From: Jiri Olsa <jolsa@kernel.org>
To: Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Andrii Nakryiko <andrii@kernel.org>
Cc: bpf@vger.kernel.org, Martin KaFai Lau <kafai@fb.com>,
Song Liu <songliubraving@fb.com>, Yonghong Song <yhs@fb.com>,
John Fastabend <john.fastabend@gmail.com>,
KP Singh <kpsingh@chromium.org>,
Stanislav Fomichev <sdf@google.com>, Hao Luo <haoluo@google.com>
Subject: [PATCHv4 bpf-next 10/28] libbpf: Add elf symbol iterator
Date: Thu, 20 Jul 2023 13:35:32 +0200 [thread overview]
Message-ID: <20230720113550.369257-11-jolsa@kernel.org> (raw)
In-Reply-To: <20230720113550.369257-1-jolsa@kernel.org>
Adding elf symbol iterator object (and some functions) that follow
open-coded iterator pattern and some functions to ease up iterating
elf object symbols.
The idea is to iterate single symbol section with:
struct elf_sym_iter iter;
struct elf_sym *sym;
if (elf_sym_iter_new(&iter, elf, binary_path, SHT_DYNSYM))
goto error;
while ((sym = elf_sym_iter_next(&iter))) {
...
}
I considered opening the elf inside the iterator and iterate all symbol
sections, but then it gets more complicated wrt user checks for when
the next section is processed.
Plus side is the we don't need 'exit' function, because caller/user is
in charge of that.
The returned iterated symbol object from elf_sym_iter_next function
is placed inside the struct elf_sym_iter, so no extra allocation or
argument is needed.
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/lib/bpf/elf.c | 179 ++++++++++++++++++++++++++++----------------
1 file changed, 115 insertions(+), 64 deletions(-)
diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index 71363acdeb67..8a3f8a725981 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -60,6 +60,104 @@ static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn)
return NULL;
}
+struct elf_sym {
+ const char *name;
+ GElf_Sym sym;
+ GElf_Shdr sh;
+};
+
+struct elf_sym_iter {
+ Elf *elf;
+ Elf_Data *syms;
+ size_t nr_syms;
+ size_t strtabidx;
+ size_t next_sym_idx;
+ struct elf_sym sym;
+ int st_type;
+};
+
+static int elf_sym_iter_new(struct elf_sym_iter *iter,
+ Elf *elf, const char *binary_path,
+ int sh_type, int st_type)
+{
+ Elf_Scn *scn = NULL;
+ GElf_Ehdr ehdr;
+ GElf_Shdr sh;
+
+ memset(iter, 0, sizeof(*iter));
+
+ if (!gelf_getehdr(elf, &ehdr)) {
+ pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1));
+ return -EINVAL;
+ }
+
+ scn = elf_find_next_scn_by_type(elf, sh_type, NULL);
+ if (!scn) {
+ pr_debug("elf: failed to find symbol table ELF sections in '%s'\n",
+ binary_path);
+ return -ENOENT;
+ }
+
+ if (!gelf_getshdr(scn, &sh))
+ return -EINVAL;
+
+ iter->strtabidx = sh.sh_link;
+ iter->syms = elf_getdata(scn, 0);
+ if (!iter->syms) {
+ pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n",
+ binary_path, elf_errmsg(-1));
+ return -EINVAL;
+ }
+ iter->nr_syms = iter->syms->d_size / sh.sh_entsize;
+ iter->elf = elf;
+ iter->st_type = st_type;
+ return 0;
+}
+
+static struct elf_sym *elf_sym_iter_next(struct elf_sym_iter *iter)
+{
+ struct elf_sym *ret = &iter->sym;
+ GElf_Sym *sym = &ret->sym;
+ const char *name = NULL;
+ Elf_Scn *sym_scn;
+ size_t idx;
+
+ for (idx = iter->next_sym_idx; idx < iter->nr_syms; idx++) {
+ if (!gelf_getsym(iter->syms, idx, sym))
+ continue;
+ if (GELF_ST_TYPE(sym->st_info) != iter->st_type)
+ continue;
+ name = elf_strptr(iter->elf, iter->strtabidx, sym->st_name);
+ if (!name)
+ continue;
+ sym_scn = elf_getscn(iter->elf, sym->st_shndx);
+ if (!sym_scn)
+ continue;
+ if (!gelf_getshdr(sym_scn, &ret->sh))
+ continue;
+
+ iter->next_sym_idx = idx + 1;
+ ret->name = name;
+ return ret;
+ }
+
+ return NULL;
+}
+
+
+/* Transform symbol's virtual address (absolute for binaries and relative
+ * for shared libs) into file offset, which is what kernel is expecting
+ * for uprobe/uretprobe attachment.
