Adding upstream version 6.8.9.upstream/6.8.9

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

24 files changed, 826 insertions, 264 deletions

diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 5cb0eeec2c..337fde770e 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -16,6 +16,7 @@
 #include <sys/mount.h>
 
 #include "fs.h"
+#include "../io.h"
 #include "debug-internal.h"
 
 #define _STR(x) #x
@@ -344,53 +345,24 @@ int filename__read_ull(const char *filename, unsigned long long *value)
 	return filename__read_ull_base(filename, value, 0);
 }
 
-#define STRERR_BUFSIZE  128     /* For the buffer size of strerror_r */
-
 int filename__read_str(const char *filename, char **buf, size_t *sizep)
 {
-	size_t size = 0, alloc_size = 0;
-	void *bf = NULL, *nbf;
-	int fd, n, err = 0;
-	char sbuf[STRERR_BUFSIZE];
+	struct io io;
+	char bf[128];
+	int err;
 
-	fd = open(filename, O_RDONLY);
-	if (fd < 0)
+	io.fd = open(filename, O_RDONLY);
+	if (io.fd < 0)
 		return -errno;
-
-	do {
-		if (size == alloc_size) {
-			alloc_size += BUFSIZ;
-			nbf = realloc(bf, alloc_size);
-			if (!nbf) {
-				err = -ENOMEM;
-				break;
-			}
-
-			bf = nbf;
-		}
-
-		n = read(fd, bf + size, alloc_size - size);
-		if (n < 0) {
-			if (size) {
-				pr_warn("read failed %d: %s\n", errno,
-					strerror_r(errno, sbuf, sizeof(sbuf)));
-				err = 0;
-			} else
-				err = -errno;
-
-			break;
-		}
-
-		size += n;
-	} while (n > 0);
-
-	if (!err) {
-		*sizep = size;
-		*buf   = bf;
+	io__init(&io, io.fd, bf, sizeof(bf));
+	*buf = NULL;
+	err = io__getdelim(&io, buf, sizep, /*delim=*/-1);
+	if (err < 0) {
+		free(*buf);
+		*buf = NULL;
 	} else
-		free(bf);
-
-	close(fd);
+		err = 0;
+	close(io.fd);
 	return err;
 }
 
@@ -475,15 +447,22 @@ int sysfs__read_str(const char *entry, char **buf, size_t *sizep)
 
 int sysfs__read_bool(const char *entry, bool *value)
 {
-	char *buf;
-	size_t size;
-	int ret;
+	struct io io;
+	char bf[16];
+	int ret = 0;
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
 
-	ret = sysfs__read_str(entry, &buf, &size);
-	if (ret < 0)
-		return ret;
+	snprintf(path, sizeof(path), "%s/%s", sysfs, entry);
+	io.fd = open(path, O_RDONLY);
+	if (io.fd < 0)
+		return -errno;
 
-	switch (buf[0]) {
+	io__init(&io, io.fd, bf, sizeof(bf));
+	switch (io__get_char(&io)) {
 	case '1':
 	case 'y':
 	case 'Y':
@@ -497,8 +476,7 @@ int sysfs__read_bool(const char *entry, bool *value)
 	default:
 		ret = -1;
 	}
-
-	free(buf);
+	close(io.fd);
 
 	return ret;
 }
diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
index 2a7fe97588..84adf81020 100644
--- a/tools/lib/api/io.h
+++ b/tools/lib/api/io.h
@@ -141,8 +141,8 @@ static inline int io__get_dec(struct io *io, __u64 *dec)
 	}
 }
 
-/* Read up to and including the first newline following the pattern of getline. */
-static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_len_out)
+/* Read up to and including the first delim. */
+static inline ssize_t io__getdelim(struct io *io, char **line_out, size_t *line_len_out, int delim)
 {
 	char buf[128];
 	int buf_pos = 0;
@@ -152,7 +152,7 @@ static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_l
 
 	/* TODO: reuse previously allocated memory. */
 	free(*line_out);
-	while (ch != '\n') {
+	while (ch != delim) {
 		ch = io__get_char(io);
 
 		if (ch < 0)
@@ -185,4 +185,9 @@ err_out:
 	return -ENOMEM;
 }
 
+static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_len_out)
+{
+	return io__getdelim(io, line_out, line_len_out, /*delim=*/'\n');
+}
+
 #endif /* __API_IO__ */
diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index 1ac57bb7ac..7325a12692 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -111,6 +111,38 @@ enum bpf_enum_value_kind {
 	val;								      \
 })
 
+/*
+ * Write to a bitfield, identified by s->field.
+ * This is the inverse of BPF_CORE_WRITE_BITFIELD().
+ */
+#define BPF_CORE_WRITE_BITFIELD(s, field, new_val) ({			\
+	void *p = (void *)s + __CORE_RELO(s, field, BYTE_OFFSET);	\
+	unsigned int byte_size = __CORE_RELO(s, field, BYTE_SIZE);	\
+	unsigned int lshift = __CORE_RELO(s, field, LSHIFT_U64);	\
+	unsigned int rshift = __CORE_RELO(s, field, RSHIFT_U64);	\
+	unsigned long long mask, val, nval = new_val;			\
+	unsigned int rpad = rshift - lshift;				\
+									\
+	asm volatile("" : "+r"(p));					\
+									\
+	switch (byte_size) {						\
+	case 1: val = *(unsigned char *)p; break;			\
+	case 2: val = *(unsigned short *)p; break;			\
+	case 4: val = *(unsigned int *)p; break;			\
+	case 8: val = *(unsigned long long *)p; break;			\
+	}								\
+									\
+	mask = (~0ULL << rshift) >> lshift;				\
+	val = (val & ~mask) | ((nval << rpad) & mask);			\
+									\
+	switch (byte_size) {						\
+	case 1: *(unsigned char *)p      = val; break;			\
+	case 2: *(unsigned short *)p     = val; break;			\
+	case 4: *(unsigned int *)p       = val; break;			\
+	case 8: *(unsigned long long *)p = val; break;			\
+	}								\
+})
+
 #define ___bpf_field_ref1(field)	(field)
 #define ___bpf_field_ref2(type, field)	(((typeof(type) *)0)->field)
 #define ___bpf_field_ref(args...)					    \
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 77ceea575d..2324cc42b0 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -188,6 +188,9 @@ enum libbpf_tristate {
 	!!sym;											\
 })
 
+#define __arg_ctx __attribute__((btf_decl_tag("arg:ctx")))
+#define __arg_nonnull __attribute((btf_decl_tag("arg:nonnull")))
+
 #ifndef ___bpf_concat
 #define ___bpf_concat(a, b) a ## b
 #endif
diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index 2a62bf411b..b02faec748 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -407,7 +407,8 @@ static int symbol_cmp(const void *a, const void *b)
  * size, that needs to be released by the caller.
  */
 int elf_resolve_syms_offsets(const char *binary_path, int cnt,
-			     const char **syms, unsigned long **poffsets)
+			     const char **syms, unsigned long **poffsets,
+			     int st_type)
 {
 	int sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
 	int err = 0, i, cnt_done = 0;
@@ -438,7 +439,7 @@ int elf_resolve_syms_offsets(const char *binary_path, int cnt,
 		struct elf_sym_iter iter;
 		struct elf_sym *sym;
 
-		err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], STT_FUNC);
+		err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], st_type);
 		if (err == -ENOENT)
 			continue;
 		if (err)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ca83af916c..92bca96587 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -33,6 +33,7 @@
 #include <linux/filter.h>
 #include <linux/limits.h>
 #include <linux/perf_event.h>
+#include <linux/bpf_perf_event.h>
 #include <linux/ring_buffer.h>
 #include <sys/epoll.h>
 #include <sys/ioctl.h>
@@ -1504,6 +1505,16 @@ static Elf64_Sym *find_elf_var_sym(const struct bpf_object *obj, const char *nam
 	return ERR_PTR(-ENOENT);
 }
 
+static int create_placeholder_fd(void)
+{
+	int fd;
+
+	fd = ensure_good_fd(memfd_create("libbpf-placeholder-fd", MFD_CLOEXEC));
+	if (fd < 0)
+		return -errno;
+	return fd;
+}
+
 static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
 {
 	struct bpf_map *map;
@@ -1516,7 +1527,21 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
 
 	map = &obj->maps[obj->nr_maps++];
 	map->obj = obj;
-	map->fd = -1;
+	/* Preallocate map FD without actually creating BPF map just yet.
+	 * These map FD "placeholders" will be reused later without changing
+	 * FD value when map is actually created in the kernel.
+	 *
+	 * This is useful to be able to perform BPF program relocations
+	 * without having to create BPF maps before that step. This allows us
+	 * to finalize and load BTF very late in BPF object's loading phase,
+	 * right before BPF maps have to be created and BPF programs have to
+	 * be loaded. By having these map FD placeholders we can perform all
+	 * the sanitizations, relocations, and any other adjustments before we
+	 * start creating actual BPF kernel objects (BTF, maps, progs).
+	 */
+	map->fd = create_placeholder_fd();
+	if (map->fd < 0)
+		return ERR_PTR(map->fd);
 	map->inner_map_fd = -1;
 	map->autocreate = true;
 
