Unsupported BTF.ext version:%u\n", hdr->version);
+		return -ENOTSUP;
+	}
+
+	if (hdr->flags) {
+		elog("Unsupported BTF.ext flags:%x\n", hdr->flags);
+		return -ENOTSUP;
+	}
+
+	meta_left = data_size - hdr->hdr_len;
+	if (!meta_left) {
+		elog("BTF.ext has no data\n");
+		return -EINVAL;
+	}
+
+	if (meta_left < hdr->func_info_off) {
+		elog("Invalid BTF.ext func_info section offset:%u\n",
+		     hdr->func_info_off);
+		return -EINVAL;
+	}
+
+	if (hdr->func_info_off & 0x03) {
+		elog("BTF.ext func_info section is not aligned to 4 bytes\n");
+		return -EINVAL;
+	}
+
+	last_func_info_pos = hdr->hdr_len + hdr->func_info_off +
+			     hdr->func_info_len;
+	if (last_func_info_pos > data_size) {
+		elog("Invalid BTF.ext func_info section size:%u\n",
+		     hdr->func_info_len);
+		return -EINVAL;
+	}
+
+	finfo = data + hdr->hdr_len + hdr->func_info_off;
+	return btf_ext_validate_func_info(finfo, hdr->func_info_len,
+					  err_log);
+}
+
+void btf_ext__free(struct btf_ext *btf_ext)
+{
+	if (!btf_ext)
+		return;
+
+	free(btf_ext->func_info);
+	free(btf_ext);
+}
+
+struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
+{
+	const struct btf_ext_header *hdr;
+	struct btf_ext *btf_ext;
+	void *org_fdata, *fdata;
+	__u32 hdrlen, size_u32;
+	int err;
+
+	err = btf_ext_parse_hdr(data, size, err_log);
+	if (err)
+		return ERR_PTR(err);
+
+	btf_ext = calloc(1, sizeof(struct btf_ext));
+	if (!btf_ext)
+		return ERR_PTR(-ENOMEM);
+
+	hdr = (const struct btf_ext_header *)data;
+	hdrlen = hdr->hdr_len;
+	size_u32 = sizeof(__u32);
+	fdata = malloc(hdr->func_info_len - size_u32);
+	if (!fdata) {
+		free(btf_ext);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* remember record size and copy rest of func_info data */
+	org_fdata = data + hdrlen + hdr->func_info_off;
+	btf_ext->func_info_rec_size = *(__u32 *)org_fdata;
+	memcpy(fdata, org_fdata + size_u32, hdr->func_info_len - size_u32);
+	btf_ext->func_info = fdata;
+	btf_ext->func_info_len = hdr->func_info_len - size_u32;
+
+	return btf_ext;
+}
+
+int btf_ext__reloc_init(struct btf *btf, struct btf_ext *btf_ext,
+			const char *sec_name, void **func_info,
+			__u32 *func_info_rec_size, __u32 *func_info_len)
+{
+	__u32 sec_hdrlen = sizeof(struct btf_sec_func_info);
+	__u32 i, record_size, records_len;
+	struct btf_sec_func_info *sinfo;
+	const char *info_sec_name;
+	__s64 remain_len;
+	void *data;
+
+	record_size = btf_ext->func_info_rec_size;
+	sinfo = btf_ext->func_info;
+	remain_len = btf_ext->func_info_len;
+
+	while (remain_len > 0) {
+		records_len = sinfo->num_func_info * record_size;
+		info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off);
+		if (strcmp(info_sec_name, sec_name)) {
+			remain_len -= sec_hdrlen + records_len;
+			sinfo = (void *)sinfo + sec_hdrlen + records_len;
+			continue;
+		}
+
+		data = malloc(records_len);
+		if (!data)
+			return -ENOMEM;
+
+		memcpy(data, sinfo->data, records_len);
+
+		/* adjust the insn_offset, the data in .BTF.ext is
+		 * the actual byte offset, and the kernel expects
+		 * the offset in term of bpf_insn.
+		 *
+		 * adjust the insn offset only, the rest data will
+		 * be passed to kernel.
+		 */
+		for (i = 0; i < sinfo->num_func_info; i++) {
+			struct bpf_func_info_min *record;
+
+			record = data + i * record_size;
+			record->insn_offset /= sizeof(struct bpf_insn);
+		}
+
+		*func_info = data;
+		*func_info_len = records_len;
+		*func_info_rec_size = record_size;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext,
+		   const char *sec_name, __u32 insns_cnt,
+		   void **func_info, __u32 *func_info_len)
+{
+	__u32 sec_hdrlen = sizeof(struct btf_sec_func_info);
+	__u32 i, record_size, existing_flen, records_len;
+	struct btf_sec_func_info *sinfo;
+	const char *info_sec_name;
+	__u64 remain_len;
+	void *data;
+
+	record_size = btf_ext->func_info_rec_size;
+	sinfo = btf_ext->func_info;
+	remain_len = btf_ext->func_info_len;
+	while (remain_len > 0) {
+		records_len = sinfo->num_func_info * record_size;
+		info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off);
+		if (strcmp(info_sec_name, sec_name)) {
+			remain_len -= sec_hdrlen + records_len;
+			sinfo = (void *)sinfo + sec_hdrlen + records_len;
+			continue;
+		}
+
+		existing_flen = *func_info_len;
+		data = realloc(*func_info, existing_flen + records_len);
+		if (!data)
+			return -ENOMEM;
+
+		memcpy(data + existing_flen, sinfo->data, records_len);
+		/* adjust insn_offset only, the rest data will be passed
+		 * to the kernel.
+		 */
+		for (i = 0; i < sinfo->num_func_info; i++) {
+			struct bpf_func_info_min *record;
+
+			record = data + existing_flen + i * record_size;
+			record->insn_offset =
+				record->insn_offset / sizeof(struct bpf_insn) +
+				insns_cnt;
+		}
+		*func_info = data;
+		*func_info_len = existing_flen + records_len;
+		return 0;
+	}
+
+	return -EINVAL;
+}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index b77e7080f7e7..701ad2b6c41f 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -6,15 +6,60 @@
 
 #include <linux/types.h>
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 #ifndef LIBBPF_API
 #define LIBBPF_API __attribute__((visibility("default")))
 #endif
 
 #define BTF_ELF_SEC ".BTF"
+#define BTF_EXT_ELF_SEC ".BTF.ext"
 
 struct btf;
+struct btf_ext;
 struct btf_type;
 
+/*
+ * The .BTF.ext ELF section layout defined as
+ *   struct btf_ext_header
+ *   func_info subsection
+ *
+ * The func_info subsection layout:
+ *   record size for struct bpf_func_info in the func_info subsection
+ *   struct btf_sec_func_info for section #1
+ *   a list of bpf_func_info records for section #1
+ *     where struct bpf_func_info mimics one in include/uapi/linux/bpf.h
+ *     but may not be identical
+ *   struct btf_sec_func_info for section #2
+ *   a list of bpf_func_info records for section #2
+ *   ......
+ *
+ * Note that the bpf_func_info record size in .BTF.ext may not
+ * be the same as the one defined in include/uapi/linux/bpf.h.
+ * The loader should ensure that record_size meets minimum
+ * requirement and pass the record as is to the kernel. The
+ * kernel will handle the func_info properly based on its contents.
+ */
+struct btf_ext_header {
+	__u16	magic;
+	__u8	version;
+	__u8	flags;
+	__u32	hdr_len;
+
+	/* All offsets are in bytes relative to the end of this header */
+	__u32	func_info_off;
+	__u32	func_info_len;
+};
+
+struct btf_sec_func_info {
+	__u32	sec_name_off;
+	__u32	num_func_info;
+	/* Followed by num_func_info number of bpf func_info records */
+	__u8	data[0];
+};
+
 typedef int (*btf_print_fn_t)(const char *, ...)
 	__attribute__((format(printf, 1, 2)));
 
@@ -28,5 +73,19 @@ LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__fd(const struct btf *btf);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
+LIBBPF_API int btf_get_from_id(__u32 id, struct btf **btf);
+
+struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
+void btf_ext__free(struct btf_ext *btf_ext);
+int btf_ext__reloc_init(struct btf *btf, struct btf_ext *btf_ext,
+			const char *sec_name, void **func_info,
+			__u32 *func_info_rec_size, __u32 *func_info_len);
+int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext,
+		   const char *sec_name, __u32 insns_cnt, void **func_info,
+		   __u32 *func_info_len);
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
 
 #endif /* __LIBBPF_BTF_H */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d6e62e90e8d4..ed4212a4c5f9 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -24,6 +24,7 @@
 #include <linux/kernel.h>
 #include <linux/bpf.h>
 #include <linux/btf.h>
+#include <linux/filter.h>
 #include <linux/list.h>
 #include <linux/limits.h>
 #include <linux/perf_event.h>
@@ -114,6 +115,11 @@ void libbpf_set_print(libbpf_print_fn_t warn,
 # define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
 #endif
 
+struct bpf_capabilities {
+	/* v4.14: kernel support for program & map names. */
+	__u32 name:1;
+};
+
 /*
  * bpf_prog should be a better name but it has been used in
  * linux/filter.h.
@@ -124,6 +130,10 @@ struct bpf_program {
 	char *name;
 	int prog_ifindex;
 	char *section_name;
+	/* section_name with / replaced by _; makes recursive pinning
+	 * in bpf_object__pin_programs easier
+	 */
+	char *pin_name;
 	struct bpf_insn *insns;
 	size_t insns_cnt, main_prog_cnt;
 	enum bpf_prog_type type;
@@ -152,6 +162,12 @@ struct bpf_program {
 	bpf_program_clear_priv_t clear_priv;
 
 	enum bpf_attach_type expected_attach_type;
+	int btf_fd;
+	void *func_info;
+	__u32 func_info_rec_size;
+	__u32 func_info_len;
+
+	struct bpf_capabilities *caps;
 };
 
 struct bpf_map {
@@ -159,6 +175,7 @@ struct bpf_map {
 	char *name;
 	size_t offset;
 	int map_ifindex;
+	int inner_map_fd;
 	struct bpf_map_def def;
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
@@ -208,10 +225,13 @@ struct bpf_object {
 	struct list_head list;
 
 	struct btf *btf;
+	struct btf_ext *btf_ext;
 
 	void *priv;
 	bpf_object_clear_priv_t clear_priv;
 
+	struct bpf_capabilities caps;
+
 	char path[];
 };
 #define obj_elf_valid(o)	((o)->efile.elf)
@@ -237,6 +257,9 @@ void bpf_program__unload(struct bpf_program *prog)
 
 	prog->instances.nr = -1;
 	zfree(&prog->instances.fds);
+
+	zclose(prog->btf_fd);
+	zfree(&prog->func_info);
 }
 
 static void bpf_program__exit(struct bpf_program *prog)
@@ -253,6 +276,7 @@ static void bpf_program__exit(struct bpf_program *prog)
 	bpf_program__unload(prog);
 	zfree(&prog->name);
 	zfree(&prog->section_name);
+	zfree(&prog->pin_name);
 	zfree(&prog->insns);
 	zfree(&prog->reloc_desc);
 
@@ -261,6 +285,17 @@ static void bpf_program__exit(struct bpf_program *prog)
 	prog->idx = -1;
 }
 
