Merge remote-tracking branch 'torvalds/master' into perf/core

To pick up some tools/perf/ patches that went via tip/perf/core, such
as:

  tools/perf: Add mem_hops field in perf_mem_data_src structure

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

24 files changed, 2805 insertions, 1191 deletions

diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index 5d4cfac671d5..0da84cb9e66d 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-libbpf_version.h
 libbpf.pc
 libbpf.so.*
 TAGS
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 74c3b73a5fbe..b393b5e82380 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -8,7 +8,8 @@ VERSION_SCRIPT := libbpf.map
 LIBBPF_VERSION := $(shell \
 	grep -oE '^LIBBPF_([0-9.]+)' $(VERSION_SCRIPT) | \
 	sort -rV | head -n1 | cut -d'_' -f2)
-LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION)))
+LIBBPF_MAJOR_VERSION := $(word 1,$(subst ., ,$(LIBBPF_VERSION)))
+LIBBPF_MINOR_VERSION := $(word 2,$(subst ., ,$(LIBBPF_VERSION)))
 
 MAKEFLAGS += --no-print-directory
 
@@ -59,7 +60,8 @@ ifndef VERBOSE
   VERBOSE = 0
 endif
 
-INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi
+INCLUDES = -I$(if $(OUTPUT),$(OUTPUT),.)				\
+	   -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi
 
 export prefix libdir src obj
 
@@ -112,6 +114,7 @@ STATIC_OBJDIR	:= $(OUTPUT)staticobjs/
 BPF_IN_SHARED	:= $(SHARED_OBJDIR)libbpf-in.o
 BPF_IN_STATIC	:= $(STATIC_OBJDIR)libbpf-in.o
 BPF_HELPER_DEFS	:= $(OUTPUT)bpf_helper_defs.h
+BPF_GENERATED	:= $(BPF_HELPER_DEFS)
 
 LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
 LIB_FILE	:= $(addprefix $(OUTPUT),$(LIB_FILE))
@@ -136,25 +139,19 @@ all: fixdep
 
 all_cmd: $(CMD_TARGETS) check
 
-$(BPF_IN_SHARED): force $(BPF_HELPER_DEFS)
+$(BPF_IN_SHARED): force $(BPF_GENERATED)
 	@(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
 	(diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true
 	@(test -f ../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \
 	(diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf_common.h' differs from latest version at 'include/uapi/linux/bpf_common.h'" >&2 )) || true
-	@(test -f ../../include/uapi/linux/netlink.h -a -f ../../../include/uapi/linux/netlink.h && ( \
-	(diff -B ../../include/uapi/linux/netlink.h ../../../include/uapi/linux/netlink.h >/dev/null) || \
-	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/netlink.h' differs from latest version at 'include/uapi/linux/netlink.h'" >&2 )) || true
-	@(test -f ../../include/uapi/linux/if_link.h -a -f ../../../include/uapi/linux/if_link.h && ( \
-	(diff -B ../../include/uapi/linux/if_link.h ../../../include/uapi/linux/if_link.h >/dev/null) || \
-	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'" >&2 )) || true
 	@(test -f ../../include/uapi/linux/if_xdp.h -a -f ../../../include/uapi/linux/if_xdp.h && ( \
 	(diff -B ../../include/uapi/linux/if_xdp.h ../../../include/uapi/linux/if_xdp.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)"
 
-$(BPF_IN_STATIC): force $(BPF_HELPER_DEFS)
+$(BPF_IN_STATIC): force $(BPF_GENERATED)
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
 
 $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
@@ -179,7 +176,7 @@ $(OUTPUT)libbpf.pc:
 		-e "s|@VERSION@|$(LIBBPF_VERSION)|" \
 		< libbpf.pc.template > $@
 
-check: check_abi
+check: check_abi check_version
 
 check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT)
 	@if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then	 \
@@ -205,6 +202,21 @@ check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT)
 		exit 1;							 \
 	fi
 
+HDR_MAJ_VERSION := $(shell grep -oE '^$(pound)define LIBBPF_MAJOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3)
+HDR_MIN_VERSION := $(shell grep -oE '^$(pound)define LIBBPF_MINOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3)
+
+check_version: $(VERSION_SCRIPT) libbpf_version.h
+	@if [ "$(HDR_MAJ_VERSION)" != "$(LIBBPF_MAJOR_VERSION)" ]; then        \
+		echo "Error: libbpf major version mismatch detected: "	       \
+		     "'$(HDR_MAJ_VERSION)' != '$(LIBBPF_MAJOR_VERSION)'" >&2;  \
+		exit 1;							       \
+	fi
+	@if [ "$(HDR_MIN_VERSION)" != "$(LIBBPF_MINOR_VERSION)" ]; then	       \
+		echo "Error: libbpf minor version mismatch detected: "	       \
+		     "'$(HDR_MIN_VERSION)' != '$(LIBBPF_MINOR_VERSION)'" >&2;  \
+		exit 1;							       \
+	fi
+
 define do_install_mkdir
 	if [ ! -d '$(DESTDIR_SQ)$1' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1';	\
@@ -223,14 +235,24 @@ install_lib: all_cmd
 		$(call do_install_mkdir,$(libdir_SQ)); \
 		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
 
-INSTALL_HEADERS = bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \
-		  bpf_helpers.h $(BPF_HELPER_DEFS) bpf_tracing.h	     \
-		  bpf_endian.h bpf_core_read.h skel_internal.h
+SRC_HDRS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h	     \
+	    bpf_helpers.h bpf_tracing.h bpf_endian.h bpf_core_read.h	     \
+	    skel_internal.h libbpf_version.h
+GEN_HDRS := $(BPF_GENERATED)
+
+INSTALL_PFX := $(DESTDIR)$(prefix)/include/bpf
+INSTALL_SRC_HDRS := $(addprefix $(INSTALL_PFX)/, $(SRC_HDRS))
+INSTALL_GEN_HDRS := $(addprefix $(INSTALL_PFX)/, $(notdir $(GEN_HDRS)))
+
+$(INSTALL_SRC_HDRS): $(INSTALL_PFX)/%.h: %.h
+	$(call QUIET_INSTALL, $@) \
+		$(call do_install,$<,$(prefix)/include/bpf,644)
+
+$(INSTALL_GEN_HDRS): $(INSTALL_PFX)/%.h: $(OUTPUT)%.h
+	$(call QUIET_INSTALL, $@) \
+		$(call do_install,$<,$(prefix)/include/bpf,644)
 
-install_headers: $(BPF_HELPER_DEFS)
-	$(call QUIET_INSTALL, headers)					     \
-		$(foreach hdr,$(INSTALL_HEADERS),			     \
-			$(call do_install,$(hdr),$(prefix)/include/bpf,644);)
+install_headers: $(BPF_GENERATED) $(INSTALL_SRC_HDRS) $(INSTALL_GEN_HDRS)
 
 install_pkgconfig: $(PC_FILE)
 	$(call QUIET_INSTALL, $(PC_FILE)) \
@@ -240,12 +262,12 @@ install: install_lib install_pkgconfig install_headers
 
 clean:
 	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS)		     \
-		*~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS)		     \
+		*~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_GENERATED)		     \
 		$(SHARED_OBJDIR) $(STATIC_OBJDIR)			     \
 		$(addprefix $(OUTPUT),					     \
 			    *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc)
 
-PHONY += force cscope tags
+PHONY += force cscope tags check check_abi check_version
 force:
 
 cscope:
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 2401fad090c5..c09cbb868c9f 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -65,19 +65,28 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
 	return syscall(__NR_bpf, cmd, attr, size);
 }
 
+static inline int sys_bpf_fd(enum bpf_cmd cmd, union bpf_attr *attr,
+			     unsigned int size)
+{
+	int fd;
+
+	fd = sys_bpf(cmd, attr, size);
+	return ensure_good_fd(fd);
+}
+
 static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size)
 {
 	int retries = 5;
 	int fd;
 
 	do {
-		fd = sys_bpf(BPF_PROG_LOAD, attr, size);
+		fd = sys_bpf_fd(BPF_PROG_LOAD, attr, size);
 	} while (fd < 0 && errno == EAGAIN && retries-- > 0);
 
 	return fd;
 }
 
-int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
+int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr)
 {
 	union bpf_attr attr;
 	int fd;
@@ -102,11 +111,36 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 			create_attr->btf_vmlinux_value_type_id;
 	else
 		attr.inner_map_fd = create_attr->inner_map_fd;
+	attr.map_extra = create_attr->map_extra;
 
-	fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
+int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
+{
+	struct bpf_create_map_params p = {};
+
+	p.map_type = create_attr->map_type;
+	p.key_size = create_attr->key_size;
+	p.value_size = create_attr->value_size;
+	p.max_entries = create_attr->max_entries;
+	p.map_flags = create_attr->map_flags;
+	p.name = create_attr->name;
+	p.numa_node = create_attr->numa_node;
+	p.btf_fd = create_attr->btf_fd;
+	p.btf_key_type_id = create_attr->btf_key_type_id;
+	p.btf_value_type_id = create_attr->btf_value_type_id;
+	p.map_ifindex = create_attr->map_ifindex;
+	if (p.map_type == BPF_MAP_TYPE_STRUCT_OPS)
+		p.btf_vmlinux_value_type_id =
+			create_attr->btf_vmlinux_value_type_id;
+	else
+		p.inner_map_fd = create_attr->inner_map_fd;
+
+	return libbpf__bpf_create_map_xattr(&p);
+}
+
 int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
 			int key_size, int value_size, int max_entries,
 			__u32 map_flags, int node)
@@ -181,7 +215,7 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
 		attr.numa_node = node;
 	}
 
-	fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -264,6 +298,7 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 	attr.line_info_rec_size = load_attr->line_info_rec_size;
 	attr.line_info_cnt = load_attr->line_info_cnt;
 	attr.line_info = ptr_to_u64(load_attr->line_info);
+	attr.fd_array = ptr_to_u64(load_attr->fd_array);
 
 	if (load_attr->name)
 		memcpy(attr.prog_name, load_attr->name,
@@ -608,7 +643,7 @@ int bpf_obj_get(const char *pathname)
 	memset(&attr, 0, sizeof(attr));
 	attr.pathname = ptr_to_u64((void *)pathname);
 
-	fd = sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_OBJ_GET, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -719,7 +754,7 @@ int bpf_link_create(int prog_fd, int target_fd,
 		break;
 	}
 proceed:
-	fd = sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -762,7 +797,7 @@ int bpf_iter_create(int link_fd)
 	memset(&attr, 0, sizeof(attr));
 	attr.iter_create.link_fd = link_fd;
 
-	fd = sys_bpf(BPF_ITER_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -920,7 +955,7 @@ int bpf_prog_get_fd_by_id(__u32 id)
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_id = id;
 
-	fd = sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -932,7 +967,7 @@ int bpf_map_get_fd_by_id(__u32 id)
 	memset(&attr, 0, sizeof(attr));
 	attr.map_id = id;
 
-	fd = sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -944,7 +979,7 @@ int bpf_btf_get_fd_by_id(__u32 id)
 	memset(&attr, 0, sizeof(attr));
 	attr.btf_id = id;
 
-	fd = sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -956,7 +991,7 @@ int bpf_link_get_fd_by_id(__u32 id)
 	memset(&attr, 0, sizeof(attr));
 	attr.link_id = id;
 
-	fd = sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -987,7 +1022,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 	attr.raw_tracepoint.name = ptr_to_u64(name);
 	attr.raw_tracepoint.prog_fd = prog_fd;
 
-	fd = sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -1007,7 +1042,7 @@ retry:
 		attr.btf_log_buf = ptr_to_u64(log_buf);
 	}
 
-	fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, sizeof(attr));
 
 	if (fd < 0 && !do_log && log_buf && log_buf_size) {
 		do_log = true;
@@ -1049,7 +1084,7 @@ int bpf_enable_stats(enum bpf_stats_type type)
 	memset(&attr, 0, sizeof(attr));
 	attr.enable_stats.type = type;
 
-	fd = sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index 09ebe3db5f2f..e4aa9996a550 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -40,7 +40,7 @@ enum bpf_enum_value_kind {
 #define __CORE_RELO(src, field, info)					      \
 	__builtin_preserve_field_info((src)->field, BPF_FIELD_##info)
 
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 #define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
 	bpf_probe_read_kernel(						      \
 			(void *)dst,				      \
diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h
index 615400391e57..d26e5472fe50 100644
--- a/tools/lib/bpf/bpf_gen_internal.h
+++ b/tools/lib/bpf/bpf_gen_internal.h
@@ -7,6 +7,21 @@ struct ksym_relo_desc {
 	const char *name;
 	int kind;
 	int insn_idx;
+	bool is_weak;
+	bool is_typeless;
+};
+
+struct ksym_desc {
+	const char *name;
+	int ref;
+	int kind;
+	union {
+		/* used for kfunc */
+		int off;
+		/* used for typeless ksym */
+		bool typeless;
+	};
+	int insn;
 };
 
 struct bpf_gen {
@@ -24,18 +39,23 @@ struct bpf_gen {
 	int relo_cnt;
 	char attach_target[128];
 	int attach_kind;
+	struct ksym_desc *ksyms;
+	__u32 nr_ksyms;
+	int fd_array;
+	int nr_fd_array;
 };
 
 void bpf_gen__init(struct bpf_gen *gen, int log_level);
 int bpf_gen__finish(struct bpf_gen *gen);
 void bpf_gen__free(struct bpf_gen *gen);
 void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size);
-void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_attr *map_attr, int map_idx);
+void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_params *map_attr, int map_idx);
 struct bpf_prog_load_params;
 void bpf_gen__prog_load(struct bpf_gen *gen, struct bpf_prog_load_params *load_attr, int prog_idx);
 void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size);
 void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx);
 void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type);
-void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind, int insn_idx);
+void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak,
+			    bool is_typeless, int kind, int insn_idx);
 
 #endif
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index b9987c3efa3c..963b1060d944 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -14,14 +14,6 @@
 #define __type(name, val) typeof(val) *name
 #define __array(name, val) typeof(val) *name[]
 
-/* Helper macro to print out debug messages */
-#define bpf_printk(fmt, ...)				\
-({							\
-	char ____fmt[] = fmt;				\
-	bpf_trace_printk(____fmt, sizeof(____fmt),	\
-			 ##__VA_ARGS__);		\
-})
-
 /*
  * Helper macro to place programs, maps, license in
  * different sections in elf_bpf file. Section names
@@ -224,4 +216,47 @@ enum libbpf_tristate {
 		     ___param, sizeof(___param));		\
 })
 
+#ifdef BPF_NO_GLOBAL_DATA
+#define BPF_PRINTK_FMT_MOD
+#else
+#define BPF_PRINTK_FMT_MOD static const
+#endif
+
+#define __bpf_printk(fmt, ...)				\
+({							\
+	BPF_PRINTK_FMT_MOD char ____fmt[] = fmt;	\
+	bpf_trace_printk(____fmt, sizeof(____fmt),	\
+			 ##__VA_ARGS__);		\
+})
+
+/*
+ * __bpf_vprintk wraps the bpf_trace_vprintk helper with variadic arguments
+ * instead of an array of u64.
+ */
+#define __bpf_vprintk(fmt, args...)				\
+({								\
+	static const char ___fmt[] = fmt;			\
+	unsigned long long ___param[___bpf_narg(args)];		\
+								\
+	_Pragma("GCC diagnostic push")				\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
+	___bpf_fill(___param, args);				\
+	_Pragma("GCC diagnostic pop")				\
+								\
+	bpf_trace_vprintk(___fmt, sizeof(___fmt),		\
+			  ___param, sizeof(___param));		\
+})
+
+/* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args
+ * Otherwise use __bpf_vprintk
+ */
+#define ___bpf_pick_printk(...) \
+	___bpf_nth(_, ##__VA_ARGS__, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk,	\
+		   __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk,		\
+		   __bpf_vprintk, __bpf_vprintk, __bpf_printk /*3*/, __bpf_printk /*2*/,\
+		   __bpf_printk /*1*/, __bpf_printk /*0*/)
+
+/* Helper macro to print out debug messages */
+#define bpf_printk(fmt, args...) ___bpf_pick_printk(args)(fmt, ##args)
+
 #endif
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index d6bfbe009296..db05a5937105 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -24,6 +24,9 @@
 #elif defined(__TARGET_ARCH_sparc)
 	#define bpf_target_sparc
 	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_riscv)
+	#define bpf_target_riscv
+	#define bpf_target_defined
 #else
 
 /* Fall back to what the compiler says */
@@ -48,6 +51,9 @@
 #elif defined(__sparc__)
 	#define bpf_target_sparc
 	#define bpf_target_defined
+#elif defined(__riscv) && __riscv_xlen == 64
+	#define bpf_target_riscv
+	#define bpf_target_defined
 #endif /* no compiler target */
 
 #endif
@@ -288,6 +294,32 @@ struct pt_regs;
 #define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), pc)
 #endif
 
+#elif defined(bpf_target_riscv)
+
+struct pt_regs;
+#define PT_REGS_RV const volatile struct user_regs_struct
+#define PT_REGS_PARM1(x) (((PT_REGS_RV *)(x))->a0)
+#define PT_REGS_PARM2(x) (((PT_REGS_RV *)(x))->a1)
+#define PT_REGS_PARM3(x) (((PT_REGS_RV *)(x))->a2)
+#define PT_REGS_PARM4(x) (((PT_REGS_RV *)(x))->a3)
+#define PT_REGS_PARM5(x) (((PT_REGS_RV *)(x))->a4)
+#define PT_REGS_RET(x) (((PT_REGS_RV *)(x))->ra)
+#define PT_REGS_FP(x) (((PT_REGS_RV *)(x))->s5)
+#define PT_REGS_RC(x) (((PT_REGS_RV *)(x))->a5)
+#define PT_REGS_SP(x) (((PT_REGS_RV *)(x))->sp)
+#define PT_REGS_IP(x) (((PT_REGS_RV *)(x))->epc)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a0)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a1)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a2)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a3)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a4)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), ra)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), fp)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a5)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), sp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), epc)
+
 #endif
 
 #if defined(bpf_target_powerpc)
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 77dc24d58302..7e4c5586bd87 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -57,7 +57,7 @@ struct btf {
 	 * representation is broken up into three independently allocated
 	 * memory regions to be able to modify them independently.
 	 * raw_data is nulled out at that point, but can be later allocated
-	 * and cached again if user calls btf__get_raw_data(), at which point
+	 * and cached again if user calls btf__raw_data(), at which point
 	 * raw_data will contain a contiguous copy of header, types, and
 	 * strings:
 	 *
@@ -189,12 +189,17 @@ int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_
 	return 0;
 }
 
+static void *btf_add_type_offs_mem(struct btf *btf, size_t add_cnt)
+{
+	return libbpf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
+			      btf->nr_types, BTF_MAX_NR_TYPES, add_cnt);
+}
+
 static int btf_add_type_idx_entry(struct btf *btf, __u32 type_off)
 {
 	__u32 *p;
 
-	p = libbpf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
-			   btf->nr_types, BTF_MAX_NR_TYPES, 1);
+	p = btf_add_type_offs_mem(btf, 1);
 	if (!p)
 		return -ENOMEM;
 
@@ -231,17 +236,23 @@ static int btf_parse_hdr(struct btf *btf)
 		}
 		btf_bswap_hdr(hdr);
 	} else if (hdr->magic != BTF_MAGIC) {
-		pr_debug("Invalid BTF magic:%x\n", hdr->magic);
+		pr_debug("Invalid BTF magic: %x\n", hdr->magic);
+		return -EINVAL;
+	}
+
+	if (btf->raw_size < hdr->hdr_len) {
+		pr_debug("BTF header len %u larger than data size %u\n",
+			 hdr->hdr_len, btf->raw_size);
 		return -EINVAL;
 	}
 
-	meta_left = btf->raw_size - sizeof(*hdr);
-	if (meta_left < hdr->str_off + hdr->str_len) {
-		pr_debug("Invalid BTF total size:%u\n", btf->raw_size);
+	meta_left = btf->raw_size - hdr->hdr_len;
+	if (meta_left < (long long)hdr->str_off + hdr->str_len) {
+		pr_debug("Invalid BTF total size: %u\n", btf->raw_size);
 		return -EINVAL;
 	}
 
-	if (hdr->type_off + hdr->type_len > hdr->str_off) {
+	if ((long long)hdr->type_off + hdr->type_len > hdr->str_off) {
 		pr_debug("Invalid BTF data sections layout: type data at %u + %u, strings data at %u + %u\n",
 			 hdr->type_off, hdr->type_len, hdr->str_off, hdr->str_len);
 		return -EINVAL;
@@ -304,6 +315,8 @@ static int btf_type_size(const struct btf_type *t)
 		return base_size + sizeof(struct btf_var);
 	case BTF_KIND_DATASEC:
 		return base_size + vlen * sizeof(struct btf_var_secinfo);
+	case BTF_KIND_DECL_TAG:
+		return base_size + sizeof(struct btf_decl_tag);
 	default:
 		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
 		return -EINVAL;
@@ -376,6 +389,9 @@ static int btf_bswap_type_rest(struct btf_type *t)
 			v->size = bswap_32(v->size);
 		}
 		return 0;
+	case BTF_KIND_DECL_TAG:
+		btf_decl_tag(t)->component_idx = bswap_32(btf_decl_tag(t)->component_idx);
+		return 0;
 	default:
 		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
 		return -EINVAL;
@@ -425,6 +441,11 @@ __u32 btf__get_nr_types(const struct btf *btf)
 	return btf->start_id + btf->nr_types - 1;
 }
 
+__u32 btf__type_cnt(const struct btf *btf)
+{
+	return btf->start_id + btf->nr_types;
+}
+
 const struct btf *btf__base_btf(const struct btf *btf)
 {
 	return btf->base_btf;
@@ -456,8 +477,8 @@ static int determine_ptr_size(const struct btf *btf)
 	if (btf->base_btf && btf->base_btf->ptr_sz > 0)
 		return btf->base_btf->ptr_sz;
 
-	n = btf__get_nr_types(btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(btf);
+	for (i = 1; i < n; i++) {
 		t = btf__type_by_id(btf, i);
 		if (!btf_is_int(t))
 			continue;
@@ -517,9 +538,9 @@ int btf__set_pointer_size(struct btf *btf, size_t ptr_sz)
 
 static bool is_host_big_endian(void)
 {
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	return false;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	return true;
 #else
 # error "Unrecognized __BYTE_ORDER__"
@@ -586,6 +607,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 		case BTF_KIND_CONST:
 		case BTF_KIND_RESTRICT:
 		case BTF_KIND_VAR:
+		case BTF_KIND_DECL_TAG:
 			type_id = t->type;
 			break;
 		case BTF_KIND_ARRAY:
@@ -673,12 +695,12 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id)
 
 __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 {
-	__u32 i, nr_types = btf__get_nr_types(btf);
+	__u32 i, nr_types = btf__type_cnt(btf);
 
 	if (!strcmp(type_name, "void"))
 		return 0;
 
-	for (i = 1; i <= nr_types; i++) {
+	for (i = 1; i < nr_types; i++) {
 		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name = btf__name_by_offset(btf, t->name_off);
 
@@ -689,15 +711,15 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 	return libbpf_err(-ENOENT);
 }
 
-__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
-			     __u32 kind)
+static __s32 btf_find_by_name_kind(const struct btf *btf, int start_id,
+				   const char *type_name, __u32 kind)
 {
-	__u32 i, nr_types = btf__get_nr_types(btf);
+	__u32 i, nr_types = btf__type_cnt(btf);
 
 	if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void"))
 		return 0;
 
-	for (i = 1; i <= nr_types; i++) {
+	for (i = start_id; i < nr_types; i++) {
 		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name;
 
@@ -711,6 +733,18 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
 	return libbpf_err(-ENOENT);
 }
 
+__s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
+				 __u32 kind)
+{
+	return btf_find_by_name_kind(btf, btf->start_id, type_name, kind);
+}
+
+__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
+			     __u32 kind)
+{
+	return btf_find_by_name_kind(btf, 1, type_name, kind);
+}
+
 static bool btf_is_modifiable(const struct btf *btf)
 {
 	return (void *)btf->hdr != btf->raw_data;
@@ -758,7 +792,7 @@ static struct btf *btf_new_empty(struct btf *base_btf)
 
 	if (base_btf) {
 		btf->base_btf = base_btf;
-		btf->start_id = btf__get_nr_types(base_btf) + 1;
+		btf->start_id = btf__type_cnt(base_btf);
 		btf->start_str_off = base_btf->hdr->str_len;
 	}
 
@@ -808,7 +842,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
 
 	if (base_btf) {
 		btf->base_btf = base_btf;
-		btf->start_id = btf__get_nr_types(base_btf) + 1;
+		btf->start_id = btf__type_cnt(base_btf);
 		btf->start_str_off = base_btf->hdr->str_len;
 	}
 
@@ -863,7 +897,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
 	}
 
-	fd = open(path, O_RDONLY);
+	fd = open(path, O_RDONLY | O_CLOEXEC);
 	if (fd < 0) {
 		err = -errno;
 		pr_warn("failed to open %s: %s\n", path, strerror(errno));
@@ -1084,99 +1118,6 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf)
 	return libbpf_ptr(btf_parse(path, base_btf, NULL));
 }
 
-static int compare_vsi_off(const void *_a, const void *_b)
-{
-	const struct btf_var_secinfo *a = _a;
-	const struct btf_var_secinfo *b = _b;
-
-	return a->offset - b->offset;
-}
-
-static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
-			     struct btf_type *t)
-{
-	__u32 size = 0, off = 0, i, vars = btf_vlen(t);
-	const char *name = btf__name_by_offset(btf, t->name_off);
-	const struct btf_type *t_var;
-	struct btf_var_secinfo *vsi;
-	const struct btf_var *var;
-	int ret;
-
-	if (!name) {
-		pr_debug("No name found in string section for DATASEC kind.\n");
-		return -ENOENT;
-	}
-
-	/* .extern datasec size and var offsets were set correctly during
-	 * extern collection step, so just skip straight to sorting variables
-	 */
-	if (t->size)
-		goto sort_vars;
-
-	ret = bpf_object__section_size(obj, name, &size);
-	if (ret || !size || (t->size && t->size != size)) {
-		pr_debug("Invalid size for section %s: %u bytes\n", name, size);
-		return -ENOENT;
-	}
-
-	t->size = size;
-
-	for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) {
-		t_var = btf__type_by_id(btf, vsi->type);
-		var = btf_var(t_var);
-
-		if (!btf_is_var(t_var)) {
-			pr_debug("Non-VAR type seen in section %s\n", name);
-			return -EINVAL;
-		}
-
-		if (var->linkage == BTF_VAR_STATIC)
-			continue;
-
-		name = btf__name_by_offset(btf, t_var->name_off);
-		if (!name) {
-			pr_debug("No name found in string section for VAR kind\n");
-			return -ENOENT;
-		}
-
-		ret = bpf_object__variable_offset(obj, name, &off);
-		if (ret) {
-			pr_debug("No offset found in symbol table for VAR %s\n",
-				 name);
-			return -ENOENT;
-		}
-
-		vsi->offset = off;
-	}
-
-sort_vars:
-	qsort(btf_var_secinfos(t), vars, sizeof(*vsi), compare_vsi_off);
-	return 0;
-}
-
-int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
-{
-	int err = 0;
-	__u32 i;
-
-	for (i = 1; i <= btf->nr_types; i++) {
-		struct btf_type *t = btf_type_by_id(btf, i);
-
-		/* Loader needs to fix up some of the things compiler
-		 * couldn't get its hands on while emitting BTF. This
-		 * is section size and global variable offset. We use
-		 * the info from the ELF itself for this purpose.
-		 */
-		if (btf_is_datasec(t)) {
-			err = btf_fixup_datasec(obj, btf, t);
-			if (err)
-				break;
-		}
-	}
-
-	return libbpf_err(err);
-}
-
 static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian);
 
 int btf__load_into_kernel(struct btf *btf)
@@ -1294,7 +1235,7 @@ err_out:
 	return NULL;
 }
 
-const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
+const void *btf__raw_data(const struct btf *btf_ro, __u32 *size)
 {
 	struct btf *btf = (struct btf *)btf_ro;
 	__u32 data_sz;
@@ -1302,7 +1243,7 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
 
 	data = btf_get_raw_data(btf, &data_sz, btf->swapped_endian);
 	if (!data)
-		return errno = -ENOMEM, NULL;
+		return errno = ENOMEM, NULL;
 
 	btf->raw_size = data_sz;
 	if (btf->swapped_endian)
@@ -1313,6 +1254,9 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
 	return data;
 }
 
+__attribute__((alias("btf__raw_data")))
+const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
+
 const char *btf__str_by_offset(const struct btf *btf, __u32 offset)
 {
 	if (offset < btf->start_str_off)
@@ -1685,6 +1629,111 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t
 	return btf_commit_type(btf, sz);
 }
 
+static int btf_rewrite_type_ids(__u32 *type_id, void *ctx)
+{
+	struct btf *btf = ctx;
+
+	if (!*type_id) /* nothing to do for VOID references */
+		return 0;
+
+	/* we haven't updated btf's type count yet, so
+	 * btf->start_id + btf->nr_types - 1 is the type ID offset we should
+	 * add to all newly added BTF types
+	 */
+	*type_id += btf->start_id + btf->nr_types - 1;
+	return 0;
+}
+
+int btf__add_btf(struct btf *btf, const struct btf *src_btf)
+{
+	struct btf_pipe p = { .src = src_btf, .dst = btf };
+	int data_sz, sz, cnt, i, err, old_strs_len;
+	__u32 *off;
+	void *t;
+
+	/* appending split BTF isn't supported yet */
+	if (src_btf->base_btf)
+		return libbpf_err(-ENOTSUP);
+
+	/* deconstruct BTF, if necessary, and invalidate raw_data */
+	if (btf_ensure_modifiable(btf))
+		return libbpf_err(-ENOMEM);
+
+	/* remember original strings section size if we have to roll back
+	 * partial strings section changes
+	 */
+	old_strs_len = btf->hdr->str_len;
+
+	data_sz = src_btf->hdr->type_len;
+	cnt = btf__type_cnt(src_btf) - 1;
+
+	/* pre-allocate enough memory for new types */
+	t = btf_add_type_mem(btf, data_sz);
+	if (!t)
+		return libbpf_err(-ENOMEM);
+
+	/* pre-allocate enough memory for type offset index for new types */
+	off = btf_add_type_offs_mem(btf, cnt);
+	if (!off)
+		return libbpf_err(-ENOMEM);
+
+	/* bulk copy types data for all types from src_btf */
+	memcpy(t, src_btf->types_data, data_sz);
+
+	for (i = 0; i < cnt; i++) {
+		sz = btf_type_size(t);
+		if (sz < 0) {
+			/* unlikely, has to be corrupted src_btf */
+			err = sz;
+			goto err_out;
+		}
+
+		/* fill out type ID to type offset mapping for lookups by type ID */
+		*off = t - btf->types_data;
+
+		/* add, dedup, and remap strings referenced by this BTF type */
+		err = btf_type_visit_str_offs(t, btf_rewrite_str, &p);
+		if (err)
+			goto err_out;
+
+		/* remap all type IDs referenced from this BTF type */
+		err = btf_type_visit_type_ids(t, btf_rewrite_type_ids, btf);
+		if (err)
+			goto err_out;
+
+		/* go to next type data and type offset index entry */
+		t += sz;
+		off++;
+	}
+
+	/* Up until now any of the copied type data was effectively invisible,
+	 * so if we exited early before this point due to error, BTF would be
+	 * effectively unmodified. There would be extra internal memory
+	 * pre-allocated, but it would not be available for querying.  But now
+	 * that we've copied and rewritten all the data successfully, we can
+	 * update type count and various internal offsets and sizes to
+	 * "commit" the changes and made them visible to the outside world.
+	 */
+	btf->hdr->type_len += data_sz;
+	btf->hdr->str_off += data_sz;
+	btf->nr_types += cnt;
+
+	/* return type ID of the first added BTF type */
+	return btf->start_id + btf->nr_types - cnt;
+err_out:
+	/* zero out preallocated memory as if it was just allocated with
+	 * libbpf_add_mem()
+	 */
+	memset(btf->types_data + btf->hdr->type_len, 0, data_sz);
+	memset(btf->strs_data + old_strs_len, 0, btf->hdr->str_len - old_strs_len);
+
+	/* and now restore original strings section size; types data size
+	 * wasn't modified, so doesn't need restoring, see big comment above */
+	btf->hdr->str_len = old_strs_len;
+
+	return libbpf_err(err);
+}
+
 /*
  * Append new BTF_KIND_INT type with:
  *   - *name* - non-empty, non-NULL type name;
@@ -1933,7 +1982,7 @@ int btf__add_union(struct btf *btf, const char *name, __u32 byte_sz)
 
 static struct btf_type *btf_last_type(struct btf *btf)
 {
-	return btf_type_by_id(btf, btf__get_nr_types(btf));
+	return btf_type_by_id(btf, btf__type_cnt(btf) - 1);
 }
 
