23 files changed, 467 insertions, 178 deletions
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index 7f6396087b46..8665c799e0fa 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -95,7 +95,7 @@ install_lib: $(LIBFILE)
 		$(call do_install_mkdir,$(libdir_SQ)); \
 		cp -fpR $(LIBFILE) $(DESTDIR)$(libdir_SQ)
 
-HDRS := cpu.h debug.h io.h
+HDRS := cpu.h debug.h io.h io_dir.h
 FD_HDRS := fd/array.h
 FS_HDRS := fs/fs.h fs/tracing_path.h
 INSTALL_HDRS_PFX := $(DESTDIR)$(prefix)/include/api
diff --git a/tools/lib/api/io_dir.h b/tools/lib/api/io_dir.h
new file mode 100644
index 000000000000..ef83e967e48c
--- /dev/null
+++ b/tools/lib/api/io_dir.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/*
+ * Lightweight directory reading library.
+ */
+#ifndef __API_IO_DIR__
+#define __API_IO_DIR__
+
+#include <dirent.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <linux/limits.h>
+
+#if !defined(SYS_getdents64)
+#if defined(__x86_64__) || defined(__arm__)
+  #define SYS_getdents64 217
+#elif defined(__i386__) || defined(__s390x__) || defined(__sh__)
+  #define SYS_getdents64 220
+#elif defined(__alpha__)
+  #define SYS_getdents64 377
+#elif defined(__mips__)
+  #define SYS_getdents64 308
+#elif defined(__powerpc64__) || defined(__powerpc__)
+  #define SYS_getdents64 202
+#elif defined(__sparc64__) || defined(__sparc__)
+  #define SYS_getdents64 154
+#elif defined(__xtensa__)
+  #define SYS_getdents64 60
+#else
+  #define SYS_getdents64 61
+#endif
+#endif /* !defined(SYS_getdents64) */
+
+static inline ssize_t perf_getdents64(int fd, void *dirp, size_t count)
+{
+#ifdef MEMORY_SANITIZER
+	memset(dirp, 0, count);
+#endif
+	return syscall(SYS_getdents64, fd, dirp, count);
+}
+
+struct io_dirent64 {
+	ino64_t        d_ino;    /* 64-bit inode number */
+	off64_t        d_off;    /* 64-bit offset to next structure */
+	unsigned short d_reclen; /* Size of this dirent */
+	unsigned char  d_type;   /* File type */
+	char           d_name[NAME_MAX + 1]; /* Filename (null-terminated) */
+};
+
+struct io_dir {
+	int dirfd;
+	ssize_t available_bytes;
+	struct io_dirent64 *next;
+	struct io_dirent64 buff[4];
+};
+
+static inline void io_dir__init(struct io_dir *iod, int dirfd)
+{
+	iod->dirfd = dirfd;
+	iod->available_bytes = 0;
+}
+
+static inline void io_dir__rewinddir(struct io_dir *iod)
+{
+	lseek(iod->dirfd, 0, SEEK_SET);
+	iod->available_bytes = 0;
+}
+
+static inline struct io_dirent64 *io_dir__readdir(struct io_dir *iod)
+{
+	struct io_dirent64 *entry;
+
+	if (iod->available_bytes <= 0) {
+		ssize_t rc = perf_getdents64(iod->dirfd, iod->buff, sizeof(iod->buff));
+
+		if (rc <= 0)
+			return NULL;
+		iod->available_bytes = rc;
+		iod->next = iod->buff;
+	}
+	entry = iod->next;
+	iod->next = (struct io_dirent64 *)((char *)entry + entry->d_reclen);
+	iod->available_bytes -= entry->d_reclen;
+	return entry;
+}
+
+static inline bool io_dir__is_dir(const struct io_dir *iod, struct io_dirent64 *dent)
+{
+	if (dent->d_type == DT_UNKNOWN) {
+		struct stat st;
+
+		if (fstatat(iod->dirfd, dent->d_name, &st, /*flags=*/0))
+			return false;
+
+		if (S_ISDIR(st.st_mode)) {
+			dent->d_type = DT_DIR;
+			return true;
+		}
+	}
+	return dent->d_type == DT_DIR;
+}
+
+#endif  /* __API_IO_DIR__ */
diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c
index 2178862bb114..51255c69754d 100644
--- a/tools/lib/bitmap.c
+++ b/tools/lib/bitmap.c
@@ -101,6 +101,26 @@ bool __bitmap_intersects(const unsigned long *bitmap1,
 	return false;
 }
 
+void __bitmap_set(unsigned long *map, unsigned int start, int len)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const unsigned int size = start + len;
+	int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
+
+	while (len - bits_to_set >= 0) {
+		*p |= mask_to_set;
+		len -= bits_to_set;
+		bits_to_set = BITS_PER_LONG;
+		mask_to_set = ~0UL;
+		p++;
+	}
+	if (len) {
+		mask_to_set &= BITMAP_LAST_WORD_MASK(size);
+		*p |= mask_to_set;
+	}
+}
+
 void __bitmap_clear(unsigned long *map, unsigned int start, int len)
 {
 	unsigned long *p = map + BIT_WORD(start);
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 857a5f7b413d..168140f8e646 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -53,13 +53,6 @@ include $(srctree)/tools/scripts/Makefile.include
 
 # copy a bit from Linux kbuild
 
-ifeq ("$(origin V)", "command line")
-  VERBOSE = $(V)
-endif
-ifndef VERBOSE
-  VERBOSE = 0
-endif
-
 INCLUDES = -I$(or $(OUTPUT),.) \
 	   -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi \
 	   -I$(srctree)/tools/arch/$(SRCARCH)/include
@@ -96,12 +89,6 @@ override CFLAGS += $(CLANG_CROSS_FLAGS)
 # flags specific for shared library
 SHLIB_FLAGS := -DSHARED -fPIC
 