@@ -2608,7 +2633,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 		map->inner_map = calloc(1, sizeof(*map->inner_map));
 		if (!map->inner_map)
 			return -ENOMEM;
-		map->inner_map->fd = -1;
+		map->inner_map->fd = create_placeholder_fd();
+		if (map->inner_map->fd < 0)
+			return map->inner_map->fd;
 		map->inner_map->sec_idx = sec_idx;
 		map->inner_map->name = malloc(strlen(map_name) + sizeof(".inner") + 1);
 		if (!map->inner_map->name)
@@ -3055,9 +3082,15 @@ static bool prog_needs_vmlinux_btf(struct bpf_program *prog)
 	return false;
 }
 
+static bool map_needs_vmlinux_btf(struct bpf_map *map)
+{
+	return bpf_map__is_struct_ops(map);
+}
+
 static bool obj_needs_vmlinux_btf(const struct bpf_object *obj)
 {
 	struct bpf_program *prog;
+	struct bpf_map *map;
 	int i;
 
 	/* CO-RE relocations need kernel BTF, only when btf_custom_path
@@ -3082,6 +3115,11 @@ static bool obj_needs_vmlinux_btf(const struct bpf_object *obj)
 			return true;
 	}
 
+	bpf_object__for_each_map(map, obj) {
+		if (map_needs_vmlinux_btf(map))
+			return true;
+	}
+
 	return false;
 }
 
@@ -3156,86 +3194,6 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 		}
 	}
 
-	if (!kernel_supports(obj, FEAT_BTF_DECL_TAG))
-		goto skip_exception_cb;
-	for (i = 0; i < obj->nr_programs; i++) {
-		struct bpf_program *prog = &obj->programs[i];
-		int j, k, n;
-
-		if (prog_is_subprog(obj, prog))
-			continue;
-		n = btf__type_cnt(obj->btf);
-		for (j = 1; j < n; j++) {
-			const char *str = "exception_callback:", *name;
-			size_t len = strlen(str);
-			struct btf_type *t;
-
-			t = btf_type_by_id(obj->btf, j);
-			if (!btf_is_decl_tag(t) || btf_decl_tag(t)->component_idx != -1)
-				continue;
-
-			name = btf__str_by_offset(obj->btf, t->name_off);
-			if (strncmp(name, str, len))
-				continue;
-
-			t = btf_type_by_id(obj->btf, t->type);
-			if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL) {
-				pr_warn("prog '%s': exception_callback:<value> decl tag not applied to the main program\n",
-					prog->name);
-				return -EINVAL;
-			}
-			if (strcmp(prog->name, btf__str_by_offset(obj->btf, t->name_off)))
-				continue;
-			/* Multiple callbacks are specified for the same prog,
-			 * the verifier will eventually return an error for this
-			 * case, hence simply skip appending a subprog.
-			 */
-			if (prog->exception_cb_idx >= 0) {
-				prog->exception_cb_idx = -1;
-				break;
-			}
-
-			name += len;
-			if (str_is_empty(name)) {
-				pr_warn("prog '%s': exception_callback:<value> decl tag contains empty value\n",
-					prog->name);
-				return -EINVAL;
-			}
-
-			for (k = 0; k < obj->nr_programs; k++) {
-				struct bpf_program *subprog = &obj->programs[k];
-
-				if (!prog_is_subprog(obj, subprog))
-					continue;
-				if (strcmp(name, subprog->name))
-					continue;
-				/* Enforce non-hidden, as from verifier point of
-				 * view it expects global functions, whereas the
-				 * mark_btf_static fixes up linkage as static.
-				 */
-				if (!subprog->sym_global || subprog->mark_btf_static) {
-					pr_warn("prog '%s': exception callback %s must be a global non-hidden function\n",
-						prog->name, subprog->name);
-					return -EINVAL;
-				}
-				/* Let's see if we already saw a static exception callback with the same name */
-				if (prog->exception_cb_idx >= 0) {
-					pr_warn("prog '%s': multiple subprogs with same name as exception callback '%s'\n",
-					        prog->name, subprog->name);
-					return -EINVAL;
-				}
-				prog->exception_cb_idx = k;
-				break;
-			}
-
-			if (prog->exception_cb_idx >= 0)
-				continue;
-			pr_warn("prog '%s': cannot find exception callback '%s'\n", prog->name, name);
-			return -ENOENT;
-		}
-	}
-skip_exception_cb:
-
 	sanitize = btf_needs_sanitization(obj);
 	if (sanitize) {
 		const void *raw_data;
@@ -4539,14 +4497,12 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 		goto err_free_new_name;
 	}
 
-	err = zclose(map->fd);
-	if (err) {
-		err = -errno;
-		goto err_close_new_fd;
-	}
+	err = reuse_fd(map->fd, new_fd);
+	if (err)
+		goto err_free_new_name;
+
 	free(map->name);
 
-	map->fd = new_fd;
 	map->name = new_name;
 	map->def.type = info.type;
 	map->def.key_size = info.key_size;
@@ -4560,8 +4516,6 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 
 	return 0;
 
-err_close_new_fd:
-	close(new_fd);
 err_free_new_name:
 	free(new_name);
 	return libbpf_err(err);
@@ -5190,12 +5144,17 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 
 static void bpf_map__destroy(struct bpf_map *map);
 
+static bool map_is_created(const struct bpf_map *map)
+{
+	return map->obj->loaded || map->reused;
+}
+
 static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, create_attr);
 	struct bpf_map_def *def = &map->def;
 	const char *map_name = NULL;
-	int err = 0;
+	int err = 0, map_fd;
 
 	if (kernel_supports(obj, FEAT_PROG_NAME))
 		map_name = map->name;
@@ -5224,7 +5183,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 					map->name, err);
 				return err;
 			}
-			map->inner_map_fd = bpf_map__fd(map->inner_map);
+			map->inner_map_fd = map->inner_map->fd;
 		}
 		if (map->inner_map_fd >= 0)
 			create_attr.inner_map_fd = map->inner_map_fd;
@@ -5257,17 +5216,19 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		bpf_gen__map_create(obj->gen_loader, def->type, map_name,
 				    def->key_size, def->value_size, def->max_entries,
 				    &create_attr, is_inner ? -1 : map - obj->maps);
-		/* Pretend to have valid FD to pass various fd >= 0 checks.
-		 * This fd == 0 will not be used with any syscall and will be reset to -1 eventually.
+		/* We keep pretenting we have valid FD to pass various fd >= 0
+		 * checks by just keeping original placeholder FDs in place.
+		 * See bpf_object__add_map() comment.
+		 * This placeholder fd will not be used with any syscall and
+		 * will be reset to -1 eventually.
 		 */
-		map->fd = 0;
+		map_fd = map->fd;
 	} else {
-		map->fd = bpf_map_create(def->type, map_name,
-					 def->key_size, def->value_size,
-					 def->max_entries, &create_attr);
+		map_fd = bpf_map_create(def->type, map_name,
+					def->key_size, def->value_size,
+					def->max_entries, &create_attr);
 	}
-	if (map->fd < 0 && (create_attr.btf_key_type_id ||
-			    create_attr.btf_value_type_id)) {
+	if (map_fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) {
 		char *cp, errmsg[STRERR_BUFSIZE];
 
 		err = -errno;
@@ -5279,13 +5240,11 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		create_attr.btf_value_type_id = 0;
 		map->btf_key_type_id = 0;
 		map->btf_value_type_id = 0;
-		map->fd = bpf_map_create(def->type, map_name,
-					 def->key_size, def->value_size,
-					 def->max_entries, &create_attr);
+		map_fd = bpf_map_create(def->type, map_name,
+					def->key_size, def->value_size,
+					def->max_entries, &create_attr);
 	}
 
-	err = map->fd < 0 ? -errno : 0;
-
 	if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) {
 		if (obj->gen_loader)
 			map->inner_map->fd = -1;
@@ -5293,7 +5252,19 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		zfree(&map->inner_map);
 	}
 