+static char *__bpf_program__pin_name(struct bpf_program *prog)
+{
+	char *name, *p;
+
+	name = p = strdup(prog->section_name);
+	while ((p = strchr(p, '/')))
+		*p = '_';
+
+	return name;
+}
+
 static int
 bpf_program__init(void *data, size_t size, char *section_name, int idx,
 		  struct bpf_program *prog)
@@ -279,6 +314,13 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx,
 		goto errout;
 	}
 
+	prog->pin_name = __bpf_program__pin_name(prog);
+	if (!prog->pin_name) {
+		pr_warning("failed to alloc pin name for prog under section(%d) %s\n",
+			   idx, section_name);
+		goto errout;
+	}
+
 	prog->insns = malloc(size);
 	if (!prog->insns) {
 		pr_warning("failed to alloc insns for prog under section %s\n",
@@ -291,7 +333,8 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx,
 	prog->idx = idx;
 	prog->instances.fds = NULL;
 	prog->instances.nr = -1;
-	prog->type = BPF_PROG_TYPE_KPROBE;
+	prog->type = BPF_PROG_TYPE_UNSPEC;
+	prog->btf_fd = -1;
 
 	return 0;
 errout:
@@ -310,6 +353,7 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
 	if (err)
 		return err;
 
+	prog.caps = &obj->caps;
 	progs = obj->programs;
 	nr_progs = obj->nr_programs;
 
@@ -562,6 +606,14 @@ static int compare_bpf_map(const void *_a, const void *_b)
 	return a->offset - b->offset;
 }
 
+static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
+{
+	if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+	    type == BPF_MAP_TYPE_HASH_OF_MAPS)
+		return true;
+	return false;
+}
+
 static int
 bpf_object__init_maps(struct bpf_object *obj, int flags)
 {
@@ -625,13 +677,15 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
 	}
 	obj->nr_maps = nr_maps;
 
-	/*
-	 * fill all fd with -1 so won't close incorrect
-	 * fd (fd=0 is stdin) when failure (zclose won't close
-	 * negative fd)).
-	 */
-	for (i = 0; i < nr_maps; i++)
+	for (i = 0; i < nr_maps; i++) {
+		/*
+		 * fill all fd with -1 so won't close incorrect
+		 * fd (fd=0 is stdin) when failure (zclose won't close
+		 * negative fd)).
+		 */
 		obj->maps[i].fd = -1;
+		obj->maps[i].inner_map_fd = -1;
+	}
 
 	/*
 	 * Fill obj->maps using data in "maps" section.
@@ -784,6 +838,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 					   BTF_ELF_SEC, PTR_ERR(obj->btf));
 				obj->btf = NULL;
 			}
+		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
+			obj->btf_ext = btf_ext__new(data->d_buf, data->d_size,
+						    __pr_debug);
+			if (IS_ERR(obj->btf_ext)) {
+				pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
+					   BTF_EXT_ELF_SEC,
+					   PTR_ERR(obj->btf_ext));
+				obj->btf_ext = NULL;
+			}
 		} else if (sh.sh_type == SHT_SYMTAB) {
 			if (obj->efile.symbols) {
 				pr_warning("bpf: multiple SYMTAB in %s\n",
@@ -1095,6 +1158,52 @@ err_free_new_name:
 }
 
 static int
+bpf_object__probe_name(struct bpf_object *obj)
+{
+	struct bpf_load_program_attr attr;
+	char *cp, errmsg[STRERR_BUFSIZE];
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int ret;
+
+	/* make sure basic loading works */
+
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	attr.insns = insns;
+	attr.insns_cnt = ARRAY_SIZE(insns);
+	attr.license = "GPL";
+
+	ret = bpf_load_program_xattr(&attr, NULL, 0);
+	if (ret < 0) {
+		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+		pr_warning("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n",
+			   __func__, cp, errno);
+		return -errno;
+	}
+	close(ret);
+
+	/* now try the same program, but with the name */
+
+	attr.name = "test";
+	ret = bpf_load_program_xattr(&attr, NULL, 0);
+	if (ret >= 0) {
+		obj->caps.name = 1;
+		close(ret);
+	}
+
+	return 0;
+}
+
+static int
+bpf_object__probe_caps(struct bpf_object *obj)
+{
+	return bpf_object__probe_name(obj);
+}
+
+static int
 bpf_object__create_maps(struct bpf_object *obj)
 {
 	struct bpf_create_map_attr create_attr = {};
@@ -1113,7 +1222,8 @@ bpf_object__create_maps(struct bpf_object *obj)
 			continue;
 		}
 
-		create_attr.name = map->name;
+		if (obj->caps.name)
+			create_attr.name = map->name;
 		create_attr.map_ifindex = map->map_ifindex;
 		create_attr.map_type = def->type;
 		create_attr.map_flags = def->map_flags;
@@ -1123,6 +1233,9 @@ bpf_object__create_maps(struct bpf_object *obj)
 		create_attr.btf_fd = 0;
 		create_attr.btf_key_type_id = 0;
 		create_attr.btf_value_type_id = 0;
+		if (bpf_map_type__is_map_in_map(def->type) &&
+		    map->inner_map_fd >= 0)
+			create_attr.inner_map_fd = map->inner_map_fd;
 
 		if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) {
 			create_attr.btf_fd = btf__fd(obj->btf);
@@ -1167,6 +1280,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 	struct bpf_insn *insn, *new_insn;
 	struct bpf_program *text;
 	size_t new_cnt;
+	int err;
 
 	if (relo->type != RELO_CALL)
 		return -LIBBPF_ERRNO__RELOC;
@@ -1189,6 +1303,20 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			pr_warning("oom in prog realloc\n");
 			return -ENOMEM;
 		}
+
+		if (obj->btf && obj->btf_ext) {
+			err = btf_ext__reloc(obj->btf, obj->btf_ext,
+					     text->section_name,
+					     prog->insns_cnt,
+					     &prog->func_info,
+					     &prog->func_info_len);
+			if (err) {
+				pr_warning("error in btf_ext__reloc for sec %s\n",
+					   text->section_name);
+				return err;
+			}
+		}
+
 		memcpy(new_insn + prog->insns_cnt, text->insns,
 		       text->insns_cnt * sizeof(*insn));
 		prog->insns = new_insn;
@@ -1208,7 +1336,24 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
 {
 	int i, err;
 
-	if (!prog || !prog->reloc_desc)
+	if (!prog)
+		return 0;
+
+	if (obj->btf && obj->btf_ext) {
+		err = btf_ext__reloc_init(obj->btf, obj->btf_ext,
+					  prog->section_name,
+					  &prog->func_info,
+					  &prog->func_info_rec_size,
+					  &prog->func_info_len);
+		if (err) {
+			pr_warning("err in btf_ext__reloc_init for sec %s\n",
+				   prog->section_name);
+			return err;
+		}
+		prog->btf_fd = btf__fd(obj->btf);
+	}
+
+	if (!prog->reloc_desc)
 		return 0;
 
 	for (i = 0; i < prog->nr_reloc; i++) {
@@ -1296,9 +1441,9 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 }
 
 static int
-load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
-	     const char *name, struct bpf_insn *insns, int insns_cnt,
-	     char *license, __u32 kern_version, int *pfd, int prog_ifindex)
+load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
+	     char *license, __u32 kern_version, int *pfd,
+	     __u32 func_info_cnt)
 {
 	struct bpf_load_program_attr load_attr;
 	char *cp, errmsg[STRERR_BUFSIZE];
@@ -1306,14 +1451,19 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
 	int ret;
 
 	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
-	load_attr.prog_type = type;
-	load_attr.expected_attach_type = expected_attach_type;
-	load_attr.name = name;
+	load_attr.prog_type = prog->type;
+	load_attr.expected_attach_type = prog->expected_attach_type;
+	if (prog->caps->name)
+		load_attr.name = prog->name;
 	load_attr.insns = insns;
 	load_attr.insns_cnt = insns_cnt;
 	load_attr.license = license;
 	load_attr.kern_version = kern_version;
-	load_attr.prog_ifindex = prog_ifindex;
+	load_attr.prog_ifindex = prog->prog_ifindex;
+	load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0;
+	load_attr.func_info = prog->func_info;
+	load_attr.func_info_rec_size = prog->func_info_rec_size;
+	load_attr.func_info_cnt = func_info_cnt;
 
 	if (!load_attr.insns || !load_attr.insns_cnt)
 		return -EINVAL;
@@ -1371,8 +1521,14 @@ int
 bpf_program__load(struct bpf_program *prog,
 		  char *license, __u32 kern_version)
 {
+	__u32 func_info_cnt;
 	int err = 0, fd, i;
 
+	if (prog->func_info_len == 0)
+		func_info_cnt = 0;
+	else
+		func_info_cnt = prog->func_info_len / prog->func_info_rec_size;
+
 	if (prog->instances.nr < 0 || !prog->instances.fds) {
 		if (prog->preprocessor) {
 			pr_warning("Internal error: can't load program '%s'\n",
@@ -1394,10 +1550,9 @@ bpf_program__load(struct bpf_program *prog,
 			pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
 				   prog->section_name, prog->instances.nr);
 		}
-		err = load_program(prog->type, prog->expected_attach_type,
-				   prog->name, prog->insns, prog->insns_cnt,
+		err = load_program(prog, prog->insns, prog->insns_cnt,
 				   license, kern_version, &fd,
-				   prog->prog_ifindex);
+				   func_info_cnt);
 		if (!err)
 			prog->instances.fds[0] = fd;
 		goto out;
@@ -1425,11 +1580,10 @@ bpf_program__load(struct bpf_program *prog,
 			continue;
 		}
 
-		err = load_program(prog->type, prog->expected_attach_type,
-				   prog->name, result.new_insn_ptr,
+		err = load_program(prog, result.new_insn_ptr,
 				   result.new_insn_cnt,
 				   license, kern_version, &fd,
-				   prog->prog_ifindex);
+				   func_info_cnt);
 
 		if (err) {
 			pr_warning("Loading the %dth instance of program '%s' failed\n",
@@ -1495,12 +1649,12 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
 	case BPF_PROG_TYPE_LIRC_MODE2:
 	case BPF_PROG_TYPE_SK_REUSEPORT:
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
-		return false;
 	case BPF_PROG_TYPE_UNSPEC:
-	case BPF_PROG_TYPE_KPROBE:
 	case BPF_PROG_TYPE_TRACEPOINT:
-	case BPF_PROG_TYPE_PERF_EVENT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_PERF_EVENT:
+		return false;
+	case BPF_PROG_TYPE_KPROBE:
 	default:
 		return true;
 	}
@@ -1627,6 +1781,7 @@ int bpf_object__load(struct bpf_object *obj)
 
 	obj->loaded = true;
 
+	CHECK_ERR(bpf_object__probe_caps(obj), err, out);
 	CHECK_ERR(bpf_object__create_maps(obj), err, out);
 	CHECK_ERR(bpf_object__relocate(obj), err, out);
 	CHECK_ERR(bpf_object__load_progs(obj), err, out);
@@ -1699,6 +1854,34 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 	return 0;
 }
 
