Merge branch 'libbpf: Support symbol versioning for uprobe'

Hengqi Chen says:

====================
Dynamic symbols in shared library may have the same name, for example:

    $ nm -D /lib/x86_64-linux-gnu/libc.so.6 | grep rwlock_wrlock
    000000000009b1a0 T __pthread_rwlock_wrlock@GLIBC_2.2.5
    000000000009b1a0 T pthread_rwlock_wrlock@@GLIBC_2.34
    000000000009b1a0 T pthread_rwlock_wrlock@GLIBC_2.2.5

    $ readelf -W --dyn-syms /lib/x86_64-linux-gnu/libc.so.6 | grep rwlock_wrlock
      706: 000000000009b1a0   878 FUNC    GLOBAL DEFAULT   15 __pthread_rwlock_wrlock@GLIBC_2.2.5
      2568: 000000000009b1a0   878 FUNC    GLOBAL DEFAULT   15 pthread_rwlock_wrlock@@GLIBC_2.34
      2571: 000000000009b1a0   878 FUNC    GLOBAL DEFAULT   15 pthread_rwlock_wrlock@GLIBC_2.2.5

There are two pthread_rwlock_wrlock symbols in libc.so .dynsym section.
The one with @@ is the default version, the other is hidden.
Note that the version info is stored in .gnu.version and .gnu.version_d
sections of libc and the two symbols are at the _same_ offset.

Currently, specify `pthread_rwlock_wrlock`, `pthread_rwlock_wrlock@@GLIBC_2.34`
or `pthread_rwlock_wrlock@GLIBC_2.2.5` in bpf_uprobe_opts::func_name won't work.
Because there are two `pthread_rwlock_wrlock` in .dynsym sections without the
version suffix and both are global bind.

We could solve this by introducing symbol versioning ([0]). So that users can
specify func, func@LIB_VERSION or func@@LIB_VERSION to attach a uprobe.

This patchset resolves symbol conflicts and add symbol versioning for uprobe.
  - Patch 1 resolves symbol conflicts at the same offset
  - Patch 2 adds symbol versioning for dynsym
  - Patch 3 adds selftests for the above changes

Changes from v3:
  - Address comments from Andrii

Changes from v2:
  - Add uretprobe selfttest (Alan)
  - Check symbol exact match (Alan)
  - Fix typo (Jiri)

Changes from v1:
  - Address comments from Alan and Jiri
  - Add selftests (Someone reminds me that there is an attempt at [1]
    and part of the selftest code from Andrii is taken from there)

  [0]: https://refspecs.linuxfoundation.org/LSB_5.0.0/LSB-Core-generic/LSB-Core-generic/symversion.html
  [1]: https://lore.kernel.org/lkml/CAEf4BzZTrjjyyOm3ak9JsssPSh6T_ZmGd677a2rt5e5rBLUrpQ@mail.gmail.com/
====================

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

tools/lib/bpf/elf.c

@@ -1,5 +1,8 @@
 // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
 #include <libelf.h>
 #include <gelf.h>
 #include <fcntl.h>
@@ -10,6 +13,17 @@
 
 #define STRERR_BUFSIZE  128
 
+/* A SHT_GNU_versym section holds 16-bit words. This bit is set if
+ * the symbol is hidden and can only be seen when referenced using an
+ * explicit version number. This is a GNU extension.
+ */
+#define VERSYM_HIDDEN	0x8000
+
+/* This is the mask for the rest of the data in a word read from a
+ * SHT_GNU_versym section.
+ */
+#define VERSYM_VERSION	0x7fff
+
 int elf_open(const char *binary_path, struct elf_fd *elf_fd)
 {
 	char errmsg[STRERR_BUFSIZE];
@@ -64,13 +78,18 @@ struct elf_sym {
 	const char *name;
 	GElf_Sym sym;
 	GElf_Shdr sh;
+	int ver;
+	bool hidden;
 };
 
 struct elf_sym_iter {
 	Elf *elf;
 	Elf_Data *syms;
+	Elf_Data *versyms;
+	Elf_Data *verdefs;
 	size_t nr_syms;
 	size_t strtabidx;
+	size_t verdef_strtabidx;
 	size_t next_sym_idx;
 	struct elf_sym sym;
 	int st_type;
@@ -111,6 +130,26 @@ static int elf_sym_iter_new(struct elf_sym_iter *iter,
 	iter->nr_syms = iter->syms->d_size / sh.sh_entsize;
 	iter->elf = elf;
 	iter->st_type = st_type;
+
+	/* Version symbol table is meaningful to dynsym only */
+	if (sh_type != SHT_DYNSYM)
+		return 0;
+
+	scn = elf_find_next_scn_by_type(elf, SHT_GNU_versym, NULL);
+	if (!scn)
+		return 0;
+	iter->versyms = elf_getdata(scn, 0);
+
+	scn = elf_find_next_scn_by_type(elf, SHT_GNU_verdef, NULL);
+	if (!scn) {
+		pr_debug("elf: failed to find verdef ELF sections in '%s'\n", binary_path);
+		return -ENOENT;
+	}
+	if (!gelf_getshdr(scn, &sh))
+		return -EINVAL;
+	iter->verdef_strtabidx = sh.sh_link;
+	iter->verdefs = elf_getdata(scn, 0);
+
 	return 0;
 }
 
