24 files changed, 127 insertions, 96 deletions

diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index 044860ac1ed1..7f6396087b46 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -31,11 +31,7 @@ CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -fPIC
 
 ifeq ($(DEBUG),0)
-ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
-else
-  CFLAGS += -O6
-endif
 endif
 
 ifeq ($(DEBUG),0)
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index 30745f35d0d2..834fd64c7130 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -69,7 +69,7 @@ char *get_tracing_file(const char *name)
 {
 	char *file;
 
-	if (asprintf(&file, "%s/%s", tracing_path_mount(), name) < 0)
+	if (asprintf(&file, "%s%s", tracing_path_mount(), name) < 0)
 		return NULL;
 
 	return file;
diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index 0da84cb9e66d..f02725b123b3 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -5,3 +5,4 @@ TAGS
 tags
 cscope.*
 /bpf_helper_defs.h
+fixdep
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 2cf892774346..1b22f0f37288 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -108,6 +108,8 @@ MAKEOVERRIDES=
 
 all:
 
+OUTPUT ?= ./
+OUTPUT := $(abspath $(OUTPUT))/
 export srctree OUTPUT CC LD CFLAGS V
 include $(srctree)/tools/build/Makefile.include
 
@@ -141,7 +143,10 @@ all: fixdep
 
 all_cmd: $(CMD_TARGETS) check
 
-$(BPF_IN_SHARED): force $(BPF_GENERATED)
+$(SHARED_OBJDIR) $(STATIC_OBJDIR):
+	$(Q)mkdir -p $@
+
+$(BPF_IN_SHARED): force $(BPF_GENERATED) | $(SHARED_OBJDIR)
 	@(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
@@ -151,9 +156,11 @@ $(BPF_IN_SHARED): force $(BPF_GENERATED)
 	@(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
+	$(SILENT_MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= OUTPUT=$(SHARED_OBJDIR) $(SHARED_OBJDIR)fixdep
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)"
 
-$(BPF_IN_STATIC): force $(BPF_GENERATED)
+$(BPF_IN_STATIC): force $(BPF_GENERATED) | $(STATIC_OBJDIR)
+	$(SILENT_MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= OUTPUT=$(STATIC_OBJDIR) $(STATIC_OBJDIR)fixdep
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
 
 $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
@@ -263,7 +270,7 @@ install_pkgconfig: $(PC_FILE)
 
 install: install_lib install_pkgconfig install_headers
 
-clean:
+clean: fixdep-clean
 	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS)		     \
 		*~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_GENERATED)		     \
 		$(SHARED_OBJDIR) $(STATIC_OBJDIR)			     \
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 972e17ec0c09..a4a7b1ad1b63 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -100,7 +100,7 @@ struct bpf_prog_load_opts {
 	__u32 log_level;
 	__u32 log_size;
 	char *log_buf;
-	/* output: actual total log contents size (including termintaing zero).
+	/* output: actual total log contents size (including terminating zero).
 	 * It could be both larger than original log_size (if log was
 	 * truncated), or smaller (if log buffer wasn't filled completely).
 	 * If kernel doesn't support this feature, log_size is left unchanged.
@@ -129,7 +129,7 @@ struct bpf_btf_load_opts {
 	char *log_buf;
 	__u32 log_level;
 	__u32 log_size;
-	/* output: actual total log contents size (including termintaing zero).
+	/* output: actual total log contents size (including terminating zero).
 	 * It could be both larger than original log_size (if log was
 	 * truncated), or smaller (if log buffer wasn't filled completely).
 	 * If kernel doesn't support this feature, log_size is left unchanged.
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 305c62817dd3..80bc0242e8dc 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -341,7 +341,7 @@ extern void bpf_iter_num_destroy(struct bpf_iter_num *it) __weak __ksym;
  * I.e., it looks almost like high-level for each loop in other languages,
  * supports continue/break, and is verifiable by BPF verifier.
  *
- * For iterating integers, the difference betwen bpf_for_each(num, i, N, M)
+ * For iterating integers, the difference between bpf_for_each(num, i, N, M)
  * and bpf_for(i, N, M) is in that bpf_for() provides additional proof to
  * verifier that i is in [N, M) range, and in bpf_for_each() case i is `int
  * *`, not just `int`. So for integers bpf_for() is more convenient.
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index 9314fa95f04e..a8f6cd4841b0 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -163,7 +163,7 @@
 
 struct pt_regs___s390 {
 	unsigned long orig_gpr2;
-};
+} __attribute__((preserve_access_index));
 