+int bpf_program__unpin_instance(struct bpf_program *prog, const char *path,
+				int instance)
+{
+	int err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (prog == NULL) {
+		pr_warning("invalid program pointer\n");
+		return -EINVAL;
+	}
+
+	if (instance < 0 || instance >= prog->instances.nr) {
+		pr_warning("invalid prog instance %d of prog %s (max %d)\n",
+			   instance, prog->section_name, prog->instances.nr);
+		return -EINVAL;
+	}
+
+	err = unlink(path);
+	if (err != 0)
+		return -errno;
+	pr_debug("unpinned program '%s'\n", path);
+
+	return 0;
+}
+
 static int make_dir(const char *path)
 {
 	char *cp, errmsg[STRERR_BUFSIZE];
@@ -1733,6 +1916,11 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 		return -EINVAL;
 	}
 
+	if (prog->instances.nr == 1) {
+		/* don't create subdirs when pinning single instance */
+		return bpf_program__pin_instance(prog, path, 0);
+	}
+
 	err = make_dir(path);
 	if (err)
 		return err;
@@ -1742,16 +1930,83 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 		int len;
 
 		len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
+		if (len < 0) {
+			err = -EINVAL;
+			goto err_unpin;
+		} else if (len >= PATH_MAX) {
+			err = -ENAMETOOLONG;
+			goto err_unpin;
+		}
+
+		err = bpf_program__pin_instance(prog, buf, i);
+		if (err)
+			goto err_unpin;
+	}
+
+	return 0;
+
+err_unpin:
+	for (i = i - 1; i >= 0; i--) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
+		if (len < 0)
+			continue;
+		else if (len >= PATH_MAX)
+			continue;
+
+		bpf_program__unpin_instance(prog, buf, i);
+	}
+
+	rmdir(path);
+
+	return err;
+}
+
+int bpf_program__unpin(struct bpf_program *prog, const char *path)
+{
+	int i, err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (prog == NULL) {
+		pr_warning("invalid program pointer\n");
+		return -EINVAL;
+	}
+
+	if (prog->instances.nr <= 0) {
+		pr_warning("no instances of prog %s to pin\n",
+			   prog->section_name);
+		return -EINVAL;
+	}
+
+	if (prog->instances.nr == 1) {
+		/* don't create subdirs when pinning single instance */
+		return bpf_program__unpin_instance(prog, path, 0);
+	}
+
+	for (i = 0; i < prog->instances.nr; i++) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
 		if (len < 0)
 			return -EINVAL;
 		else if (len >= PATH_MAX)
 			return -ENAMETOOLONG;
 
-		err = bpf_program__pin_instance(prog, buf, i);
+		err = bpf_program__unpin_instance(prog, buf, i);
 		if (err)
 			return err;
 	}
 
+	err = rmdir(path);
+	if (err)
+		return -errno;
+
 	return 0;
 }
 
@@ -1776,12 +2031,33 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 	}
 
 	pr_debug("pinned map '%s'\n", path);
+
 	return 0;
 }
 
-int bpf_object__pin(struct bpf_object *obj, const char *path)
+int bpf_map__unpin(struct bpf_map *map, const char *path)
+{
+	int err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (map == NULL) {
+		pr_warning("invalid map pointer\n");
+		return -EINVAL;
+	}
+
+	err = unlink(path);
+	if (err != 0)
+		return -errno;
+	pr_debug("unpinned map '%s'\n", path);
+
+	return 0;
+}
+
+int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
 {
-	struct bpf_program *prog;
 	struct bpf_map *map;
 	int err;
 
@@ -1803,28 +2079,142 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
 
 		len = snprintf(buf, PATH_MAX, "%s/%s", path,
 			       bpf_map__name(map));
+		if (len < 0) {
+			err = -EINVAL;
+			goto err_unpin_maps;
+		} else if (len >= PATH_MAX) {
+			err = -ENAMETOOLONG;
+			goto err_unpin_maps;
+		}
+
+		err = bpf_map__pin(map, buf);
+		if (err)
+			goto err_unpin_maps;
+	}
+
+	return 0;
+
+err_unpin_maps:
+	while ((map = bpf_map__prev(map, obj))) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       bpf_map__name(map));
+		if (len < 0)
+			continue;
+		else if (len >= PATH_MAX)
+			continue;
+
+		bpf_map__unpin(map, buf);
+	}
+
+	return err;
+}
+
+int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
+{
+	struct bpf_map *map;
+	int err;
+
+	if (!obj)
+		return -ENOENT;
+
+	bpf_map__for_each(map, obj) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       bpf_map__name(map));
 		if (len < 0)
 			return -EINVAL;
 		else if (len >= PATH_MAX)
 			return -ENAMETOOLONG;
 
-		err = bpf_map__pin(map, buf);
+		err = bpf_map__unpin(map, buf);
 		if (err)
 			return err;
 	}
 
+	return 0;
+}
+
+int bpf_object__pin_programs(struct bpf_object *obj, const char *path)
+{
+	struct bpf_program *prog;
+	int err;
+
+	if (!obj)
+		return -ENOENT;
+
+	if (!obj->loaded) {
+		pr_warning("object not yet loaded; load it first\n");
+		return -ENOENT;
+	}
+
+	err = make_dir(path);
+	if (err)
+		return err;
+
+	bpf_object__for_each_program(prog, obj) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       prog->pin_name);
+		if (len < 0) {
+			err = -EINVAL;
+			goto err_unpin_programs;
+		} else if (len >= PATH_MAX) {
+			err = -ENAMETOOLONG;
+			goto err_unpin_programs;
+		}
+
+		err = bpf_program__pin(prog, buf);
+		if (err)
+			goto err_unpin_programs;
+	}
+
+	return 0;
+
+err_unpin_programs:
+	while ((prog = bpf_program__prev(prog, obj))) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       prog->pin_name);
+		if (len < 0)
+			continue;
+		else if (len >= PATH_MAX)
+			continue;
+
+		bpf_program__unpin(prog, buf);
+	}
+
+	return err;
+}
+
+int bpf_object__unpin_programs(struct bpf_object *obj, const char *path)
+{
+	struct bpf_program *prog;
+	int err;
+
+	if (!obj)
+		return -ENOENT;
+
 	bpf_object__for_each_program(prog, obj) {
 		char buf[PATH_MAX];
 		int len;
 
 		len = snprintf(buf, PATH_MAX, "%s/%s", path,
-			       prog->section_name);
+			       prog->pin_name);
 		if (len < 0)
 			return -EINVAL;
 		else if (len >= PATH_MAX)
 			return -ENAMETOOLONG;
 
-		err = bpf_program__pin(prog, buf);
+		err = bpf_program__unpin(prog, buf);
 		if (err)
 			return err;
 	}
@@ -1832,6 +2222,23 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
 	return 0;
 }
 
+int bpf_object__pin(struct bpf_object *obj, const char *path)
+{
+	int err;
+
+	err = bpf_object__pin_maps(obj, path);
+	if (err)
+		return err;
+
+	err = bpf_object__pin_programs(obj, path);
+	if (err) {
+		bpf_object__unpin_maps(obj, path);
+		return err;
+	}
+
+	return 0;
+}
+
 void bpf_object__close(struct bpf_object *obj)
 {
 	size_t i;
@@ -1845,6 +2252,7 @@ void bpf_object__close(struct bpf_object *obj)
 	bpf_object__elf_finish(obj);
 	bpf_object__unload(obj);
 	btf__free(obj->btf);
+	btf_ext__free(obj->btf_ext);
 
 	for (i = 0; i < obj->nr_maps; i++) {
 		zfree(&obj->maps[i].name);
@@ -1918,23 +2326,26 @@ void *bpf_object__priv(struct bpf_object *obj)
 }
 
 static struct bpf_program *
-__bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
+__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward)
 {
-	size_t idx;
+	size_t nr_programs = obj->nr_programs;
+	ssize_t idx;
 
-	if (!obj->programs)
+	if (!nr_programs)
 		return NULL;
-	/* First handler */
-	if (prev == NULL)
-		return &obj->programs[0];
 
-	if (prev->obj != obj) {
+	if (!p)
+		/* Iter from the beginning */
+		return forward ? &obj->programs[0] :
+			&obj->programs[nr_programs - 1];
+
+	if (p->obj != obj) {
 		pr_warning("error: program handler doesn't match object\n");
 		return NULL;
 	}
 
-	idx = (prev - obj->programs) + 1;
-	if (idx >= obj->nr_programs)
+	idx = (p - obj->programs) + (forward ? 1 : -1);
+	if (idx >= obj->nr_programs || idx < 0)
 		return NULL;
 	return &obj->programs[idx];
 }
@@ -1945,7 +2356,19 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
 	struct bpf_program *prog = prev;
 
 	do {
-		prog = __bpf_program__next(prog, obj);
+		prog = __bpf_program__iter(prog, obj, true);
+	} while (prog && bpf_program__is_function_storage(prog, obj));
+
+	return prog;
+}
+
+struct bpf_program *
+bpf_program__prev(struct bpf_program *next, struct bpf_object *obj)
+{
+	struct bpf_program *prog = next;
+
+	do {
+		prog = __bpf_program__iter(prog, obj, false);
 	} while (prog && bpf_program__is_function_storage(prog, obj));
 
 	return prog;
@@ -2272,10 +2695,24 @@ void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
 	map->map_ifindex = ifindex;
 }
 
-struct bpf_map *
-bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
+int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd)
 {
-	size_t idx;
+	if (!bpf_map_type__is_map_in_map(map->def.type)) {
+		pr_warning("error: unsupported map type\n");
+		return -EINVAL;
+	}
+	if (map->inner_map_fd != -1) {
+		pr_warning("error: inner_map_fd already specified\n");
+		return -EINVAL;
+	}
+	map->inner_map_fd = fd;
+	return 0;
+}
+
+static struct bpf_map *
+__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i)
+{
+	ssize_t idx;
 	struct bpf_map *s, *e;
 
 	if (!obj || !obj->maps)
@@ -2284,22 +2721,40 @@ bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
 	s = obj->maps;
 	e = obj->maps + obj->nr_maps;
 
-	if (prev == NULL)
-		return s;
-
-	if ((prev < s) || (prev >= e)) {
+	if ((m < s) || (m >= e)) {
 		pr_warning("error in %s: map handler doesn't belong to object\n",
 			   __func__);
 		return NULL;
 	}
 
-	idx = (prev - obj->maps) + 1;
-	if (idx >= obj->nr_maps)
+	idx = (m - obj->maps) + i;
+	if (idx >= obj->nr_maps || idx < 0)
 		return NULL;
 	return &obj->maps[idx];
 }
 
 struct bpf_map *
+bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
+{
+	if (prev == NULL)
+		return obj->maps;
+
+	return __bpf_map__iter(prev, obj, 1);
+}
+
+struct bpf_map *
+bpf_map__prev(struct bpf_map *next, struct bpf_object *obj)
+{
+	if (next == NULL) {
+		if (!obj->nr_maps)
+			return NULL;
+		return obj->maps + obj->nr_maps - 1;
+	}
+
+	return __bpf_map__iter(next, obj, -1);
+}
+
+struct bpf_map *
 bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
 {
 	struct bpf_map *pos;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 1f3468dad8b2..f30c3d07bb7d 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -16,6 +16,10 @@
 #include <sys/types.h>  // for size_t
 #include <linux/bpf.h>
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 #ifndef LIBBPF_API
 #define LIBBPF_API __attribute__((visibility("default")))
 #endif
@@ -71,6 +75,13 @@ struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
 LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf,
 						      size_t obj_buf_sz,
 						      const char *name);
+LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path);
+LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj,
+				      const char *path);
+LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj,
+					const char *path);
+LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj,
+					  const char *path);
 LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path);
 LIBBPF_API void bpf_object__close(struct bpf_object *object);
 