-ifeq ($(VERBOSE),1)
-  Q =
-else
-  Q = @
-endif
-
 # Disable command line variables (CFLAGS) override from top
 # level Makefile (perf), otherwise build Makefile will get
 # the same command line setup.
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 359f73ead613..a9c3e33d0f8a 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1097,7 +1097,7 @@ int bpf_map_get_fd_by_id(__u32 id)
 int bpf_btf_get_fd_by_id_opts(__u32 id,
 			      const struct bpf_get_fd_by_id_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, open_flags);
+	const size_t attr_sz = offsetofend(union bpf_attr, fd_by_id_token_fd);
 	union bpf_attr attr;
 	int fd;
 
@@ -1107,6 +1107,7 @@ int bpf_btf_get_fd_by_id_opts(__u32 id,
 	memset(&attr, 0, attr_sz);
 	attr.btf_id = id;
 	attr.open_flags = OPTS_GET(opts, open_flags, 0);
+	attr.fd_by_id_token_fd = OPTS_GET(opts, token_fd, 0);
 
 	fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 435da95d2058..777627d33d25 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -487,9 +487,10 @@ LIBBPF_API int bpf_link_get_next_id(__u32 start_id, __u32 *next_id);
 struct bpf_get_fd_by_id_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
 	__u32 open_flags; /* permissions requested for the operation on fd */
+	__u32 token_fd;
 	size_t :0;
 };
-#define bpf_get_fd_by_id_opts__last_field open_flags
+#define bpf_get_fd_by_id_opts__last_field token_fd
 
 LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
 LIBBPF_API int bpf_prog_get_fd_by_id_opts(__u32 id,
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 48c66f3a9200..38bc6b14b066 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1619,12 +1619,18 @@ exit_free:
 	return btf;
 }
 
-struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf)
+struct btf *btf_load_from_kernel(__u32 id, struct btf *base_btf, int token_fd)
 {
 	struct btf *btf;
 	int btf_fd;
+	LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts);
+
+	if (token_fd) {
+		opts.open_flags |= BPF_F_TOKEN_FD;
+		opts.token_fd = token_fd;
+	}
 
-	btf_fd = bpf_btf_get_fd_by_id(id);
+	btf_fd = bpf_btf_get_fd_by_id_opts(id, &opts);
 	if (btf_fd < 0)
 		return libbpf_err_ptr(-errno);
 
@@ -1634,6 +1640,11 @@ struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf)
 	return libbpf_ptr(btf);
 }
 
+struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf)
+{
+	return btf_load_from_kernel(id, base_btf, 0);
+}
+
 struct btf *btf__load_from_kernel_by_id(__u32 id)
 {
 	return btf__load_from_kernel_by_id_split(id, NULL);
@@ -2090,7 +2101,7 @@ static int validate_type_id(int id)
 }
 
 /* generic append function for PTR, TYPEDEF, CONST/VOLATILE/RESTRICT */
-static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id)
+static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id, int kflag)
 {
 	struct btf_type *t;
 	int sz, name_off = 0;
@@ -2113,7 +2124,7 @@ static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref
 	}
 
 	t->name_off = name_off;
-	t->info = btf_type_info(kind, 0, 0);
+	t->info = btf_type_info(kind, 0, kflag);
 	t->type = ref_type_id;
 
 	return btf_commit_type(btf, sz);
@@ -2128,7 +2139,7 @@ static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref
  */
 int btf__add_ptr(struct btf *btf, int ref_type_id)
 {
-	return btf_add_ref_kind(btf, BTF_KIND_PTR, NULL, ref_type_id);
+	return btf_add_ref_kind(btf, BTF_KIND_PTR, NULL, ref_type_id, 0);
 }
 
 /*
@@ -2506,7 +2517,7 @@ int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind)
 		struct btf_type *t;
 		int id;
 
-		id = btf_add_ref_kind(btf, BTF_KIND_FWD, name, 0);
+		id = btf_add_ref_kind(btf, BTF_KIND_FWD, name, 0, 0);
 		if (id <= 0)
 			return id;
 		t = btf_type_by_id(btf, id);
@@ -2536,7 +2547,7 @@ int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id)
 	if (!name || !name[0])
 		return libbpf_err(-EINVAL);
 
-	return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id);
+	return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id, 0);
 }
 
 /*
@@ -2548,7 +2559,7 @@ int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id)
  */
 int btf__add_volatile(struct btf *btf, int ref_type_id)
 {
-	return btf_add_ref_kind(btf, BTF_KIND_VOLATILE, NULL, ref_type_id);
+	return btf_add_ref_kind(btf, BTF_KIND_VOLATILE, NULL, ref_type_id, 0);
 }
 
 /*
@@ -2560,7 +2571,7 @@ int btf__add_volatile(struct btf *btf, int ref_type_id)
  */
 int btf__add_const(struct btf *btf, int ref_type_id)
 {
-	return btf_add_ref_kind(btf, BTF_KIND_CONST, NULL, ref_type_id);
+	return btf_add_ref_kind(btf, BTF_KIND_CONST, NULL, ref_type_id, 0);
 }
 
 /*
@@ -2572,7 +2583,7 @@ int btf__add_const(struct btf *btf, int ref_type_id)
  */
 int btf__add_restrict(struct btf *btf, int ref_type_id)
 {
-	return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id);
+	return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id, 0);
 }
 
 /*
@@ -2588,7 +2599,24 @@ int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id)
 	if (!value || !value[0])
 		return libbpf_err(-EINVAL);
 
