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

To resolve a trivial merge conflict with c302378bc157f6a7 ("libbpf:
Hashmap interface update to allow both long and void* keys/values"),
where a function present upstream was removed in the perf tools
development tree.

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

13 files changed, 613 insertions, 290 deletions

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 7f5f7d2ebe1f..cf7f02c67968 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -287,3 +287,20 @@ tags:
 
 # Delete partially updated (corrupted) files on error
 .DELETE_ON_ERROR:
+
+help:
+	@echo 'libbpf common targets:'
+	@echo '  HINT: use "V=1" to enable verbose build'
+	@echo '  all     - build libraries and pkgconfig'
+	@echo '  clean   - remove all generated files'
+	@echo '  check   - check abi and version info'
+	@echo ''
+	@echo 'libbpf install targets:'
+	@echo '  HINT: use "prefix"(defaults to "/usr/local") or "DESTDIR" (defaults to "/")'
+	@echo '        to adjust target desitantion, e.g. "make prefix=/usr/local install"'
+	@echo '  install          - build and install all headers, libraries and pkgconfig'
+	@echo '  install_headers  - install only headers to include/bpf'
+	@echo ''
+	@echo 'libbpf make targets:'
+	@echo '  tags    - use ctags to make tag information for source code browsing'
+	@echo '  cscope  - use cscope to make interactive source code browsing database'
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 1d49a0352836..9aff98f42a3d 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -935,58 +935,98 @@ int bpf_link_get_next_id(__u32 start_id, __u32 *next_id)
 	return bpf_obj_get_next_id(start_id, next_id, BPF_LINK_GET_NEXT_ID);
 }
 
-int bpf_prog_get_fd_by_id(__u32 id)
+int bpf_prog_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);
 	union bpf_attr attr;
 	int fd;
 
+	if (!OPTS_VALID(opts, bpf_get_fd_by_id_opts))
+		return libbpf_err(-EINVAL);
+
 	memset(&attr, 0, attr_sz);
 	attr.prog_id = id;
+	attr.open_flags = OPTS_GET(opts, open_flags, 0);
 
 	fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
-int bpf_map_get_fd_by_id(__u32 id)
+int bpf_prog_get_fd_by_id(__u32 id)
+{
+	return bpf_prog_get_fd_by_id_opts(id, NULL);
+}
+
+int bpf_map_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);
 	union bpf_attr attr;
 	int fd;
 
+	if (!OPTS_VALID(opts, bpf_get_fd_by_id_opts))
+		return libbpf_err(-EINVAL);
+
 	memset(&attr, 0, attr_sz);
 	attr.map_id = id;
+	attr.open_flags = OPTS_GET(opts, open_flags, 0);
 
 	fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
-int bpf_btf_get_fd_by_id(__u32 id)
+int bpf_map_get_fd_by_id(__u32 id)
+{
+	return bpf_map_get_fd_by_id_opts(id, NULL);
+}
+
+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);
 	union bpf_attr attr;
 	int fd;
 
+	if (!OPTS_VALID(opts, bpf_get_fd_by_id_opts))
+		return libbpf_err(-EINVAL);
+
 	memset(&attr, 0, attr_sz);
 	attr.btf_id = id;
+	attr.open_flags = OPTS_GET(opts, open_flags, 0);
 
 	fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
-int bpf_link_get_fd_by_id(__u32 id)
+int bpf_btf_get_fd_by_id(__u32 id)
+{
+	return bpf_btf_get_fd_by_id_opts(id, NULL);
+}
+
+int bpf_link_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);
 	union bpf_attr attr;
 	int fd;
 
+	if (!OPTS_VALID(opts, bpf_get_fd_by_id_opts))
+		return libbpf_err(-EINVAL);
+
 	memset(&attr, 0, attr_sz);
 	attr.link_id = id;
+	attr.open_flags = OPTS_GET(opts, open_flags, 0);
 
 	fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
+int bpf_link_get_fd_by_id(__u32 id)
+{
+	return bpf_link_get_fd_by_id_opts(id, NULL);
+}
+
 int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, info);
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 9c50beabdd14..7468978d3c27 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -365,10 +365,26 @@ LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id);
 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 */
+	size_t :0;
+};
+#define bpf_get_fd_by_id_opts__last_field open_flags
+
 LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_prog_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_map_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_map_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_btf_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_link_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_link_get_fd_by_id_opts(__u32 id,
+				const struct bpf_get_fd_by_id_opts *opts);
 LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len);
 
 struct bpf_prog_query_opts {
@@ -393,8 +409,15 @@ LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
 				 __u64 *probe_offset, __u64 *probe_addr);
 
+#ifdef __cplusplus
+/* forward-declaring enums in C++ isn't compatible with pure C enums, so
+ * instead define bpf_enable_stats() as accepting int as an input
+ */
+LIBBPF_API int bpf_enable_stats(int type);
+#else
 enum bpf_stats_type; /* defined in up-to-date linux/bpf.h */
 LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type);
+#endif
 
 struct bpf_prog_bind_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index d88647da2c7f..71e165b09ed5 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1559,15 +1559,15 @@ struct btf_pipe {
 static int btf_rewrite_str(__u32 *str_off, void *ctx)
 {
 	struct btf_pipe *p = ctx;
-	void *mapped_off;
+	long mapped_off;
 	int off, err;
 
 	if (!*str_off) /* nothing to do for empty strings */
 		return 0;
 
 	if (p->str_off_map &&
-	    hashmap__find(p->str_off_map, (void *)(long)*str_off, &mapped_off)) {
-		*str_off = (__u32)(long)mapped_off;
+	    hashmap__find(p->str_off_map, *str_off, &mapped_off)) {
+		*str_off = mapped_off;
 		return 0;
 	}
 
@@ -1579,7 +1579,7 @@ static int btf_rewrite_str(__u32 *str_off, void *ctx)
 	 * performing expensive string comparisons.
 	 */
 	if (p->str_off_map) {
-		err = hashmap__append(p->str_off_map, (void *)(long)*str_off, (void *)(long)off);
+		err = hashmap__append(p->str_off_map, *str_off, off);
 		if (err)
 			return err;
 	}
@@ -1630,8 +1630,8 @@ static int btf_rewrite_type_ids(__u32 *type_id, void *ctx)
 	return 0;
 }
 
-static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx);
-static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx);
+static size_t btf_dedup_identity_hash_fn(long key, void *ctx);
+static bool btf_dedup_equal_fn(long k1, long k2, void *ctx);
 
 int btf__add_btf(struct btf *btf, const struct btf *src_btf)
 {
@@ -1724,7 +1724,8 @@ err_out:
 	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 */
+	 * wasn't modified, so doesn't need restoring, see big comment above
+	 */
 	btf->hdr->str_len = old_strs_len;
 
 	hashmap__free(p.str_off_map);
@@ -2329,7 +2330,7 @@ int btf__add_restrict(struct btf *btf, int ref_type_id)
  */
 int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id)
 {
-	if (!value|| !value[0])
+	if (!value || !value[0])
 		return libbpf_err(-EINVAL);
 
 	return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id);
@@ -2881,6 +2882,7 @@ static int btf_dedup_strings(struct btf_dedup *d);
 static int btf_dedup_prim_types(struct btf_dedup *d);
 static int btf_dedup_struct_types(struct btf_dedup *d);
 static int btf_dedup_ref_types(struct btf_dedup *d);
+static int btf_dedup_resolve_fwds(struct btf_dedup *d);
 static int btf_dedup_compact_types(struct btf_dedup *d);
 static int btf_dedup_remap_types(struct btf_dedup *d);
 