@@ -119,6 +158,7 @@ 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;
+	GElf_Versym versym;
 	Elf_Scn *sym_scn;
 	size_t idx;
 
@@ -138,12 +178,80 @@ static struct elf_sym *elf_sym_iter_next(struct elf_sym_iter *iter)
 
 		iter->next_sym_idx = idx + 1;
 		ret->name = name;
+		ret->ver = 0;
+		ret->hidden = false;
+
+		if (iter->versyms) {
+			if (!gelf_getversym(iter->versyms, idx, &versym))
+				continue;
+			ret->ver = versym & VERSYM_VERSION;
+			ret->hidden = versym & VERSYM_HIDDEN;
+		}
 		return ret;
 	}
 
 	return NULL;
 }
 
+static const char *elf_get_vername(struct elf_sym_iter *iter, int ver)
+{
+	GElf_Verdaux verdaux;
+	GElf_Verdef verdef;
+	int offset;
+
+	offset = 0;
+	while (gelf_getverdef(iter->verdefs, offset, &verdef)) {
+		if (verdef.vd_ndx != ver) {
+			if (!verdef.vd_next)
+				break;
+
+			offset += verdef.vd_next;
+			continue;
+		}
+
+		if (!gelf_getverdaux(iter->verdefs, offset + verdef.vd_aux, &verdaux))
+			break;
+
+		return elf_strptr(iter->elf, iter->verdef_strtabidx, verdaux.vda_name);
+
+	}
+	return NULL;
+}
+
+static bool symbol_match(struct elf_sym_iter *iter, int sh_type, struct elf_sym *sym,
+			 const char *name, size_t name_len, const char *lib_ver)
+{
+	const char *ver_name;
+
+	/* Symbols are in forms of func, func@LIB_VER or func@@LIB_VER
+	 * make sure the func part matches the user specified name
+	 */
+	if (strncmp(sym->name, name, name_len) != 0)
+		return false;
+
+	/* ...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 (sym->name[name_len] != '\0' && sym->name[name_len] != '@')
+		return false;
+
+	/* If user does not specify symbol version, then we got a match */
+	if (!lib_ver)
+		return true;
+
+	/* If user specifies symbol version, for dynamic symbols,
+	 * get version name from ELF verdef section for comparison.
+	 */
+	if (sh_type == SHT_DYNSYM) {
+		ver_name = elf_get_vername(iter, sym->ver);
+		if (!ver_name)
+			return false;
+		return strcmp(ver_name, lib_ver) == 0;
+	}
+
+	/* For normal symbols, it is already in form of func@LIB_VER */
+	return strcmp(sym->name, name) == 0;
+}
 
 /* Transform symbol's virtual address (absolute for binaries and relative
  * for shared libs) into file offset, which is what kernel is expecting
@@ -166,7 +274,8 @@ static unsigned long elf_sym_offset(struct elf_sym *sym)
 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;
+	const char *at_symbol, *lib_ver;
+	bool is_shared_lib;
 	long ret = -ENOENT;
 	size_t name_len;
 	GElf_Ehdr ehdr;
@@ -179,9 +288,18 @@ long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
 	/* 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;
+	/* Does name specify "@@LIB_VER" or "@LIB_VER" ? */
+	at_symbol = strchr(name, '@');
+	if (at_symbol) {
+		name_len = at_symbol - name;
+		/* skip second @ if it's @@LIB_VER case */
+		if (at_symbol[1] == '@')
+			at_symbol++;
+		lib_ver = at_symbol + 1;
+	} else {
+		name_len = strlen(name);
+		lib_ver = 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
@@ -201,20 +319,17 @@ long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
 			goto out;
 
 		while ((sym = elf_sym_iter_next(&iter))) {
-			/* User can specify func, func@@LIB or func@@LIB_VERSION. */
-			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 && sym->name[name_len] != '\0' && sym->name[name_len] != '@')
+			if (!symbol_match(&iter, sh_types[i], sym, name, name_len, lib_ver))
 				continue;
 
 			cur_bind = GELF_ST_BIND(sym->sym.st_info);
 
 			if (ret > 0) {
 				/* handle multiple matches */
-				if (last_bind != STB_WEAK && cur_bind != STB_WEAK) {
+				if (elf_sym_offset(sym) == ret) {
+					/* same offset, no problem */
+					continue;
+				} else 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",
 						sym->name, name, binary_path);

tools/lib/bpf/libbpf.c

@@ -11630,7 +11630,7 @@ static int attach_uprobe(const struct bpf_program *prog, long cookie, struct bpf
 
