22 files changed, 1727 insertions, 227 deletions
diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
index bc276388f432..68454ef28f58 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
@@ -25,6 +25,8 @@ GEN COMMANDS
 
 |	**bpftool** **gen object** *OUTPUT_FILE* *INPUT_FILE* [*INPUT_FILE*...]
 |	**bpftool** **gen skeleton** *FILE* [**name** *OBJECT_NAME*]
+|	**bpftool** **gen subskeleton** *FILE* [**name** *OBJECT_NAME*]
+|	**bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...]
 |	**bpftool** **gen help**
 
 DESCRIPTION
@@ -149,6 +151,50 @@ DESCRIPTION
 		  (non-read-only) data from userspace, with same simplicity
 		  as for BPF side.
 
+	**bpftool gen subskeleton** *FILE*
+		  Generate BPF subskeleton C header file for a given *FILE*.
+
+		  Subskeletons are similar to skeletons, except they do not own
+		  the corresponding maps, programs, or global variables. They
+		  require that the object file used to generate them is already
+		  loaded into a *bpf_object* by some other means.
+
+		  This functionality is useful when a library is included into a
+		  larger BPF program. A subskeleton for the library would have
+		  access to all objects and globals defined in it, without
+		  having to know about the larger program.
+
+		  Consequently, there are only two functions defined
+		  for subskeletons:
+
+		  - **example__open(bpf_object\*)**
+		    Instantiates a subskeleton from an already opened (but not
+		    necessarily loaded) **bpf_object**.
+
+		  - **example__destroy()**
+		    Frees the storage for the subskeleton but *does not* unload
+		    any BPF programs or maps.
+
+	**bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...]
+		  Generate a minimum BTF file as *OUTPUT*, derived from a given
+		  *INPUT* BTF file, containing all needed BTF types so one, or
+		  more, given eBPF objects CO-RE relocations may be satisfied.
+
+		  When kernels aren't compiled with CONFIG_DEBUG_INFO_BTF,
+		  libbpf, when loading an eBPF object, has to rely on external
+		  BTF files to be able to calculate CO-RE relocations.
+
+		  Usually, an external BTF file is built from existing kernel
+		  DWARF data using pahole. It contains all the types used by
+		  its respective kernel image and, because of that, is big.
+
+		  The min_core_btf feature builds smaller BTF files, customized
+		  to one or multiple eBPF objects, so they can be distributed
+		  together with an eBPF CO-RE based application, turning the
+		  application portable to different kernel versions.
+
+		  Check examples bellow for more information how to use it.
+
 	**bpftool gen help**
 		  Print short help message.
 
@@ -215,7 +261,9 @@ This is example BPF application with two BPF programs and a mix of BPF maps
 and global variables. Source code is split across two source code files.
 
 **$ clang -target bpf -g example1.bpf.c -o example1.bpf.o**
+
 **$ clang -target bpf -g example2.bpf.c -o example2.bpf.o**
+
 **$ bpftool gen object example.bpf.o example1.bpf.o example2.bpf.o**
 
 This set of commands compiles *example1.bpf.c* and *example2.bpf.c*
@@ -329,3 +377,70 @@ BPF ELF object file *example.bpf.o*.
   my_static_var: 7
 
 This is a stripped-out version of skeleton generated for above example code.
+
+min_core_btf
+------------
+
+**$ bpftool btf dump file 5.4.0-example.btf format raw**
+
+::
+
+  [1] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none)
+  [2] CONST '(anon)' type_id=1
+  [3] VOLATILE '(anon)' type_id=1
+  [4] ARRAY '(anon)' type_id=1 index_type_id=21 nr_elems=2
+  [5] PTR '(anon)' type_id=8
+  [6] CONST '(anon)' type_id=5
+  [7] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=(none)
+  [8] CONST '(anon)' type_id=7
+  [9] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none)
+  <long output>
+
+**$ bpftool btf dump file one.bpf.o format raw**
+
+::
+
+  [1] PTR '(anon)' type_id=2
+  [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=4
+        'ent' type_id=3 bits_offset=0
+        'id' type_id=7 bits_offset=64
+        'args' type_id=9 bits_offset=128
+        '__data' type_id=12 bits_offset=512
+  [3] STRUCT 'trace_entry' size=8 vlen=4
+        'type' type_id=4 bits_offset=0
+        'flags' type_id=5 bits_offset=16
+        'preempt_count' type_id=5 bits_offset=24
+  <long output>
+
+**$ bpftool gen min_core_btf 5.4.0-example.btf 5.4.0-smaller.btf one.bpf.o**
+
+**$ bpftool btf dump file 5.4.0-smaller.btf format raw**
+
+::
+
+  [1] TYPEDEF 'pid_t' type_id=6
+  [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=1
+        'args' type_id=4 bits_offset=128
+  [3] STRUCT 'task_struct' size=9216 vlen=2
+        'pid' type_id=1 bits_offset=17920
+        'real_parent' type_id=7 bits_offset=18048
+  [4] ARRAY '(anon)' type_id=5 index_type_id=8 nr_elems=6
+  [5] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none)
+  [6] TYPEDEF '__kernel_pid_t' type_id=8
+  [7] PTR '(anon)' type_id=3
+  [8] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED
+  <end>
+
+Now, the "5.4.0-smaller.btf" file may be used by libbpf as an external BTF file
+when loading the "one.bpf.o" object into the "5.4.0-example" kernel. Note that
+the generated BTF file won't allow other eBPF objects to be loaded, just the
+ones given to min_core_btf.
+
+::
+
+  LIBBPF_OPTS(bpf_object_open_opts, opts, .btf_custom_path = "5.4.0-smaller.btf");
+  struct bpf_object *obj;
+
+  obj = bpf_object__open_file("one.bpf.o", &opts);
+
+  ...
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 7084dd9fa2f8..6965c94dfdaf 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -20,7 +20,8 @@ SYNOPSIS
 
 	**bpftool** **version**
 
-	*OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** | **feature** }
+	*OBJECT* := { **map** | **program** | **link** | **cgroup** | **perf** | **net** | **feature** |
+	**btf** | **gen** | **struct_ops** | **iter** }
 
 	*OPTIONS* := { { **-V** | **--version** } | |COMMON_OPTIONS| }
 
@@ -31,6 +32,8 @@ SYNOPSIS
 	*PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** |
 	**load** | **attach** | **detach** | **help** }
 
+	*LINK-COMMANDS* := { **show** | **list** | **pin** | **detach** | **help** }
+
 	*CGROUP-COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** }
 
 	*PERF-COMMANDS* := { **show** | **list** | **help** }
@@ -39,6 +42,14 @@ SYNOPSIS
 
 	*FEATURE-COMMANDS* := { **probe** | **help** }
 
+	*BTF-COMMANDS* := { **show** | **list** | **dump** | **help** }
+
+	*GEN-COMMANDS* := { **object** | **skeleton** | **min_core_btf** | **help** }
+
+	*STRUCT-OPS-COMMANDS* := { **show** | **list** | **dump** | **register** | **unregister** | **help** }
+
+	*ITER-COMMANDS* := { **pin** | **help** }
+
 DESCRIPTION
 ===========
 	*bpftool* allows for inspection and simple modification of BPF objects
diff --git a/tools/bpf/bpftool/Documentation/common_options.rst b/tools/bpf/bpftool/Documentation/common_options.rst
index 908487b9c2ad..4107a586b68b 100644
--- a/tools/bpf/bpftool/Documentation/common_options.rst
+++ b/tools/bpf/bpftool/Documentation/common_options.rst
@@ -4,12 +4,13 @@
 	  Print short help message (similar to **bpftool help**).
 
 -V, --version
-	  Print version number (similar to **bpftool version**), and optional
-	  features that were included when bpftool was compiled. Optional
-	  features include linking against libbfd to provide the disassembler
-	  for JIT-ted programs (**bpftool prog dump jited**) and usage of BPF
-	  skeletons (some features like **bpftool prog profile** or showing
-	  pids associated to BPF objects may rely on it).
+	  Print bpftool's version number (similar to **bpftool version**), the
+	  number of the libbpf version in use, and optional features that were
+	  included when bpftool was compiled. Optional features include linking
+	  against libbfd to provide the disassembler for JIT-ted programs
+	  (**bpftool prog dump jited**) and usage of BPF skeletons (some
+	  features like **bpftool prog profile** or showing pids associated to
+	  BPF objects may rely on it).
 
 -j, --json
 	  Generate JSON output. For commands that cannot produce JSON, this
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 83369f55df61..c6d2c77d0252 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -18,37 +18,33 @@ BPF_DIR = $(srctree)/tools/lib/bpf
 ifneq ($(OUTPUT),)
   _OUTPUT := $(OUTPUT)
 else
-  _OUTPUT := $(CURDIR)
+  _OUTPUT := $(CURDIR)/
 endif
-BOOTSTRAP_OUTPUT := $(_OUTPUT)/bootstrap/
+BOOTSTRAP_OUTPUT := $(_OUTPUT)bootstrap/
 
-LIBBPF_OUTPUT := $(_OUTPUT)/libbpf/
+LIBBPF_OUTPUT := $(_OUTPUT)libbpf/
 LIBBPF_DESTDIR := $(LIBBPF_OUTPUT)
-LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)/include
+LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include
 LIBBPF_HDRS_DIR := $(LIBBPF_INCLUDE)/bpf
 LIBBPF := $(LIBBPF_OUTPUT)libbpf.a
 
 LIBBPF_BOOTSTRAP_OUTPUT := $(BOOTSTRAP_OUTPUT)libbpf/
 LIBBPF_BOOTSTRAP_DESTDIR := $(LIBBPF_BOOTSTRAP_OUTPUT)
-LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)/include
+LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)include
 LIBBPF_BOOTSTRAP_HDRS_DIR := $(LIBBPF_BOOTSTRAP_INCLUDE)/bpf
 LIBBPF_BOOTSTRAP := $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a
 
-# We need to copy hashmap.h and nlattr.h which is not otherwise exported by
-# libbpf, but still required by bpftool.
-LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h)
-LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h)
-
-ifeq ($(BPFTOOL_VERSION),)
-BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
-endif
+# We need to copy hashmap.h, nlattr.h, relo_core.h and libbpf_internal.h
+# which are not otherwise exported by libbpf, but still required by bpftool.
+LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h relo_core.h libbpf_internal.h)
+LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h relo_core.h libbpf_internal.h)
 
 $(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR) $(LIBBPF_BOOTSTRAP_HDRS_DIR):
 	$(QUIET_MKDIR)mkdir -p $@
 
 $(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT)
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) \
-		DESTDIR=$(LIBBPF_DESTDIR) prefix= $(LIBBPF) install_headers
+		DESTDIR=$(LIBBPF_DESTDIR:/=) prefix= $(LIBBPF) install_headers
 
 $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_DIR)
 	$(call QUIET_INSTALL, $@)
@@ -56,7 +52,7 @@ $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_
 
 $(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT)
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \
-		DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR) prefix= \
+		DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR:/=) prefix= \
 		ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) $@ install_headers
 
 $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR)
@@ -78,12 +74,14 @@ CFLAGS += -O2
 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers
 CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS))
 CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \
-	-I$(if $(OUTPUT),$(OUTPUT),.) \
+	-I$(or $(OUTPUT),.) \
 	-I$(LIBBPF_INCLUDE) \
 	-I$(srctree)/kernel/bpf/ \
 	-I$(srctree)/tools/include \
 	-I$(srctree)/tools/include/uapi
+ifneq ($(BPFTOOL_VERSION),)
 CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"'
+endif
 ifneq ($(EXTRA_CFLAGS),)
 CFLAGS += $(EXTRA_CFLAGS)
 endif
@@ -95,7 +93,7 @@ INSTALL ?= install
 RM ?= rm -f
 
 FEATURE_USER = .bpftool
-FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib libcap \
+FEATURE_TESTS = libbfd disassembler-four-args zlib libcap \
 	clang-bpf-co-re
 FEATURE_DISPLAY = libbfd disassembler-four-args zlib libcap \
 	clang-bpf-co-re
@@ -120,10 +118,6 @@ ifeq ($(feature-disassembler-four-args), 1)
 CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE
 endif
 