-	return err;
+	if (map_fd < 0)
+		return map_fd;
+
+	/* obj->gen_loader case, prevent reuse_fd() from closing map_fd */
+	if (map->fd == map_fd)
+		return 0;
+
+	/* Keep placeholder FD value but now point it to the BPF map object.
+	 * This way everything that relied on this map's FD (e.g., relocated
+	 * ldimm64 instructions) will stay valid and won't need adjustments.
+	 * map->fd stays valid but now point to what map_fd points to.
+	 */
+	return reuse_fd(map->fd, map_fd);
 }
 
 static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map)
@@ -5307,7 +5278,7 @@ static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map)
 			continue;
 
 		targ_map = map->init_slots[i];
-		fd = bpf_map__fd(targ_map);
+		fd = targ_map->fd;
 
 		if (obj->gen_loader) {
 			bpf_gen__populate_outer_map(obj->gen_loader,
@@ -5377,10 +5348,8 @@ static int bpf_object_init_prog_arrays(struct bpf_object *obj)
 			continue;
 
 		err = init_prog_array_slots(obj, map);
-		if (err < 0) {
-			zclose(map->fd);
+		if (err < 0)
 			return err;
-		}
 	}
 	return 0;
 }
@@ -5458,7 +5427,7 @@ retry:
 			}
 		}
 
-		if (map->fd >= 0) {
+		if (map->reused) {
 			pr_debug("map '%s': skipping creation (preset fd=%d)\n",
 				 map->name, map->fd);
 		} else {
@@ -5471,25 +5440,20 @@ retry:
 
 			if (bpf_map__is_internal(map)) {
 				err = bpf_object__populate_internal_map(obj, map);
-				if (err < 0) {
-					zclose(map->fd);
+				if (err < 0)
 					goto err_out;
-				}
 			}
 
 			if (map->init_slots_sz && map->def.type != BPF_MAP_TYPE_PROG_ARRAY) {
 				err = init_map_in_map_slots(obj, map);
-				if (err < 0) {
-					zclose(map->fd);
+				if (err < 0)
 					goto err_out;
-				}
 			}
 		}
 
 		if (map->pin_path && !map->pinned) {
 			err = bpf_map__pin(map, NULL);
 			if (err) {
-				zclose(map->fd);
 				if (!retried && err == -EEXIST) {
 					retried = true;
 					goto retry;
@@ -6222,7 +6186,7 @@ reloc_prog_func_and_line_info(const struct bpf_object *obj,
 	int err;
 
 	/* no .BTF.ext relocation if .BTF.ext is missing or kernel doesn't
-	 * supprot func/line info
+	 * support func/line info
 	 */
 	if (!obj->btf_ext || !kernel_supports(obj, FEAT_BTF_FUNC))
 		return 0;
@@ -6622,8 +6586,471 @@ static void bpf_object__sort_relos(struct bpf_object *obj)
 	}
 }
 