@@ -2988,15 +2990,16 @@ static int btf_dedup_remap_types(struct btf_dedup *d);
  * Algorithm summary
  * =================
  *
- * Algorithm completes its work in 6 separate passes:
+ * Algorithm completes its work in 7 separate passes:
  *
  * 1. Strings deduplication.
  * 2. Primitive types deduplication (int, enum, fwd).
  * 3. Struct/union types deduplication.
- * 4. Reference types deduplication (pointers, typedefs, arrays, funcs, func
+ * 4. Resolve unambiguous forward declarations.
+ * 5. Reference types deduplication (pointers, typedefs, arrays, funcs, func
  *    protos, and const/volatile/restrict modifiers).
- * 5. Types compaction.
- * 6. Types remapping.
+ * 6. Types compaction.
+ * 7. Types remapping.
  *
  * Algorithm determines canonical type descriptor, which is a single
  * representative type for each truly unique type. This canonical type is the
@@ -3060,6 +3063,11 @@ int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts)
 		pr_debug("btf_dedup_struct_types failed:%d\n", err);
 		goto done;
 	}
+	err = btf_dedup_resolve_fwds(d);
+	if (err < 0) {
+		pr_debug("btf_dedup_resolve_fwds failed:%d\n", err);
+		goto done;
+	}
 	err = btf_dedup_ref_types(d);
 	if (err < 0) {
 		pr_debug("btf_dedup_ref_types failed:%d\n", err);
@@ -3126,12 +3134,11 @@ static long hash_combine(long h, long value)
 }
 
 #define for_each_dedup_cand(d, node, hash) \
-	hashmap__for_each_key_entry(d->dedup_table, node, (void *)hash)
+	hashmap__for_each_key_entry(d->dedup_table, node, hash)
 
 static int btf_dedup_table_add(struct btf_dedup *d, long hash, __u32 type_id)
 {
-	return hashmap__append(d->dedup_table,
-			       (void *)hash, (void *)(long)type_id);
+	return hashmap__append(d->dedup_table, hash, type_id);
 }
 
 static int btf_dedup_hypot_map_add(struct btf_dedup *d,
@@ -3178,17 +3185,17 @@ static void btf_dedup_free(struct btf_dedup *d)
 	free(d);
 }
 
-static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx)
+static size_t btf_dedup_identity_hash_fn(long key, void *ctx)
 {
-	return (size_t)key;
+	return key;
 }
 
-static size_t btf_dedup_collision_hash_fn(const void *key, void *ctx)
+static size_t btf_dedup_collision_hash_fn(long key, void *ctx)
 {
 	return 0;
 }
 
-static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx)
+static bool btf_dedup_equal_fn(long k1, long k2, void *ctx)
 {
 	return k1 == k2;
 }
@@ -3404,23 +3411,17 @@ static long btf_hash_enum(struct btf_type *t)
 {
 	long h;
 
-	/* don't hash vlen and enum members to support enum fwd resolving */
+	/* don't hash vlen, enum members and size to support enum fwd resolving */
 	h = hash_combine(0, t->name_off);
-	h = hash_combine(h, t->info & ~0xffff);
-	h = hash_combine(h, t->size);
 	return h;
 }
 
-/* Check structural equality of two ENUMs. */
-static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
+static bool btf_equal_enum_members(struct btf_type *t1, struct btf_type *t2)
 {
 	const struct btf_enum *m1, *m2;
 	__u16 vlen;
 	int i;
 
-	if (!btf_equal_common(t1, t2))
-		return false;
-
 	vlen = btf_vlen(t1);
 	m1 = btf_enum(t1);
 	m2 = btf_enum(t2);
@@ -3433,15 +3434,12 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
 	return true;
 }
 
-static bool btf_equal_enum64(struct btf_type *t1, struct btf_type *t2)
+static bool btf_equal_enum64_members(struct btf_type *t1, struct btf_type *t2)
 {
 	const struct btf_enum64 *m1, *m2;
 	__u16 vlen;
 	int i;
 
-	if (!btf_equal_common(t1, t2))
-		return false;
-
 	vlen = btf_vlen(t1);
 	m1 = btf_enum64(t1);
 	m2 = btf_enum64(t2);
@@ -3455,6 +3453,19 @@ static bool btf_equal_enum64(struct btf_type *t1, struct btf_type *t2)
 	return true;
 }
 
+/* Check structural equality of two ENUMs or ENUM64s. */
+static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
+{
+	if (!btf_equal_common(t1, t2))
+		return false;
+
+	/* t1 & t2 kinds are identical because of btf_equal_common */
+	if (btf_kind(t1) == BTF_KIND_ENUM)
+		return btf_equal_enum_members(t1, t2);
+	else
+		return btf_equal_enum64_members(t1, t2);
+}
+
 static inline bool btf_is_enum_fwd(struct btf_type *t)
 {
 	return btf_is_any_enum(t) && btf_vlen(t) == 0;
@@ -3464,21 +3475,14 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
 {
 	if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2))
 		return btf_equal_enum(t1, t2);
-	/* ignore vlen when comparing */
-	return t1->name_off == t2->name_off &&
-	       (t1->info & ~0xffff) == (t2->info & ~0xffff) &&
-	       t1->size == t2->size;
-}
-
-static bool btf_compat_enum64(struct btf_type *t1, struct btf_type *t2)
-{
-	if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2))
-		return btf_equal_enum64(t1, t2);
-
-	/* ignore vlen when comparing */
+	/* At this point either t1 or t2 or both are forward declarations, thus:
+	 * - skip comparing vlen because it is zero for forward declarations;
+	 * - skip comparing size to allow enum forward declarations
+	 *   to be compatible with enum64 full declarations;
+	 * - skip comparing kind for the same reason.
+	 */
 	return t1->name_off == t2->name_off &&
-	       (t1->info & ~0xffff) == (t2->info & ~0xffff) &&
-	       t1->size == t2->size;
+	       btf_is_any_enum(t1) && btf_is_any_enum(t2);
 }
 
 /*
@@ -3753,7 +3757,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 	case BTF_KIND_INT:
 		h = btf_hash_int_decl_tag(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_int_tag(t, cand)) {
 				new_id = cand_id;
@@ -3763,9 +3767,10 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 		break;
 
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 		h = btf_hash_enum(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_enum(t, cand)) {
 				new_id = cand_id;
@@ -3783,32 +3788,11 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 		}
 		break;
 
-	case BTF_KIND_ENUM64:
-		h = btf_hash_enum(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_enum64(t, cand)) {
-				new_id = cand_id;
-				break;
-			}
-			if (btf_compat_enum64(t, cand)) {
-				if (btf_is_enum_fwd(t)) {
-					/* resolve fwd to full enum */
-					new_id = cand_id;
-					break;
-				}
-				/* resolve canonical enum fwd to full enum */
-				d->map[cand_id] = type_id;
-			}
-		}
-		break;
-
 	case BTF_KIND_FWD:
 	case BTF_KIND_FLOAT:
 		h = btf_hash_common(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_common(t, cand)) {
 				new_id = cand_id;
@@ -3887,14 +3871,14 @@ static inline __u16 btf_fwd_kind(struct btf_type *t)
 }
 
 /* Check if given two types are identical ARRAY definitions */
-static int btf_dedup_identical_arrays(struct btf_dedup *d, __u32 id1, __u32 id2)
+static bool btf_dedup_identical_arrays(struct btf_dedup *d, __u32 id1, __u32 id2)
 {
 	struct btf_type *t1, *t2;
 
 	t1 = btf_type_by_id(d->btf, id1);
 	t2 = btf_type_by_id(d->btf, id2);
 	if (!btf_is_array(t1) || !btf_is_array(t2))
-		return 0;
+		return false;
 
 	return btf_equal_array(t1, t2);
 }
@@ -3918,7 +3902,9 @@ static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id
 	m1 = btf_members(t1);
 	m2 = btf_members(t2);
 	for (i = 0, n = btf_vlen(t1); i < n; i++, m1++, m2++) {
-		if (m1->type != m2->type)
+		if (m1->type != m2->type &&
+		    !btf_dedup_identical_arrays(d, m1->type, m2->type) &&
+		    !btf_dedup_identical_structs(d, m1->type, m2->type))
 			return false;
 	}
 	return true;
@@ -4097,10 +4083,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		return btf_equal_int_tag(cand_type, canon_type);
 
 	case BTF_KIND_ENUM:
-		return btf_compat_enum(cand_type, canon_type);
-
 	case BTF_KIND_ENUM64:
-		return btf_compat_enum64(cand_type, canon_type);
+		return btf_compat_enum(cand_type, canon_type);
 
 	case BTF_KIND_FWD:
 	case BTF_KIND_FLOAT:
@@ -4311,7 +4295,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 
 	h = btf_hash_struct(t);
 	for_each_dedup_cand(d, hash_entry, h) {
-		__u32 cand_id = (__u32)(long)hash_entry->value;
+		__u32 cand_id = hash_entry->value;
 		int eq;
 