-ifeq ($(feature-reallocarray), 0)
-CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
-endif
-
 LIBS = $(LIBBPF) -lelf -lz
 LIBS_BOOTSTRAP = $(LIBBPF_BOOTSTRAP) -lelf -lz
 ifeq ($(feature-libcap), 1)
@@ -186,7 +180,7 @@ endif
 
 $(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP)
 	$(QUIET_CLANG)$(CLANG) \
-		-I$(if $(OUTPUT),$(OUTPUT),.) \
+		-I$(or $(OUTPUT),.) \
 		-I$(srctree)/tools/include/uapi/ \
 		-I$(LIBBPF_BOOTSTRAP_INCLUDE) \
 		-g -O2 -Wall -target bpf -c $< -o $@
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 493753a4962e..5df8d72c5179 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -1003,9 +1003,25 @@ _bpftool()
                             ;;
                     esac
                     ;;
+                subskeleton)
+                    case $prev in
+                        $command)
+                            _filedir
+                            return 0
+                            ;;
+                        *)
+                            _bpftool_once_attr 'name'
+                            return 0
+                            ;;
+                    esac
+                    ;;
+                min_core_btf)
+                    _filedir
+                    return 0
+                    ;;
                 *)
                     [[ $prev == $object ]] && \
-                        COMPREPLY=( $( compgen -W 'object skeleton help' -- "$cur" ) )
+                        COMPREPLY=( $( compgen -W 'object skeleton subskeleton help min_core_btf' -- "$cur" ) )
                     ;;
             esac
             ;;
diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index 59833125ac0a..a2c665beda87 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -902,7 +902,7 @@ static int do_show(int argc, char **argv)
 				      equal_fn_for_key_as_id, NULL);
 	btf_map_table = hashmap__new(hash_fn_for_key_as_id,
 				     equal_fn_for_key_as_id, NULL);
-	if (!btf_prog_table || !btf_map_table) {
+	if (IS_ERR(btf_prog_table) || IS_ERR(btf_map_table)) {
 		hashmap__free(btf_prog_table);
 		hashmap__free(btf_map_table);
 		if (fd >= 0)
diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index 3571a281c43f..effe136119d7 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -50,6 +50,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type,
 			 const char *attach_flags_str,
 			 int level)
 {
+	char prog_name[MAX_PROG_FULL_NAME];
 	struct bpf_prog_info info = {};
 	__u32 info_len = sizeof(info);
 	int prog_fd;
@@ -63,6 +64,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type,
 		return -1;
 	}
 
+	get_prog_full_name(&info, prog_fd, prog_name, sizeof(prog_name));
 	if (json_output) {
 		jsonw_start_object(json_wtr);
 		jsonw_uint_field(json_wtr, "id", info.id);
@@ -73,7 +75,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type,
 			jsonw_uint_field(json_wtr, "attach_type", attach_type);
 		jsonw_string_field(json_wtr, "attach_flags",
 				   attach_flags_str);
-		jsonw_string_field(json_wtr, "name", info.name);
+		jsonw_string_field(json_wtr, "name", prog_name);
 		jsonw_end_object(json_wtr);
 	} else {
 		printf("%s%-8u ", level ? "    " : "", info.id);
@@ -81,7 +83,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type,
 			printf("%-15s", attach_type_name[attach_type]);
 		else
 			printf("type %-10u", attach_type);
-		printf(" %-15s %-15s\n", attach_flags_str, info.name);
+		printf(" %-15s %-15s\n", attach_flags_str, prog_name);
 	}
 
 	close(prog_fd);
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index fa8eb8134344..0c1e06cf50b9 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -24,6 +24,7 @@
 #include <bpf/bpf.h>
 #include <bpf/hashmap.h>
 #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
+#include <bpf/btf.h>
 
 #include "main.h"
 
@@ -55,7 +56,6 @@ const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = {
 	[BPF_CGROUP_UDP6_RECVMSG]	= "recvmsg6",
 	[BPF_CGROUP_GETSOCKOPT]		= "getsockopt",
 	[BPF_CGROUP_SETSOCKOPT]		= "setsockopt",
-
 	[BPF_SK_SKB_STREAM_PARSER]	= "sk_skb_stream_parser",
 	[BPF_SK_SKB_STREAM_VERDICT]	= "sk_skb_stream_verdict",
 	[BPF_SK_SKB_VERDICT]		= "sk_skb_verdict",
@@ -75,6 +75,7 @@ const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = {
 	[BPF_SK_REUSEPORT_SELECT]	= "sk_skb_reuseport_select",
 	[BPF_SK_REUSEPORT_SELECT_OR_MIGRATE]	= "sk_skb_reuseport_select_or_migrate",
 	[BPF_PERF_EVENT]		= "perf_event",
+	[BPF_TRACE_KPROBE_MULTI]	= "trace_kprobe_multi",
 };
 
 void p_err(const char *fmt, ...)
@@ -304,6 +305,49 @@ const char *get_fd_type_name(enum bpf_obj_type type)
 	return names[type];
 }
 
+void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd,
+			char *name_buff, size_t buff_len)
+{
+	const char *prog_name = prog_info->name;
+	const struct btf_type *func_type;
+	const struct bpf_func_info finfo = {};
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	struct btf *prog_btf = NULL;
+
+	if (buff_len <= BPF_OBJ_NAME_LEN ||
+	    strlen(prog_info->name) < BPF_OBJ_NAME_LEN - 1)
+		goto copy_name;
+
+	if (!prog_info->btf_id || prog_info->nr_func_info == 0)
+		goto copy_name;
+
+	info.nr_func_info = 1;
+	info.func_info_rec_size = prog_info->func_info_rec_size;
+	if (info.func_info_rec_size > sizeof(finfo))
+		info.func_info_rec_size = sizeof(finfo);
+	info.func_info = ptr_to_u64(&finfo);
+
+	if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len))
+		goto copy_name;
+
+	prog_btf = btf__load_from_kernel_by_id(info.btf_id);
+	if (!prog_btf)
+		goto copy_name;
+
+	func_type = btf__type_by_id(prog_btf, finfo.type_id);
+	if (!func_type || !btf_is_func(func_type))
+		goto copy_name;
+
+	prog_name = btf__name_by_offset(prog_btf, func_type->name_off);
+
+copy_name:
+	snprintf(name_buff, buff_len, "%s", prog_name);
+
+	if (prog_btf)
+		btf__free(prog_btf);
+}
+
 int get_fd_type(int fd)
 {
 	char path[PATH_MAX];
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index e999159fa28d..290998c82de1 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -3,6 +3,7 @@
 
 #include <ctype.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <string.h>
 #include <unistd.h>
 #include <net/if.h>
@@ -45,6 +46,11 @@ static bool run_as_unprivileged;
 
 /* Miscellaneous utility functions */
 
+static bool grep(const char *buffer, const char *pattern)
+{
+	return !!strstr(buffer, pattern);
+}
+
 static bool check_procfs(void)
 {
 	struct statfs st_fs;
@@ -135,6 +141,32 @@ static void print_end_section(void)
 
 /* Probing functions */
 
+static int get_vendor_id(int ifindex)
+{
+	char ifname[IF_NAMESIZE], path[64], buf[8];
+	ssize_t len;
+	int fd;
+
+	if (!if_indextoname(ifindex, ifname))
+		return -1;
+
+	snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname);
+
+	fd = open(path, O_RDONLY | O_CLOEXEC);
+	if (fd < 0)
+		return -1;
+
+	len = read(fd, buf, sizeof(buf));
+	close(fd);
+	if (len < 0)
+		return -1;
+	if (len >= (ssize_t)sizeof(buf))
+		return -1;
+	buf[len] = '\0';
+
+	return strtol(buf, NULL, 0);
+}
+
 static int read_procfs(const char *path)
 {
 	char *endptr, *line = NULL;
@@ -175,7 +207,10 @@ static void probe_unprivileged_disabled(void)
 			printf("bpf() syscall for unprivileged users is enabled\n");
 			break;
 		case 1:
-			printf("bpf() syscall restricted to privileged users\n");
+			printf("bpf() syscall restricted to privileged users (without recovery)\n");
+			break;
+		case 2:
+			printf("bpf() syscall restricted to privileged users (admin can change)\n");
 			break;
 		case -1:
 			printf("Unable to retrieve required privileges for bpf() syscall\n");
@@ -478,6 +513,40 @@ static bool probe_bpf_syscall(const char *define_prefix)
 	return res;
 }
 
+static bool
+probe_prog_load_ifindex(enum bpf_prog_type prog_type,
+			const struct bpf_insn *insns, size_t insns_cnt,
+			char *log_buf, size_t log_buf_sz,
+			__u32 ifindex)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		    .log_buf = log_buf,
+		    .log_size = log_buf_sz,
+		    .log_level = log_buf ? 1 : 0,
+		    .prog_ifindex = ifindex,
+		   );
+	int fd;
+
+	errno = 0;
+	fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts);
+	if (fd >= 0)
+		close(fd);
+
+	return fd >= 0 && errno != EINVAL && errno != EOPNOTSUPP;
+}
+
+static bool probe_prog_type_ifindex(enum bpf_prog_type prog_type, __u32 ifindex)
+{
+	/* nfp returns -EINVAL on exit(0) with TC offload */
+	struct bpf_insn insns[2] = {
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_EXIT_INSN()
+	};
+
+	return probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns),
+				       NULL, 0, ifindex);
+}
+
 static void
 probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types,
 		const char *define_prefix, __u32 ifindex)
@@ -487,8 +556,7 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types,
 	size_t maxlen;
 	bool res;
 
-	if (ifindex)
-		/* Only test offload-able program types */
+	if (ifindex) {
 		switch (prog_type) {
 		case BPF_PROG_TYPE_SCHED_CLS:
 		case BPF_PROG_TYPE_XDP:
@@ -497,7 +565,11 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types,
 			return;
 		}
 
-	res = bpf_probe_prog_type(prog_type, ifindex);
+		res = probe_prog_type_ifindex(prog_type, ifindex);
+	} else {
+		res = libbpf_probe_bpf_prog_type(prog_type, NULL);
+	}
+
 #ifdef USE_LIBCAP
 	/* Probe may succeed even if program load fails, for unprivileged users
 	 * check that we did not fail because of insufficient permissions
@@ -526,6 +598,26 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types,
 			   define_prefix);
 }
 
+static bool probe_map_type_ifindex(enum bpf_map_type map_type, __u32 ifindex)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
+	int key_size, value_size, max_entries;
+	int fd;
+
+	opts.map_ifindex = ifindex;
+
+	key_size = sizeof(__u32);
+	value_size = sizeof(__u32);
+	max_entries = 1;
+
+	fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries,
+			    &opts);
+	if (fd >= 0)
+		close(fd);
+
+	return fd >= 0;
+}
+
 static void
 probe_map_type(enum bpf_map_type map_type, const char *define_prefix,
 	       __u32 ifindex)
@@ -535,7 +627,19 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix,
 	size_t maxlen;
 	bool res;
 
-	res = bpf_probe_map_type(map_type, ifindex);
+	if (ifindex) {
+		switch (map_type) {
+		case BPF_MAP_TYPE_HASH:
+		case BPF_MAP_TYPE_ARRAY:
+			break;
+		default:
+			return;
+		}
+
+		res = probe_map_type_ifindex(map_type, ifindex);
+	} else {
+		res = libbpf_probe_bpf_map_type(map_type, NULL);
+	}
 
 	/* Probe result depends on the success of map creation, no additional
 	 * check required for unprivileged users
@@ -559,6 +663,33 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix,
 			   define_prefix);
 }
 
+static bool
+probe_helper_ifindex(enum bpf_func_id id, enum bpf_prog_type prog_type,
+		     __u32 ifindex)
+{
+	struct bpf_insn insns[2] = {
+		BPF_EMIT_CALL(id),
+		BPF_EXIT_INSN()
+	};
+	char buf[4096] = {};
+	bool res;
+
+	probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), buf,
+				sizeof(buf), ifindex);
+	res = !grep(buf, "invalid func ") && !grep(buf, "unknown func ");
+
+	switch (get_vendor_id(ifindex)) {
+	case 0x19ee: /* Netronome specific */
+		res = res && !grep(buf, "not supported by FW") &&
+			!grep(buf, "unsupported function id");
+		break;
+	default:
+		break;
+	}
+
+	return res;
+}
+
 static void
 probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type,
 			  const char *define_prefix, unsigned int id,
@@ -567,7 +698,10 @@ probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type,
 	bool res = false;
 
 	if (supported_type) {
-		res = bpf_probe_helper(id, prog_type, ifindex);
+		if (ifindex)
+			res = probe_helper_ifindex(id, prog_type, ifindex);
+		else
+			res = libbpf_probe_bpf_helper(prog_type, id, NULL);
 #ifdef USE_LIBCAP
 		/* Probe may succeed even if program load fails, for
 		 * unprivileged users check that we did not fail because of
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index b4695df2ea3d..91af2850b505 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -14,6 +14,7 @@
 #include <unistd.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
+#include <bpf/libbpf_internal.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/mman.h>
@@ -63,11 +64,11 @@ static void get_obj_name(char *name, const char *file)
 	sanitize_identifier(name);
 }
 