-	return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id);
+	return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id, 0);
+}
+
+/*
+ * Append new BTF_KIND_TYPE_TAG type with:
+ *   - *value*, non-empty/non-NULL tag value;
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ * Set info->kflag to 1, indicating this tag is an __attribute__
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_type_attr(struct btf *btf, const char *value, int ref_type_id)
+{
+	if (!value || !value[0])
+		return libbpf_err(-EINVAL);
+
+	return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id, 1);
 }
 
 /*
@@ -2610,7 +2638,7 @@ int btf__add_func(struct btf *btf, const char *name,
 	    linkage != BTF_FUNC_EXTERN)
 		return libbpf_err(-EINVAL);
 
-	id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id);
+	id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id, 0);
 	if (id > 0) {
 		struct btf_type *t = btf_type_by_id(btf, id);
 
@@ -2845,18 +2873,8 @@ 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)
+static int btf_add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
+			    int component_idx, int kflag)
 {
 	struct btf_type *t;
 	int sz, value_off;
@@ -2880,13 +2898,46 @@ int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
 		return value_off;
 
 	t->name_off = value_off;
-	t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, false);
+	t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, kflag);
 	t->type = ref_type_id;
 	btf_decl_tag(t)->component_idx = component_idx;
 
 	return btf_commit_type(btf, sz);
 }
 
+/*
+ * 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)
+{
+	return btf_add_decl_tag(btf, value, ref_type_id, component_idx, 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;
+ * Set info->kflag to 1, indicating this tag is an __attribute__
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_decl_attr(struct btf *btf, const char *value, int ref_type_id,
+		       int component_idx)
+{
+	return btf_add_decl_tag(btf, value, ref_type_id, component_idx, 1);
+}
+
 struct btf_ext_sec_info_param {
 	__u32 off;
 	__u32 len;
@@ -3015,8 +3066,6 @@ static int btf_ext_parse_info(struct btf_ext *btf_ext, bool is_native)
 		.desc = "line_info",
 	};
 	struct btf_ext_sec_info_param core_relo = {
-		.off = btf_ext->hdr->core_relo_off,
-		.len = btf_ext->hdr->core_relo_len,
 		.min_rec_size = sizeof(struct bpf_core_relo),
 		.ext_info = &btf_ext->core_relo_info,
 		.desc = "core_relo",
@@ -3034,6 +3083,8 @@ static int btf_ext_parse_info(struct btf_ext *btf_ext, bool is_native)
 	if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len))
 		return 0; /* skip core relos parsing */
 
+	core_relo.off = btf_ext->hdr->core_relo_off;
+	core_relo.len = btf_ext->hdr->core_relo_len;
 	err = btf_ext_parse_sec_info(btf_ext, &core_relo, is_native);
 	if (err)
 		return err;
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 47ee8f6ac489..4392451d634b 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -227,6 +227,7 @@ LIBBPF_API int btf__add_volatile(struct btf *btf, int ref_type_id);
 LIBBPF_API int btf__add_const(struct btf *btf, int ref_type_id);
 LIBBPF_API int btf__add_restrict(struct btf *btf, int ref_type_id);
 LIBBPF_API int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id);
+LIBBPF_API int btf__add_type_attr(struct btf *btf, const char *value, int ref_type_id);
 
 /* func and func_proto construction APIs */
 LIBBPF_API int btf__add_func(struct btf *btf, const char *name,
@@ -243,6 +244,8 @@ LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id,
 /* tag construction API */
 LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
 			    int component_idx);
+LIBBPF_API int btf__add_decl_attr(struct btf *btf, const char *value, int ref_type_id,
+				  int component_idx);
 
 struct btf_dedup_opts {
 	size_t sz;
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index a3fc6908f6c9..460c3e57fadb 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -1494,7 +1494,10 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 		case BTF_KIND_TYPE_TAG:
 			btf_dump_emit_mods(d, decls);
 			name = btf_name_of(d, t->name_off);
-			btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name);
+			if (btf_kflag(t))
+				btf_dump_printf(d, " __attribute__((%s))", name);
+			else
+				btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name);
 			break;
 		case BTF_KIND_ARRAY: {
 			const struct btf_array *a = btf_array(t);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 194809da5172..6b85060f07b3 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -670,11 +670,18 @@ struct elf_state {
 
 struct usdt_manager;
 
+enum bpf_object_state {
+	OBJ_OPEN,
+	OBJ_PREPARED,
+	OBJ_LOADED,
+};
+
 struct bpf_object {
 	char name[BPF_OBJ_NAME_LEN];
 	char license[64];
 	__u32 kern_version;
 
+	enum bpf_object_state state;
 	struct bpf_program *programs;
 	size_t nr_programs;
 	struct bpf_map *maps;
@@ -686,7 +693,6 @@ struct bpf_object {
 	int nr_extern;
 	int kconfig_map_idx;
 
-	bool loaded;
 	bool has_subcalls;
 	bool has_rodata;
 
@@ -1511,7 +1517,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 	obj->kconfig_map_idx = -1;
 
 	obj->kern_version = get_kernel_version();
-	obj->loaded = false;
+	obj->state  = OBJ_OPEN;
 
 	return obj;
 }
@@ -2106,7 +2112,7 @@ static int set_kcfg_value_str(struct extern_desc *ext, char *ext_val,
 	}
 
 	len = strlen(value);
-	if (value[len - 1] != '"') {
+	if (len < 2 || value[len - 1] != '"') {
 		pr_warn("extern (kcfg) '%s': invalid string config '%s'\n",
 			ext->name, value);
 		return -EINVAL;
@@ -4845,6 +4851,11 @@ static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info)
 	return 0;
 }
 