@@ -112,6 +123,9 @@ LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog,
 	     (pos) != NULL;				\
 	     (pos) = bpf_program__next((pos), (obj)))
 
+LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog,
+						 struct bpf_object *obj);
+
 typedef void (*bpf_program_clear_priv_t)(struct bpf_program *,
 					 void *);
 
@@ -131,7 +145,11 @@ LIBBPF_API int bpf_program__fd(struct bpf_program *prog);
 LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog,
 					 const char *path,
 					 int instance);
+LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog,
+					   const char *path,
+					   int instance);
 LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path);
+LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path);
 LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
 
 struct bpf_insn;
@@ -260,6 +278,9 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
 	     (pos) != NULL;				\
 	     (pos) = bpf_map__next((pos), (obj)))
 
+LIBBPF_API struct bpf_map *
+bpf_map__prev(struct bpf_map *map, struct bpf_object *obj);
+
 LIBBPF_API int bpf_map__fd(struct bpf_map *map);
 LIBBPF_API const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
 LIBBPF_API const char *bpf_map__name(struct bpf_map *map);
@@ -274,6 +295,9 @@ LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
 LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map);
 LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
 LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
+LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
+
+LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd);
 
 LIBBPF_API long libbpf_get_error(const void *ptr);
 
@@ -317,4 +341,9 @@ int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
 			libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
 int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
 			 libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie);
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
 #endif /* __LIBBPF_LIBBPF_H */
diff --git a/tools/lib/bpf/test_libbpf.cpp b/tools/lib/bpf/test_libbpf.cpp
new file mode 100644
index 000000000000..abf3fc25c9fa
--- /dev/null
+++ b/tools/lib/bpf/test_libbpf.cpp
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#include "libbpf.h"
+#include "bpf.h"
+#include "btf.h"
+
+/* do nothing, just make sure we can link successfully */
+
+int main(int argc, char *argv[])
+{
+    /* libbpf.h */
+    libbpf_set_print(NULL, NULL, NULL);
+
+    /* bpf.h */
+    bpf_prog_get_fd_by_id(0);
+
+    /* btf.h */
+    btf__new(NULL, 0, NULL);
+}
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 4a54236475ae..73aa6d8f4a2f 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -24,12 +24,13 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
 	test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \
-	test_netcnt
+	test_netcnt test_tcpnotify_user
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
 	sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
 	test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
+	test_tcpnotify_kern.o \
 	sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \
 	sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \
 	test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
@@ -38,7 +39,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
 	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o \
 	test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o \
-	xdp_dummy.o
+	xdp_dummy.o test_map_in_map.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -75,6 +76,7 @@ $(OUTPUT)/test_sock_addr: cgroup_helpers.c
 $(OUTPUT)/test_socket_cookie: cgroup_helpers.c
 $(OUTPUT)/test_sockmap: cgroup_helpers.c
 $(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
+$(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c
 $(OUTPUT)/test_progs: trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
 $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
@@ -125,7 +127,14 @@ $(OUTPUT)/test_stack_map.o: test_queue_stack_map.h
 BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
 BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
 BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
+BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \
+			  $(CLANG) -target bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \
+			  readelf -S ./llvm_btf_verify.o | grep BTF; \
+			  /bin/rm -f ./llvm_btf_verify.o)
 
+ifneq ($(BTF_LLVM_PROBE),)
+	CLANG_FLAGS += -g
+else
 ifneq ($(BTF_LLC_PROBE),)
 ifneq ($(BTF_PAHOLE_PROBE),)
 ifneq ($(BTF_OBJCOPY_PROBE),)
@@ -135,6 +144,17 @@ ifneq ($(BTF_OBJCOPY_PROBE),)
 endif
 endif
 endif
+endif
+
+# Have one program compiled without "-target bpf" to test whether libbpf loads
+# it successfully
+$(OUTPUT)/test_xdp.o: test_xdp.c
+	$(CLANG) $(CLANG_FLAGS) \
+		-O2 -emit-llvm -c $< -o - | \
+	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
+ifeq ($(DWARF2BTF),y)
+	$(BTF_PAHOLE) -J $@
+endif
 
 $(OUTPUT)/%.o: %.c
 	$(CLANG) $(CLANG_FLAGS) \
diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/bpf_flow.c
index 107350a7821d..b9798f558ca7 100644
--- a/tools/testing/selftests/bpf/bpf_flow.c
+++ b/tools/testing/selftests/bpf/bpf_flow.c
@@ -116,7 +116,7 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 	return BPF_DROP;
 }
 
-SEC("dissect")
+SEC("flow_dissector")
 int _dissect(struct __sk_buff *skb)
 {
 	if (!skb->vlan_present)
diff --git a/tools/testing/selftests/bpf/connect4_prog.c b/tools/testing/selftests/bpf/connect4_prog.c
index 5a88a681d2ab..b8395f3c43e9 100644
--- a/tools/testing/selftests/bpf/connect4_prog.c
+++ b/tools/testing/selftests/bpf/connect4_prog.c
@@ -21,23 +21,48 @@ int _version SEC("version") = 1;
 SEC("cgroup/connect4")
 int connect_v4_prog(struct bpf_sock_addr *ctx)
 {
+	struct bpf_sock_tuple tuple = {};
 	struct sockaddr_in sa;
+	struct bpf_sock *sk;
+
+	/* Verify that new destination is available. */
+	memset(&tuple.ipv4.saddr, 0, sizeof(tuple.ipv4.saddr));
+	memset(&tuple.ipv4.sport, 0, sizeof(tuple.ipv4.sport));
+
+	tuple.ipv4.daddr = bpf_htonl(DST_REWRITE_IP4);
+	tuple.ipv4.dport = bpf_htons(DST_REWRITE_PORT4);
+
+	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
+		return 0;
+	else if (ctx->type == SOCK_STREAM)
+		sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv4), 0, 0);
+	else
+		sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv4), 0, 0);
+
+	if (!sk)
+		return 0;
+
+	if (sk->src_ip4 != tuple.ipv4.daddr ||
+	    sk->src_port != DST_REWRITE_PORT4) {
+		bpf_sk_release(sk);
+		return 0;
+	}
+
+	bpf_sk_release(sk);
 
 	/* Rewrite destination. */
 	ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4);
 	ctx->user_port = bpf_htons(DST_REWRITE_PORT4);
 
-	if (ctx->type == SOCK_DGRAM || ctx->type == SOCK_STREAM) {
-		///* Rewrite source. */
-		memset(&sa, 0, sizeof(sa));
+	/* Rewrite source. */
+	memset(&sa, 0, sizeof(sa));
 
-		sa.sin_family = AF_INET;
-		sa.sin_port = bpf_htons(0);
-		sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4);
+	sa.sin_family = AF_INET;
+	sa.sin_port = bpf_htons(0);
+	sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4);
 
-		if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
-			return 0;
-	}
+	if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+		return 0;
 
 	return 1;
 }
diff --git a/tools/testing/selftests/bpf/connect6_prog.c b/tools/testing/selftests/bpf/connect6_prog.c
index 8ea3f7d12dee..25f5dc7b7aa0 100644
--- a/tools/testing/selftests/bpf/connect6_prog.c
+++ b/tools/testing/selftests/bpf/connect6_prog.c
@@ -29,7 +29,41 @@ int _version SEC("version") = 1;
 SEC("cgroup/connect6")
 int connect_v6_prog(struct bpf_sock_addr *ctx)
 {
+	struct bpf_sock_tuple tuple = {};
 	struct sockaddr_in6 sa;
+	struct bpf_sock *sk;
+
+	/* Verify that new destination is available. */
+	memset(&tuple.ipv6.saddr, 0, sizeof(tuple.ipv6.saddr));
+	memset(&tuple.ipv6.sport, 0, sizeof(tuple.ipv6.sport));
+
+	tuple.ipv6.daddr[0] = bpf_htonl(DST_REWRITE_IP6_0);
+	tuple.ipv6.daddr[1] = bpf_htonl(DST_REWRITE_IP6_1);
+	tuple.ipv6.daddr[2] = bpf_htonl(DST_REWRITE_IP6_2);
+	tuple.ipv6.daddr[3] = bpf_htonl(DST_REWRITE_IP6_3);
+
+	tuple.ipv6.dport = bpf_htons(DST_REWRITE_PORT6);
+
+	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
+		return 0;
+	else if (ctx->type == SOCK_STREAM)
+		sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv6), 0, 0);
+	else
+		sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv6), 0, 0);
+
+	if (!sk)
+		return 0;
+
+	if (sk->src_ip6[0] != tuple.ipv6.daddr[0] ||
+	    sk->src_ip6[1] != tuple.ipv6.daddr[1] ||
+	    sk->src_ip6[2] != tuple.ipv6.daddr[2] ||
+	    sk->src_ip6[3] != tuple.ipv6.daddr[3] ||
+	    sk->src_port != DST_REWRITE_PORT6) {
+		bpf_sk_release(sk);
+		return 0;
+	}
+
+	bpf_sk_release(sk);
 
 	/* Rewrite destination. */
 	ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0);
@@ -39,21 +73,19 @@ int connect_v6_prog(struct bpf_sock_addr *ctx)
 
 	ctx->user_port = bpf_htons(DST_REWRITE_PORT6);
 
-	if (ctx->type == SOCK_DGRAM || ctx->type == SOCK_STREAM) {
-		/* Rewrite source. */
-		memset(&sa, 0, sizeof(sa));
+	/* Rewrite source. */
+	memset(&sa, 0, sizeof(sa));
 
-		sa.sin6_family = AF_INET6;
-		sa.sin6_port = bpf_htons(0);
+	sa.sin6_family = AF_INET6;
+	sa.sin6_port = bpf_htons(0);
 
-		sa.sin6_addr.s6_addr32[0] = bpf_htonl(SRC_REWRITE_IP6_0);
-		sa.sin6_addr.s6_addr32[1] = bpf_htonl(SRC_REWRITE_IP6_1);
-		sa.sin6_addr.s6_addr32[2] = bpf_htonl(SRC_REWRITE_IP6_2);
-		sa.sin6_addr.s6_addr32[3] = bpf_htonl(SRC_REWRITE_IP6_3);
+	sa.sin6_addr.s6_addr32[0] = bpf_htonl(SRC_REWRITE_IP6_0);
+	sa.sin6_addr.s6_addr32[1] = bpf_htonl(SRC_REWRITE_IP6_1);
+	sa.sin6_addr.s6_addr32[2] = bpf_htonl(SRC_REWRITE_IP6_2);
+	sa.sin6_addr.s6_addr32[3] = bpf_htonl(SRC_REWRITE_IP6_3);
 
