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>,
	Yafang Shao <laoar.shao@gmail.com>
Subject: [PATCHv7 bpf-next 08/28] libbpf: Move elf_find_func_offset* functions to elf object
Date: Wed,  9 Aug 2023 10:34:20 +0200	[thread overview]
Message-ID: <20230809083440.3209381-9-jolsa@kernel.org> (raw)
In-Reply-To: <20230809083440.3209381-1-jolsa@kernel.org>

Adding new elf object that will contain elf related functions.
There's no functional change.

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/lib/bpf/Build             |   2 +-
 tools/lib/bpf/elf.c             | 197 ++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.c          | 185 ------------------------------
 tools/lib/bpf/libbpf_internal.h |   4 +
 4 files changed, 202 insertions(+), 186 deletions(-)
 create mode 100644 tools/lib/bpf/elf.c

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index b8b0a6369363..2d0c282c8588 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1,4 +1,4 @@
 libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
 	    netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \
 	    btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \
-	    usdt.o zip.o
+	    usdt.o zip.o elf.o
diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
new file mode 100644
index 000000000000..735ef10093ac
--- /dev/null
+++ b/tools/lib/bpf/elf.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+#include <libelf.h>
+#include <gelf.h>
+#include <fcntl.h>
+#include <linux/kernel.h>
+
+#include "libbpf_internal.h"
+#include "str_error.h"
+
+#define STRERR_BUFSIZE  128
+
+/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */
+static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn)
+{
+	while ((scn = elf_nextscn(elf, scn)) != NULL) {
+		GElf_Shdr sh;
+
+		if (!gelf_getshdr(scn, &sh))
+			continue;
+		if (sh.sh_type == sh_type)
+			return scn;
+	}
+	return NULL;
+}
+
+/* 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
+ * functions.
+ */
+long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
+{
+	int i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
+	bool is_shared_lib, is_name_qualified;
+	long ret = -ENOENT;
+	size_t name_len;
+	GElf_Ehdr ehdr;
+
+	if (!gelf_getehdr(elf, &ehdr)) {
+		pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1));
+		ret = -LIBBPF_ERRNO__FORMAT;
+		goto out;
+	}
+	/* for shared lib case, we do not need to calculate relative offset */
+	is_shared_lib = ehdr.e_type == ET_DYN;
+
+	name_len = strlen(name);
+	/* Does name specify "@@LIB"? */
+	is_name_qualified = strstr(name, "@@") != NULL;
+
+	/* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if
+	 * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically
+	 * linked binary may not have SHT_DYMSYM, so absence of a section should not be
+	 * 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;
+		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);
+			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);
+
+			/* User can specify func, func@@LIB or func@@LIB_VERSION. */
+			if (strncmp(sname, 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] != '@')
+				continue;
+
+			if (ret >= 0) {
+				/* handle multiple matches */
+				if (last_bind != STB_WEAK && curr_bind != STB_WEAK) {
+					/* Only accept one non-weak bind. */
+					pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n",
+						sname, name, binary_path);
+					ret = -LIBBPF_ERRNO__FORMAT;
+					goto out;
+				} else if (curr_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;
+		}
+		if (ret > 0)
+			break;
+	}
+
+	if (ret > 0) {
+		pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path,
+			 ret);
+	} else {
+		if (ret == 0) {
+			pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path,
+				is_shared_lib ? "should not be 0 in a shared library" :
+						"try using shared library path instead");
+			ret = -ENOENT;
+		} else {
+			pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path);
+		}
+	}
+out:
+	return ret;
+}
+
+/* Find offset of function name in ELF object specified by path. "name" matches
+ * symbol name or name@@LIB for library functions.
+ */
+long elf_find_func_offset_from_file(const char *binary_path, const char *name)
+{
+	char errmsg[STRERR_BUFSIZE];
+	long ret = -ENOENT;
+	Elf *elf;
+	int fd;
+
+	fd = open(binary_path, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		ret = -errno;
+		pr_warn("failed to open %s: %s\n", binary_path,
+			libbpf_strerror_r(ret, errmsg, sizeof(errmsg)));
+		return ret;
+	}
+	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+	if (!elf) {
+		pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1));
+		close(fd);
+		return -LIBBPF_ERRNO__FORMAT;
+	}
+
+	ret = elf_find_func_offset(elf, binary_path, name);
+	elf_end(elf);
+	close(fd);
+	return ret;
+}
+
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2fc98d857142..1bdda3f8c865 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -10986,191 +10986,6 @@ static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe,
 	return err;
 }
 