 		/*
@@ -4416,7 +4400,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 
 		h = btf_hash_common(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_common(t, cand)) {
 				new_id = cand_id;
@@ -4433,7 +4417,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 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_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_int_tag(t, cand)) {
 				new_id = cand_id;
@@ -4457,7 +4441,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 
 		h = btf_hash_array(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_array(t, cand)) {
 				new_id = cand_id;
@@ -4489,7 +4473,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 
 		h = btf_hash_fnproto(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_fnproto(t, cand)) {
 				new_id = cand_id;
@@ -4526,6 +4510,134 @@ static int btf_dedup_ref_types(struct btf_dedup *d)
 }
 
 /*
+ * Collect a map from type names to type ids for all canonical structs
+ * and unions. If the same name is shared by several canonical types
+ * use a special value 0 to indicate this fact.
+ */
+static int btf_dedup_fill_unique_names_map(struct btf_dedup *d, struct hashmap *names_map)
+{
+	__u32 nr_types = btf__type_cnt(d->btf);
+	struct btf_type *t;
+	__u32 type_id;
+	__u16 kind;
+	int err;
+
+	/*
+	 * Iterate over base and split module ids in order to get all
+	 * available structs in the map.
+	 */
+	for (type_id = 1; type_id < nr_types; ++type_id) {
+		t = btf_type_by_id(d->btf, type_id);
+		kind = btf_kind(t);
+
+		if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION)
+			continue;
+
+		/* Skip non-canonical types */
+		if (type_id != d->map[type_id])
+			continue;
+
+		err = hashmap__add(names_map, t->name_off, type_id);
+		if (err == -EEXIST)
+			err = hashmap__set(names_map, t->name_off, 0, NULL, NULL);
+
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int btf_dedup_resolve_fwd(struct btf_dedup *d, struct hashmap *names_map, __u32 type_id)
+{
+	struct btf_type *t = btf_type_by_id(d->btf, type_id);
+	enum btf_fwd_kind fwd_kind = btf_kflag(t);
+	__u16 cand_kind, kind = btf_kind(t);
+	struct btf_type *cand_t;
+	uintptr_t cand_id;
+
+	if (kind != BTF_KIND_FWD)
+		return 0;
+
+	/* Skip if this FWD already has a mapping */
+	if (type_id != d->map[type_id])
+		return 0;
+
+	if (!hashmap__find(names_map, t->name_off, &cand_id))
+		return 0;
+
+	/* Zero is a special value indicating that name is not unique */
+	if (!cand_id)
+		return 0;
+
+	cand_t = btf_type_by_id(d->btf, cand_id);
+	cand_kind = btf_kind(cand_t);
+	if ((cand_kind == BTF_KIND_STRUCT && fwd_kind != BTF_FWD_STRUCT) ||
+	    (cand_kind == BTF_KIND_UNION && fwd_kind != BTF_FWD_UNION))
+		return 0;
+
+	d->map[type_id] = cand_id;
+
+	return 0;
+}
+
+/*
+ * Resolve unambiguous forward declarations.
+ *
+ * The lion's share of all FWD declarations is resolved during
+ * `btf_dedup_struct_types` phase when different type graphs are
+ * compared against each other. However, if in some compilation unit a
+ * FWD declaration is not a part of a type graph compared against
+ * another type graph that declaration's canonical type would not be
+ * changed. Example:
+ *
+ * CU #1:
+ *
+ * struct foo;
+ * struct foo *some_global;
+ *
+ * CU #2:
+ *
+ * struct foo { int u; };
+ * struct foo *another_global;
+ *
+ * After `btf_dedup_struct_types` the BTF looks as follows:
+ *
+ * [1] STRUCT 'foo' size=4 vlen=1 ...
+ * [2] INT 'int' size=4 ...
+ * [3] PTR '(anon)' type_id=1
+ * [4] FWD 'foo' fwd_kind=struct
+ * [5] PTR '(anon)' type_id=4
+ *
+ * This pass assumes that such FWD declarations should be mapped to
+ * structs or unions with identical name in case if the name is not
+ * ambiguous.
+ */
+static int btf_dedup_resolve_fwds(struct btf_dedup *d)
+{
+	int i, err;
+	struct hashmap *names_map;
+
+	names_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL);
+	if (IS_ERR(names_map))
+		return PTR_ERR(names_map);
+
+	err = btf_dedup_fill_unique_names_map(d, names_map);
+	if (err < 0)
+		goto exit;
+
+	for (i = 0; i < d->btf->nr_types; i++) {
+		err = btf_dedup_resolve_fwd(d, names_map, d->btf->start_id + i);
+		if (err < 0)
+			break;
+	}
+
+exit:
+	hashmap__free(names_map);
+	return err;
+}
+
+/*
  * Compact types.
  *
  * After we established for each type its corresponding canonical representative
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 4221f73a74d0..deb2bc9a0a7b 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -117,14 +117,14 @@ struct btf_dump {
 	struct btf_dump_data *typed_dump;
 };
 
-static size_t str_hash_fn(const void *key, void *ctx)
+static size_t str_hash_fn(long key, void *ctx)
 {
-	return str_hash(key);
+	return str_hash((void *)key);
 }
 
-static bool str_equal_fn(const void *a, const void *b, void *ctx)
+static bool str_equal_fn(long a, long b, void *ctx)
 {
-	return strcmp(a, b) == 0;
+	return strcmp((void *)a, (void *)b) == 0;
 }
 
 static const char *btf_name_of(const struct btf_dump *d, __u32 name_off)
@@ -219,6 +219,17 @@ static int btf_dump_resize(struct btf_dump *d)
 	return 0;
 }
 
+static void btf_dump_free_names(struct hashmap *map)
+{
+	size_t bkt;
+	struct hashmap_entry *cur;
+
+	hashmap__for_each_entry(map, cur, bkt)
+		free((void *)cur->pkey);
+
+	hashmap__free(map);
+}
+
 void btf_dump__free(struct btf_dump *d)
 {
 	int i;
@@ -237,8 +248,8 @@ void btf_dump__free(struct btf_dump *d)
 	free(d->cached_names);
 	free(d->emit_queue);
 	free(d->decl_stack);
-	hashmap__free(d->type_names);
-	hashmap__free(d->ident_names);
+	btf_dump_free_names(d->type_names);
+	btf_dump_free_names(d->ident_names);
 
 	free(d);
 }
@@ -944,7 +955,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 					  lvl + 1);
 	}
 
-	if (vlen)
+	/*
+	 * Keep `struct empty {}` on a single line,
+	 * only print newline when there are regular or padding fields.
+	 */
+	if (vlen || t->size)
 		btf_dump_printf(d, "\n");
 	btf_dump_printf(d, "%s}", pfx(lvl));
 	if (packed)
@@ -1520,11 +1535,22 @@ static void btf_dump_emit_type_cast(struct btf_dump *d, __u32 id,
 static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map,
 				 const char *orig_name)
 {
+	char *old_name, *new_name;
 	size_t dup_cnt = 0;
+	int err;
+
+	new_name = strdup(orig_name);
+	if (!new_name)
+		return 1;
 
-	hashmap__find(name_map, orig_name, (void **)&dup_cnt);
+	(void)hashmap__find(name_map, orig_name, &dup_cnt);
 	dup_cnt++;
-	hashmap__set(name_map, orig_name, (void *)dup_cnt, NULL, NULL);
+
+	err = hashmap__set(name_map, new_name, dup_cnt, &old_name, NULL);
+	if (err)
+		free(new_name);
+
+	free(old_name);
 
 	return dup_cnt;
 }
@@ -1963,7 +1989,7 @@ static int btf_dump_struct_data(struct btf_dump *d,
 {
 	const struct btf_member *m = btf_members(t);
 	__u16 n = btf_vlen(t);
-	int i, err;
+	int i, err = 0;
 
 	/* note that we increment depth before calling btf_dump_print() below;
 	 * this is intentional.  btf_dump_data_newline() will not print a
diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c
index aeb09c288716..140ee4055676 100644
--- a/tools/lib/bpf/hashmap.c
+++ b/tools/lib/bpf/hashmap.c
@@ -128,7 +128,7 @@ static int hashmap_grow(struct hashmap *map)
 }
 
 static bool hashmap_find_entry(const struct hashmap *map,
-			       const void *key, size_t hash,
+			       const long key, size_t hash,
 			       struct hashmap_entry ***pprev,
 			       struct hashmap_entry **entry)
 {
@@ -151,18 +151,18 @@ static bool hashmap_find_entry(const struct hashmap *map,
 	return false;
 }
 