-		if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
-			return 0;
-	}
+	if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+		return 0;
 
 	return 1;
 }
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index f42b3396d622..bcbda7037840 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -5,6 +5,7 @@
 #include <linux/btf.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
+#include <linux/filter.h>
 #include <bpf/bpf.h>
 #include <sys/resource.h>
 #include <libelf.h>
@@ -22,9 +23,13 @@
 #include "bpf_rlimit.h"
 #include "bpf_util.h"
 
+#define MAX_INSNS	512
+#define MAX_SUBPROGS	16
+
 static uint32_t pass_cnt;
 static uint32_t error_cnt;
 static uint32_t skip_cnt;
+static bool jit_enabled;
 
 #define CHECK(condition, format...) ({					\
 	int __ret = !!(condition);					\
@@ -60,6 +65,24 @@ static int __base_pr(const char *format, ...)
 	return err;
 }
 
+static bool is_jit_enabled(void)
+{
+	const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
+	bool enabled = false;
+	int sysctl_fd;
+
+	sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
+	if (sysctl_fd != -1) {
+		char tmpc;
+
+		if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
+			enabled = (tmpc != '0');
+		close(sysctl_fd);
+	}
+
+	return enabled;
+}
+
 #define BTF_INFO_ENC(kind, root, vlen)			\
 	((!!(root) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
 
@@ -85,8 +108,20 @@ static int __base_pr(const char *format, ...)
 #define BTF_TYPEDEF_ENC(name, type) \
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type)
 
-#define BTF_PTR_ENC(name, type) \
-	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type)
+#define BTF_PTR_ENC(type) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type)
+
+#define BTF_CONST_ENC(type) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), type)
+
+#define BTF_FUNC_PROTO_ENC(ret_type, nargs) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, nargs), ret_type)
+
+#define BTF_FUNC_PROTO_ARG_ENC(name, type) \
+	(name), (type)
+
+#define BTF_FUNC_ENC(name, func_proto) \
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), func_proto)
 
 #define BTF_END_RAW 0xdeadbeef
 #define NAME_TBD 0xdeadb33f
@@ -103,6 +138,7 @@ static struct args {
 	bool get_info_test;
 	bool pprint_test;
 	bool always_log;
+	bool func_type_test;
 } args;
 
 static char btf_log_buf[BTF_LOG_BUF_SIZE];
@@ -1374,6 +1410,464 @@ static struct btf_raw_test raw_tests[] = {
 	.map_create_err = true,
 },
 
+{
+	.descr = "func proto (int (*)(int, unsigned int))",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* int (*)(int, unsigned int) */
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "func proto (vararg)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int, unsigned int, ...) */
+		BTF_FUNC_PROTO_ENC(0, 3),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+			BTF_FUNC_PROTO_ARG_ENC(0, 0),
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "func proto (vararg with name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int b, ... c) */
+		BTF_FUNC_PROTO_ENC(0, 3),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 0),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0b\0c",
+	.str_sec_size = sizeof("\0a\0b\0c"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid arg#3",
+},
+
+{
+	.descr = "func proto (arg after vararg)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, ..., unsigned int b) */
+		BTF_FUNC_PROTO_ENC(0, 3),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 0),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0b",
+	.str_sec_size = sizeof("\0a\0b"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid arg#2",
+},
+
+{
+	.descr = "func proto (CONST=>TYPEDEF=>PTR=>FUNC_PROTO)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* typedef void (*func_ptr)(int, unsigned int) */
+		BTF_TYPEDEF_ENC(NAME_TBD, 5),			/* [3] */
+		/* const func_ptr */
+		BTF_CONST_ENC(3),				/* [4] */
+		BTF_PTR_ENC(6),					/* [5] */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [6] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0func_ptr",
+	.str_sec_size = sizeof("\0func_ptr"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "func proto (CONST=>TYPEDEF=>FUNC_PROTO)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		BTF_CONST_ENC(4),				/* [3] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 5),			/* [4] */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [5] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0func_typedef",
+	.str_sec_size = sizeof("\0func_typedef"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid type_id",
+},
+
+{
+	.descr = "func proto (btf_resolve(arg))",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* void (*)(const void *) */
+		BTF_FUNC_PROTO_ENC(0, 1),			/* [2] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 3),
+		BTF_CONST_ENC(4),				/* [3] */
+		BTF_PTR_ENC(0),					/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "func proto (Not all arg has name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int, unsigned int b) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0b",
+	.str_sec_size = sizeof("\0b"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "func proto (Bad arg name_off)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int <bad_name_off>) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0xffffffff, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a",
+	.str_sec_size = sizeof("\0a"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid arg#2",
+},
+
+{
+	.descr = "func proto (Bad arg name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int !!!) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0!!!",
+	.str_sec_size = sizeof("\0a\0!!!"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid arg#2",
+},
+
+{
+	.descr = "func proto (Invalid return type)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* <bad_ret_type> (*)(int, unsigned int) */
+		BTF_FUNC_PROTO_ENC(100, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid return type",
+},
+
+{
+	.descr = "func proto (with func name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void func_proto(int, unsigned int) */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 2), 0),	/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0func_proto",
+	.str_sec_size = sizeof("\0func_proto"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid name",
+},
+
+{
+	.descr = "func proto (const void arg)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(const void) */
+		BTF_FUNC_PROTO_ENC(0, 1),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(0, 4),
+		BTF_CONST_ENC(0),				/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "",
+	.str_sec_size = sizeof(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid arg#1",
+},
+
+{
+	.descr = "func (void func(int a, unsigned int b))",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int b) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		/* void func(int a, unsigned int b) */
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0b\0func",
+	.str_sec_size = sizeof("\0a\0b\0func"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "func (No func name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int b) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		/* void <no_name>(int a, unsigned int b) */
+		BTF_FUNC_ENC(0, 3),				/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0b",
+	.str_sec_size = sizeof("\0a\0b"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid name",
+},
+
+{
+	.descr = "func (Invalid func name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int b) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		/* void !!!(int a, unsigned int b) */
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0b\0!!!",
+	.str_sec_size = sizeof("\0a\0b\0!!!"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid name",
+},
+
+{
+	.descr = "func (Some arg has no name)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(0, 2),
+		/* void func(int a, unsigned int) */
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0func",
+	.str_sec_size = sizeof("\0a\0func"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid arg#2",
+},
+
+{
+	.descr = "func (Non zero vlen)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
+		/* void (*)(int a, unsigned int b) */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		/* void func(int a, unsigned int b) */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 2), 3), 	/* [4] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0b\0func",
+	.str_sec_size = sizeof("\0a\0b\0func"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "vlen != 0",
+},
+
+{
+	.descr = "func (Not referring to FUNC_PROTO)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_FUNC_ENC(NAME_TBD, 1),			/* [2] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0func",
+	.str_sec_size = sizeof("\0func"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid type_id",
+},
+
 }; /* struct btf_raw_test raw_tests[] */
 
 static const char *get_next_str(const char *start, const char *end)
@@ -1940,13 +2434,13 @@ static struct btf_file_test file_tests[] = {
 },
 };
 
-static int file_has_btf_elf(const char *fn)
+static int file_has_btf_elf(const char *fn, bool *has_btf_ext)
 {
 	Elf_Scn *scn = NULL;
 	GElf_Ehdr ehdr;
+	int ret = 0;
 	int elf_fd;
 	Elf *elf;
-	int ret;
 
 	if (CHECK(elf_version(EV_CURRENT) == EV_NONE,
 		  "elf_version(EV_CURRENT) == EV_NONE"))
@@ -1978,14 +2472,12 @@ static int file_has_btf_elf(const char *fn)
 		}
 
 		sh_name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
-		if (!strcmp(sh_name, BTF_ELF_SEC)) {
+		if (!strcmp(sh_name, BTF_ELF_SEC))
 			ret = 1;
-			goto done;
-		}
+		if (!strcmp(sh_name, BTF_EXT_ELF_SEC))
+			*has_btf_ext = true;
 	}
 
-	ret = 0;
-
 done:
 	close(elf_fd);
 	elf_end(elf);
@@ -1995,15 +2487,24 @@ done:
 static int do_test_file(unsigned int test_num)
 {
 	const struct btf_file_test *test = &file_tests[test_num - 1];
+	const char *expected_fnames[] = {"_dummy_tracepoint",
+					 "test_long_fname_1",
+					 "test_long_fname_2"};
+	struct bpf_prog_info info = {};
 	struct bpf_object *obj = NULL;
+	struct bpf_func_info *finfo;
 	struct bpf_program *prog;
+	__u32 info_len, rec_size;
+	bool has_btf_ext = false;
+	struct btf *btf = NULL;
+	void *func_info = NULL;
 	struct bpf_map *map;
-	int err;
+	int i, err, prog_fd;
 
 	fprintf(stderr, "BTF libbpf test[%u] (%s): ", test_num,
 		test->file);
 
-	err = file_has_btf_elf(test->file);
+	err = file_has_btf_elf(test->file, &has_btf_ext);
 	if (err == -1)
 		return err;
 
@@ -2031,6 +2532,7 @@ static int do_test_file(unsigned int test_num)
 	err = bpf_object__load(obj);
 	if (CHECK(err < 0, "bpf_object__load: %d", err))
 		goto done;
+	prog_fd = bpf_program__fd(prog);
 
 	map = bpf_object__find_map_by_name(obj, "btf_map");
 	if (CHECK(!map, "btf_map not found")) {
@@ -2045,9 +2547,100 @@ static int do_test_file(unsigned int test_num)
 		  test->btf_kv_notfound))
 		goto done;
 
+	if (!jit_enabled || !has_btf_ext)
+		goto skip_jit;
+
+	/* get necessary program info */
+	info_len = sizeof(struct bpf_prog_info);
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+
+	if (CHECK(err == -1, "invalid get info (1st) errno:%d", errno)) {
+		fprintf(stderr, "%s\n", btf_log_buf);
+		err = -1;
+		goto done;
+	}
+	if (CHECK(info.func_info_cnt != 3,
+		  "incorrect info.func_info_cnt (1st) %d",
+		  info.func_info_cnt)) {
+		err = -1;
+		goto done;
+	}
+	rec_size = info.func_info_rec_size;
+	if (CHECK(rec_size < 4,
+		  "incorrect info.func_info_rec_size (1st) %d\n", rec_size)) {
+		err = -1;
+		goto done;
+	}
+
+	func_info = malloc(info.func_info_cnt * rec_size);
+	if (CHECK(!func_info, "out of memory")) {
+		err = -1;
+		goto done;
+	}
+
+	/* reset info to only retrieve func_info related data */
+	memset(&info, 0, sizeof(info));
+	info.func_info_cnt = 3;
+	info.func_info_rec_size = rec_size;
+	info.func_info = ptr_to_u64(func_info);
+
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+
+	if (CHECK(err == -1, "invalid get info (2nd) errno:%d", errno)) {
+		fprintf(stderr, "%s\n", btf_log_buf);
+		err = -1;
+		goto done;
+	}
+	if (CHECK(info.func_info_cnt != 3,
+		  "incorrect info.func_info_cnt (2nd) %d",
+		  info.func_info_cnt)) {
+		err = -1;
+		goto done;
+	}
+	if (CHECK(info.func_info_rec_size != rec_size,
+		  "incorrect info.func_info_rec_size (2nd) %d",
+		  info.func_info_rec_size)) {
+		err = -1;
+		goto done;
+	}
+
+	err = btf_get_from_id(info.btf_id, &btf);
+	if (CHECK(err, "cannot get btf from kernel, err: %d", err))
+		goto done;
+
+	/* check three functions */
+	finfo = func_info;
+	for (i = 0; i < 3; i++) {
+		const struct btf_type *t;
+		const char *fname;
+
+		t = btf__type_by_id(btf, finfo->type_id);
+		if (CHECK(!t, "btf__type_by_id failure: id %u",
+			  finfo->type_id)) {
+			err = -1;
+			goto done;
+		}
+
+		fname = btf__name_by_offset(btf, t->name_off);
+		err = strcmp(fname, expected_fnames[i]);
+		/* for the second and third functions in .text section,
+		 * the compiler may order them either way.
+		 */
+		if (i && err)
+			err = strcmp(fname, expected_fnames[3 - i]);
+		if (CHECK(err, "incorrect fname %s", fname ? : "")) {
+			err = -1;
+			goto done;
+		}
+
+		finfo = (void *)finfo + rec_size;
+	}
+
+skip_jit:
 	fprintf(stderr, "OK");
 
 done:
+	free(func_info);
 	bpf_object__close(obj);
 	return err;
 }
@@ -2477,16 +3070,310 @@ static int test_pprint(void)
 	return err;
 }
 