-/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */
-static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn)
-{
-	while ((scn = elf_nextscn(elf, scn)) != NULL) {
-		GElf_Shdr sh;
-
-		if (!gelf_getshdr(scn, &sh))
-			continue;
-		if (sh.sh_type == sh_type)
-			return scn;
-	}
-	return NULL;
-}
-
-/* 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
- * functions.
- */
-static long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
-{
-	int i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB };
-	bool is_shared_lib, is_name_qualified;
-	long ret = -ENOENT;
-	size_t name_len;
-	GElf_Ehdr ehdr;
-
-	if (!gelf_getehdr(elf, &ehdr)) {
-		pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1));
-		ret = -LIBBPF_ERRNO__FORMAT;
-		goto out;
-	}
-	/* for shared lib case, we do not need to calculate relative offset */
-	is_shared_lib = ehdr.e_type == ET_DYN;
-
-	name_len = strlen(name);
-	/* Does name specify "@@LIB"? */
-	is_name_qualified = strstr(name, "@@") != NULL;
-
-	/* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if
-	 * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically
-	 * linked binary may not have SHT_DYMSYM, so absence of a section should not be
-	 * 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;
-		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);
-			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);
-
-			/* User can specify func, func@@LIB or func@@LIB_VERSION. */
-			if (strncmp(sname, 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] != '@')
-				continue;
-
-			if (ret >= 0) {
-				/* handle multiple matches */
-				if (last_bind != STB_WEAK && curr_bind != STB_WEAK) {
-					/* Only accept one non-weak bind. */
-					pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n",
-						sname, name, binary_path);
-					ret = -LIBBPF_ERRNO__FORMAT;
-					goto out;
-				} else if (curr_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;
-		}
-		if (ret > 0)
-			break;
-	}
-
-	if (ret > 0) {
-		pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path,
-			 ret);
-	} else {
-		if (ret == 0) {
-			pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path,
-				is_shared_lib ? "should not be 0 in a shared library" :
-						"try using shared library path instead");
-			ret = -ENOENT;
-		} else {
-			pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path);
-		}
-	}
-out:
-	return ret;
-}
-
-/* Find offset of function name in ELF object specified by path. "name" matches
- * symbol name or name@@LIB for library functions.
- */
-static long elf_find_func_offset_from_file(const char *binary_path, const char *name)
-{
-	char errmsg[STRERR_BUFSIZE];
-	long ret = -ENOENT;
-	Elf *elf;
-	int fd;
-
-	fd = open(binary_path, O_RDONLY | O_CLOEXEC);
-	if (fd < 0) {
-		ret = -errno;
-		pr_warn("failed to open %s: %s\n", binary_path,
-			libbpf_strerror_r(ret, errmsg, sizeof(errmsg)));
-		return ret;
-	}
-	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
-	if (!elf) {
-		pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1));
-		close(fd);
-		return -LIBBPF_ERRNO__FORMAT;
-	}
-
-	ret = elf_find_func_offset(elf, binary_path, name);
-	elf_end(elf);
-	close(fd);
-	return ret;
-}
-
 /* Find offset of function name in archive specified by path. Currently
  * supported are .zip files that do not compress their contents, as used on
  * Android in the form of APKs, for example. "file_name" is the name of the ELF
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index e4d05662a96c..44eb63541507 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -15,6 +15,7 @@
 #include <linux/err.h>
 #include <fcntl.h>
 #include <unistd.h>
+#include <libelf.h>
 #include "relo_core.h"
 
