Merge branch 'bpf: Add kprobe multi link'

Jiri Olsa says:

====================

hi,
this patchset adds new link type BPF_TRACE_KPROBE_MULTI that attaches
kprobe program through fprobe API [1] instroduced by Masami.

The fprobe API allows to attach probe on multiple functions at once very
fast, because it works on top of ftrace. On the other hand this limits
the probe point to the function entry or return.

With bpftrace support I see following attach speed:

  # perf stat --null -r 5 ./src/bpftrace -e 'kprobe:x* { } i:ms:1 { exit(); } '
  Attaching 2 probes...
  Attaching 3342 functions
  ...

  1.4960 +- 0.0285 seconds time elapsed  ( +-  1.91% )

v3 changes:
  - based on latest fprobe post from Masami [2]
  - add acks
  - add extra comment to kprobe_multi_link_handler wrt entry ip setup [Masami]
  - keep swap_words_64 static and swap values directly in
    bpf_kprobe_multi_cookie_swap [Andrii]
  - rearrange locking/migrate setup in kprobe_multi_link_prog_run [Andrii]
  - move uapi fields [Andrii]
  - add bpf_program__attach_kprobe_multi_opts function [Andrii]
  - many small test changes [Andrii]
  - added tests for bpf_program__attach_kprobe_multi_opts
  - make kallsyms_lookup_name check for empty string [Andrii]

v2 changes:
  - based on latest fprobe changes [1]
  - renaming the uapi interface to kprobe multi
  - adding support for sort_r to pass user pointer for swap functions
    and using that in cookie support to keep just single functions array
  - moving new link to kernel/trace/bpf_trace.c file
  - using single fprobe callback function for entry and exit
  - using kvzalloc, libbpf_ensure_mem functions
  - adding new k[ret]probe.multi sections instead of using current kprobe
  - used glob_match from test_progs.c, added '?' matching
  - move bpf_get_func_ip verifier inline change to seprate change
  - couple of other minor fixes

Also available at:
  https://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git
  bpf/kprobe_multi

thanks,
jirka

[1] https://lore.kernel.org/bpf/164458044634.586276.3261555265565111183.stgit@devnote2/
[2] https://lore.kernel.org/bpf/164735281449.1084943.12438881786173547153.stgit@devnote2/
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 198 insertions, 24 deletions

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 43161fdd44bbf..f3a31478e23b7 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -7171,12 +7171,10 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj)
 	return 0;
 }
 
-static int bpf_object__read_kallsyms_file(struct bpf_object *obj)
+int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx)
 {
 	char sym_type, sym_name[500];
 	unsigned long long sym_addr;
-	const struct btf_type *t;
-	struct extern_desc *ext;
 	int ret, err = 0;
 	FILE *f;
 
@@ -7195,35 +7193,51 @@ static int bpf_object__read_kallsyms_file(struct bpf_object *obj)
 		if (ret != 3) {
 			pr_warn("failed to read kallsyms entry: %d\n", ret);
 			err = -EINVAL;
-			goto out;
+			break;
 		}
 
-		ext = find_extern_by_name(obj, sym_name);
-		if (!ext || ext->type != EXT_KSYM)
-			continue;
-
-		t = btf__type_by_id(obj->btf, ext->btf_id);
-		if (!btf_is_var(t))
-			continue;
-
-		if (ext->is_set && ext->ksym.addr != sym_addr) {
-			pr_warn("extern (ksym) '%s' resolution is ambiguous: 0x%llx or 0x%llx\n",
-				sym_name, ext->ksym.addr, sym_addr);
-			err = -EINVAL;
-			goto out;
-		}
-		if (!ext->is_set) {
-			ext->is_set = true;
-			ext->ksym.addr = sym_addr;
-			pr_debug("extern (ksym) %s=0x%llx\n", sym_name, sym_addr);
-		}
+		err = cb(sym_addr, sym_type, sym_name, ctx);
+		if (err)
+			break;
 	}
 