-static int
-bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
+static int bpf_prog_assign_exc_cb(struct bpf_object *obj, struct bpf_program *prog)
+{
+	const char *str = "exception_callback:";
+	size_t pfx_len = strlen(str);
+	int i, j, n;
+
+	if (!obj->btf || !kernel_supports(obj, FEAT_BTF_DECL_TAG))
+		return 0;
+
+	n = btf__type_cnt(obj->btf);
+	for (i = 1; i < n; i++) {
+		const char *name;
+		struct btf_type *t;
+
+		t = btf_type_by_id(obj->btf, i);
+		if (!btf_is_decl_tag(t) || btf_decl_tag(t)->component_idx != -1)
+			continue;
+
+		name = btf__str_by_offset(obj->btf, t->name_off);
+		if (strncmp(name, str, pfx_len) != 0)
+			continue;
+
+		t = btf_type_by_id(obj->btf, t->type);
+		if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL) {
+			pr_warn("prog '%s': exception_callback:<value> decl tag not applied to the main program\n",
+				prog->name);
+			return -EINVAL;
+		}
+		if (strcmp(prog->name, btf__str_by_offset(obj->btf, t->name_off)) != 0)
+			continue;
+		/* Multiple callbacks are specified for the same prog,
+		 * the verifier will eventually return an error for this
+		 * case, hence simply skip appending a subprog.
+		 */
+		if (prog->exception_cb_idx >= 0) {
+			prog->exception_cb_idx = -1;
+			break;
+		}
+
+		name += pfx_len;
+		if (str_is_empty(name)) {
+			pr_warn("prog '%s': exception_callback:<value> decl tag contains empty value\n",
+				prog->name);
+			return -EINVAL;
+		}
+
+		for (j = 0; j < obj->nr_programs; j++) {
+			struct bpf_program *subprog = &obj->programs[j];
+
+			if (!prog_is_subprog(obj, subprog))
+				continue;
+			if (strcmp(name, subprog->name) != 0)
+				continue;
+			/* Enforce non-hidden, as from verifier point of
+			 * view it expects global functions, whereas the
+			 * mark_btf_static fixes up linkage as static.
+			 */
+			if (!subprog->sym_global || subprog->mark_btf_static) {
+				pr_warn("prog '%s': exception callback %s must be a global non-hidden function\n",
+					prog->name, subprog->name);
+				return -EINVAL;
+			}
+			/* Let's see if we already saw a static exception callback with the same name */
+			if (prog->exception_cb_idx >= 0) {
+				pr_warn("prog '%s': multiple subprogs with same name as exception callback '%s'\n",
+					prog->name, subprog->name);
+				return -EINVAL;
+			}
+			prog->exception_cb_idx = j;
+			break;
+		}
+
+		if (prog->exception_cb_idx >= 0)
+			continue;
+
+		pr_warn("prog '%s': cannot find exception callback '%s'\n", prog->name, name);
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+static struct {
+	enum bpf_prog_type prog_type;
+	const char *ctx_name;
+} global_ctx_map[] = {
+	{ BPF_PROG_TYPE_CGROUP_DEVICE,           "bpf_cgroup_dev_ctx" },
+	{ BPF_PROG_TYPE_CGROUP_SKB,              "__sk_buff" },
+	{ BPF_PROG_TYPE_CGROUP_SOCK,             "bpf_sock" },
+	{ BPF_PROG_TYPE_CGROUP_SOCK_ADDR,        "bpf_sock_addr" },
+	{ BPF_PROG_TYPE_CGROUP_SOCKOPT,          "bpf_sockopt" },
+	{ BPF_PROG_TYPE_CGROUP_SYSCTL,           "bpf_sysctl" },
+	{ BPF_PROG_TYPE_FLOW_DISSECTOR,          "__sk_buff" },
+	{ BPF_PROG_TYPE_KPROBE,                  "bpf_user_pt_regs_t" },
+	{ BPF_PROG_TYPE_LWT_IN,                  "__sk_buff" },
+	{ BPF_PROG_TYPE_LWT_OUT,                 "__sk_buff" },
+	{ BPF_PROG_TYPE_LWT_SEG6LOCAL,           "__sk_buff" },
+	{ BPF_PROG_TYPE_LWT_XMIT,                "__sk_buff" },
+	{ BPF_PROG_TYPE_NETFILTER,               "bpf_nf_ctx" },
+	{ BPF_PROG_TYPE_PERF_EVENT,              "bpf_perf_event_data" },
+	{ BPF_PROG_TYPE_RAW_TRACEPOINT,          "bpf_raw_tracepoint_args" },
+	{ BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, "bpf_raw_tracepoint_args" },
+	{ BPF_PROG_TYPE_SCHED_ACT,               "__sk_buff" },
+	{ BPF_PROG_TYPE_SCHED_CLS,               "__sk_buff" },
+	{ BPF_PROG_TYPE_SK_LOOKUP,               "bpf_sk_lookup" },
+	{ BPF_PROG_TYPE_SK_MSG,                  "sk_msg_md" },
+	{ BPF_PROG_TYPE_SK_REUSEPORT,            "sk_reuseport_md" },
+	{ BPF_PROG_TYPE_SK_SKB,                  "__sk_buff" },
+	{ BPF_PROG_TYPE_SOCK_OPS,                "bpf_sock_ops" },
+	{ BPF_PROG_TYPE_SOCKET_FILTER,           "__sk_buff" },
+	{ BPF_PROG_TYPE_XDP,                     "xdp_md" },
+	/* all other program types don't have "named" context structs */
+};
+
+/* forward declarations for arch-specific underlying types of bpf_user_pt_regs_t typedef,
+ * for below __builtin_types_compatible_p() checks;
+ * with this approach we don't need any extra arch-specific #ifdef guards
+ */
+struct pt_regs;
+struct user_pt_regs;
+struct user_regs_struct;
+
+static bool need_func_arg_type_fixup(const struct btf *btf, const struct bpf_program *prog,
+				     const char *subprog_name, int arg_idx,
+				     int arg_type_id, const char *ctx_name)
+{
+	const struct btf_type *t;
+	const char *tname;
+
+	/* check if existing parameter already matches verifier expectations */
+	t = skip_mods_and_typedefs(btf, arg_type_id, NULL);
+	if (!btf_is_ptr(t))
+		goto out_warn;
+
+	/* typedef bpf_user_pt_regs_t is a special PITA case, valid for kprobe
+	 * and perf_event programs, so check this case early on and forget
+	 * about it for subsequent checks
+	 */
+	while (btf_is_mod(t))
+		t = btf__type_by_id(btf, t->type);
+	if (btf_is_typedef(t) &&
+	    (prog->type == BPF_PROG_TYPE_KPROBE || prog->type == BPF_PROG_TYPE_PERF_EVENT)) {
+		tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>";
+		if (strcmp(tname, "bpf_user_pt_regs_t") == 0)
+			return false; /* canonical type for kprobe/perf_event */
+	}
+
+	/* now we can ignore typedefs moving forward */
+	t = skip_mods_and_typedefs(btf, t->type, NULL);
+
+	/* if it's `void *`, definitely fix up BTF info */
+	if (btf_is_void(t))
+		return true;
+
+	/* if it's already proper canonical type, no need to fix up */
+	tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>";
+	if (btf_is_struct(t) && strcmp(tname, ctx_name) == 0)
+		return false;
+
+	/* special cases */
+	switch (prog->type) {
+	case BPF_PROG_TYPE_KPROBE:
+		/* `struct pt_regs *` is expected, but we need to fix up */
+		if (btf_is_struct(t) && strcmp(tname, "pt_regs") == 0)
+			return true;
+		break;
+	case BPF_PROG_TYPE_PERF_EVENT:
+		if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct pt_regs) &&
+		    btf_is_struct(t) && strcmp(tname, "pt_regs") == 0)
+			return true;
+		if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_pt_regs) &&
+		    btf_is_struct(t) && strcmp(tname, "user_pt_regs") == 0)
+			return true;
+		if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_regs_struct) &&
+		    btf_is_struct(t) && strcmp(tname, "user_regs_struct") == 0)
+			return true;
+		break;
+	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
+		/* allow u64* as ctx */
+		if (btf_is_int(t) && t->size == 8)
+			return true;
+		break;
+	default:
+		break;
+	}
+
+out_warn:
+	pr_warn("prog '%s': subprog '%s' arg#%d is expected to be of `struct %s *` type\n",
+		prog->name, subprog_name, arg_idx, ctx_name);
+	return false;
+}
+
+static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_program *prog)
+{
+	int fn_id, fn_proto_id, ret_type_id, orig_proto_id;
+	int i, err, arg_cnt, fn_name_off, linkage;
+	struct btf_type *fn_t, *fn_proto_t, *t;
+	struct btf_param *p;
+
+	/* caller already validated FUNC -> FUNC_PROTO validity */
+	fn_t = btf_type_by_id(btf, orig_fn_id);
+	fn_proto_t = btf_type_by_id(btf, fn_t->type);
+
+	/* Note that each btf__add_xxx() operation invalidates
+	 * all btf_type and string pointers, so we need to be
+	 * very careful when cloning BTF types. BTF type
+	 * pointers have to be always refetched. And to avoid
+	 * problems with invalidated string pointers, we
+	 * add empty strings initially, then just fix up
+	 * name_off offsets in place. Offsets are stable for
+	 * existing strings, so that works out.
+	 */
+	fn_name_off = fn_t->name_off; /* we are about to invalidate fn_t */
+	linkage = btf_func_linkage(fn_t);
+	orig_proto_id = fn_t->type; /* original FUNC_PROTO ID */
+	ret_type_id = fn_proto_t->type; /* fn_proto_t will be invalidated */
+	arg_cnt = btf_vlen(fn_proto_t);
+
+	/* clone FUNC_PROTO and its params */
+	fn_proto_id = btf__add_func_proto(btf, ret_type_id);
+	if (fn_proto_id < 0)
+		return -EINVAL;
+
+	for (i = 0; i < arg_cnt; i++) {
+		int name_off;
+
+		/* copy original parameter data */
+		t = btf_type_by_id(btf, orig_proto_id);
+		p = &btf_params(t)[i];
+		name_off = p->name_off;
+
+		err = btf__add_func_param(btf, "", p->type);
+		if (err)
+			return err;
+
+		fn_proto_t = btf_type_by_id(btf, fn_proto_id);
+		p = &btf_params(fn_proto_t)[i];
+		p->name_off = name_off; /* use remembered str offset */
+	}
+
+	/* clone FUNC now, btf__add_func() enforces non-empty name, so use
+	 * entry program's name as a placeholder, which we replace immediately
+	 * with original name_off
+	 */
+	fn_id = btf__add_func(btf, prog->name, linkage, fn_proto_id);
+	if (fn_id < 0)
+		return -EINVAL;
+
+	fn_t = btf_type_by_id(btf, fn_id);
+	fn_t->name_off = fn_name_off; /* reuse original string */
+
+	return fn_id;
+}
+
+static int probe_kern_arg_ctx_tag(void)
+{
+	/* To minimize merge conflicts with BPF token series that refactors
+	 * feature detection code a lot, we don't integrate
+	 * probe_kern_arg_ctx_tag() into kernel_supports() feature-detection
+	 * framework yet, doing our own caching internally.
+	 * This will be cleaned up a bit later when bpf/bpf-next trees settle.
+	 */
+	static int cached_result = -1;
+	static const char strs[] = "\0a\0b\0arg:ctx\0";
+	const __u32 types[] = {
+		/* [1] INT */
+		BTF_TYPE_INT_ENC(1 /* "a" */, BTF_INT_SIGNED, 0, 32, 4),
+		/* [2] PTR -> VOID */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0),
+		/* [3] FUNC_PROTO `int(void *a)` */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1),
+		BTF_PARAM_ENC(1 /* "a" */, 2),
+		/* [4] FUNC 'a' -> FUNC_PROTO (main prog) */
+		BTF_TYPE_ENC(1 /* "a" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 3),
+		/* [5] FUNC_PROTO `int(void *b __arg_ctx)` */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1),
+		BTF_PARAM_ENC(3 /* "b" */, 2),
+		/* [6] FUNC 'b' -> FUNC_PROTO (subprog) */
+		BTF_TYPE_ENC(3 /* "b" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 5),
+		/* [7] DECL_TAG 'arg:ctx' -> func 'b' arg 'b' */
+		BTF_TYPE_DECL_TAG_ENC(5 /* "arg:ctx" */, 6, 0),
+	};
+	const struct bpf_insn insns[] = {
+		/* main prog */
+		BPF_CALL_REL(+1),
+		BPF_EXIT_INSN(),
+		/* global subprog */
+		BPF_EMIT_CALL(BPF_FUNC_get_func_ip), /* needs PTR_TO_CTX */
+		BPF_EXIT_INSN(),
+	};
+	const struct bpf_func_info_min func_infos[] = {
+		{ 0, 4 }, /* main prog -> FUNC 'a' */
+		{ 2, 6 }, /* subprog -> FUNC 'b' */
+	};
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+	int prog_fd, btf_fd, insn_cnt = ARRAY_SIZE(insns);
+
+	if (cached_result >= 0)
+		return cached_result;
+
+	btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs));
+	if (btf_fd < 0)
+		return 0;
+
+	opts.prog_btf_fd = btf_fd;
+	opts.func_info = &func_infos;
+	opts.func_info_cnt = ARRAY_SIZE(func_infos);
+	opts.func_info_rec_size = sizeof(func_infos[0]);
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, "det_arg_ctx",
+				"GPL", insns, insn_cnt, &opts);
+	close(btf_fd);
+
+	cached_result = probe_fd(prog_fd);
+	return cached_result;
+}
+
+/* Check if main program or global subprog's function prototype has `arg:ctx`
+ * argument tags, and, if necessary, substitute correct type to match what BPF
+ * verifier would expect, taking into account specific program type. This
+ * allows to support __arg_ctx tag transparently on old kernels that don't yet
+ * have a native support for it in the verifier, making user's life much
+ * easier.
+ */
+static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_program *prog)
+{
+	const char *ctx_name = NULL, *ctx_tag = "arg:ctx", *fn_name;
+	struct bpf_func_info_min *func_rec;
+	struct btf_type *fn_t, *fn_proto_t;
+	struct btf *btf = obj->btf;
+	const struct btf_type *t;
+	struct btf_param *p;
+	int ptr_id = 0, struct_id, tag_id, orig_fn_id;
+	int i, n, arg_idx, arg_cnt, err, rec_idx;
+	int *orig_ids;
+
+	/* no .BTF.ext, no problem */
+	if (!obj->btf_ext || !prog->func_info)
+		return 0;
+
+	/* don't do any fix ups if kernel natively supports __arg_ctx */
+	if (probe_kern_arg_ctx_tag() > 0)
+		return 0;
+
+	/* some BPF program types just don't have named context structs, so
+	 * this fallback mechanism doesn't work for them
+	 */
+	for (i = 0; i < ARRAY_SIZE(global_ctx_map); i++) {
+		if (global_ctx_map[i].prog_type != prog->type)
+			continue;
+		ctx_name = global_ctx_map[i].ctx_name;
+		break;
+	}
+	if (!ctx_name)
+		return 0;
+
+	/* remember original func BTF IDs to detect if we already cloned them */
+	orig_ids = calloc(prog->func_info_cnt, sizeof(*orig_ids));
+	if (!orig_ids)
+		return -ENOMEM;
+	for (i = 0; i < prog->func_info_cnt; i++) {
+		func_rec = prog->func_info + prog->func_info_rec_size * i;
+		orig_ids[i] = func_rec->type_id;
+	}
+
+	/* go through each DECL_TAG with "arg:ctx" and see if it points to one
+	 * of our subprogs; if yes and subprog is global and needs adjustment,
+	 * clone and adjust FUNC -> FUNC_PROTO combo
+	 */
+	for (i = 1, n = btf__type_cnt(btf); i < n; i++) {
+		/* only DECL_TAG with "arg:ctx" value are interesting */
+		t = btf__type_by_id(btf, i);
+		if (!btf_is_decl_tag(t))
+			continue;
+		if (strcmp(btf__str_by_offset(btf, t->name_off), ctx_tag) != 0)
+			continue;
+
+		/* only global funcs need adjustment, if at all */
+		orig_fn_id = t->type;
+		fn_t = btf_type_by_id(btf, orig_fn_id);
+		if (!btf_is_func(fn_t) || btf_func_linkage(fn_t) != BTF_FUNC_GLOBAL)
+			continue;
+
+		/* sanity check FUNC -> FUNC_PROTO chain, just in case */
+		fn_proto_t = btf_type_by_id(btf, fn_t->type);
+		if (!fn_proto_t || !btf_is_func_proto(fn_proto_t))
+			continue;
+
+		/* find corresponding func_info record */
+		func_rec = NULL;
+		for (rec_idx = 0; rec_idx < prog->func_info_cnt; rec_idx++) {
+			if (orig_ids[rec_idx] == t->type) {
+				func_rec = prog->func_info + prog->func_info_rec_size * rec_idx;
+				break;
+			}
+		}
+		/* current main program doesn't call into this subprog */
+		if (!func_rec)
+			continue;
+
+		/* some more sanity checking of DECL_TAG */
+		arg_cnt = btf_vlen(fn_proto_t);
+		arg_idx = btf_decl_tag(t)->component_idx;
+		if (arg_idx < 0 || arg_idx >= arg_cnt)
+			continue;
+
+		/* check if we should fix up argument type */
+		p = &btf_params(fn_proto_t)[arg_idx];
+		fn_name = btf__str_by_offset(btf, fn_t->name_off) ?: "<anon>";
+		if (!need_func_arg_type_fixup(btf, prog, fn_name, arg_idx, p->type, ctx_name))
+			continue;
+
+		/* clone fn/fn_proto, unless we already did it for another arg */
+		if (func_rec->type_id == orig_fn_id) {
+			int fn_id;
+
+			fn_id = clone_func_btf_info(btf, orig_fn_id, prog);
+			if (fn_id < 0) {
+				err = fn_id;
+				goto err_out;
+			}
+
+			/* point func_info record to a cloned FUNC type */
+			func_rec->type_id = fn_id;
+		}
+
+		/* create PTR -> STRUCT type chain to mark PTR_TO_CTX argument;
+		 * we do it just once per main BPF program, as all global
+		 * funcs share the same program type, so need only PTR ->
+		 * STRUCT type chain
+		 */
+		if (ptr_id == 0) {
+			struct_id = btf__add_struct(btf, ctx_name, 0);
+			ptr_id = btf__add_ptr(btf, struct_id);
+			if (ptr_id < 0 || struct_id < 0) {
+				err = -EINVAL;
+				goto err_out;
+			}
+		}
+
+		/* for completeness, clone DECL_TAG and point it to cloned param */
+		tag_id = btf__add_decl_tag(btf, ctx_tag, func_rec->type_id, arg_idx);
+		if (tag_id < 0) {
+			err = -EINVAL;
+			goto err_out;
+		}
+
+		/* all the BTF manipulations invalidated pointers, refetch them */
+		fn_t = btf_type_by_id(btf, func_rec->type_id);
+		fn_proto_t = btf_type_by_id(btf, fn_t->type);
+
+		/* fix up type ID pointed to by param */
+		p = &btf_params(fn_proto_t)[arg_idx];
+		p->type = ptr_id;
+	}
+
+	free(orig_ids);
+	return 0;
+err_out:
+	free(orig_ids);
+	return err;
+}
+
+static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 {
 	struct bpf_program *prog;
 	size_t i, j;
@@ -6682,6 +7109,9 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 			return err;
 		}
 