+ * See Documentation/trace/uprobetracer.rst for more details. This is done
+ * by looking up symbol's containing section's header and using iter's virtual
+ * address (sh_addr) and corresponding file offset (sh_offset) to transform
+ * sym.st_value (virtual address) into desired final file offset.
+ */
+static unsigned long elf_sym_offset(struct elf_sym *sym)
+{
+ return sym->sym.st_value - sym->sh.sh_addr + sym->sh.sh_offset;
+}
+
/* Find offset of function name in the provided ELF object. "binary_path" is
* the path to the ELF binary represented by "elf", and only used for error
* reporting matters. "name" matches symbol name or name@@LIB for library
@@ -91,67 +189,38 @@ long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
* reported as a warning/error.
*/
for (i = 0; i < ARRAY_SIZE(sh_types); i++) {
- size_t nr_syms, strtabidx, idx;
- Elf_Data *symbols = NULL;
- Elf_Scn *scn = NULL;
+ struct elf_sym_iter iter;
+ struct elf_sym *sym;
int last_bind = -1;
- const char *sname;
- GElf_Shdr sh;
+ int cur_bind;
- scn = elf_find_next_scn_by_type(elf, sh_types[i], NULL);
- if (!scn) {
- pr_debug("elf: failed to find symbol table ELF sections in '%s'\n",
- binary_path);
+ ret = elf_sym_iter_new(&iter, elf, binary_path, sh_types[i], STT_FUNC);
+ if (ret == -ENOENT)
continue;
- }
- if (!gelf_getshdr(scn, &sh))
- continue;
- strtabidx = sh.sh_link;
- symbols = elf_getdata(scn, 0);
- if (!symbols) {
- pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n",
- binary_path, elf_errmsg(-1));
- ret = -LIBBPF_ERRNO__FORMAT;
+ if (ret)
goto out;
- }
- nr_syms = symbols->d_size / sh.sh_entsize;
-
- for (idx = 0; idx < nr_syms; idx++) {
- int curr_bind;
- GElf_Sym sym;
- Elf_Scn *sym_scn;
- GElf_Shdr sym_sh;
-
- if (!gelf_getsym(symbols, idx, &sym))
- continue;
-
- if (GELF_ST_TYPE(sym.st_info) != STT_FUNC)
- continue;
-
- sname = elf_strptr(elf, strtabidx, sym.st_name);
- if (!sname)
- continue;
-
- curr_bind = GELF_ST_BIND(sym.st_info);
+ while ((sym = elf_sym_iter_next(&iter))) {
/* User can specify func, func@@LIB or func@@LIB_VERSION. */
- if (strncmp(sname, name, name_len) != 0)
+ if (strncmp(sym->name, name, name_len) != 0)
continue;
/* ...but we don't want a search for "foo" to match 'foo2" also, so any
* additional characters in sname should be of the form "@@LIB".
*/
- if (!is_name_qualified && sname[name_len] != '\0' && sname[name_len] != '@')
+ if (!is_name_qualified && sym->name[name_len] != '\0' && sym->name[name_len] != '@')
continue;
- if (ret >= 0) {
+ cur_bind = GELF_ST_BIND(sym->sym.st_info);
+
+ if (ret > 0) {
/* handle multiple matches */
- if (last_bind != STB_WEAK && curr_bind != STB_WEAK) {
+ if (last_bind != STB_WEAK && cur_bind != STB_WEAK) {
/* Only accept one non-weak bind. */
pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n",
- sname, name, binary_path);
+ sym->name, name, binary_path);
ret = -LIBBPF_ERRNO__FORMAT;
goto out;
- } else if (curr_bind == STB_WEAK) {
+ } else if (cur_bind == STB_WEAK) {
/* already have a non-weak bind, and
* this is a weak bind, so ignore.