 /* s390 provides user_pt_regs instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const user_pt_regs *)(x))
@@ -179,7 +179,7 @@ struct pt_regs___s390 {
 #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
 #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
 #define __PT_PARM6_SYSCALL_REG gprs[7]
-#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
+#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___s390 *)(x))->__PT_PARM1_SYSCALL_REG)
 #define PT_REGS_PARM1_CORE_SYSCALL(x) \
 	BPF_CORE_READ((const struct pt_regs___s390 *)(x), __PT_PARM1_SYSCALL_REG)
 
@@ -222,7 +222,7 @@ struct pt_regs___s390 {
 
 struct pt_regs___arm64 {
 	unsigned long orig_x0;
-};
+} __attribute__((preserve_access_index));
 
 /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x))
@@ -241,7 +241,7 @@ struct pt_regs___arm64 {
 #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
 #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
 #define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
-#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
+#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___arm64 *)(x))->__PT_PARM1_SYSCALL_REG)
 #define PT_REGS_PARM1_CORE_SYSCALL(x) \
 	BPF_CORE_READ((const struct pt_regs___arm64 *)(x), __PT_PARM1_SYSCALL_REG)
 
@@ -351,6 +351,10 @@ struct pt_regs___arm64 {
  * https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#risc-v-calling-conventions
  */
 
+struct pt_regs___riscv {
+	unsigned long orig_a0;
+} __attribute__((preserve_access_index));
+
 /* riscv provides struct user_regs_struct instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
 #define __PT_PARM1_REG a0
@@ -362,12 +366,15 @@ struct pt_regs___arm64 {
 #define __PT_PARM7_REG a6
 #define __PT_PARM8_REG a7
 
-#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG
+#define __PT_PARM1_SYSCALL_REG orig_a0
 #define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG
 #define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG
 #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
 #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
 #define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
+#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___riscv *)(x))->__PT_PARM1_SYSCALL_REG)
+#define PT_REGS_PARM1_CORE_SYSCALL(x) \
+	BPF_CORE_READ((const struct pt_regs___riscv *)(x), __PT_PARM1_SYSCALL_REG)
 
 #define __PT_RET_REG ra
 #define __PT_FP_REG s0
@@ -473,7 +480,7 @@ struct pt_regs;
 #endif
 /*
  * Similarly, syscall-specific conventions might differ between function call
- * conventions within each architecutre. All supported architectures pass
+ * conventions within each architecture. All supported architectures pass
  * either 6 or 7 syscall arguments in registers.
  *
  * See syscall(2) manpage for succinct table with information on each arch.
@@ -515,7 +522,7 @@ struct pt_regs;
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
 
-#elif defined(bpf_target_sparc)
+#elif defined(bpf_target_sparc) || defined(bpf_target_arm64)
 
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
@@ -651,7 +658,7 @@ struct pt_regs;
  * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
  * similar kinds of BPF programs, that accept input arguments as a single
  * pointer to untyped u64 array, where each u64 can actually be a typed
- * pointer or integer of different size. Instead of requring user to write
+ * pointer or integer of different size. Instead of requiring user to write
  * manual casts and work with array elements by index, BPF_PROG macro
  * allows user to declare a list of named and typed input arguments in the
  * same syntax as for normal C function. All the casting is hidden and
@@ -801,7 +808,7 @@ struct pt_regs;
  * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific
  * low-level way of getting kprobe input arguments from struct pt_regs, and
  * provides a familiar typed and named function arguments syntax and
- * semantics of accessing kprobe input paremeters.
+ * semantics of accessing kprobe input parameters.
  *
  * Original struct pt_regs* context is preserved as 'ctx' argument. This might
  * be necessary when using BPF helpers like bpf_perf_event_output().
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 32c00db3b91b..3c131039c523 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -996,6 +996,7 @@ static struct btf *btf_new_empty(struct btf *base_btf)
 		btf->base_btf = base_btf;
 		btf->start_id = btf__type_cnt(base_btf);
 		btf->start_str_off = base_btf->hdr->str_len;
+		btf->swapped_endian = base_btf->swapped_endian;
 	}
 