-static void get_header_guard(char *guard, const char *obj_name)
+static void get_header_guard(char *guard, const char *obj_name, const char *suffix)
 {
 	int i;
 
-	sprintf(guard, "__%s_SKEL_H__", obj_name);
+	sprintf(guard, "__%s_%s__", obj_name, suffix);
 	for (i = 0; guard[i]; i++)
 		guard[i] = toupper(guard[i]);
 }
@@ -208,15 +209,47 @@ static int codegen_datasec_def(struct bpf_object *obj,
 	return 0;
 }
 
+static const struct btf_type *find_type_for_map(struct btf *btf, const char *map_ident)
+{
+	int n = btf__type_cnt(btf), i;
+	char sec_ident[256];
+
+	for (i = 1; i < n; i++) {
+		const struct btf_type *t = btf__type_by_id(btf, i);
+		const char *name;
+
+		if (!btf_is_datasec(t))
+			continue;
+
+		name = btf__str_by_offset(btf, t->name_off);
+		if (!get_datasec_ident(name, sec_ident, sizeof(sec_ident)))
+			continue;
+
+		if (strcmp(sec_ident, map_ident) == 0)
+			return t;
+	}
+	return NULL;
+}
+
+static bool is_internal_mmapable_map(const struct bpf_map *map, char *buf, size_t sz)
+{
+	if (!bpf_map__is_internal(map) || !(bpf_map__map_flags(map) & BPF_F_MMAPABLE))
+		return false;
+
+	if (!get_map_ident(map, buf, sz))
+		return false;
+
+	return true;
+}
+
 static int codegen_datasecs(struct bpf_object *obj, const char *obj_name)
 {
 	struct btf *btf = bpf_object__btf(obj);
-	int n = btf__type_cnt(btf);
 	struct btf_dump *d;
 	struct bpf_map *map;
 	const struct btf_type *sec;
-	char sec_ident[256], map_ident[256];
-	int i, err = 0;
+	char map_ident[256];
+	int err = 0;
 
 	d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL);
 	err = libbpf_get_error(d);
@@ -225,31 +258,10 @@ static int codegen_datasecs(struct bpf_object *obj, const char *obj_name)
 
 	bpf_object__for_each_map(map, obj) {
 		/* only generate definitions for memory-mapped internal maps */
-		if (!bpf_map__is_internal(map))
+		if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident)))
 			continue;
-		if (!(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
-			continue;
-
-		if (!get_map_ident(map, map_ident, sizeof(map_ident)))
-			continue;
-
-		sec = NULL;
-		for (i = 1; i < n; i++) {
-			const struct btf_type *t = btf__type_by_id(btf, i);
-			const char *name;
-
-			if (!btf_is_datasec(t))
-				continue;
-
-			name = btf__str_by_offset(btf, t->name_off);
-			if (!get_datasec_ident(name, sec_ident, sizeof(sec_ident)))
-				continue;
 
-			if (strcmp(sec_ident, map_ident) == 0) {
-				sec = t;
-				break;
-			}
-		}
+		sec = find_type_for_map(btf, map_ident);
 
 		/* In some cases (e.g., sections like .rodata.cst16 containing
 		 * compiler allocated string constants only) there will be
@@ -274,6 +286,96 @@ out:
 	return err;
 }
 
+static bool btf_is_ptr_to_func_proto(const struct btf *btf,
+				     const struct btf_type *v)
+{
+	return btf_is_ptr(v) && btf_is_func_proto(btf__type_by_id(btf, v->type));
+}
+
+static int codegen_subskel_datasecs(struct bpf_object *obj, const char *obj_name)
+{
+	struct btf *btf = bpf_object__btf(obj);
+	struct btf_dump *d;
+	struct bpf_map *map;
+	const struct btf_type *sec, *var;
+	const struct btf_var_secinfo *sec_var;
+	int i, err = 0, vlen;
+	char map_ident[256], sec_ident[256];
+	bool strip_mods = false, needs_typeof = false;
+	const char *sec_name, *var_name;
+	__u32 var_type_id;
+
+	d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL);
+	if (!d)
+		return -errno;
+
+	bpf_object__for_each_map(map, obj) {
+		/* only generate definitions for memory-mapped internal maps */
+		if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident)))
+			continue;
+
+		sec = find_type_for_map(btf, map_ident);
+		if (!sec)
+			continue;
+
+		sec_name = btf__name_by_offset(btf, sec->name_off);
+		if (!get_datasec_ident(sec_name, sec_ident, sizeof(sec_ident)))
+			continue;
+
+		strip_mods = strcmp(sec_name, ".kconfig") != 0;
+		printf("	struct %s__%s {\n", obj_name, sec_ident);
+
+		sec_var = btf_var_secinfos(sec);
+		vlen = btf_vlen(sec);
+		for (i = 0; i < vlen; i++, sec_var++) {
+			DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts,
+				.indent_level = 2,
+				.strip_mods = strip_mods,
+				/* we'll print the name separately */
+				.field_name = "",
+			);
+
+			var = btf__type_by_id(btf, sec_var->type);
+			var_name = btf__name_by_offset(btf, var->name_off);
+			var_type_id = var->type;
+
+			/* static variables are not exposed through BPF skeleton */
+			if (btf_var(var)->linkage == BTF_VAR_STATIC)
+				continue;
+
+			/* The datasec member has KIND_VAR but we want the
+			 * underlying type of the variable (e.g. KIND_INT).
+			 */
+			var = skip_mods_and_typedefs(btf, var->type, NULL);
+
+			printf("\t\t");
+			/* Func and array members require special handling.
+			 * Instead of producing `typename *var`, they produce
+			 * `typeof(typename) *var`. This allows us to keep a
+			 * similar syntax where the identifier is just prefixed
+			 * by *, allowing us to ignore C declaration minutiae.
+			 */
+			needs_typeof = btf_is_array(var) || btf_is_ptr_to_func_proto(btf, var);
+			if (needs_typeof)
+				printf("typeof(");
+
+			err = btf_dump__emit_type_decl(d, var_type_id, &opts);
+			if (err)
+				goto out;
+
+			if (needs_typeof)
+				printf(")");
+
+			printf(" *%s;\n", var_name);
+		}
+		printf("	} %s;\n", sec_ident);
+	}
+
+out:
+	btf_dump__free(d);
+	return err;
+}
+
 static void codegen(const char *template, ...)
 {
 	const char *src, *end;
@@ -362,6 +464,69 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map)
 	return map_sz;
 }
 
+/* Emit type size asserts for all top-level fields in memory-mapped internal maps. */
+static void codegen_asserts(struct bpf_object *obj, const char *obj_name)
+{
+	struct btf *btf = bpf_object__btf(obj);
+	struct bpf_map *map;
+	struct btf_var_secinfo *sec_var;
+	int i, vlen;
+	const struct btf_type *sec;
+	char map_ident[256], var_ident[256];
+
+	codegen("\
+		\n\
+		__attribute__((unused)) static void			    \n\
+		%1$s__assert(struct %1$s *s __attribute__((unused)))	    \n\
+		{							    \n\
+		#ifdef __cplusplus					    \n\
+		#define _Static_assert static_assert			    \n\
+		#endif							    \n\
+		", obj_name);
+
+	bpf_object__for_each_map(map, obj) {
+		if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident)))
+			continue;
+
+		sec = find_type_for_map(btf, map_ident);
+		if (!sec) {
+			/* best effort, couldn't find the type for this map */
+			continue;
+		}
+
+		sec_var = btf_var_secinfos(sec);
+		vlen =  btf_vlen(sec);
+
+		for (i = 0; i < vlen; i++, sec_var++) {
+			const struct btf_type *var = btf__type_by_id(btf, sec_var->type);
+			const char *var_name = btf__name_by_offset(btf, var->name_off);
+			long var_size;
+
+			/* static variables are not exposed through BPF skeleton */
+			if (btf_var(var)->linkage == BTF_VAR_STATIC)
+				continue;
+
+			var_size = btf__resolve_size(btf, var->type);
+			if (var_size < 0)
+				continue;
+
+			var_ident[0] = '\0';
+			strncat(var_ident, var_name, sizeof(var_ident) - 1);
+			sanitize_identifier(var_ident);
+
+			printf("\t_Static_assert(sizeof(s->%s->%s) == %ld, \"unexpected size of '%s'\");\n",
+			       map_ident, var_ident, var_size, var_ident);
+		}
+	}
+	codegen("\
+		\n\
+		#ifdef __cplusplus					    \n\
+		#undef _Static_assert					    \n\
+		#endif							    \n\
+		}							    \n\
+		");
+}
+
 static void codegen_attach_detach(struct bpf_object *obj, const char *obj_name)
 {
 	struct bpf_program *prog;
@@ -378,13 +543,16 @@ static void codegen_attach_detach(struct bpf_object *obj, const char *obj_name)
 				int prog_fd = skel->progs.%2$s.prog_fd;		    \n\
 			", obj_name, bpf_program__name(prog));
 
-		switch (bpf_program__get_type(prog)) {
+		switch (bpf_program__type(prog)) {
 		case BPF_PROG_TYPE_RAW_TRACEPOINT:
 			tp_name = strchr(bpf_program__section_name(prog), '/') + 1;
-			printf("\tint fd = bpf_raw_tracepoint_open(\"%s\", prog_fd);\n", tp_name);
+			printf("\tint fd = skel_raw_tracepoint_open(\"%s\", prog_fd);\n", tp_name);
 			break;
 		case BPF_PROG_TYPE_TRACING:
-			printf("\tint fd = bpf_raw_tracepoint_open(NULL, prog_fd);\n");
+			if (bpf_program__expected_attach_type(prog) == BPF_TRACE_ITER)
+				printf("\tint fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER);\n");
+			else
+				printf("\tint fd = skel_raw_tracepoint_open(NULL, prog_fd);\n");
 			break;
 		default:
 			printf("\tint fd = ((void)prog_fd, 0); /* auto-attach not supported */\n");
@@ -468,8 +636,8 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name)
 		if (!get_map_ident(map, ident, sizeof(ident)))
 			continue;
 		if (bpf_map__is_internal(map) &&
-		    (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
-			printf("\tmunmap(skel->%1$s, %2$zd);\n",
+		    (bpf_map__map_flags(map) & BPF_F_MMAPABLE))
+			printf("\tskel_free_map_data(skel->%1$s, skel->maps.%1$s.initial_value, %2$zd);\n",
 			       ident, bpf_map_mmap_sz(map));
 		codegen("\
 			\n\
@@ -478,7 +646,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name)
 	}
 	codegen("\
 		\n\
-			free(skel);					    \n\
+			skel_free(skel);				    \n\
 		}							    \n\
 		",
 		obj_name);
@@ -522,7 +690,7 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 		{							    \n\
 			struct %1$s *skel;				    \n\
 									    \n\
-			skel = calloc(sizeof(*skel), 1);		    \n\
+			skel = skel_alloc(sizeof(*skel));		    \n\
 			if (!skel)					    \n\
 				goto cleanup;				    \n\
 			skel->ctx.sz = (void *)&skel->links - (void *)skel; \n\
@@ -532,27 +700,22 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 		const void *mmap_data = NULL;
 		size_t mmap_size = 0;
 