*/
@@ -159,26 +228,8 @@ long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
}
}
- /* Transform symbol's virtual address (absolute for
- * binaries and relative for shared libs) into file
- * offset, which is what kernel is expecting for
- * uprobe/uretprobe attachment.
- * See Documentation/trace/uprobetracer.rst for more
- * details.
- * This is done by looking up symbol's containing
- * section's header and using it's virtual address
- * (sh_addr) and corresponding file offset (sh_offset)
- * to transform sym.st_value (virtual address) into
- * desired final file offset.
- */
- sym_scn = elf_getscn(elf, sym.st_shndx);
- if (!sym_scn)
- continue;
- if (!gelf_getshdr(sym_scn, &sym_sh))
- continue;
-
- ret = sym.st_value - sym_sh.sh_addr + sym_sh.sh_offset;
- last_bind = curr_bind;
+ ret = elf_sym_offset(sym);
+ last_bind = cur_bind;
}
if (ret > 0)
break;
--
2.41.0
next prev parent reply other threads:[~2023-07-20 11:37 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-20 11:35 [PATCHv4 bpf-next 00/28] bpf: Add multi uprobe link Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 01/28] bpf: Switch BPF_F_KPROBE_MULTI_RETURN macro to enum Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 02/28] bpf: Add attach_type checks under bpf_prog_attach_check_attach_type Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 03/28] bpf: Add multi uprobe link Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 04/28] bpf: Add cookies support for uprobe_multi link Jiri Olsa
2023-07-21 2:18 ` Yafang Shao
2023-07-21 7:39 ` Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 05/28] bpf: Add pid filter " Jiri Olsa
2023-07-21 2:55 ` Yafang Shao
2023-07-21 8:31 ` Oleg Nesterov
2023-07-21 8:54 ` Oleg Nesterov
2023-07-21 9:05 ` Yafang Shao
2023-07-21 10:41 ` Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 06/28] bpf: Add bpf_get_func_ip helper support for uprobe link Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 07/28] libbpf: Add uprobe_multi attach type and link names Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 08/28] libbpf: Move elf_find_func_offset* functions to elf object Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 09/28] libbpf: Add elf_open/elf_close functions Jiri Olsa
2023-07-20 11:35 ` Jiri Olsa [this message]
2023-07-20 11:35 ` [PATCHv4 bpf-next 11/28] libbpf: Add elf_resolve_syms_offsets function Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 12/28] libbpf: Add elf_resolve_pattern_offsets function Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 13/28] libbpf: Add bpf_link_create support for multi uprobes Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 14/28] libbpf: Add bpf_program__attach_uprobe_multi function Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 15/28] libbpf: Add support for u[ret]probe.multi[.s] program sections Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 16/28] libbpf: Add uprobe multi link detection Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 17/28] libbpf: Add uprobe multi link support to bpf_program__attach_usdt Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 18/28] selftests/bpf: Move get_time_ns to testing_helpers.h Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 19/28] selftests/bpf: Add uprobe_multi skel test Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 20/28] selftests/bpf: Add uprobe_multi api test Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 21/28] selftests/bpf: Add uprobe_multi link test Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 22/28] selftests/bpf: Add uprobe_multi test program Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 23/28] selftests/bpf: Add uprobe_multi bench test Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 24/28] selftests/bpf: Add uprobe_multi usdt test code Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 25/28] selftests/bpf: Add uprobe_multi usdt bench test Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 26/28] selftests/bpf: Add uprobe_multi cookie test Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 27/28] selftests/bpf: Add uprobe_multi pid filter tests Jiri Olsa
2023-07-20 11:35 ` [PATCHv4 bpf-next 28/28] selftests/bpf: Add extra link to uprobe_multi tests Jiri Olsa
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230720113550.369257-11-jolsa@kernel.org \
--to=jolsa@kernel.org \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=haoluo@google.com \
--cc=john.fastabend@gmail.com \
--cc=kafai@fb.com \
--cc=kpsingh@chromium.org \
--cc=sdf@google.com \
--cc=songliubraving@fb.com \
--cc=yhs@fb.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).