+static bool map_is_created(const struct bpf_map *map)
+{
+	return map->obj->state >= OBJ_PREPARED || map->reused;
+}
+
 bool bpf_map__autocreate(const struct bpf_map *map)
 {
 	return map->autocreate;
@@ -4852,7 +4863,7 @@ bool bpf_map__autocreate(const struct bpf_map *map)
 
 int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate)
 {
-	if (map->obj->loaded)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 
 	map->autocreate = autocreate;
@@ -4946,7 +4957,7 @@ struct bpf_map *bpf_map__inner_map(struct bpf_map *map)
 
 int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries)
 {
-	if (map->obj->loaded)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 
 	map->def.max_entries = max_entries;
@@ -5191,11 +5202,6 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 
 static void bpf_map__destroy(struct bpf_map *map);
 
-static bool map_is_created(const struct bpf_map *map)
-{
-	return map->obj->loaded || map->reused;
-}
-
 static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, create_attr);
@@ -7897,13 +7903,6 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
 
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
-		err = bpf_object__sanitize_prog(obj, prog);
-		if (err)
-			return err;
-	}
-
-	for (i = 0; i < obj->nr_programs; i++) {
-		prog = &obj->programs[i];
 		if (prog_is_subprog(obj, prog))
 			continue;
 		if (!prog->autoload) {
@@ -7927,6 +7926,21 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
 	return 0;
 }
 
+static int bpf_object_prepare_progs(struct bpf_object *obj)
+{
+	struct bpf_program *prog;
+	size_t i;
+	int err;
+
+	for (i = 0; i < obj->nr_programs; i++) {
+		prog = &obj->programs[i];
+		err = bpf_object__sanitize_prog(obj, prog);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
 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)
@@ -8543,14 +8557,77 @@ static int bpf_object_prepare_struct_ops(struct bpf_object *obj)
 	return 0;
 }
 
+static void bpf_object_unpin(struct bpf_object *obj)
+{
+	int i;
+
+	/* unpin any maps that were auto-pinned during load */
+	for (i = 0; i < obj->nr_maps; i++)
+		if (obj->maps[i].pinned && !obj->maps[i].reused)
+			bpf_map__unpin(&obj->maps[i], NULL);
+}
+
+static void bpf_object_post_load_cleanup(struct bpf_object *obj)
+{
+	int i;
+
+	/* 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);
+		btf__free(obj->btf_modules[i].btf);
+		free(obj->btf_modules[i].name);
+	}
+	obj->btf_module_cnt = 0;
+	zfree(&obj->btf_modules);
+
+	/* clean up vmlinux BTF */
+	btf__free(obj->btf_vmlinux);
+	obj->btf_vmlinux = NULL;
+}
+
+static int bpf_object_prepare(struct bpf_object *obj, const char *target_btf_path)
+{
+	int err;
+
+	if (obj->state >= OBJ_PREPARED) {
+		pr_warn("object '%s': prepare loading can't be attempted twice\n", obj->name);
+		return -EINVAL;
+	}
+
+	err = bpf_object_prepare_token(obj);
+	err = err ? : bpf_object__probe_loading(obj);
+	err = err ? : bpf_object__load_vmlinux_btf(obj, false);
+	err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
+	err = err ? : bpf_object__sanitize_maps(obj);
+	err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
+	err = err ? : bpf_object_adjust_struct_ops_autoload(obj);
+	err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path);
+	err = err ? : bpf_object__sanitize_and_load_btf(obj);
+	err = err ? : bpf_object__create_maps(obj);
+	err = err ? : bpf_object_prepare_progs(obj);
+
+	if (err) {
+		bpf_object_unpin(obj);
+		bpf_object_unload(obj);
+		obj->state = OBJ_LOADED;
+		return err;
+	}
+
+	obj->state = OBJ_PREPARED;
+	return 0;
+}
+
 static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const char *target_btf_path)
 {
-	int err, i;
+	int err;
 
 	if (!obj)
 		return libbpf_err(-EINVAL);
 
-	if (obj->loaded) {
+	if (obj->state >= OBJ_LOADED) {
 		pr_warn("object '%s': load can't be attempted twice\n", obj->name);
 		return libbpf_err(-EINVAL);
 	}
@@ -8565,17 +8642,12 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
 		return libbpf_err(-LIBBPF_ERRNO__ENDIAN);
 	}
 
-	err = bpf_object_prepare_token(obj);
-	err = err ? : bpf_object__probe_loading(obj);
-	err = err ? : bpf_object__load_vmlinux_btf(obj, false);
-	err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
-	err = err ? : bpf_object__sanitize_maps(obj);
-	err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
-	err = err ? : bpf_object_adjust_struct_ops_autoload(obj);
-	err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path);
-	err = err ? : bpf_object__sanitize_and_load_btf(obj);
-	err = err ? : bpf_object__create_maps(obj);
-	err = err ? : bpf_object__load_progs(obj, extra_log_level);
+	if (obj->state < OBJ_PREPARED) {
+		err = bpf_object_prepare(obj, target_btf_path);
+		if (err)
+			return libbpf_err(err);
+	}
+	err = bpf_object__load_progs(obj, extra_log_level);
 	err = err ? : bpf_object_init_prog_arrays(obj);
 	err = err ? : bpf_object_prepare_struct_ops(obj);
 
@@ -8587,36 +8659,22 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
 			err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps);
 	}
 
-	/* clean up fd_array */
-	zfree(&obj->fd_array);
+	bpf_object_post_load_cleanup(obj);
+	obj->state = OBJ_LOADED; /* doesn't matter if successfully or not */
 