 	/* +1 for empty string at offset 0 */
@@ -4191,7 +4192,7 @@ static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id
  * and canonical graphs are not compatible structurally, whole graphs are
  * incompatible. If types are structurally equivalent (i.e., all information
  * except referenced type IDs is exactly the same), a mapping from `canon_id` to
- * a `cand_id` is recored in hypothetical mapping (`btf_dedup->hypot_map`).
+ * a `cand_id` is recoded in hypothetical mapping (`btf_dedup->hypot_map`).
  * If a type references other types, then those referenced types are checked
  * for equivalence recursively.
  *
@@ -4229,7 +4230,7 @@ static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id
  * consists of portions of the graph that come from multiple compilation units.
  * This is due to the fact that types within single compilation unit are always
  * deduplicated and FWDs are already resolved, if referenced struct/union
- * definiton is available. So, if we had unresolved FWD and found corresponding
+ * definition is available. So, if we had unresolved FWD and found corresponding
  * STRUCT/UNION, they will be from different compilation units. This
  * consequently means that when we "link" FWD to corresponding STRUCT/UNION,
  * type graph will likely have at least two different BTF types that describe
@@ -5394,6 +5395,9 @@ int btf__distill_base(const struct btf *src_btf, struct btf **new_base_btf,
 	new_base = btf__new_empty();
 	if (!new_base)
 		return libbpf_err(-ENOMEM);
+
+	btf__set_endianness(new_base, btf__endianness(src_btf));
+
 	dist.id_map = calloc(n, sizeof(*dist.id_map));
 	if (!dist.id_map) {
 		err = -ENOMEM;
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index b68d216837a9..4e349ad79ee6 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -286,7 +286,7 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d);
 LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id);
 
 struct btf_dump_emit_type_decl_opts {
-	/* size of this struct, for forward/backward compatiblity */
+	/* size of this struct, for forward/backward compatibility */
 	size_t sz;
 	/* optional field name for type declaration, e.g.:
 	 * - struct my_struct <FNAME>
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 894860111ddb..0a7327541c17 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -304,7 +304,7 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
  * definition, in which case they have to be declared inline as part of field
  * type declaration; or as a top-level anonymous enum, typically used for
  * declaring global constants. It's impossible to distinguish between two
- * without knowning whether given enum type was referenced from other type:
+ * without knowing whether given enum type was referenced from other type:
  * top-level anonymous enum won't be referenced by anything, while embedded
  * one will.
  */
diff --git a/tools/lib/bpf/btf_relocate.c b/tools/lib/bpf/btf_relocate.c
index 17f8b32f94a0..4f7399d85eab 100644
--- a/tools/lib/bpf/btf_relocate.c
+++ b/tools/lib/bpf/btf_relocate.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (c) 2024, Oracle and/or its affiliates. */
 
 #ifndef _GNU_SOURCE
diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index c92e02394159..b5ab1cb13e5e 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -28,6 +28,9 @@ int elf_open(const char *binary_path, struct elf_fd *elf_fd)
 	int fd, ret;
 	Elf *elf;
 
+	elf_fd->elf = NULL;
+	elf_fd->fd = -1;
+
 	if (elf_version(EV_CURRENT) == EV_NONE) {
 		pr_warn("elf: failed to init libelf for %s\n", binary_path);
 		return -LIBBPF_ERRNO__LIBELF;
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a3be6f8fac09..219facd0e66e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -496,8 +496,6 @@ struct bpf_program {
 };
 
 struct bpf_struct_ops {
-	const char *tname;
-	const struct btf_type *type;
 	struct bpf_program **progs;
 	__u32 *kern_func_off;
 	/* e.g. struct tcp_congestion_ops in bpf_prog's btf format */
@@ -988,7 +986,7 @@ find_struct_ops_kern_types(struct bpf_object *obj, const char *tname_raw,
 {
 	const struct btf_type *kern_type, *kern_vtype;
 	const struct btf_member *kern_data_member;
-	struct btf *btf;
+	struct btf *btf = NULL;
 	__s32 kern_vtype_id, kern_type_id;
 	char tname[256];
 	__u32 i;
@@ -1083,11 +1081,14 @@ static int bpf_object_adjust_struct_ops_autoload(struct bpf_object *obj)
 			continue;
 
 		for (j = 0; j < obj->nr_maps; ++j) {
+			const struct btf_type *type;
+
 			map = &obj->maps[j];
 			if (!bpf_map__is_struct_ops(map))
 				continue;
 