-int hashmap__insert(struct hashmap *map, const void *key, void *value,
-		    enum hashmap_insert_strategy strategy,
-		    const void **old_key, void **old_value)
+int hashmap_insert(struct hashmap *map, long key, long value,
+		   enum hashmap_insert_strategy strategy,
+		   long *old_key, long *old_value)
 {
 	struct hashmap_entry *entry;
 	size_t h;
 	int err;
 
 	if (old_key)
-		*old_key = NULL;
+		*old_key = 0;
 	if (old_value)
-		*old_value = NULL;
+		*old_value = 0;
 
 	h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
 	if (strategy != HASHMAP_APPEND &&
@@ -203,7 +203,7 @@ int hashmap__insert(struct hashmap *map, const void *key, void *value,
 	return 0;
 }
 
-bool hashmap__find(const struct hashmap *map, const void *key, void **value)
+bool hashmap_find(const struct hashmap *map, long key, long *value)
 {
 	struct hashmap_entry *entry;
 	size_t h;
@@ -217,8 +217,8 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value)
 	return true;
 }
 
-bool hashmap__delete(struct hashmap *map, const void *key,
-		     const void **old_key, void **old_value)
+bool hashmap_delete(struct hashmap *map, long key,
+		    long *old_key, long *old_value)
 {
 	struct hashmap_entry **pprev, *entry;
 	size_t h;
diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
index 10a4c4cd13cf..0a5bf1937a7c 100644
--- a/tools/lib/bpf/hashmap.h
+++ b/tools/lib/bpf/hashmap.h
@@ -40,12 +40,32 @@ static inline size_t str_hash(const char *s)
 	return h;
 }
 
-typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
-typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
+typedef size_t (*hashmap_hash_fn)(long key, void *ctx);
+typedef bool (*hashmap_equal_fn)(long key1, long key2, void *ctx);
 
+/*
+ * Hashmap interface is polymorphic, keys and values could be either
+ * long-sized integers or pointers, this is achieved as follows:
+ * - interface functions that operate on keys and values are hidden
+ *   behind auxiliary macros, e.g. hashmap_insert <-> hashmap__insert;
+ * - these auxiliary macros cast the key and value parameters as
+ *   long or long *, so the user does not have to specify the casts explicitly;
+ * - for pointer parameters (e.g. old_key) the size of the pointed
+ *   type is verified by hashmap_cast_ptr using _Static_assert;
+ * - when iterating using hashmap__for_each_* forms
+ *   hasmap_entry->key should be used for integer keys and
+ *   hasmap_entry->pkey should be used for pointer keys,
+ *   same goes for values.
+ */
 struct hashmap_entry {
-	const void *key;
-	void *value;
+	union {
+		long key;
+		const void *pkey;
+	};
+	union {
+		long value;
+		void *pvalue;
+	};
 	struct hashmap_entry *next;
 };
 
@@ -102,6 +122,13 @@ enum hashmap_insert_strategy {
 	HASHMAP_APPEND,
 };
 
+#define hashmap_cast_ptr(p) ({								\
+	_Static_assert((__builtin_constant_p((p)) ? (p) == NULL : 0) ||			\
+				sizeof(*(p)) == sizeof(long),				\
+		       #p " pointee should be a long-sized integer or a pointer");	\
+	(long *)(p);									\
+})
+
 /*
  * hashmap__insert() adds key/value entry w/ various semantics, depending on
  * provided strategy value. If a given key/value pair replaced already
@@ -109,42 +136,38 @@ enum hashmap_insert_strategy {
  * through old_key and old_value to allow calling code do proper memory
  * management.
  */
-int hashmap__insert(struct hashmap *map, const void *key, void *value,
-		    enum hashmap_insert_strategy strategy,
-		    const void **old_key, void **old_value);
+int hashmap_insert(struct hashmap *map, long key, long value,
+		   enum hashmap_insert_strategy strategy,
+		   long *old_key, long *old_value);
 
-static inline int hashmap__add(struct hashmap *map,
-			       const void *key, void *value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_ADD, NULL, NULL);
-}
+#define hashmap__insert(map, key, value, strategy, old_key, old_value) \
+	hashmap_insert((map), (long)(key), (long)(value), (strategy),  \
+		       hashmap_cast_ptr(old_key),		       \
+		       hashmap_cast_ptr(old_value))
 
-static inline int hashmap__set(struct hashmap *map,
-			       const void *key, void *value,
-			       const void **old_key, void **old_value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_SET,
-			       old_key, old_value);
-}
+#define hashmap__add(map, key, value) \
+	hashmap__insert((map), (key), (value), HASHMAP_ADD, NULL, NULL)
 
-static inline int hashmap__update(struct hashmap *map,
-				  const void *key, void *value,
-				  const void **old_key, void **old_value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_UPDATE,
-			       old_key, old_value);
-}
+#define hashmap__set(map, key, value, old_key, old_value) \
+	hashmap__insert((map), (key), (value), HASHMAP_SET, (old_key), (old_value))
 
-static inline int hashmap__append(struct hashmap *map,
-				  const void *key, void *value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_APPEND, NULL, NULL);
-}
+#define hashmap__update(map, key, value, old_key, old_value) \
+	hashmap__insert((map), (key), (value), HASHMAP_UPDATE, (old_key), (old_value))
+
+#define hashmap__append(map, key, value) \
+	hashmap__insert((map), (key), (value), HASHMAP_APPEND, NULL, NULL)
+
+bool hashmap_delete(struct hashmap *map, long key, long *old_key, long *old_value);
+
+#define hashmap__delete(map, key, old_key, old_value)		       \
+	hashmap_delete((map), (long)(key),			       \
+		       hashmap_cast_ptr(old_key),		       \
+		       hashmap_cast_ptr(old_value))
 
-bool hashmap__delete(struct hashmap *map, const void *key,
-		     const void **old_key, void **old_value);
+bool hashmap_find(const struct hashmap *map, long key, long *value);
 
-bool hashmap__find(const struct hashmap *map, const void *key, void **value);
+#define hashmap__find(map, key, value) \
+	hashmap_find((map), (long)(key), hashmap_cast_ptr(value))
 
 /*
  * hashmap__for_each_entry - iterate over all entries in hashmap
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 184ce1684dcd..2a82f49ce16f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -164,6 +164,7 @@ static const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_TASK_STORAGE]		= "task_storage",
 	[BPF_MAP_TYPE_BLOOM_FILTER]		= "bloom_filter",
 	[BPF_MAP_TYPE_USER_RINGBUF]             = "user_ringbuf",
+	[BPF_MAP_TYPE_CGRP_STORAGE]		= "cgrp_storage",
 };
 
 static const char * const prog_type_name[] = {
@@ -346,7 +347,8 @@ enum sec_def_flags {
 	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 */
+	 * other BPF program's BTF object
+	 */
 	SEC_ATTACH_BTF = 4,
 	/* BPF program type allows sleeping/blocking in kernel */
 	SEC_SLEEPABLE = 8,
@@ -487,7 +489,7 @@ 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
+	 * name. This is important to be able to find corresponding BTF
 	 * DATASEC information.
 	 */
 	char *real_name;
@@ -597,7 +599,7 @@ struct elf_state {
 	size_t shstrndx; /* section index for section name strings */
 	size_t strtabidx;
 	struct elf_sec_desc *secs;
-	int sec_cnt;
+	size_t sec_cnt;
 	int btf_maps_shndx;
 	__u32 btf_maps_sec_btf_id;
 	int text_shndx;
@@ -1408,6 +1410,10 @@ static int bpf_object__check_endianness(struct bpf_object *obj)
 static int
 bpf_object__init_license(struct bpf_object *obj, void *data, size_t size)
 {
+	if (!data) {
+		pr_warn("invalid license section in %s\n", obj->path);
+		return -LIBBPF_ERRNO__FORMAT;
+	}
 	/* libbpf_strlcpy() only copies first N - 1 bytes, so size + 1 won't
 	 * go over allowed ELF data section buffer
 	 */
@@ -1421,7 +1427,7 @@ bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size)
 {
 	__u32 kver;
 