-	/* clean up module BTFs */
-	for (i = 0; i < obj->btf_module_cnt; i++) {
-		close(obj->btf_modules[i].fd);
-		btf__free(obj->btf_modules[i].btf);
-		free(obj->btf_modules[i].name);
+	if (err) {
+		bpf_object_unpin(obj);
+		bpf_object_unload(obj);
+		pr_warn("failed to load object '%s'\n", obj->path);
+		return libbpf_err(err);
 	}
-	free(obj->btf_modules);
-
-	/* clean up vmlinux BTF */
-	btf__free(obj->btf_vmlinux);
-	obj->btf_vmlinux = NULL;
-
-	obj->loaded = true; /* doesn't matter if successfully or not */
-
-	if (err)
-		goto out;
 
 	return 0;
-out:
-	/* unpin any maps that were auto-pinned during load */
-	for (i = 0; i < obj->nr_maps; i++)
-		if (obj->maps[i].pinned && !obj->maps[i].reused)
-			bpf_map__unpin(&obj->maps[i], NULL);
+}
 
-	bpf_object_unload(obj);
-	pr_warn("failed to load object '%s'\n", obj->path);
-	return libbpf_err(err);
+int bpf_object__prepare(struct bpf_object *obj)
+{
+	return libbpf_err(bpf_object_prepare(obj, NULL));
 }
 
 int bpf_object__load(struct bpf_object *obj)
@@ -8866,7 +8924,7 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
 	if (!obj)
 		return libbpf_err(-ENOENT);
 
-	if (!obj->loaded) {
+	if (obj->state < OBJ_PREPARED) {
 		pr_warn("object not yet loaded; load it first\n");
 		return libbpf_err(-ENOENT);
 	}
@@ -8945,7 +9003,7 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path)
 	if (!obj)
 		return libbpf_err(-ENOENT);
 
-	if (!obj->loaded) {
+	if (obj->state < OBJ_LOADED) {
 		pr_warn("object not yet loaded; load it first\n");
 		return libbpf_err(-ENOENT);
 	}
@@ -9064,6 +9122,13 @@ void bpf_object__close(struct bpf_object *obj)
 	if (IS_ERR_OR_NULL(obj))
 		return;
 
+	/*
+	 * if user called bpf_object__prepare() without ever getting to
+	 * bpf_object__load(), we need to clean up stuff that is normally
+	 * cleaned up at the end of loading step
+	 */
+	bpf_object_post_load_cleanup(obj);
+
 	usdt_manager_free(obj->usdt_man);
 	obj->usdt_man = NULL;
 
@@ -9132,7 +9197,7 @@ int bpf_object__btf_fd(const struct bpf_object *obj)
 
 int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version)
 {
-	if (obj->loaded)
+	if (obj->state >= OBJ_LOADED)
 		return libbpf_err(-EINVAL);
 
 	obj->kern_version = kern_version;
@@ -9145,12 +9210,12 @@ int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts)
 	struct bpf_gen *gen;
 
 	if (!opts)
-		return -EFAULT;
+		return libbpf_err(-EFAULT);
 	if (!OPTS_VALID(opts, gen_loader_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	gen = calloc(sizeof(*gen), 1);
 	if (!gen)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 	gen->opts = opts;
 	gen->swapped_endian = !is_native_endianness(obj);
 	obj->gen_loader = gen;
@@ -9229,7 +9294,7 @@ bool bpf_program__autoload(const struct bpf_program *prog)
 
 int bpf_program__set_autoload(struct bpf_program *prog, bool autoload)
 {
-	if (prog->obj->loaded)
+	if (prog->obj->state >= OBJ_LOADED)
 		return libbpf_err(-EINVAL);
 
 	prog->autoload = autoload;
@@ -9261,14 +9326,14 @@ int bpf_program__set_insns(struct bpf_program *prog,
 {
 	struct bpf_insn *insns;
 
-	if (prog->obj->loaded)
-		return -EBUSY;
+	if (prog->obj->state >= OBJ_LOADED)
+		return libbpf_err(-EBUSY);
 
 	insns = libbpf_reallocarray(prog->insns, new_insn_cnt, sizeof(*insns));
 	/* NULL is a valid return from reallocarray if the new count is zero */
 	if (!insns && new_insn_cnt) {
 		pr_warn("prog '%s': failed to realloc prog code\n", prog->name);
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 	}
 	memcpy(insns, new_insns, new_insn_cnt * sizeof(*insns));
 
@@ -9304,7 +9369,7 @@ static int last_custom_sec_def_handler_id;
 
 int bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
 {
-	if (prog->obj->loaded)
+	if (prog->obj->state >= OBJ_LOADED)
 		return libbpf_err(-EBUSY);
 
 	/* if type is not changed, do nothing */
@@ -9335,7 +9400,7 @@ enum bpf_attach_type bpf_program__expected_attach_type(const struct bpf_program
 int bpf_program__set_expected_attach_type(struct bpf_program *prog,
 					   enum bpf_attach_type type)
 {
-	if (prog->obj->loaded)
+	if (prog->obj->state >= OBJ_LOADED)
 		return libbpf_err(-EBUSY);
 
 	prog->expected_attach_type = type;
@@ -9349,7 +9414,7 @@ __u32 bpf_program__flags(const struct bpf_program *prog)
 
 int bpf_program__set_flags(struct bpf_program *prog, __u32 flags)
 {
-	if (prog->obj->loaded)
+	if (prog->obj->state >= OBJ_LOADED)
 		return libbpf_err(-EBUSY);
 
 	prog->prog_flags = flags;
@@ -9363,7 +9428,7 @@ __u32 bpf_program__log_level(const struct bpf_program *prog)
 
 int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level)
 {
-	if (prog->obj->loaded)
+	if (prog->obj->state >= OBJ_LOADED)
 		return libbpf_err(-EBUSY);
 
 	prog->log_level = log_level;
@@ -9379,11 +9444,11 @@ const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_siz
 int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size)
 {
 	if (log_size && !log_buf)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (prog->log_size > UINT_MAX)
-		return -EINVAL;
-	if (prog->obj->loaded)
-		return -EBUSY;
+		return libbpf_err(-EINVAL);
+	if (prog->obj->state >= OBJ_LOADED)
+		return libbpf_err(-EBUSY);
 
 	prog->log_buf = log_buf;
 	prog->log_size = log_size;
@@ -9959,7 +10024,7 @@ int libbpf_find_vmlinux_btf_id(const char *name,
 	return libbpf_err(err);
 }
 