-			vlen = btf_vlen(map->st_ops->type);
+			type = btf__type_by_id(obj->btf, map->st_ops->type_id);
+			vlen = btf_vlen(type);
 			for (k = 0; k < vlen; ++k) {
 				slot_prog = map->st_ops->progs[k];
 				if (prog != slot_prog)
@@ -1115,14 +1116,14 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map)
 	const struct btf *btf = obj->btf;
 	struct bpf_struct_ops *st_ops;
 	const struct btf *kern_btf;
-	struct module_btf *mod_btf;
+	struct module_btf *mod_btf = NULL;
 	void *data, *kern_data;
 	const char *tname;
 	int err;
 
 	st_ops = map->st_ops;
-	type = st_ops->type;
-	tname = st_ops->tname;
+	type = btf__type_by_id(btf, st_ops->type_id);
+	tname = btf__name_by_offset(btf, type->name_off);
 	err = find_struct_ops_kern_types(obj, tname, &mod_btf,
 					 &kern_type, &kern_type_id,
 					 &kern_vtype, &kern_vtype_id,
@@ -1423,8 +1424,6 @@ static int init_struct_ops_maps(struct bpf_object *obj, const char *sec_name,
 		memcpy(st_ops->data,
 		       data->d_buf + vsi->offset,
 		       type->size);
-		st_ops->tname = tname;
-		st_ops->type = type;
 		st_ops->type_id = type_id;
 
 		pr_debug("struct_ops init: struct %s(type_id=%u) %s found at offset %u\n",
@@ -1849,7 +1848,7 @@ static char *internal_map_name(struct bpf_object *obj, const char *real_name)
 	snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name,
 		 sfx_len, real_name);
 
-	/* sanitise map name to characters allowed by kernel */
+	/* sanities map name to characters allowed by kernel */
 	for (p = map_name; *p && p < map_name + sizeof(map_name); p++)
 		if (!isalnum(*p) && *p != '_' && *p != '.')
 			*p = '_';
@@ -7906,16 +7905,19 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object
 }
 
 static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz,
+					  const char *obj_name,
 					  const struct bpf_object_open_opts *opts)
 {
-	const char *obj_name, *kconfig, *btf_tmp_path, *token_path;
+	const char *kconfig, *btf_tmp_path, *token_path;
 	struct bpf_object *obj;
-	char tmp_name[64];
 	int err;
 	char *log_buf;
 	size_t log_size;
 	__u32 log_level;
 
+	if (obj_buf && !obj_name)
+		return ERR_PTR(-EINVAL);
+
 	if (elf_version(EV_CURRENT) == EV_NONE) {
 		pr_warn("failed to init libelf for %s\n",
 			path ? : "(mem buf)");
@@ -7925,16 +7927,12 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
 	if (!OPTS_VALID(opts, bpf_object_open_opts))
 		return ERR_PTR(-EINVAL);
 
-	obj_name = OPTS_GET(opts, object_name, NULL);
+	obj_name = OPTS_GET(opts, object_name, NULL) ?: obj_name;
 	if (obj_buf) {
-		if (!obj_name) {
-			snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
-				 (unsigned long)obj_buf,
-				 (unsigned long)obj_buf_sz);
-			obj_name = tmp_name;
-		}
 		path = obj_name;
 		pr_debug("loading object '%s' from buffer\n", obj_name);
+	} else {
+		pr_debug("loading object from %s\n", path);
 	}
 
 	log_buf = OPTS_GET(opts, kernel_log_buf, NULL);
@@ -8018,9 +8016,7 @@ bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts)
 	if (!path)
 		return libbpf_err_ptr(-EINVAL);
 
-	pr_debug("loading %s\n", path);
-
-	return libbpf_ptr(bpf_object_open(path, NULL, 0, opts));
+	return libbpf_ptr(bpf_object_open(path, NULL, 0, NULL, opts));
 }
 
 struct bpf_object *bpf_object__open(const char *path)
@@ -8032,10 +8028,15 @@ struct bpf_object *
 bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
 		     const struct bpf_object_open_opts *opts)
 {
+	char tmp_name[64];
+
 	if (!obj_buf || obj_buf_sz == 0)
 		return libbpf_err_ptr(-EINVAL);
 