 /*
@@ -2440,6 +2489,48 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __
 	return 0;
 }
 
+/*
+ * Append new BTF_KIND_DECL_TAG type with:
+ *   - *value* - non-empty/non-NULL string;
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ *   - *component_idx* - -1 for tagging reference type, otherwise struct/union
+ *     member or function argument index;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
+		 int component_idx)
+{
+	struct btf_type *t;
+	int sz, value_off;
+
+	if (!value || !value[0] || component_idx < -1)
+		return libbpf_err(-EINVAL);
+
+	if (validate_type_id(ref_type_id))
+		return libbpf_err(-EINVAL);
+
+	if (btf_ensure_modifiable(btf))
+		return libbpf_err(-ENOMEM);
+
+	sz = sizeof(struct btf_type) + sizeof(struct btf_decl_tag);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return libbpf_err(-ENOMEM);
+
+	value_off = btf__add_str(btf, value);
+	if (value_off < 0)
+		return value_off;
+
+	t->name_off = value_off;
+	t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, false);
+	t->type = ref_type_id;
+	btf_decl_tag(t)->component_idx = component_idx;
+
+	return btf_commit_type(btf, sz);
+}
+
 struct btf_ext_sec_setup_param {
 	__u32 off;
 	__u32 len;
@@ -2914,8 +3005,10 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
 		return libbpf_err(-EINVAL);
 	}
 
-	if (btf_ensure_modifiable(btf))
-		return libbpf_err(-ENOMEM);
+	if (btf_ensure_modifiable(btf)) {
+		err = -ENOMEM;
+		goto done;
+	}
 
 	err = btf_dedup_prep(d);
 	if (err) {
@@ -3095,7 +3188,7 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 		goto done;
 	}
 
-	type_cnt = btf__get_nr_types(btf) + 1;
+	type_cnt = btf__type_cnt(btf);
 	d->map = malloc(sizeof(__u32) * type_cnt);
 	if (!d->map) {
 		err = -ENOMEM;
@@ -3256,8 +3349,8 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2)
 	       t1->size == t2->size;
 }
 
-/* Calculate type signature hash of INT. */
-static long btf_hash_int(struct btf_type *t)
+/* Calculate type signature hash of INT or TAG. */
+static long btf_hash_int_decl_tag(struct btf_type *t)
 {
 	__u32 info = *(__u32 *)(t + 1);
 	long h;
@@ -3267,8 +3360,8 @@ static long btf_hash_int(struct btf_type *t)
 	return h;
 }
 
-/* Check structural equality of two INTs. */
-static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2)
+/* Check structural equality of two INTs or TAGs. */
+static bool btf_equal_int_tag(struct btf_type *t1, struct btf_type *t2)
 {
 	__u32 info1, info2;
 
@@ -3535,7 +3628,8 @@ static int btf_dedup_prep(struct btf_dedup *d)
 			h = btf_hash_common(t);
 			break;
 		case BTF_KIND_INT:
-			h = btf_hash_int(t);
+		case BTF_KIND_DECL_TAG:
+			h = btf_hash_int_decl_tag(t);
 			break;
 		case BTF_KIND_ENUM:
 			h = btf_hash_enum(t);
@@ -3590,14 +3684,15 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 	case BTF_KIND_FUNC_PROTO:
 	case BTF_KIND_VAR:
 	case BTF_KIND_DATASEC:
+	case BTF_KIND_DECL_TAG:
 		return 0;
 
 	case BTF_KIND_INT:
-		h = btf_hash_int(t);
+		h = btf_hash_int_decl_tag(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
-			if (btf_equal_int(t, cand)) {
+			if (btf_equal_int_tag(t, cand)) {
 				new_id = cand_id;
 				break;
 			}
@@ -3881,7 +3976,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 
 	switch (cand_kind) {
 	case BTF_KIND_INT:
-		return btf_equal_int(cand_type, canon_type);
+		return btf_equal_int_tag(cand_type, canon_type);
 
 	case BTF_KIND_ENUM:
 		if (d->opts.dont_resolve_fwds)
@@ -4210,6 +4305,23 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		}
 		break;
 
+	case BTF_KIND_DECL_TAG:
+		ref_type_id = btf_dedup_ref_type(d, t->type);
+		if (ref_type_id < 0)
+			return ref_type_id;
+		t->type = ref_type_id;
+
+		h = btf_hash_int_decl_tag(t);
+		for_each_dedup_cand(d, hash_entry, h) {
+			cand_id = (__u32)(long)hash_entry->value;
+			cand = btf_type_by_id(d->btf, cand_id);
+			if (btf_equal_int_tag(t, cand)) {
+				new_id = cand_id;
+				break;
+			}
+		}
+		break;
+
 	case BTF_KIND_ARRAY: {
 		struct btf_array *info = btf_array(t);
 
@@ -4482,6 +4594,7 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_VAR:
+	case BTF_KIND_DECL_TAG:
 		return visit(&t->type, ctx);
 
 	case BTF_KIND_ARRAY: {
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 4a711f990904..bc005ba3ceec 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -1,5 +1,6 @@
 /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 /* Copyright (c) 2018 Facebook */
+/*! \file */
 
 #ifndef __LIBBPF_BTF_H
 #define __LIBBPF_BTF_H
@@ -30,11 +31,80 @@ enum btf_endianness {
 	BTF_BIG_ENDIAN = 1,
 };
 
+/**
+ * @brief **btf__free()** frees all data of a BTF object
+ * @param btf BTF object to free
+ */
 LIBBPF_API void btf__free(struct btf *btf);
 
+/**
+ * @brief **btf__new()** creates a new instance of a BTF object from the raw
+ * bytes of an ELF's BTF section
+ * @param data raw bytes
+ * @param size number of bytes passed in `data`
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
 LIBBPF_API struct btf *btf__new(const void *data, __u32 size);
+
+/**
+ * @brief **btf__new_split()** create a new instance of a BTF object from the
+ * provided raw data bytes. It takes another BTF instance, **base_btf**, which
+ * serves as a base BTF, which is extended by types in a newly created BTF
+ * instance
+ * @param data raw bytes
+ * @param size length of raw bytes
+ * @param base_btf the base BTF object
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * If *base_btf* is NULL, `btf__new_split()` is equivalent to `btf__new()` and
+ * creates non-split BTF.
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
 LIBBPF_API struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf);
+
+/**
+ * @brief **btf__new_empty()** creates an empty BTF object.  Use
+ * `btf__add_*()` to populate such BTF object.
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
 LIBBPF_API struct btf *btf__new_empty(void);
+
+/**
+ * @brief **btf__new_empty_split()** creates an unpopulated BTF object from an
+ * ELF BTF section except with a base BTF on top of which split BTF should be
+ * based
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * If *base_btf* is NULL, `btf__new_empty_split()` is equivalent to
+ * `btf__new_empty()` and creates non-split BTF.
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
 LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf);
 
 LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext);
@@ -50,16 +120,21 @@ LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
 
 LIBBPF_API struct btf *btf__load_from_kernel_by_id(__u32 id);
 LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf);
+LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_from_kernel_by_id instead")
 LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
 
+LIBBPF_DEPRECATED_SINCE(0, 6, "intended for internal libbpf use only")
 LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
+LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_into_kernel instead")
 LIBBPF_API int btf__load(struct btf *btf);
 LIBBPF_API int btf__load_into_kernel(struct btf *btf);
 LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
 				   const char *type_name);
 LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf,
 					const char *type_name, __u32 kind);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__type_cnt() instead; note that btf__get_nr_types() == btf__type_cnt() - 1")
 LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf);
+LIBBPF_API __u32 btf__type_cnt(const struct btf *btf);
 LIBBPF_API const struct btf *btf__base_btf(const struct btf *btf);
 LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
 						  __u32 id);
@@ -72,7 +147,9 @@ LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id);
 LIBBPF_API int btf__fd(const struct btf *btf);
 LIBBPF_API void btf__set_fd(struct btf *btf, int fd);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__raw_data() instead")
 LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
+LIBBPF_API const void *btf__raw_data(const struct btf *btf, __u32 *size);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
 LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset);
 LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
@@ -101,6 +178,28 @@ LIBBPF_API int btf__find_str(struct btf *btf, const char *s);
 LIBBPF_API int btf__add_str(struct btf *btf, const char *s);
 LIBBPF_API int btf__add_type(struct btf *btf, const struct btf *src_btf,
 			     const struct btf_type *src_type);
+/**
+ * @brief **btf__add_btf()** appends all the BTF types from *src_btf* into *btf*
+ * @param btf BTF object which all the BTF types and strings are added to
+ * @param src_btf BTF object which all BTF types and referenced strings are copied from
+ * @return BTF type ID of the first appended BTF type, or negative error code
+ *
+ * **btf__add_btf()** can be used to simply and efficiently append the entire
+ * contents of one BTF object to another one. All the BTF type data is copied
+ * over, all referenced type IDs are adjusted by adding a necessary ID offset.
+ * Only strings referenced from BTF types are copied over and deduplicated, so
+ * if there were some unused strings in *src_btf*, those won't be copied over,
+ * which is consistent with the general string deduplication semantics of BTF
+ * writing APIs.
+ *
+ * If any error is encountered during this process, the contents of *btf* is
+ * left intact, which means that **btf__add_btf()** follows the transactional
+ * semantics and the operation as a whole is all-or-nothing.
+ *
+ * *src_btf* has to be non-split BTF, as of now copying types from split BTF
+ * is not supported and will result in -ENOTSUP error code returned.
+ */
+LIBBPF_API int btf__add_btf(struct btf *btf, const struct btf *src_btf);
 
 LIBBPF_API int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding);
 LIBBPF_API int btf__add_float(struct btf *btf, const char *name, size_t byte_sz);
@@ -141,6 +240,10 @@ LIBBPF_API int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz
 LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id,
 					 __u32 offset, __u32 byte_sz);
 
+/* tag construction API */
+LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
+			    int component_idx);
+
 struct btf_dedup_opts {
 	unsigned int dedup_table_size;
 	bool dont_resolve_fwds;
@@ -328,6 +431,11 @@ static inline bool btf_is_float(const struct btf_type *t)
 	return btf_kind(t) == BTF_KIND_FLOAT;
 }
 
+static inline bool btf_is_decl_tag(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_DECL_TAG;
+}
+
 static inline __u8 btf_int_encoding(const struct btf_type *t)
 {
 	return BTF_INT_ENCODING(*(__u32 *)(t + 1));
@@ -396,6 +504,12 @@ btf_var_secinfos(const struct btf_type *t)
 	return (struct btf_var_secinfo *)(t + 1);
 }
 
+struct btf_decl_tag;
+static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t)
+{
+	return (struct btf_decl_tag *)(t + 1);
+}
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index e4b483f15fb9..17db62b5002e 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -188,7 +188,7 @@ err:
 
 static int btf_dump_resize(struct btf_dump *d)
 {
-	int err, last_id = btf__get_nr_types(d->btf);
+	int err, last_id = btf__type_cnt(d->btf) - 1;
 
 	if (last_id <= d->last_id)
 		return 0;
@@ -262,7 +262,7 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
 {
 	int err, i;
 
-	if (id > btf__get_nr_types(d->btf))
+	if (id >= btf__type_cnt(d->btf))
 		return libbpf_err(-EINVAL);
 
 	err = btf_dump_resize(d);
@@ -294,11 +294,11 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
  */
 static int btf_dump_mark_referenced(struct btf_dump *d)
 {
-	int i, j, n = btf__get_nr_types(d->btf);
+	int i, j, n = btf__type_cnt(d->btf);
 	const struct btf_type *t;
 	__u16 vlen;
 
-	for (i = d->last_id + 1; i <= n; i++) {
+	for (i = d->last_id + 1; i < n; i++) {
 		t = btf__type_by_id(d->btf, i);
 		vlen = btf_vlen(t);
 
@@ -316,6 +316,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d)
 		case BTF_KIND_TYPEDEF:
 		case BTF_KIND_FUNC:
 		case BTF_KIND_VAR:
+		case BTF_KIND_DECL_TAG:
 			d->type_states[t->type].referenced = 1;
 			break;
 
@@ -583,6 +584,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 	case BTF_KIND_FUNC:
 	case BTF_KIND_VAR:
 	case BTF_KIND_DATASEC:
+	case BTF_KIND_DECL_TAG:
 		d->type_states[id].order_state = ORDERED;
 		return 0;
 
@@ -1560,29 +1562,28 @@ static int btf_dump_get_bitfield_value(struct btf_dump *d,
 				       __u64 *value)
 {
 	__u16 left_shift_bits, right_shift_bits;
-	__u8 nr_copy_bits, nr_copy_bytes;
 	const __u8 *bytes = data;
-	int sz = t->size;
+	__u8 nr_copy_bits;
 	__u64 num = 0;
 	int i;
 
 	/* Maximum supported bitfield size is 64 bits */
-	if (sz > 8) {
-		pr_warn("unexpected bitfield size %d\n", sz);
+	if (t->size > 8) {
+		pr_warn("unexpected bitfield size %d\n", t->size);
 		return -EINVAL;
 	}
 
 	/* Bitfield value retrieval is done in two steps; first relevant bytes are
 	 * stored in num, then we left/right shift num to eliminate irrelevant bits.
 	 */
-	nr_copy_bits = bit_sz + bits_offset;
-	nr_copy_bytes = t->size;
-#if __BYTE_ORDER == __LITTLE_ENDIAN
-	for (i = nr_copy_bytes - 1; i >= 0; i--)
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	for (i = t->size - 1; i >= 0; i--)
 		num = num * 256 + bytes[i];
-#elif __BYTE_ORDER == __BIG_ENDIAN
-	for (i = 0; i < nr_copy_bytes; i++)
+	nr_copy_bits = bit_sz + bits_offset;
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+	for (i = 0; i < t->size; i++)
 		num = num * 256 + bytes[i];
+	nr_copy_bits = t->size * 8 - bits_offset;
 #else
 # error "Unrecognized __BYTE_ORDER__"
 #endif
@@ -1656,9 +1657,15 @@ static int btf_dump_base_type_check_zero(struct btf_dump *d,
 	return 0;
 }
 
-static bool ptr_is_aligned(const void *data, int data_sz)
+static bool ptr_is_aligned(const struct btf *btf, __u32 type_id,
+			   const void *data)
 {
-	return ((uintptr_t)data) % data_sz == 0;
+	int alignment = btf__align_of(btf, type_id);
+
+	if (alignment == 0)
+		return false;
+
+	return ((uintptr_t)data) % alignment == 0;
 }
 
 static int btf_dump_int_data(struct btf_dump *d,
@@ -1669,9 +1676,10 @@ static int btf_dump_int_data(struct btf_dump *d,
 {
 	__u8 encoding = btf_int_encoding(t);
 	bool sign = encoding & BTF_INT_SIGNED;
+	char buf[16] __attribute__((aligned(16)));
 	int sz = t->size;
 
-	if (sz == 0) {
+	if (sz == 0 || sz > sizeof(buf)) {
 		pr_warn("unexpected size %d for id [%u]\n", sz, type_id);
 		return -EINVAL;
 	}
@@ -1679,8 +1687,10 @@ static int btf_dump_int_data(struct btf_dump *d,
 	/* handle packed int data - accesses of integers not aligned on
 	 * int boundaries can cause problems on some platforms.
 	 */
-	if (!ptr_is_aligned(data, sz))
-		return btf_dump_bitfield_data(d, t, data, 0, 0);
+	if (!ptr_is_aligned(d->btf, type_id, data)) {
+		memcpy(buf, data, sz);
+		data = buf;
+	}
 
 	switch (sz) {
 	case 16: {
@@ -1690,10 +1700,10 @@ static int btf_dump_int_data(struct btf_dump *d,
 		/* avoid use of __int128 as some 32-bit platforms do not
 		 * support it.
 		 */
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 		lsi = ints[0];
 		msi = ints[1];
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 		lsi = ints[1];
 		msi = ints[0];
 #else
@@ -1766,7 +1776,7 @@ static int btf_dump_float_data(struct btf_dump *d,
 	int sz = t->size;
 
 	/* handle unaligned data; copy to local union */
-	if (!ptr_is_aligned(data, sz)) {
+	if (!ptr_is_aligned(d->btf, type_id, data)) {
 		memcpy(&fl, data, sz);
 		flp = &fl;
 	}
@@ -1929,7 +1939,7 @@ static int btf_dump_ptr_data(struct btf_dump *d,
 			      __u32 id,
 			      const void *data)
 {
-	if (ptr_is_aligned(data, d->ptr_sz) && d->ptr_sz == sizeof(void *)) {
+	if (ptr_is_aligned(d->btf, id, data) && d->ptr_sz == sizeof(void *)) {
 		btf_dump_type_values(d, "%p", *(void **)data);
 	} else {
 		union ptr_data pt;
@@ -1949,10 +1959,8 @@ static int btf_dump_get_enum_value(struct btf_dump *d,
 				   __u32 id,
 				   __s64 *value)
 {
-	int sz = t->size;
-
 	/* handle unaligned enum value */
-	if (!ptr_is_aligned(data, sz)) {
+	if (!ptr_is_aligned(d->btf, id, data)) {
 		__u64 val;
 		int err;
 
@@ -2215,6 +2223,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d,
 	case BTF_KIND_FWD:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_FUNC_PROTO:
+	case BTF_KIND_DECL_TAG:
 		err = btf_dump_unsupported_data(d, t, id);
 		break;
 	case BTF_KIND_INT:
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index 8df718a6b142..502dea53a742 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -5,6 +5,7 @@
 #include <string.h>
 #include <errno.h>
 #include <linux/filter.h>
+#include <sys/param.h>
 #include "btf.h"
 #include "bpf.h"
 #include "libbpf.h"
@@ -12,9 +13,12 @@
 #include "hashmap.h"
 #include "bpf_gen_internal.h"
 #include "skel_internal.h"
+#include <asm/byteorder.h>
 
-#define MAX_USED_MAPS 64
-#define MAX_USED_PROGS 32
+#define MAX_USED_MAPS	64
+#define MAX_USED_PROGS	32
+#define MAX_KFUNC_DESCS 256
+#define MAX_FD_ARRAY_SZ (MAX_USED_PROGS + MAX_KFUNC_DESCS)
 
 /* The following structure describes the stack layout of the loader program.
  * In addition R6 contains the pointer to context.
@@ -29,7 +33,6 @@
  */
 struct loader_stack {
 	__u32 btf_fd;
-	__u32 map_fd[MAX_USED_MAPS];
 	__u32 prog_fd[MAX_USED_PROGS];
 	__u32 inner_map_fd;
 };
@@ -135,16 +138,56 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level)
 
 static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
 {
+	__u32 size8 = roundup(size, 8);
+	__u64 zero = 0;
 	void *prev;
 
-	if (realloc_data_buf(gen, size))
+	if (realloc_data_buf(gen, size8))
 		return 0;
 	prev = gen->data_cur;
-	memcpy(gen->data_cur, data, size);
-	gen->data_cur += size;
+	if (data) {
+		memcpy(gen->data_cur, data, size);
+		memcpy(gen->data_cur + size, &zero, size8 - size);
+	} else {
+		memset(gen->data_cur, 0, size8);
+	}
+	gen->data_cur += size8;
 	return prev - gen->data_start;
 }
 
+/* Get index for map_fd/btf_fd slot in reserved fd_array, or in data relative
+ * to start of fd_array. Caller can decide if it is usable or not.
+ */
+static int add_map_fd(struct bpf_gen *gen)
+{
+	if (!gen->fd_array)
+		gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
+	if (gen->nr_maps == MAX_USED_MAPS) {
+		pr_warn("Total maps exceeds %d\n", MAX_USED_MAPS);
+		gen->error = -E2BIG;
+		return 0;
+	}
+	return gen->nr_maps++;
+}
+
+static int add_kfunc_btf_fd(struct bpf_gen *gen)
+{
+	int cur;
+
+	if (!gen->fd_array)
+		gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
+	if (gen->nr_fd_array == MAX_KFUNC_DESCS) {
+		cur = add_data(gen, NULL, sizeof(int));
+		return (cur - gen->fd_array) / sizeof(int);
+	}
+	return MAX_USED_MAPS + gen->nr_fd_array++;
+}
+
+static int blob_fd_array_off(struct bpf_gen *gen, int index)
+{
+	return gen->fd_array + index * sizeof(int);
+}
+
 static int insn_bytes_to_bpf_size(__u32 sz)
 {
 	switch (sz) {
@@ -166,14 +209,22 @@ static void emit_rel_store(struct bpf_gen *gen, int off, int data)
 	emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0));
 }
 
-/* *(u64 *)(blob + off) = (u64)(void *)(%sp + stack_off) */
-static void emit_rel_store_sp(struct bpf_gen *gen, int off, int stack_off)
+static void move_blob2blob(struct bpf_gen *gen, int off, int size, int blob_off)
 {
-	emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_10));
-	emit(gen, BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, stack_off));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_2, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, blob_off));
+	emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_2, 0));
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
 					 0, 0, 0, off));
-	emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0));
+	emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0));
+}
+
+static void move_blob2ctx(struct bpf_gen *gen, int ctx_off, int size, int blob_off)
+{
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, blob_off));
+	emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_1, 0));
+	emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_6, BPF_REG_0, ctx_off));
 }
 
 static void move_ctx2blob(struct bpf_gen *gen, int off, int size, int ctx_off,
@@ -321,11 +372,11 @@ int bpf_gen__finish(struct bpf_gen *gen)
 			       offsetof(struct bpf_prog_desc, prog_fd), 4,
 			       stack_off(prog_fd[i]));
 	for (i = 0; i < gen->nr_maps; i++)
-		move_stack2ctx(gen,
-			       sizeof(struct bpf_loader_ctx) +
-			       sizeof(struct bpf_map_desc) * i +
-			       offsetof(struct bpf_map_desc, map_fd), 4,
-			       stack_off(map_fd[i]));
+		move_blob2ctx(gen,
+			      sizeof(struct bpf_loader_ctx) +
+			      sizeof(struct bpf_map_desc) * i +
+			      offsetof(struct bpf_map_desc, map_fd), 4,
+			      blob_fd_array_off(gen, i));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0));
 	emit(gen, BPF_EXIT_INSN());
 	pr_debug("gen: finish %d\n", gen->error);
@@ -381,11 +432,11 @@ void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data,
 }
 
 void bpf_gen__map_create(struct bpf_gen *gen,
-			 struct bpf_create_map_attr *map_attr, int map_idx)
+			 struct bpf_create_map_params *map_attr, int map_idx)
 {
 	int attr_size = offsetofend(union bpf_attr, btf_vmlinux_value_type_id);
 	bool close_inner_map_fd = false;
-	int map_create_attr;
+	int map_create_attr, idx;
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
@@ -393,6 +444,7 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 	attr.key_size = map_attr->key_size;
 	attr.value_size = map_attr->value_size;
 	attr.map_flags = map_attr->map_flags;
+	attr.map_extra = map_attr->map_extra;
 	memcpy(attr.map_name, map_attr->name,
 	       min((unsigned)strlen(map_attr->name), BPF_OBJ_NAME_LEN - 1));
 	attr.numa_node = map_attr->numa_node;
@@ -462,9 +514,11 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 		gen->error = -EDOM; /* internal bug */
 		return;
 	} else {
-		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7,
-				      stack_off(map_fd[map_idx])));
-		gen->nr_maps++;
+		/* add_map_fd does gen->nr_maps++ */
+		idx = add_map_fd(gen);
+		emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+						 0, 0, 0, blob_fd_array_off(gen, idx)));
+		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_7, 0));
 	}
 	if (close_inner_map_fd)
 		emit_sys_close_stack(gen, stack_off(inner_map_fd));
@@ -506,8 +560,8 @@ static void emit_find_attach_target(struct bpf_gen *gen)
 	 */
 }
 
-void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind,
-			    int insn_idx)
+void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak,
+			    bool is_typeless, int kind, int insn_idx)
 {
 	struct ksym_relo_desc *relo;
 
@@ -519,38 +573,292 @@ void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind,
 	gen->relos = relo;
 	relo += gen->relo_cnt;
 	relo->name = name;
+	relo->is_weak = is_weak;
+	relo->is_typeless = is_typeless;
 	relo->kind = kind;
 	relo->insn_idx = insn_idx;
 	gen->relo_cnt++;
 }
 
-static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns)
+/* returns existing ksym_desc with ref incremented, or inserts a new one */
+static struct ksym_desc *get_ksym_desc(struct bpf_gen *gen, struct ksym_relo_desc *relo)
 {
-	int name, insn, len = strlen(relo->name) + 1;
+	struct ksym_desc *kdesc;
 
-	pr_debug("gen: emit_relo: %s at %d\n", relo->name, relo->insn_idx);
-	name = add_data(gen, relo->name, len);
+	for (int i = 0; i < gen->nr_ksyms; i++) {
+		if (!strcmp(gen->ksyms[i].name, relo->name)) {
+			gen->ksyms[i].ref++;
+			return &gen->ksyms[i];
+		}
+	}
+	kdesc = libbpf_reallocarray(gen->ksyms, gen->nr_ksyms + 1, sizeof(*kdesc));
+	if (!kdesc) {
+		gen->error = -ENOMEM;
+		return NULL;
+	}
+	gen->ksyms = kdesc;
+	kdesc = &gen->ksyms[gen->nr_ksyms++];
+	kdesc->name = relo->name;
+	kdesc->kind = relo->kind;
+	kdesc->ref = 1;
+	kdesc->off = 0;
+	kdesc->insn = 0;
+	return kdesc;
+}
+
+/* Overwrites BPF_REG_{0, 1, 2, 3, 4, 7}
+ * Returns result in BPF_REG_7
+ */
+static void emit_bpf_find_by_name_kind(struct bpf_gen *gen, struct ksym_relo_desc *relo)
+{
+	int name_off, len = strlen(relo->name) + 1;
 
+	name_off = add_data(gen, relo->name, len);
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
-					 0, 0, 0, name));
+					 0, 0, 0, name_off));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_2, len));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_3, relo->kind));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0));
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind));
 	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
 	debug_ret(gen, "find_by_name_kind(%s,%d)", relo->name, relo->kind);
-	emit_check_err(gen);
+}
+
+/* Overwrites BPF_REG_{0, 1, 2, 3, 4, 7}
+ * Returns result in BPF_REG_7
+ * Returns u64 symbol addr in BPF_REG_9
+ */
+static void emit_bpf_kallsyms_lookup_name(struct bpf_gen *gen, struct ksym_relo_desc *relo)
+{
+	int name_off, len = strlen(relo->name) + 1, res_off;
+
+	name_off = add_data(gen, relo->name, len);
+	res_off = add_data(gen, NULL, 8); /* res is u64 */
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, name_off));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_2, len));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_4, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, res_off));
+	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_4));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_kallsyms_lookup_name));
+	emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0));
+	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
+	debug_ret(gen, "kallsyms_lookup_name(%s,%d)", relo->name, relo->kind);
+}
+
+/* Expects:
+ * BPF_REG_8 - pointer to instruction
+ *
+ * We need to reuse BTF fd for same symbol otherwise each relocation takes a new
+ * index, while kernel limits total kfunc BTFs to 256. For duplicate symbols,
+ * this would mean a new BTF fd index for each entry. By pairing symbol name
+ * with index, we get the insn->imm, insn->off pairing that kernel uses for
+ * kfunc_tab, which becomes the effective limit even though all of them may
+ * share same index in fd_array (such that kfunc_btf_tab has 1 element).
+ */
+static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn)
+{
+	struct ksym_desc *kdesc;
+	int btf_fd_idx;
+
+	kdesc = get_ksym_desc(gen, relo);
+	if (!kdesc)
+		return;
+	/* try to copy from existing bpf_insn */
+	if (kdesc->ref > 1) {
+		move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + offsetof(struct bpf_insn, imm));
+		move_blob2blob(gen, insn + offsetof(struct bpf_insn, off), 2,
+			       kdesc->insn + offsetof(struct bpf_insn, off));
+		goto log;
+	}
+	/* remember insn offset, so we can copy BTF ID and FD later */
+	kdesc->insn = insn;
+	emit_bpf_find_by_name_kind(gen, relo);
+	if (!relo->is_weak)
+		emit_check_err(gen);
+	/* get index in fd_array to store BTF FD at */
+	btf_fd_idx = add_kfunc_btf_fd(gen);
+	if (btf_fd_idx > INT16_MAX) {
+		pr_warn("BTF fd off %d for kfunc %s exceeds INT16_MAX, cannot process relocation\n",
+			btf_fd_idx, relo->name);
+		gen->error = -E2BIG;
+		return;
+	}
+	kdesc->off = btf_fd_idx;
+	/* set a default value for imm */
+	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0));
+	/* skip success case store if ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 1));
 	/* store btf_id into insn[insn_idx].imm */
-	insn = insns + sizeof(struct bpf_insn) * relo->insn_idx +
-		offsetof(struct bpf_insn, imm);
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm)));
+	/* load fd_array slot pointer */
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
-					 0, 0, 0, insn));
-	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, 0));
-	if (relo->kind == BTF_KIND_VAR) {
-		/* store btf_obj_fd into insn[insn_idx + 1].imm */
-		emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
-		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7,
-				      sizeof(struct bpf_insn)));
+					 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx)));
+	/* skip store of BTF fd if ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 3));
+	/* store BTF fd in slot */
+	emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7));
+	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32));
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0));
+	/* set a default value for off */
+	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0));
+	/* skip insn->off store if ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 2));
+	/* skip if vmlinux BTF */
+	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_9, 0, 1));
+	/* store index into insn[insn_idx].off */
+	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), btf_fd_idx));
+log:
+	if (!gen->log_level)
+		return;
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_8,
+			      offsetof(struct bpf_insn, imm)));
+	emit(gen, BPF_LDX_MEM(BPF_H, BPF_REG_9, BPF_REG_8,
+			      offsetof(struct bpf_insn, off)));
+	debug_regs(gen, BPF_REG_7, BPF_REG_9, " func (%s:count=%d): imm: %%d, off: %%d",
+		   relo->name, kdesc->ref);
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, blob_fd_array_off(gen, kdesc->off)));
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_0, 0));
+	debug_regs(gen, BPF_REG_9, -1, " func (%s:count=%d): btf_fd",
+		   relo->name, kdesc->ref);
+}
+
+static void emit_ksym_relo_log(struct bpf_gen *gen, struct ksym_relo_desc *relo,
+			       int ref)
+{
+	if (!gen->log_level)
+		return;
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_8,
+			      offsetof(struct bpf_insn, imm)));
+	emit(gen, BPF_LDX_MEM(BPF_H, BPF_REG_9, BPF_REG_8, sizeof(struct bpf_insn) +
+			      offsetof(struct bpf_insn, imm)));
+	debug_regs(gen, BPF_REG_7, BPF_REG_9, " var t=%d w=%d (%s:count=%d): imm[0]: %%d, imm[1]: %%d",
+		   relo->is_typeless, relo->is_weak, relo->name, ref);
+	emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code)));
+	debug_regs(gen, BPF_REG_9, -1, " var t=%d w=%d (%s:count=%d): insn.reg",
+		   relo->is_typeless, relo->is_weak, relo->name, ref);
+}
+
+/* Expects:
+ * BPF_REG_8 - pointer to instruction
+ */
+static void emit_relo_ksym_typeless(struct bpf_gen *gen,
+				    struct ksym_relo_desc *relo, int insn)
+{
+	struct ksym_desc *kdesc;
+
+	kdesc = get_ksym_desc(gen, relo);
+	if (!kdesc)
+		return;
+	/* try to copy from existing ldimm64 insn */
+	if (kdesc->ref > 1) {
+		move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + offsetof(struct bpf_insn, imm));
+		move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm));
+		goto log;
+	}
+	/* remember insn offset, so we can copy ksym addr later */
+	kdesc->insn = insn;
+	/* skip typeless ksym_desc in fd closing loop in cleanup_relos */
+	kdesc->typeless = true;
+	emit_bpf_kallsyms_lookup_name(gen, relo);
+	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_7, -ENOENT, 1));
+	emit_check_err(gen);
+	/* store lower half of addr into insn[insn_idx].imm */
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_9, offsetof(struct bpf_insn, imm)));
+	/* store upper half of addr into insn[insn_idx + 1].imm */
+	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32));
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_9,
+		      sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)));
+log:
+	emit_ksym_relo_log(gen, relo, kdesc->ref);
+}
+
+static __u32 src_reg_mask(void)
+{
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	return 0x0f; /* src_reg,dst_reg,... */
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	return 0xf0; /* dst_reg,src_reg,... */
+#else
+#error "Unsupported bit endianness, cannot proceed"
+#endif
+}
+
+/* Expects:
+ * BPF_REG_8 - pointer to instruction
+ */
+static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn)
+{
+	struct ksym_desc *kdesc;
+	__u32 reg_mask;
+
+	kdesc = get_ksym_desc(gen, relo);
+	if (!kdesc)
+		return;
+	/* try to copy from existing ldimm64 insn */
+	if (kdesc->ref > 1) {
+		move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + offsetof(struct bpf_insn, imm));
+		move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm));
+		emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_8, offsetof(struct bpf_insn, imm)));
+		/* jump over src_reg adjustment if imm is not 0 */
+		emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 3));
+		goto clear_src_reg;
+	}
+	/* remember insn offset, so we can copy BTF ID and FD later */
+	kdesc->insn = insn;
+	emit_bpf_find_by_name_kind(gen, relo);
+	if (!relo->is_weak)
+		emit_check_err(gen);
+	/* set default values as 0 */
+	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0));
+	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 0));
+	/* skip success case stores if ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 4));
+	/* store btf_id into insn[insn_idx].imm */
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm)));
+	/* store btf_obj_fd into insn[insn_idx + 1].imm */
+	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7,
+			      sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)));
+	emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3));
+clear_src_reg:
+	/* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */
+	reg_mask = src_reg_mask();
+	emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code)));
+	emit(gen, BPF_ALU32_IMM(BPF_AND, BPF_REG_9, reg_mask));
+	emit(gen, BPF_STX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, offsetofend(struct bpf_insn, code)));
+
+	emit_ksym_relo_log(gen, relo, kdesc->ref);
+}
+
+static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns)
+{
+	int insn;
+
+	pr_debug("gen: emit_relo (%d): %s at %d\n", relo->kind, relo->name, relo->insn_idx);
+	insn = insns + sizeof(struct bpf_insn) * relo->insn_idx;
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_8, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, insn));
+	switch (relo->kind) {
+	case BTF_KIND_VAR:
+		if (relo->is_typeless)
+			emit_relo_ksym_typeless(gen, relo, insn);
+		else
+			emit_relo_ksym_btf(gen, relo, insn);
+		break;
+	case BTF_KIND_FUNC:
+		emit_relo_kfunc_btf(gen, relo, insn);
+		break;
+	default:
+		pr_warn("Unknown relocation kind '%d'\n", relo->kind);
+		gen->error = -EDOM;
+		return;
 	}
 }
 