-static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
+static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd, int token_fd)
 {
 	struct bpf_prog_info info;
 	__u32 info_len = sizeof(info);
@@ -9979,7 +10044,7 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
 		pr_warn("The target program doesn't have BTF\n");
 		goto out;
 	}
-	btf = btf__load_from_kernel_by_id(info.btf_id);
+	btf = btf_load_from_kernel(info.btf_id, NULL, token_fd);
 	err = libbpf_get_error(btf);
 	if (err) {
 		pr_warn("Failed to get BTF %d of the program: %s\n", info.btf_id, errstr(err));
@@ -10062,7 +10127,7 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac
 			pr_warn("prog '%s': attach program FD is not set\n", prog->name);
 			return -EINVAL;
 		}
-		err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd);
+		err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd, prog->obj->token_fd);
 		if (err < 0) {
 			pr_warn("prog '%s': failed to find BPF program (FD %d) BTF ID for '%s': %s\n",
 				prog->name, attach_prog_fd, attach_name, errstr(err));
@@ -10299,7 +10364,7 @@ static int map_btf_datasec_resize(struct bpf_map *map, __u32 size)
 
 int bpf_map__set_value_size(struct bpf_map *map, __u32 size)
 {
-	if (map->obj->loaded || map->reused)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 
 	if (map->mmaped) {
@@ -10307,7 +10372,7 @@ int bpf_map__set_value_size(struct bpf_map *map, __u32 size)
 		int err;
 
 		if (map->def.type != BPF_MAP_TYPE_ARRAY)
-			return -EOPNOTSUPP;
+			return libbpf_err(-EOPNOTSUPP);
 
 		mmap_old_sz = bpf_map_mmap_sz(map);
 		mmap_new_sz = array_map_mmap_sz(size, map->def.max_entries);
@@ -10315,7 +10380,7 @@ int bpf_map__set_value_size(struct bpf_map *map, __u32 size)
 		if (err) {
 			pr_warn("map '%s': failed to resize memory-mapped region: %s\n",
 				bpf_map__name(map), errstr(err));
-			return err;
+			return libbpf_err(err);
 		}
 		err = map_btf_datasec_resize(map, size);
 		if (err && err != -ENOENT) {
@@ -10345,7 +10410,7 @@ int bpf_map__set_initial_value(struct bpf_map *map,
 {
 	size_t actual_sz;
 
-	if (map->obj->loaded || map->reused)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 
 	if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG)
@@ -12858,7 +12923,7 @@ struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog,
 	if (target_fd) {
 		LIBBPF_OPTS(bpf_link_create_opts, target_opts);
 
-		btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd);
+		btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd, prog->obj->token_fd);
 		if (btf_id < 0)
 			return libbpf_err_ptr(btf_id);
 
@@ -13070,17 +13135,17 @@ int bpf_link__update_map(struct bpf_link *link, const struct bpf_map *map)
 	int err;
 
 	if (!bpf_map__is_struct_ops(map))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (map->fd < 0) {
 		pr_warn("map '%s': can't use BPF map without FD (was it created?)\n", map->name);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	st_ops_link = container_of(link, struct bpf_link_struct_ops, link);
 	/* Ensure the type of a link is correct */
 	if (st_ops_link->map_fd < 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	err = bpf_map_update_elem(map->fd, &zero, map->st_ops->kern_vdata, 0);
 	/* It can be EBUSY if the map has been used to create or
@@ -13666,7 +13731,7 @@ int bpf_program__set_attach_target(struct bpf_program *prog,
 	if (!prog || attach_prog_fd < 0)
 		return libbpf_err(-EINVAL);
 
-	if (prog->obj->loaded)
+	if (prog->obj->state >= OBJ_LOADED)
 		return libbpf_err(-EINVAL);
 
 	if (attach_prog_fd && !attach_func_name) {
@@ -13679,7 +13744,7 @@ int bpf_program__set_attach_target(struct bpf_program *prog,
 
 	if (attach_prog_fd) {
 		btf_id = libbpf_find_prog_btf_id(attach_func_name,
-						 attach_prog_fd);
+						 attach_prog_fd, prog->obj->token_fd);
 		if (btf_id < 0)
 			return libbpf_err(btf_id);
 	} else {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 3020ee45303a..e0605403f977 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -242,6 +242,19 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
 		     const struct bpf_object_open_opts *opts);
 