+		err = bpf_prog_assign_exc_cb(obj, prog);
+		if (err)
+			return err;
 		/* Now, also append exception callback if it has not been done already. */
 		if (prog->exception_cb_idx >= 0) {
 			struct bpf_program *subprog = &obj->programs[prog->exception_cb_idx];
@@ -6701,19 +7131,28 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 			}
 		}
 	}
-	/* Process data relos for main programs */
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
 		if (prog_is_subprog(obj, prog))
 			continue;
 		if (!prog->autoload)
 			continue;
+
+		/* Process data relos for main programs */
 		err = bpf_object__relocate_data(obj, prog);
 		if (err) {
 			pr_warn("prog '%s': failed to relocate data references: %d\n",
 				prog->name, err);
 			return err;
 		}
+
+		/* Fix up .BTF.ext information, if necessary */
+		err = bpf_program_fixup_func_info(obj, prog);
+		if (err) {
+			pr_warn("prog '%s': failed to perform .BTF.ext fix ups: %d\n",
+				prog->name, err);
+			return err;
+		}
 	}
 
 	return 0;
@@ -7043,7 +7482,7 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 	load_attr.prog_ifindex = prog->prog_ifindex;
 
 	/* specify func_info/line_info only if kernel supports them */
-	btf_fd = bpf_object__btf_fd(obj);
+	btf_fd = btf__fd(obj->btf);
 	if (btf_fd >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) {
 		load_attr.prog_btf_fd = btf_fd;
 		load_attr.func_info = prog->func_info;
@@ -7128,7 +7567,7 @@ retry_load:
 				if (map->libbpf_type != LIBBPF_MAP_RODATA)
 					continue;
 
-				if (bpf_prog_bind_map(ret, bpf_map__fd(map), NULL)) {
+				if (bpf_prog_bind_map(ret, map->fd, NULL)) {
 					cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 					pr_warn("prog '%s': failed to bind map '%s': %s\n",
 						prog->name, map->real_name, cp);
@@ -8060,11 +8499,11 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
 	err = bpf_object__probe_loading(obj);
 	err = err ? : bpf_object__load_vmlinux_btf(obj, false);
 	err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
-	err = err ? : bpf_object__sanitize_and_load_btf(obj);
 	err = err ? : bpf_object__sanitize_maps(obj);
 	err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
-	err = err ? : bpf_object__create_maps(obj);
 	err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path);
+	err = err ? : bpf_object__sanitize_and_load_btf(obj);
+	err = err ? : bpf_object__create_maps(obj);
 	err = err ? : bpf_object__load_progs(obj, extra_log_level);
 	err = err ? : bpf_object_init_prog_arrays(obj);
 	err = err ? : bpf_object_prepare_struct_ops(obj);
@@ -8073,8 +8512,6 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
 		/* reset FDs */
 		if (obj->btf)
 			btf__set_fd(obj->btf, -1);
-		for (i = 0; i < obj->nr_maps; i++)
-			obj->maps[i].fd = -1;
 		if (!err)
 			err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps);
 	}
@@ -9594,7 +10031,11 @@ int libbpf_attach_type_by_name(const char *name,
 
 int bpf_map__fd(const struct bpf_map *map)
 {
-	return map ? map->fd : libbpf_err(-EINVAL);
+	if (!map)
+		return libbpf_err(-EINVAL);
+	if (!map_is_created(map))
+		return -1;
+	return map->fd;
 }
 
 static bool map_uses_real_name(const struct bpf_map *map)
@@ -9630,7 +10071,7 @@ enum bpf_map_type bpf_map__type(const struct bpf_map *map)
 