-	return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, opts));
+	/* create a (quite useless) default "name" for this memory buffer object */
+	snprintf(tmp_name, sizeof(tmp_name), "%lx-%zx", (unsigned long)obj_buf, obj_buf_sz);
+
+	return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, tmp_name, opts));
 }
 
 static int bpf_object_unload(struct bpf_object *obj)
@@ -8445,11 +8446,13 @@ static int bpf_object__resolve_externs(struct bpf_object *obj,
 
 static void bpf_map_prepare_vdata(const struct bpf_map *map)
 {
+	const struct btf_type *type;
 	struct bpf_struct_ops *st_ops;
 	__u32 i;
 
 	st_ops = map->st_ops;
-	for (i = 0; i < btf_vlen(st_ops->type); i++) {
+	type = btf__type_by_id(map->obj->btf, st_ops->type_id);
+	for (i = 0; i < btf_vlen(type); i++) {
 		struct bpf_program *prog = st_ops->progs[i];
 		void *kern_data;
 		int prog_fd;
@@ -9056,6 +9059,11 @@ unsigned int bpf_object__kversion(const struct bpf_object *obj)
 	return obj ? obj->kern_version : 0;
 }
 
+int bpf_object__token_fd(const struct bpf_object *obj)
+{
+	return obj->token_fd ?: -1;
+}
+
 struct btf *bpf_object__btf(const struct bpf_object *obj)
 {
 	return obj ? obj->btf : NULL;
@@ -9712,6 +9720,7 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
 static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 					    Elf64_Shdr *shdr, Elf_Data *data)
 {
+	const struct btf_type *type;
 	const struct btf_member *member;
 	struct bpf_struct_ops *st_ops;
 	struct bpf_program *prog;
@@ -9771,13 +9780,14 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 		}
 		insn_idx = sym->st_value / BPF_INSN_SZ;
 
-		member = find_member_by_offset(st_ops->type, moff * 8);
+		type = btf__type_by_id(btf, st_ops->type_id);
+		member = find_member_by_offset(type, moff * 8);
 		if (!member) {
 			pr_warn("struct_ops reloc %s: cannot find member at moff %u\n",
 				map->name, moff);
 			return -EINVAL;
 		}
-		member_idx = member - btf_members(st_ops->type);
+		member_idx = member - btf_members(type);
 		name = btf__name_by_offset(btf, member->name_off);
 
 		if (!resolve_func_ptr(btf, member->type, NULL)) {
@@ -11683,7 +11693,7 @@ static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, stru
 		ret = 0;
 		break;
 	case 3:
-		opts.retprobe = strcmp(probe_type, "uretprobe.multi") == 0;
+		opts.retprobe = str_has_pfx(probe_type, "uretprobe.multi");
 		*link = bpf_program__attach_uprobe_multi(prog, -1, binary_path, func_name, &opts);
 		ret = libbpf_get_error(*link);
 		break;
@@ -13758,29 +13768,13 @@ static int populate_skeleton_progs(const struct bpf_object *obj,
 int bpf_object__open_skeleton(struct bpf_object_skeleton *s,
 			      const struct bpf_object_open_opts *opts)
 {
-	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, skel_opts,
-		.object_name = s->name,
-	);
 	struct bpf_object *obj;
 	int err;
 
-	/* Attempt to preserve opts->object_name, unless overriden by user
-	 * explicitly. Overwriting object name for skeletons is discouraged,
-	 * as it breaks global data maps, because they contain object name
-	 * prefix as their own map name prefix. When skeleton is generated,
-	 * bpftool is making an assumption that this name will stay the same.
-	 */
-	if (opts) {
-		memcpy(&skel_opts, opts, sizeof(*opts));
-		if (!opts->object_name)
-			skel_opts.object_name = s->name;
-	}
-
-	obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts);
-	err = libbpf_get_error(obj);
-	if (err) {
-		pr_warn("failed to initialize skeleton BPF object '%s': %d\n",
-			s->name, err);
+	obj = bpf_object_open(NULL, s->data, s->data_sz, s->name, opts);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		pr_warn("failed to initialize skeleton BPF object '%s': %d\n", s->name, err);
 		return libbpf_err(err);
 	}
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 64a6a3d323e3..91484303849c 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -152,7 +152,7 @@ struct bpf_object_open_opts {
 	 * log_buf and log_level settings.
 	 *
 	 * If specified, this log buffer will be passed for:
-	 *   - each BPF progral load (BPF_PROG_LOAD) attempt, unless overriden
+	 *   - each BPF progral load (BPF_PROG_LOAD) attempt, unless overridden
 	 *     with bpf_program__set_log() on per-program level, to get
 	 *     BPF verifier log output.
 	 *   - during BPF object's BTF load into kernel (BPF_BTF_LOAD) to get
@@ -294,6 +294,14 @@ LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj);
 LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj);
 LIBBPF_API int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version);
 