 /**
+ * @brief **bpf_object__prepare()** prepares BPF object for loading:
+ * performs ELF processing, relocations, prepares final state of BPF program
+ * instructions (accessible with bpf_program__insns()), creates and
+ * (potentially) pins maps. Leaves BPF object in the state ready for program
+ * loading.
+ * @param obj Pointer to a valid BPF object instance returned by
+ * **bpf_object__open*()** API
+ * @return 0, on success; negative error code, otherwise, error code is
+ * stored in errno
+ */
+int bpf_object__prepare(struct bpf_object *obj);
+
+/**
  * @brief **bpf_object__load()** loads BPF object into kernel.
  * @param obj Pointer to a valid BPF object instance returned by
  * **bpf_object__open*()** APIs
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index a8b2936a1646..d8b71f22f197 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -436,4 +436,7 @@ LIBBPF_1.6.0 {
 		bpf_linker__add_buf;
 		bpf_linker__add_fd;
 		bpf_linker__new_fd;
+		bpf_object__prepare;
+		btf__add_decl_attr;
+		btf__add_type_attr;
 } LIBBPF_1.5.0;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index de498e2dd6b0..76669c73dcd1 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -409,6 +409,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 int btf_load_into_kernel(struct btf *btf,
 			 char *log_buf, size_t log_sz, __u32 log_level,
 			 int token_fd);
+struct btf *btf_load_from_kernel(__u32 id, struct btf *base_btf, int token_fd);
 
 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,
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index b52f71c59616..800e0ef09c37 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -2163,7 +2163,7 @@ add_sym:
 
 	obj->sym_map[src_sym_idx] = dst_sym_idx;
 
-	if (sym_type == STT_SECTION && dst_sym) {
+	if (sym_type == STT_SECTION && dst_sec) {
 		dst_sec->sec_sym_idx = dst_sym_idx;
 		dst_sym->st_value = 0;
 	}
diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c
index 7632e9d41827..2b83c98a1137 100644
--- a/tools/lib/bpf/relo_core.c
+++ b/tools/lib/bpf/relo_core.c
@@ -683,7 +683,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 {
 	const struct bpf_core_accessor *acc;
 	const struct btf_type *t;
-	__u32 byte_off, byte_sz, bit_off, bit_sz, field_type_id;
+	__u32 byte_off, byte_sz, bit_off, bit_sz, field_type_id, elem_id;
 	const struct btf_member *m;
 	const struct btf_type *mt;
 	bool bitfield;
@@ -706,8 +706,14 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 	if (!acc->name) {
 		if (relo->kind == BPF_CORE_FIELD_BYTE_OFFSET) {
 			*val = spec->bit_offset / 8;
-			/* remember field size for load/store mem size */
-			sz = btf__resolve_size(spec->btf, acc->type_id);
+			/* remember field size for load/store mem size;
+			 * note, for arrays we care about individual element
+			 * sizes, not the overall array size
+			 */
+			t = skip_mods_and_typedefs(spec->btf, acc->type_id, &elem_id);
+			while (btf_is_array(t))
+				t = skip_mods_and_typedefs(spec->btf, btf_array(t)->type, &elem_id);
+			sz = btf__resolve_size(spec->btf, elem_id);
 			if (sz < 0)
 				return -EINVAL;
 			*field_sz = sz;
@@ -767,7 +773,17 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 	case BPF_CORE_FIELD_BYTE_OFFSET:
 		*val = byte_off;
 		if (!bitfield) {
-			*field_sz = byte_sz;
+			/* remember field size for load/store mem size;
+			 * note, for arrays we care about individual element
+			 * sizes, not the overall array size
+			 */
+			t = skip_mods_and_typedefs(spec->btf, field_type_id, &elem_id);
+			while (btf_is_array(t))
+				t = skip_mods_and_typedefs(spec->btf, btf_array(t)->type, &elem_id);
+			sz = btf__resolve_size(spec->btf, elem_id);
+			if (sz < 0)
+				return -EINVAL;
+			*field_sz = sz;
 			*type_id = field_type_id;
 		}
 		break;
diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c
index 8743049e32b7..9a541762f54c 100644
--- a/tools/lib/bpf/str_error.c
+++ b/tools/lib/bpf/str_error.c
@@ -36,7 +36,7 @@ char *libbpf_strerror_r(int err, char *dst, int len)
 	return dst;
 }
 
-const char *errstr(int err)
+const char *libbpf_errstr(int err)
 {
 	static __thread char buf[12];
 
diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h
index 66ffebde0684..53e7fbffc13e 100644
--- a/tools/lib/bpf/str_error.h
+++ b/tools/lib/bpf/str_error.h
@@ -7,10 +7,13 @@
 char *libbpf_strerror_r(int err, char *dst, int len);
 
 /**
- * @brief **errstr()** returns string corresponding to numeric errno
+ * @brief **libbpf_errstr()** returns string corresponding to numeric errno
  * @param err negative numeric errno
  * @return pointer to string representation of the errno, that is invalidated
  * upon the next call.
  */
-const char *errstr(int err);
+const char *libbpf_errstr(int err);
+
+#define errstr(err) libbpf_errstr(err)
+
 #endif /* __LIBBPF_STR_ERROR_H */
diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h
index b811f754939f..2a7865c8e3fe 100644
--- a/tools/lib/bpf/usdt.bpf.h
+++ b/tools/lib/bpf/usdt.bpf.h
@@ -108,6 +108,38 @@ int bpf_usdt_arg_cnt(struct pt_regs *ctx)
 	return spec->arg_cnt;
 }
 