-		if (!get_map_ident(map, ident, sizeof(ident)))
-			continue;
-
-		if (!bpf_map__is_internal(map) ||
-		    !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
+		if (!is_internal_mmapable_map(map, ident, sizeof(ident)))
 			continue;
 
 		codegen("\
-			\n\
-				skel->%1$s =					 \n\
-					mmap(NULL, %2$zd, PROT_READ | PROT_WRITE,\n\
-					     MAP_SHARED | MAP_ANONYMOUS, -1, 0); \n\
-				if (skel->%1$s == (void *) -1)			 \n\
-					goto cleanup;				 \n\
-				memcpy(skel->%1$s, (void *)\"\\			 \n\
-			", ident, bpf_map_mmap_sz(map));
+		\n\
+			skel->%1$s = skel_prep_map_data((void *)\"\\	    \n\
+		", ident);
 		mmap_data = bpf_map__initial_value(map, &mmap_size);
 		print_hex(mmap_data, mmap_size);
-		printf("\", %2$zd);\n"
-		       "\tskel->maps.%1$s.initial_value = (__u64)(long)skel->%1$s;\n",
-		       ident, mmap_size);
+		codegen("\
+		\n\
+		\", %1$zd, %2$zd);					    \n\
+			if (!skel->%3$s)				    \n\
+				goto cleanup;				    \n\
+			skel->maps.%3$s.initial_value = (__u64) (long) skel->%3$s;\n\
+		", bpf_map_mmap_sz(map), mmap_size, ident);
 	}
 	codegen("\
 		\n\
@@ -596,21 +759,21 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 	bpf_object__for_each_map(map, obj) {
 		const char *mmap_flags;
 
-		if (!get_map_ident(map, ident, sizeof(ident)))
-			continue;
-
-		if (!bpf_map__is_internal(map) ||
-		    !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
+		if (!is_internal_mmapable_map(map, ident, sizeof(ident)))
 			continue;
 
-		if (bpf_map__def(map)->map_flags & BPF_F_RDONLY_PROG)
+		if (bpf_map__map_flags(map) & BPF_F_RDONLY_PROG)
 			mmap_flags = "PROT_READ";
 		else
 			mmap_flags = "PROT_READ | PROT_WRITE";
 
-		printf("\tskel->%1$s =\n"
-		       "\t\tmmap(skel->%1$s, %2$zd, %3$s, MAP_SHARED | MAP_FIXED,\n"
-		       "\t\t\tskel->maps.%1$s.map_fd, 0);\n",
+		codegen("\
+		\n\
+			skel->%1$s = skel_finalize_map_data(&skel->maps.%1$s.initial_value,  \n\
+							%2$zd, %3$s, skel->maps.%1$s.map_fd);\n\
+			if (!skel->%1$s)				    \n\
+				return -ENOMEM;				    \n\
+			",
 		       ident, bpf_map_mmap_sz(map), mmap_flags);
 	}
 	codegen("\
@@ -632,8 +795,11 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 			}						    \n\
 			return skel;					    \n\
 		}							    \n\
+									    \n\
 		", obj_name);
 
+	codegen_asserts(obj, obj_name);
+
 	codegen("\
 		\n\
 									    \n\
@@ -645,10 +811,95 @@ out:
 	return err;
 }
 
+static void
+codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped)
+{
+	struct bpf_map *map;
+	char ident[256];
+	size_t i;
+
+	if (!map_cnt)
+		return;
+
+	codegen("\
+		\n\
+									\n\
+			/* maps */				    \n\
+			s->map_cnt = %zu;			    \n\
+			s->map_skel_sz = sizeof(*s->maps);	    \n\
+			s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\
+			if (!s->maps)				    \n\
+				goto err;			    \n\
+		",
+		map_cnt
+	);
+	i = 0;
+	bpf_object__for_each_map(map, obj) {
+		if (!get_map_ident(map, ident, sizeof(ident)))
+			continue;
+
+		codegen("\
+			\n\
+									\n\
+				s->maps[%zu].name = \"%s\";	    \n\
+				s->maps[%zu].map = &obj->maps.%s;   \n\
+			",
+			i, bpf_map__name(map), i, ident);
+		/* memory-mapped internal maps */
+		if (mmaped && is_internal_mmapable_map(map, ident, sizeof(ident))) {
+			printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n",
+				i, ident);
+		}
+		i++;
+	}
+}
+
+static void
+codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_links)
+{
+	struct bpf_program *prog;
+	int i;
+
+	if (!prog_cnt)
+		return;
+
+	codegen("\
+		\n\
+									\n\
+			/* programs */				    \n\
+			s->prog_cnt = %zu;			    \n\
+			s->prog_skel_sz = sizeof(*s->progs);	    \n\
+			s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\
+			if (!s->progs)				    \n\
+				goto err;			    \n\
+		",
+		prog_cnt
+	);
+	i = 0;
+	bpf_object__for_each_program(prog, obj) {
+		codegen("\
+			\n\
+									\n\
+				s->progs[%1$zu].name = \"%2$s\";    \n\
+				s->progs[%1$zu].prog = &obj->progs.%2$s;\n\
+			",
+			i, bpf_program__name(prog));
+
+		if (populate_links) {
+			codegen("\
+				\n\
+					s->progs[%1$zu].link = &obj->links.%2$s;\n\
+				",
+				i, bpf_program__name(prog));
+		}
+		i++;
+	}
+}
+
 static int do_skeleton(int argc, char **argv)
 {
 	char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")];
-	size_t i, map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz;
+	size_t map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz;
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
 	char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data;
 	struct bpf_object *obj = NULL;
@@ -739,7 +990,7 @@ static int do_skeleton(int argc, char **argv)
 		prog_cnt++;
 	}
 
-	get_header_guard(header_guard, obj_name);
+	get_header_guard(header_guard, obj_name, "SKEL_H");
 	if (use_loader) {
 		codegen("\
 		\n\
@@ -748,8 +999,6 @@ static int do_skeleton(int argc, char **argv)
 		#ifndef %2$s						    \n\
 		#define %2$s						    \n\
 									    \n\
-		#include <stdlib.h>					    \n\
-		#include <bpf/bpf.h>					    \n\
 		#include <bpf/skel_internal.h>				    \n\
 									    \n\
 		struct %1$s {						    \n\
@@ -827,6 +1076,16 @@ static int do_skeleton(int argc, char **argv)
 
 	codegen("\
 		\n\
+									    \n\
+		#ifdef __cplusplus					    \n\
+			static inline struct %1$s *open(const struct bpf_object_open_opts *opts = nullptr);\n\
+			static inline struct %1$s *open_and_load();	    \n\
+			static inline int load(struct %1$s *skel);	    \n\
+			static inline int attach(struct %1$s *skel);	    \n\
+			static inline void detach(struct %1$s *skel);	    \n\
+			static inline void destroy(struct %1$s *skel);	    \n\
+			static inline const void *elf_bytes(size_t *sz);    \n\
+		#endif /* __cplusplus */				    \n\
 		};							    \n\
 									    \n\
 		static void						    \n\
@@ -927,7 +1186,6 @@ static int do_skeleton(int argc, char **argv)
 			s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\
 			if (!s)						    \n\
 				goto err;				    \n\
-			obj->skeleton = s;				    \n\
 									    \n\
 			s->sz = sizeof(*s);				    \n\
 			s->name = \"%1$s\";				    \n\
@@ -935,71 +1193,16 @@ static int do_skeleton(int argc, char **argv)
 		",
 		obj_name
 	);
-	if (map_cnt) {
-		codegen("\
-			\n\
-									    \n\
-				/* maps */				    \n\
-				s->map_cnt = %zu;			    \n\
-				s->map_skel_sz = sizeof(*s->maps);	    \n\
-				s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\
-				if (!s->maps)				    \n\
-					goto err;			    \n\
-			",
-			map_cnt
-		);
-		i = 0;
-		bpf_object__for_each_map(map, obj) {
-			if (!get_map_ident(map, ident, sizeof(ident)))
-				continue;
 
-			codegen("\
-				\n\
-									    \n\
-					s->maps[%zu].name = \"%s\";	    \n\
-					s->maps[%zu].map = &obj->maps.%s;   \n\
-				",
-				i, bpf_map__name(map), i, ident);
-			/* memory-mapped internal maps */
-			if (bpf_map__is_internal(map) &&
-			    (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) {
-				printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n",
-				       i, ident);
-			}
-			i++;
-		}
-	}
-	if (prog_cnt) {
-		codegen("\
-			\n\
-									    \n\
-				/* programs */				    \n\
-				s->prog_cnt = %zu;			    \n\
-				s->prog_skel_sz = sizeof(*s->progs);	    \n\
-				s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\
-				if (!s->progs)				    \n\
-					goto err;			    \n\
-			",
-			prog_cnt
-		);
-		i = 0;
-		bpf_object__for_each_program(prog, obj) {
-			codegen("\
-				\n\
-									    \n\
-					s->progs[%1$zu].name = \"%2$s\";    \n\
-					s->progs[%1$zu].prog = &obj->progs.%2$s;\n\
-					s->progs[%1$zu].link = &obj->links.%2$s;\n\
-				",
-				i, bpf_program__name(prog));
-			i++;
-		}
-	}
+	codegen_maps_skeleton(obj, map_cnt, true /*mmaped*/);
+	codegen_progs_skeleton(obj, prog_cnt, true /*populate_links*/);
+
 	codegen("\
 		\n\
 									    \n\
 			s->data = (void *)%2$s__elf_bytes(&s->data_sz);	    \n\
 									    \n\
+			obj->skeleton = s;				    \n\
 			return 0;					    \n\
 		err:							    \n\
 			bpf_object__destroy_skeleton(s);		    \n\
@@ -1021,7 +1224,25 @@ static int do_skeleton(int argc, char **argv)
 		\";							    \n\
 		}							    \n\
 									    \n\
-		#endif /* %s */						    \n\
+		#ifdef __cplusplus					    \n\
+		struct %1$s *%1$s::open(const struct bpf_object_open_opts *opts) { return %1$s__open_opts(opts); }\n\
+		struct %1$s *%1$s::open_and_load() { return %1$s__open_and_load(); }	\n\
+		int %1$s::load(struct %1$s *skel) { return %1$s__load(skel); }		\n\
+		int %1$s::attach(struct %1$s *skel) { return %1$s__attach(skel); }	\n\
+		void %1$s::detach(struct %1$s *skel) { %1$s__detach(skel); }		\n\
+		void %1$s::destroy(struct %1$s *skel) { %1$s__destroy(skel); }		\n\
+		const void *%1$s::elf_bytes(size_t *sz) { return %1$s__elf_bytes(sz); } \n\
+		#endif /* __cplusplus */				    \n\
+									    \n\
+		",
+		obj_name);
+
+	codegen_asserts(obj, obj_name);
+
+	codegen("\
+		\n\
+									    \n\
+		#endif /* %1$s */					    \n\
 		",
 		header_guard);
 	err = 0;
@@ -1033,6 +1254,310 @@ out:
 	return err;
 }
 