@@ -566,14 +874,23 @@ static void cleanup_relos(struct bpf_gen *gen, int insns)
 {
 	int i, insn;
 
-	for (i = 0; i < gen->relo_cnt; i++) {
-		if (gen->relos[i].kind != BTF_KIND_VAR)
-			continue;
-		/* close fd recorded in insn[insn_idx + 1].imm */
-		insn = insns +
-			sizeof(struct bpf_insn) * (gen->relos[i].insn_idx + 1) +
-			offsetof(struct bpf_insn, imm);
-		emit_sys_close_blob(gen, insn);
+	for (i = 0; i < gen->nr_ksyms; i++) {
+		/* only close fds for typed ksyms and kfuncs */
+		if (gen->ksyms[i].kind == BTF_KIND_VAR && !gen->ksyms[i].typeless) {
+			/* close fd recorded in insn[insn_idx + 1].imm */
+			insn = gen->ksyms[i].insn;
+			insn += sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm);
+			emit_sys_close_blob(gen, insn);
+		} else if (gen->ksyms[i].kind == BTF_KIND_FUNC) {
+			emit_sys_close_blob(gen, blob_fd_array_off(gen, gen->ksyms[i].off));
+			if (gen->ksyms[i].off < MAX_FD_ARRAY_SZ)
+				gen->nr_fd_array--;
+		}
+	}
+	if (gen->nr_ksyms) {
+		free(gen->ksyms);
+		gen->nr_ksyms = 0;
+		gen->ksyms = NULL;
 	}
 	if (gen->relo_cnt) {
 		free(gen->relos);
@@ -632,9 +949,8 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 	/* populate union bpf_attr with a pointer to line_info */
 	emit_rel_store(gen, attr_field(prog_load_attr, line_info), line_info);
 
-	/* populate union bpf_attr fd_array with a pointer to stack where map_fds are saved */
-	emit_rel_store_sp(gen, attr_field(prog_load_attr, fd_array),
-			  stack_off(map_fd[0]));
+	/* populate union bpf_attr fd_array with a pointer to data where map_fds are saved */
+	emit_rel_store(gen, attr_field(prog_load_attr, fd_array), gen->fd_array);
 
 	/* populate union bpf_attr with user provided log details */
 	move_ctx2blob(gen, attr_field(prog_load_attr, log_level), 4,
@@ -701,8 +1017,8 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user));
 
 	map_update_attr = add_data(gen, &attr, attr_size);
-	move_stack2blob(gen, attr_field(map_update_attr, map_fd), 4,
-			stack_off(map_fd[map_idx]));
+	move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4,
+		       blob_fd_array_off(gen, map_idx));
 	emit_rel_store(gen, attr_field(map_update_attr, key), key);
 	emit_rel_store(gen, attr_field(map_update_attr, value), value);
 	/* emit MAP_UPDATE_ELEM command */
@@ -720,8 +1036,8 @@ void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx)
 	memset(&attr, 0, attr_size);
 	pr_debug("gen: map_freeze: idx %d\n", map_idx);
 	map_freeze_attr = add_data(gen, &attr, attr_size);
-	move_stack2blob(gen, attr_field(map_freeze_attr, map_fd), 4,
-			stack_off(map_fd[map_idx]));
+	move_blob2blob(gen, attr_field(map_freeze_attr, map_fd), 4,
+		       blob_fd_array_off(gen, map_idx));
 	/* emit MAP_FREEZE command */
 	emit_sys_bpf(gen, BPF_MAP_FREEZE, map_freeze_attr, attr_size);
 	debug_ret(gen, "map_freeze");
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e4f83c304ec9..a1bea1953df6 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -195,6 +195,8 @@ enum kern_feature_id {
 	FEAT_BTF_FLOAT,
 	/* BPF perf link support */
 	FEAT_PERF_LINK,
+	/* BTF_KIND_DECL_TAG support */
+	FEAT_BTF_DECL_TAG,
 	__FEAT_CNT,
 };
 
@@ -218,18 +220,40 @@ struct reloc_desc {
 
 struct bpf_sec_def;
 
-typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec,
-					struct bpf_program *prog);
+typedef int (*init_fn_t)(struct bpf_program *prog, long cookie);
+typedef int (*preload_fn_t)(struct bpf_program *prog, struct bpf_prog_load_params *attr, long cookie);
+typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long cookie);
+
+/* stored as sec_def->cookie for all libbpf-supported SEC()s */
+enum sec_def_flags {
+	SEC_NONE = 0,
+	/* expected_attach_type is optional, if kernel doesn't support that */
+	SEC_EXP_ATTACH_OPT = 1,
+	/* legacy, only used by libbpf_get_type_names() and
+	 * libbpf_attach_type_by_name(), not used by libbpf itself at all.
+	 * This used to be associated with cgroup (and few other) BPF programs
+	 * that were attachable through BPF_PROG_ATTACH command. Pretty
+	 * meaningless nowadays, though.
+	 */
+	SEC_ATTACHABLE = 2,
+	SEC_ATTACHABLE_OPT = SEC_ATTACHABLE | SEC_EXP_ATTACH_OPT,
+	/* attachment target is specified through BTF ID in either kernel or
+	 * other BPF program's BTF object */
+	SEC_ATTACH_BTF = 4,
+	/* BPF program type allows sleeping/blocking in kernel */
+	SEC_SLEEPABLE = 8,
+	/* allow non-strict prefix matching */
+	SEC_SLOPPY_PFX = 16,
+};
 
 struct bpf_sec_def {
 	const char *sec;
-	size_t len;
 	enum bpf_prog_type prog_type;
 	enum bpf_attach_type expected_attach_type;
-	bool is_exp_attach_type_optional;
-	bool is_attachable;
-	bool is_attach_btf;
-	bool is_sleepable;
+	long cookie;
+
+	init_fn_t init_fn;
+	preload_fn_t preload_fn;
 	attach_fn_t attach_fn;
 };
 
@@ -261,7 +285,7 @@ struct bpf_program {
 	size_t sub_insn_off;
 
 	char *name;
-	/* sec_name with / replaced by _; makes recursive pinning
+	/* name with / replaced by _; makes recursive pinning
 	 * in bpf_object__pin_programs easier
 	 */
 	char *pin_name;
@@ -346,15 +370,14 @@ enum libbpf_map_type {
 	LIBBPF_MAP_KCONFIG,
 };
 
-static const char * const libbpf_type_to_btf_name[] = {
-	[LIBBPF_MAP_DATA]	= DATA_SEC,
-	[LIBBPF_MAP_BSS]	= BSS_SEC,
-	[LIBBPF_MAP_RODATA]	= RODATA_SEC,
-	[LIBBPF_MAP_KCONFIG]	= KCONFIG_SEC,
-};
-
 struct bpf_map {
 	char *name;
+	/* real_name is defined for special internal maps (.rodata*,
+	 * .data*, .bss, .kconfig) and preserves their original ELF section
+	 * name. This is important to be be able to find corresponding BTF
+	 * DATASEC information.
+	 */
+	char *real_name;
 	int fd;
 	int sec_idx;
 	size_t sec_offset;
@@ -377,6 +400,7 @@ struct bpf_map {
 	char *pin_path;
 	bool pinned;
 	bool reused;
+	__u64 map_extra;
 };
 
 enum extern_type {
@@ -419,6 +443,11 @@ struct extern_desc {
 
 			/* local btf_id of the ksym extern's type. */
 			__u32 type_id;
+			/* BTF fd index to be patched in for insn->off, this is
+			 * 0 for vmlinux BTF, index in obj->fd_array for module
+			 * BTF
+			 */
+			__s16 btf_fd_idx;
 		} ksym;
 	};
 };
@@ -430,6 +459,41 @@ struct module_btf {
 	char *name;
 	__u32 id;
 	int fd;
+	int fd_array_idx;
+};
+
+enum sec_type {
+	SEC_UNUSED = 0,
+	SEC_RELO,
+	SEC_BSS,
+	SEC_DATA,
+	SEC_RODATA,
+};
+
+struct elf_sec_desc {
+	enum sec_type sec_type;
+	Elf64_Shdr *shdr;
+	Elf_Data *data;
+};
+
+struct elf_state {
+	int fd;
+	const void *obj_buf;
+	size_t obj_buf_sz;
+	Elf *elf;
+	Elf64_Ehdr *ehdr;
+	Elf_Data *symbols;
+	Elf_Data *st_ops_data;
+	size_t shstrndx; /* section index for section name strings */
+	size_t strtabidx;
+	struct elf_sec_desc *secs;
+	int sec_cnt;
+	int maps_shndx;
+	int btf_maps_shndx;
+	__u32 btf_maps_sec_btf_id;
+	int text_shndx;
+	int symbols_shndx;
+	int st_ops_shndx;
 };
 
 struct bpf_object {
@@ -447,47 +511,17 @@ struct bpf_object {
 	struct extern_desc *externs;
 	int nr_extern;
 	int kconfig_map_idx;
-	int rodata_map_idx;
 
 	bool loaded;
 	bool has_subcalls;
+	bool has_rodata;
 
 	struct bpf_gen *gen_loader;
 
+	/* Information when doing ELF related work. Only valid if efile.elf is not NULL */
+	struct elf_state efile;
 	/*
-	 * Information when doing elf related work. Only valid if fd
-	 * is valid.
-	 */
-	struct {
-		int fd;
-		const void *obj_buf;
-		size_t obj_buf_sz;
-		Elf *elf;
-		GElf_Ehdr ehdr;
-		Elf_Data *symbols;
-		Elf_Data *data;
-		Elf_Data *rodata;
-		Elf_Data *bss;
-		Elf_Data *st_ops_data;
-		size_t shstrndx; /* section index for section name strings */
-		size_t strtabidx;
-		struct {
-			GElf_Shdr shdr;
-			Elf_Data *data;
-		} *reloc_sects;
-		int nr_reloc_sects;
-		int maps_shndx;
-		int btf_maps_shndx;
-		__u32 btf_maps_sec_btf_id;
-		int text_shndx;
-		int symbols_shndx;
-		int data_shndx;
-		int rodata_shndx;
-		int bss_shndx;
-		int st_ops_shndx;
-	} efile;
-	/*
-	 * All loaded bpf_object is linked in a list, which is
+	 * All loaded bpf_object are linked in a list, which is
 	 * hidden to caller. bpf_objects__<func> handlers deal with
 	 * all objects.
 	 */
@@ -515,17 +549,22 @@ struct bpf_object {
 	void *priv;
 	bpf_object_clear_priv_t clear_priv;
 
+	int *fd_array;
+	size_t fd_array_cap;
+	size_t fd_array_cnt;
+
 	char path[];
 };
-#define obj_elf_valid(o)	((o)->efile.elf)
 
 static const char *elf_sym_str(const struct bpf_object *obj, size_t off);
 static const char *elf_sec_str(const struct bpf_object *obj, size_t off);
 static Elf_Scn *elf_sec_by_idx(const struct bpf_object *obj, size_t idx);
 static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name);
-static int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr);
+static Elf64_Shdr *elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn);
 static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn);
 static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn);
+static Elf64_Sym *elf_sym_by_idx(const struct bpf_object *obj, size_t idx);
+static Elf64_Rel *elf_rel_by_idx(Elf_Data *data, size_t idx);
 
 void bpf_program__unload(struct bpf_program *prog)
 {
@@ -580,7 +619,16 @@ static char *__bpf_program__pin_name(struct bpf_program *prog)
 {
 	char *name, *p;
 
-	name = p = strdup(prog->sec_name);
+	if (libbpf_mode & LIBBPF_STRICT_SEC_NAME)
+		name = strdup(prog->name);
+	else
+		name = strdup(prog->sec_name);
+
+	if (!name)
+		return NULL;
+
+	p = name;
+
 	while ((p = strchr(p, '/')))
 		*p = '_';
 
@@ -667,25 +715,25 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 	size_t sec_sz = sec_data->d_size, sec_off, prog_sz, nr_syms;
 	int nr_progs, err, i;
 	const char *name;
-	GElf_Sym sym;
+	Elf64_Sym *sym;
 
 	progs = obj->programs;
 	nr_progs = obj->nr_programs;
-	nr_syms = symbols->d_size / sizeof(GElf_Sym);
+	nr_syms = symbols->d_size / sizeof(Elf64_Sym);
 	sec_off = 0;
 
 	for (i = 0; i < nr_syms; i++) {
-		if (!gelf_getsym(symbols, i, &sym))
-			continue;
-		if (sym.st_shndx != sec_idx)
+		sym = elf_sym_by_idx(obj, i);
+
+		if (sym->st_shndx != sec_idx)
 			continue;
-		if (GELF_ST_TYPE(sym.st_info) != STT_FUNC)
+		if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC)
 			continue;
 
-		prog_sz = sym.st_size;
-		sec_off = sym.st_value;
+		prog_sz = sym->st_size;
+		sec_off = sym->st_value;
 
-		name = elf_sym_str(obj, sym.st_name);
+		name = elf_sym_str(obj, sym->st_name);
 		if (!name) {
 			pr_warn("sec '%s': failed to get symbol name for offset %zu\n",
 				sec_name, sec_off);
@@ -698,7 +746,7 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		if (sec_idx != obj->efile.text_shndx && GELF_ST_BIND(sym.st_info) == STB_LOCAL) {
+		if (sec_idx != obj->efile.text_shndx && ELF64_ST_BIND(sym->st_info) == STB_LOCAL) {
 			pr_warn("sec '%s': program '%s' is static and not supported\n", sec_name, name);
 			return -ENOTSUP;
 		}
@@ -731,9 +779,9 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 		 * as static to enable more permissive BPF verification mode
 		 * with more outside context available to BPF verifier
 		 */
-		if (GELF_ST_BIND(sym.st_info) != STB_LOCAL
-		    && (GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN
-			|| GELF_ST_VISIBILITY(sym.st_other) == STV_INTERNAL))
+		if (ELF64_ST_BIND(sym->st_info) != STB_LOCAL
+		    && (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN
+			|| ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL))
 			prog->mark_btf_static = true;
 
 		nr_progs++;
@@ -1101,6 +1149,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 					  size_t obj_buf_sz,
 					  const char *obj_name)
 {
+	bool strict = (libbpf_mode & LIBBPF_STRICT_NO_OBJECT_LIST);
 	struct bpf_object *obj;
 	char *end;
 
@@ -1134,24 +1183,21 @@ static struct bpf_object *bpf_object__new(const char *path,
 	obj->efile.obj_buf_sz = obj_buf_sz;
 	obj->efile.maps_shndx = -1;
 	obj->efile.btf_maps_shndx = -1;
-	obj->efile.data_shndx = -1;
-	obj->efile.rodata_shndx = -1;
-	obj->efile.bss_shndx = -1;
 	obj->efile.st_ops_shndx = -1;
 	obj->kconfig_map_idx = -1;
-	obj->rodata_map_idx = -1;
 
 	obj->kern_version = get_kernel_version();
 	obj->loaded = false;
 
 	INIT_LIST_HEAD(&obj->list);
-	list_add(&obj->list, &bpf_objects_list);
+	if (!strict)
+		list_add(&obj->list, &bpf_objects_list);
 	return obj;
 }
 
 static void bpf_object__elf_finish(struct bpf_object *obj)
 {
-	if (!obj_elf_valid(obj))
+	if (!obj->efile.elf)
 		return;
 
 	if (obj->efile.elf) {
@@ -1159,13 +1205,10 @@ static void bpf_object__elf_finish(struct bpf_object *obj)
 		obj->efile.elf = NULL;
 	}
 	obj->efile.symbols = NULL;
-	obj->efile.data = NULL;
-	obj->efile.rodata = NULL;
-	obj->efile.bss = NULL;
 	obj->efile.st_ops_data = NULL;
 
-	zfree(&obj->efile.reloc_sects);
-	obj->efile.nr_reloc_sects = 0;
+	zfree(&obj->efile.secs);
+	obj->efile.sec_cnt = 0;
 	zclose(obj->efile.fd);
 	obj->efile.obj_buf = NULL;
 	obj->efile.obj_buf_sz = 0;
@@ -1173,10 +1216,11 @@ static void bpf_object__elf_finish(struct bpf_object *obj)
 
 static int bpf_object__elf_init(struct bpf_object *obj)
 {
+	Elf64_Ehdr *ehdr;
 	int err = 0;
-	GElf_Ehdr *ep;
+	Elf *elf;
 
-	if (obj_elf_valid(obj)) {
+	if (obj->efile.elf) {
 		pr_warn("elf: init internal error\n");
 		return -LIBBPF_ERRNO__LIBELF;
 	}
@@ -1186,10 +1230,9 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 		 * obj_buf should have been validated by
 		 * bpf_object__open_buffer().
 		 */
-		obj->efile.elf = elf_memory((char *)obj->efile.obj_buf,
-					    obj->efile.obj_buf_sz);
+		elf = elf_memory((char *)obj->efile.obj_buf, obj->efile.obj_buf_sz);
 	} else {
-		obj->efile.fd = open(obj->path, O_RDONLY);
+		obj->efile.fd = open(obj->path, O_RDONLY | O_CLOEXEC);
 		if (obj->efile.fd < 0) {
 			char errmsg[STRERR_BUFSIZE], *cp;
 
@@ -1199,23 +1242,37 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 			return err;
 		}
 
-		obj->efile.elf = elf_begin(obj->efile.fd, ELF_C_READ_MMAP, NULL);
+		elf = elf_begin(obj->efile.fd, ELF_C_READ_MMAP, NULL);
 	}
 
-	if (!obj->efile.elf) {
+	if (!elf) {
 		pr_warn("elf: failed to open %s as ELF file: %s\n", obj->path, elf_errmsg(-1));
 		err = -LIBBPF_ERRNO__LIBELF;
 		goto errout;
 	}
 
-	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
+	obj->efile.elf = elf;
+
+	if (elf_kind(elf) != ELF_K_ELF) {
+		err = -LIBBPF_ERRNO__FORMAT;
+		pr_warn("elf: '%s' is not a proper ELF object\n", obj->path);
+		goto errout;
+	}
+
+	if (gelf_getclass(elf) != ELFCLASS64) {
+		err = -LIBBPF_ERRNO__FORMAT;
+		pr_warn("elf: '%s' is not a 64-bit ELF object\n", obj->path);
+		goto errout;
+	}
+
+	obj->efile.ehdr = ehdr = elf64_getehdr(elf);
+	if (!obj->efile.ehdr) {
 		pr_warn("elf: failed to get ELF header from %s: %s\n", obj->path, elf_errmsg(-1));
 		err = -LIBBPF_ERRNO__FORMAT;
 		goto errout;
 	}
-	ep = &obj->efile.ehdr;
 
-	if (elf_getshdrstrndx(obj->efile.elf, &obj->efile.shstrndx)) {
+	if (elf_getshdrstrndx(elf, &obj->efile.shstrndx)) {
 		pr_warn("elf: failed to get section names section index for %s: %s\n",
 			obj->path, elf_errmsg(-1));
 		err = -LIBBPF_ERRNO__FORMAT;
@@ -1223,7 +1280,7 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 	}
 
 	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
-	if (!elf_rawdata(elf_getscn(obj->efile.elf, obj->efile.shstrndx), NULL)) {
+	if (!elf_rawdata(elf_getscn(elf, obj->efile.shstrndx), NULL)) {
 		pr_warn("elf: failed to get section names strings from %s: %s\n",
 			obj->path, elf_errmsg(-1));
 		err = -LIBBPF_ERRNO__FORMAT;
@@ -1231,8 +1288,7 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 	}
 
 	/* Old LLVM set e_machine to EM_NONE */
-	if (ep->e_type != ET_REL ||
-	    (ep->e_machine && ep->e_machine != EM_BPF)) {
+	if (ehdr->e_type != ET_REL || (ehdr->e_machine && ehdr->e_machine != EM_BPF)) {
 		pr_warn("elf: %s is not a valid eBPF object file\n", obj->path);
 		err = -LIBBPF_ERRNO__FORMAT;
 		goto errout;
@@ -1246,11 +1302,11 @@ errout:
 
 static int bpf_object__check_endianness(struct bpf_object *obj)
 {
-#if __BYTE_ORDER == __LITTLE_ENDIAN
-	if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB)
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
 		return 0;
-#elif __BYTE_ORDER == __BIG_ENDIAN
-	if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB)
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+	if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
 		return 0;
 #else
 # error "Unrecognized __BYTE_ORDER__"
@@ -1290,41 +1346,27 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
 	return false;
 }
 
-int bpf_object__section_size(const struct bpf_object *obj, const char *name,
-			     __u32 *size)
+static int find_elf_sec_sz(const struct bpf_object *obj, const char *name, __u32 *size)
 {
 	int ret = -ENOENT;
+	Elf_Data *data;
+	Elf_Scn *scn;
 
 	*size = 0;
-	if (!name) {
+	if (!name)
 		return -EINVAL;
-	} else if (!strcmp(name, DATA_SEC)) {
-		if (obj->efile.data)
-			*size = obj->efile.data->d_size;
-	} else if (!strcmp(name, BSS_SEC)) {
-		if (obj->efile.bss)
-			*size = obj->efile.bss->d_size;
-	} else if (!strcmp(name, RODATA_SEC)) {
-		if (obj->efile.rodata)
-			*size = obj->efile.rodata->d_size;
-	} else if (!strcmp(name, STRUCT_OPS_SEC)) {
-		if (obj->efile.st_ops_data)
-			*size = obj->efile.st_ops_data->d_size;
-	} else {
-		Elf_Scn *scn = elf_sec_by_name(obj, name);
-		Elf_Data *data = elf_sec_data(obj, scn);
 
-		if (data) {
-			ret = 0; /* found it */
-			*size = data->d_size;
-		}
+	scn = elf_sec_by_name(obj, name);
+	data = elf_sec_data(obj, scn);
+	if (data) {
+		ret = 0; /* found it */
+		*size = data->d_size;
 	}
 
 	return *size ? 0 : ret;
 }
 
-int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
-				__u32 *off)
+static int find_elf_var_offset(const struct bpf_object *obj, const char *name, __u32 *off)
 {
 	Elf_Data *symbols = obj->efile.symbols;
 	const char *sname;
@@ -1333,23 +1375,20 @@ int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
 	if (!name || !off)
 		return -EINVAL;
 
-	for (si = 0; si < symbols->d_size / sizeof(GElf_Sym); si++) {
-		GElf_Sym sym;
+	for (si = 0; si < symbols->d_size / sizeof(Elf64_Sym); si++) {
+		Elf64_Sym *sym = elf_sym_by_idx(obj, si);
 
-		if (!gelf_getsym(symbols, si, &sym))
-			continue;
-		if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL ||
-		    GELF_ST_TYPE(sym.st_info) != STT_OBJECT)
+		if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL ||
+		    ELF64_ST_TYPE(sym->st_info) != STT_OBJECT)
 			continue;
 
-		sname = elf_sym_str(obj, sym.st_name);
+		sname = elf_sym_str(obj, sym->st_name);
 		if (!sname) {
-			pr_warn("failed to get sym name string for var %s\n",
-				name);
+			pr_warn("failed to get sym name string for var %s\n", name);
 			return -EIO;
 		}
 		if (strcmp(name, sname) == 0) {
-			*off = sym.st_value;
+			*off = sym->st_value;
 			return 0;
 		}
 	}
@@ -1401,17 +1440,55 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map)
 	return map_sz;
 }
 
-static char *internal_map_name(struct bpf_object *obj,
-			       enum libbpf_map_type type)
+static char *internal_map_name(struct bpf_object *obj, const char *real_name)
 {
 	char map_name[BPF_OBJ_NAME_LEN], *p;
-	const char *sfx = libbpf_type_to_btf_name[type];
-	int sfx_len = max((size_t)7, strlen(sfx));
-	int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1,
-			  strlen(obj->name));
+	int pfx_len, sfx_len = max((size_t)7, strlen(real_name));
+
+	/* This is one of the more confusing parts of libbpf for various
+	 * reasons, some of which are historical. The original idea for naming
+	 * internal names was to include as much of BPF object name prefix as
+	 * possible, so that it can be distinguished from similar internal
+	 * maps of a different BPF object.
+	 * As an example, let's say we have bpf_object named 'my_object_name'
+	 * and internal map corresponding to '.rodata' ELF section. The final
+	 * map name advertised to user and to the kernel will be
+	 * 'my_objec.rodata', taking first 8 characters of object name and
+	 * entire 7 characters of '.rodata'.
+	 * Somewhat confusingly, if internal map ELF section name is shorter
+	 * than 7 characters, e.g., '.bss', we still reserve 7 characters
+	 * for the suffix, even though we only have 4 actual characters, and
+	 * resulting map will be called 'my_objec.bss', not even using all 15
+	 * characters allowed by the kernel. Oh well, at least the truncated
+	 * object name is somewhat consistent in this case. But if the map
+	 * name is '.kconfig', we'll still have entirety of '.kconfig' added
+	 * (8 chars) and thus will be left with only first 7 characters of the
+	 * object name ('my_obje'). Happy guessing, user, that the final map
+	 * name will be "my_obje.kconfig".
+	 * Now, with libbpf starting to support arbitrarily named .rodata.*
+	 * and .data.* data sections, it's possible that ELF section name is
+	 * longer than allowed 15 chars, so we now need to be careful to take
+	 * only up to 15 first characters of ELF name, taking no BPF object
+	 * name characters at all. So '.rodata.abracadabra' will result in
+	 * '.rodata.abracad' kernel and user-visible name.
+	 * We need to keep this convoluted logic intact for .data, .bss and
+	 * .rodata maps, but for new custom .data.custom and .rodata.custom
+	 * maps we use their ELF names as is, not prepending bpf_object name
+	 * in front. We still need to truncate them to 15 characters for the
+	 * kernel. Full name can be recovered for such maps by using DATASEC
+	 * BTF type associated with such map's value type, though.
+	 */
+	if (sfx_len >= BPF_OBJ_NAME_LEN)
+		sfx_len = BPF_OBJ_NAME_LEN - 1;
+
+	/* if there are two or more dots in map name, it's a custom dot map */
+	if (strchr(real_name + 1, '.') != NULL)
+		pfx_len = 0;
+	else
+		pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1, strlen(obj->name));
 
 	snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name,
-		 sfx_len, libbpf_type_to_btf_name[type]);
+		 sfx_len, real_name);
 
 	/* sanitise map name to characters allowed by kernel */
 	for (p = map_name; *p && p < map_name + sizeof(map_name); p++)
@@ -1423,7 +1500,7 @@ static char *internal_map_name(struct bpf_object *obj,
 
 static int
 bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
-			      int sec_idx, void *data, size_t data_sz)
+			      const char *real_name, int sec_idx, void *data, size_t data_sz)
 {
 	struct bpf_map_def *def;
 	struct bpf_map *map;
@@ -1436,9 +1513,11 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 	map->libbpf_type = type;
 	map->sec_idx = sec_idx;
 	map->sec_offset = 0;
-	map->name = internal_map_name(obj, type);
-	if (!map->name) {
-		pr_warn("failed to alloc map name\n");
+	map->real_name = strdup(real_name);
+	map->name = internal_map_name(obj, real_name);
+	if (!map->real_name || !map->name) {
+		zfree(&map->real_name);
+		zfree(&map->name);
 		return -ENOMEM;
 	}
 
@@ -1461,6 +1540,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 		map->mmaped = NULL;
 		pr_warn("failed to alloc map '%s' content buffer: %d\n",
 			map->name, err);
+		zfree(&map->real_name);
 		zfree(&map->name);
 		return err;
 	}
@@ -1474,34 +1554,43 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 
 static int bpf_object__init_global_data_maps(struct bpf_object *obj)
 {
-	int err;
+	struct elf_sec_desc *sec_desc;
+	const char *sec_name;
+	int err = 0, sec_idx;
 