 /* make sure libbpf doesn't use kernel-only integer typedefs */
@@ -577,4 +578,7 @@ static inline bool is_pow_of_2(size_t x)
 #define PROG_LOAD_ATTEMPTS 5
 int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts);
 
+long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name);
+long elf_find_func_offset_from_file(const char *binary_path, const char *name);
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */
-- 
2.41.0


  parent reply	other threads:[~2023-08-09  8:36 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-08-09  8:34 [PATCHv7 bpf-next 00/28] bpf: Add multi uprobe link Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 01/28] bpf: Switch BPF_F_KPROBE_MULTI_RETURN macro to enum Jiri Olsa
2023-08-09 16:06   ` Yonghong Song
2023-08-09  8:34 ` [PATCHv7 bpf-next 02/28] bpf: Add attach_type checks under bpf_prog_attach_check_attach_type Jiri Olsa
2023-08-09 16:11   ` Yonghong Song
2023-08-09  8:34 ` [PATCHv7 bpf-next 03/28] bpf: Add multi uprobe link Jiri Olsa
2023-08-09 16:29   ` Yonghong Song
2023-08-09  8:34 ` [PATCHv7 bpf-next 04/28] bpf: Add cookies support for uprobe_multi link Jiri Olsa
2023-08-09 16:39   ` Yonghong Song
2023-08-11 13:19     ` Jiri Olsa
2023-08-11 16:45       ` Yonghong Song
2023-08-09  8:34 ` [PATCHv7 bpf-next 05/28] bpf: Add pid filter " Jiri Olsa
2023-08-09 16:45   ` Yonghong Song
2023-08-09  8:34 ` [PATCHv7 bpf-next 06/28] bpf: Add bpf_get_func_ip helper support for uprobe link Jiri Olsa
2023-08-09 16:48   ` Yonghong Song
2023-08-09  8:34 ` [PATCHv7 bpf-next 07/28] libbpf: Add uprobe_multi attach type and link names Jiri Olsa
2023-08-09  8:34 ` Jiri Olsa [this message]
2023-08-09  8:34 ` [PATCHv7 bpf-next 09/28] libbpf: Add elf_open/elf_close functions Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 10/28] libbpf: Add elf symbol iterator Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 11/28] libbpf: Add elf_resolve_syms_offsets function Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 12/28] libbpf: Add elf_resolve_pattern_offsets function Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 13/28] libbpf: Add bpf_link_create support for multi uprobes Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 14/28] libbpf: Add bpf_program__attach_uprobe_multi function Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 15/28] libbpf: Add support for u[ret]probe.multi[.s] program sections Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 16/28] libbpf: Add uprobe multi link detection Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 17/28] libbpf: Add uprobe multi link support to bpf_program__attach_usdt Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 18/28] selftests/bpf: Move get_time_ns to testing_helpers.h Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 19/28] selftests/bpf: Add uprobe_multi skel test Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 20/28] selftests/bpf: Add uprobe_multi api test Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 21/28] selftests/bpf: Add uprobe_multi link test Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 22/28] selftests/bpf: Add uprobe_multi test program Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 23/28] selftests/bpf: Add uprobe_multi bench test Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 24/28] selftests/bpf: Add uprobe_multi usdt test code Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 25/28] selftests/bpf: Add uprobe_multi usdt bench test Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 26/28] selftests/bpf: Add uprobe_multi cookie test Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 27/28] selftests/bpf: Add uprobe_multi pid filter tests Jiri Olsa
2023-08-09  8:34 ` [PATCHv7 bpf-next 28/28] selftests/bpf: Add extra link to uprobe_multi tests Jiri Olsa
2023-08-21 23:00 ` [PATCHv7 bpf-next 00/28] bpf: Add multi uprobe link patchwork-bot+netdevbpf

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=20230809083440.3209381-9-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=laoar.shao@gmail.com \
    --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.