+/* Subskeletons are like skeletons, except they don't own the bpf_object,
+ * associated maps, links, etc. Instead, they know about the existence of
+ * variables, maps, programs and are able to find their locations
+ * _at runtime_ from an already loaded bpf_object.
+ *
+ * This allows for library-like BPF objects to have userspace counterparts
+ * with access to their own items without having to know anything about the
+ * final BPF object that the library was linked into.
+ */
+static int do_subskeleton(int argc, char **argv)
+{
+	char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SUBSKEL_H__")];
+	size_t i, len, file_sz, map_cnt = 0, prog_cnt = 0, mmap_sz, var_cnt = 0, var_idx = 0;
+	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
+	char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data;
+	struct bpf_object *obj = NULL;
+	const char *file, *var_name;
+	char ident[256];
+	int fd, err = -1, map_type_id;
+	const struct bpf_map *map;
+	struct bpf_program *prog;
+	struct btf *btf;
+	const struct btf_type *map_type, *var_type;
+	const struct btf_var_secinfo *var;
+	struct stat st;
+
+	if (!REQ_ARGS(1)) {
+		usage();
+		return -1;
+	}
+	file = GET_ARG();
+
+	while (argc) {
+		if (!REQ_ARGS(2))
+			return -1;
+
+		if (is_prefix(*argv, "name")) {
+			NEXT_ARG();
+
+			if (obj_name[0] != '\0') {
+				p_err("object name already specified");
+				return -1;
+			}
+
+			strncpy(obj_name, *argv, MAX_OBJ_NAME_LEN - 1);
+			obj_name[MAX_OBJ_NAME_LEN - 1] = '\0';
+		} else {
+			p_err("unknown arg %s", *argv);
+			return -1;
+		}
+
+		NEXT_ARG();
+	}
+
+	if (argc) {
+		p_err("extra unknown arguments");
+		return -1;
+	}
+
+	if (use_loader) {
+		p_err("cannot use loader for subskeletons");
+		return -1;
+	}
+
+	if (stat(file, &st)) {
+		p_err("failed to stat() %s: %s", file, strerror(errno));
+		return -1;
+	}
+	file_sz = st.st_size;
+	mmap_sz = roundup(file_sz, sysconf(_SC_PAGE_SIZE));
+	fd = open(file, O_RDONLY);
+	if (fd < 0) {
+		p_err("failed to open() %s: %s", file, strerror(errno));
+		return -1;
+	}
+	obj_data = mmap(NULL, mmap_sz, PROT_READ, MAP_PRIVATE, fd, 0);
+	if (obj_data == MAP_FAILED) {
+		obj_data = NULL;
+		p_err("failed to mmap() %s: %s", file, strerror(errno));
+		goto out;
+	}
+	if (obj_name[0] == '\0')
+		get_obj_name(obj_name, file);
+
+	/* The empty object name allows us to use bpf_map__name and produce
+	 * ELF section names out of it. (".data" instead of "obj.data")
+	 */
+	opts.object_name = "";
+	obj = bpf_object__open_mem(obj_data, file_sz, &opts);
+	if (!obj) {
+		char err_buf[256];
+
+		libbpf_strerror(errno, err_buf, sizeof(err_buf));
+		p_err("failed to open BPF object file: %s", err_buf);
+		obj = NULL;
+		goto out;
+	}
+
+	btf = bpf_object__btf(obj);
+	if (!btf) {
+		err = -1;
+		p_err("need btf type information for %s", obj_name);
+		goto out;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		prog_cnt++;
+	}
+
+	/* First, count how many variables we have to find.
+	 * We need this in advance so the subskel can allocate the right
+	 * amount of storage.
+	 */
+	bpf_object__for_each_map(map, obj) {
+		if (!get_map_ident(map, ident, sizeof(ident)))
+			continue;
+
+		/* Also count all maps that have a name */
+		map_cnt++;
+
+		if (!is_internal_mmapable_map(map, ident, sizeof(ident)))
+			continue;
+
+		map_type_id = bpf_map__btf_value_type_id(map);
+		if (map_type_id <= 0) {
+			err = map_type_id;
+			goto out;
+		}
+		map_type = btf__type_by_id(btf, map_type_id);
+
+		var = btf_var_secinfos(map_type);
+		len = btf_vlen(map_type);
+		for (i = 0; i < len; i++, var++) {
+			var_type = btf__type_by_id(btf, var->type);
+
+			if (btf_var(var_type)->linkage == BTF_VAR_STATIC)
+				continue;
+
+			var_cnt++;
+		}
+	}
+
+	get_header_guard(header_guard, obj_name, "SUBSKEL_H");
+	codegen("\
+	\n\
+	/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */	    \n\
+									    \n\
+	/* THIS FILE IS AUTOGENERATED! */				    \n\
+	#ifndef %2$s							    \n\
+	#define %2$s							    \n\
+									    \n\
+	#include <errno.h>						    \n\
+	#include <stdlib.h>						    \n\
+	#include <bpf/libbpf.h>						    \n\
+									    \n\
+	struct %1$s {							    \n\
+		struct bpf_object *obj;					    \n\
+		struct bpf_object_subskeleton *subskel;			    \n\
+	", obj_name, header_guard);
+
+	if (map_cnt) {
+		printf("\tstruct {\n");
+		bpf_object__for_each_map(map, obj) {
+			if (!get_map_ident(map, ident, sizeof(ident)))
+				continue;
+			printf("\t\tstruct bpf_map *%s;\n", ident);
+		}
+		printf("\t} maps;\n");
+	}
+
+	if (prog_cnt) {
+		printf("\tstruct {\n");
+		bpf_object__for_each_program(prog, obj) {
+			printf("\t\tstruct bpf_program *%s;\n",
+				bpf_program__name(prog));
+		}
+		printf("\t} progs;\n");
+	}
+
+	err = codegen_subskel_datasecs(obj, obj_name);
+	if (err)
+		goto out;
+
+	/* emit code that will allocate enough storage for all symbols */
+	codegen("\
+		\n\
+									    \n\
+		#ifdef __cplusplus					    \n\
+			static inline struct %1$s *open(const struct bpf_object *src);\n\
+			static inline void destroy(struct %1$s *skel);	    \n\
+		#endif /* __cplusplus */				    \n\
+		};							    \n\
+									    \n\
+		static inline void					    \n\
+		%1$s__destroy(struct %1$s *skel)			    \n\
+		{							    \n\
+			if (!skel)					    \n\
+				return;					    \n\
+			if (skel->subskel)				    \n\
+				bpf_object__destroy_subskeleton(skel->subskel);\n\
+			free(skel);					    \n\
+		}							    \n\
+									    \n\
+		static inline struct %1$s *				    \n\
+		%1$s__open(const struct bpf_object *src)		    \n\
+		{							    \n\
+			struct %1$s *obj;				    \n\
+			struct bpf_object_subskeleton *s;		    \n\
+			int err;					    \n\
+									    \n\
+			obj = (struct %1$s *)calloc(1, sizeof(*obj));	    \n\
+			if (!obj) {					    \n\
+				errno = ENOMEM;				    \n\
+				goto err;				    \n\
+			}						    \n\
+			s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\
+			if (!s) {					    \n\
+				errno = ENOMEM;				    \n\
+				goto err;				    \n\
+			}						    \n\
+			s->sz = sizeof(*s);				    \n\
+			s->obj = src;					    \n\
+			s->var_skel_sz = sizeof(*s->vars);		    \n\
+			obj->subskel = s;				    \n\
+									    \n\
+			/* vars */					    \n\
+			s->var_cnt = %2$d;				    \n\
+			s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\
+			if (!s->vars) {					    \n\
+				errno = ENOMEM;				    \n\
+				goto err;				    \n\
+			}						    \n\
+		",
+		obj_name, var_cnt
+	);
+
+	/* walk through each symbol and emit the runtime representation */
+	bpf_object__for_each_map(map, obj) {
+		if (!is_internal_mmapable_map(map, ident, sizeof(ident)))
+			continue;
+
+		map_type_id = bpf_map__btf_value_type_id(map);
+		if (map_type_id <= 0)
+			/* skip over internal maps with no type*/
+			continue;
+
+		map_type = btf__type_by_id(btf, map_type_id);
+		var = btf_var_secinfos(map_type);
+		len = btf_vlen(map_type);
+		for (i = 0; i < len; i++, var++) {
+			var_type = btf__type_by_id(btf, var->type);
+			var_name = btf__name_by_offset(btf, var_type->name_off);
+
+			if (btf_var(var_type)->linkage == BTF_VAR_STATIC)
+				continue;
+
+			/* Note that we use the dot prefix in .data as the
+			 * field access operator i.e. maps%s becomes maps.data
+			 */
+			codegen("\
+			\n\
+									    \n\
+				s->vars[%3$d].name = \"%1$s\";		    \n\
+				s->vars[%3$d].map = &obj->maps.%2$s;	    \n\
+				s->vars[%3$d].addr = (void **) &obj->%2$s.%1$s;\n\
+			", var_name, ident, var_idx);
+
+			var_idx++;
+		}
+	}
+
+	codegen_maps_skeleton(obj, map_cnt, false /*mmaped*/);
+	codegen_progs_skeleton(obj, prog_cnt, false /*links*/);
+
+	codegen("\
+		\n\
+									    \n\
+			err = bpf_object__open_subskeleton(s);		    \n\
+			if (err)					    \n\
+				goto err;				    \n\
+									    \n\
+			return obj;					    \n\
+		err:							    \n\
+			%1$s__destroy(obj);				    \n\
+			return NULL;					    \n\
+		}							    \n\
+									    \n\
+		#ifdef __cplusplus					    \n\
+		struct %1$s *%1$s::open(const struct bpf_object *src) { return %1$s__open(src); }\n\
+		void %1$s::destroy(struct %1$s *skel) { %1$s__destroy(skel); }\n\
+		#endif /* __cplusplus */				    \n\
+									    \n\
+		#endif /* %2$s */					    \n\
+		",
+		obj_name, header_guard);
+	err = 0;
+out:
+	bpf_object__close(obj);
+	if (obj_data)
+		munmap(obj_data, mmap_sz);
+	close(fd);
+	return err;
+}
+
 static int do_object(int argc, char **argv)
 {
 	struct bpf_linker *linker;
@@ -1084,6 +1609,8 @@ static int do_help(int argc, char **argv)
 	fprintf(stderr,
 		"Usage: %1$s %2$s object OUTPUT_FILE INPUT_FILE [INPUT_FILE...]\n"
 		"       %1$s %2$s skeleton FILE [name OBJECT_NAME]\n"
+		"       %1$s %2$s subskeleton FILE [name OBJECT_NAME]\n"
+		"       %1$s %2$s min_core_btf INPUT OUTPUT OBJECT [OBJECT...]\n"
 		"       %1$s %2$s help\n"
 		"\n"
 		"       " HELP_SPEC_OPTIONS " |\n"
@@ -1094,10 +1621,594 @@ static int do_help(int argc, char **argv)
 	return 0;
 }
 