 	/*
 	 * Populate obj->maps with libbpf internal maps.
 	 */
-	if (obj->efile.data_shndx >= 0) {
-		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA,
-						    obj->efile.data_shndx,
-						    obj->efile.data->d_buf,
-						    obj->efile.data->d_size);
-		if (err)
-			return err;
-	}
-	if (obj->efile.rodata_shndx >= 0) {
-		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA,
-						    obj->efile.rodata_shndx,
-						    obj->efile.rodata->d_buf,
-						    obj->efile.rodata->d_size);
-		if (err)
-			return err;
-
-		obj->rodata_map_idx = obj->nr_maps - 1;
-	}
-	if (obj->efile.bss_shndx >= 0) {
-		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS,
-						    obj->efile.bss_shndx,
-						    NULL,
-						    obj->efile.bss->d_size);
+	for (sec_idx = 1; sec_idx < obj->efile.sec_cnt; sec_idx++) {
+		sec_desc = &obj->efile.secs[sec_idx];
+
+		switch (sec_desc->sec_type) {
+		case SEC_DATA:
+			sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx));
+			err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA,
+							    sec_name, sec_idx,
+							    sec_desc->data->d_buf,
+							    sec_desc->data->d_size);
+			break;
+		case SEC_RODATA:
+			obj->has_rodata = true;
+			sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx));
+			err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA,
+							    sec_name, sec_idx,
+							    sec_desc->data->d_buf,
+							    sec_desc->data->d_size);
+			break;
+		case SEC_BSS:
+			sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx));
+			err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS,
+							    sec_name, sec_idx,
+							    NULL,
+							    sec_desc->data->d_size);
+			break;
+		default:
+			/* skip */
+			break;
+		}
 		if (err)
 			return err;
 	}
@@ -1664,7 +1753,7 @@ static int bpf_object__process_kconfig_line(struct bpf_object *obj,
 	void *ext_val;
 	__u64 num;
 
-	if (strncmp(buf, "CONFIG_", 7))
+	if (!str_has_pfx(buf, "CONFIG_"))
 		return 0;
 
 	sep = strchr(buf, '=');
@@ -1798,7 +1887,7 @@ static int bpf_object__init_kconfig_map(struct bpf_object *obj)
 
 	map_sz = last_ext->kcfg.data_off + last_ext->kcfg.sz;
 	err = bpf_object__init_internal_map(obj, LIBBPF_MAP_KCONFIG,
-					    obj->efile.symbols_shndx,
+					    ".kconfig", obj->efile.symbols_shndx,
 					    NULL, map_sz);
 	if (err)
 		return err;
@@ -1836,13 +1925,13 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 	 *
 	 * TODO: Detect array of map and report error.
 	 */
-	nr_syms = symbols->d_size / sizeof(GElf_Sym);
+	nr_syms = symbols->d_size / sizeof(Elf64_Sym);
 	for (i = 0; i < nr_syms; i++) {
-		GElf_Sym sym;
+		Elf64_Sym *sym = elf_sym_by_idx(obj, i);
 
-		if (!gelf_getsym(symbols, i, &sym))
+		if (sym->st_shndx != obj->efile.maps_shndx)
 			continue;
-		if (sym.st_shndx != obj->efile.maps_shndx)
+		if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION)
 			continue;
 		nr_maps++;
 	}
@@ -1859,39 +1948,38 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 
 	/* Fill obj->maps using data in "maps" section.  */
 	for (i = 0; i < nr_syms; i++) {
-		GElf_Sym sym;
+		Elf64_Sym *sym = elf_sym_by_idx(obj, i);
 		const char *map_name;
 		struct bpf_map_def *def;
 		struct bpf_map *map;
 
-		if (!gelf_getsym(symbols, i, &sym))
+		if (sym->st_shndx != obj->efile.maps_shndx)
 			continue;
-		if (sym.st_shndx != obj->efile.maps_shndx)
+		if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION)
 			continue;
 
 		map = bpf_object__add_map(obj);
 		if (IS_ERR(map))
 			return PTR_ERR(map);
 
-		map_name = elf_sym_str(obj, sym.st_name);
+		map_name = elf_sym_str(obj, sym->st_name);
 		if (!map_name) {
 			pr_warn("failed to get map #%d name sym string for obj %s\n",
 				i, obj->path);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		if (GELF_ST_TYPE(sym.st_info) == STT_SECTION
-		    || GELF_ST_BIND(sym.st_info) == STB_LOCAL) {
+		if (ELF64_ST_BIND(sym->st_info) == STB_LOCAL) {
 			pr_warn("map '%s' (legacy): static maps are not supported\n", map_name);
 			return -ENOTSUP;
 		}
 
 		map->libbpf_type = LIBBPF_MAP_UNSPEC;
-		map->sec_idx = sym.st_shndx;
-		map->sec_offset = sym.st_value;
+		map->sec_idx = sym->st_shndx;
+		map->sec_offset = sym->st_value;
 		pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n",
 			 map_name, map->sec_idx, map->sec_offset);
-		if (sym.st_value + map_def_sz > data->d_size) {
+		if (sym->st_value + map_def_sz > data->d_size) {
 			pr_warn("corrupted maps section in %s: last map \"%s\" too small\n",
 				obj->path, map_name);
 			return -EINVAL;
@@ -1899,11 +1987,11 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 
 		map->name = strdup(map_name);
 		if (!map->name) {
-			pr_warn("failed to alloc map name\n");
+			pr_warn("map '%s': failed to alloc map name\n", map_name);
 			return -ENOMEM;
 		}
 		pr_debug("map %d is \"%s\"\n", i, map->name);
-		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
+		def = (struct bpf_map_def *)(data->d_buf + sym->st_value);
 		/*
 		 * If the definition of the map in the object file fits in
 		 * bpf_map_def, copy it.  Any extra fields in our version
@@ -1987,6 +2075,7 @@ static const char *__btf_kind_str(__u16 kind)
 	case BTF_KIND_VAR: return "var";
 	case BTF_KIND_DATASEC: return "datasec";
 	case BTF_KIND_FLOAT: return "float";
+	case BTF_KIND_DECL_TAG: return "decl_tag";
 	default: return "unknown";
 	}
 }
@@ -2236,6 +2325,13 @@ int parse_btf_map_def(const char *map_name, struct btf *btf,
 			}
 			map_def->pinning = val;
 			map_def->parts |= MAP_DEF_PINNING;
+		} else if (strcmp(name, "map_extra") == 0) {
+			__u32 map_extra;
+
+			if (!get_map_field_int(map_name, btf, m, &map_extra))
+				return -EINVAL;
+			map_def->map_extra = map_extra;
+			map_def->parts |= MAP_DEF_MAP_EXTRA;
 		} else {
 			if (strict) {
 				pr_warn("map '%s': unknown field '%s'.\n", map_name, name);
@@ -2260,6 +2356,7 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def
 	map->def.value_size = def->value_size;
 	map->def.max_entries = def->max_entries;
 	map->def.map_flags = def->map_flags;
+	map->map_extra = def->map_extra;
 
 	map->numa_node = def->numa_node;
 	map->btf_key_type_id = def->key_type_id;
@@ -2283,7 +2380,10 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def
 	if (def->parts & MAP_DEF_MAX_ENTRIES)
 		pr_debug("map '%s': found max_entries = %u.\n", map->name, def->max_entries);
 	if (def->parts & MAP_DEF_MAP_FLAGS)
-		pr_debug("map '%s': found map_flags = %u.\n", map->name, def->map_flags);
+		pr_debug("map '%s': found map_flags = 0x%x.\n", map->name, def->map_flags);
+	if (def->parts & MAP_DEF_MAP_EXTRA)
+		pr_debug("map '%s': found map_extra = 0x%llx.\n", map->name,
+			 (unsigned long long)def->map_extra);
 	if (def->parts & MAP_DEF_PINNING)
 		pr_debug("map '%s': found pinning = %u.\n", map->name, def->pinning);
 	if (def->parts & MAP_DEF_NUMA_NODE)
@@ -2420,8 +2520,8 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict,
 		return -EINVAL;
 	}
 
-	nr_types = btf__get_nr_types(obj->btf);
-	for (i = 1; i <= nr_types; i++) {
+	nr_types = btf__type_cnt(obj->btf);
+	for (i = 1; i < nr_types; i++) {
 		t = btf__type_by_id(obj->btf, i);
 		if (!btf_is_datasec(t))
 			continue;
@@ -2472,12 +2572,13 @@ static int bpf_object__init_maps(struct bpf_object *obj,
 
 static bool section_have_execinstr(struct bpf_object *obj, int idx)
 {
-	GElf_Shdr sh;
+	Elf64_Shdr *sh;
 
-	if (elf_sec_hdr(obj, elf_sec_by_idx(obj, idx), &sh))
+	sh = elf_sec_hdr(obj, elf_sec_by_idx(obj, idx));
+	if (!sh)
 		return false;
 
-	return sh.sh_flags & SHF_EXECINSTR;
+	return sh->sh_flags & SHF_EXECINSTR;
 }
 
 static bool btf_needs_sanitization(struct bpf_object *obj)
@@ -2486,8 +2587,9 @@ static bool btf_needs_sanitization(struct bpf_object *obj)
 	bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC);
 	bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT);
 	bool has_func = kernel_supports(obj, FEAT_BTF_FUNC);
+	bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG);
 
-	return !has_func || !has_datasec || !has_func_global || !has_float;
+	return !has_func || !has_datasec || !has_func_global || !has_float || !has_decl_tag;
 }
 
 static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
@@ -2496,14 +2598,15 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
 	bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC);
 	bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT);
 	bool has_func = kernel_supports(obj, FEAT_BTF_FUNC);
+	bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG);
 	struct btf_type *t;
 	int i, j, vlen;
 
-	for (i = 1; i <= btf__get_nr_types(btf); i++) {
+	for (i = 1; i < btf__type_cnt(btf); i++) {
 		t = (struct btf_type *)btf__type_by_id(btf, i);
 
-		if (!has_datasec && btf_is_var(t)) {
-			/* replace VAR with INT */
+		if ((!has_datasec && btf_is_var(t)) || (!has_decl_tag && btf_is_decl_tag(t))) {
+			/* replace VAR/DECL_TAG with INT */
 			t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
 			/*
 			 * using size = 1 is the safest choice, 4 will be too
@@ -2610,6 +2713,104 @@ out:
 	return 0;
 }
 
+static int compare_vsi_off(const void *_a, const void *_b)
+{
+	const struct btf_var_secinfo *a = _a;
+	const struct btf_var_secinfo *b = _b;
+
+	return a->offset - b->offset;
+}
+
+static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
+			     struct btf_type *t)
+{
+	__u32 size = 0, off = 0, i, vars = btf_vlen(t);
+	const char *name = btf__name_by_offset(btf, t->name_off);
+	const struct btf_type *t_var;
+	struct btf_var_secinfo *vsi;
+	const struct btf_var *var;
+	int ret;
+
+	if (!name) {
+		pr_debug("No name found in string section for DATASEC kind.\n");
+		return -ENOENT;
+	}
+
+	/* .extern datasec size and var offsets were set correctly during
+	 * extern collection step, so just skip straight to sorting variables
+	 */
+	if (t->size)
+		goto sort_vars;
+
+	ret = find_elf_sec_sz(obj, name, &size);
+	if (ret || !size || (t->size && t->size != size)) {
+		pr_debug("Invalid size for section %s: %u bytes\n", name, size);
+		return -ENOENT;
+	}
+
+	t->size = size;
+
+	for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) {
+		t_var = btf__type_by_id(btf, vsi->type);
+		var = btf_var(t_var);
+
+		if (!btf_is_var(t_var)) {
+			pr_debug("Non-VAR type seen in section %s\n", name);
+			return -EINVAL;
+		}
+
+		if (var->linkage == BTF_VAR_STATIC)
+			continue;
+
+		name = btf__name_by_offset(btf, t_var->name_off);
+		if (!name) {
+			pr_debug("No name found in string section for VAR kind\n");
+			return -ENOENT;
+		}
+
+		ret = find_elf_var_offset(obj, name, &off);
+		if (ret) {
+			pr_debug("No offset found in symbol table for VAR %s\n",
+				 name);
+			return -ENOENT;
+		}
+
+		vsi->offset = off;
+	}
+
+sort_vars:
+	qsort(btf_var_secinfos(t), vars, sizeof(*vsi), compare_vsi_off);
+	return 0;
+}
+
+static int btf_finalize_data(struct bpf_object *obj, struct btf *btf)
+{
+	int err = 0;
+	__u32 i, n = btf__type_cnt(btf);
+
+	for (i = 1; i < n; i++) {
+		struct btf_type *t = btf_type_by_id(btf, i);
+
+		/* Loader needs to fix up some of the things compiler
+		 * couldn't get its hands on while emitting BTF. This
+		 * is section size and global variable offset. We use
+		 * the info from the ELF itself for this purpose.
+		 */
+		if (btf_is_datasec(t)) {
+			err = btf_fixup_datasec(obj, btf, t);
+			if (err)
+				break;
+		}
+	}
+
+	return libbpf_err(err);
+}
+
+int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
+{
+	return btf_finalize_data(obj, btf);
+}
+
 static int bpf_object__finalize_btf(struct bpf_object *obj)
 {
 	int err;
@@ -2617,7 +2818,7 @@ static int bpf_object__finalize_btf(struct bpf_object *obj)
 	if (!obj->btf)
 		return 0;
 
-	err = btf__finalize_data(obj, obj->btf);
+	err = btf_finalize_data(obj, obj->btf);
 	if (err) {
 		pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err);
 		return err;
@@ -2727,8 +2928,8 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 		if (!prog->mark_btf_static || !prog_is_subprog(obj, prog))
 			continue;
 
-		n = btf__get_nr_types(obj->btf);
-		for (j = 1; j <= n; j++) {
+		n = btf__type_cnt(obj->btf);
+		for (j = 1; j < n; j++) {
 			t = btf_type_by_id(obj->btf, j);
 			if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL)
 				continue;
@@ -2748,7 +2949,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 		__u32 sz;
 
 		/* clone BTF to sanitize a copy and leave the original intact */
-		raw_data = btf__get_raw_data(obj->btf, &sz);
+		raw_data = btf__raw_data(obj->btf, &sz);
 		kern_btf = btf__new(raw_data, sz);
 		err = libbpf_get_error(kern_btf);
 		if (err)
@@ -2761,7 +2962,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 
 	if (obj->gen_loader) {
 		__u32 raw_size = 0;
-		const void *raw_data = btf__get_raw_data(kern_btf, &raw_size);
+		const void *raw_data = btf__raw_data(kern_btf, &raw_size);
 
 		if (!raw_data)
 			return -ENOMEM;
@@ -2853,32 +3054,36 @@ static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name)
 	return NULL;
 }
 
-static int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr)
+static Elf64_Shdr *elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn)
 {
+	Elf64_Shdr *shdr;
+
 	if (!scn)
-		return -EINVAL;
+		return NULL;
 
-	if (gelf_getshdr(scn, hdr) != hdr) {
+	shdr = elf64_getshdr(scn);
+	if (!shdr) {
 		pr_warn("elf: failed to get section(%zu) header from %s: %s\n",
 			elf_ndxscn(scn), obj->path, elf_errmsg(-1));
-		return -EINVAL;
+		return NULL;
 	}
 
-	return 0;
+	return shdr;
 }
 
 static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn)
 {
 	const char *name;
-	GElf_Shdr sh;
+	Elf64_Shdr *sh;
 
 	if (!scn)
 		return NULL;
 
-	if (elf_sec_hdr(obj, scn, &sh))
+	sh = elf_sec_hdr(obj, scn);
+	if (!sh)
 		return NULL;
 
-	name = elf_sec_str(obj, sh.sh_name);
+	name = elf_sec_str(obj, sh->sh_name);
 	if (!name) {
 		pr_warn("elf: failed to get section(%zu) name from %s: %s\n",
 			elf_ndxscn(scn), obj->path, elf_errmsg(-1));
@@ -2906,13 +3111,29 @@ static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn)
 	return data;
 }
 
+static Elf64_Sym *elf_sym_by_idx(const struct bpf_object *obj, size_t idx)
+{
+	if (idx >= obj->efile.symbols->d_size / sizeof(Elf64_Sym))
+		return NULL;
+
+	return (Elf64_Sym *)obj->efile.symbols->d_buf + idx;
+}
+
+static Elf64_Rel *elf_rel_by_idx(Elf_Data *data, size_t idx)
+{
+	if (idx >= data->d_size / sizeof(Elf64_Rel))
+		return NULL;
+
+	return (Elf64_Rel *)data->d_buf + idx;
+}
+
 static bool is_sec_name_dwarf(const char *name)
 {
 	/* approximation, but the actual list is too long */
-	return strncmp(name, ".debug_", sizeof(".debug_") - 1) == 0;
+	return str_has_pfx(name, ".debug_");
 }
 
-static bool ignore_elf_section(GElf_Shdr *hdr, const char *name)
+static bool ignore_elf_section(Elf64_Shdr *hdr, const char *name)
 {
 	/* no special handling of .strtab */
 	if (hdr->sh_type == SHT_STRTAB)
@@ -2931,7 +3152,7 @@ static bool ignore_elf_section(GElf_Shdr *hdr, const char *name)
 	if (is_sec_name_dwarf(name))
 		return true;
 
-	if (strncmp(name, ".rel", sizeof(".rel") - 1) == 0) {
+	if (str_has_pfx(name, ".rel")) {
 		name += sizeof(".rel") - 1;
 		/* DWARF section relocations */
 		if (is_sec_name_dwarf(name))
@@ -2960,6 +3181,7 @@ static int cmp_progs(const void *_a, const void *_b)
 
 static int bpf_object__elf_collect(struct bpf_object *obj)
 {
+	struct elf_sec_desc *sec_desc;
 	Elf *elf = obj->efile.elf;
 	Elf_Data *btf_ext_data = NULL;
 	Elf_Data *btf_data = NULL;
@@ -2967,17 +3189,27 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	const char *name;
 	Elf_Data *data;
 	Elf_Scn *scn;
-	GElf_Shdr sh;
+	Elf64_Shdr *sh;
+
+	/* ELF section indices are 1-based, so allocate +1 element to keep
+	 * indexing simple. Also include 0th invalid section into sec_cnt for
+	 * simpler and more traditional iteration logic.
+	 */
+	obj->efile.sec_cnt = 1 + obj->efile.ehdr->e_shnum;
+	obj->efile.secs = calloc(obj->efile.sec_cnt, sizeof(*obj->efile.secs));
+	if (!obj->efile.secs)
+		return -ENOMEM;
 
 	/* a bunch of ELF parsing functionality depends on processing symbols,
 	 * so do the first pass and find the symbol table
 	 */
 	scn = NULL;
 	while ((scn = elf_nextscn(elf, scn)) != NULL) {
-		if (elf_sec_hdr(obj, scn, &sh))
+		sh = elf_sec_hdr(obj, scn);
+		if (!sh)
 			return -LIBBPF_ERRNO__FORMAT;
 
-		if (sh.sh_type == SHT_SYMTAB) {
+		if (sh->sh_type == SHT_SYMTAB) {
 			if (obj->efile.symbols) {
 				pr_warn("elf: multiple symbol tables in %s\n", obj->path);
 				return -LIBBPF_ERRNO__FORMAT;
@@ -2987,24 +3219,34 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			if (!data)
 				return -LIBBPF_ERRNO__FORMAT;
 
+			idx = elf_ndxscn(scn);
+
 			obj->efile.symbols = data;
-			obj->efile.symbols_shndx = elf_ndxscn(scn);
-			obj->efile.strtabidx = sh.sh_link;
+			obj->efile.symbols_shndx = idx;
+			obj->efile.strtabidx = sh->sh_link;
 		}
 	}
 
+	if (!obj->efile.symbols) {
+		pr_warn("elf: couldn't find symbol table in %s, stripped object file?\n",
+			obj->path);
+		return -ENOENT;
+	}
+
 	scn = NULL;
 	while ((scn = elf_nextscn(elf, scn)) != NULL) {
-		idx++;
+		idx = elf_ndxscn(scn);
+		sec_desc = &obj->efile.secs[idx];
 
-		if (elf_sec_hdr(obj, scn, &sh))
+		sh = elf_sec_hdr(obj, scn);
+		if (!sh)
 			return -LIBBPF_ERRNO__FORMAT;
 
-		name = elf_sec_str(obj, sh.sh_name);
+		name = elf_sec_str(obj, sh->sh_name);
 		if (!name)
 			return -LIBBPF_ERRNO__FORMAT;
 
-		if (ignore_elf_section(&sh, name))
+		if (ignore_elf_section(sh, name))
 			continue;
 
 		data = elf_sec_data(obj, scn);
@@ -3013,8 +3255,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 
 		pr_debug("elf: section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
 			 idx, name, (unsigned long)data->d_size,
-			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
-			 (int)sh.sh_type);
+			 (int)sh->sh_link, (unsigned long)sh->sh_flags,
+			 (int)sh->sh_type);
 
 		if (strcmp(name, "license") == 0) {
 			err = bpf_object__init_license(obj, data->d_buf, data->d_size);
@@ -3032,21 +3274,25 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			btf_data = data;
 		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
 			btf_ext_data = data;
-		} else if (sh.sh_type == SHT_SYMTAB) {
+		} else if (sh->sh_type == SHT_SYMTAB) {
 			/* already processed during the first pass above */
-		} else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) {
-			if (sh.sh_flags & SHF_EXECINSTR) {
+		} else if (sh->sh_type == SHT_PROGBITS && data->d_size > 0) {
+			if (sh->sh_flags & SHF_EXECINSTR) {
 				if (strcmp(name, ".text") == 0)
 					obj->efile.text_shndx = idx;
 				err = bpf_object__add_programs(obj, data, name, idx);
 				if (err)
 					return err;
-			} else if (strcmp(name, DATA_SEC) == 0) {
-				obj->efile.data = data;
-				obj->efile.data_shndx = idx;
-			} else if (strcmp(name, RODATA_SEC) == 0) {
-				obj->efile.rodata = data;
-				obj->efile.rodata_shndx = idx;
+			} else if (strcmp(name, DATA_SEC) == 0 ||
+				   str_has_pfx(name, DATA_SEC ".")) {
+				sec_desc->sec_type = SEC_DATA;
+				sec_desc->shdr = sh;
+				sec_desc->data = data;
+			} else if (strcmp(name, RODATA_SEC) == 0 ||
+				   str_has_pfx(name, RODATA_SEC ".")) {
+				sec_desc->sec_type = SEC_RODATA;
+				sec_desc->shdr = sh;
+				sec_desc->data = data;
 			} else if (strcmp(name, STRUCT_OPS_SEC) == 0) {
 				obj->efile.st_ops_data = data;
 				obj->efile.st_ops_shndx = idx;
@@ -3054,37 +3300,29 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 				pr_info("elf: skipping unrecognized data section(%d) %s\n",
 					idx, name);
 			}
-		} else if (sh.sh_type == SHT_REL) {
-			int nr_sects = obj->efile.nr_reloc_sects;
-			void *sects = obj->efile.reloc_sects;
-			int sec = sh.sh_info; /* points to other section */
+		} else if (sh->sh_type == SHT_REL) {
+			int targ_sec_idx = sh->sh_info; /* points to other section */
 
 			/* Only do relo for section with exec instructions */
-			if (!section_have_execinstr(obj, sec) &&
+			if (!section_have_execinstr(obj, targ_sec_idx) &&
 			    strcmp(name, ".rel" STRUCT_OPS_SEC) &&
 			    strcmp(name, ".rel" MAPS_ELF_SEC)) {
 				pr_info("elf: skipping relo section(%d) %s for section(%d) %s\n",
-					idx, name, sec,
-					elf_sec_name(obj, elf_sec_by_idx(obj, sec)) ?: "<?>");
+					idx, name, targ_sec_idx,
+					elf_sec_name(obj, elf_sec_by_idx(obj, targ_sec_idx)) ?: "<?>");
 				continue;
 			}
 
-			sects = libbpf_reallocarray(sects, nr_sects + 1,
-						    sizeof(*obj->efile.reloc_sects));
-			if (!sects)
-				return -ENOMEM;
-
-			obj->efile.reloc_sects = sects;
-			obj->efile.nr_reloc_sects++;
-
-			obj->efile.reloc_sects[nr_sects].shdr = sh;
-			obj->efile.reloc_sects[nr_sects].data = data;
-		} else if (sh.sh_type == SHT_NOBITS && strcmp(name, BSS_SEC) == 0) {
-			obj->efile.bss = data;
-			obj->efile.bss_shndx = idx;
+			sec_desc->sec_type = SEC_RELO;
+			sec_desc->shdr = sh;
+			sec_desc->data = data;
+		} else if (sh->sh_type == SHT_NOBITS && strcmp(name, BSS_SEC) == 0) {
+			sec_desc->sec_type = SEC_BSS;
+			sec_desc->shdr = sh;
+			sec_desc->data = data;
 		} else {
 			pr_info("elf: skipping section(%d) %s (size %zu)\n", idx, name,
-				(size_t)sh.sh_size);
+				(size_t)sh->sh_size);
 		}
 	}
 
@@ -3100,19 +3338,19 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	return bpf_object__init_btf(obj, btf_data, btf_ext_data);
 }
 
-static bool sym_is_extern(const GElf_Sym *sym)
+static bool sym_is_extern(const Elf64_Sym *sym)
 {
-	int bind = GELF_ST_BIND(sym->st_info);
+	int bind = ELF64_ST_BIND(sym->st_info);
 	/* externs are symbols w/ type=NOTYPE, bind=GLOBAL|WEAK, section=UND */
 	return sym->st_shndx == SHN_UNDEF &&
 	       (bind == STB_GLOBAL || bind == STB_WEAK) &&
-	       GELF_ST_TYPE(sym->st_info) == STT_NOTYPE;
+	       ELF64_ST_TYPE(sym->st_info) == STT_NOTYPE;
 }
 
-static bool sym_is_subprog(const GElf_Sym *sym, int text_shndx)
+static bool sym_is_subprog(const Elf64_Sym *sym, int text_shndx)
 {
-	int bind = GELF_ST_BIND(sym->st_info);
-	int type = GELF_ST_TYPE(sym->st_info);
+	int bind = ELF64_ST_BIND(sym->st_info);
+	int type = ELF64_ST_TYPE(sym->st_info);
 
 	/* in .text section */
 	if (sym->st_shndx != text_shndx)
@@ -3135,8 +3373,8 @@ static int find_extern_btf_id(const struct btf *btf, const char *ext_name)
 	if (!btf)
 		return -ESRCH;
 
-	n = btf__get_nr_types(btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(btf);
+	for (i = 1; i < n; i++) {
 		t = btf__type_by_id(btf, i);
 
 		if (!btf_is_var(t) && !btf_is_func(t))
@@ -3167,8 +3405,8 @@ static int find_extern_sec_btf_id(struct btf *btf, int ext_btf_id) {
 	if (!btf)
 		return -ESRCH;
 
-	n = btf__get_nr_types(btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(btf);
+	for (i = 1; i < n; i++) {
 		t = btf__type_by_id(btf, i);
 
 		if (!btf_is_datasec(t))
@@ -3252,8 +3490,8 @@ static int find_int_btf_id(const struct btf *btf)
 	const struct btf_type *t;
 	int i, n;
 
-	n = btf__get_nr_types(btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(btf);
+	for (i = 1; i < n; i++) {
 		t = btf__type_by_id(btf, i);
 
 		if (btf_is_int(t) && btf_int_bits(t) == 32)
@@ -3310,30 +3548,31 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 	int i, n, off, dummy_var_btf_id;
 	const char *ext_name, *sec_name;
 	Elf_Scn *scn;
-	GElf_Shdr sh;
+	Elf64_Shdr *sh;
 
 	if (!obj->efile.symbols)
 		return 0;
 
 	scn = elf_sec_by_idx(obj, obj->efile.symbols_shndx);
-	if (elf_sec_hdr(obj, scn, &sh))
+	sh = elf_sec_hdr(obj, scn);
+	if (!sh)
 		return -LIBBPF_ERRNO__FORMAT;
 
 	dummy_var_btf_id = add_dummy_ksym_var(obj->btf);
 	if (dummy_var_btf_id < 0)
 		return dummy_var_btf_id;
 
-	n = sh.sh_size / sh.sh_entsize;
+	n = sh->sh_size / sh->sh_entsize;
 	pr_debug("looking for externs among %d symbols...\n", n);
 
 	for (i = 0; i < n; i++) {
-		GElf_Sym sym;
+		Elf64_Sym *sym = elf_sym_by_idx(obj, i);
 
-		if (!gelf_getsym(obj->efile.symbols, i, &sym))
+		if (!sym)
 			return -LIBBPF_ERRNO__FORMAT;
-		if (!sym_is_extern(&sym))
+		if (!sym_is_extern(sym))
 			continue;
-		ext_name = elf_sym_str(obj, sym.st_name);
+		ext_name = elf_sym_str(obj, sym->st_name);
 		if (!ext_name || !ext_name[0])
 			continue;
 
@@ -3355,7 +3594,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 		t = btf__type_by_id(obj->btf, ext->btf_id);
 		ext->name = btf__name_by_offset(obj->btf, t->name_off);
 		ext->sym_idx = i;
-		ext->is_weak = GELF_ST_BIND(sym.st_info) == STB_WEAK;
+		ext->is_weak = ELF64_ST_BIND(sym->st_info) == STB_WEAK;
 
 		ext->sec_btf_id = find_extern_sec_btf_id(obj->btf, ext->btf_id);
 		if (ext->sec_btf_id <= 0) {
@@ -3393,11 +3632,6 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 				return -ENOTSUP;
 			}
 		} else if (strcmp(sec_name, KSYMS_SEC) == 0) {
-			if (btf_is_func(t) && ext->is_weak) {
-				pr_warn("extern weak function %s is unsupported\n",
-					ext->name);
-				return -ENOTSUP;
-			}
 			ksym_sec = sec;
 			ext->type = EXT_KSYM;
 			skip_mods_and_typedefs(obj->btf, t->type,
@@ -3565,9 +3799,14 @@ bpf_object__find_program_by_name(const struct bpf_object *obj,
 static bool bpf_object__shndx_is_data(const struct bpf_object *obj,
 				      int shndx)
 {
-	return shndx == obj->efile.data_shndx ||
-	       shndx == obj->efile.bss_shndx ||
-	       shndx == obj->efile.rodata_shndx;
+	switch (obj->efile.secs[shndx].sec_type) {
+	case SEC_BSS:
+	case SEC_DATA:
+	case SEC_RODATA:
+		return true;
+	default:
+		return false;
+	}
 }
 
 static bool bpf_object__shndx_is_maps(const struct bpf_object *obj,
@@ -3580,22 +3819,25 @@ static bool bpf_object__shndx_is_maps(const struct bpf_object *obj,
 static enum libbpf_map_type
 bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx)
 {
-	if (shndx == obj->efile.data_shndx)
-		return LIBBPF_MAP_DATA;
-	else if (shndx == obj->efile.bss_shndx)
+	if (shndx == obj->efile.symbols_shndx)
+		return LIBBPF_MAP_KCONFIG;
+
+	switch (obj->efile.secs[shndx].sec_type) {
+	case SEC_BSS:
 		return LIBBPF_MAP_BSS;
-	else if (shndx == obj->efile.rodata_shndx)
+	case SEC_DATA:
+		return LIBBPF_MAP_DATA;
+	case SEC_RODATA:
 		return LIBBPF_MAP_RODATA;
-	else if (shndx == obj->efile.symbols_shndx)
-		return LIBBPF_MAP_KCONFIG;
-	else
+	default:
 		return LIBBPF_MAP_UNSPEC;
+	}
 }
 
 static int bpf_program__record_reloc(struct bpf_program *prog,
 				     struct reloc_desc *reloc_desc,
 				     __u32 insn_idx, const char *sym_name,
-				     const GElf_Sym *sym, const GElf_Rel *rel)
+				     const Elf64_Sym *sym, const Elf64_Rel *rel)
 {
 	struct bpf_insn *insn = &prog->insns[insn_idx];
 	size_t map_idx, nr_maps = prog->obj->nr_maps;
@@ -3612,7 +3854,7 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
 	}
 
 	if (sym_is_extern(sym)) {
-		int sym_idx = GELF_R_SYM(rel->r_info);
+		int sym_idx = ELF64_R_SYM(rel->r_info);
 		int i, n = obj->nr_extern;
 		struct extern_desc *ext;
 