-	if (size != sizeof(kver)) {
+	if (!data || size != sizeof(kver)) {
 		pr_warn("invalid kver section in %s\n", obj->path);
 		return -LIBBPF_ERRNO__FORMAT;
 	}
@@ -1457,15 +1463,12 @@ static int find_elf_sec_sz(const struct bpf_object *obj, const char *name, __u32
 	return -ENOENT;
 }
 
-static int find_elf_var_offset(const struct bpf_object *obj, const char *name, __u32 *off)
+static Elf64_Sym *find_elf_var_sym(const struct bpf_object *obj, const char *name)
 {
 	Elf_Data *symbols = obj->efile.symbols;
 	const char *sname;
 	size_t si;
 
-	if (!name || !off)
-		return -EINVAL;
-
 	for (si = 0; si < symbols->d_size / sizeof(Elf64_Sym); si++) {
 		Elf64_Sym *sym = elf_sym_by_idx(obj, si);
 
@@ -1479,15 +1482,13 @@ static int find_elf_var_offset(const struct bpf_object *obj, const char *name, _
 		sname = elf_sym_str(obj, sym->st_name);
 		if (!sname) {
 			pr_warn("failed to get sym name string for var %s\n", name);
-			return -EIO;
-		}
-		if (strcmp(name, sname) == 0) {
-			*off = sym->st_value;
-			return 0;
+			return ERR_PTR(-EIO);
 		}
+		if (strcmp(name, sname) == 0)
+			return sym;
 	}
 
-	return -ENOENT;
+	return ERR_PTR(-ENOENT);
 }
 
 static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
@@ -1578,7 +1579,38 @@ static char *internal_map_name(struct bpf_object *obj, const char *real_name)
 }
 
 static int
-bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map);
+map_fill_btf_type_info(struct bpf_object *obj, struct bpf_map *map);
+
+/* Internal BPF map is mmap()'able only if at least one of corresponding
+ * DATASEC's VARs are to be exposed through BPF skeleton. I.e., it's a GLOBAL
+ * variable and it's not marked as __hidden (which turns it into, effectively,
+ * a STATIC variable).
+ */
+static bool map_is_mmapable(struct bpf_object *obj, struct bpf_map *map)
+{
+	const struct btf_type *t, *vt;
+	struct btf_var_secinfo *vsi;
+	int i, n;
+
+	if (!map->btf_value_type_id)
+		return false;
+
+	t = btf__type_by_id(obj->btf, map->btf_value_type_id);
+	if (!btf_is_datasec(t))
+		return false;
+
+	vsi = btf_var_secinfos(t);
+	for (i = 0, n = btf_vlen(t); i < n; i++, vsi++) {
+		vt = btf__type_by_id(obj->btf, vsi->type);
+		if (!btf_is_var(vt))
+			continue;
+
+		if (btf_var(vt)->linkage != BTF_VAR_STATIC)
+			return true;
+	}
+
+	return false;
+}
 
 static int
 bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
@@ -1610,7 +1642,12 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 	def->max_entries = 1;
 	def->map_flags = type == LIBBPF_MAP_RODATA || type == LIBBPF_MAP_KCONFIG
 			 ? BPF_F_RDONLY_PROG : 0;
-	def->map_flags |= BPF_F_MMAPABLE;
+
+	/* failures are fine because of maps like .rodata.str1.1 */
+	(void) map_fill_btf_type_info(obj, map);
+
+	if (map_is_mmapable(obj, map))
+		def->map_flags |= BPF_F_MMAPABLE;
 
 	pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n",
 		 map->name, map->sec_idx, map->sec_offset, def->map_flags);
@@ -1627,9 +1664,6 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 		return err;
 	}
 
-	/* failures are fine because of maps like .rodata.str1.1 */
-	(void) bpf_map_find_btf_info(obj, map);
-
 	if (data)
 		memcpy(map->mmaped, data, data_sz);
 
@@ -1830,12 +1864,20 @@ static int set_kcfg_value_num(struct extern_desc *ext, void *ext_val,
 		return -ERANGE;
 	}
 	switch (ext->kcfg.sz) {
-		case 1: *(__u8 *)ext_val = value; break;
-		case 2: *(__u16 *)ext_val = value; break;
-		case 4: *(__u32 *)ext_val = value; break;
-		case 8: *(__u64 *)ext_val = value; break;
-		default:
-			return -EINVAL;
+	case 1:
+		*(__u8 *)ext_val = value;
+		break;
+	case 2:
+		*(__u16 *)ext_val = value;
+		break;
+	case 4:
+		*(__u32 *)ext_val = value;
+		break;
+	case 8:
+		*(__u64 *)ext_val = value;
+		break;
+	default:
+		return -EINVAL;
 	}
 	ext->is_set = true;
 	return 0;
@@ -2541,7 +2583,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 		fill_map_from_def(map->inner_map, &inner_def);
 	}
 
-	err = bpf_map_find_btf_info(obj, map);
+	err = map_fill_btf_type_info(obj, map);
 	if (err)
 		return err;
 
@@ -2737,7 +2779,7 @@ static int bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
 				m->type = enum64_placeholder_id;
 				m->offset = 0;
 			}
-                }
+		}
 	}
 
 	return 0;
@@ -2846,57 +2888,89 @@ static int compare_vsi_off(const void *_a, const void *_b)
 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;
+	__u32 size = 0, i, vars = btf_vlen(t);
+	const char *sec_name = btf__name_by_offset(btf, t->name_off);
 	struct btf_var_secinfo *vsi;
-	const struct btf_var *var;
-	int ret;
+	bool fixup_offsets = false;
+	int err;
 
-	if (!name) {
+	if (!sec_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
+	/* Extern-backing datasecs (.ksyms, .kconfig) have their size and
+	 * variable offsets set at the previous step. Further, not every
+	 * extern BTF VAR has corresponding ELF symbol preserved, so we skip
+	 * all fixups altogether for such sections and go straight to sorting
+	 * VARs within their DATASEC.
 	 */
-	if (t->size)
+	if (strcmp(sec_name, KCONFIG_SEC) == 0 || strcmp(sec_name, KSYMS_SEC) == 0)
 		goto sort_vars;
 
-	ret = find_elf_sec_sz(obj, name, &size);
-	if (ret || !size) {
-		pr_debug("Invalid size for section %s: %u bytes\n", name, size);
-		return -ENOENT;
-	}
+	/* Clang leaves DATASEC size and VAR offsets as zeroes, so we need to
+	 * fix this up. But BPF static linker already fixes this up and fills
+	 * all the sizes and offsets during static linking. So this step has
+	 * to be optional. But the STV_HIDDEN handling is non-optional for any
+	 * non-extern DATASEC, so the variable fixup loop below handles both
+	 * functions at the same time, paying the cost of BTF VAR <-> ELF
+	 * symbol matching just once.
+	 */
+	if (t->size == 0) {
+		err = find_elf_sec_sz(obj, sec_name, &size);
+		if (err || !size) {
+			pr_debug("sec '%s': failed to determine size from ELF: size %u, err %d\n",
+				 sec_name, size, err);
+			return -ENOENT;
+		}
 
-	t->size = size;
+		t->size = size;
+		fixup_offsets = true;
+	}
 
 	for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) {
+		const struct btf_type *t_var;
+		struct btf_var *var;
+		const char *var_name;
+		Elf64_Sym *sym;
+
 		t_var = btf__type_by_id(btf, vsi->type);
 		if (!t_var || !btf_is_var(t_var)) {
-			pr_debug("Non-VAR type seen in section %s\n", name);
+			pr_debug("sec '%s': unexpected non-VAR type found\n", sec_name);
 			return -EINVAL;
 		}
 
 		var = btf_var(t_var);
-		if (var->linkage == BTF_VAR_STATIC)
+		if (var->linkage == BTF_VAR_STATIC || var->linkage == BTF_VAR_GLOBAL_EXTERN)
 			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");
+		var_name = btf__name_by_offset(btf, t_var->name_off);
+		if (!var_name) {
+			pr_debug("sec '%s': failed to find name of DATASEC's member #%d\n",
+				 sec_name, i);
 			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);
+		sym = find_elf_var_sym(obj, var_name);
+		if (IS_ERR(sym)) {
+			pr_debug("sec '%s': failed to find ELF symbol for VAR '%s'\n",
+				 sec_name, var_name);
 			return -ENOENT;
 		}
 