+static int btf_save_raw(const struct btf *btf, const char *path)
+{
+	const void *data;
+	FILE *f = NULL;
+	__u32 data_sz;
+	int err = 0;
+
+	data = btf__raw_data(btf, &data_sz);
+	if (!data)
+		return -ENOMEM;
+
+	f = fopen(path, "wb");
+	if (!f)
+		return -errno;
+
+	if (fwrite(data, 1, data_sz, f) != data_sz)
+		err = -errno;
+
+	fclose(f);
+	return err;
+}
+
+struct btfgen_info {
+	struct btf *src_btf;
+	struct btf *marked_btf; /* btf structure used to mark used types */
+};
+
+static size_t btfgen_hash_fn(const void *key, void *ctx)
+{
+	return (size_t)key;
+}
+
+static bool btfgen_equal_fn(const void *k1, const void *k2, void *ctx)
+{
+	return k1 == k2;
+}
+
+static void *u32_as_hash_key(__u32 x)
+{
+	return (void *)(uintptr_t)x;
+}
+
+static void btfgen_free_info(struct btfgen_info *info)
+{
+	if (!info)
+		return;
+
+	btf__free(info->src_btf);
+	btf__free(info->marked_btf);
+
+	free(info);
+}
+
+static struct btfgen_info *
+btfgen_new_info(const char *targ_btf_path)
+{
+	struct btfgen_info *info;
+	int err;
+
+	info = calloc(1, sizeof(*info));
+	if (!info)
+		return NULL;
+
+	info->src_btf = btf__parse(targ_btf_path, NULL);
+	if (!info->src_btf) {
+		err = -errno;
+		p_err("failed parsing '%s' BTF file: %s", targ_btf_path, strerror(errno));
+		goto err_out;
+	}
+
+	info->marked_btf = btf__parse(targ_btf_path, NULL);
+	if (!info->marked_btf) {
+		err = -errno;
+		p_err("failed parsing '%s' BTF file: %s", targ_btf_path, strerror(errno));
+		goto err_out;
+	}
+
+	return info;
+
+err_out:
+	btfgen_free_info(info);
+	errno = -err;
+	return NULL;
+}
+
+#define MARKED UINT32_MAX
+
+static void btfgen_mark_member(struct btfgen_info *info, int type_id, int idx)
+{
+	const struct btf_type *t = btf__type_by_id(info->marked_btf, type_id);
+	struct btf_member *m = btf_members(t) + idx;
+
+	m->name_off = MARKED;
+}
+
+static int
+btfgen_mark_type(struct btfgen_info *info, unsigned int type_id, bool follow_pointers)
+{
+	const struct btf_type *btf_type = btf__type_by_id(info->src_btf, type_id);
+	struct btf_type *cloned_type;
+	struct btf_param *param;
+	struct btf_array *array;
+	int err, i;
+
+	if (type_id == 0)
+		return 0;
+
+	/* mark type on cloned BTF as used */
+	cloned_type = (struct btf_type *) btf__type_by_id(info->marked_btf, type_id);
+	cloned_type->name_off = MARKED;
+
+	/* recursively mark other types needed by it */
+	switch (btf_kind(btf_type)) {
+	case BTF_KIND_UNKN:
+	case BTF_KIND_INT:
+	case BTF_KIND_FLOAT:
+	case BTF_KIND_ENUM:
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+		break;
+	case BTF_KIND_PTR:
+		if (follow_pointers) {
+			err = btfgen_mark_type(info, btf_type->type, follow_pointers);
+			if (err)
+				return err;
+		}
+		break;
+	case BTF_KIND_CONST:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_TYPEDEF:
+		err = btfgen_mark_type(info, btf_type->type, follow_pointers);
+		if (err)
+			return err;
+		break;
+	case BTF_KIND_ARRAY:
+		array = btf_array(btf_type);
+
+		/* mark array type */
+		err = btfgen_mark_type(info, array->type, follow_pointers);
+		/* mark array's index type */
+		err = err ? : btfgen_mark_type(info, array->index_type, follow_pointers);
+		if (err)
+			return err;
+		break;
+	case BTF_KIND_FUNC_PROTO:
+		/* mark ret type */
+		err = btfgen_mark_type(info, btf_type->type, follow_pointers);
+		if (err)
+			return err;
+
+		/* mark parameters types */
+		param = btf_params(btf_type);
+		for (i = 0; i < btf_vlen(btf_type); i++) {
+			err = btfgen_mark_type(info, param->type, follow_pointers);
+			if (err)
+				return err;
+			param++;
+		}
+		break;
+	/* tells if some other type needs to be handled */
+	default:
+		p_err("unsupported kind: %s (%d)", btf_kind_str(btf_type), type_id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int btfgen_record_field_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec)
+{
+	struct btf *btf = info->src_btf;
+	const struct btf_type *btf_type;
+	struct btf_member *btf_member;
+	struct btf_array *array;
+	unsigned int type_id = targ_spec->root_type_id;
+	int idx, err;
+
+	/* mark root type */
+	btf_type = btf__type_by_id(btf, type_id);
+	err = btfgen_mark_type(info, type_id, false);
+	if (err)
+		return err;
+
+	/* mark types for complex types (arrays, unions, structures) */
+	for (int i = 1; i < targ_spec->raw_len; i++) {
+		/* skip typedefs and mods */
+		while (btf_is_mod(btf_type) || btf_is_typedef(btf_type)) {
+			type_id = btf_type->type;
+			btf_type = btf__type_by_id(btf, type_id);
+		}
+
+		switch (btf_kind(btf_type)) {
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+			idx = targ_spec->raw_spec[i];
+			btf_member = btf_members(btf_type) + idx;
+
+			/* mark member */
+			btfgen_mark_member(info, type_id, idx);
+
+			/* mark member's type */
+			type_id = btf_member->type;
+			btf_type = btf__type_by_id(btf, type_id);
+			err = btfgen_mark_type(info, type_id, false);
+			if (err)
+				return err;
+			break;
+		case BTF_KIND_ARRAY:
+			array = btf_array(btf_type);
+			type_id = array->type;
+			btf_type = btf__type_by_id(btf, type_id);
+			break;
+		default:
+			p_err("unsupported kind: %s (%d)",
+			      btf_kind_str(btf_type), btf_type->type);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int btfgen_record_type_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec)
+{
+	return btfgen_mark_type(info, targ_spec->root_type_id, true);
+}
+
+static int btfgen_record_enumval_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec)
+{
+	return btfgen_mark_type(info, targ_spec->root_type_id, false);
+}
+
+static int btfgen_record_reloc(struct btfgen_info *info, struct bpf_core_spec *res)
+{
+	switch (res->relo_kind) {
+	case BPF_CORE_FIELD_BYTE_OFFSET:
+	case BPF_CORE_FIELD_BYTE_SIZE:
+	case BPF_CORE_FIELD_EXISTS:
+	case BPF_CORE_FIELD_SIGNED:
+	case BPF_CORE_FIELD_LSHIFT_U64:
+	case BPF_CORE_FIELD_RSHIFT_U64:
+		return btfgen_record_field_relo(info, res);
+	case BPF_CORE_TYPE_ID_LOCAL: /* BPF_CORE_TYPE_ID_LOCAL doesn't require kernel BTF */
+		return 0;
+	case BPF_CORE_TYPE_ID_TARGET:
+	case BPF_CORE_TYPE_EXISTS:
+	case BPF_CORE_TYPE_SIZE:
+		return btfgen_record_type_relo(info, res);
+	case BPF_CORE_ENUMVAL_EXISTS:
+	case BPF_CORE_ENUMVAL_VALUE:
+		return btfgen_record_enumval_relo(info, res);
+	default:
+		return -EINVAL;
+	}
+}
+
+static struct bpf_core_cand_list *
+btfgen_find_cands(const struct btf *local_btf, const struct btf *targ_btf, __u32 local_id)
+{
+	const struct btf_type *local_type;
+	struct bpf_core_cand_list *cands = NULL;
+	struct bpf_core_cand local_cand = {};
+	size_t local_essent_len;
+	const char *local_name;
+	int err;
+
+	local_cand.btf = local_btf;
+	local_cand.id = local_id;
+
+	local_type = btf__type_by_id(local_btf, local_id);
+	if (!local_type) {
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	local_name = btf__name_by_offset(local_btf, local_type->name_off);
+	if (!local_name) {
+		err = -EINVAL;
+		goto err_out;
+	}
+	local_essent_len = bpf_core_essential_name_len(local_name);
+
+	cands = calloc(1, sizeof(*cands));
+	if (!cands)
+		return NULL;
+
+	err = bpf_core_add_cands(&local_cand, local_essent_len, targ_btf, "vmlinux", 1, cands);
+	if (err)
+		goto err_out;
+
+	return cands;
+
+err_out:
+	bpf_core_free_cands(cands);
+	errno = -err;
+	return NULL;
+}
+
+/* Record relocation information for a single BPF object */
+static int btfgen_record_obj(struct btfgen_info *info, const char *obj_path)
+{
+	const struct btf_ext_info_sec *sec;
+	const struct bpf_core_relo *relo;
+	const struct btf_ext_info *seg;
+	struct hashmap_entry *entry;
+	struct hashmap *cand_cache = NULL;
+	struct btf_ext *btf_ext = NULL;
+	unsigned int relo_idx;
+	struct btf *btf = NULL;
+	size_t i;
+	int err;
+
+	btf = btf__parse(obj_path, &btf_ext);
+	if (!btf) {
+		err = -errno;
+		p_err("failed to parse BPF object '%s': %s", obj_path, strerror(errno));
+		return err;
+	}
+
+	if (!btf_ext) {
+		p_err("failed to parse BPF object '%s': section %s not found",
+		      obj_path, BTF_EXT_ELF_SEC);
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (btf_ext->core_relo_info.len == 0) {
+		err = 0;
+		goto out;
+	}
+
+	cand_cache = hashmap__new(btfgen_hash_fn, btfgen_equal_fn, NULL);
+	if (IS_ERR(cand_cache)) {
+		err = PTR_ERR(cand_cache);
+		goto out;
+	}
+
+	seg = &btf_ext->core_relo_info;
+	for_each_btf_ext_sec(seg, sec) {
+		for_each_btf_ext_rec(seg, sec, relo_idx, relo) {
+			struct bpf_core_spec specs_scratch[3] = {};
+			struct bpf_core_relo_res targ_res = {};
+			struct bpf_core_cand_list *cands = NULL;
+			const void *type_key = u32_as_hash_key(relo->type_id);
+			const char *sec_name = btf__name_by_offset(btf, sec->sec_name_off);
+
+			if (relo->kind != BPF_CORE_TYPE_ID_LOCAL &&
+			    !hashmap__find(cand_cache, type_key, (void **)&cands)) {
+				cands = btfgen_find_cands(btf, info->src_btf, relo->type_id);
+				if (!cands) {
+					err = -errno;
+					goto out;
+				}
+
+				err = hashmap__set(cand_cache, type_key, cands, NULL, NULL);
+				if (err)
+					goto out;
+			}
+
+			err = bpf_core_calc_relo_insn(sec_name, relo, relo_idx, btf, cands,
+						      specs_scratch, &targ_res);
+			if (err)
+				goto out;
+
+			/* specs_scratch[2] is the target spec */
+			err = btfgen_record_reloc(info, &specs_scratch[2]);
+			if (err)
+				goto out;
+		}
+	}
+
+out:
+	btf__free(btf);
+	btf_ext__free(btf_ext);
+
+	if (!IS_ERR_OR_NULL(cand_cache)) {
+		hashmap__for_each_entry(cand_cache, entry, i) {
+			bpf_core_free_cands(entry->value);
+		}
+		hashmap__free(cand_cache);
+	}
+
+	return err;
+}
+
+static int btfgen_remap_id(__u32 *type_id, void *ctx)
+{
+	unsigned int *ids = ctx;
+
+	*type_id = ids[*type_id];
+
+	return 0;
+}
+
+/* Generate BTF from relocation information previously recorded */
+static struct btf *btfgen_get_btf(struct btfgen_info *info)
+{
+	struct btf *btf_new = NULL;
+	unsigned int *ids = NULL;
+	unsigned int i, n = btf__type_cnt(info->marked_btf);
+	int err = 0;
+
+	btf_new = btf__new_empty();
+	if (!btf_new) {
+		err = -errno;
+		goto err_out;
+	}
+
+	ids = calloc(n, sizeof(*ids));
+	if (!ids) {
+		err = -errno;
+		goto err_out;
+	}
+
+	/* first pass: add all marked types to btf_new and add their new ids to the ids map */
+	for (i = 1; i < n; i++) {
+		const struct btf_type *cloned_type, *type;
+		const char *name;
+		int new_id;
+
+		cloned_type = btf__type_by_id(info->marked_btf, i);
+
+		if (cloned_type->name_off != MARKED)
+			continue;
+
+		type = btf__type_by_id(info->src_btf, i);
+
+		/* add members for struct and union */
+		if (btf_is_composite(type)) {
+			struct btf_member *cloned_m, *m;
+			unsigned short vlen;
+			int idx_src;
+
+			name = btf__str_by_offset(info->src_btf, type->name_off);
+
+			if (btf_is_struct(type))
+				err = btf__add_struct(btf_new, name, type->size);
+			else
+				err = btf__add_union(btf_new, name, type->size);
+
+			if (err < 0)
+				goto err_out;
+			new_id = err;
+
+			cloned_m = btf_members(cloned_type);
+			m = btf_members(type);
+			vlen = btf_vlen(cloned_type);
+			for (idx_src = 0; idx_src < vlen; idx_src++, cloned_m++, m++) {
+				/* add only members that are marked as used */
+				if (cloned_m->name_off != MARKED)
+					continue;
+
+				name = btf__str_by_offset(info->src_btf, m->name_off);
+				err = btf__add_field(btf_new, name, m->type,
+						     btf_member_bit_offset(cloned_type, idx_src),
+						     btf_member_bitfield_size(cloned_type, idx_src));
+				if (err < 0)
+					goto err_out;
+			}
+		} else {
+			err = btf__add_type(btf_new, info->src_btf, type);
+			if (err < 0)
+				goto err_out;
+			new_id = err;
+		}
+
+		/* add ID mapping */
+		ids[i] = new_id;
+	}
+
+	/* second pass: fix up type ids */
+	for (i = 1; i < btf__type_cnt(btf_new); i++) {
+		struct btf_type *btf_type = (struct btf_type *) btf__type_by_id(btf_new, i);
+
+		err = btf_type_visit_type_ids(btf_type, btfgen_remap_id, ids);
+		if (err)
+			goto err_out;
+	}
+
+	free(ids);
+	return btf_new;
+
+err_out:
+	btf__free(btf_new);
+	free(ids);
+	errno = -err;
+	return NULL;
+}
+
+/* Create minimized BTF file for a set of BPF objects.
+ *
+ * The BTFGen algorithm is divided in two main parts: (1) collect the
+ * BTF types that are involved in relocations and (2) generate the BTF
+ * object using the collected types.
+ *
+ * In order to collect the types involved in the relocations, we parse
+ * the BTF and BTF.ext sections of the BPF objects and use
+ * bpf_core_calc_relo_insn() to get the target specification, this
+ * indicates how the types and fields are used in a relocation.
+ *
+ * Types are recorded in different ways according to the kind of the
+ * relocation. For field-based relocations only the members that are
+ * actually used are saved in order to reduce the size of the generated
+ * BTF file. For type-based relocations empty struct / unions are
+ * generated and for enum-based relocations the whole type is saved.
+ *
+ * The second part of the algorithm generates the BTF object. It creates
+ * an empty BTF object and fills it with the types recorded in the
+ * previous step. This function takes care of only adding the structure
+ * and union members that were marked as used and it also fixes up the
+ * type IDs on the generated BTF object.
+ */
+static int minimize_btf(const char *src_btf, const char *dst_btf, const char *objspaths[])
+{
+	struct btfgen_info *info;
+	struct btf *btf_new = NULL;
+	int err, i;
+
+	info = btfgen_new_info(src_btf);
+	if (!info) {
+		err = -errno;
+		p_err("failed to allocate info structure: %s", strerror(errno));
+		goto out;
+	}
+
+	for (i = 0; objspaths[i] != NULL; i++) {
+		err = btfgen_record_obj(info, objspaths[i]);
+		if (err) {
+			p_err("error recording relocations for %s: %s", objspaths[i],
+			      strerror(errno));
+			goto out;
+		}
+	}
+
+	btf_new = btfgen_get_btf(info);
+	if (!btf_new) {
+		err = -errno;
+		p_err("error generating BTF: %s", strerror(errno));
+		goto out;
+	}
+
+	err = btf_save_raw(btf_new, dst_btf);
+	if (err) {
+		p_err("error saving btf file: %s", strerror(errno));
+		goto out;
+	}
+
+out:
+	btf__free(btf_new);
+	btfgen_free_info(info);
+
+	return err;
+}
+
+static int do_min_core_btf(int argc, char **argv)
+{
+	const char *input, *output, **objs;
+	int i, err;
+
+	if (!REQ_ARGS(3)) {
+		usage();
+		return -1;
+	}
+
+	input = GET_ARG();
+	output = GET_ARG();
+
+	objs = (const char **) calloc(argc + 1, sizeof(*objs));
+	if (!objs) {
+		p_err("failed to allocate array for object names");
+		return -ENOMEM;
+	}
+
+	i = 0;
+	while (argc)
+		objs[i++] = GET_ARG();
+
+	err = minimize_btf(input, output, objs);
+	free(objs);
+	return err;
+}
+
 static const struct cmd cmds[] = {
-	{ "object",	do_object },
-	{ "skeleton",	do_skeleton },
-	{ "help",	do_help },
+	{ "object",		do_object },
+	{ "skeleton",		do_skeleton },
+	{ "subskeleton",	do_subskeleton },
+	{ "min_core_btf",	do_min_core_btf},
+	{ "help",		do_help },
 	{ 0 }
 };
 
diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 2c258db0d352..97dec81950e5 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2020 Facebook */
 
 #include <errno.h>
+#include <linux/err.h>
 #include <net/if.h>
 #include <stdio.h>
 #include <unistd.h>
@@ -306,7 +307,7 @@ static int do_show(int argc, char **argv)
 	if (show_pinned) {
 		link_table = hashmap__new(hash_fn_for_key_as_id,
 					  equal_fn_for_key_as_id, NULL);
-		if (!link_table) {
+		if (IS_ERR(link_table)) {
 			p_err("failed to create hashmap for pinned paths");
 			return -1;
 		}
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 020e91a542d5..e81227761f5d 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -71,6 +71,17 @@ static int do_help(int argc, char **argv)
 	return 0;
 }
 
+#ifndef BPFTOOL_VERSION
+/* bpftool's major and minor version numbers are aligned on libbpf's. There is
+ * an offset of 6 for the version number, because bpftool's version was higher
+ * than libbpf's when we adopted this scheme. The patch number remains at 0
+ * for now. Set BPFTOOL_VERSION to override.
+ */
+#define BPFTOOL_MAJOR_VERSION (LIBBPF_MAJOR_VERSION + 6)
+#define BPFTOOL_MINOR_VERSION LIBBPF_MINOR_VERSION
+#define BPFTOOL_PATCH_VERSION 0
+#endif
+
 static int do_version(int argc, char **argv)
 {
 #ifdef HAVE_LIBBFD_SUPPORT
@@ -88,7 +99,15 @@ static int do_version(int argc, char **argv)
 		jsonw_start_object(json_wtr);	/* root object */
 
 		jsonw_name(json_wtr, "version");
+#ifdef BPFTOOL_VERSION
 		jsonw_printf(json_wtr, "\"%s\"", BPFTOOL_VERSION);
+#else
+		jsonw_printf(json_wtr, "\"%d.%d.%d\"", BPFTOOL_MAJOR_VERSION,
+			     BPFTOOL_MINOR_VERSION, BPFTOOL_PATCH_VERSION);
+#endif
+		jsonw_name(json_wtr, "libbpf_version");
+		jsonw_printf(json_wtr, "\"%d.%d\"",
+			     libbpf_major_version(), libbpf_minor_version());
 
 		jsonw_name(json_wtr, "features");
 		jsonw_start_object(json_wtr);	/* features */
@@ -101,7 +120,13 @@ static int do_version(int argc, char **argv)
 	} else {
 		unsigned int nb_features = 0;
 
+#ifdef BPFTOOL_VERSION
 		printf("%s v%s\n", bin_name, BPFTOOL_VERSION);
+#else
+		printf("%s v%d.%d.%d\n", bin_name, BPFTOOL_MAJOR_VERSION,
+		       BPFTOOL_MINOR_VERSION, BPFTOOL_PATCH_VERSION);
+#endif
+		printf("using libbpf %s\n", libbpf_version_string());
 		printf("features:");
 		if (has_libbfd) {
 			printf(" libbfd");
@@ -478,7 +503,11 @@ int main(int argc, char **argv)
 	}
 
 	if (!legacy_libbpf) {
-		ret = libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+		/* Allow legacy map definitions for skeleton generation.
+		 * It will still be rejected if users use LIBBPF_STRICT_ALL
+		 * mode for loading generated skeleton.
+		 */
+		ret = libbpf_set_strict_mode(LIBBPF_STRICT_ALL & ~LIBBPF_STRICT_MAP_DEFINITIONS);
 		if (ret)
 			p_err("failed to enable libbpf strict mode: %d", ret);
 	}
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 8d76d937a62b..6e9277ffc68c 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -8,10 +8,10 @@
 #undef GCC_VERSION
 #include <stdbool.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <linux/bpf.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
-#include <tools/libc_compat.h>
 
 #include <bpf/hashmap.h>
 #include <bpf/libbpf.h>
@@ -113,7 +113,9 @@ struct obj_ref {
 
 struct obj_refs {
 	int ref_cnt;
+	bool has_bpf_cookie;
 	struct obj_ref *refs;
+	__u64 bpf_cookie;
 };
 
 struct btf;
@@ -140,6 +142,10 @@ struct cmd {
 int cmd_select(const struct cmd *cmds, int argc, char **argv,
 	       int (*help)(int argc, char **argv));
 
+#define MAX_PROG_FULL_NAME 128
+void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd,
+			char *name_buff, size_t buff_len);
+
 int get_fd_type(int fd);
 const char *get_fd_type_name(enum bpf_obj_type type);
 char *get_fdinfo(int fd, const char *key);
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index cc530a229812..c26378f20831 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -504,7 +504,7 @@ static int show_map_close_json(int fd, struct bpf_map_info *info)
 	jsonw_uint_field(json_wtr, "max_entries", info->max_entries);
 
 	if (memlock)
-		jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock));
+		jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock));
 	free(memlock);
 
 	if (info->type == BPF_MAP_TYPE_PROG_ARRAY) {
@@ -620,17 +620,14 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info)
 					    u32_as_hash_field(info->id))
 			printf("\n\tpinned %s", (char *)entry->value);
 	}
-	printf("\n");
 
 	if (frozen_str) {
 		frozen = atoi(frozen_str);
 		free(frozen_str);
 	}
 
-	if (!info->btf_id && !frozen)
-		return 0;
-
-	printf("\t");
+	if (info->btf_id || frozen)
+		printf("\n\t");
 
 	if (info->btf_id)
 		printf("btf_id %d", info->btf_id);
@@ -699,7 +696,7 @@ static int do_show(int argc, char **argv)
 	if (show_pinned) {
 		map_table = hashmap__new(hash_fn_for_key_as_id,
 					 equal_fn_for_key_as_id, NULL);
-		if (!map_table) {
+		if (IS_ERR(map_table)) {
 			p_err("failed to create hashmap for pinned paths");
 			return -1;
 		}
@@ -805,29 +802,30 @@ static int maps_have_btf(int *fds, int nb_fds)
 
 static struct btf *btf_vmlinux;
 
-static struct btf *get_map_kv_btf(const struct bpf_map_info *info)
+static int get_map_kv_btf(const struct bpf_map_info *info, struct btf **btf)
 {
-	struct btf *btf = NULL;
+	int err = 0;
 
 	if (info->btf_vmlinux_value_type_id) {
 		if (!btf_vmlinux) {
 			btf_vmlinux = libbpf_find_kernel_btf();
-			if (libbpf_get_error(btf_vmlinux))
+			err = libbpf_get_error(btf_vmlinux);
+			if (err) {
 				p_err("failed to get kernel btf");
+				return err;
+			}
 		}
-		return btf_vmlinux;
+		*btf = btf_vmlinux;
 	} else if (info->btf_value_type_id) {
-		int err;
-
-		btf = btf__load_from_kernel_by_id(info->btf_id);
-		err = libbpf_get_error(btf);
-		if (err) {
+		*btf = btf__load_from_kernel_by_id(info->btf_id);
+		err = libbpf_get_error(*btf);
+		if (err)
 			p_err("failed to get btf");
-			btf = ERR_PTR(err);
-		}
+	} else {
+		*btf = NULL;
 	}
 
-	return btf;
+	return err;
 }
 
 static void free_map_kv_btf(struct btf *btf)
@@ -862,8 +860,7 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr,
 	prev_key = NULL;
 
 	if (wtr) {
-		btf = get_map_kv_btf(info);
-		err = libbpf_get_error(btf);
+		err = get_map_kv_btf(info, &btf);
 		if (err) {
 			goto exit_free;
 		}
@@ -1054,11 +1051,8 @@ static void print_key_value(struct bpf_map_info *info, void *key,
 	json_writer_t *btf_wtr;
 	struct btf *btf;
 
-	btf = btf__load_from_kernel_by_id(info->btf_id);
-	if (libbpf_get_error(btf)) {
-		p_err("failed to get btf");
+	if (get_map_kv_btf(info, &btf))
 		return;
-	}
 
 	if (json_output) {
 		print_entry_json(info, key, value, btf);
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index 649053704bd7..526a332c48e6 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -551,7 +551,7 @@ static int do_attach_detach_xdp(int progfd, enum net_attach_type attach_type,
 	if (attach_type == NET_ATTACH_TYPE_XDP_OFFLOAD)
 		flags |= XDP_FLAGS_HW_MODE;
 
-	return bpf_set_link_xdp_fd(ifindex, progfd, flags);
+	return bpf_xdp_attach(ifindex, progfd, flags, NULL);
 }
 
 static int do_attach(int argc, char **argv)
diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c
index 56b598eee043..bb6c969a114a 100644
--- a/tools/bpf/bpftool/pids.c
+++ b/tools/bpf/bpftool/pids.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (C) 2020 Facebook */
 #include <errno.h>
+#include <linux/err.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -77,6 +78,8 @@ static void add_ref(struct hashmap *map, struct pid_iter_entry *e)
 	ref->pid = e->pid;
 	memcpy(ref->comm, e->comm, sizeof(ref->comm));
 	refs->ref_cnt = 1;
+	refs->has_bpf_cookie = e->has_bpf_cookie;
+	refs->bpf_cookie = e->bpf_cookie;
 
 	err = hashmap__append(map, u32_as_hash_field(e->id), refs);
 	if (err)
@@ -101,7 +104,7 @@ int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type)
 	libbpf_print_fn_t default_print;
 
 	*map = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL);
-	if (!*map) {
+	if (IS_ERR(*map)) {
 		p_err("failed to create hashmap for PID references");
 		return -1;
 	}
@@ -204,6 +207,9 @@ void emit_obj_refs_json(struct hashmap *map, __u32 id,
 		if (refs->ref_cnt == 0)
 			break;
 