@@ -3725,7 +3967,7 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
 	}
 	for (map_idx = 0; map_idx < nr_maps; map_idx++) {
 		map = &obj->maps[map_idx];
-		if (map->libbpf_type != type)
+		if (map->libbpf_type != type || map->sec_idx != sym->st_shndx)
 			continue;
 		pr_debug("prog '%s': found data map %zd (%s, sec %d, off %zu) for insn %u\n",
 			 prog->name, map_idx, map->name, map->sec_idx,
@@ -3777,9 +4019,8 @@ static struct bpf_program *find_prog_by_sec_insn(const struct bpf_object *obj,
 }
 
 static int
-bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data *data)
+bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Data *data)
 {
-	Elf_Data *symbols = obj->efile.symbols;
 	const char *relo_sec_name, *sec_name;
 	size_t sec_idx = shdr->sh_info;
 	struct bpf_program *prog;
@@ -3789,8 +4030,8 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data
 	__u32 insn_idx;
 	Elf_Scn *scn;
 	Elf_Data *scn_data;
-	GElf_Sym sym;
-	GElf_Rel rel;
+	Elf64_Sym *sym;
+	Elf64_Rel *rel;
 
 	scn = elf_sec_by_idx(obj, sec_idx);
 	scn_data = elf_sec_data(obj, scn);
@@ -3805,33 +4046,36 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data
 	nrels = shdr->sh_size / shdr->sh_entsize;
 
 	for (i = 0; i < nrels; i++) {
-		if (!gelf_getrel(data, i, &rel)) {
+		rel = elf_rel_by_idx(data, i);
+		if (!rel) {
 			pr_warn("sec '%s': failed to get relo #%d\n", relo_sec_name, i);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
-		if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
+
+		sym = elf_sym_by_idx(obj, ELF64_R_SYM(rel->r_info));
+		if (!sym) {
 			pr_warn("sec '%s': symbol 0x%zx not found for relo #%d\n",
-				relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i);
+				relo_sec_name, (size_t)ELF64_R_SYM(rel->r_info), i);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		if (rel.r_offset % BPF_INSN_SZ || rel.r_offset >= scn_data->d_size) {
+		if (rel->r_offset % BPF_INSN_SZ || rel->r_offset >= scn_data->d_size) {
 			pr_warn("sec '%s': invalid offset 0x%zx for relo #%d\n",
-				relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i);
+				relo_sec_name, (size_t)ELF64_R_SYM(rel->r_info), i);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		insn_idx = rel.r_offset / BPF_INSN_SZ;
+		insn_idx = rel->r_offset / BPF_INSN_SZ;
 		/* relocations against static functions are recorded as
 		 * relocations against the section that contains a function;
 		 * in such case, symbol will be STT_SECTION and sym.st_name
 		 * will point to empty string (0), so fetch section name
 		 * instead
 		 */
-		if (GELF_ST_TYPE(sym.st_info) == STT_SECTION && sym.st_name == 0)
-			sym_name = elf_sec_name(obj, elf_sec_by_idx(obj, sym.st_shndx));
+		if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION && sym->st_name == 0)
+			sym_name = elf_sec_name(obj, elf_sec_by_idx(obj, sym->st_shndx));
 		else
-			sym_name = elf_sym_str(obj, sym.st_name);
+			sym_name = elf_sym_str(obj, sym->st_name);
 		sym_name = sym_name ?: "<?";
 
 		pr_debug("sec '%s': relo #%d: insn #%u against '%s'\n",
@@ -3853,7 +4097,7 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data
 		/* adjust insn_idx to local BPF program frame of reference */
 		insn_idx -= prog->sec_insn_off;
 		err = bpf_program__record_reloc(prog, &relos[prog->nr_reloc],
-						insn_idx, sym_name, &sym, &rel);
+						insn_idx, sym_name, sym, rel);
 		if (err)
 			return err;
 
@@ -3885,8 +4129,7 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
 		 * LLVM annotates global data differently in BTF, that is,
 		 * only as '.data', '.bss' or '.rodata'.
 		 */
-		ret = btf__find_by_name(obj->btf,
-				libbpf_type_to_btf_name[map->libbpf_type]);
+		ret = btf__find_by_name(obj->btf, map->real_name);
 	}
 	if (ret < 0)
 		return ret;
@@ -3979,6 +4222,7 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 	map->btf_key_type_id = info.btf_key_type_id;
 	map->btf_value_type_id = info.btf_value_type_id;
 	map->reused = true;
+	map->map_extra = info.map_extra;
 
 	return 0;
 
@@ -4207,6 +4451,23 @@ static int probe_kern_btf_float(void)
 					     strs, sizeof(strs)));
 }
 
+static int probe_kern_btf_decl_tag(void)
+{
+	static const char strs[] = "\0tag";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* VAR x */                                     /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+		BTF_VAR_STATIC,
+		/* attr */
+		BTF_TYPE_DECL_TAG_ENC(1, 2, -1),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs)));
+}
+
 static int probe_kern_array_mmap(void)
 {
 	struct bpf_create_map_attr attr = {
@@ -4423,6 +4684,9 @@ static struct kern_feature_desc {
 	[FEAT_PERF_LINK] = {
 		"BPF perf link support", probe_perf_link,
 	},
+	[FEAT_BTF_DECL_TAG] = {
+		"BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag,
+	},
 };
 
 static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
@@ -4473,7 +4737,8 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
 		map_info.key_size == map->def.key_size &&
 		map_info.value_size == map->def.value_size &&
 		map_info.max_entries == map->def.max_entries &&
-		map_info.map_flags == map->def.map_flags);
+		map_info.map_flags == map->def.map_flags &&
+		map_info.map_extra == map->map_extra);
 }
 
 static int
@@ -4556,7 +4821,7 @@ static void bpf_map__destroy(struct bpf_map *map);
 
 static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner)
 {
-	struct bpf_create_map_attr create_attr;
+	struct bpf_create_map_params create_attr;
 	struct bpf_map_def *def = &map->def;
 	int err = 0;
 
@@ -4570,6 +4835,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 	create_attr.key_size = def->key_size;
 	create_attr.value_size = def->value_size;
 	create_attr.numa_node = map->numa_node;
+	create_attr.map_extra = map->map_extra;
 
 	if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !def->max_entries) {
 		int nr_cpus;
@@ -4613,6 +4879,30 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 			create_attr.inner_map_fd = map->inner_map_fd;
 	}
 
+	switch (def->type) {
+	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+	case BPF_MAP_TYPE_CGROUP_ARRAY:
+	case BPF_MAP_TYPE_STACK_TRACE:
+	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
+	case BPF_MAP_TYPE_HASH_OF_MAPS:
+	case BPF_MAP_TYPE_DEVMAP:
+	case BPF_MAP_TYPE_DEVMAP_HASH:
+	case BPF_MAP_TYPE_CPUMAP:
+	case BPF_MAP_TYPE_XSKMAP:
+	case BPF_MAP_TYPE_SOCKMAP:
+	case BPF_MAP_TYPE_SOCKHASH:
+	case BPF_MAP_TYPE_QUEUE:
+	case BPF_MAP_TYPE_STACK:
+	case BPF_MAP_TYPE_RINGBUF:
+		create_attr.btf_fd = 0;
+		create_attr.btf_key_type_id = 0;
+		create_attr.btf_value_type_id = 0;
+		map->btf_key_type_id = 0;
+		map->btf_value_type_id = 0;
+	default:
+		break;
+	}
+
 	if (obj->gen_loader) {
 		bpf_gen__map_create(obj->gen_loader, &create_attr, is_inner ? -1 : map - obj->maps);
 		/* Pretend to have valid FD to pass various fd >= 0 checks.
@@ -4620,7 +4910,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		 */
 		map->fd = 0;
 	} else {
-		map->fd = bpf_create_map_xattr(&create_attr);
+		map->fd = libbpf__bpf_create_map_xattr(&create_attr);
 	}
 	if (map->fd < 0 && (create_attr.btf_key_type_id ||
 			    create_attr.btf_value_type_id)) {
@@ -4635,7 +4925,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		create_attr.btf_value_type_id = 0;
 		map->btf_key_type_id = 0;
 		map->btf_value_type_id = 0;
-		map->fd = bpf_create_map_xattr(&create_attr);
+		map->fd = libbpf__bpf_create_map_xattr(&create_attr);
 	}
 
 	err = map->fd < 0 ? -errno : 0;
@@ -4812,8 +5102,8 @@ static int bpf_core_add_cands(struct bpf_core_cand *local_cand,
 	size_t targ_essent_len;
 	int n, i;
 
-	n = btf__get_nr_types(targ_btf);
-	for (i = targ_start_id; i <= n; i++) {
+	n = btf__type_cnt(targ_btf);
+	for (i = targ_start_id; i < n; i++) {
 		t = btf__type_by_id(targ_btf, i);
 		if (btf_kind(t) != btf_kind(local_cand->t))
 			continue;
@@ -4988,7 +5278,7 @@ bpf_core_find_cands(struct bpf_object *obj, const struct btf *local_btf, __u32 l
 		err = bpf_core_add_cands(&local_cand, local_essent_len,
 					 obj->btf_modules[i].btf,
 					 obj->btf_modules[i].name,
-					 btf__get_nr_types(obj->btf_vmlinux) + 1,
+					 btf__type_cnt(obj->btf_vmlinux),
 					 cands);
 		if (err)
 			goto err_out;
@@ -5132,7 +5422,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 	 * relocated, so it's enough to just subtract in-section offset
 	 */
 	insn_idx = insn_idx - prog->sec_insn_off;
-	if (insn_idx > prog->insns_cnt)
+	if (insn_idx >= prog->insns_cnt)
 		return -EINVAL;
 	insn = &prog->insns[insn_idx];
 
@@ -5326,7 +5616,13 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 		case RELO_EXTERN_FUNC:
 			ext = &obj->externs[relo->sym_off];
 			insn[0].src_reg = BPF_PSEUDO_KFUNC_CALL;
-			insn[0].imm = ext->ksym.kernel_btf_id;
+			if (ext->is_set) {
+				insn[0].imm = ext->ksym.kernel_btf_id;
+				insn[0].off = ext->ksym.btf_fd_idx;
+			} else { /* unresolved weak kfunc */
+				insn[0].imm = 0;
+				insn[0].off = 0;
+			}
 			break;
 		case RELO_SUBPROG_ADDR:
 			if (insn[0].src_reg != BPF_PSEUDO_FUNC) {
@@ -5851,10 +6147,10 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 }
 
 static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
-					    GElf_Shdr *shdr, Elf_Data *data);
+					    Elf64_Shdr *shdr, Elf_Data *data);
 
 static int bpf_object__collect_map_relos(struct bpf_object *obj,
-					 GElf_Shdr *shdr, Elf_Data *data)
+					 Elf64_Shdr *shdr, Elf_Data *data)
 {
 	const int bpf_ptr_sz = 8, host_ptr_sz = sizeof(void *);
 	int i, j, nrels, new_sz;
@@ -5863,10 +6159,9 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj,
 	struct bpf_map *map = NULL, *targ_map;
 	const struct btf_member *member;
 	const char *name, *mname;
-	Elf_Data *symbols;
 	unsigned int moff;
-	GElf_Sym sym;
-	GElf_Rel rel;
+	Elf64_Sym *sym;
+	Elf64_Rel *rel;
 	void *tmp;
 
 	if (!obj->efile.btf_maps_sec_btf_id || !obj->btf)
@@ -5875,28 +6170,30 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj,
 	if (!sec)
 		return -EINVAL;
 
-	symbols = obj->efile.symbols;
 	nrels = shdr->sh_size / shdr->sh_entsize;
 	for (i = 0; i < nrels; i++) {
-		if (!gelf_getrel(data, i, &rel)) {
+		rel = elf_rel_by_idx(data, i);
+		if (!rel) {
 			pr_warn(".maps relo #%d: failed to get ELF relo\n", i);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
-		if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
+
+		sym = elf_sym_by_idx(obj, ELF64_R_SYM(rel->r_info));
+		if (!sym) {
 			pr_warn(".maps relo #%d: symbol %zx not found\n",
-				i, (size_t)GELF_R_SYM(rel.r_info));
+				i, (size_t)ELF64_R_SYM(rel->r_info));
 			return -LIBBPF_ERRNO__FORMAT;
 		}
-		name = elf_sym_str(obj, sym.st_name) ?: "<?>";
-		if (sym.st_shndx != obj->efile.btf_maps_shndx) {
+		name = elf_sym_str(obj, sym->st_name) ?: "<?>";
+		if (sym->st_shndx != obj->efile.btf_maps_shndx) {
 			pr_warn(".maps relo #%d: '%s' isn't a BTF-defined map\n",
 				i, name);
 			return -LIBBPF_ERRNO__RELOC;
 		}
 
-		pr_debug(".maps relo #%d: for %zd value %zd rel.r_offset %zu name %d ('%s')\n",
-			 i, (ssize_t)(rel.r_info >> 32), (size_t)sym.st_value,
-			 (size_t)rel.r_offset, sym.st_name, name);
+		pr_debug(".maps relo #%d: for %zd value %zd rel->r_offset %zu name %d ('%s')\n",
+			 i, (ssize_t)(rel->r_info >> 32), (size_t)sym->st_value,
+			 (size_t)rel->r_offset, sym->st_name, name);
 
 		for (j = 0; j < obj->nr_maps; j++) {
 			map = &obj->maps[j];
@@ -5904,13 +6201,13 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj,
 				continue;
 
 			vi = btf_var_secinfos(sec) + map->btf_var_idx;
-			if (vi->offset <= rel.r_offset &&
-			    rel.r_offset + bpf_ptr_sz <= vi->offset + vi->size)
+			if (vi->offset <= rel->r_offset &&
+			    rel->r_offset + bpf_ptr_sz <= vi->offset + vi->size)
 				break;
 		}
 		if (j == obj->nr_maps) {
-			pr_warn(".maps relo #%d: cannot find map '%s' at rel.r_offset %zu\n",
-				i, name, (size_t)rel.r_offset);
+			pr_warn(".maps relo #%d: cannot find map '%s' at rel->r_offset %zu\n",
+				i, name, (size_t)rel->r_offset);
 			return -EINVAL;
 		}
 
@@ -5937,10 +6234,10 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj,
 			return -EINVAL;
 
 		moff = btf_member_bit_offset(def, btf_vlen(def) - 1) / 8;
-		if (rel.r_offset - vi->offset < moff)
+		if (rel->r_offset - vi->offset < moff)
 			return -EINVAL;
 
-		moff = rel.r_offset - vi->offset - moff;
+		moff = rel->r_offset - vi->offset - moff;
 		/* here we use BPF pointer size, which is always 64 bit, as we
 		 * are parsing ELF that was built for BPF target
 		 */
@@ -5985,10 +6282,18 @@ static int bpf_object__collect_relos(struct bpf_object *obj)
 {
 	int i, err;
 
-	for (i = 0; i < obj->efile.nr_reloc_sects; i++) {
-		GElf_Shdr *shdr = &obj->efile.reloc_sects[i].shdr;
-		Elf_Data *data = obj->efile.reloc_sects[i].data;
-		int idx = shdr->sh_info;
+	for (i = 0; i < obj->efile.sec_cnt; i++) {
+		struct elf_sec_desc *sec_desc = &obj->efile.secs[i];
+		Elf64_Shdr *shdr;
+		Elf_Data *data;
+		int idx;
+
+		if (sec_desc->sec_type != SEC_RELO)
+			continue;
+
+		shdr = sec_desc->shdr;
+		data = sec_desc->data;
+		idx = shdr->sh_info;
 
 		if (shdr->sh_type != SHT_REL) {
 			pr_warn("internal error at %d\n", __LINE__);
@@ -6064,15 +6369,58 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program
 	return 0;
 }
 
+static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name,
+				     int *btf_obj_fd, int *btf_type_id);
+
+/* this is called as prog->sec_def->preload_fn for libbpf-supported sec_defs */
+static int libbpf_preload_prog(struct bpf_program *prog,
+			       struct bpf_prog_load_params *attr, long cookie)
+{
+	enum sec_def_flags def = cookie;
+
+	/* old kernels might not support specifying expected_attach_type */
+	if ((def & SEC_EXP_ATTACH_OPT) && !kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE))
+		attr->expected_attach_type = 0;
+
+	if (def & SEC_SLEEPABLE)
+		attr->prog_flags |= BPF_F_SLEEPABLE;
+
+	if ((prog->type == BPF_PROG_TYPE_TRACING ||
+	     prog->type == BPF_PROG_TYPE_LSM ||
+	     prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) {
+		int btf_obj_fd = 0, btf_type_id = 0, err;
+		const char *attach_name;
+
+		attach_name = strchr(prog->sec_name, '/') + 1;
+		err = libbpf_find_attach_btf_id(prog, attach_name, &btf_obj_fd, &btf_type_id);
+		if (err)
+			return err;
+
+		/* cache resolved BTF FD and BTF type ID in the prog */
+		prog->attach_btf_obj_fd = btf_obj_fd;
+		prog->attach_btf_id = btf_type_id;
+
+		/* but by now libbpf common logic is not utilizing
+		 * prog->atach_btf_obj_fd/prog->attach_btf_id anymore because
+		 * this callback is called after attrs were populated by
+		 * libbpf, so this callback has to update attr explicitly here
+		 */
+		attr->attach_btf_obj_fd = btf_obj_fd;
+		attr->attach_btf_id = btf_type_id;
+	}
+	return 0;
+}
+
 static int
 load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	     char *license, __u32 kern_version, int *pfd)
 {
 	struct bpf_prog_load_params load_attr = {};
+	struct bpf_object *obj = prog->obj;
 	char *cp, errmsg[STRERR_BUFSIZE];
 	size_t log_buf_size = 0;
 	char *log_buf = NULL;
-	int btf_fd, ret;
+	int btf_fd, ret, err;
 
 	if (prog->type == BPF_PROG_TYPE_UNSPEC) {
 		/*
@@ -6088,29 +6436,22 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 		return -EINVAL;
 
 	load_attr.prog_type = prog->type;
-	/* old kernels might not support specifying expected_attach_type */
-	if (!kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE) && prog->sec_def &&
-	    prog->sec_def->is_exp_attach_type_optional)
-		load_attr.expected_attach_type = 0;
-	else
-		load_attr.expected_attach_type = prog->expected_attach_type;
-	if (kernel_supports(prog->obj, FEAT_PROG_NAME))
+	load_attr.expected_attach_type = prog->expected_attach_type;
+	if (kernel_supports(obj, FEAT_PROG_NAME))
 		load_attr.name = prog->name;
 	load_attr.insns = insns;
 	load_attr.insn_cnt = insns_cnt;
 	load_attr.license = license;
 	load_attr.attach_btf_id = prog->attach_btf_id;
-	if (prog->attach_prog_fd)
-		load_attr.attach_prog_fd = prog->attach_prog_fd;
-	else
-		load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd;
+	load_attr.attach_prog_fd = prog->attach_prog_fd;
+	load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd;
 	load_attr.attach_btf_id = prog->attach_btf_id;
 	load_attr.kern_version = kern_version;
 	load_attr.prog_ifindex = prog->prog_ifindex;
 
 	/* specify func_info/line_info only if kernel supports them */
-	btf_fd = bpf_object__btf_fd(prog->obj);
-	if (btf_fd >= 0 && kernel_supports(prog->obj, FEAT_BTF_FUNC)) {
+	btf_fd = bpf_object__btf_fd(obj);
+	if (btf_fd >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) {
 		load_attr.prog_btf_fd = btf_fd;
 		load_attr.func_info = prog->func_info;
 		load_attr.func_info_rec_size = prog->func_info_rec_size;
@@ -6121,10 +6462,21 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	}
 	load_attr.log_level = prog->log_level;
 	load_attr.prog_flags = prog->prog_flags;
+	load_attr.fd_array = obj->fd_array;
 
-	if (prog->obj->gen_loader) {
-		bpf_gen__prog_load(prog->obj->gen_loader, &load_attr,
-				   prog - prog->obj->programs);
+	/* adjust load_attr if sec_def provides custom preload callback */
+	if (prog->sec_def && prog->sec_def->preload_fn) {
+		err = prog->sec_def->preload_fn(prog, &load_attr, prog->sec_def->cookie);
+		if (err < 0) {
+			pr_warn("prog '%s': failed to prepare load attributes: %d\n",
+				prog->name, err);
+			return err;
+		}
+	}
+
+	if (obj->gen_loader) {
+		bpf_gen__prog_load(obj->gen_loader, &load_attr,
+				   prog - obj->programs);
 		*pfd = -1;
 		return 0;
 	}
@@ -6145,16 +6497,21 @@ retry_load:
 		if (log_buf && load_attr.log_level)
 			pr_debug("verifier log:\n%s", log_buf);
 
-		if (prog->obj->rodata_map_idx >= 0 &&
-		    kernel_supports(prog->obj, FEAT_PROG_BIND_MAP)) {
-			struct bpf_map *rodata_map =
-				&prog->obj->maps[prog->obj->rodata_map_idx];
+		if (obj->has_rodata && kernel_supports(obj, FEAT_PROG_BIND_MAP)) {
+			struct bpf_map *map;
+			int i;
 
-			if (bpf_prog_bind_map(ret, bpf_map__fd(rodata_map), NULL)) {
-				cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
-				pr_warn("prog '%s': failed to bind .rodata map: %s\n",
-					prog->name, cp);
-				/* Don't fail hard if can't bind rodata. */
+			for (i = 0; i < obj->nr_maps; i++) {
+				map = &prog->obj->maps[i];
+				if (map->libbpf_type != LIBBPF_MAP_RODATA)
+					continue;
+
+				if (bpf_prog_bind_map(ret, bpf_map__fd(map), NULL)) {
+					cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+					pr_warn("prog '%s': failed to bind .rodata map: %s\n",
+						prog->name, cp);
+					/* Don't fail hard if can't bind rodata. */
+				}
 			}
 		}
 
@@ -6218,16 +6575,13 @@ static int bpf_program__record_externs(struct bpf_program *prog)
 		case RELO_EXTERN_VAR:
 			if (ext->type != EXT_KSYM)
 				continue;
-			if (!ext->ksym.type_id) {
-				pr_warn("typeless ksym %s is not supported yet\n",
-					ext->name);
-				return -ENOTSUP;
-			}
-			bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_VAR,
-					       relo->insn_idx);
+			bpf_gen__record_extern(obj->gen_loader, ext->name,
+					       ext->is_weak, !ext->ksym.type_id,
+					       BTF_KIND_VAR, relo->insn_idx);
 			break;
 		case RELO_EXTERN_FUNC:
-			bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_FUNC,
+			bpf_gen__record_extern(obj->gen_loader, ext->name,
+					       ext->is_weak, false, BTF_KIND_FUNC,
 					       relo->insn_idx);
 			break;
 		default:
@@ -6237,8 +6591,6 @@ static int bpf_program__record_externs(struct bpf_program *prog)
 	return 0;
 }
 
-static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id);
-
 int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 {
 	int err = 0, fd, i;
@@ -6248,19 +6600,6 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 		return libbpf_err(-EINVAL);
 	}
 
-	if ((prog->type == BPF_PROG_TYPE_TRACING ||
-	     prog->type == BPF_PROG_TYPE_LSM ||
-	     prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) {
-		int btf_obj_fd = 0, btf_type_id = 0;
-
-		err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id);
-		if (err)
-			return libbpf_err(err);
-
-		prog->attach_btf_obj_fd = btf_obj_fd;
-		prog->attach_btf_id = btf_type_id;
-	}
-
 	if (prog->instances.nr < 0 || !prog->instances.fds) {
 		if (prog->preprocessor) {
 			pr_warn("Internal error: can't load program '%s'\n",
@@ -6328,8 +6667,6 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 out:
 	if (err)
 		pr_warn("failed to load program '%s'\n", prog->name);
-	zfree(&prog->insns);
-	prog->insns_cnt = 0;
 	return libbpf_err(err);
 }
 
@@ -6367,12 +6704,51 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
 
 static const struct bpf_sec_def *find_sec_def(const char *sec_name);
 
+static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object_open_opts *opts)
+{
+	struct bpf_program *prog;
+	int err;
+
+	bpf_object__for_each_program(prog, obj) {
+		prog->sec_def = find_sec_def(prog->sec_name);
+		if (!prog->sec_def) {
+			/* couldn't guess, but user might manually specify */
+			pr_debug("prog '%s': unrecognized ELF section name '%s'\n",
+				prog->name, prog->sec_name);
+			continue;
+		}
+
+		bpf_program__set_type(prog, prog->sec_def->prog_type);
+		bpf_program__set_expected_attach_type(prog, prog->sec_def->expected_attach_type);
+
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+		if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING ||
+		    prog->sec_def->prog_type == BPF_PROG_TYPE_EXT)
+			prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
+#pragma GCC diagnostic pop
+
+		/* sec_def can have custom callback which should be called
+		 * after bpf_program is initialized to adjust its properties
+		 */
+		if (prog->sec_def->init_fn) {
+			err = prog->sec_def->init_fn(prog, prog->sec_def->cookie);
+			if (err < 0) {
+				pr_warn("prog '%s': failed to initialize: %d\n",
+					prog->name, err);
+				return err;
+			}
+		}
+	}
+
+	return 0;
+}
+
 static struct bpf_object *
 __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 		   const struct bpf_object_open_opts *opts)
 {
 	const char *obj_name, *kconfig, *btf_tmp_path;
-	struct bpf_program *prog;
 	struct bpf_object *obj;
 	char tmp_name[64];
 	int err;
@@ -6430,30 +6806,12 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 	err = err ? : bpf_object__collect_externs(obj);
 	err = err ? : bpf_object__finalize_btf(obj);
 	err = err ? : bpf_object__init_maps(obj, opts);
+	err = err ? : bpf_object_init_progs(obj, opts);
 	err = err ? : bpf_object__collect_relos(obj);
 	if (err)
 		goto out;
-	bpf_object__elf_finish(obj);
 
-	bpf_object__for_each_program(prog, obj) {
-		prog->sec_def = find_sec_def(prog->sec_name);
-		if (!prog->sec_def) {
-			/* couldn't guess, but user might manually specify */
-			pr_debug("prog '%s': unrecognized ELF section name '%s'\n",
-				prog->name, prog->sec_name);
-			continue;
-		}
-
-		if (prog->sec_def->is_sleepable)
-			prog->prog_flags |= BPF_F_SLEEPABLE;
-		bpf_program__set_type(prog, prog->sec_def->prog_type);
-		bpf_program__set_expected_attach_type(prog,
-				prog->sec_def->expected_attach_type);
-
-		if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING ||
-		    prog->sec_def->prog_type == BPF_PROG_TYPE_EXT)
-			prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
-	}
+	bpf_object__elf_finish(obj);
 
 	return obj;
 out:
@@ -6529,7 +6887,7 @@ bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz,
 	return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, &opts));
 }
 
-int bpf_object__unload(struct bpf_object *obj)
+static int bpf_object_unload(struct bpf_object *obj)
 {
 	size_t i;
 
@@ -6548,6 +6906,8 @@ int bpf_object__unload(struct bpf_object *obj)
 	return 0;
 }
 
+int bpf_object__unload(struct bpf_object *obj) __attribute__((alias("bpf_object_unload")));
+
 static int bpf_object__sanitize_maps(struct bpf_object *obj)
 {
 	struct bpf_map *m;
@@ -6621,13 +6981,14 @@ out:
 
 static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name,
 			    __u16 kind, struct btf **res_btf,
-			    int *res_btf_fd)
+			    struct module_btf **res_mod_btf)
 {
-	int i, id, btf_fd, err;
+	struct module_btf *mod_btf;
 	struct btf *btf;
+	int i, id, err;
 
 	btf = obj->btf_vmlinux;
-	btf_fd = 0;
+	mod_btf = NULL;
 	id = btf__find_by_name_kind(btf, ksym_name, kind);
 
 	if (id == -ENOENT) {
@@ -6636,10 +6997,10 @@ static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name,
 			return err;
 
 		for (i = 0; i < obj->btf_module_cnt; i++) {
-			btf = obj->btf_modules[i].btf;
-			/* we assume module BTF FD is always >0 */
-			btf_fd = obj->btf_modules[i].fd;
-			id = btf__find_by_name_kind(btf, ksym_name, kind);
+			/* we assume module_btf's BTF FD is always >0 */
+			mod_btf = &obj->btf_modules[i];
+			btf = mod_btf->btf;
+			id = btf__find_by_name_kind_own(btf, ksym_name, kind);
 			if (id != -ENOENT)
 				break;
 		}
@@ -6648,7 +7009,7 @@ static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name,
 		return -ESRCH;
 
 	*res_btf = btf;
-	*res_btf_fd = btf_fd;
+	*res_mod_btf = mod_btf;
 	return id;
 }
 
@@ -6657,14 +7018,15 @@ static int bpf_object__resolve_ksym_var_btf_id(struct bpf_object *obj,
 {
 	const struct btf_type *targ_var, *targ_type;
 	__u32 targ_type_id, local_type_id;
+	struct module_btf *mod_btf = NULL;
 	const char *targ_var_name;
-	int id, btf_fd = 0, err;
 	struct btf *btf = NULL;
+	int id, err;
 
-	id = find_ksym_btf_id(obj, ext->name, BTF_KIND_VAR, &btf, &btf_fd);
-	if (id == -ESRCH && ext->is_weak) {
-		return 0;
-	} else if (id < 0) {
+	id = find_ksym_btf_id(obj, ext->name, BTF_KIND_VAR, &btf, &mod_btf);
+	if (id < 0) {
+		if (id == -ESRCH && ext->is_weak)
+			return 0;
 		pr_warn("extern (var ksym) '%s': not found in kernel BTF\n",
 			ext->name);
 		return id;
@@ -6696,7 +7058,7 @@ static int bpf_object__resolve_ksym_var_btf_id(struct bpf_object *obj,
 	}
 
 	ext->is_set = true;
-	ext->ksym.kernel_btf_obj_fd = btf_fd;
+	ext->ksym.kernel_btf_obj_fd = mod_btf ? mod_btf->fd : 0;
 	ext->ksym.kernel_btf_id = id;
 	pr_debug("extern (var ksym) '%s': resolved to [%d] %s %s\n",
 		 ext->name, id, btf_kind_str(targ_var), targ_var_name);
@@ -6708,26 +7070,22 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj,
 						struct extern_desc *ext)
 {
 	int local_func_proto_id, kfunc_proto_id, kfunc_id;
+	struct module_btf *mod_btf = NULL;
 	const struct btf_type *kern_func;
 	struct btf *kern_btf = NULL;
-	int ret, kern_btf_fd = 0;
+	int ret;
 
 	local_func_proto_id = ext->ksym.type_id;
 
-	kfunc_id = find_ksym_btf_id(obj, ext->name, BTF_KIND_FUNC,
-				    &kern_btf, &kern_btf_fd);
+	kfunc_id = find_ksym_btf_id(obj, ext->name, BTF_KIND_FUNC, &kern_btf, &mod_btf);
 	if (kfunc_id < 0) {
-		pr_warn("extern (func ksym) '%s': not found in kernel BTF\n",
+		if (kfunc_id == -ESRCH && ext->is_weak)
+			return 0;
+		pr_warn("extern (func ksym) '%s': not found in kernel or module BTFs\n",
 			ext->name);
 		return kfunc_id;
 	}
 
-	if (kern_btf != obj->btf_vmlinux) {
-		pr_warn("extern (func ksym) '%s': function in kernel module is not supported\n",
-			ext->name);
-		return -ENOTSUP;
-	}
-
 	kern_func = btf__type_by_id(kern_btf, kfunc_id);
 	kfunc_proto_id = kern_func->type;
 
@@ -6739,9 +7097,30 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj,
 		return -EINVAL;
 	}
 
+	/* set index for module BTF fd in fd_array, if unset */
+	if (mod_btf && !mod_btf->fd_array_idx) {
+		/* insn->off is s16 */
+		if (obj->fd_array_cnt == INT16_MAX) {
+			pr_warn("extern (func ksym) '%s': module BTF fd index %d too big to fit in bpf_insn offset\n",
+				ext->name, mod_btf->fd_array_idx);
+			return -E2BIG;
+		}
+		/* Cannot use index 0 for module BTF fd */
+		if (!obj->fd_array_cnt)
+			obj->fd_array_cnt = 1;
+
+		ret = libbpf_ensure_mem((void **)&obj->fd_array, &obj->fd_array_cap, sizeof(int),
+					obj->fd_array_cnt + 1);
+		if (ret)
+			return ret;
+		mod_btf->fd_array_idx = obj->fd_array_cnt;
+		/* we assume module BTF FD is always >0 */
+		obj->fd_array[obj->fd_array_cnt++] = mod_btf->fd;
+	}
+
 	ext->is_set = true;
-	ext->ksym.kernel_btf_obj_fd = kern_btf_fd;
 	ext->ksym.kernel_btf_id = kfunc_id;
+	ext->ksym.btf_fd_idx = mod_btf ? mod_btf->fd_array_idx : 0;
 	pr_debug("extern (func ksym) '%s': resolved to kernel [%d]\n",
 		 ext->name, kfunc_id);
 