+static struct btf_func_type_test {
+	const char *descr;
+	const char *str_sec;
+	__u32 raw_types[MAX_NR_RAW_TYPES];
+	__u32 str_sec_size;
+	struct bpf_insn insns[MAX_INSNS];
+	__u32 prog_type;
+	__u32 func_info[MAX_SUBPROGS][2];
+	__u32 func_info_rec_size;
+	__u32 func_info_cnt;
+	bool expected_prog_load_failure;
+} func_type_test[] = {
+{
+	.descr = "func_type (main func + one sub)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),	/* [2] */
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [4] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [5] */
+		BTF_FUNC_ENC(NAME_TBD, 4),			/* [6] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB",
+	.str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"),
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info = { {0, 5}, {3, 6} },
+	.func_info_rec_size = 8,
+	.func_info_cnt = 2,
+},
+
+{
+	.descr = "func_type (Incorrect func_info_rec_size)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),	/* [2] */
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [4] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [5] */
+		BTF_FUNC_ENC(NAME_TBD, 4),			/* [6] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB",
+	.str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"),
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info = { {0, 5}, {3, 6} },
+	.func_info_rec_size = 4,
+	.func_info_cnt = 2,
+	.expected_prog_load_failure = true,
+},
+
+{
+	.descr = "func_type (Incorrect func_info_cnt)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),	/* [2] */
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [4] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [5] */
+		BTF_FUNC_ENC(NAME_TBD, 4),			/* [6] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB",
+	.str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"),
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info = { {0, 5}, {3, 6} },
+	.func_info_rec_size = 8,
+	.func_info_cnt = 1,
+	.expected_prog_load_failure = true,
+},
+
+{
+	.descr = "func_type (Incorrect bpf_func_info.insn_offset)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),	/* [2] */
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [3] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+		BTF_FUNC_PROTO_ENC(1, 2),			/* [4] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 2),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+		BTF_FUNC_ENC(NAME_TBD, 3),			/* [5] */
+		BTF_FUNC_ENC(NAME_TBD, 4),			/* [6] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB",
+	.str_sec_size = sizeof("\0int\0unsigned int\0a\0b\0c\0d\0funcA\0funcB"),
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info = { {0, 5}, {2, 6} },
+	.func_info_rec_size = 8,
+	.func_info_cnt = 2,
+	.expected_prog_load_failure = true,
+},
+
+};
+
+static size_t probe_prog_length(const struct bpf_insn *fp)
+{
+	size_t len;
+
+	for (len = MAX_INSNS - 1; len > 0; --len)
+		if (fp[len].code != 0 || fp[len].imm != 0)
+			break;
+	return len + 1;
+}
+
+static int do_test_func_type(int test_num)
+{
+	const struct btf_func_type_test *test = &func_type_test[test_num];
+	unsigned int raw_btf_size, info_len, rec_size;
+	int i, btf_fd = -1, prog_fd = -1, err = 0;
+	struct bpf_load_program_attr attr = {};
+	void *raw_btf, *func_info = NULL;
+	struct bpf_prog_info info = {};
+	struct bpf_func_info *finfo;
+
+	fprintf(stderr, "%s......", test->descr);
+	raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
+				 test->str_sec, test->str_sec_size,
+				 &raw_btf_size);
+
+	if (!raw_btf)
+		return -1;
+
+	*btf_log_buf = '\0';
+	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
+			      btf_log_buf, BTF_LOG_BUF_SIZE,
+			      args.always_log);
+	free(raw_btf);
+
+	if (CHECK(btf_fd == -1, "invalid btf_fd errno:%d", errno)) {
+		err = -1;
+		goto done;
+	}
+
+	if (*btf_log_buf && args.always_log)
+		fprintf(stderr, "\n%s", btf_log_buf);
+
+	attr.prog_type = test->prog_type;
+	attr.insns = test->insns;
+	attr.insns_cnt = probe_prog_length(attr.insns);
+	attr.license = "GPL";
+	attr.prog_btf_fd = btf_fd;
+	attr.func_info_rec_size = test->func_info_rec_size;
+	attr.func_info_cnt = test->func_info_cnt;
+	attr.func_info = test->func_info;
+
+	*btf_log_buf = '\0';
+	prog_fd = bpf_load_program_xattr(&attr, btf_log_buf,
+					 BTF_LOG_BUF_SIZE);
+	if (test->expected_prog_load_failure && prog_fd == -1) {
+		err = 0;
+		goto done;
+	}
+	if (CHECK(prog_fd == -1, "invalid prog_id errno:%d", errno)) {
+		fprintf(stderr, "%s\n", btf_log_buf);
+		err = -1;
+		goto done;
+	}
+	if (!jit_enabled) {
+		skip_cnt++;
+		fprintf(stderr, "SKIPPED, please enable sysctl bpf_jit_enable\n");
+		err = 0;
+		goto done;
+	}
+
+	/* get necessary lens */
+	info_len = sizeof(struct bpf_prog_info);
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	if (CHECK(err == -1, "invalid get info (1st) errno:%d", errno)) {
+		fprintf(stderr, "%s\n", btf_log_buf);
+		err = -1;
+		goto done;
+	}
+	if (CHECK(info.func_info_cnt != 2,
+		  "incorrect info.func_info_cnt (1st) %d\n",
+		  info.func_info_cnt)) {
+		err = -1;
+		goto done;
+	}
+	rec_size = info.func_info_rec_size;
+	if (CHECK(rec_size < 4,
+		  "incorrect info.func_info_rec_size (1st) %d\n", rec_size)) {
+		err = -1;
+		goto done;
+	}
+
+	func_info = malloc(info.func_info_cnt * rec_size);
+	if (CHECK(!func_info, "out of memory")) {
+		err = -1;
+		goto done;
+	}
+
+	/* reset info to only retrieve func_info related data */
+	memset(&info, 0, sizeof(info));
+	info.func_info_cnt = 2;
+	info.func_info_rec_size = rec_size;
+	info.func_info = ptr_to_u64(func_info);
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	if (CHECK(err == -1, "invalid get info (2nd) errno:%d", errno)) {
+		fprintf(stderr, "%s\n", btf_log_buf);
+		err = -1;
+		goto done;
+	}
+	if (CHECK(info.func_info_cnt != 2,
+		  "incorrect info.func_info_cnt (2nd) %d\n",
+		  info.func_info_cnt)) {
+		err = -1;
+		goto done;
+	}
+	if (CHECK(info.func_info_rec_size != rec_size,
+		  "incorrect info.func_info_rec_size (2nd) %d\n",
+		  info.func_info_rec_size)) {
+		err = -1;
+		goto done;
+	}
+
+	finfo = func_info;
+	for (i = 0; i < 2; i++) {
+		if (CHECK(finfo->type_id != test->func_info[i][1],
+			  "incorrect func_type %u expected %u",
+			  finfo->type_id, test->func_info[i][1])) {
+			err = -1;
+			goto done;
+		}
+		finfo = (void *)finfo + rec_size;
+	}
+
+done:
+	if (*btf_log_buf && (err || args.always_log))
+		fprintf(stderr, "\n%s", btf_log_buf);
+
+	if (btf_fd != -1)
+		close(btf_fd);
+	if (prog_fd != -1)
+		close(prog_fd);
+	free(func_info);
+	return err;
+}
+
+static int test_func_type(void)
+{
+	unsigned int i;
+	int err = 0;
+
+	for (i = 0; i < ARRAY_SIZE(func_type_test); i++)
+		err |= count_result(do_test_func_type(i));
+
+	return err;
+}
+
 static void usage(const char *cmd)
 {
-	fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] | [-g test_num (1 - %zu)] | [-f test_num (1 - %zu)] | [-p]]\n",
+	fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] |"
+			" [-g test_num (1 - %zu)] |"
+			" [-f test_num (1 - %zu)] | [-p] | [-k] ]\n",
 		cmd, ARRAY_SIZE(raw_tests), ARRAY_SIZE(get_info_tests),
 		ARRAY_SIZE(file_tests));
 }
 
 static int parse_args(int argc, char **argv)
 {
-	const char *optstr = "lpf:r:g:";
+	const char *optstr = "lpkf:r:g:";
 	int opt;
 
 	while ((opt = getopt(argc, argv, optstr)) != -1) {
@@ -2509,6 +3396,9 @@ static int parse_args(int argc, char **argv)
 		case 'p':
 			args.pprint_test = true;
 			break;
+		case 'k':
+			args.func_type_test = true;
+			break;
 		case 'h':
 			usage(argv[0]);
 			exit(0);
@@ -2562,6 +3452,8 @@ int main(int argc, char **argv)
 	if (args.always_log)
 		libbpf_set_print(__base_pr, __base_pr, __base_pr);
 
+	jit_enabled = is_jit_enabled();
+
 	if (args.raw_test)
 		err |= test_raw();
 
@@ -2574,8 +3466,11 @@ int main(int argc, char **argv)
 	if (args.pprint_test)
 		err |= test_pprint();
 
+	if (args.func_type_test)
+		err |= test_func_type();
+
 	if (args.raw_test || args.get_info_test || args.file_test ||
-	    args.pprint_test)
+	    args.pprint_test || args.func_type_test)
 		goto done;
 
 	err |= test_raw();
diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/test_btf_haskv.c
index b21b876f475d..e5c79fe0ffdb 100644
--- a/tools/testing/selftests/bpf/test_btf_haskv.c
+++ b/tools/testing/selftests/bpf/test_btf_haskv.c
@@ -24,8 +24,8 @@ struct dummy_tracepoint_args {
 	struct sock *sock;
 };
 
-SEC("dummy_tracepoint")
-int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+__attribute__((noinline))
+static int test_long_fname_2(struct dummy_tracepoint_args *arg)
 {
 	struct ipv_counts *counts;
 	int key = 0;
@@ -42,4 +42,16 @@ int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
 	return 0;
 }
 