 	*link = NULL;
 
-	n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%m[a-zA-Z0-9_.]+%li",
+	n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%m[a-zA-Z0-9_.@]+%li",
 		   &probe_type, &binary_path, &func_name, &offset);
 	switch (n) {
 	case 1:

tools/testing/selftests/bpf/Makefile

@@ -196,11 +196,12 @@ endif
 
 # Filter out -static for liburandom_read.so and its dependent targets so that static builds
 # do not fail. Static builds leave urandom_read relying on system-wide shared libraries.
-$(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c
+$(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c liburandom_read.map
 	$(call msg,LIB,,$@)
 	$(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS))   \
-		     $^ $(filter-out -static,$(LDLIBS))	     \
+		     $(filter %.c,$^) $(filter-out -static,$(LDLIBS)) \
 		     -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \
+		     -Wl,--version-script=liburandom_read.map \
 		     -fPIC -shared -o $@
 
 $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_read.so

tools/testing/selftests/bpf/liburandom_read.map

@@ -0,0 +1,15 @@
+LIBURANDOM_READ_1.0.0 {
+	global:
+		urandlib_api;
+		urandlib_api_sameoffset;
+		urandlib_read_without_sema;
+		urandlib_read_with_sema;
+		urandlib_read_with_sema_semaphore;
+	local:
+		*;
+};
+
+LIBURANDOM_READ_2.0.0 {
+	global:
+		urandlib_api;
+} LIBURANDOM_READ_1.0.0;

tools/testing/selftests/bpf/prog_tests/uprobe.c

@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Hengqi Chen */
+
+#include <test_progs.h>
+#include "test_uprobe.skel.h"
+
+static FILE *urand_spawn(int *pid)
+{
+	FILE *f;
+
+	/* urandom_read's stdout is wired into f */
+	f = popen("./urandom_read 1 report-pid", "r");
+	if (!f)
+		return NULL;
+
+	if (fscanf(f, "%d", pid) != 1) {
+		pclose(f);
+		errno = EINVAL;
+		return NULL;
+	}
+
+	return f;
+}
+
+static int urand_trigger(FILE **urand_pipe)
+{
+	int exit_code;
+
+	/* pclose() waits for child process to exit and returns their exit code */
+	exit_code = pclose(*urand_pipe);
+	*urand_pipe = NULL;
+
+	return exit_code;
+}
+
+void test_uprobe(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	struct test_uprobe *skel;
+	FILE *urand_pipe = NULL;
+	int urand_pid = 0, err;
+
+	skel = test_uprobe__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	urand_pipe = urand_spawn(&urand_pid);
+	if (!ASSERT_OK_PTR(urand_pipe, "urand_spawn"))
+		goto cleanup;
+
+	skel->bss->my_pid = urand_pid;
+
+	/* Manual attach uprobe to urandlib_api
+	 * There are two `urandlib_api` symbols in .dynsym section:
+	 *   - urandlib_api@LIBURANDOM_READ_1.0.0
+	 *   - urandlib_api@@LIBURANDOM_READ_2.0.0
+	 * Both are global bind and would cause a conflict if user
+	 * specify the symbol name without a version suffix
+	 */
+	uprobe_opts.func_name = "urandlib_api";
+	skel->links.test4 = bpf_program__attach_uprobe_opts(skel->progs.test4,
+							    urand_pid,
+							    "./liburandom_read.so",
+							    0 /* offset */,
+							    &uprobe_opts);
+	if (!ASSERT_ERR_PTR(skel->links.test4, "urandlib_api_attach_conflict"))
+		goto cleanup;
+
+	uprobe_opts.func_name = "urandlib_api@LIBURANDOM_READ_1.0.0";
+	skel->links.test4 = bpf_program__attach_uprobe_opts(skel->progs.test4,
+							    urand_pid,
+							    "./liburandom_read.so",
+							    0 /* offset */,
+							    &uprobe_opts);
+	if (!ASSERT_OK_PTR(skel->links.test4, "urandlib_api_attach_ok"))
+		goto cleanup;
+
+	/* Auto attach 3 u[ret]probes to urandlib_api_sameoffset */
+	err = test_uprobe__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* trigger urandom_read */
+	ASSERT_OK(urand_trigger(&urand_pipe), "urand_exit_code");
+
+	ASSERT_EQ(skel->bss->test1_result, 1, "urandlib_api_sameoffset");
+	ASSERT_EQ(skel->bss->test2_result, 1, "urandlib_api_sameoffset@v1");
+	ASSERT_EQ(skel->bss->test3_result, 3, "urandlib_api_sameoffset@@v2");
+	ASSERT_EQ(skel->bss->test4_result, 1, "urandlib_api");
+
+cleanup:
+	if (urand_pipe)
+		pclose(urand_pipe);
+	test_uprobe__destroy(skel);
+}