@@ -6807,8 +7186,7 @@ static int bpf_object__resolve_externs(struct bpf_object *obj,
 			if (err)
 				return err;
 			pr_debug("extern (kcfg) %s=0x%x\n", ext->name, kver);
-		} else if (ext->type == EXT_KCFG &&
-			   strncmp(ext->name, "CONFIG_", 7) == 0) {
+		} else if (ext->type == EXT_KCFG && str_has_pfx(ext->name, "CONFIG_")) {
 			need_config = true;
 		} else if (ext->type == EXT_KSYM) {
 			if (ext->ksym.type_id)
@@ -6902,6 +7280,9 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 			err = bpf_gen__finish(obj->gen_loader);
 	}
 
+	/* clean up fd_array */
+	zfree(&obj->fd_array);
+
 	/* clean up module BTFs */
 	for (i = 0; i < obj->btf_module_cnt; i++) {
 		close(obj->btf_modules[i].fd);
@@ -6926,7 +7307,7 @@ out:
 		if (obj->maps[i].pinned && !obj->maps[i].reused)
 			bpf_map__unpin(&obj->maps[i], NULL);
 
-	bpf_object__unload(obj);
+	bpf_object_unload(obj);
 	pr_warn("failed to load object '%s'\n", obj->path);
 	return libbpf_err(err);
 }
@@ -6992,8 +7373,7 @@ static int check_path(const char *path)
 	return err;
 }
 
-int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
-			      int instance)
+static int bpf_program_pin_instance(struct bpf_program *prog, const char *path, int instance)
 {
 	char *cp, errmsg[STRERR_BUFSIZE];
 	int err;
@@ -7028,8 +7408,7 @@ 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)
+static int bpf_program_unpin_instance(struct bpf_program *prog, const char *path, int instance)
 {
 	int err;
 
@@ -7057,6 +7436,12 @@ int bpf_program__unpin_instance(struct bpf_program *prog, const char *path,
 	return 0;
 }
 
+__attribute__((alias("bpf_program_pin_instance")))
+int bpf_object__pin_instance(struct bpf_program *prog, const char *path, int instance);
+
+__attribute__((alias("bpf_program_unpin_instance")))
+int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, int instance);
+
 int bpf_program__pin(struct bpf_program *prog, const char *path)
 {
 	int i, err;
@@ -7081,7 +7466,7 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 
 	if (prog->instances.nr == 1) {
 		/* don't create subdirs when pinning single instance */
-		return bpf_program__pin_instance(prog, path, 0);
+		return bpf_program_pin_instance(prog, path, 0);
 	}
 
 	for (i = 0; i < prog->instances.nr; i++) {
@@ -7097,7 +7482,7 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 			goto err_unpin;
 		}
 
-		err = bpf_program__pin_instance(prog, buf, i);
+		err = bpf_program_pin_instance(prog, buf, i);
 		if (err)
 			goto err_unpin;
 	}
@@ -7115,7 +7500,7 @@ err_unpin:
 		else if (len >= PATH_MAX)
 			continue;
 
-		bpf_program__unpin_instance(prog, buf, i);
+		bpf_program_unpin_instance(prog, buf, i);
 	}
 
 	rmdir(path);
@@ -7143,7 +7528,7 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path)
 
 	if (prog->instances.nr == 1) {
 		/* don't create subdirs when pinning single instance */
-		return bpf_program__unpin_instance(prog, path, 0);
+		return bpf_program_unpin_instance(prog, path, 0);
 	}
 
 	for (i = 0; i < prog->instances.nr; i++) {
@@ -7156,7 +7541,7 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path)
 		else if (len >= PATH_MAX)
 			return libbpf_err(-ENAMETOOLONG);
 
-		err = bpf_program__unpin_instance(prog, buf, i);
+		err = bpf_program_unpin_instance(prog, buf, i);
 		if (err)
 			return err;
 	}
@@ -7517,6 +7902,7 @@ static void bpf_map__destroy(struct bpf_map *map)
 	}
 
 	zfree(&map->name);
+	zfree(&map->real_name);
 	zfree(&map->pin_path);
 
 	if (map->fd >= 0)
@@ -7535,7 +7921,7 @@ void bpf_object__close(struct bpf_object *obj)
 
 	bpf_gen__free(obj->gen_loader);
 	bpf_object__elf_finish(obj);
-	bpf_object__unload(obj);
+	bpf_object_unload(obj);
 	btf__free(obj->btf);
 	btf_ext__free(obj->btf_ext);
 
@@ -7564,6 +7950,10 @@ struct bpf_object *
 bpf_object__next(struct bpf_object *prev)
 {
 	struct bpf_object *next;
+	bool strict = (libbpf_mode & LIBBPF_STRICT_NO_OBJECT_LIST);
+
+	if (strict)
+		return NULL;
 
 	if (!prev)
 		next = list_first_entry(&bpf_objects_list,
@@ -7670,6 +8060,12 @@ __bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj,
 struct bpf_program *
 bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj)
 {
+	return bpf_object__next_program(obj, prev);
+}
+
+struct bpf_program *
+bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prev)
+{
 	struct bpf_program *prog = prev;
 
 	do {
@@ -7682,6 +8078,12 @@ bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj)
 struct bpf_program *
 bpf_program__prev(struct bpf_program *next, const struct bpf_object *obj)
 {
+	return bpf_object__prev_program(obj, next);
+}
+
+struct bpf_program *
+bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *next)
+{
 	struct bpf_program *prog = next;
 
 	do {
@@ -7762,6 +8164,16 @@ size_t bpf_program__size(const struct bpf_program *prog)
 	return prog->insns_cnt * BPF_INSN_SZ;
 }
 
+const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog)
+{
+	return prog->insns;
+}
+
+size_t bpf_program__insn_cnt(const struct bpf_program *prog)
+{
+	return prog->insns_cnt;
+}
+
 int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
 			  bpf_program_prep_t prep)
 {
@@ -7869,223 +8281,145 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 	prog->expected_attach_type = type;
 }
 
-#define BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype_optional,	    \
-			  attachable, attach_btf)			    \
-	{								    \
-		.sec = string,						    \
-		.len = sizeof(string) - 1,				    \
-		.prog_type = ptype,					    \
-		.expected_attach_type = eatype,				    \
-		.is_exp_attach_type_optional = eatype_optional,		    \
-		.is_attachable = attachable,				    \
-		.is_attach_btf = attach_btf,				    \
-	}
-
-/* Programs that can NOT be attached. */
-#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0)
-
-/* Programs that can be attached. */
-#define BPF_APROG_SEC(string, ptype, atype) \
-	BPF_PROG_SEC_IMPL(string, ptype, atype, true, 1, 0)
-
-/* Programs that must specify expected attach type at load time. */
-#define BPF_EAPROG_SEC(string, ptype, eatype) \
-	BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 1, 0)
-
-/* Programs that use BTF to identify attach point */
-#define BPF_PROG_BTF(string, ptype, eatype) \
-	BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 0, 1)
-
-/* Programs that can be attached but attach type can't be identified by section
- * name. Kept for backward compatibility.
- */
-#define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype)
-
-#define SEC_DEF(sec_pfx, ptype, ...) {					    \
+#define SEC_DEF(sec_pfx, ptype, atype, flags, ...) {			    \
 	.sec = sec_pfx,							    \
-	.len = sizeof(sec_pfx) - 1,					    \
 	.prog_type = BPF_PROG_TYPE_##ptype,				    \
+	.expected_attach_type = atype,					    \
+	.cookie = (long)(flags),					    \
+	.preload_fn = libbpf_preload_prog,				    \
 	__VA_ARGS__							    \
 }
 
-static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
-				      struct bpf_program *prog);
-static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
-				  struct bpf_program *prog);
-static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
-				      struct bpf_program *prog);
-static struct bpf_link *attach_trace(const struct bpf_sec_def *sec,
-				     struct bpf_program *prog);
-static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
-				   struct bpf_program *prog);
-static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
-				    struct bpf_program *prog);
+static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie);
+static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie);
+static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie);
+static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie);
+static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie);
+static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie);
 
 static const struct bpf_sec_def section_defs[] = {
-	BPF_PROG_SEC("socket",			BPF_PROG_TYPE_SOCKET_FILTER),
-	BPF_EAPROG_SEC("sk_reuseport/migrate",	BPF_PROG_TYPE_SK_REUSEPORT,
-						BPF_SK_REUSEPORT_SELECT_OR_MIGRATE),
-	BPF_EAPROG_SEC("sk_reuseport",		BPF_PROG_TYPE_SK_REUSEPORT,
-						BPF_SK_REUSEPORT_SELECT),
-	SEC_DEF("kprobe/", KPROBE,
-		.attach_fn = attach_kprobe),
-	BPF_PROG_SEC("uprobe/",			BPF_PROG_TYPE_KPROBE),
-	SEC_DEF("kretprobe/", KPROBE,
-		.attach_fn = attach_kprobe),
-	BPF_PROG_SEC("uretprobe/",		BPF_PROG_TYPE_KPROBE),
-	BPF_PROG_SEC("classifier",		BPF_PROG_TYPE_SCHED_CLS),
-	BPF_PROG_SEC("action",			BPF_PROG_TYPE_SCHED_ACT),
-	SEC_DEF("tracepoint/", TRACEPOINT,
-		.attach_fn = attach_tp),
-	SEC_DEF("tp/", TRACEPOINT,
-		.attach_fn = attach_tp),
-	SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT,
-		.attach_fn = attach_raw_tp),
-	SEC_DEF("raw_tp/", RAW_TRACEPOINT,
-		.attach_fn = attach_raw_tp),
-	SEC_DEF("tp_btf/", TRACING,
-		.expected_attach_type = BPF_TRACE_RAW_TP,
-		.is_attach_btf = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("fentry/", TRACING,
-		.expected_attach_type = BPF_TRACE_FENTRY,
-		.is_attach_btf = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("fmod_ret/", TRACING,
-		.expected_attach_type = BPF_MODIFY_RETURN,
-		.is_attach_btf = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("fexit/", TRACING,
-		.expected_attach_type = BPF_TRACE_FEXIT,
-		.is_attach_btf = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("fentry.s/", TRACING,
-		.expected_attach_type = BPF_TRACE_FENTRY,
-		.is_attach_btf = true,
-		.is_sleepable = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("fmod_ret.s/", TRACING,
-		.expected_attach_type = BPF_MODIFY_RETURN,
-		.is_attach_btf = true,
-		.is_sleepable = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("fexit.s/", TRACING,
-		.expected_attach_type = BPF_TRACE_FEXIT,
-		.is_attach_btf = true,
-		.is_sleepable = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("freplace/", EXT,
-		.is_attach_btf = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("lsm/", LSM,
-		.is_attach_btf = true,
-		.expected_attach_type = BPF_LSM_MAC,
-		.attach_fn = attach_lsm),
-	SEC_DEF("lsm.s/", LSM,
-		.is_attach_btf = true,
-		.is_sleepable = true,
-		.expected_attach_type = BPF_LSM_MAC,
-		.attach_fn = attach_lsm),
-	SEC_DEF("iter/", TRACING,
-		.expected_attach_type = BPF_TRACE_ITER,
-		.is_attach_btf = true,
-		.attach_fn = attach_iter),
-	SEC_DEF("syscall", SYSCALL,
-		.is_sleepable = true),
-	BPF_EAPROG_SEC("xdp_devmap/",		BPF_PROG_TYPE_XDP,
-						BPF_XDP_DEVMAP),
-	BPF_EAPROG_SEC("xdp_cpumap/",		BPF_PROG_TYPE_XDP,
-						BPF_XDP_CPUMAP),
-	BPF_APROG_SEC("xdp",			BPF_PROG_TYPE_XDP,
-						BPF_XDP),
-	BPF_PROG_SEC("perf_event",		BPF_PROG_TYPE_PERF_EVENT),
-	BPF_PROG_SEC("lwt_in",			BPF_PROG_TYPE_LWT_IN),
-	BPF_PROG_SEC("lwt_out",			BPF_PROG_TYPE_LWT_OUT),
-	BPF_PROG_SEC("lwt_xmit",		BPF_PROG_TYPE_LWT_XMIT),
-	BPF_PROG_SEC("lwt_seg6local",		BPF_PROG_TYPE_LWT_SEG6LOCAL),
-	BPF_APROG_SEC("cgroup_skb/ingress",	BPF_PROG_TYPE_CGROUP_SKB,
-						BPF_CGROUP_INET_INGRESS),
-	BPF_APROG_SEC("cgroup_skb/egress",	BPF_PROG_TYPE_CGROUP_SKB,
-						BPF_CGROUP_INET_EGRESS),
-	BPF_APROG_COMPAT("cgroup/skb",		BPF_PROG_TYPE_CGROUP_SKB),
-	BPF_EAPROG_SEC("cgroup/sock_create",	BPF_PROG_TYPE_CGROUP_SOCK,
-						BPF_CGROUP_INET_SOCK_CREATE),
-	BPF_EAPROG_SEC("cgroup/sock_release",	BPF_PROG_TYPE_CGROUP_SOCK,
-						BPF_CGROUP_INET_SOCK_RELEASE),
-	BPF_APROG_SEC("cgroup/sock",		BPF_PROG_TYPE_CGROUP_SOCK,
-						BPF_CGROUP_INET_SOCK_CREATE),
-	BPF_EAPROG_SEC("cgroup/post_bind4",	BPF_PROG_TYPE_CGROUP_SOCK,
-						BPF_CGROUP_INET4_POST_BIND),
-	BPF_EAPROG_SEC("cgroup/post_bind6",	BPF_PROG_TYPE_CGROUP_SOCK,
-						BPF_CGROUP_INET6_POST_BIND),
-	BPF_APROG_SEC("cgroup/dev",		BPF_PROG_TYPE_CGROUP_DEVICE,
-						BPF_CGROUP_DEVICE),
-	BPF_APROG_SEC("sockops",		BPF_PROG_TYPE_SOCK_OPS,
-						BPF_CGROUP_SOCK_OPS),
-	BPF_APROG_SEC("sk_skb/stream_parser",	BPF_PROG_TYPE_SK_SKB,
-						BPF_SK_SKB_STREAM_PARSER),
-	BPF_APROG_SEC("sk_skb/stream_verdict",	BPF_PROG_TYPE_SK_SKB,
-						BPF_SK_SKB_STREAM_VERDICT),
-	BPF_APROG_COMPAT("sk_skb",		BPF_PROG_TYPE_SK_SKB),
-	BPF_APROG_SEC("sk_msg",			BPF_PROG_TYPE_SK_MSG,
-						BPF_SK_MSG_VERDICT),
-	BPF_APROG_SEC("lirc_mode2",		BPF_PROG_TYPE_LIRC_MODE2,
-						BPF_LIRC_MODE2),
-	BPF_APROG_SEC("flow_dissector",		BPF_PROG_TYPE_FLOW_DISSECTOR,
-						BPF_FLOW_DISSECTOR),
-	BPF_EAPROG_SEC("cgroup/bind4",		BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET4_BIND),
-	BPF_EAPROG_SEC("cgroup/bind6",		BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET6_BIND),
-	BPF_EAPROG_SEC("cgroup/connect4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET4_CONNECT),
-	BPF_EAPROG_SEC("cgroup/connect6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET6_CONNECT),
-	BPF_EAPROG_SEC("cgroup/sendmsg4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_UDP4_SENDMSG),
-	BPF_EAPROG_SEC("cgroup/sendmsg6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_UDP6_SENDMSG),
-	BPF_EAPROG_SEC("cgroup/recvmsg4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_UDP4_RECVMSG),
-	BPF_EAPROG_SEC("cgroup/recvmsg6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_UDP6_RECVMSG),
-	BPF_EAPROG_SEC("cgroup/getpeername4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET4_GETPEERNAME),
-	BPF_EAPROG_SEC("cgroup/getpeername6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET6_GETPEERNAME),
-	BPF_EAPROG_SEC("cgroup/getsockname4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET4_GETSOCKNAME),
-	BPF_EAPROG_SEC("cgroup/getsockname6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET6_GETSOCKNAME),
-	BPF_EAPROG_SEC("cgroup/sysctl",		BPF_PROG_TYPE_CGROUP_SYSCTL,
-						BPF_CGROUP_SYSCTL),
-	BPF_EAPROG_SEC("cgroup/getsockopt",	BPF_PROG_TYPE_CGROUP_SOCKOPT,
-						BPF_CGROUP_GETSOCKOPT),
-	BPF_EAPROG_SEC("cgroup/setsockopt",	BPF_PROG_TYPE_CGROUP_SOCKOPT,
-						BPF_CGROUP_SETSOCKOPT),
-	BPF_PROG_SEC("struct_ops",		BPF_PROG_TYPE_STRUCT_OPS),
-	BPF_EAPROG_SEC("sk_lookup/",		BPF_PROG_TYPE_SK_LOOKUP,
-						BPF_SK_LOOKUP),
+	SEC_DEF("socket",		SOCKET_FILTER, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("sk_reuseport/migrate",	SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("sk_reuseport",		SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("kprobe/",		KPROBE,	0, SEC_NONE, attach_kprobe),
+	SEC_DEF("uprobe/",		KPROBE,	0, SEC_NONE),
+	SEC_DEF("kretprobe/",		KPROBE, 0, SEC_NONE, attach_kprobe),
+	SEC_DEF("uretprobe/",		KPROBE, 0, SEC_NONE),
+	SEC_DEF("tc",			SCHED_CLS, 0, SEC_NONE),
+	SEC_DEF("classifier",		SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("action",		SCHED_ACT, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("tracepoint/",		TRACEPOINT, 0, SEC_NONE, attach_tp),
+	SEC_DEF("tp/",			TRACEPOINT, 0, SEC_NONE, attach_tp),
+	SEC_DEF("raw_tracepoint/",	RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp),
+	SEC_DEF("raw_tp/",		RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp),
+	SEC_DEF("raw_tracepoint.w/",	RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp),
+	SEC_DEF("raw_tp.w/",		RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp),
+	SEC_DEF("tp_btf/",		TRACING, BPF_TRACE_RAW_TP, SEC_ATTACH_BTF, attach_trace),
+	SEC_DEF("fentry/",		TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF, attach_trace),
+	SEC_DEF("fmod_ret/",		TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF, attach_trace),
+	SEC_DEF("fexit/",		TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF, attach_trace),
+	SEC_DEF("fentry.s/",		TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace),
+	SEC_DEF("fmod_ret.s/",		TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace),
+	SEC_DEF("fexit.s/",		TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace),
+	SEC_DEF("freplace/",		EXT, 0, SEC_ATTACH_BTF, attach_trace),
+	SEC_DEF("lsm/",			LSM, BPF_LSM_MAC, SEC_ATTACH_BTF, attach_lsm),
+	SEC_DEF("lsm.s/",		LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm),
+	SEC_DEF("iter/",		TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter),
+	SEC_DEF("syscall",		SYSCALL, 0, SEC_SLEEPABLE),
+	SEC_DEF("xdp_devmap/",		XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE),
+	SEC_DEF("xdp_cpumap/",		XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE),
+	SEC_DEF("xdp",			XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("perf_event",		PERF_EVENT, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("lwt_in",		LWT_IN, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("lwt_out",		LWT_OUT, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("lwt_xmit",		LWT_XMIT, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("lwt_seg6local",	LWT_SEG6LOCAL, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup_skb/ingress",	CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup_skb/egress",	CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/skb",		CGROUP_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/sock_create",	CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/sock_release",	CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/sock",		CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/post_bind4",	CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/post_bind6",	CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/dev",		CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("sockops",		SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("sk_skb/stream_parser",	SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("sk_skb",		SK_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("sk_msg",		SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("lirc_mode2",		LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("flow_dissector",	FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/bind4",		CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/bind6",		CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/connect4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/connect6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/sendmsg4",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/sendmsg6",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/recvmsg4",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/recvmsg6",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/getpeername4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/getpeername6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/getsockname4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/getsockname6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/sysctl",	CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/getsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/setsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("struct_ops+",		STRUCT_OPS, 0, SEC_NONE),
+	SEC_DEF("sk_lookup",		SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
 };
 
-#undef BPF_PROG_SEC_IMPL
-#undef BPF_PROG_SEC
-#undef BPF_APROG_SEC
-#undef BPF_EAPROG_SEC
-#undef BPF_APROG_COMPAT
-#undef SEC_DEF
-
 #define MAX_TYPE_NAME_SIZE 32
 
 static const struct bpf_sec_def *find_sec_def(const char *sec_name)
 {
-	int i, n = ARRAY_SIZE(section_defs);
+	const struct bpf_sec_def *sec_def;
+	enum sec_def_flags sec_flags;
+	int i, n = ARRAY_SIZE(section_defs), len;
+	bool strict = libbpf_mode & LIBBPF_STRICT_SEC_NAME;
 
 	for (i = 0; i < n; i++) {
-		if (strncmp(sec_name,
-			    section_defs[i].sec, section_defs[i].len))
+		sec_def = &section_defs[i];
+		sec_flags = sec_def->cookie;
+		len = strlen(sec_def->sec);
+
+		/* "type/" always has to have proper SEC("type/extras") form */
+		if (sec_def->sec[len - 1] == '/') {
+			if (str_has_pfx(sec_name, sec_def->sec))
+				return sec_def;
 			continue;
-		return &section_defs[i];
+		}
+
+		/* "type+" means it can be either exact SEC("type") or
+		 * well-formed SEC("type/extras") with proper '/' separator
+		 */
+		if (sec_def->sec[len - 1] == '+') {
+			len--;
+			/* not even a prefix */
+			if (strncmp(sec_name, sec_def->sec, len) != 0)
+				continue;
+			/* exact match or has '/' separator */
+			if (sec_name[len] == '\0' || sec_name[len] == '/')
+				return sec_def;
+			continue;
+		}
+
+		/* SEC_SLOPPY_PFX definitions are allowed to be just prefix
+		 * matches, unless strict section name mode
+		 * (LIBBPF_STRICT_SEC_NAME) is enabled, in which case the
+		 * match has to be exact.
+		 */
+		if ((sec_flags & SEC_SLOPPY_PFX) && !strict)  {
+			if (str_has_pfx(sec_name, sec_def->sec))
+				return sec_def;
+			continue;
+		}
+
+		/* Definitions not marked SEC_SLOPPY_PFX (e.g.,
+		 * SEC("syscall")) are exact matches in both modes.
+		 */
+		if (strcmp(sec_name, sec_def->sec) == 0)
+			return sec_def;
 	}
 	return NULL;
 }
@@ -8102,8 +8436,15 @@ static char *libbpf_get_type_names(bool attach_type)
 	buf[0] = '\0';
 	/* Forge string buf with all available names */
 	for (i = 0; i < ARRAY_SIZE(section_defs); i++) {
-		if (attach_type && !section_defs[i].is_attachable)
-			continue;
+		const struct bpf_sec_def *sec_def = &section_defs[i];
+
+		if (attach_type) {
+			if (sec_def->preload_fn != libbpf_preload_prog)
+				continue;
+
+			if (!(sec_def->cookie & SEC_ATTACHABLE))
+				continue;
+		}
 
 		if (strlen(buf) + strlen(section_defs[i].sec) + 2 > len) {
 			free(buf);
@@ -8162,7 +8503,7 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
 
 /* Collect the reloc from ELF and populate the st_ops->progs[] */
 static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
-					    GElf_Shdr *shdr, Elf_Data *data)
+					    Elf64_Shdr *shdr, Elf_Data *data)
 {
 	const struct btf_member *member;
 	struct bpf_struct_ops *st_ops;
@@ -8170,58 +8511,58 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 	unsigned int shdr_idx;
 	const struct btf *btf;
 	struct bpf_map *map;
-	Elf_Data *symbols;
 	unsigned int moff, insn_idx;
 	const char *name;
 	__u32 member_idx;
-	GElf_Sym sym;
-	GElf_Rel rel;
+	Elf64_Sym *sym;
+	Elf64_Rel *rel;
 	int i, nrels;
 
-	symbols = obj->efile.symbols;
 	btf = obj->btf;
 	nrels = shdr->sh_size / shdr->sh_entsize;
 	for (i = 0; i < nrels; i++) {
-		if (!gelf_getrel(data, i, &rel)) {
+		rel = elf_rel_by_idx(data, i);
+		if (!rel) {
 			pr_warn("struct_ops reloc: failed to get %d reloc\n", i);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
+		sym = elf_sym_by_idx(obj, ELF64_R_SYM(rel->r_info));
+		if (!sym) {
 			pr_warn("struct_ops reloc: symbol %zx not found\n",
-				(size_t)GELF_R_SYM(rel.r_info));
+				(size_t)ELF64_R_SYM(rel->r_info));
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		name = elf_sym_str(obj, sym.st_name) ?: "<?>";
-		map = find_struct_ops_map_by_offset(obj, rel.r_offset);
+		name = elf_sym_str(obj, sym->st_name) ?: "<?>";
+		map = find_struct_ops_map_by_offset(obj, rel->r_offset);
 		if (!map) {
-			pr_warn("struct_ops reloc: cannot find map at rel.r_offset %zu\n",
-				(size_t)rel.r_offset);
+			pr_warn("struct_ops reloc: cannot find map at rel->r_offset %zu\n",
+				(size_t)rel->r_offset);
 			return -EINVAL;
 		}
 
-		moff = rel.r_offset - map->sec_offset;
-		shdr_idx = sym.st_shndx;
+		moff = rel->r_offset - map->sec_offset;
+		shdr_idx = sym->st_shndx;
 		st_ops = map->st_ops;
-		pr_debug("struct_ops reloc %s: for %lld value %lld shdr_idx %u rel.r_offset %zu map->sec_offset %zu name %d (\'%s\')\n",
+		pr_debug("struct_ops reloc %s: for %lld value %lld shdr_idx %u rel->r_offset %zu map->sec_offset %zu name %d (\'%s\')\n",
 			 map->name,
-			 (long long)(rel.r_info >> 32),
-			 (long long)sym.st_value,
-			 shdr_idx, (size_t)rel.r_offset,
-			 map->sec_offset, sym.st_name, name);
+			 (long long)(rel->r_info >> 32),
+			 (long long)sym->st_value,
+			 shdr_idx, (size_t)rel->r_offset,
+			 map->sec_offset, sym->st_name, name);
 
 		if (shdr_idx >= SHN_LORESERVE) {
-			pr_warn("struct_ops reloc %s: rel.r_offset %zu shdr_idx %u unsupported non-static function\n",
-				map->name, (size_t)rel.r_offset, shdr_idx);
+			pr_warn("struct_ops reloc %s: rel->r_offset %zu shdr_idx %u unsupported non-static function\n",
+				map->name, (size_t)rel->r_offset, shdr_idx);
 			return -LIBBPF_ERRNO__RELOC;
 		}
-		if (sym.st_value % BPF_INSN_SZ) {
+		if (sym->st_value % BPF_INSN_SZ) {
 			pr_warn("struct_ops reloc %s: invalid target program offset %llu\n",
-				map->name, (unsigned long long)sym.st_value);
+				map->name, (unsigned long long)sym->st_value);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
-		insn_idx = sym.st_value / BPF_INSN_SZ;
+		insn_idx = sym->st_value / BPF_INSN_SZ;
 
 		member = find_member_by_offset(st_ops->type, moff * 8);
 		if (!member) {
@@ -8245,35 +8586,37 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 			return -EINVAL;
 		}
 
-		if (prog->type == BPF_PROG_TYPE_UNSPEC) {
-			const struct bpf_sec_def *sec_def;
-
-			sec_def = find_sec_def(prog->sec_name);
-			if (sec_def &&
-			    sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) {
-				/* for pr_warn */
-				prog->type = sec_def->prog_type;
-				goto invalid_prog;
-			}
+		/* prevent the use of BPF prog with invalid type */
+		if (prog->type != BPF_PROG_TYPE_STRUCT_OPS) {
+			pr_warn("struct_ops reloc %s: prog %s is not struct_ops BPF program\n",
+				map->name, prog->name);
+			return -EINVAL;
+		}
 
-			prog->type = BPF_PROG_TYPE_STRUCT_OPS;
+		/* if we haven't yet processed this BPF program, record proper
+		 * attach_btf_id and member_idx
+		 */
+		if (!prog->attach_btf_id) {
 			prog->attach_btf_id = st_ops->type_id;
 			prog->expected_attach_type = member_idx;
-		} else if (prog->type != BPF_PROG_TYPE_STRUCT_OPS ||
-			   prog->attach_btf_id != st_ops->type_id ||
-			   prog->expected_attach_type != member_idx) {
-			goto invalid_prog;
 		}
+
+		/* struct_ops BPF prog can be re-used between multiple
+		 * .struct_ops as long as it's the same struct_ops struct
+		 * definition and the same function pointer field
+		 */
+		if (prog->attach_btf_id != st_ops->type_id ||
+		    prog->expected_attach_type != member_idx) {
+			pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n",
+				map->name, prog->name, prog->sec_name, prog->type,
+				prog->attach_btf_id, prog->expected_attach_type, name);
+			return -EINVAL;
+		}
+
 		st_ops->progs[member_idx] = prog;
 	}
 
 	return 0;
-
-invalid_prog:
-	pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n",
-		map->name, prog->name, prog->sec_name, prog->type,
-		prog->attach_btf_id, prog->expected_attach_type, name);
-	return -EINVAL;
 }
 
 #define BTF_TRACE_PREFIX "btf_trace_"
@@ -8353,28 +8696,27 @@ int libbpf_find_vmlinux_btf_id(const char *name,
 
 static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
 {
-	struct bpf_prog_info_linear *info_linear;
-	struct bpf_prog_info *info;
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
 	struct btf *btf;
 	int err;
 
-	info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0);
-	err = libbpf_get_error(info_linear);
+	err = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len);
 	if (err) {
-		pr_warn("failed get_prog_info_linear for FD %d\n",
-			attach_prog_fd);
+		pr_warn("failed bpf_obj_get_info_by_fd for FD %d: %d\n",
+			attach_prog_fd, err);
 		return err;
 	}
 
 	err = -EINVAL;
-	info = &info_linear->info;
-	if (!info->btf_id) {
+	if (!info.btf_id) {
 		pr_warn("The target program doesn't have BTF\n");
 		goto out;
 	}
-	btf = btf__load_from_kernel_by_id(info->btf_id);
-	if (libbpf_get_error(btf)) {
-		pr_warn("Failed to get BTF of the program\n");
+	btf = btf__load_from_kernel_by_id(info.btf_id);
+	err = libbpf_get_error(btf);
+	if (err) {
+		pr_warn("Failed to get BTF %d of the program: %d\n", info.btf_id, err);
 		goto out;
 	}
 	err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
@@ -8384,7 +8726,6 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
 		goto out;
 	}
 out:
-	free(info_linear);
 	return err;
 }
 
@@ -8425,32 +8766,12 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name,
 	return -ESRCH;
 }
 
-static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id)
+static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name,
+				     int *btf_obj_fd, int *btf_type_id)
 {
 	enum bpf_attach_type attach_type = prog->expected_attach_type;
 	__u32 attach_prog_fd = prog->attach_prog_fd;
-	const char *name = prog->sec_name, *attach_name;
-	const struct bpf_sec_def *sec = NULL;
-	int i, err = 0;
-
-	if (!name)
-		return -EINVAL;
-
-	for (i = 0; i < ARRAY_SIZE(section_defs); i++) {
-		if (!section_defs[i].is_attach_btf)
-			continue;
-		if (strncmp(name, section_defs[i].sec, section_defs[i].len))
-			continue;
-
-		sec = &section_defs[i];
-		break;
-	}
-
-	if (!sec) {
-		pr_warn("failed to identify BTF ID based on ELF section name '%s'\n", name);
-		return -ESRCH;
-	}
-	attach_name = name + sec->len;
+	int err = 0;
 