+/* Returns the size in bytes of the #*arg_num* (zero-indexed) USDT argument.
+ * Returns negative error if argument is not found or arg_num is invalid.
+ */
+static __always_inline
+int bpf_usdt_arg_size(struct pt_regs *ctx, __u64 arg_num)
+{
+	struct __bpf_usdt_arg_spec *arg_spec;
+	struct __bpf_usdt_spec *spec;
+	int spec_id;
+
+	spec_id = __bpf_usdt_spec_id(ctx);
+	if (spec_id < 0)
+		return -ESRCH;
+
+	spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id);
+	if (!spec)
+		return -ESRCH;
+
+	if (arg_num >= BPF_USDT_MAX_ARG_CNT)
+		return -ENOENT;
+	barrier_var(arg_num);
+	if (arg_num >= spec->arg_cnt)
+		return -ENOENT;
+
+	arg_spec = &spec->args[arg_num];
+
+	/* arg_spec->arg_bitshift = 64 - arg_sz * 8
+	 * so: arg_sz = (64 - arg_spec->arg_bitshift) / 8
+	 */
+	return (unsigned int)(64 - arg_spec->arg_bitshift) / 8;
+}
+
 /* Fetch USDT argument #*arg_num* (zero-indexed) and put its value into *res.
  * Returns 0 on success; negative error, otherwise.
  * On error *res is guaranteed to be set to zero.
diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile
index 3a9b2140aa04..ffcfd777c451 100644
--- a/tools/lib/perf/Makefile
+++ b/tools/lib/perf/Makefile
@@ -39,28 +39,8 @@ libdir = $(prefix)/$(libdir_relative)
 libdir_SQ = $(subst ','\'',$(libdir))
 libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 
-ifeq ("$(origin V)", "command line")
-  VERBOSE = $(V)
-endif
-ifndef VERBOSE
-  VERBOSE = 0
-endif
-
-ifeq ($(VERBOSE),1)
-  Q =
-else
-  Q = @
-endif
-
 TEST_ARGS := $(if $(V),-v)
 
-# Set compile option CFLAGS
-ifdef EXTRA_CFLAGS
-  CFLAGS := $(EXTRA_CFLAGS)
-else
-  CFLAGS := -g -Wall
-endif
-
 INCLUDES = \
 -I$(srctree)/tools/lib/perf/include \
 -I$(srctree)/tools/lib/ \
@@ -70,11 +50,12 @@ INCLUDES = \
 -I$(srctree)/tools/include/uapi
 
 # Append required CFLAGS
-override CFLAGS += $(EXTRA_WARNINGS)
-override CFLAGS += -Werror -Wall
+override CFLAGS += -g -Werror -Wall
 override CFLAGS += -fPIC
 override CFLAGS += $(INCLUDES)
 override CFLAGS += -fvisibility=hidden
+override CFLAGS += $(EXTRA_WARNINGS)
+override CFLAGS += $(EXTRA_CFLAGS)
 
 all:
 
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index fcc47214062a..4454a5987570 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -185,7 +185,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 	while (isdigit(*cpu_list)) {
 		p = NULL;
 		start_cpu = strtoul(cpu_list, &p, 0);
-		if (start_cpu >= INT_MAX
+		if (start_cpu >= INT16_MAX
 		    || (*p != '\0' && *p != ',' && *p != '-' && *p != '\n'))
 			goto invalid;
 
@@ -194,7 +194,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 			p = NULL;
 			end_cpu = strtoul(cpu_list, &p, 0);
 
-			if (end_cpu >= INT_MAX || (*p != '\0' && *p != ',' && *p != '\n'))
+			if (end_cpu >= INT16_MAX || (*p != '\0' && *p != ',' && *p != '\n'))
 				goto invalid;
 
 			if (end_cpu < start_cpu)
@@ -209,7 +209,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 		for (; start_cpu <= end_cpu; start_cpu++) {
 			/* check for duplicates */
 			for (i = 0; i < nr_cpus; i++)
-				if (tmp_cpus[i].cpu == (int)start_cpu)
+				if (tmp_cpus[i].cpu == (int16_t)start_cpu)
 					goto invalid;
 
 			if (nr_cpus == max_entries) {
@@ -219,7 +219,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 					goto invalid;
 				tmp_cpus = tmp;
 			}
-			tmp_cpus[nr_cpus++].cpu = (int)start_cpu;
+			tmp_cpus[nr_cpus++].cpu = (int16_t)start_cpu;
 		}
 		if (*p)
 			++p;
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 188a667babc6..8c1ab0f9194e 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -4,10 +4,11 @@
 
 #include <perf/core.h>
 #include <stdbool.h>
+#include <stdint.h>
 
 /** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */
 struct perf_cpu {
-	int cpu;
+	int16_t cpu;
 };
 
 struct perf_cache {
diff --git a/tools/lib/slab.c b/tools/lib/slab.c
index 959997fb0652..981a21404f32 100644
--- a/tools/lib/slab.c
+++ b/tools/lib/slab.c
@@ -36,3 +36,19 @@ void kfree(void *p)
 		printf("Freeing %p to malloc\n", p);
 	free(p);
 }
+
+void *kmalloc_array(size_t n, size_t size, gfp_t gfp)
+{
+	void *ret;
+
+	if (!(gfp & __GFP_DIRECT_RECLAIM))
+		return NULL;
+
+	ret = calloc(n, size);
+	uatomic_inc(&kmalloc_nr_allocated);
+	if (kmalloc_verbose)
+		printf("Allocating %p from calloc\n", ret);
+	if (gfp & __GFP_ZERO)
+		memset(ret, 0, n * size);
+	return ret;
+}
diff --git a/tools/lib/thermal/Makefile b/tools/lib/thermal/Makefile
index 8890fd57b110..a1f5e388644d 100644
--- a/tools/lib/thermal/Makefile
+++ b/tools/lib/thermal/Makefile
@@ -39,19 +39,6 @@ libdir = $(prefix)/$(libdir_relative)
 libdir_SQ = $(subst ','\'',$(libdir))
 libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 
-ifeq ("$(origin V)", "command line")
-  VERBOSE = $(V)
-endif
-ifndef VERBOSE
-  VERBOSE = 0
-endif
-
-ifeq ($(VERBOSE),1)
-  Q =
-else
-  Q = @
-endif
-
 # Set compile option CFLAGS
 ifdef EXTRA_CFLAGS
   CFLAGS := $(EXTRA_CFLAGS)