+__attribute__((noinline))
+static int test_long_fname_1(struct dummy_tracepoint_args *arg)
+{
+	return test_long_fname_2(arg);
+}
+
+SEC("dummy_tracepoint")
+int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+{
+	return test_long_fname_1(arg);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_btf_nokv.c b/tools/testing/selftests/bpf/test_btf_nokv.c
index 0ed8e088eebf..434188c37774 100644
--- a/tools/testing/selftests/bpf/test_btf_nokv.c
+++ b/tools/testing/selftests/bpf/test_btf_nokv.c
@@ -22,8 +22,8 @@ struct dummy_tracepoint_args {
 	struct sock *sock;
 };
 
-SEC("dummy_tracepoint")
-int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+__attribute__((noinline))
+static int test_long_fname_2(struct dummy_tracepoint_args *arg)
 {
 	struct ipv_counts *counts;
 	int key = 0;
@@ -40,4 +40,16 @@ int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
 	return 0;
 }
 
+__attribute__((noinline))
+static int test_long_fname_1(struct dummy_tracepoint_args *arg)
+{
+	return test_long_fname_2(arg);
+}
+
+SEC("dummy_tracepoint")
+int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+{
+	return test_long_fname_1(arg);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh
index c0fb073b5eab..d23d4da66b83 100755
--- a/tools/testing/selftests/bpf/test_flow_dissector.sh
+++ b/tools/testing/selftests/bpf/test_flow_dissector.sh
@@ -59,7 +59,7 @@ else
 fi
 
 # Attach BPF program
-./flow_dissector_load -p bpf_flow.o -s dissect
+./flow_dissector_load -p bpf_flow.o -s flow_dissector
 
 # Setup
 tc qdisc add dev lo ingress
diff --git a/tools/testing/selftests/bpf/test_libbpf.sh b/tools/testing/selftests/bpf/test_libbpf.sh
index 156d89f1edcc..2989b2e2d856 100755
--- a/tools/testing/selftests/bpf/test_libbpf.sh
+++ b/tools/testing/selftests/bpf/test_libbpf.sh
@@ -33,17 +33,11 @@ trap exit_handler 0 2 3 6 9
 
 libbpf_open_file test_l4lb.o
 
-# TODO: fix libbpf to load noinline functions
-# [warning] libbpf: incorrect bpf_call opcode
-#libbpf_open_file test_l4lb_noinline.o
+# Load a program with BPF-to-BPF calls
+libbpf_open_file test_l4lb_noinline.o
 
-# TODO: fix test_xdp_meta.c to load with libbpf
-# [warning] libbpf: test_xdp_meta.o doesn't provide kernel version
-#libbpf_open_file test_xdp_meta.o
-
-# TODO: fix libbpf to handle .eh_frame
-# [warning] libbpf: relocation failed: no section(10)
-#libbpf_open_file ../../../../samples/bpf/tracex3_kern.o
+# Load a program compiled without the "-target bpf" flag
+libbpf_open_file test_xdp.o
 
 # Success
 exit 0
diff --git a/tools/testing/selftests/bpf/test_map_in_map.c b/tools/testing/selftests/bpf/test_map_in_map.c
new file mode 100644
index 000000000000..ce923e67e08e
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_map_in_map.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") mim_array = {
+	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	.key_size = sizeof(int),
+	/* must be sizeof(__u32) for map in map */
+	.value_size = sizeof(__u32),
+	.max_entries = 1,
+	.map_flags = 0,
+};
+
+struct bpf_map_def SEC("maps") mim_hash = {
+	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
+	.key_size = sizeof(int),
+	/* must be sizeof(__u32) for map in map */
+	.value_size = sizeof(__u32),
+	.max_entries = 1,
+	.map_flags = 0,
+};
+
+SEC("xdp_mimtest")
+int xdp_mimtest0(struct xdp_md *ctx)
+{
+	int value = 123;
+	int key = 0;
+	void *map;
+
+	map = bpf_map_lookup_elem(&mim_array, &key);
+	if (!map)
+		return XDP_DROP;
+
+	bpf_map_update_elem(map, &key, &value, 0);
+
+	map = bpf_map_lookup_elem(&mim_hash, &key);
+	if (!map)
+		return XDP_DROP;
+
+	bpf_map_update_elem(map, &key, &value, 0);
+
+	return XDP_PASS;
+}
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 4db2116e52be..9c79ee017df3 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -258,24 +258,36 @@ static void test_hashmap_percpu(int task, void *data)
 	close(fd);
 }
 
-static void test_hashmap_walk(int task, void *data)
+static int helper_fill_hashmap(int max_entries)
 {
-	int fd, i, max_entries = 1000;
-	long long key, value, next_key;
-	bool next_key_valid = true;
+	int i, fd, ret;
+	long long key, value;
 
 	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
 			    max_entries, map_flags);
-	if (fd < 0) {
-		printf("Failed to create hashmap '%s'!\n", strerror(errno));
-		exit(1);
-	}
+	CHECK(fd < 0,
+	      "failed to create hashmap",
+	      "err: %s, flags: 0x%x\n", strerror(errno), map_flags);
 
 	for (i = 0; i < max_entries; i++) {
 		key = i; value = key;
-		assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == 0);
+		ret = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+		CHECK(ret != 0,
+		      "can't update hashmap",
+		      "err: %s\n", strerror(ret));
 	}
 
+	return fd;
+}
+
+static void test_hashmap_walk(int task, void *data)
+{
+	int fd, i, max_entries = 1000;
+	long long key, value, next_key;
+	bool next_key_valid = true;
+
+	fd = helper_fill_hashmap(max_entries);
+
 	for (i = 0; bpf_map_get_next_key(fd, !i ? NULL : &key,
 					 &next_key) == 0; i++) {
 		key = next_key;
@@ -306,6 +318,39 @@ static void test_hashmap_walk(int task, void *data)
 	close(fd);
 }
 
+static void test_hashmap_zero_seed(void)
+{
+	int i, first, second, old_flags;
+	long long key, next_first, next_second;
+
+	old_flags = map_flags;
+	map_flags |= BPF_F_ZERO_SEED;
+
+	first = helper_fill_hashmap(3);
+	second = helper_fill_hashmap(3);
+
+	for (i = 0; ; i++) {
+		void *key_ptr = !i ? NULL : &key;
+
+		if (bpf_map_get_next_key(first, key_ptr, &next_first) != 0)
+			break;
+
+		CHECK(bpf_map_get_next_key(second, key_ptr, &next_second) != 0,
+		      "next_key for second map must succeed",
+		      "key_ptr: %p", key_ptr);
+		CHECK(next_first != next_second,
+		      "keys must match",
+		      "i: %d first: %lld second: %lld\n", i,
+		      next_first, next_second);
+
+		key = next_first;
+	}
+
+	map_flags = old_flags;
+	close(first);
+	close(second);
+}
+
 static void test_arraymap(int task, void *data)
 {
 	int key, next_key, fd;
@@ -1080,6 +1125,94 @@ out_sockmap:
 	exit(1);
 }
 
+#define MAPINMAP_PROG "./test_map_in_map.o"
+static void test_map_in_map(void)
+{
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	struct bpf_map *map;
+	int mim_fd, fd, err;
+	int pos = 0;
+
+	obj = bpf_object__open(MAPINMAP_PROG);
+
+	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int), sizeof(int),
+			    2, 0);
+	if (fd < 0) {
+		printf("Failed to create hashmap '%s'!\n", strerror(errno));
+		exit(1);
+	}
+
+	map = bpf_object__find_map_by_name(obj, "mim_array");
+	if (IS_ERR(map)) {
+		printf("Failed to load array of maps from test prog\n");
+		goto out_map_in_map;
+	}
+	err = bpf_map__set_inner_map_fd(map, fd);
+	if (err) {
+		printf("Failed to set inner_map_fd for array of maps\n");
+		goto out_map_in_map;
+	}
+
+	map = bpf_object__find_map_by_name(obj, "mim_hash");
+	if (IS_ERR(map)) {
+		printf("Failed to load hash of maps from test prog\n");
+		goto out_map_in_map;
+	}
+	err = bpf_map__set_inner_map_fd(map, fd);
+	if (err) {
+		printf("Failed to set inner_map_fd for hash of maps\n");
+		goto out_map_in_map;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		bpf_program__set_xdp(prog);
+	}
+	bpf_object__load(obj);
+
+	map = bpf_object__find_map_by_name(obj, "mim_array");
+	if (IS_ERR(map)) {
+		printf("Failed to load array of maps from test prog\n");
+		goto out_map_in_map;
+	}
+	mim_fd = bpf_map__fd(map);
+	if (mim_fd < 0) {
+		printf("Failed to get descriptor for array of maps\n");
+		goto out_map_in_map;
+	}
+
+	err = bpf_map_update_elem(mim_fd, &pos, &fd, 0);
+	if (err) {
+		printf("Failed to update array of maps\n");
+		goto out_map_in_map;
+	}
+
+	map = bpf_object__find_map_by_name(obj, "mim_hash");
+	if (IS_ERR(map)) {
+		printf("Failed to load hash of maps from test prog\n");
+		goto out_map_in_map;
+	}
+	mim_fd = bpf_map__fd(map);
+	if (mim_fd < 0) {
+		printf("Failed to get descriptor for hash of maps\n");
+		goto out_map_in_map;
+	}
+
+	err = bpf_map_update_elem(mim_fd, &pos, &fd, 0);
+	if (err) {
+		printf("Failed to update hash of maps\n");
+		goto out_map_in_map;
+	}
+
+	close(fd);
+	bpf_object__close(obj);
+	return;
+
+out_map_in_map:
+	close(fd);
+	exit(1);
+}
+
 #define MAP_SIZE (32 * 1024)
 
 static void test_map_large(void)
@@ -1534,6 +1667,7 @@ static void run_all_tests(void)
 	test_hashmap(0, NULL);
 	test_hashmap_percpu(0, NULL);
 	test_hashmap_walk(0, NULL);
+	test_hashmap_zero_seed();
 
 	test_arraymap(0, NULL);
 	test_arraymap_percpu(0, NULL);
@@ -1554,6 +1688,8 @@ static void run_all_tests(void)
 
 	test_queuemap(0, NULL);
 	test_stackmap(0, NULL);
+
+	test_map_in_map();
 }
 
 int main(void)
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 2d3c04f45530..c1e688f61061 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1703,7 +1703,7 @@ static void test_reference_tracking()
 	const char *file = "./test_sk_lookup_kern.o";
 	struct bpf_object *obj;
 	struct bpf_program *prog;
-	__u32 duration;
+	__u32 duration = 0;
 	int err = 0;
 
 	obj = bpf_object__open(file);
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index aeeb76a54d63..73b7493d4120 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -574,24 +574,44 @@ static int bind4_prog_load(const struct sock_addr_test *test)
 		/* if (sk.family == AF_INET && */
 		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, family)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 16),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 24),
 
 		/*     (sk.type == SOCK_DGRAM || sk.type == SOCK_STREAM) && */
 		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, type)),
 		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 1),
 		BPF_JMP_A(1),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 12),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 20),
 