-		vsi->offset = off;
+		if (fixup_offsets)
+			vsi->offset = sym->st_value;
+
+		/* if variable is a global/weak symbol, but has restricted
+		 * (STV_HIDDEN or STV_INTERNAL) visibility, mark its BTF VAR
+		 * as static. This follows similar logic for functions (BPF
+		 * subprogs) and influences libbpf's further decisions about
+		 * whether to make global data BPF array maps as
+		 * BPF_F_MMAPABLE.
+		 */
+		if (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN
+		    || ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL)
+			var->linkage = BTF_VAR_STATIC;
 	}
 
 sort_vars:
@@ -2904,13 +2978,16 @@ sort_vars:
 	return 0;
 }
 
-static int btf_finalize_data(struct bpf_object *obj, struct btf *btf)
+static int bpf_object_fixup_btf(struct bpf_object *obj)
 {
-	int err = 0;
-	__u32 i, n = btf__type_cnt(btf);
+	int i, n, err = 0;
 
+	if (!obj->btf)
+		return 0;
+
+	n = btf__type_cnt(obj->btf);
 	for (i = 1; i < n; i++) {
-		struct btf_type *t = btf_type_by_id(btf, i);
+		struct btf_type *t = btf_type_by_id(obj->btf, i);
 
 		/* Loader needs to fix up some of the things compiler
 		 * couldn't get its hands on while emitting BTF. This
@@ -2918,28 +2995,12 @@ static int btf_finalize_data(struct bpf_object *obj, struct btf *btf)
 		 * the info from the ELF itself for this purpose.
 		 */
 		if (btf_is_datasec(t)) {
-			err = btf_fixup_datasec(obj, btf, t);
+			err = btf_fixup_datasec(obj, obj->btf, t);
 			if (err)
-				break;
+				return err;
 		}
 	}
 
-	return libbpf_err(err);
-}
-
-static int bpf_object__finalize_btf(struct bpf_object *obj)
-{
-	int err;
-
-	if (!obj->btf)
-		return 0;
-
-	err = btf_finalize_data(obj, obj->btf);
-	if (err) {
-		pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err);
-		return err;
-	}
-
 	return 0;
 }
 
@@ -3312,10 +3373,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	Elf64_Shdr *sh;
 
 	/* ELF section indices are 0-based, but sec #0 is special "invalid"
-	 * section. e_shnum does include sec #0, so e_shnum is the necessary
-	 * size of an array to keep all the sections.
+	 * section. Since section count retrieved by elf_getshdrnum() does
+	 * include sec #0, it is already the necessary size of an array to keep
+	 * all the sections.
 	 */
-	obj->efile.sec_cnt = obj->efile.ehdr->e_shnum;
+	if (elf_getshdrnum(obj->efile.elf, &obj->efile.sec_cnt)) {
+		pr_warn("elf: failed to get the number of sections for %s: %s\n",
+			obj->path, elf_errmsg(-1));
+		return -LIBBPF_ERRNO__FORMAT;
+	}
 	obj->efile.secs = calloc(obj->efile.sec_cnt, sizeof(*obj->efile.secs));
 	if (!obj->efile.secs)
 		return -ENOMEM;
@@ -3445,7 +3511,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			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) {
+		} else if (sh->sh_type == SHT_NOBITS && (strcmp(name, BSS_SEC) == 0 ||
+							 str_has_pfx(name, BSS_SEC "."))) {
 			sec_desc->sec_type = SEC_BSS;
 			sec_desc->shdr = sh;
 			sec_desc->data = data;
@@ -3461,7 +3528,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	}
 
 	/* sort BPF programs by section name and in-section instruction offset
-	 * for faster search */
+	 * for faster search
+	 */
 	if (obj->nr_programs)
 		qsort(obj->programs, obj->nr_programs, sizeof(*obj->programs), cmp_progs);
 
@@ -3760,7 +3828,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 				return -EINVAL;
 			}
 			ext->kcfg.type = find_kcfg_type(obj->btf, t->type,
-						        &ext->kcfg.is_signed);
+							&ext->kcfg.is_signed);
 			if (ext->kcfg.type == KCFG_UNKNOWN) {
 				pr_warn("extern (kcfg) '%s': type is unsupported\n", ext_name);
 				return -ENOTSUP;
@@ -4106,6 +4174,9 @@ static struct bpf_program *find_prog_by_sec_insn(const struct bpf_object *obj,
 	int l = 0, r = obj->nr_programs - 1, m;
 	struct bpf_program *prog;
 
+	if (!obj->nr_programs)
+		return NULL;
+
 	while (l < r) {
 		m = l + (r - l + 1) / 2;
 		prog = &obj->programs[m];
@@ -4223,7 +4294,7 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Dat
 	return 0;
 }
 
-static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
+static int map_fill_btf_type_info(struct bpf_object *obj, struct bpf_map *map)
 {
 	int id;
 
@@ -4905,9 +4976,9 @@ bpf_object__reuse_map(struct bpf_map *map)
 
 	err = bpf_map__reuse_fd(map, pin_fd);
 	close(pin_fd);
-	if (err) {
+	if (err)
 		return err;
-	}
+
 	map->pinned = true;
 	pr_debug("reused pinned map at '%s'\n", map->pin_path);
 
@@ -5425,7 +5496,7 @@ static int load_module_btfs(struct bpf_object *obj)
 		}
 
 		err = libbpf_ensure_mem((void **)&obj->btf_modules, &obj->btf_module_cap,
-				        sizeof(*obj->btf_modules), obj->btf_module_cnt + 1);
+					sizeof(*obj->btf_modules), obj->btf_module_cnt + 1);
 		if (err)
 			goto err_out;
 
@@ -5541,21 +5612,16 @@ int bpf_core_types_match(const struct btf *local_btf, __u32 local_id,
 	return __bpf_core_types_match(local_btf, local_id, targ_btf, targ_id, false, 32);
 }
 
-static size_t bpf_core_hash_fn(const void *key, void *ctx)
+static size_t bpf_core_hash_fn(const long key, void *ctx)
 {
-	return (size_t)key;
+	return key;
 }
 
-static bool bpf_core_equal_fn(const void *k1, const void *k2, void *ctx)
+static bool bpf_core_equal_fn(const long k1, const long k2, void *ctx)
 {
 	return k1 == k2;
 }
 
-static void *u32_as_hash_key(__u32 x)
-{
-	return (void *)(uintptr_t)x;
-}
-
 static int record_relo_core(struct bpf_program *prog,
 			    const struct bpf_core_relo *core_relo, int insn_idx)
 {
@@ -5598,7 +5664,6 @@ static int bpf_core_resolve_relo(struct bpf_program *prog,
 				 struct bpf_core_relo_res *targ_res)
 {
 	struct bpf_core_spec specs_scratch[3] = {};
-	const void *type_key = u32_as_hash_key(relo->type_id);
 	struct bpf_core_cand_list *cands = NULL;
 	const char *prog_name = prog->name;
 	const struct btf_type *local_type;
@@ -5615,7 +5680,7 @@ static int bpf_core_resolve_relo(struct bpf_program *prog,
 		return -EINVAL;
 
 	if (relo->kind != BPF_CORE_TYPE_ID_LOCAL &&
-	    !hashmap__find(cand_cache, type_key, (void **)&cands)) {
+	    !hashmap__find(cand_cache, local_id, &cands)) {
 		cands = bpf_core_find_cands(prog->obj, local_btf, local_id);
 		if (IS_ERR(cands)) {
 			pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s %s: %ld\n",
@@ -5623,7 +5688,7 @@ static int bpf_core_resolve_relo(struct bpf_program *prog,
 				local_name, PTR_ERR(cands));
 			return PTR_ERR(cands);
 		}
-		err = hashmap__set(cand_cache, type_key, cands, NULL, NULL);
+		err = hashmap__set(cand_cache, local_id, cands, NULL, NULL);
 		if (err) {
 			bpf_core_free_cands(cands);
 			return err;
@@ -5746,7 +5811,7 @@ out:
 