tools/testing/selftests/bpf/progs/test_uprobe.c

@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Hengqi Chen */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+pid_t my_pid = 0;
+
+int test1_result = 0;
+int test2_result = 0;
+int test3_result = 0;
+int test4_result = 0;
+
+SEC("uprobe/./liburandom_read.so:urandlib_api_sameoffset")
+int BPF_UPROBE(test1)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	test1_result = 1;
+	return 0;
+}
+
+SEC("uprobe/./liburandom_read.so:urandlib_api_sameoffset@LIBURANDOM_READ_1.0.0")
+int BPF_UPROBE(test2)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	test2_result = 1;
+	return 0;
+}
+
+SEC("uretprobe/./liburandom_read.so:urandlib_api_sameoffset@@LIBURANDOM_READ_2.0.0")
+int BPF_URETPROBE(test3, int ret)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	test3_result = ret;
+	return 0;
+}
+
+SEC("uprobe")
+int BPF_UPROBE(test4)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	test4_result = 1;
+	return 0;
+}

tools/testing/selftests/bpf/urandom_read.c

@@ -11,6 +11,9 @@
 #define _SDT_HAS_SEMAPHORES 1
 #include "sdt.h"
 
+#define SHARED 1
+#include "bpf/libbpf_internal.h"
+
 #define SEC(name) __attribute__((section(name), used))
 
 #define BUF_SIZE 256
@@ -21,10 +24,14 @@ void urand_read_without_sema(int iter_num, int iter_cnt, int read_sz);
 void urandlib_read_with_sema(int iter_num, int iter_cnt, int read_sz);
 void urandlib_read_without_sema(int iter_num, int iter_cnt, int read_sz);
 
+int urandlib_api(void);
+COMPAT_VERSION(urandlib_api_old, urandlib_api, LIBURANDOM_READ_1.0.0)
+int urandlib_api_old(void);
+int urandlib_api_sameoffset(void);
+
 unsigned short urand_read_with_sema_semaphore SEC(".probes");
 
-static __attribute__((noinline))
-void urandom_read(int fd, int count)
+static noinline void urandom_read(int fd, int count)
 {
 	char buf[BUF_SIZE];
 	int i;
@@ -83,6 +90,10 @@ int main(int argc, char *argv[])
 
 	urandom_read(fd, count);
 
+	urandlib_api();
+	urandlib_api_old();
+	urandlib_api_sameoffset();
+
 	close(fd);
 	return 0;
 }

tools/testing/selftests/bpf/urandom_read_lib1.c

@@ -3,6 +3,9 @@
 #define _SDT_HAS_SEMAPHORES 1
 #include "sdt.h"
 
+#define SHARED 1
+#include "bpf/libbpf_internal.h"
+
 #define SEC(name) __attribute__((section(name), used))
 
 unsigned short urandlib_read_with_sema_semaphore SEC(".probes");
@@ -11,3 +14,22 @@ void urandlib_read_with_sema(int iter_num, int iter_cnt, int read_sz)
 {
 	STAP_PROBE3(urandlib, read_with_sema, iter_num, iter_cnt, read_sz);
 }
+
+COMPAT_VERSION(urandlib_api_v1, urandlib_api, LIBURANDOM_READ_1.0.0)
+int urandlib_api_v1(void)
+{
+	return 1;
+}
+
+DEFAULT_VERSION(urandlib_api_v2, urandlib_api, LIBURANDOM_READ_2.0.0)
+int urandlib_api_v2(void)
+{
+	return 2;
+}
+
+COMPAT_VERSION(urandlib_api_sameoffset, urandlib_api_sameoffset, LIBURANDOM_READ_1.0.0)
+DEFAULT_VERSION(urandlib_api_sameoffset, urandlib_api_sameoffset, LIBURANDOM_READ_2.0.0)
+int urandlib_api_sameoffset(void)
+{
+	return 3;
+}