 		/*     1st_byte_of_user_ip4 == expected && */
 		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, user_ip4)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 10),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 18),
+
+		/*     2nd_byte_of_user_ip4 == expected && */
+		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, user_ip4) + 1),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[1], 16),
+
+		/*     3rd_byte_of_user_ip4 == expected && */
+		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, user_ip4) + 2),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[2], 14),
+
+		/*     4th_byte_of_user_ip4 == expected && */
+		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, user_ip4) + 3),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[3], 12),
 
 		/*     1st_half_of_user_ip4 == expected && */
 		BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, user_ip4)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 8),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 10),
+
+		/*     2nd_half_of_user_ip4 == expected && */
+		BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, user_ip4) + 2),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[1], 8),
 
 		/*     whole_user_ip4 == expected) { */
 		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
diff --git a/tools/testing/selftests/bpf/test_tcpnotify.h b/tools/testing/selftests/bpf/test_tcpnotify.h
new file mode 100644
index 000000000000..8b6cea030bfc
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpnotify.h
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _TEST_TCPBPF_H
+#define _TEST_TCPBPF_H
+
+struct tcpnotify_globals {
+	__u32 total_retrans;
+	__u32 ncalls;
+};
+
+struct tcp_notifier {
+	__u8    type;
+	__u8    subtype;
+	__u8    source;
+	__u8    hash;
+};
+
+#define	TESTPORT	12877
+#endif
diff --git a/tools/testing/selftests/bpf/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/test_tcpnotify_kern.c
new file mode 100644
index 000000000000..edbca203ce2d
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpnotify_kern.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/tcp.h>
+#include <netinet/in.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+#include "test_tcpnotify.h"
+
+struct bpf_map_def SEC("maps") global_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct tcpnotify_globals),
+	.max_entries = 4,
+};
+
+struct bpf_map_def SEC("maps") perf_event_map = {
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(__u32),
+	.max_entries = 2,
+};
+
+int _version SEC("version") = 1;
+
+SEC("sockops")
+int bpf_testcb(struct bpf_sock_ops *skops)
+{
+	int rv = -1;
+	int op;
+
+	op = (int) skops->op;
+
+	if (bpf_ntohl(skops->remote_port) != TESTPORT) {
+		skops->reply = -1;
+		return 0;
+	}
+
+	switch (op) {
+	case BPF_SOCK_OPS_TIMEOUT_INIT:
+	case BPF_SOCK_OPS_RWND_INIT:
+	case BPF_SOCK_OPS_NEEDS_ECN:
+	case BPF_SOCK_OPS_BASE_RTT:
+	case BPF_SOCK_OPS_RTO_CB:
+		rv = 1;
+		break;
+
+	case BPF_SOCK_OPS_TCP_CONNECT_CB:
+	case BPF_SOCK_OPS_TCP_LISTEN_CB:
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		bpf_sock_ops_cb_flags_set(skops, (BPF_SOCK_OPS_RETRANS_CB_FLAG|
+					  BPF_SOCK_OPS_RTO_CB_FLAG));
+		rv = 1;
+		break;
+	case BPF_SOCK_OPS_RETRANS_CB: {
+			__u32 key = 0;
+			struct tcpnotify_globals g, *gp;
+			struct tcp_notifier msg = {
+				.type = 0xde,
+				.subtype = 0xad,
+				.source = 0xbe,
+				.hash = 0xef,
+			};
+
+			rv = 1;
+
+			/* Update results */
+			gp = bpf_map_lookup_elem(&global_map, &key);
+			if (!gp)
+				break;
+			g = *gp;
+			g.total_retrans = skops->total_retrans;
+			g.ncalls++;
+			bpf_map_update_elem(&global_map, &key, &g,
+					    BPF_ANY);
+			bpf_perf_event_output(skops, &perf_event_map,
+					      BPF_F_CURRENT_CPU,
+					      &msg, sizeof(msg));
+		}
+		break;
+	default:
+		rv = -1;
+	}
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c
new file mode 100644
index 000000000000..ff3c4522aed6
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <asm/types.h>
+#include <sys/syscall.h>
+#include <errno.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <sys/socket.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <sys/ioctl.h>
+#include <linux/rtnetlink.h>
+#include <signal.h>
+#include <linux/perf_event.h>
+
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
+#include "test_tcpnotify.h"
+#include "trace_helpers.h"
+
+#define SOCKET_BUFFER_SIZE (getpagesize() < 8192L ? getpagesize() : 8192L)
+
+pthread_t tid;
+int rx_callbacks;
+
+static int dummyfn(void *data, int size)
+{
+	struct tcp_notifier *t = data;
+
+	if (t->type != 0xde || t->subtype != 0xad ||
+	    t->source != 0xbe || t->hash != 0xef)
+		return 1;
+	rx_callbacks++;
+	return 0;
+}
+
+void tcp_notifier_poller(int fd)
+{
+	while (1)
+		perf_event_poller(fd, dummyfn);
+}
+
+static void *poller_thread(void *arg)
+{
+	int fd = *(int *)arg;
+
+	tcp_notifier_poller(fd);
+	return arg;
+}
+
+int verify_result(const struct tcpnotify_globals *result)
+{
+	return (result->ncalls > 0 && result->ncalls == rx_callbacks ? 0 : 1);
+}
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+			const char *name)
+{
+	struct bpf_map *map;
+
+	map = bpf_object__find_map_by_name(obj, name);
+	if (!map) {
+		printf("%s:FAIL:map '%s' not found\n", test, name);
+		return -1;
+	}
+	return bpf_map__fd(map);
+}
+
+static int setup_bpf_perf_event(int mapfd)
+{
+	struct perf_event_attr attr = {
+		.sample_type = PERF_SAMPLE_RAW,
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_BPF_OUTPUT,
+	};
+	int key = 0;
+	int pmu_fd;
+
+	pmu_fd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, 0);
+	if (pmu_fd < 0)
+		return pmu_fd;
+	bpf_map_update_elem(mapfd, &key, &pmu_fd, BPF_ANY);
+
+	ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+	return pmu_fd;
+}
+
+int main(int argc, char **argv)
+{
+	const char *file = "test_tcpnotify_kern.o";
+	int prog_fd, map_fd, perf_event_fd;
+	struct tcpnotify_globals g = {0};
+	const char *cg_path = "/foo";
+	int error = EXIT_FAILURE;
+	struct bpf_object *obj;
+	int cg_fd = -1;
+	__u32 key = 0;
+	int rv;
+	char test_script[80];
+	int pmu_fd;
+	cpu_set_t cpuset;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset);
+
+	if (setup_cgroup_environment())
+		goto err;
+
+	cg_fd = create_and_get_cgroup(cg_path);
+	if (!cg_fd)
+		goto err;
+
+	if (join_cgroup(cg_path))
+		goto err;
+
+	if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
+		printf("FAILED: load_bpf_file failed for: %s\n", file);
+		goto err;
+	}
+
+	rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+	if (rv) {
+		printf("FAILED: bpf_prog_attach: %d (%s)\n",
+		       error, strerror(errno));
+		goto err;
+	}
+
+	perf_event_fd = bpf_find_map(__func__, obj, "perf_event_map");
+	if (perf_event_fd < 0)
+		goto err;
+
+	map_fd = bpf_find_map(__func__, obj, "global_map");
+	if (map_fd < 0)
+		goto err;
+
+	pmu_fd = setup_bpf_perf_event(perf_event_fd);
+	if (pmu_fd < 0 || perf_event_mmap(pmu_fd) < 0)
+		goto err;
+
+	pthread_create(&tid, NULL, poller_thread, (void *)&pmu_fd);
+
+	sprintf(test_script,
+		"/usr/sbin/iptables -A INPUT -p tcp --dport %d -j DROP",
+		TESTPORT);
+	system(test_script);
+
+	sprintf(test_script,
+		"/usr/bin/nc 127.0.0.1 %d < /etc/passwd > /dev/null 2>&1 ",
+		TESTPORT);
+	system(test_script);
+
+	sprintf(test_script,
+		"/usr/sbin/iptables -D INPUT -p tcp --dport %d -j DROP",
+		TESTPORT);
+	system(test_script);
+
+	rv = bpf_map_lookup_elem(map_fd, &key, &g);
+	if (rv != 0) {
+		printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
+		goto err;
+	}
+
+	sleep(10);
+
+	if (verify_result(&g)) {
+		printf("FAILED: Wrong stats Expected %d calls, got %d\n",
+			g.ncalls, rx_callbacks);
+		goto err;
+	}
+
+	printf("PASSED!\n");
+	error = 0;
+err:
+	bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+	close(cg_fd);
+	cleanup_cgroup_environment();
+	return error;
+}
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 6f61df62f690..537a8f91af02 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -2026,29 +2026,27 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 	},
 	{
-		"check skb->hash byte load not permitted 1",
+		"check skb->hash byte load permitted 1",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
 				    offsetof(struct __sk_buff, hash) + 1),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid bpf_context access",
-		.result = REJECT,
+		.result = ACCEPT,
 	},
 	{
-		"check skb->hash byte load not permitted 2",
+		"check skb->hash byte load permitted 2",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
 				    offsetof(struct __sk_buff, hash) + 2),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid bpf_context access",
-		.result = REJECT,
+		.result = ACCEPT,
 	},
 	{
-		"check skb->hash byte load not permitted 3",
+		"check skb->hash byte load permitted 3",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 #if __BYTE_ORDER == __LITTLE_ENDIAN
@@ -2060,8 +2058,7 @@ static struct bpf_test tests[] = {
 #endif
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid bpf_context access",
-		.result = REJECT,
+		.result = ACCEPT,
 	},
 	{
 		"check cb access: byte, wrong type",
@@ -2173,7 +2170,7 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 	},
 	{
-		"check skb->hash half load not permitted",
+		"check skb->hash half load permitted 2",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 #if __BYTE_ORDER == __LITTLE_ENDIAN
@@ -2185,6 +2182,37 @@ static struct bpf_test tests[] = {
 #endif
 			BPF_EXIT_INSN(),
 		},
+		.result = ACCEPT,
+	},
+	{
+		"check skb->hash half load not permitted, unaligned 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+			BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, hash) + 1),
+#else
+			BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, hash) + 3),
+#endif
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "invalid bpf_context access",
+		.result = REJECT,
+	},
+	{
+		"check skb->hash half load not permitted, unaligned 3",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+			BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, hash) + 3),
+#else
+			BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, hash) + 1),
+#endif
+			BPF_EXIT_INSN(),
+		},
 		.errstr = "invalid bpf_context access",
 		.result = REJECT,
 	},
@@ -2418,6 +2446,10 @@ static struct bpf_test tests[] = {
 				    offsetof(struct __sk_buff, tc_index)),
 			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
 				    offsetof(struct __sk_buff, cb[3])),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, tstamp)),
+			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+				    offsetof(struct __sk_buff, tstamp)),
 			BPF_EXIT_INSN(),
 		},
 		.errstr_unpriv = "",
@@ -5270,6 +5302,31 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
 	{
+		"write tstamp from CGROUP_SKB",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+				    offsetof(struct __sk_buff, tstamp)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.result_unpriv = REJECT,
+		.errstr_unpriv = "invalid bpf_context access off=152 size=8",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"read tstamp from CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, tstamp)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
 		"multiple registers share map_lookup_elem result",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_1, 10),