 int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->def.type = type;
 	return 0;
@@ -9643,7 +10084,7 @@ __u32 bpf_map__map_flags(const struct bpf_map *map)
 
 int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->def.map_flags = flags;
 	return 0;
@@ -9656,7 +10097,7 @@ __u64 bpf_map__map_extra(const struct bpf_map *map)
 
 int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->map_extra = map_extra;
 	return 0;
@@ -9669,7 +10110,7 @@ __u32 bpf_map__numa_node(const struct bpf_map *map)
 
 int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->numa_node = numa_node;
 	return 0;
@@ -9682,7 +10123,7 @@ __u32 bpf_map__key_size(const struct bpf_map *map)
 
 int bpf_map__set_key_size(struct bpf_map *map, __u32 size)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->def.key_size = size;
 	return 0;
@@ -9766,7 +10207,7 @@ static int map_btf_datasec_resize(struct bpf_map *map, __u32 size)
 
 int bpf_map__set_value_size(struct bpf_map *map, __u32 size)
 {
-	if (map->fd >= 0)
+	if (map->obj->loaded || map->reused)
 		return libbpf_err(-EBUSY);
 
 	if (map->mmaped) {
@@ -9807,8 +10248,11 @@ __u32 bpf_map__btf_value_type_id(const struct bpf_map *map)
 int bpf_map__set_initial_value(struct bpf_map *map,
 			       const void *data, size_t size)
 {
+	if (map->obj->loaded || map->reused)
+		return libbpf_err(-EBUSY);
+
 	if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG ||
-	    size != map->def.value_size || map->fd >= 0)
+	    size != map->def.value_size)
 		return libbpf_err(-EINVAL);
 
 	memcpy(map->mmaped, data, size);
@@ -9835,7 +10279,7 @@ __u32 bpf_map__ifindex(const struct bpf_map *map)
 
 int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->map_ifindex = ifindex;
 	return 0;
@@ -9940,7 +10384,7 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name)
 static int validate_map_op(const struct bpf_map *map, size_t key_sz,
 			   size_t value_sz, bool check_value_sz)
 {
-	if (map->fd <= 0)
+	if (!map_is_created(map)) /* map is not yet created */
 		return -ENOENT;
 
 	if (map->def.key_size != key_sz) {
@@ -11453,7 +11897,7 @@ bpf_program__attach_uprobe_multi(const struct bpf_program *prog,
 			return libbpf_err_ptr(err);
 		offsets = resolved_offsets;
 	} else if (syms) {
-		err = elf_resolve_syms_offsets(path, cnt, syms, &resolved_offsets);
+		err = elf_resolve_syms_offsets(path, cnt, syms, &resolved_offsets, STT_FUNC);
 		if (err < 0)
 			return libbpf_err_ptr(err);
 		offsets = resolved_offsets;
@@ -12393,7 +12837,7 @@ int bpf_link__update_map(struct bpf_link *link, const struct bpf_map *map)
 	__u32 zero = 0;
 	int err;
 
-	if (!bpf_map__is_struct_ops(map) || map->fd < 0)
+	if (!bpf_map__is_struct_ops(map) || !map_is_created(map))
 		return -EINVAL;
 
 	st_ops_link = container_of(link, struct bpf_link_struct_ops, link);
@@ -13297,7 +13741,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s)
 	for (i = 0; i < s->map_cnt; i++) {
 		struct bpf_map *map = *s->maps[i].map;
 		size_t mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries);
-		int prot, map_fd = bpf_map__fd(map);
+		int prot, map_fd = map->fd;
 		void **mmaped = s->maps[i].mmaped;
 
 		if (!mmaped)
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index b52dc28dc8..91c5aef7da 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -409,3 +409,6 @@ LIBBPF_1.3.0 {
 		ring__size;
 		ring_buffer__ring;
 } LIBBPF_1.2.0;
+
+LIBBPF_1.4.0 {
+} LIBBPF_1.3.0;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 57dec645d6..878a0d0b51 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -569,6 +569,20 @@ static inline int ensure_good_fd(int fd)
 	return fd;
 }
 
+/* Point *fixed_fd* to the same file that *tmp_fd* points to.
+ * Regardless of success, *tmp_fd* is closed.
+ * Whatever *fixed_fd* pointed to is closed silently.
+ */
+static inline int reuse_fd(int fixed_fd, int tmp_fd)
+{
+	int err;
+
+	err = dup2(tmp_fd, fixed_fd);
+	err = err < 0 ? -errno : 0;
+	close(tmp_fd); /* clean up temporary FD */
+	return err;
+}
+
 /* The following two functions are exposed to bpftool */
 int bpf_core_add_cands(struct bpf_core_cand *local_cand,
 		       size_t local_essent_len,
@@ -608,7 +622,8 @@ int elf_open(const char *binary_path, struct elf_fd *elf_fd);
 void elf_close(struct elf_fd *elf_fd);
 
 int elf_resolve_syms_offsets(const char *binary_path, int cnt,
-			     const char **syms, unsigned long **poffsets);
+			     const char **syms, unsigned long **poffsets,
+			     int st_type);
 int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern,
 				 unsigned long **poffsets, size_t *pcnt);
 
diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h
index 290411ddb3..e783a47da8 100644
--- a/tools/lib/bpf/libbpf_version.h
+++ b/tools/lib/bpf/libbpf_version.h
@@ -4,6 +4,6 @@
 #define __LIBBPF_VERSION_H
 
 #define LIBBPF_MAJOR_VERSION 1
-#define LIBBPF_MINOR_VERSION 3
+#define LIBBPF_MINOR_VERSION 4
 
 #endif /* __LIBBPF_VERSION_H */
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 5ced96d99f..16bca56002 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -719,13 +719,28 @@ static int linker_sanity_check_elf(struct src_obj *obj)
 			return -EINVAL;
 		}
 
-		if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign))
+		if (is_dwarf_sec_name(sec->sec_name))
+			continue;
+
+		if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign)) {
+			pr_warn("ELF section #%zu alignment %llu is non pow-of-2 alignment in %s\n",
+				sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign,
+				obj->filename);
 			return -EINVAL;
-		if (sec->shdr->sh_addralign != sec->data->d_align)
+		}
+		if (sec->shdr->sh_addralign != sec->data->d_align) {
+			pr_warn("ELF section #%zu has inconsistent alignment addr=%llu != d=%llu in %s\n",
+				sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign,
+				(long long unsigned)sec->data->d_align, obj->filename);
 			return -EINVAL;
+		}
 
-		if (sec->shdr->sh_size != sec->data->d_size)
+		if (sec->shdr->sh_size != sec->data->d_size) {
+			pr_warn("ELF section #%zu has inconsistent section size sh=%llu != d=%llu in %s\n",
+				sec->sec_idx, (long long unsigned)sec->shdr->sh_size,
+				(long long unsigned)sec->data->d_size, obj->filename);
 			return -EINVAL;
+		}
 
 		switch (sec->shdr->sh_type) {
 		case SHT_SYMTAB:
@@ -737,8 +752,12 @@ static int linker_sanity_check_elf(struct src_obj *obj)
 			break;
 		case SHT_PROGBITS:
 			if (sec->shdr->sh_flags & SHF_EXECINSTR) {
-				if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0)
+				if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0) {
+					pr_warn("ELF section #%zu has unexpected size alignment %llu in %s\n",
+						sec->sec_idx, (long long unsigned)sec->shdr->sh_size,
+						obj->filename);
 					return -EINVAL;
+				}
 			}
 			break;
 		case SHT_NOBITS:
diff --git a/tools/lib/perf/Documentation/examples/sampling.c b/tools/lib/perf/Documentation/examples/sampling.c
index 8e1a926a9c..bc142f0664 100644
--- a/tools/lib/perf/Documentation/examples/sampling.c
+++ b/tools/lib/perf/Documentation/examples/sampling.c
@@ -39,7 +39,7 @@ int main(int argc, char **argv)
 
 	libperf_init(libperf_print);
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus) {
 		fprintf(stderr, "failed to create cpus\n");
 		return -1;
diff --git a/tools/lib/perf/Documentation/libperf-sampling.txt b/tools/lib/perf/Documentation/libperf-sampling.txt
index d6ca24f6ef..2378980fab 100644
--- a/tools/lib/perf/Documentation/libperf-sampling.txt
+++ b/tools/lib/perf/Documentation/libperf-sampling.txt
@@ -97,7 +97,7 @@ In this case we will monitor all the available CPUs:
 