+/**
+ * @brief **bpf_object__token_fd** is an accessor for BPF token FD associated
+ * with BPF object.
+ * @param obj Pointer to a valid BPF object
+ * @return BPF token FD or -1, if it wasn't set
+ */
+LIBBPF_API int bpf_object__token_fd(const struct bpf_object *obj);
+
 struct btf;
 LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj);
 LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj);
@@ -455,7 +463,7 @@ LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
 /**
  * @brief **bpf_program__attach()** is a generic function for attaching
  * a BPF program based on auto-detection of program type, attach type,
- * and extra paremeters, where applicable.
+ * and extra parameters, where applicable.
  *
  * @param prog BPF program to attach
  * @return Reference to the newly created BPF link; or NULL is returned on error,
@@ -679,7 +687,7 @@ struct bpf_uprobe_opts {
 /**
  * @brief **bpf_program__attach_uprobe()** attaches a BPF program
  * to the userspace function which is found by binary path and
- * offset. You can optionally specify a particular proccess to attach
+ * offset. You can optionally specify a particular process to attach
  * to. You can also optionally attach the program to the function
  * exit instead of entry.
  *
@@ -1593,11 +1601,11 @@ LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_i
  * memory region of the ring buffer.
  * This ring buffer can be used to implement a custom events consumer.
  * The ring buffer starts with the *struct perf_event_mmap_page*, which
- * holds the ring buffer managment fields, when accessing the header
+ * holds the ring buffer management fields, when accessing the header
  * structure it's important to be SMP aware.
  * You can refer to *perf_event_read_simple* for a simple example.
  * @param pb the perf buffer structure
- * @param buf_idx the buffer index to retreive
+ * @param buf_idx the buffer index to retrieve
  * @param buf (out) gets the base pointer of the mmap()'ed memory
  * @param buf_size (out) gets the size of the mmap()'ed region
  * @return 0 on success, negative error code for failure
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 8f0d9ea3b1b4..0096e483f7eb 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -423,6 +423,7 @@ LIBBPF_1.5.0 {
 		btf__relocate;
 		bpf_map__autoattach;
 		bpf_map__set_autoattach;
+		bpf_object__token_fd;
 		bpf_program__attach_sockmap;
 		ring__consume_n;
 		ring_buffer__consume_n;
diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h
index 1e1be467bede..60b2600be88a 100644
--- a/tools/lib/bpf/libbpf_legacy.h
+++ b/tools/lib/bpf/libbpf_legacy.h
@@ -76,7 +76,7 @@ enum libbpf_strict_mode {
 	 * first BPF program or map creation operation. This is done only if
 	 * kernel is too old to support memcg-based memory accounting for BPF
 	 * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY,
-	 * but it can be overriden with libbpf_set_memlock_rlim() API.
+	 * but it can be overridden with libbpf_set_memlock_rlim() API.
 	 * Note that libbpf_set_memlock_rlim() needs to be called before
 	 * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load()
 	 * operation.
@@ -97,7 +97,7 @@ LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode);
  * @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
+ * @return error code; or 0 if no error occurred
  *
  * Note, as of libbpf 1.0 this function is not necessary and not recommended
  * to be used. Libbpf doesn't return error code embedded into the pointer
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 9cd3d4109788..e0005c6ade88 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -1413,7 +1413,7 @@ recur:
 		return true;
 	case BTF_KIND_PTR:
 		/* just validate overall shape of the referenced type, so no
-		 * contents comparison for struct/union, and allowd fwd vs
+		 * contents comparison for struct/union, and allowed fwd vs
 		 * struct/union
 		 */
 		exact = false;
@@ -1962,7 +1962,7 @@ static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj,
 