 	if (!IS_ERR_OR_NULL(cand_cache)) {
 		hashmap__for_each_entry(cand_cache, entry, i) {
-			bpf_core_free_cands(entry->value);
+			bpf_core_free_cands(entry->pvalue);
 		}
 		hashmap__free(cand_cache);
 	}
@@ -6183,7 +6248,8 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 		 * prog; each main prog can have a different set of
 		 * subprograms appended (potentially in different order as
 		 * well), so position of any subprog can be different for
-		 * different main programs */
+		 * different main programs
+		 */
 		insn->imm = subprog->sub_insn_off - (prog->sub_insn_off + insn_idx) - 1;
 
 		pr_debug("prog '%s': insn #%zu relocated, imm %d points to subprog '%s' (now at %zu offset)\n",
@@ -7221,7 +7287,7 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
 	err = err ? : bpf_object__check_endianness(obj);
 	err = err ? : bpf_object__elf_collect(obj);
 	err = err ? : bpf_object__collect_externs(obj);
-	err = err ? : bpf_object__finalize_btf(obj);
+	err = err ? : bpf_object_fixup_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);
@@ -10941,7 +11007,7 @@ struct bpf_link *bpf_program__attach_usdt(const struct bpf_program *prog,
 
 	usdt_cookie = OPTS_GET(opts, usdt_cookie, 0);
 	link = usdt_manager_attach_usdt(obj->usdt_man, prog, pid, binary_path,
-				        usdt_provider, usdt_name, usdt_cookie);
+					usdt_provider, usdt_name, usdt_cookie);
 	err = libbpf_get_error(link);
 	if (err)
 		return libbpf_err_ptr(err);
@@ -11169,7 +11235,7 @@ static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf
 	}
 
 	*link = bpf_program__attach_raw_tracepoint(prog, tp_name);
-	return libbpf_get_error(link);
+	return libbpf_get_error(*link);
 }
 
 /* Common logic for all BPF program types that attach to a btf_id */
@@ -12250,7 +12316,7 @@ int bpf_object__open_subskeleton(struct bpf_object_subskeleton *s)
 	btf = bpf_object__btf(s->obj);
 	if (!btf) {
 		pr_warn("subskeletons require BTF at runtime (object %s)\n",
-		        bpf_object__name(s->obj));
+			bpf_object__name(s->obj));
 		return libbpf_err(-errno);
 	}
 
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index c1d6aa7c82b6..71bf5691a689 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -367,10 +367,14 @@ LIBBPF_1.0.0 {
 		libbpf_bpf_map_type_str;
 		libbpf_bpf_prog_type_str;
 		perf_buffer__buffer;
-};
+} LIBBPF_0.8.0;
 
 LIBBPF_1.1.0 {
 	global:
+		bpf_btf_get_fd_by_id_opts;
+		bpf_link_get_fd_by_id_opts;
+		bpf_map_get_fd_by_id_opts;
+		bpf_prog_get_fd_by_id_opts;
 		user_ring_buffer__discard;
 		user_ring_buffer__free;
 		user_ring_buffer__new;
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index f3a8e8e74eb8..b44fcbb4b42e 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -221,6 +221,7 @@ static int probe_map_create(enum bpf_map_type map_type)
 	case BPF_MAP_TYPE_SK_STORAGE:
 	case BPF_MAP_TYPE_INODE_STORAGE:
 	case BPF_MAP_TYPE_TASK_STORAGE:
+	case BPF_MAP_TYPE_CGRP_STORAGE:
 		btf_key_type_id = 1;
 		btf_value_type_id = 3;
 		value_size = 8;
@@ -234,7 +235,7 @@ static int probe_map_create(enum bpf_map_type map_type)
 	case BPF_MAP_TYPE_USER_RINGBUF:
 		key_size = 0;
 		value_size = 0;
-		max_entries = 4096;
+		max_entries = sysconf(_SC_PAGE_SIZE);
 		break;
 	case BPF_MAP_TYPE_STRUCT_OPS:
 		/* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index d285171d4b69..47855af25f3b 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -77,6 +77,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	__u32 len = sizeof(info);
 	struct epoll_event *e;
 	struct ring *r;
+	__u64 mmap_sz;
 	void *tmp;
 	int err;
 
@@ -115,8 +116,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	r->mask = info.max_entries - 1;
 
 	/* Map writable consumer page */
-	tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
-		   map_fd, 0);
+	tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, 0);
 	if (tmp == MAP_FAILED) {
 		err = -errno;
 		pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
@@ -128,9 +128,13 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 	/* Map read-only producer page and data pages. We map twice as big
 	 * data size to allow simple reading of samples that wrap around the
 	 * end of a ring buffer. See kernel implementation for details.
-	 * */
-	tmp = mmap(NULL, rb->page_size + 2 * info.max_entries, PROT_READ,
-		   MAP_SHARED, map_fd, rb->page_size);
+	 */
+	mmap_sz = rb->page_size + 2 * (__u64)info.max_entries;
+	if (mmap_sz != (__u64)(size_t)mmap_sz) {
+		pr_warn("ringbuf: ring buffer size (%u) is too big\n", info.max_entries);
+		return libbpf_err(-E2BIG);
+	}
+	tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ, MAP_SHARED, map_fd, rb->page_size);
 	if (tmp == MAP_FAILED) {
 		err = -errno;
 		ringbuf_unmap_ring(rb, r);
@@ -220,7 +224,7 @@ static inline int roundup_len(__u32 len)
 	return (len + 7) / 8 * 8;
 }
 
-static int64_t ringbuf_process_ring(struct ring* r)
+static int64_t ringbuf_process_ring(struct ring *r)
 {
 	int *len_ptr, len, err;
 	/* 64-bit to avoid overflow in case of extreme application behavior */
@@ -348,6 +352,7 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd)
 {
 	struct bpf_map_info info;
 	__u32 len = sizeof(info);
+	__u64 mmap_sz;
 	void *tmp;
 	struct epoll_event *rb_epoll;
 	int err;
@@ -384,8 +389,13 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd)
 	 * simple reading and writing of samples that wrap around the end of
 	 * the buffer.  See the kernel implementation for details.
 	 */
-	tmp = mmap(NULL, rb->page_size + 2 * info.max_entries,
-		   PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, rb->page_size);
+	mmap_sz = rb->page_size + 2 * (__u64)info.max_entries;
+	if (mmap_sz != (__u64)(size_t)mmap_sz) {
+		pr_warn("user ringbuf: ring buf size (%u) is too big\n", info.max_entries);
+		return -E2BIG;
+	}
+	tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ | PROT_WRITE, MAP_SHARED,
+		   map_fd, rb->page_size);
 	if (tmp == MAP_FAILED) {
 		err = -errno;
 		pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %d\n",
@@ -476,6 +486,10 @@ void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size)
 	__u64 cons_pos, prod_pos;
 	struct ringbuf_hdr *hdr;
 
+	/* The top two bits are used as special flags */
+	if (size & (BPF_RINGBUF_BUSY_BIT | BPF_RINGBUF_DISCARD_BIT))
+		return errno = E2BIG, NULL;
+
 	/* Synchronizes with smp_store_release() in __bpf_user_ringbuf_peek() in
 	 * the kernel.
 	 */
diff --git a/tools/lib/bpf/strset.c b/tools/lib/bpf/strset.c
index ea655318153f..2464bcbd04e0 100644
--- a/tools/lib/bpf/strset.c
+++ b/tools/lib/bpf/strset.c
@@ -19,19 +19,19 @@ struct strset {
 	struct hashmap *strs_hash;
 };
 
-static size_t strset_hash_fn(const void *key, void *ctx)
+static size_t strset_hash_fn(long key, void *ctx)
 {
 	const struct strset *s = ctx;
-	const char *str = s->strs_data + (long)key;
+	const char *str = s->strs_data + key;
 
 	return str_hash(str);
 }
 
-static bool strset_equal_fn(const void *key1, const void *key2, void *ctx)
+static bool strset_equal_fn(long key1, long key2, void *ctx)
 {
 	const struct strset *s = ctx;
-	const char *str1 = s->strs_data + (long)key1;
-	const char *str2 = s->strs_data + (long)key2;
+	const char *str1 = s->strs_data + key1;
+	const char *str2 = s->strs_data + key2;
 
 	return strcmp(str1, str2) == 0;
 }
@@ -67,7 +67,7 @@ struct strset *strset__new(size_t max_data_sz, const char *init_data, size_t ini
 			/* hashmap__add() returns EEXIST if string with the same
 			 * content already is in the hash map
 			 */
-			err = hashmap__add(hash, (void *)off, (void *)off);
+			err = hashmap__add(hash, off, off);
 			if (err == -EEXIST)
 				continue; /* duplicate */
 			if (err)
@@ -127,7 +127,7 @@ int strset__find_str(struct strset *set, const char *s)
 	new_off = set->strs_data_len;
 	memcpy(p, s, len);
 