 	/* BPF program's BTF ID */
 	if (attach_prog_fd) {
@@ -8484,27 +8805,30 @@ int libbpf_attach_type_by_name(const char *name,
 			       enum bpf_attach_type *attach_type)
 {
 	char *type_names;
-	int i;
+	const struct bpf_sec_def *sec_def;
 
 	if (!name)
 		return libbpf_err(-EINVAL);
 
-	for (i = 0; i < ARRAY_SIZE(section_defs); i++) {
-		if (strncmp(name, section_defs[i].sec, section_defs[i].len))
-			continue;
-		if (!section_defs[i].is_attachable)
-			return libbpf_err(-EINVAL);
-		*attach_type = section_defs[i].expected_attach_type;
-		return 0;
-	}
-	pr_debug("failed to guess attach type based on ELF section name '%s'\n", name);
-	type_names = libbpf_get_type_names(true);
-	if (type_names != NULL) {
-		pr_debug("attachable section(type) names are:%s\n", type_names);
-		free(type_names);
+	sec_def = find_sec_def(name);
+	if (!sec_def) {
+		pr_debug("failed to guess attach type based on ELF section name '%s'\n", name);
+		type_names = libbpf_get_type_names(true);
+		if (type_names != NULL) {
+			pr_debug("attachable section(type) names are:%s\n", type_names);
+			free(type_names);
+		}
+
+		return libbpf_err(-EINVAL);
 	}
 
-	return libbpf_err(-EINVAL);
+	if (sec_def->preload_fn != libbpf_preload_prog)
+		return libbpf_err(-EINVAL);
+	if (!(sec_def->cookie & SEC_ATTACHABLE))
+		return libbpf_err(-EINVAL);
+
+	*attach_type = sec_def->expected_attach_type;
+	return 0;
 }
 
 int bpf_map__fd(const struct bpf_map *map)
@@ -8517,9 +8841,30 @@ const struct bpf_map_def *bpf_map__def(const struct bpf_map *map)
 	return map ? &map->def : libbpf_err_ptr(-EINVAL);
 }
 
+static bool map_uses_real_name(const struct bpf_map *map)
+{
+	/* Since libbpf started to support custom .data.* and .rodata.* maps,
+	 * their user-visible name differs from kernel-visible name. Users see
+	 * such map's corresponding ELF section name as a map name.
+	 * This check distinguishes .data/.rodata from .data.* and .rodata.*
+	 * maps to know which name has to be returned to the user.
+	 */
+	if (map->libbpf_type == LIBBPF_MAP_DATA && strcmp(map->real_name, DATA_SEC) != 0)
+		return true;
+	if (map->libbpf_type == LIBBPF_MAP_RODATA && strcmp(map->real_name, RODATA_SEC) != 0)
+		return true;
+	return false;
+}
+
 const char *bpf_map__name(const struct bpf_map *map)
 {
-	return map ? map->name : NULL;
+	if (!map)
+		return NULL;
+
+	if (map_uses_real_name(map))
+		return map->real_name;
+
+	return map->name;
 }
 
 enum bpf_map_type bpf_map__type(const struct bpf_map *map)
@@ -8548,6 +8893,19 @@ int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags)
 	return 0;
 }
 
+__u64 bpf_map__map_extra(const struct bpf_map *map)
+{
+	return map->map_extra;
+}
+
+int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra)
+{
+	if (map->fd >= 0)
+		return libbpf_err(-EBUSY);
+	map->map_extra = map_extra;
+	return 0;
+}
+
 __u32 bpf_map__numa_node(const struct bpf_map *map)
 {
 	return map->numa_node;
@@ -8702,6 +9060,12 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i)
 struct bpf_map *
 bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj)
 {
+	return bpf_object__next_map(obj, prev);
+}
+
+struct bpf_map *
+bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev)
+{
 	if (prev == NULL)
 		return obj->maps;
 
@@ -8711,6 +9075,12 @@ bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj)
 struct bpf_map *
 bpf_map__prev(const struct bpf_map *next, const struct bpf_object *obj)
 {
+	return bpf_object__prev_map(obj, next);
+}
+
+struct bpf_map *
+bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *next)
+{
 	if (next == NULL) {
 		if (!obj->nr_maps)
 			return NULL;
@@ -8726,7 +9096,22 @@ bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name)
 	struct bpf_map *pos;
 
 	bpf_object__for_each_map(pos, obj) {
-		if (pos->name && !strcmp(pos->name, name))
+		/* if it's a special internal map name (which always starts
+		 * with dot) then check if that special name matches the
+		 * real map name (ELF section name)
+		 */
+		if (name[0] == '.') {
+			if (pos->real_name && strcmp(pos->real_name, name) == 0)
+				return pos;
+			continue;
+		}
+		/* otherwise map name has to be an exact match */
+		if (map_uses_real_name(pos)) {
+			if (strcmp(pos->real_name, name) == 0)
+				return pos;
+			continue;
+		}
+		if (strcmp(pos->name, name) == 0)
 			return pos;
 	}
 	return errno = ENOENT, NULL;
@@ -8991,8 +9376,15 @@ int bpf_link__unpin(struct bpf_link *link)
 struct bpf_link_perf {
 	struct bpf_link link;
 	int perf_event_fd;
+	/* legacy kprobe support: keep track of probe identifier and type */
+	char *legacy_probe_name;
+	bool legacy_is_kprobe;
+	bool legacy_is_retprobe;
 };
 
+static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe);
+static int remove_uprobe_event_legacy(const char *probe_name, bool retprobe);
+
 static int bpf_link_perf_detach(struct bpf_link *link)
 {
 	struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
@@ -9005,17 +9397,29 @@ static int bpf_link_perf_detach(struct bpf_link *link)
 		close(perf_link->perf_event_fd);
 	close(link->fd);
 
-	return libbpf_err(err);
+	/* legacy uprobe/kprobe needs to be removed after perf event fd closure */
+	if (perf_link->legacy_probe_name) {
+		if (perf_link->legacy_is_kprobe) {
+			err = remove_kprobe_event_legacy(perf_link->legacy_probe_name,
+							 perf_link->legacy_is_retprobe);
+		} else {
+			err = remove_uprobe_event_legacy(perf_link->legacy_probe_name,
+							 perf_link->legacy_is_retprobe);
+		}
+	}
+
+	return err;
 }
 
 static void bpf_link_perf_dealloc(struct bpf_link *link)
 {
 	struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
 
+	free(perf_link->legacy_probe_name);
 	free(perf_link);
 }
 
-struct bpf_link *bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd,
+struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd,
 						     const struct bpf_perf_event_opts *opts)
 {
 	char errmsg[STRERR_BUFSIZE];
@@ -9090,7 +9494,7 @@ err_out:
 	return libbpf_err_ptr(err);
 }
 
-struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pfd)
+struct bpf_link *bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd)
 {
 	return bpf_program__attach_perf_event_opts(prog, pfd, NULL);
 }
@@ -9207,16 +9611,110 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
 	return pfd;
 }
 
+static int append_to_file(const char *file, const char *fmt, ...)
+{
+	int fd, n, err = 0;
+	va_list ap;
+
+	fd = open(file, O_WRONLY | O_APPEND | O_CLOEXEC, 0);
+	if (fd < 0)
+		return -errno;
+
+	va_start(ap, fmt);
+	n = vdprintf(fd, fmt, ap);
+	va_end(ap);
+
+	if (n < 0)
+		err = -errno;
+
+	close(fd);
+	return err;
+}
+
+static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz,
+					 const char *kfunc_name, size_t offset)
+{
+	snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), kfunc_name, offset);
+}
+
+static int add_kprobe_event_legacy(const char *probe_name, bool retprobe,
+				   const char *kfunc_name, size_t offset)
+{
+	const char *file = "/sys/kernel/debug/tracing/kprobe_events";
+
+	return append_to_file(file, "%c:%s/%s %s+0x%zx",
+			      retprobe ? 'r' : 'p',
+			      retprobe ? "kretprobes" : "kprobes",
+			      probe_name, kfunc_name, offset);
+}
+
+static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe)
+{
+	const char *file = "/sys/kernel/debug/tracing/kprobe_events";
+
+	return append_to_file(file, "-:%s/%s", retprobe ? "kretprobes" : "kprobes", probe_name);
+}
+
+static int determine_kprobe_perf_type_legacy(const char *probe_name, bool retprobe)
+{
+	char file[256];
+
+	snprintf(file, sizeof(file),
+		 "/sys/kernel/debug/tracing/events/%s/%s/id",
+		 retprobe ? "kretprobes" : "kprobes", probe_name);
+
+	return parse_uint_from_file(file, "%d\n");
+}
+
+static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe,
+					 const char *kfunc_name, size_t offset, int pid)
+{
+	struct perf_event_attr attr = {};
+	char errmsg[STRERR_BUFSIZE];
+	int type, pfd, err;
+
+	err = add_kprobe_event_legacy(probe_name, retprobe, kfunc_name, offset);
+	if (err < 0) {
+		pr_warn("failed to add legacy kprobe event for '%s+0x%zx': %s\n",
+			kfunc_name, offset,
+			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+		return err;
+	}
+	type = determine_kprobe_perf_type_legacy(probe_name, retprobe);
+	if (type < 0) {
+		pr_warn("failed to determine legacy kprobe event id for '%s+0x%zx': %s\n",
+			kfunc_name, offset,
+			libbpf_strerror_r(type, errmsg, sizeof(errmsg)));
+		return type;
+	}
+	attr.size = sizeof(attr);
+	attr.config = type;
+	attr.type = PERF_TYPE_TRACEPOINT;
+
+	pfd = syscall(__NR_perf_event_open, &attr,
+		      pid < 0 ? -1 : pid, /* pid */
+		      pid == -1 ? 0 : -1, /* cpu */
+		      -1 /* group_fd */,  PERF_FLAG_FD_CLOEXEC);
+	if (pfd < 0) {
+		err = -errno;
+		pr_warn("legacy kprobe perf_event_open() failed: %s\n",
+			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+		return err;
+	}
+	return pfd;
+}
+
 struct bpf_link *
-bpf_program__attach_kprobe_opts(struct bpf_program *prog,
+bpf_program__attach_kprobe_opts(const struct bpf_program *prog,
 				const char *func_name,
 				const struct bpf_kprobe_opts *opts)
 {
 	DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts);
 	char errmsg[STRERR_BUFSIZE];
+	char *legacy_probe = NULL;
 	struct bpf_link *link;
-	unsigned long offset;
-	bool retprobe;
+	size_t offset;
+	bool retprobe, legacy;
 	int pfd, err;
 
 	if (!OPTS_VALID(opts, bpf_kprobe_opts))
@@ -9226,27 +9724,57 @@ bpf_program__attach_kprobe_opts(struct bpf_program *prog,
 	offset = OPTS_GET(opts, offset, 0);
 	pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0);
 
-	pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name,
-				    offset, -1 /* pid */, 0 /* ref_ctr_off */);
+	legacy = determine_kprobe_perf_type() < 0;
+	if (!legacy) {
+		pfd = perf_event_open_probe(false /* uprobe */, retprobe,
+					    func_name, offset,
+					    -1 /* pid */, 0 /* ref_ctr_off */);
+	} else {
+		char probe_name[256];
+
+		gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name),
+					     func_name, offset);
+
+		legacy_probe = strdup(func_name);
+		if (!legacy_probe)
+			return libbpf_err_ptr(-ENOMEM);
+
+		pfd = perf_event_kprobe_open_legacy(legacy_probe, retprobe, func_name,
+						    offset, -1 /* pid */);
+	}
 	if (pfd < 0) {
-		pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n",
-			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
-			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return libbpf_err_ptr(pfd);
+		err = -errno;
+		pr_warn("prog '%s': failed to create %s '%s+0x%zx' perf event: %s\n",
+			prog->name, retprobe ? "kretprobe" : "kprobe",
+			func_name, offset,
+			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+		goto err_out;
 	}
 	link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts);
 	err = libbpf_get_error(link);
 	if (err) {
 		close(pfd);
-		pr_warn("prog '%s': failed to attach to %s '%s': %s\n",
-			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
+		pr_warn("prog '%s': failed to attach to %s '%s+0x%zx': %s\n",
+			prog->name, retprobe ? "kretprobe" : "kprobe",
+			func_name, offset,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		return libbpf_err_ptr(err);
+		goto err_out;
 	}
+	if (legacy) {
+		struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
+
+		perf_link->legacy_probe_name = legacy_probe;
+		perf_link->legacy_is_kprobe = true;
+		perf_link->legacy_is_retprobe = retprobe;
+	}
+
 	return link;
+err_out:
+	free(legacy_probe);
+	return libbpf_err_ptr(err);
 }
 
-struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
+struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog,
 					    bool retprobe,
 					    const char *func_name)
 {
@@ -9257,8 +9785,7 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
 	return bpf_program__attach_kprobe_opts(prog, func_name, &opts);
 }
 
-static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
-				      struct bpf_program *prog)
+static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie)
 {
 	DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts);
 	unsigned long offset = 0;
@@ -9267,8 +9794,11 @@ static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
 	char *func;
 	int n, err;
 
-	func_name = prog->sec_name + sec->len;
-	opts.retprobe = strcmp(sec->sec, "kretprobe/") == 0;
+	opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe/");
+	if (opts.retprobe)
+		func_name = prog->sec_name + sizeof("kretprobe/") - 1;
+	else
+		func_name = prog->sec_name + sizeof("kprobe/") - 1;
 
 	n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset);
 	if (n < 1) {
@@ -9289,17 +9819,96 @@ static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
 	return link;
 }
 
+static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz,
+					 const char *binary_path, uint64_t offset)
+{
+	int i;
+
+	snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), binary_path, (size_t)offset);
+
+	/* sanitize binary_path in the probe name */
+	for (i = 0; buf[i]; i++) {
+		if (!isalnum(buf[i]))
+			buf[i] = '_';
+	}
+}
+
+static inline int add_uprobe_event_legacy(const char *probe_name, bool retprobe,
+					  const char *binary_path, size_t offset)
+{
+	const char *file = "/sys/kernel/debug/tracing/uprobe_events";
+
+	return append_to_file(file, "%c:%s/%s %s:0x%zx",
+			      retprobe ? 'r' : 'p',
+			      retprobe ? "uretprobes" : "uprobes",
+			      probe_name, binary_path, offset);
+}
+
+static inline int remove_uprobe_event_legacy(const char *probe_name, bool retprobe)
+{
+	const char *file = "/sys/kernel/debug/tracing/uprobe_events";
+
+	return append_to_file(file, "-:%s/%s", retprobe ? "uretprobes" : "uprobes", probe_name);
+}
+
+static int determine_uprobe_perf_type_legacy(const char *probe_name, bool retprobe)
+{
+	char file[512];
+
+	snprintf(file, sizeof(file),
+		 "/sys/kernel/debug/tracing/events/%s/%s/id",
+		 retprobe ? "uretprobes" : "uprobes", probe_name);
+
+	return parse_uint_from_file(file, "%d\n");
+}
+
+static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe,
+					 const char *binary_path, size_t offset, int pid)
+{
+	struct perf_event_attr attr;
+	int type, pfd, err;
+
+	err = add_uprobe_event_legacy(probe_name, retprobe, binary_path, offset);
+	if (err < 0) {
+		pr_warn("failed to add legacy uprobe event for %s:0x%zx: %d\n",
+			binary_path, (size_t)offset, err);
+		return err;
+	}
+	type = determine_uprobe_perf_type_legacy(probe_name, retprobe);
+	if (type < 0) {
+		pr_warn("failed to determine legacy uprobe event id for %s:0x%zx: %d\n",
+			binary_path, offset, err);
+		return type;
+	}
+
+	memset(&attr, 0, sizeof(attr));
+	attr.size = sizeof(attr);
+	attr.config = type;
+	attr.type = PERF_TYPE_TRACEPOINT;
+
+	pfd = syscall(__NR_perf_event_open, &attr,
+		      pid < 0 ? -1 : pid, /* pid */
+		      pid == -1 ? 0 : -1, /* cpu */
+		      -1 /* group_fd */,  PERF_FLAG_FD_CLOEXEC);
+	if (pfd < 0) {
+		err = -errno;
+		pr_warn("legacy uprobe perf_event_open() failed: %d\n", err);
+		return err;
+	}
+	return pfd;
+}
+
 LIBBPF_API struct bpf_link *
-bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid,
+bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid,
 				const char *binary_path, size_t func_offset,
 				const struct bpf_uprobe_opts *opts)
 {
 	DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts);
-	char errmsg[STRERR_BUFSIZE];
+	char errmsg[STRERR_BUFSIZE], *legacy_probe = NULL;
 	struct bpf_link *link;
 	size_t ref_ctr_off;
 	int pfd, err;
-	bool retprobe;
+	bool retprobe, legacy;
 
 	if (!OPTS_VALID(opts, bpf_uprobe_opts))
 		return libbpf_err_ptr(-EINVAL);
@@ -9308,15 +9917,35 @@ bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid,
 	ref_ctr_off = OPTS_GET(opts, ref_ctr_offset, 0);
 	pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0);
 
-	pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path,
-				    func_offset, pid, ref_ctr_off);
+	legacy = determine_uprobe_perf_type() < 0;
+	if (!legacy) {
+		pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path,
+					    func_offset, pid, ref_ctr_off);
+	} else {
+		char probe_name[512];
+
+		if (ref_ctr_off)
+			return libbpf_err_ptr(-EINVAL);
+
+		gen_uprobe_legacy_event_name(probe_name, sizeof(probe_name),
+					     binary_path, func_offset);
+
+		legacy_probe = strdup(probe_name);
+		if (!legacy_probe)
+			return libbpf_err_ptr(-ENOMEM);
+
+		pfd = perf_event_uprobe_open_legacy(legacy_probe, retprobe,
+						    binary_path, func_offset, pid);
+	}
 	if (pfd < 0) {
+		err = -errno;
 		pr_warn("prog '%s': failed to create %s '%s:0x%zx' perf event: %s\n",
 			prog->name, retprobe ? "uretprobe" : "uprobe",
 			binary_path, func_offset,
-			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return libbpf_err_ptr(pfd);
+			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+		goto err_out;
 	}
+
 	link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts);
 	err = libbpf_get_error(link);
 	if (err) {
@@ -9325,12 +9954,23 @@ bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid,
 			prog->name, retprobe ? "uretprobe" : "uprobe",
 			binary_path, func_offset,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		return libbpf_err_ptr(err);
+		goto err_out;
+	}
+	if (legacy) {
+		struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
+
+		perf_link->legacy_probe_name = legacy_probe;
+		perf_link->legacy_is_kprobe = false;
+		perf_link->legacy_is_retprobe = retprobe;
 	}
 	return link;
+err_out:
+	free(legacy_probe);
+	return libbpf_err_ptr(err);
+
 }
 
-struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
+struct bpf_link *bpf_program__attach_uprobe(const struct bpf_program *prog,
 					    bool retprobe, pid_t pid,
 					    const char *binary_path,
 					    size_t func_offset)
@@ -9390,7 +10030,7 @@ static int perf_event_open_tracepoint(const char *tp_category,
 	return pfd;
 }
 
-struct bpf_link *bpf_program__attach_tracepoint_opts(struct bpf_program *prog,
+struct bpf_link *bpf_program__attach_tracepoint_opts(const struct bpf_program *prog,
 						     const char *tp_category,
 						     const char *tp_name,
 						     const struct bpf_tracepoint_opts *opts)
@@ -9424,15 +10064,14 @@ struct bpf_link *bpf_program__attach_tracepoint_opts(struct bpf_program *prog,
 	return link;
 }
 
-struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
+struct bpf_link *bpf_program__attach_tracepoint(const struct bpf_program *prog,
 						const char *tp_category,
 						const char *tp_name)
 {
 	return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL);
 }
 
-static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
-				  struct bpf_program *prog)
+static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie)
 {
 	char *sec_name, *tp_cat, *tp_name;
 	struct bpf_link *link;
@@ -9441,8 +10080,11 @@ static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
 	if (!sec_name)
 		return libbpf_err_ptr(-ENOMEM);
 
-	/* extract "tp/<category>/<name>" */
-	tp_cat = sec_name + sec->len;
+	/* extract "tp/<category>/<name>" or "tracepoint/<category>/<name>" */
+	if (str_has_pfx(prog->sec_name, "tp/"))
+		tp_cat = sec_name + sizeof("tp/") - 1;
+	else
+		tp_cat = sec_name + sizeof("tracepoint/") - 1;
 	tp_name = strchr(tp_cat, '/');
 	if (!tp_name) {
 		free(sec_name);
@@ -9456,7 +10098,7 @@ static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
 	return link;
 }
 
-struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
+struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog,
 						    const char *tp_name)
 {
 	char errmsg[STRERR_BUFSIZE];
@@ -9486,16 +10128,34 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 	return link;
 }
 
-static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
-				      struct bpf_program *prog)
+static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie)
 {
-	const char *tp_name = prog->sec_name + sec->len;
+	static const char *const prefixes[] = {
+		"raw_tp/",
+		"raw_tracepoint/",
+		"raw_tp.w/",
+		"raw_tracepoint.w/",
+	};
+	size_t i;
+	const char *tp_name = NULL;
+
+	for (i = 0; i < ARRAY_SIZE(prefixes); i++) {
+		if (str_has_pfx(prog->sec_name, prefixes[i])) {
+			tp_name = prog->sec_name + strlen(prefixes[i]);
+			break;
+		}
+	}
+	if (!tp_name) {
+		pr_warn("prog '%s': invalid section name '%s'\n",
+			prog->name, prog->sec_name);
+		return libbpf_err_ptr(-EINVAL);
+	}
 
 	return bpf_program__attach_raw_tracepoint(prog, tp_name);
 }
 
 /* Common logic for all BPF program types that attach to a btf_id */
-static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog)
+static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *prog)
 {
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
@@ -9524,30 +10184,28 @@ static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog)
 	return (struct bpf_link *)link;
 }
 
-struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
+struct bpf_link *bpf_program__attach_trace(const struct bpf_program *prog)
 {
 	return bpf_program__attach_btf_id(prog);
 }
 
-struct bpf_link *bpf_program__attach_lsm(struct bpf_program *prog)
+struct bpf_link *bpf_program__attach_lsm(const struct bpf_program *prog)
 {
 	return bpf_program__attach_btf_id(prog);
 }
 
-static struct bpf_link *attach_trace(const struct bpf_sec_def *sec,
-				     struct bpf_program *prog)
+static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie)
 {
 	return bpf_program__attach_trace(prog);
 }
 
-static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
-				   struct bpf_program *prog)
+static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie)
 {
 	return bpf_program__attach_lsm(prog);
 }
 
 static struct bpf_link *
-bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id,
+bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id,
 		       const char *target_name)
 {
 	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts,
@@ -9583,24 +10241,24 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id,
 }
 
 struct bpf_link *
-bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd)
+bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd)
 {
 	return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup");
 }
 
 struct bpf_link *
-bpf_program__attach_netns(struct bpf_program *prog, int netns_fd)
+bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd)
 {
 	return bpf_program__attach_fd(prog, netns_fd, 0, "netns");
 }
 
-struct bpf_link *bpf_program__attach_xdp(struct bpf_program *prog, int ifindex)
+struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex)
 {
 	/* target_fd/target_ifindex use the same field in LINK_CREATE */
 	return bpf_program__attach_fd(prog, ifindex, 0, "xdp");
 }
 
-struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog,
+struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog,
 					      int target_fd,
 					      const char *attach_func_name)
 {
@@ -9633,7 +10291,7 @@ struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog,
 }
 
 struct bpf_link *
-bpf_program__attach_iter(struct bpf_program *prog,
+bpf_program__attach_iter(const struct bpf_program *prog,
 			 const struct bpf_iter_attach_opts *opts)
 {
 	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, link_create_opts);
@@ -9672,21 +10330,17 @@ bpf_program__attach_iter(struct bpf_program *prog,
 	return link;
 }
 
-static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
-				    struct bpf_program *prog)
+static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie)
 {
 	return bpf_program__attach_iter(prog, NULL);
 }
 
-struct bpf_link *bpf_program__attach(struct bpf_program *prog)
+struct bpf_link *bpf_program__attach(const struct bpf_program *prog)
 {
-	const struct bpf_sec_def *sec_def;
-
-	sec_def = find_sec_def(prog->sec_name);
-	if (!sec_def || !sec_def->attach_fn)
+	if (!prog->sec_def || !prog->sec_def->attach_fn)
 		return libbpf_err_ptr(-ESRCH);
 
-	return sec_def->attach_fn(sec_def, prog);
+	return prog->sec_def->attach_fn(prog, prog->sec_def->cookie);
 }
 
 static int bpf_link__detach_struct_ops(struct bpf_link *link)
@@ -9699,7 +10353,7 @@ static int bpf_link__detach_struct_ops(struct bpf_link *link)
 	return 0;
 }
 
-struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
+struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map)
 {
 	struct bpf_struct_ops *st_ops;
 	struct bpf_link *link;
@@ -10512,18 +11166,29 @@ int bpf_program__set_attach_target(struct bpf_program *prog,
 {
 	int btf_obj_fd = 0, btf_id = 0, err;
 
-	if (!prog || attach_prog_fd < 0 || !attach_func_name)
+	if (!prog || attach_prog_fd < 0)
 		return libbpf_err(-EINVAL);
 
 	if (prog->obj->loaded)
 		return libbpf_err(-EINVAL);
 
+	if (attach_prog_fd && !attach_func_name) {
+		/* remember attach_prog_fd and let bpf_program__load() find
+		 * BTF ID during the program load
+		 */
+		prog->attach_prog_fd = attach_prog_fd;
+		return 0;
+	}
+
 	if (attach_prog_fd) {
 		btf_id = libbpf_find_prog_btf_id(attach_func_name,
 						 attach_prog_fd);
 		if (btf_id < 0)
 			return libbpf_err(btf_id);
 	} else {
+		if (!attach_func_name)
+			return libbpf_err(-EINVAL);
+
 		/* load btf_vmlinux, if not yet */
 		err = bpf_object__load_vmlinux_btf(prog->obj, true);
 		if (err)
@@ -10596,7 +11261,7 @@ int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz)
 	int fd, err = 0, len;
 	char buf[128];
 
-	fd = open(fcpu, O_RDONLY);
+	fd = open(fcpu, O_RDONLY | O_CLOEXEC);
 	if (fd < 0) {
 		err = -errno;
 		pr_warn("Failed to open cpu mask file %s: %d\n", fcpu, err);
@@ -10765,16 +11430,15 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s)
 	for (i = 0; i < s->prog_cnt; i++) {
 		struct bpf_program *prog = *s->progs[i].prog;
 		struct bpf_link **link = s->progs[i].link;
-		const struct bpf_sec_def *sec_def;
 
 		if (!prog->load)
 			continue;
 
-		sec_def = find_sec_def(prog->sec_name);
-		if (!sec_def || !sec_def->attach_fn)
+		/* auto-attaching not supported for this program */
+		if (!prog->sec_def || !prog->sec_def->attach_fn)
 			continue;
 
-		*link = sec_def->attach_fn(sec_def, prog);
+		*link = bpf_program__attach(prog);
 		err = libbpf_get_error(*link);
 		if (err) {
 			pr_warn("failed to auto-attach program '%s': %d\n",
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index f177d897c5f7..9de0f299706b 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -83,12 +83,15 @@ struct bpf_object_open_opts {
 	 * Non-relocatable instructions are replaced with invalid ones to
 	 * prevent accidental errors.
 	 * */
+	LIBBPF_DEPRECATED_SINCE(0, 6, "field has no effect")
 	bool relaxed_core_relocs;
 	/* maps that set the 'pinning' attribute in their definition will have
 	 * their pin_path attribute set to a file in this directory, and be
 	 * auto-pinned to that path on load; defaults to "/sys/fs/bpf".
 	 */
 	const char *pin_root_path;
+
+	LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__set_attach_target() on each individual bpf_program")
 	__u32 attach_prog_fd;
 	/* Additional kernel config content that augments and overrides
 	 * system Kconfig for CONFIG_xxx externs.
@@ -147,6 +150,7 @@ struct bpf_object_load_attr {
 /* Load/unload object into/from kernel */
 LIBBPF_API int bpf_object__load(struct bpf_object *obj);
 LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr);
+LIBBPF_DEPRECATED_SINCE(0, 6, "bpf_object__unload() is deprecated, use bpf_object__close() instead")
 LIBBPF_API int bpf_object__unload(struct bpf_object *obj);
 
 LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj);
@@ -164,7 +168,8 @@ LIBBPF_API struct bpf_program *
 bpf_object__find_program_by_name(const struct bpf_object *obj,
 				 const char *name);
 
-LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "track bpf_objects in application code instead")
+struct bpf_object *bpf_object__next(struct bpf_object *prev);
 #define bpf_object__for_each_safe(pos, tmp)			\
 	for ((pos) = bpf_object__next(NULL),		\
 		(tmp) = bpf_object__next(pos);		\
@@ -186,16 +191,22 @@ LIBBPF_API int libbpf_find_vmlinux_btf_id(const char *name,
 
 /* Accessors of bpf_program */
 struct bpf_program;
-LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog,
-						 const struct bpf_object *obj);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_program() instead")
+struct bpf_program *bpf_program__next(struct bpf_program *prog,
+				      const struct bpf_object *obj);
+LIBBPF_API struct bpf_program *
+bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prog);
 
-#define bpf_object__for_each_program(pos, obj)		\
-	for ((pos) = bpf_program__next(NULL, (obj));	\
-	     (pos) != NULL;				\
-	     (pos) = bpf_program__next((pos), (obj)))
+#define bpf_object__for_each_program(pos, obj)			\
+	for ((pos) = bpf_object__next_program((obj), NULL);	\
+	     (pos) != NULL;					\
+	     (pos) = bpf_object__next_program((obj), (pos)))
 
-LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog,
-						 const struct bpf_object *obj);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__prev_program() instead")
+struct bpf_program *bpf_program__prev(struct bpf_program *prog,
+				      const struct bpf_object *obj);
+LIBBPF_API struct bpf_program *
+bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *prog);
 
 typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *);
 
@@ -214,14 +225,51 @@ LIBBPF_API bool bpf_program__autoload(const struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_autoload(struct bpf_program *prog, bool autoload);
 
 /* returns program size in bytes */
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insn_cnt() instead")
 LIBBPF_API size_t bpf_program__size(const struct bpf_program *prog);
 
+struct bpf_insn;
+
+/**
+ * @brief **bpf_program__insns()** gives read-only access to BPF program's
+ * underlying BPF instructions.
+ * @param prog BPF program for which to return instructions
+ * @return a pointer to an array of BPF instructions that belong to the
+ * specified BPF program
+ *
+ * Returned pointer is always valid and not NULL. Number of `struct bpf_insn`
+ * pointed to can be fetched using **bpf_program__insn_cnt()** API.
+ *
+ * Keep in mind, libbpf can modify and append/delete BPF program's
+ * instructions as it processes BPF object file and prepares everything for
+ * uploading into the kernel. So depending on the point in BPF object
+ * lifetime, **bpf_program__insns()** can return different sets of
+ * instructions. As an example, during BPF object load phase BPF program
+ * instructions will be CO-RE-relocated, BPF subprograms instructions will be
+ * appended, ldimm64 instructions will have FDs embedded, etc. So instructions
+ * returned before **bpf_object__load()** and after it might be quite
+ * different.
+ */
+LIBBPF_API const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog);
+/**
+ * @brief **bpf_program__insn_cnt()** returns number of `struct bpf_insn`'s
+ * that form specified BPF program.
+ * @param prog BPF program for which to return number of BPF instructions
+ *
+ * See **bpf_program__insns()** documentation for notes on how libbpf can
+ * change instructions and their count during different phases of
+ * **bpf_object** lifetime.
+ */
+LIBBPF_API size_t bpf_program__insn_cnt(const struct bpf_program *prog);
+
 LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license,
 				 __u32 kern_version);
 LIBBPF_API int bpf_program__fd(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated")
 LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog,
 					 const char *path,
 					 int instance);
+LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated")
 LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog,
 					   const char *path,
 					   int instance);
@@ -243,7 +291,7 @@ LIBBPF_API int bpf_link__detach(struct bpf_link *link);
 LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach(struct bpf_program *prog);
+bpf_program__attach(const struct bpf_program *prog);
 
 struct bpf_perf_event_opts {
 	/* size of this struct, for forward/backward compatiblity */
@@ -254,10 +302,10 @@ struct bpf_perf_event_opts {
 #define bpf_perf_event_opts__last_field bpf_cookie
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_perf_event(struct bpf_program *prog, int pfd);
+bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd);
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd,
+bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd,
 				    const struct bpf_perf_event_opts *opts);
 
 struct bpf_kprobe_opts {
@@ -266,7 +314,7 @@ struct bpf_kprobe_opts {
 	/* custom user-provided value fetchable through bpf_get_attach_cookie() */
 	__u64 bpf_cookie;
 	/* function's offset to install kprobe to */
-	unsigned long offset;
+	size_t offset;
 	/* kprobe is return probe */
 	bool retprobe;
 	size_t :0;
@@ -274,10 +322,10 @@ struct bpf_kprobe_opts {
 #define bpf_kprobe_opts__last_field retprobe
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe,
+bpf_program__attach_kprobe(const struct bpf_program *prog, bool retprobe,
 			   const char *func_name);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_kprobe_opts(struct bpf_program *prog,
+bpf_program__attach_kprobe_opts(const struct bpf_program *prog,
                                 const char *func_name,
                                 const struct bpf_kprobe_opts *opts);
 