 [source,c]
 --
- 42         cpus = perf_cpu_map__new(NULL);
+ 42         cpus = perf_cpu_map__new_online_cpus();
  43         if (!cpus) {
  44                 fprintf(stderr, "failed to create cpus\n");
  45                 return -1;
diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index a8f1a23793..fcfb9499ef 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -37,7 +37,7 @@ SYNOPSIS
 
   struct perf_cpu_map;
 
-  struct perf_cpu_map *perf_cpu_map__dummy_new(void);
+  struct perf_cpu_map *perf_cpu_map__new_any_cpu(void);
   struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
   struct perf_cpu_map *perf_cpu_map__read(FILE *file);
   struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
@@ -46,7 +46,7 @@ SYNOPSIS
   void perf_cpu_map__put(struct perf_cpu_map *map);
   int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
   int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
-  bool perf_cpu_map__empty(const struct perf_cpu_map *map);
+  bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map);
   int perf_cpu_map__max(struct perf_cpu_map *map);
   bool perf_cpu_map__has(const struct perf_cpu_map *map, int cpu);
 
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 2a5a292173..4adcd7920d 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -9,6 +9,7 @@
 #include <unistd.h>
 #include <ctype.h>
 #include <limits.h>
+#include "internal.h"
 
 void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus)
 {
@@ -27,7 +28,7 @@ struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
 	return result;
 }
 
-struct perf_cpu_map *perf_cpu_map__dummy_new(void)
+struct perf_cpu_map *perf_cpu_map__new_any_cpu(void)
 {
 	struct perf_cpu_map *cpus = perf_cpu_map__alloc(1);
 
@@ -66,15 +67,21 @@ void perf_cpu_map__put(struct perf_cpu_map *map)
 	}
 }
 
-static struct perf_cpu_map *cpu_map__default_new(void)
+static struct perf_cpu_map *cpu_map__new_sysconf(void)
 {
 	struct perf_cpu_map *cpus;
-	int nr_cpus;
+	int nr_cpus, nr_cpus_conf;
 
 	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
 	if (nr_cpus < 0)
 		return NULL;
 
+	nr_cpus_conf = sysconf(_SC_NPROCESSORS_CONF);
+	if (nr_cpus != nr_cpus_conf) {
+		pr_warning("Number of online CPUs (%d) differs from the number configured (%d) the CPU map will only cover the first %d CPUs.",
+			nr_cpus, nr_cpus_conf, nr_cpus);
+	}
+
 	cpus = perf_cpu_map__alloc(nr_cpus);
 	if (cpus != NULL) {
 		int i;
@@ -86,9 +93,27 @@ static struct perf_cpu_map *cpu_map__default_new(void)
 	return cpus;
 }
 
-struct perf_cpu_map *perf_cpu_map__default_new(void)
+static struct perf_cpu_map *cpu_map__new_sysfs_online(void)
 {
-	return cpu_map__default_new();
+	struct perf_cpu_map *cpus = NULL;
+	FILE *onlnf;
+
+	onlnf = fopen("/sys/devices/system/cpu/online", "r");
+	if (onlnf) {
+		cpus = perf_cpu_map__read(onlnf);
+		fclose(onlnf);
+	}
+	return cpus;
+}
+
+struct perf_cpu_map *perf_cpu_map__new_online_cpus(void)
+{
+	struct perf_cpu_map *cpus = cpu_map__new_sysfs_online();
+
+	if (cpus)
+		return cpus;
+
+	return cpu_map__new_sysconf();
 }
 
 
@@ -180,27 +205,11 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
 
 	if (nr_cpus > 0)
 		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-	else
-		cpus = cpu_map__default_new();
 out_free_tmp:
 	free(tmp_cpus);
 	return cpus;
 }
 
-static struct perf_cpu_map *cpu_map__read_all_cpu_map(void)
-{
-	struct perf_cpu_map *cpus = NULL;
-	FILE *onlnf;
-
-	onlnf = fopen("/sys/devices/system/cpu/online", "r");
-	if (!onlnf)
-		return cpu_map__default_new();
-
-	cpus = perf_cpu_map__read(onlnf);
-	fclose(onlnf);
-	return cpus;
-}
-
 struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 {
 	struct perf_cpu_map *cpus = NULL;
@@ -211,7 +220,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 	int max_entries = 0;
 
 	if (!cpu_list)
-		return cpu_map__read_all_cpu_map();
+		return perf_cpu_map__new_online_cpus();
 
 	/*
 	 * must handle the case of empty cpumap to cover
@@ -268,10 +277,12 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 
 	if (nr_cpus > 0)
 		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-	else if (*cpu_list != '\0')
-		cpus = cpu_map__default_new();
-	else
-		cpus = perf_cpu_map__dummy_new();
+	else if (*cpu_list != '\0') {
+		pr_warning("Unexpected characters at end of cpu list ('%s'), using online CPUs.",
+			   cpu_list);
+		cpus = perf_cpu_map__new_online_cpus();
+	} else
+		cpus = perf_cpu_map__new_any_cpu();
 invalid:
 	free(tmp_cpus);
 out:
@@ -300,7 +311,7 @@ int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
 	return cpus ? __perf_cpu_map__nr(cpus) : 1;
 }
 
-bool perf_cpu_map__empty(const struct perf_cpu_map *map)
+bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map)
 {
 	return map ? __perf_cpu_map__cpu(map, 0).cpu == -1 : true;
 }
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 3acbbccc19..c6d67fc9e5 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -39,7 +39,7 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 	if (evsel->system_wide) {
 		/* System wide: set the cpu map of the evsel to all online CPUs. */
 		perf_cpu_map__put(evsel->cpus);
-		evsel->cpus = perf_cpu_map__new(NULL);
+		evsel->cpus = perf_cpu_map__new_online_cpus();
 	} else if (evlist->has_user_cpus && evsel->is_pmu_core) {
 		/*
 		 * User requested CPUs on a core PMU, ensure the requested CPUs
@@ -248,10 +248,10 @@ u64 perf_evlist__read_format(struct perf_evlist *evlist)
 
 static void perf_evlist__id_hash(struct perf_evlist *evlist,
 				 struct perf_evsel *evsel,
-				 int cpu, int thread, u64 id)
+				 int cpu_map_idx, int thread, u64 id)
 {
 	int hash;
-	struct perf_sample_id *sid = SID(evsel, cpu, thread);
+	struct perf_sample_id *sid = SID(evsel, cpu_map_idx, thread);
 
 	sid->id = id;
 	sid->evsel = evsel;
@@ -269,21 +269,27 @@ void perf_evlist__reset_id_hash(struct perf_evlist *evlist)
 
 void perf_evlist__id_add(struct perf_evlist *evlist,
 			 struct perf_evsel *evsel,
-			 int cpu, int thread, u64 id)
+			 int cpu_map_idx, int thread, u64 id)
 {
-	perf_evlist__id_hash(evlist, evsel, cpu, thread, id);
+	if (!SID(evsel, cpu_map_idx, thread))
+		return;
+
+	perf_evlist__id_hash(evlist, evsel, cpu_map_idx, thread, id);
 	evsel->id[evsel->ids++] = id;
 }
 
 int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 			   struct perf_evsel *evsel,
-			   int cpu, int thread, int fd)
+			   int cpu_map_idx, int thread, int fd)
 {
 	u64 read_data[4] = { 0, };
 	int id_idx = 1; /* The first entry is the counter value */
 	u64 id;
 	int ret;
 
+	if (!SID(evsel, cpu_map_idx, thread))
+		return -1;
+
 	ret = ioctl(fd, PERF_EVENT_IOC_ID, &id);
 	if (!ret)
 		goto add;
@@ -312,7 +318,7 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 	id = read_data[id_idx];
 
 add:
-	perf_evlist__id_add(evlist, evsel, cpu, thread, id);
+	perf_evlist__id_add(evlist, evsel, cpu_map_idx, thread, id);
 	return 0;
 }
 
@@ -619,7 +625,7 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist)
 
 	/* One for each CPU */
 	nr_mmaps = perf_cpu_map__nr(evlist->all_cpus);
-	if (perf_cpu_map__empty(evlist->all_cpus)) {
+	if (perf_cpu_map__has_any_cpu_or_is_empty(evlist->all_cpus)) {
 		/* Plus one for each thread */
 		nr_mmaps += perf_thread_map__nr(evlist->threads);
 		/* Minus the per-thread CPU (-1) */
@@ -653,7 +659,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
 		return -ENOMEM;
 
