All of lore.kernel.org
 help / color / mirror / Atom feed
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: [PATCHv2 bpf-next 06/24] libbpf: Add elf symbol iterator
Date: Tue, 20 Jun 2023 10:35:32 +0200	[thread overview]
Message-ID: <20230620083550.690426-7-jolsa@kernel.org> (raw)
In-Reply-To: <20230620083550.690426-1-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_symbol_iter iter;
  struct elf_symbol *sym;

  if (elf_symbol_iter_new(&iter, elf, binary_path, SHT_DYNSYM))
        goto error;

  while ((sym = elf_symbol_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_symbol_iter_next function
is placed inside the struct elf_symbol_iter, so no extra allocation or
argument is needed.

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/lib/bpf/libbpf.c | 179 ++++++++++++++++++++++++++---------------
 1 file changed, 114 insertions(+), 65 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index af52188daa80..cdac368c7ce1 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -10824,6 +10824,109 @@ static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn)
 	return NULL;
 }
 
+struct elf_symbol {
+	const char *name;
+	unsigned long offset;
+	int bind;
+};
+
+struct elf_symbol_iter {
+	Elf *elf;
+	Elf_Data *symbols;
+	size_t nr_syms;
+	size_t strtabidx;
+	size_t idx;
+	struct elf_symbol sym;
+};
+
+static int elf_symbol_iter_new(struct elf_symbol_iter *iter,
+			       Elf *elf, const char *binary_path,
+			       int sh_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 -LIBBPF_ERRNO__FORMAT;
+	}
+
+	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 -EINVAL;
+	}
+
+	if (!gelf_getshdr(scn, &sh))
+		return -EINVAL;
+
+	iter->strtabidx = sh.sh_link;
+	iter->symbols = elf_getdata(scn, 0);
+	if (!iter->symbols) {
+		pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n",
+			binary_path, elf_errmsg(-1));
+		return -LIBBPF_ERRNO__FORMAT;
+	}
+	iter->nr_syms = iter->symbols->d_size / sh.sh_entsize;
+	iter->elf = elf;
+	return 0;
+}
+
+static struct elf_symbol *elf_symbol_iter_next(struct elf_symbol_iter *iter)
+{
+	struct elf_symbol *ret = &iter->sym;
+	unsigned long offset = 0;
+	const char *name = NULL;
+	GElf_Shdr sym_sh;
+	Elf_Scn *sym_scn;
+	GElf_Sym sym;
+	size_t idx;
+
+	for (idx = iter->idx; idx < iter->nr_syms; idx++) {
+		if (!gelf_getsym(iter->symbols, idx, &sym))
+			continue;
+		if (GELF_ST_TYPE(sym.st_info) != STT_FUNC)
+			continue;
+		name = elf_strptr(iter->elf, iter->strtabidx, sym.st_name);
+		if (!name)
+			continue;
+
+		/* 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.
+		 */
+		sym_scn = elf_getscn(iter->elf, sym.st_shndx);
+		if (!sym_scn)
+			continue;
+		if (!gelf_getshdr(sym_scn, &sym_sh))
+			continue;
+
+		offset = sym.st_value - sym_sh.sh_addr + sym_sh.sh_offset;
+		break;
+	}
+
+	/* we reached the last symbol */
+	if (idx == iter->nr_syms)
+		return NULL;
+	iter->idx = idx + 1;
+	ret->name = name;
+	ret->bind = GELF_ST_BIND(sym.st_info);
+	ret->offset = offset;
+	return ret;
+}
+
 /* 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
@@ -10855,94 +10958,40 @@ static long elf_find_func_offset(Elf *elf, const char *binary_path, const char *
 	 * 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_symbol_iter iter;
+		struct elf_symbol *sym;
 		int last_bind = -1;
-		const char *sname;
-		GElf_Shdr sh;
 