+		if (refs->has_bpf_cookie)
+			jsonw_lluint_field(json_writer, "bpf_cookie", refs->bpf_cookie);
+
 		jsonw_name(json_writer, "pids");
 		jsonw_start_array(json_writer);
 		for (i = 0; i < refs->ref_cnt; i++) {
@@ -233,6 +239,9 @@ void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix)
 		if (refs->ref_cnt == 0)
 			break;
 
+		if (refs->has_bpf_cookie)
+			printf("\n\tbpf_cookie %llu", (unsigned long long) refs->bpf_cookie);
+
 		printf("%s", prefix);
 		for (i = 0; i < refs->ref_cnt; i++) {
 			struct obj_ref *ref = &refs->refs[i];
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 2a21d50516bc..bc4e05542c2b 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -26,6 +26,7 @@
 #include <bpf/btf.h>
 #include <bpf/hashmap.h>
 #include <bpf/libbpf.h>
+#include <bpf/libbpf_internal.h>
 #include <bpf/skel_internal.h>
 
 #include "cfg.h"
@@ -424,8 +425,10 @@ out_free:
 	free(value);
 }
 
-static void print_prog_header_json(struct bpf_prog_info *info)
+static void print_prog_header_json(struct bpf_prog_info *info, int fd)
 {
+	char prog_name[MAX_PROG_FULL_NAME];
+
 	jsonw_uint_field(json_wtr, "id", info->id);
 	if (info->type < ARRAY_SIZE(prog_type_name))
 		jsonw_string_field(json_wtr, "type",
@@ -433,8 +436,10 @@ static void print_prog_header_json(struct bpf_prog_info *info)
 	else
 		jsonw_uint_field(json_wtr, "type", info->type);
 
-	if (*info->name)
-		jsonw_string_field(json_wtr, "name", info->name);
+	if (*info->name) {
+		get_prog_full_name(info, fd, prog_name, sizeof(prog_name));
+		jsonw_string_field(json_wtr, "name", prog_name);
+	}
 
 	jsonw_name(json_wtr, "tag");
 	jsonw_printf(json_wtr, "\"" BPF_TAG_FMT "\"",
@@ -455,7 +460,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 	char *memlock;
 
 	jsonw_start_object(json_wtr);
-	print_prog_header_json(info);
+	print_prog_header_json(info, fd);
 	print_dev_json(info->ifindex, info->netns_dev, info->netns_ino);
 
 	if (info->load_time) {
@@ -480,7 +485,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 
 	memlock = get_fdinfo(fd, "memlock");
 	if (memlock)
-		jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock));
+		jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock));
 	free(memlock);
 
 	if (info->nr_map_ids)
@@ -507,16 +512,20 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 	jsonw_end_object(json_wtr);
 }
 
-static void print_prog_header_plain(struct bpf_prog_info *info)
+static void print_prog_header_plain(struct bpf_prog_info *info, int fd)
 {
+	char prog_name[MAX_PROG_FULL_NAME];
+
 	printf("%u: ", info->id);
 	if (info->type < ARRAY_SIZE(prog_type_name))
 		printf("%s  ", prog_type_name[info->type]);
 	else
 		printf("type %u  ", info->type);
 
-	if (*info->name)
-		printf("name %s  ", info->name);
+	if (*info->name) {
+		get_prog_full_name(info, fd, prog_name, sizeof(prog_name));
+		printf("name %s  ", prog_name);
+	}
 
 	printf("tag ");
 	fprint_hex(stdout, info->tag, BPF_TAG_SIZE, "");
@@ -534,7 +543,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 {
 	char *memlock;
 
-	print_prog_header_plain(info);
+	print_prog_header_plain(info, fd);
 
 	if (info->load_time) {
 		char buf[32];
@@ -641,7 +650,7 @@ static int do_show(int argc, char **argv)
 	if (show_pinned) {
 		prog_table = hashmap__new(hash_fn_for_key_as_id,
 					  equal_fn_for_key_as_id, NULL);
-		if (!prog_table) {
+		if (IS_ERR(prog_table)) {
 			p_err("failed to create hashmap for pinned paths");
 			return -1;
 		}
@@ -972,10 +981,10 @@ static int do_dump(int argc, char **argv)
 
 		if (json_output && nb_fds > 1) {
 			jsonw_start_object(json_wtr);	/* prog object */
-			print_prog_header_json(&info);
+			print_prog_header_json(&info, fds[i]);
 			jsonw_name(json_wtr, "insns");
 		} else if (nb_fds > 1) {
-			print_prog_header_plain(&info);
+			print_prog_header_plain(&info, fds[i]);
 		}
 
 		err = prog_dump(&info, mode, filepath, opcodes, visual, linum);
@@ -1264,12 +1273,12 @@ static int do_run(int argc, char **argv)
 {
 	char *data_fname_in = NULL, *data_fname_out = NULL;
 	char *ctx_fname_in = NULL, *ctx_fname_out = NULL;
-	struct bpf_prog_test_run_attr test_attr = {0};
 	const unsigned int default_size = SZ_32K;
 	void *data_in = NULL, *data_out = NULL;
 	void *ctx_in = NULL, *ctx_out = NULL;
 	unsigned int repeat = 1;
 	int fd, err;
+	LIBBPF_OPTS(bpf_test_run_opts, test_attr);
 
 	if (!REQ_ARGS(4))
 		return -1;
@@ -1387,14 +1396,13 @@ static int do_run(int argc, char **argv)
 			goto free_ctx_in;
 	}
 
-	test_attr.prog_fd	= fd;
 	test_attr.repeat	= repeat;
 	test_attr.data_in	= data_in;
 	test_attr.data_out	= data_out;
 	test_attr.ctx_in	= ctx_in;
 	test_attr.ctx_out	= ctx_out;
 
-	err = bpf_prog_test_run_xattr(&test_attr);
+	err = bpf_prog_test_run_opts(fd, &test_attr);
 	if (err) {
 		p_err("failed to run program: %s", strerror(errno));
 		goto free_ctx_out;
@@ -1551,9 +1559,9 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 			if (fd < 0)
 				goto err_free_reuse_maps;
 
-			new_map_replace = reallocarray(map_replace,
-						       old_map_fds + 1,
-						       sizeof(*map_replace));
+			new_map_replace = libbpf_reallocarray(map_replace,
+							      old_map_fds + 1,
+							      sizeof(*map_replace));
 			if (!new_map_replace) {
 				p_err("mem alloc failed");
 				goto err_free_reuse_maps;
@@ -2275,10 +2283,10 @@ static int do_profile(int argc, char **argv)
 	profile_obj->rodata->num_metric = num_metric;
 
 	/* adjust map sizes */
-	bpf_map__resize(profile_obj->maps.events, num_metric * num_cpu);
-	bpf_map__resize(profile_obj->maps.fentry_readings, num_metric);
-	bpf_map__resize(profile_obj->maps.accum_readings, num_metric);
-	bpf_map__resize(profile_obj->maps.counts, 1);
+	bpf_map__set_max_entries(profile_obj->maps.events, num_metric * num_cpu);
+	bpf_map__set_max_entries(profile_obj->maps.fentry_readings, num_metric);
+	bpf_map__set_max_entries(profile_obj->maps.accum_readings, num_metric);
+	bpf_map__set_max_entries(profile_obj->maps.counts, 1);
 
 	/* change target name */
 	profile_tgt_name = profile_target_name(profile_tgt_fd);
diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
index f70702fcb224..eb05ea53afb1 100644
--- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
+++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
@@ -38,6 +38,17 @@ static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type)
 	}
 }
 
+/* could be used only with BPF_LINK_TYPE_PERF_EVENT links */
+static __u64 get_bpf_cookie(struct bpf_link *link)
+{
+	struct bpf_perf_link *perf_link;
+	struct perf_event *event;
+
+	perf_link = container_of(link, struct bpf_perf_link, link);
+	event = BPF_CORE_READ(perf_link, perf_file, private_data);
+	return BPF_CORE_READ(event, bpf_cookie);
+}
+
 SEC("iter/task_file")
 int iter(struct bpf_iter__task_file *ctx)
 {
@@ -69,8 +80,19 @@ int iter(struct bpf_iter__task_file *ctx)
 	if (file->f_op != fops)
 		return 0;
 
+	__builtin_memset(&e, 0, sizeof(e));
 	e.pid = task->tgid;
 	e.id = get_obj_id(file->private_data, obj_type);
+
+	if (obj_type == BPF_OBJ_LINK) {
+		struct bpf_link *link = (struct bpf_link *) file->private_data;
+
+		if (BPF_CORE_READ(link, type) == BPF_LINK_TYPE_PERF_EVENT) {
+			e.has_bpf_cookie = true;
+			e.bpf_cookie = get_bpf_cookie(link);
+		}
+	}
+
 	bpf_probe_read_kernel_str(&e.comm, sizeof(e.comm),
 				  task->group_leader->comm);
 	bpf_seq_write(ctx->meta->seq, &e, sizeof(e));
diff --git a/tools/bpf/bpftool/skeleton/pid_iter.h b/tools/bpf/bpftool/skeleton/pid_iter.h
index 5692cf257adb..bbb570d4cca6 100644
--- a/tools/bpf/bpftool/skeleton/pid_iter.h
+++ b/tools/bpf/bpftool/skeleton/pid_iter.h
@@ -6,6 +6,8 @@
 struct pid_iter_entry {
 	__u32 id;
 	int pid;
+	__u64 bpf_cookie;
+	bool has_bpf_cookie;
 	char comm[16];
 };
 
diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c
index 2f693b082bdb..e08a6ff2866c 100644
--- a/tools/bpf/bpftool/struct_ops.c
+++ b/tools/bpf/bpftool/struct_ops.c
@@ -480,7 +480,6 @@ static int do_unregister(int argc, char **argv)
 static int do_register(int argc, char **argv)
 {
 	LIBBPF_OPTS(bpf_object_open_opts, open_opts);
-	const struct bpf_map_def *def;
 	struct bpf_map_info info = {};
 	__u32 info_len = sizeof(info);
 	int nr_errs = 0, nr_maps = 0;
@@ -510,8 +509,7 @@ static int do_register(int argc, char **argv)
 	}
 
 	bpf_object__for_each_map(map, obj) {
-		def = bpf_map__def(map);
-		if (def->type != BPF_MAP_TYPE_STRUCT_OPS)
+		if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS)
 			continue;
 
 		link = bpf_map__attach_struct_ops(map);
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index f1f32e21d5cd..2d9cd6a7b3c8 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -8,6 +8,7 @@
 #include <string.h>
 #include <sys/types.h>
 #include <bpf/libbpf.h>
+#include <bpf/libbpf_internal.h>
 
 #include "disasm.h"
 #include "json_writer.h"
@@ -32,8 +33,8 @@ void kernel_syms_load(struct dump_data *dd)
 		return;
 
 	while (fgets(buff, sizeof(buff), fp)) {
-		tmp = reallocarray(dd->sym_mapping, dd->sym_count + 1,
-				   sizeof(*dd->sym_mapping));
+		tmp = libbpf_reallocarray(dd->sym_mapping, dd->sym_count + 1,
+					  sizeof(*dd->sym_mapping));
 		if (!tmp) {
 out:
 			free(dd->sym_mapping);
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index 320a88ac28c9..19a3112e271a 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -24,6 +24,8 @@ LD       = $(HOSTLD)
 ARCH     = $(HOSTARCH)
 RM      ?= rm
 CROSS_COMPILE =
+CFLAGS  := $(KBUILD_HOSTCFLAGS)
+LDFLAGS := $(KBUILD_HOSTLDFLAGS)
 
 OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/
 
@@ -51,10 +53,10 @@ $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd
 
 $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUT)
 	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT)    \
-		    DESTDIR=$(LIBBPF_DESTDIR) prefix=			       \
+		    DESTDIR=$(LIBBPF_DESTDIR) prefix= EXTRA_CFLAGS="$(CFLAGS)" \
 		    $(abspath $@) install_headers
 
-CFLAGS := -g \
+CFLAGS += -g \
           -I$(srctree)/tools/include \
           -I$(srctree)/tools/include/uapi \
           -I$(LIBBPF_INCLUDE) \