@@ -297,11 +345,11 @@ struct bpf_uprobe_opts {
 #define bpf_uprobe_opts__last_field retprobe
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe,
+bpf_program__attach_uprobe(const struct bpf_program *prog, bool retprobe,
 			   pid_t pid, const char *binary_path,
 			   size_t func_offset);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid,
+bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid,
 				const char *binary_path, size_t func_offset,
 				const struct bpf_uprobe_opts *opts);
 
@@ -314,35 +362,35 @@ struct bpf_tracepoint_opts {
 #define bpf_tracepoint_opts__last_field bpf_cookie
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_tracepoint(struct bpf_program *prog,
+bpf_program__attach_tracepoint(const struct bpf_program *prog,
 			       const char *tp_category,
 			       const char *tp_name);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_tracepoint_opts(struct bpf_program *prog,
+bpf_program__attach_tracepoint_opts(const struct bpf_program *prog,
 				    const char *tp_category,
 				    const char *tp_name,
 				    const struct bpf_tracepoint_opts *opts);
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
+bpf_program__attach_raw_tracepoint(const struct bpf_program *prog,
 				   const char *tp_name);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_trace(struct bpf_program *prog);
+bpf_program__attach_trace(const struct bpf_program *prog);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_lsm(struct bpf_program *prog);
+bpf_program__attach_lsm(const struct bpf_program *prog);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd);
+bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_netns(struct bpf_program *prog, int netns_fd);
+bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_xdp(struct bpf_program *prog, int ifindex);
+bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_freplace(struct bpf_program *prog,
+bpf_program__attach_freplace(const struct bpf_program *prog,
 			     int target_fd, const char *attach_func_name);
 
 struct bpf_map;
 
-LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map);
+LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);
 
 struct bpf_iter_attach_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
@@ -352,11 +400,9 @@ struct bpf_iter_attach_opts {
 #define bpf_iter_attach_opts__last_field link_info_len
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_iter(struct bpf_program *prog,
+bpf_program__attach_iter(const struct bpf_program *prog,
 			 const struct bpf_iter_attach_opts *opts);
 
-struct bpf_insn;
-
 /*
  * Libbpf allows callers to adjust BPF programs before being loaded
  * into kernel. One program in an object file can be transformed into
@@ -385,7 +431,7 @@ struct bpf_insn;
  * one instance. In this case bpf_program__fd(prog) is equal to
  * bpf_program__nth_fd(prog, 0).
  */
-
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insns() for getting bpf_program instructions")
 struct bpf_prog_prep_result {
 	/*
 	 * If not NULL, load new instruction array.
@@ -414,9 +460,11 @@ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n,
 				  struct bpf_insn *insns, int insns_cnt,
 				  struct bpf_prog_prep_result *res);
 
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insns() for getting bpf_program instructions")
 LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
 				     bpf_program_prep_t prep);
 
+LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated")
 LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n);
 
 /*
@@ -478,9 +526,13 @@ struct bpf_map_def {
 	unsigned int map_flags;
 };
 
-/*
- * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel,
- * so no need to worry about a name clash.
+/**
+ * @brief **bpf_object__find_map_by_name()** returns BPF map of
+ * the given name, if it exists within the passed BPF object
+ * @param obj BPF object
+ * @param name name of the BPF map
+ * @return BPF map instance, if such map exists within the BPF object;
+ * or NULL otherwise.
  */
 LIBBPF_API struct bpf_map *
 bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name);
@@ -495,18 +547,28 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name);
 LIBBPF_API struct bpf_map *
 bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset);
 
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_map() instead")
+struct bpf_map *bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj);
 LIBBPF_API struct bpf_map *
-bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj);
+bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *map);
+
 #define bpf_object__for_each_map(pos, obj)		\
-	for ((pos) = bpf_map__next(NULL, (obj));	\
+	for ((pos) = bpf_object__next_map((obj), NULL);	\
 	     (pos) != NULL;				\
-	     (pos) = bpf_map__next((pos), (obj)))
+	     (pos) = bpf_object__next_map((obj), (pos)))
 #define bpf_map__for_each bpf_object__for_each_map
 
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__prev_map() instead")
+struct bpf_map *bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj);
 LIBBPF_API struct bpf_map *
-bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj);
+bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map);
 
-/* get/set map FD */
+/**
+ * @brief **bpf_map__fd()** gets the file descriptor of the passed
+ * BPF map
+ * @param map the BPF map instance
+ * @return the file descriptor; or -EINVAL in case of an error
+ */
 LIBBPF_API int bpf_map__fd(const struct bpf_map *map);
 LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
 /* get map definition */
@@ -538,6 +600,9 @@ LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
 /* get/set map if_index */
 LIBBPF_API __u32 bpf_map__ifindex(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
+/* get/set map map_extra flags */
+LIBBPF_API __u64 bpf_map__map_extra(const struct bpf_map *map);
+LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra);
 
 typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
@@ -547,6 +612,14 @@ LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map,
 					  const void *data, size_t size);
 LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize);
 LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map);
+
+/**
+ * @brief **bpf_map__is_internal()** tells the caller whether or not the
+ * passed map is a special map created by libbpf automatically for things like
+ * global variables, __ksym externs, Kconfig values, etc
+ * @param map the bpf_map
+ * @return true, if the map is an internal map; false, otherwise
+ */
 LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path);
 LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map);
@@ -558,6 +631,38 @@ 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 struct bpf_map *bpf_map__inner_map(struct bpf_map *map);
 
+/**
+ * @brief **libbpf_get_error()** extracts the error code from the passed
+ * pointer
+ * @param ptr pointer returned from libbpf API function
+ * @return error code; or 0 if no error occured
+ *
+ * Many libbpf API functions which return pointers have logic to encode error
+ * codes as pointers, and do not return NULL. Meaning **libbpf_get_error()**
+ * should be used on the return value from these functions immediately after
+ * calling the API function, with no intervening calls that could clobber the
+ * `errno` variable. Consult the individual functions documentation to verify
+ * if this logic applies should be used.
+ *
+ * For these API functions, if `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)`
+ * is enabled, NULL is returned on error instead.
+ *
+ * If ptr is NULL, then errno should be already set by the failing
+ * API, because libbpf never returns NULL on success and it now always
+ * sets errno on error.
+ *
+ * Example usage:
+ *
+ *   struct perf_buffer *pb;
+ *
+ *   pb = perf_buffer__new(bpf_map__fd(obj->maps.events), PERF_BUFFER_PAGES, &opts);
+ *   err = libbpf_get_error(pb);
+ *   if (err) {
+ *	  pb = NULL;
+ *	  fprintf(stderr, "failed to open perf buffer: %d\n", err);
+ *	  goto cleanup;
+ *   }
+ */
 LIBBPF_API long libbpf_get_error(const void *ptr);
 
 struct bpf_prog_load_attr {
@@ -822,9 +927,10 @@ bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear);
 LIBBPF_API void
 bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear);
 
-/*
- * A helper function to get the number of possible CPUs before looking up
- * per-CPU maps. Negative errno is returned on failure.
+/**
+ * @brief **libbpf_num_possible_cpus()** is a helper function to get the
+ * number of possible CPUs that the host kernel supports and expects.
+ * @return number of possible CPUs; or error code on failure
  *
  * Example usage:
  *
@@ -834,7 +940,6 @@ bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear);
  *     }
  *     long values[ncpus];
  *     bpf_map_lookup_elem(per_cpu_map_fd, key, values);
- *
  */
 LIBBPF_API int libbpf_num_possible_cpus(void);
 
@@ -854,7 +959,7 @@ struct bpf_object_skeleton {
 	size_t sz; /* size of this struct, for forward/backward compatibility */
 
 	const char *name;
-	void *data;
+	const void *data;
 	size_t data_sz;
 
 	struct bpf_object **obj;
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index bbc53bb25f68..43580eb47740 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -386,3 +386,19 @@ LIBBPF_0.5.0 {
 		btf_dump__dump_type_data;
 		libbpf_set_strict_mode;
 } LIBBPF_0.4.0;
+
+LIBBPF_0.6.0 {
+	global:
+		bpf_map__map_extra;
+		bpf_map__set_map_extra;
+		bpf_object__next_map;
+		bpf_object__next_program;
+		bpf_object__prev_map;
+		bpf_object__prev_program;
+		bpf_program__insn_cnt;
+		bpf_program__insns;
+		btf__add_btf;
+		btf__add_decl_tag;
+		btf__raw_data;
+		btf__type_cnt;
+} LIBBPF_0.5.0;
diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h
index 947d8bd8a7bb..aaa1efbf6f51 100644
--- a/tools/lib/bpf/libbpf_common.h
+++ b/tools/lib/bpf/libbpf_common.h
@@ -10,6 +10,7 @@
 #define __LIBBPF_LIBBPF_COMMON_H
 
 #include <string.h>
+#include "libbpf_version.h"
 
 #ifndef LIBBPF_API
 #define LIBBPF_API __attribute__((visibility("default")))
@@ -17,6 +18,29 @@
 
 #define LIBBPF_DEPRECATED(msg) __attribute__((deprecated(msg)))
 
+/* Mark a symbol as deprecated when libbpf version is >= {major}.{minor} */
+#define LIBBPF_DEPRECATED_SINCE(major, minor, msg)			    \
+	__LIBBPF_MARK_DEPRECATED_ ## major ## _ ## minor		    \
+		(LIBBPF_DEPRECATED("libbpf v" # major "." # minor "+: " msg))
+
+#define __LIBBPF_CURRENT_VERSION_GEQ(major, minor)			    \
+	(LIBBPF_MAJOR_VERSION > (major) ||				    \
+	 (LIBBPF_MAJOR_VERSION == (major) && LIBBPF_MINOR_VERSION >= (minor)))
+
+/* Add checks for other versions below when planning deprecation of API symbols
+ * with the LIBBPF_DEPRECATED_SINCE macro.
+ */
+#if __LIBBPF_CURRENT_VERSION_GEQ(0, 6)
+#define __LIBBPF_MARK_DEPRECATED_0_6(X) X
+#else
+#define __LIBBPF_MARK_DEPRECATED_0_6(X)
+#endif
+#if __LIBBPF_CURRENT_VERSION_GEQ(0, 7)
+#define __LIBBPF_MARK_DEPRECATED_0_7(X) X
+#else
+#define __LIBBPF_MARK_DEPRECATED_0_7(X)
+#endif
+
 /* Helper macro to declare and initialize libbpf options struct
  *
  * This dance with uninitialized declaration, followed by memset to zero,
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 533b0211f40a..aeb79e3a8ff9 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -13,6 +13,8 @@
 #include <limits.h>
 #include <errno.h>
 #include <linux/err.h>
+#include <fcntl.h>
+#include <unistd.h>
 #include "libbpf_legacy.h"
 #include "relo_core.h"
 
@@ -52,8 +54,8 @@
 #endif
 
 /* Older libelf all end up in this expression, for both 32 and 64 bit */
-#ifndef GELF_ST_VISIBILITY
-#define GELF_ST_VISIBILITY(o) ((o) & 0x03)
+#ifndef ELF64_ST_VISIBILITY
+#define ELF64_ST_VISIBILITY(o) ((o) & 0x03)
 #endif
 
 #define BTF_INFO_ENC(kind, kind_flag, vlen) \
@@ -69,6 +71,8 @@
 #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size)
 #define BTF_TYPE_FLOAT_ENC(name, sz) \
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz)
+#define BTF_TYPE_DECL_TAG_ENC(value, type, component_idx) \
+	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx)
 
 #ifndef likely
 #define likely(x) __builtin_expect(!!(x), 1)
@@ -87,20 +91,40 @@
 	(offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD))
 #endif
 
+/* Check whether a string `str` has prefix `pfx`, regardless if `pfx` is
+ * a string literal known at compilation time or char * pointer known only at
+ * runtime.
+ */
+#define str_has_pfx(str, pfx) \
+	(strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0)
+
 /* Symbol versioning is different between static and shared library.
  * Properly versioned symbols are needed for shared library, but
  * only the symbol of the new version is needed for static library.
+ * Starting with GNU C 10, use symver attribute instead of .symver assembler
+ * directive, which works better with GCC LTO builds.
  */
-#ifdef SHARED
-# define COMPAT_VERSION(internal_name, api_name, version) \
+#if defined(SHARED) && defined(__GNUC__) && __GNUC__ >= 10
+
+#define DEFAULT_VERSION(internal_name, api_name, version) \
+	__attribute__((symver(#api_name "@@" #version)))
+#define COMPAT_VERSION(internal_name, api_name, version) \
+	__attribute__((symver(#api_name "@" #version)))
+
+#elif defined(SHARED)
+
+#define COMPAT_VERSION(internal_name, api_name, version) \
 	asm(".symver " #internal_name "," #api_name "@" #version);
-# define DEFAULT_VERSION(internal_name, api_name, version) \
+#define DEFAULT_VERSION(internal_name, api_name, version) \
 	asm(".symver " #internal_name "," #api_name "@@" #version);
-#else
-# define COMPAT_VERSION(internal_name, api_name, version)
-# define DEFAULT_VERSION(internal_name, api_name, version) \
+
+#else /* !SHARED */
+
+#define COMPAT_VERSION(internal_name, api_name, version)
+#define DEFAULT_VERSION(internal_name, api_name, version) \
 	extern typeof(internal_name) api_name \
 	__attribute__((alias(#internal_name)));
+
 #endif
 
 extern void libbpf_print(enum libbpf_print_level level,
@@ -171,8 +195,9 @@ enum map_def_parts {
 	MAP_DEF_NUMA_NODE	= 0x080,
 	MAP_DEF_PINNING		= 0x100,
 	MAP_DEF_INNER_MAP	= 0x200,
+	MAP_DEF_MAP_EXTRA	= 0x400,
 
-	MAP_DEF_ALL		= 0x3ff, /* combination of all above */
+	MAP_DEF_ALL		= 0x7ff, /* combination of all above */
 };
 
 struct btf_map_def {
@@ -186,6 +211,7 @@ struct btf_map_def {
 	__u32 map_flags;
 	__u32 numa_node;
 	__u32 pinning;
+	__u64 map_extra;
 };
 
 int parse_btf_map_def(const char *map_name, struct btf *btf,
@@ -276,14 +302,32 @@ struct bpf_prog_load_params {
 	__u32 log_level;
 	char *log_buf;
 	size_t log_buf_sz;
+	int *fd_array;
 };
 
 int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr);
 
-int bpf_object__section_size(const struct bpf_object *obj, const char *name,
-			     __u32 *size);
-int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
-				__u32 *off);
+struct bpf_create_map_params {
+	const char *name;
+	enum bpf_map_type map_type;
+	__u32 map_flags;
+	__u32 key_size;
+	__u32 value_size;
+	__u32 max_entries;
+	__u32 numa_node;
+	__u32 btf_fd;
+	__u32 btf_key_type_id;
+	__u32 btf_value_type_id;
+	__u32 map_ifindex;
+	union {
+		__u32 inner_map_fd;
+		__u32 btf_vmlinux_value_type_id;
+	};
+	__u64 map_extra;
+};
+
+int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr);
+
 struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
 void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
 				const char **prefix, int *kind);
@@ -386,6 +430,8 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct
 int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx);
 int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx);
 int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx);
+__s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
+				 __u32 kind);
 
 extern enum libbpf_strict_mode libbpf_mode;
 
@@ -447,4 +493,26 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn)
 	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
 }
 
+/* if fd is stdin, stdout, or stderr, dup to a fd greater than 2
+ * Takes ownership of the fd passed in, and closes it if calling
+ * fcntl(fd, F_DUPFD_CLOEXEC, 3).
+ */
+static inline int ensure_good_fd(int fd)
+{
+	int old_fd = fd, saved_errno;
+
+	if (fd < 0)
+		return fd;
+	if (fd < 3) {
+		fd = fcntl(fd, F_DUPFD_CLOEXEC, 3);
+		saved_errno = errno;
+		close(old_fd);
+		if (fd < 0) {
+			pr_warn("failed to dup FD %d to FD > 2: %d\n", old_fd, -saved_errno);
+			errno = saved_errno;
+		}
+	}
+	return fd;
+}
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */
diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h
index df0d03dcffab..5ba5c9beccfa 100644
--- a/tools/lib/bpf/libbpf_legacy.h
+++ b/tools/lib/bpf/libbpf_legacy.h
@@ -46,6 +46,24 @@ enum libbpf_strict_mode {
 	 */
 	LIBBPF_STRICT_DIRECT_ERRS = 0x02,
 
+	/*
+	 * Enforce strict BPF program section (SEC()) names.
+	 * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were
+	 * allowed, with LIBBPF_STRICT_SEC_PREFIX this will become
+	 * unrecognized by libbpf and would have to be just SEC("xdp") and
+	 * SEC("xdp") and SEC("perf_event").
+	 *
+	 * Note, in this mode the program pin path will be based on the
+	 * function name instead of section name.
+	 */
+	LIBBPF_STRICT_SEC_NAME = 0x04,
+	/*
+	 * Disable the global 'bpf_objects_list'. Maintaining this list adds
+	 * a race condition to bpf_object__open() and bpf_object__close().
+	 * Clients can maintain it on their own if it is valuable for them.
+	 */
+	LIBBPF_STRICT_NO_OBJECT_LIST = 0x08,
+
 	__LIBBPF_STRICT_LAST,
 };
 
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index cd8c703dde71..68f2dbf364aa 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -33,7 +33,7 @@ static int get_vendor_id(int ifindex)
 
 	snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname);
 
-	fd = open(path, O_RDONLY);
+	fd = open(path, O_RDONLY | O_CLOEXEC);
 	if (fd < 0)
 		return -1;
 
diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h
new file mode 100644
index 000000000000..dd56d76f291c
--- /dev/null
+++ b/tools/lib/bpf/libbpf_version.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (C) 2021 Facebook */
+#ifndef __LIBBPF_VERSION_H
+#define __LIBBPF_VERSION_H
+
+#define LIBBPF_MAJOR_VERSION 0
+#define LIBBPF_MINOR_VERSION 6
+
+#endif /* __LIBBPF_VERSION_H */
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 2df880cefdae..f677dccdeae4 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -15,7 +15,6 @@
 #include <linux/btf.h>
 #include <elf.h>
 #include <libelf.h>
-#include <gelf.h>
 #include <fcntl.h>
 #include "libbpf.h"
 #include "btf.h"
@@ -302,7 +301,7 @@ static int init_output_elf(struct bpf_linker *linker, const char *file)
 	if (!linker->filename)
 		return -ENOMEM;
 
-	linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC, 0644);
+	linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644);
 	if (linker->fd < 0) {
 		err = -errno;
 		pr_warn("failed to create '%s': %d\n", file, err);
@@ -324,12 +323,12 @@ static int init_output_elf(struct bpf_linker *linker, const char *file)
 
 	linker->elf_hdr->e_machine = EM_BPF;
 	linker->elf_hdr->e_type = ET_REL;
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2LSB;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2MSB;
 #else
-#error "Unknown __BYTE_ORDER"
+#error "Unknown __BYTE_ORDER__"
 #endif
 
 	/* STRTAB */
@@ -539,12 +538,12 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
 				const struct bpf_linker_file_opts *opts,
 				struct src_obj *obj)
 {
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	const int host_endianness = ELFDATA2LSB;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	const int host_endianness = ELFDATA2MSB;
 #else
-#error "Unknown __BYTE_ORDER"
+#error "Unknown __BYTE_ORDER__"
 #endif
 	int err = 0;
 	Elf_Scn *scn;
@@ -557,7 +556,7 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
 
 	obj->filename = filename;
 
-	obj->fd = open(filename, O_RDONLY);
+	obj->fd = open(filename, O_RDONLY | O_CLOEXEC);
 	if (obj->fd < 0) {
 		err = -errno;
 		pr_warn("failed to open file '%s': %d\n", filename, err);
@@ -921,7 +920,7 @@ static int check_btf_type_id(__u32 *type_id, void *ctx)
 {
 	struct btf *btf = ctx;
 
-	if (*type_id > btf__get_nr_types(btf))
+	if (*type_id >= btf__type_cnt(btf))
 		return -EINVAL;
 
 	return 0;
@@ -948,8 +947,8 @@ static int linker_sanity_check_btf(struct src_obj *obj)
 	if (!obj->btf)
 		return 0;
 
-	n = btf__get_nr_types(obj->btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(obj->btf);
+	for (i = 1; i < n; i++) {
 		t = btf_type_by_id(obj->btf, i);
 
 		err = err ?: btf_type_visit_type_ids(t, check_btf_type_id, obj->btf);
@@ -1659,8 +1658,8 @@ static int find_glob_sym_btf(struct src_obj *obj, Elf64_Sym *sym, const char *sy
 		return -EINVAL;
 	}
 
-	n = btf__get_nr_types(obj->btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(obj->btf);
+	for (i = 1; i < n; i++) {
 		t = btf__type_by_id(obj->btf, i);
 
 		/* some global and extern FUNCs and VARs might not be associated with any
@@ -2131,8 +2130,8 @@ static int linker_fixup_btf(struct src_obj *obj)
 	if (!obj->btf)
 		return 0;
 
-	n = btf__get_nr_types(obj->btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(obj->btf);
+	for (i = 1; i < n; i++) {
 		struct btf_var_secinfo *vi;
 		struct btf_type *t;
 
@@ -2235,14 +2234,14 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 	if (!obj->btf)
 		return 0;
 
-	start_id = btf__get_nr_types(linker->btf) + 1;
-	n = btf__get_nr_types(obj->btf);
+	start_id = btf__type_cnt(linker->btf);
+	n = btf__type_cnt(obj->btf);
 
 	obj->btf_type_map = calloc(n + 1, sizeof(int));
 	if (!obj->btf_type_map)
 		return -ENOMEM;
 
-	for (i = 1; i <= n; i++) {
+	for (i = 1; i < n; i++) {
 		struct glob_sym *glob_sym = NULL;
 
 		t = btf__type_by_id(obj->btf, i);
@@ -2297,8 +2296,8 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 	}
 
 	/* remap all the types except DATASECs */
-	n = btf__get_nr_types(linker->btf);
-	for (i = start_id; i <= n; i++) {
+	n = btf__type_cnt(linker->btf);
+	for (i = start_id; i < n; i++) {
 		struct btf_type *dst_t = btf_type_by_id(linker->btf, i);
 
 		if (btf_type_visit_type_ids(dst_t, remap_type_id, obj->btf_type_map))
@@ -2657,7 +2656,7 @@ static int finalize_btf(struct bpf_linker *linker)
 	__u32 raw_sz;
 
 	/* bail out if no BTF data was produced */
-	if (btf__get_nr_types(linker->btf) == 0)
+	if (btf__type_cnt(linker->btf) == 1)
 		return 0;
 
 	for (i = 1; i < linker->sec_cnt; i++) {
@@ -2694,7 +2693,7 @@ static int finalize_btf(struct bpf_linker *linker)
 	}
 
 	/* Emit .BTF section */
-	raw_data = btf__get_raw_data(linker->btf, &raw_sz);
+	raw_data = btf__raw_data(linker->btf, &raw_sz);
 	if (!raw_data)
 		return -ENOMEM;
 
diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c
index 4016ed492d0c..b5b8956a1be8 100644
--- a/tools/lib/bpf/relo_core.c
+++ b/tools/lib/bpf/relo_core.c
@@ -662,7 +662,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 			*validate = true; /* signedness is never ambiguous */
 		break;
 	case BPF_FIELD_LSHIFT_U64:
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 		*val = 64 - (bit_off + bit_sz - byte_off  * 8);
 #else
 		*val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8);
diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h
index b22b50c1b173..9cf66702fa8d 100644
--- a/tools/lib/bpf/skel_internal.h
+++ b/tools/lib/bpf/skel_internal.h
@@ -105,10 +105,12 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 	err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr));
 	if (err < 0 || (int)attr.test.retval < 0) {
 		opts->errstr = "failed to execute loader prog";
-		if (err < 0)
+		if (err < 0) {
 			err = -errno;
-		else
+		} else {
 			err = (int)attr.test.retval;
+			errno = -err;
+		}
 		goto out;
 	}
 	err = 0;
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index e9b619aa0cdf..81f8fbc85e70 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -281,6 +281,7 @@ out_mmap:
 	return err;
 }
 
+DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4)
 int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 			    __u64 size, struct xsk_ring_prod *fill,
 			    struct xsk_ring_cons *comp,
@@ -299,7 +300,7 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 	if (!umem)
 		return -ENOMEM;
 
-	umem->fd = socket(AF_XDP, SOCK_RAW, 0);
+	umem->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0);
 	if (umem->fd < 0) {
 		err = -errno;
 		goto out_umem_alloc;
@@ -345,6 +346,7 @@ struct xsk_umem_config_v1 {
 	__u32 frame_headroom;
 };
 
+COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2)
 int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area,
 			    __u64 size, struct xsk_ring_prod *fill,
 			    struct xsk_ring_cons *comp,
@@ -358,8 +360,6 @@ int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area,
 	return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp,
 					&config);
 }
-COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2)
-DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4)
 
 static enum xsk_prog get_xsk_prog(void)
 {
@@ -549,7 +549,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 	struct ifreq ifr = {};
 	int fd, err, ret;
 
-	fd = socket(AF_LOCAL, SOCK_DGRAM, 0);
+	fd = socket(AF_LOCAL, SOCK_DGRAM | SOCK_CLOEXEC, 0);
 	if (fd < 0)
 		return -errno;
 
@@ -1046,7 +1046,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	}
 
 	if (umem->refcount++ > 0) {
-		xsk->fd = socket(AF_XDP, SOCK_RAW, 0);
+		xsk->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0);
 		if (xsk->fd < 0) {
 			err = -errno;
 			goto out_xsk_alloc;
diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h
index 01c12dca9c10..64e9c57fd792 100644
--- a/tools/lib/bpf/xsk.h
+++ b/tools/lib/bpf/xsk.h
@@ -23,6 +23,12 @@
 extern "C" {
 #endif
 
+/* This whole API has been deprecated and moved to libxdp that can be found at
+ * https://github.com/xdp-project/xdp-tools. The APIs are exactly the same so
+ * it should just be linking with libxdp instead of libbpf for this set of
+ * functionality. If not, please submit a bug report on the aforementioned page.
+ */
+
 /* Load-Acquire Store-Release barriers used by the XDP socket
  * library. The following macros should *NOT* be considered part of
  * the xsk.h API, and is subject to change anytime.
@@ -245,8 +251,10 @@ static inline __u64 xsk_umem__add_offset_to_addr(__u64 addr)
 	return xsk_umem__extract_addr(addr) + xsk_umem__extract_offset(addr);
 }
 
-LIBBPF_API int xsk_umem__fd(const struct xsk_umem *umem);
-LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__fd(const struct xsk_umem *umem);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__fd(const struct xsk_socket *xsk);
 
 #define XSK_RING_CONS__DEFAULT_NUM_DESCS      2048
 #define XSK_RING_PROD__DEFAULT_NUM_DESCS      2048
@@ -263,10 +271,10 @@ struct xsk_umem_config {
 	__u32 flags;
 };
 
-LIBBPF_API int xsk_setup_xdp_prog(int ifindex,
-				  int *xsks_map_fd);
-LIBBPF_API int xsk_socket__update_xskmap(struct xsk_socket *xsk,
-					 int xsks_map_fd);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__update_xskmap(struct xsk_socket *xsk, int xsks_map_fd);
 
 /* Flags for the libbpf_flags field. */
 #define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0)
@@ -280,40 +288,46 @@ struct xsk_socket_config {
 };
 
 /* Set config to NULL to get the default configuration. */
-LIBBPF_API int xsk_umem__create(struct xsk_umem **umem,
-				void *umem_area, __u64 size,
-				struct xsk_ring_prod *fill,
-				struct xsk_ring_cons *comp,
-				const struct xsk_umem_config *config);
-LIBBPF_API int xsk_umem__create_v0_0_2(struct xsk_umem **umem,
-				       void *umem_area, __u64 size,
-				       struct xsk_ring_prod *fill,
-				       struct xsk_ring_cons *comp,
-				       const struct xsk_umem_config *config);
-LIBBPF_API int xsk_umem__create_v0_0_4(struct xsk_umem **umem,
-				       void *umem_area, __u64 size,
-				       struct xsk_ring_prod *fill,
-				       struct xsk_ring_cons *comp,
-				       const struct xsk_umem_config *config);
-LIBBPF_API int xsk_socket__create(struct xsk_socket **xsk,
-				  const char *ifname, __u32 queue_id,
-				  struct xsk_umem *umem,
-				  struct xsk_ring_cons *rx,
-				  struct xsk_ring_prod *tx,
-				  const struct xsk_socket_config *config);
-LIBBPF_API int
-xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
-			  const char *ifname,
-			  __u32 queue_id, struct xsk_umem *umem,
-			  struct xsk_ring_cons *rx,
-			  struct xsk_ring_prod *tx,
-			  struct xsk_ring_prod *fill,
-			  struct xsk_ring_cons *comp,
-			  const struct xsk_socket_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__create(struct xsk_umem **umem,
+		     void *umem_area, __u64 size,
+		     struct xsk_ring_prod *fill,
+		     struct xsk_ring_cons *comp,
+		     const struct xsk_umem_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__create_v0_0_2(struct xsk_umem **umem,
+			    void *umem_area, __u64 size,
+			    struct xsk_ring_prod *fill,
+			    struct xsk_ring_cons *comp,
+			    const struct xsk_umem_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__create_v0_0_4(struct xsk_umem **umem,
+			    void *umem_area, __u64 size,
+			    struct xsk_ring_prod *fill,
+			    struct xsk_ring_cons *comp,
+			    const struct xsk_umem_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__create(struct xsk_socket **xsk,
+		       const char *ifname, __u32 queue_id,
+		       struct xsk_umem *umem,
+		       struct xsk_ring_cons *rx,
+		       struct xsk_ring_prod *tx,
+		       const struct xsk_socket_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
+			      const char *ifname,
+			      __u32 queue_id, struct xsk_umem *umem,
+			      struct xsk_ring_cons *rx,
+			      struct xsk_ring_prod *tx,
+			      struct xsk_ring_prod *fill,
+			      struct xsk_ring_cons *comp,
+			      const struct xsk_socket_config *config);
 
 /* Returns 0 for success and -EBUSY if the umem is still in use. */
-LIBBPF_API int xsk_umem__delete(struct xsk_umem *umem);
-LIBBPF_API void xsk_socket__delete(struct xsk_socket *xsk);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__delete(struct xsk_umem *umem);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+void xsk_socket__delete(struct xsk_socket *xsk);
 
 #ifdef __cplusplus
 } /* extern "C" */