-		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);
+		if (elf_symbol_iter_new(&iter, elf, binary_path, sh_types[i]))
 			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;
-			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_symbol_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) {
 				/* handle multiple matches */
-				if (last_bind != STB_WEAK && curr_bind != STB_WEAK) {
+				if (last_bind != STB_WEAK && sym->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 (sym->bind == STB_WEAK) {
 					/* already have a non-weak bind, and
 					 * this is a weak bind, so ignore.
 					 */
 					continue;
 				}
 			}
-
-			/* 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;
+			last_bind = sym->bind;
+			ret = sym->offset;
 		}
 		if (ret > 0)
 			break;
-- 
2.41.0


  parent reply	other threads:[~2023-06-20  8:36 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-06-20  8:35 [PATCHv2 bpf-next 00/24] bpf: Add multi uprobe link Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 01/24] " Jiri Olsa
2023-06-20 17:11   ` Alexei Starovoitov
2023-06-21  8:32     ` Jiri Olsa
2023-06-23  0:18   ` Andrii Nakryiko
2023-06-23  8:19     ` Jiri Olsa
2023-06-23 16:24       ` Andrii Nakryiko
2023-06-23 16:39         ` Alexei Starovoitov
2023-06-23 17:11           ` Andrii Nakryiko
2023-06-23 17:20             ` Alexei Starovoitov
2023-06-25  1:19               ` Jiri Olsa
2023-06-25  1:18         ` Jiri Olsa
2023-06-26 18:27           ` Andrii Nakryiko
2023-06-26 19:23             ` Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 02/24] bpf: Add cookies support for uprobe_multi link Jiri Olsa
2023-06-23  0:18   ` Andrii Nakryiko
2023-06-23  8:01     ` Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 03/24] bpf: Add pid filter " Jiri Olsa
2023-06-20 12:40   ` Oleg Nesterov
2023-06-20  8:35 ` [PATCHv2 bpf-next 04/24] bpf: Add bpf_get_func_ip helper support for uprobe link Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 05/24] libbpf: Add uprobe_multi attach type and link names Jiri Olsa
2023-06-20  8:35 ` Jiri Olsa [this message]
2023-06-23  0:31   ` [PATCHv2 bpf-next 06/24] libbpf: Add elf symbol iterator Andrii Nakryiko
2023-06-23  8:19     ` Jiri Olsa
2023-06-23 16:27       ` Andrii Nakryiko
2023-06-23 16:29       ` Andrii Nakryiko
2023-06-20  8:35 ` [PATCHv2 bpf-next 07/24] libbpf: Add open_elf/close_elf functions Jiri Olsa
2023-06-23  0:33   ` Andrii Nakryiko
2023-06-23  8:21     ` Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 08/24] libbpf: Add elf_find_multi_func_offset function Jiri Olsa
2023-06-23 20:39   ` Andrii Nakryiko
2023-06-25  1:19     ` Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 09/24] libbpf: Add elf_find_pattern_func_offset function Jiri Olsa
2023-06-23 20:39   ` Andrii Nakryiko
2023-06-25  1:19     ` Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 10/24] libbpf: Add bpf_link_create support for multi uprobes Jiri Olsa
2023-06-23 20:40   ` Andrii Nakryiko
2023-06-20  8:35 ` [PATCHv2 bpf-next 11/24] libbpf: Add bpf_program__attach_uprobe_multi_opts function Jiri Olsa
2023-06-23 20:40   ` Andrii Nakryiko
2023-06-25  1:19     ` Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 12/24] libbpf: Add support for u[ret]probe.multi[.s] program sections Jiri Olsa
2023-06-23 20:40   ` Andrii Nakryiko
2023-06-25  1:20     ` Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 13/24] libbpf: Add uprobe multi link detection Jiri Olsa
2023-06-23 20:40   ` Andrii Nakryiko
2023-06-25  1:18     ` Jiri Olsa
2023-06-26 18:21       ` Andrii Nakryiko
2023-06-26 19:22         ` Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 14/24] libbpf: Add uprobe multi link support to bpf_program__attach_usdt Jiri Olsa
2023-06-23 20:40   ` Andrii Nakryiko
2023-06-25  1:18     ` Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 15/24] selftests/bpf: Add uprobe_multi skel test Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 16/24] selftests/bpf: Add uprobe_multi api test Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 17/24] selftests/bpf: Add uprobe_multi link test Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 18/24] selftests/bpf: Add uprobe_multi test program Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 19/24] selftests/bpf: Add uprobe_multi bench test Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 20/24] selftests/bpf: Add usdt_multi test program Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 21/24] selftests/bpf: Add usdt_multi bench test Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 22/24] selftests/bpf: Add uprobe_multi cookie test Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 23/24] selftests/bpf: Add uprobe_multi pid filter tests Jiri Olsa
2023-06-20  8:35 ` [PATCHv2 bpf-next 24/24] 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=20230620083550.690426-7-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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.