-	if (perf_cpu_map__empty(cpus))
+	if (perf_cpu_map__has_any_cpu_or_is_empty(cpus))
 		return mmap_per_thread(evlist, ops, mp);
 
 	return mmap_per_cpu(evlist, ops, mp);
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index 8b51b008a8..c071609532 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -120,7 +120,7 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 		static struct perf_cpu_map *empty_cpu_map;
 
 		if (empty_cpu_map == NULL) {
-			empty_cpu_map = perf_cpu_map__dummy_new();
+			empty_cpu_map = perf_cpu_map__new_any_cpu();
 			if (empty_cpu_map == NULL)
 				return -ENOMEM;
 		}
diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index d86ffe8ed4..f43bdb9b62 100644
--- a/tools/lib/perf/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
@@ -126,11 +126,11 @@ u64 perf_evlist__read_format(struct perf_evlist *evlist);
 
 void perf_evlist__id_add(struct perf_evlist *evlist,
 			 struct perf_evsel *evsel,
-			 int cpu, int thread, u64 id);
+			 int cpu_map_idx, int thread, u64 id);
 
 int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 			   struct perf_evsel *evsel,
-			   int cpu, int thread, int fd);
+			   int cpu_map_idx, int thread, int fd);
 
 void perf_evlist__reset_id_hash(struct perf_evlist *evlist);
 
diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h
index 5a062af8e9..5f08cab61e 100644
--- a/tools/lib/perf/include/internal/mmap.h
+++ b/tools/lib/perf/include/internal/mmap.h
@@ -33,7 +33,8 @@ struct perf_mmap {
 	bool			 overwrite;
 	u64			 flush;
 	libperf_unmap_cb_t	 unmap_cb;
-	char			 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
+	void			*event_copy;
+	size_t			 event_copy_sz;
 	struct perf_mmap	*next;
 };
 
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index e38d859a38..228c6c629b 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -19,10 +19,23 @@ struct perf_cache {
 struct perf_cpu_map;
 
 /**
- * perf_cpu_map__dummy_new - a map with a singular "any CPU"/dummy -1 value.
+ * perf_cpu_map__new_any_cpu - a map with a singular "any CPU"/dummy -1 value.
+ */
+LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_any_cpu(void);
+/**
+ * perf_cpu_map__new_online_cpus - a map read from
+ *                                 /sys/devices/system/cpu/online if
+ *                                 available. If reading wasn't possible a map
+ *                                 is created using the online processors
+ *                                 assuming the first 'n' processors are all
+ *                                 online.
+ */
+LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_online_cpus(void);
+/**
+ * perf_cpu_map__new - create a map from the given cpu_list such as "0-7". If no
+ *                     cpu_list argument is provided then
+ *                     perf_cpu_map__new_online_cpus is returned.
  */
-LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
-LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
@@ -31,12 +44,23 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig,
 							 struct perf_cpu_map *other);
 LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__cpu - get the CPU value at the given index. Returns -1 if index
+ *                     is invalid.
+ */
 LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
+/**
+ * perf_cpu_map__nr - for an empty map returns 1, as perf_cpu_map__cpu returns a
+ *                    cpu of -1 for an invalid index, this makes an empty map
+ *                    look like it contains the "any CPU"/dummy value. Otherwise
+ *                    the result is the number CPUs in the map plus one if the
+ *                    "any CPU"/dummy value is present.
+ */
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
 /**
- * perf_cpu_map__empty - is map either empty or the "any CPU"/dummy value.
+ * perf_cpu_map__has_any_cpu_or_is_empty - is map either empty or has the "any CPU"/dummy value.
  */
-LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
+LIBPERF_API bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map);
 LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map);
 LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
 LIBPERF_API bool perf_cpu_map__equal(const struct perf_cpu_map *lhs,
@@ -51,6 +75,12 @@ LIBPERF_API bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map);
 	     (idx) < perf_cpu_map__nr(cpus);			\
 	     (idx)++, (cpu) = perf_cpu_map__cpu(cpus, idx))
 
+#define perf_cpu_map__for_each_cpu_skip_any(_cpu, idx, cpus)	\
+	for ((idx) = 0, (_cpu) = perf_cpu_map__cpu(cpus, idx);	\
+	     (idx) < perf_cpu_map__nr(cpus);			\
+	     (idx)++, (_cpu) = perf_cpu_map__cpu(cpus, idx))	\
+		if ((_cpu).cpu != -1)
+
 #define perf_cpu_map__for_each_idx(idx, cpus)				\
 	for ((idx) = 0; (idx) < perf_cpu_map__nr(cpus); (idx)++)
 
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 190b56ae92..10b3f37226 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -1,15 +1,15 @@
 LIBPERF_0.0.1 {
 	global:
 		libperf_init;
-		perf_cpu_map__dummy_new;
-		perf_cpu_map__default_new;
+		perf_cpu_map__new_any_cpu;
+		perf_cpu_map__new_online_cpus;
 		perf_cpu_map__get;
 		perf_cpu_map__put;
 		perf_cpu_map__new;
 		perf_cpu_map__read;
 		perf_cpu_map__nr;
 		perf_cpu_map__cpu;
-		perf_cpu_map__empty;
+		perf_cpu_map__has_any_cpu_or_is_empty;
 		perf_cpu_map__max;
 		perf_cpu_map__has;
 		perf_thread_map__new_array;
diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index 2184814b37..0c903c2372 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -19,6 +19,7 @@
 void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
 		     bool overwrite, libperf_unmap_cb_t unmap_cb)
 {
+	/* Assume fields were zero initialized. */
 	map->fd = -1;
 	map->overwrite = overwrite;
 	map->unmap_cb  = unmap_cb;
@@ -51,13 +52,18 @@ int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
 
 void perf_mmap__munmap(struct perf_mmap *map)
 {
-	if (map && map->base != NULL) {
+	if (!map)
+		return;
+
+	zfree(&map->event_copy);
+	map->event_copy_sz = 0;
+	if (map->base) {
 		munmap(map->base, perf_mmap__mmap_len(map));
 		map->base = NULL;
 		map->fd = -1;
 		refcount_set(&map->refcnt, 0);
 	}
-	if (map && map->unmap_cb)
+	if (map->unmap_cb)
 		map->unmap_cb(map);
 }
 
@@ -223,9 +229,17 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map,
 		 */
 		if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) {
 			unsigned int offset = *startp;
-			unsigned int len = min(sizeof(*event), size), cpy;
+			unsigned int len = size, cpy;
 			void *dst = map->event_copy;
 
+			if (size > map->event_copy_sz) {
+				dst = realloc(map->event_copy, size);
+				if (!dst)
+					return NULL;
+				map->event_copy = dst;
+				map->event_copy_sz = size;
+			}
+
 			do {
 				cpy = min(map->mask + 1 - (offset & map->mask), len);
 				memcpy(dst, &data[offset & map->mask], cpy);
diff --git a/tools/lib/perf/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c
index 87b0510a55..c998b1dae8 100644
--- a/tools/lib/perf/tests/test-cpumap.c
+++ b/tools/lib/perf/tests/test-cpumap.c
@@ -21,7 +21,7 @@ int test_cpumap(int argc, char **argv)
 
 	libperf_init(libperf_print);
 
-	cpus = perf_cpu_map__dummy_new();
+	cpus = perf_cpu_map__new_any_cpu();
 	if (!cpus)
 		return -1;
 
@@ -29,7 +29,7 @@ int test_cpumap(int argc, char **argv)
 	perf_cpu_map__put(cpus);
 	perf_cpu_map__put(cpus);
 
-	cpus = perf_cpu_map__default_new();
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		return -1;
 
diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c
index ed616fc19b..10f70cb41f 100644
--- a/tools/lib/perf/tests/test-evlist.c
+++ b/tools/lib/perf/tests/test-evlist.c
@@ -46,7 +46,7 @@ static int test_stat_cpu(void)
 	};
 	int err, idx;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	__T("failed to create cpus", cpus);
 
 	evlist = perf_evlist__new();
@@ -261,7 +261,7 @@ static int test_mmap_thread(void)
 	threads = perf_thread_map__new_dummy();
 	__T("failed to create threads", threads);
 
-	cpus = perf_cpu_map__dummy_new();
+	cpus = perf_cpu_map__new_any_cpu();
 	__T("failed to create cpus", cpus);
 
 	perf_thread_map__set_pid(threads, 0, pid);
@@ -350,7 +350,7 @@ static int test_mmap_cpus(void)
 
 	attr.config = id;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	__T("failed to create cpus", cpus);
 
 	evlist = perf_evlist__new();
diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c
index a11fc51bfb..545ec31505 100644
--- a/tools/lib/perf/tests/test-evsel.c
+++ b/tools/lib/perf/tests/test-evsel.c
@@ -27,7 +27,7 @@ static int test_stat_cpu(void)
 	};
 	int err, idx;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	__T("failed to create cpus", cpus);
 
 	evsel = perf_evsel__new(&attr);