-	if (hashmap__find(set->strs_hash, (void *)new_off, (void **)&old_off))
+	if (hashmap__find(set->strs_hash, new_off, &old_off))
 		return old_off;
 
 	return -ENOENT;
@@ -165,8 +165,8 @@ int strset__add_str(struct strset *set, const char *s)
 	 * contents doesn't exist already (HASHMAP_ADD strategy). If such
 	 * string exists, we'll get its offset in old_off (that's old_key).
 	 */
-	err = hashmap__insert(set->strs_hash, (void *)new_off, (void *)new_off,
-			      HASHMAP_ADD, (const void **)&old_off, NULL);
+	err = hashmap__insert(set->strs_hash, new_off, new_off,
+			      HASHMAP_ADD, &old_off, NULL);
 	if (err == -EEXIST)
 		return old_off; /* duplicated string, return existing offset */
 	if (err)
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
index e83b497c2245..75b411fc2c77 100644
--- a/tools/lib/bpf/usdt.c
+++ b/tools/lib/bpf/usdt.c
@@ -873,31 +873,27 @@ static void bpf_link_usdt_dealloc(struct bpf_link *link)
 	free(usdt_link);
 }
 
-static size_t specs_hash_fn(const void *key, void *ctx)
+static size_t specs_hash_fn(long key, void *ctx)
 {
-	const char *s = key;
-
-	return str_hash(s);
+	return str_hash((char *)key);
 }
 
-static bool specs_equal_fn(const void *key1, const void *key2, void *ctx)
+static bool specs_equal_fn(long key1, long key2, void *ctx)
 {
-	const char *s1 = key1;
-	const char *s2 = key2;
-
-	return strcmp(s1, s2) == 0;
+	return strcmp((char *)key1, (char *)key2) == 0;
 }
 
 static int allocate_spec_id(struct usdt_manager *man, struct hashmap *specs_hash,
 			    struct bpf_link_usdt *link, struct usdt_target *target,
 			    int *spec_id, bool *is_new)
 {
-	void *tmp;
+	long tmp;
+	void *new_ids;
 	int err;
 
 	/* check if we already allocated spec ID for this spec string */
 	if (hashmap__find(specs_hash, target->spec_str, &tmp)) {
-		*spec_id = (long)tmp;
+		*spec_id = tmp;
 		*is_new = false;
 		return 0;
 	}
@@ -905,17 +901,17 @@ static int allocate_spec_id(struct usdt_manager *man, struct hashmap *specs_hash
 	/* otherwise it's a new ID that needs to be set up in specs map and
 	 * returned back to usdt_manager when USDT link is detached
 	 */
-	tmp = libbpf_reallocarray(link->spec_ids, link->spec_cnt + 1, sizeof(*link->spec_ids));
-	if (!tmp)
+	new_ids = libbpf_reallocarray(link->spec_ids, link->spec_cnt + 1, sizeof(*link->spec_ids));
+	if (!new_ids)
 		return -ENOMEM;
-	link->spec_ids = tmp;
+	link->spec_ids = new_ids;
 
 	/* get next free spec ID, giving preference to free list, if not empty */
 	if (man->free_spec_cnt) {
 		*spec_id = man->free_spec_ids[man->free_spec_cnt - 1];
 
 		/* cache spec ID for current spec string for future lookups */
-		err = hashmap__add(specs_hash, target->spec_str, (void *)(long)*spec_id);
+		err = hashmap__add(specs_hash, target->spec_str, *spec_id);
 		if (err)
 			 return err;
 
@@ -928,7 +924,7 @@ static int allocate_spec_id(struct usdt_manager *man, struct hashmap *specs_hash
 		*spec_id = man->next_free_spec_id;
 
 		/* cache spec ID for current spec string for future lookups */
-		err = hashmap__add(specs_hash, target->spec_str, (void *)(long)*spec_id);
+		err = hashmap__add(specs_hash, target->spec_str, *spec_id);
 		if (err)
 			 return err;
 
@@ -1225,26 +1221,32 @@ static int calc_pt_regs_off(const char *reg_name)
 
 static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
 {
-	char *reg_name = NULL;
+	char reg_name[16];
 	int arg_sz, len, reg_off;
 	long off;
 
-	if (sscanf(arg_str, " %d @ %ld ( %%%m[^)] ) %n", &arg_sz, &off, &reg_name, &len) == 3) {
+	if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", &arg_sz, &off, reg_name, &len) == 3) {
 		/* Memory dereference case, e.g., -4@-20(%rbp) */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ %%%ms %n", &arg_sz, &reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ ( %%%15[^)] ) %n", &arg_sz, reg_name, &len) == 2) {
+		/* Memory dereference case without offset, e.g., 8@(%rsp) */
+		arg->arg_type = USDT_ARG_REG_DEREF;
+		arg->val_off = 0;
+		reg_off = calc_pt_regs_off(reg_name);
+		if (reg_off < 0)
+			return reg_off;
+		arg->reg_off = reg_off;
+	} else if (sscanf(arg_str, " %d @ %%%15s %n", &arg_sz, reg_name, &len) == 2) {
 		/* Register read case, e.g., -4@%eax */
 		arg->arg_type = USDT_ARG_REG;
 		arg->val_off = 0;
 
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
@@ -1348,25 +1350,23 @@ static int calc_pt_regs_off(const char *reg_name)
 
 static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
 {
-	char *reg_name = NULL;
+	char reg_name[16];
 	int arg_sz, len, reg_off;
 	long off;
 
-	if (sscanf(arg_str, " %d @ \[ %m[a-z0-9], %ld ] %n", &arg_sz, &reg_name, &off, &len) == 3) {
+	if (sscanf(arg_str, " %d @ \[ %15[a-z0-9], %ld ] %n", &arg_sz, reg_name, &off, &len) == 3) {
 		/* Memory dereference case, e.g., -4@[sp, 96] */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ \[ %m[a-z0-9] ] %n", &arg_sz, &reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] ] %n", &arg_sz, reg_name, &len) == 2) {
 		/* Memory dereference case, e.g., -4@[sp] */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = 0;
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
@@ -1375,12 +1375,11 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		arg->arg_type = USDT_ARG_CONST;
 		arg->val_off = off;
 		arg->reg_off = 0;
-	} else if (sscanf(arg_str, " %d @ %m[a-z0-9] %n", &arg_sz, &reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", &arg_sz, reg_name, &len) == 2) {
 		/* Register read case, e.g., -8@x4 */
 		arg->arg_type = USDT_ARG_REG;
 		arg->val_off = 0;
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
@@ -1459,16 +1458,15 @@ static int calc_pt_regs_off(const char *reg_name)
 
 static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
 {
-	char *reg_name = NULL;
+	char reg_name[16];
 	int arg_sz, len, reg_off;
 	long off;
 
-	if (sscanf(arg_str, " %d @ %ld ( %m[a-z0-9] ) %n", &arg_sz, &off, &reg_name, &len) == 3) {
+	if (sscanf(arg_str, " %d @ %ld ( %15[a-z0-9] ) %n", &arg_sz, &off, reg_name, &len) == 3) {
 		/* Memory dereference case, e.g., -8@-88(s0) */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
@@ -1477,12 +1475,11 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		arg->arg_type = USDT_ARG_CONST;
 		arg->val_off = off;
 		arg->reg_off = 0;
-	} else if (sscanf(arg_str, " %d @ %m[a-z0-9] %n", &arg_sz, &reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", &arg_sz, reg_name, &len) == 2) {
 		/* Register read case, e.g., -8@a1 */
 		arg->arg_type = USDT_ARG_REG;
 		arg->val_off = 0;
 		reg_off = calc_pt_regs_off(reg_name);
-		free(reg_name);
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;