 		/* If existing symbol is a strong resolved symbol, bail out,
 		 * because we lost resolution battle have nothing to
-		 * contribute. We already checked abover that there is no
+		 * contribute. We already checked above that there is no
 		 * strong-strong conflict. We also already tightened binding
 		 * and visibility, so nothing else to contribute at that point.
 		 */
diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h
index 1e82ab06c3eb..0875452521e9 100644
--- a/tools/lib/bpf/skel_internal.h
+++ b/tools/lib/bpf/skel_internal.h
@@ -107,7 +107,7 @@ static inline void skel_free(const void *p)
  * The loader program will perform probe_read_kernel() from maps.rodata.initial_value.
  * skel_finalize_map_data() sets skel->rodata to point to actual value in a bpf map and
  * does maps.rodata.initial_value = ~0ULL to signal skel_free_map_data() that kvfree
- * is not nessary.
+ * is not necessary.
  *
  * For user space:
  * skel_prep_map_data() mmaps anon memory into skel->rodata that can be accessed directly.
diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h
index 76359bcdc94a..b811f754939f 100644
--- a/tools/lib/bpf/usdt.bpf.h
+++ b/tools/lib/bpf/usdt.bpf.h
@@ -39,7 +39,7 @@ enum __bpf_usdt_arg_type {
 struct __bpf_usdt_arg_spec {
 	/* u64 scalar interpreted depending on arg_type, see below */
 	__u64 val_off;
-	/* arg location case, see bpf_udst_arg() for details */
+	/* arg location case, see bpf_usdt_arg() for details */
 	enum __bpf_usdt_arg_type arg_type;
 	/* offset of referenced register within struct pt_regs */
 	short reg_off;
diff --git a/tools/lib/perf/.gitignore b/tools/lib/perf/.gitignore
new file mode 100644
index 000000000000..0f5b4af63f62
--- /dev/null
+++ b/tools/lib/perf/.gitignore
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
+libperf.pc
+libperf.so.*
+tests-shared
+tests-static
diff --git a/tools/lib/string.c b/tools/lib/string.c
index 8b6892f959ab..3126d2cff716 100644
--- a/tools/lib/string.c
+++ b/tools/lib/string.c
@@ -153,6 +153,19 @@ char *strim(char *s)
 	return skip_spaces(s);
 }
 
+/*
+ * remove_spaces - Removes whitespaces from @s
+ */
+void remove_spaces(char *s)
+{
+	char *d = s;
+
+	do {
+		while (*d == ' ')
+			++d;
+	} while ((*s++ = *d++));
+}
+
 /**
  * strreplace - Replace all occurrences of character in string.
  * @s: The string to operate on.
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
index b87213263a5e..8703ab487b68 100644
--- a/tools/lib/subcmd/Makefile
+++ b/tools/lib/subcmd/Makefile
@@ -38,10 +38,8 @@ endif
 
 ifeq ($(DEBUG),1)
   CFLAGS += -O0
-else ifeq ($(CC_NO_CLANG), 0)
-  CFLAGS += -O3
 else
-  CFLAGS += -O6
+  CFLAGS += -O3
 endif
 
 # Treat warnings as errors unless directed not to
@@ -76,7 +74,7 @@ include $(srctree)/tools/build/Makefile.include
 
 all: fixdep $(LIBFILE)
 
-$(SUBCMD_IN): FORCE
+$(SUBCMD_IN): fixdep FORCE
 	@$(MAKE) $(build)=libsubcmd
 
 $(LIBFILE): $(SUBCMD_IN)
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index 4b60ec03b0bb..eb896d30545b 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -633,10 +633,11 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o
 			const char *const subcommands[], const char *usagestr[], int flags)
 {
 	struct parse_opt_ctx_t ctx;
-	char *buf = NULL;
 
 	/* build usage string if it's not provided */
 	if (subcommands && !usagestr[0]) {
+		char *buf = NULL;
+
 		astrcatf(&buf, "%s %s [<options>] {", subcmd_config.exec_name, argv[0]);
 
 		for (int i = 0; subcommands[i]; i++) {
@@ -678,10 +679,7 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o
 			astrcatf(&error_buf, "unknown switch `%c'", *ctx.opt);
 		usage_with_options(usagestr, options);
 	}
-	if (buf) {
-		usagestr[0] = NULL;
-		free(buf);
-	}
+
 	return parse_options_end(&ctx);
 }
 
diff --git a/tools/lib/symbol/Makefile b/tools/lib/symbol/Makefile
index 13d43c6f92b4..426b845edfac 100644
--- a/tools/lib/symbol/Makefile
+++ b/tools/lib/symbol/Makefile
@@ -31,11 +31,7 @@ CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 CFLAGS += -ggdb3 -Wall -Wextra -std=gnu11 -U_FORTIFY_SOURCE -fPIC
 
 ifeq ($(DEBUG),0)
-ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
-else
-  CFLAGS += -O6
-endif
 endif
 
 ifeq ($(DEBUG),0)