-out:
 	fclose(f);
 	return err;
 }
 
+static int kallsyms_cb(unsigned long long sym_addr, char sym_type,
+		       const char *sym_name, void *ctx)
+{
+	struct bpf_object *obj = ctx;
+	const struct btf_type *t;
+	struct extern_desc *ext;
+
+	ext = find_extern_by_name(obj, sym_name);
+	if (!ext || ext->type != EXT_KSYM)
+		return 0;
+
+	t = btf__type_by_id(obj->btf, ext->btf_id);
+	if (!btf_is_var(t))
+		return 0;
+
+	if (ext->is_set && ext->ksym.addr != sym_addr) {
+		pr_warn("extern (ksym) '%s' resolution is ambiguous: 0x%llx or 0x%llx\n",
+			sym_name, ext->ksym.addr, sym_addr);
+		return -EINVAL;
+	}
+	if (!ext->is_set) {
+		ext->is_set = true;
+		ext->ksym.addr = sym_addr;
+		pr_debug("extern (ksym) %s=0x%llx\n", sym_name, sym_addr);
+	}
+	return 0;
+}
+
+static int bpf_object__read_kallsyms_file(struct bpf_object *obj)
+{
+	return libbpf_kallsyms_parse(kallsyms_cb, obj);
+}
+
 static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name,
 			    __u16 kind, struct btf **res_btf,
 			    struct module_btf **res_mod_btf)
@@ -8596,6 +8610,7 @@ static int attach_kprobe(const struct bpf_program *prog, long cookie, struct bpf
 static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link);
+static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 
@@ -8607,6 +8622,8 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("uprobe/",		KPROBE,	0, SEC_NONE),
 	SEC_DEF("kretprobe/",		KPROBE, 0, SEC_NONE, attach_kprobe),
 	SEC_DEF("uretprobe/",		KPROBE, 0, SEC_NONE),
+	SEC_DEF("kprobe.multi/",	KPROBE,	BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi),
+	SEC_DEF("kretprobe.multi/",	KPROBE,	BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi),
 	SEC_DEF("tc",			SCHED_CLS, 0, SEC_NONE),
 	SEC_DEF("classifier",		SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX | SEC_DEPRECATED),
 	SEC_DEF("action",		SCHED_ACT, 0, SEC_NONE | SEC_SLOPPY_PFX),
@@ -10210,6 +10227,139 @@ struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog,
 	return bpf_program__attach_kprobe_opts(prog, func_name, &opts);
 }
 
+/* Adapted from perf/util/string.c */
+static bool glob_match(const char *str, const char *pat)
+{
+	while (*str && *pat && *pat != '*') {
+		if (*pat == '?') {      /* Matches any single character */
+			str++;
+			pat++;
+			continue;
+		}
+		if (*str != *pat)
+			return false;
+		str++;
+		pat++;
+	}
+	/* Check wild card */
+	if (*pat == '*') {
+		while (*pat == '*')
+			pat++;
+		if (!*pat) /* Tail wild card matches all */
+			return true;
+		while (*str)
+			if (glob_match(str++, pat))
+				return true;
+	}
+	return !*str && !*pat;
+}
+
+struct kprobe_multi_resolve {
+	const char *pattern;
+	unsigned long *addrs;
+	size_t cap;
+	size_t cnt;
+};
+
+static int
+resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type,
+			const char *sym_name, void *ctx)
+{
+	struct kprobe_multi_resolve *res = ctx;
+	int err;
+
+	if (!glob_match(sym_name, res->pattern))
+		return 0;
+
+	err = libbpf_ensure_mem((void **) &res->addrs, &res->cap, sizeof(unsigned long),
+				res->cnt + 1);
+	if (err)
+		return err;
+
+	res->addrs[res->cnt++] = (unsigned long) sym_addr;
+	return 0;
+}
+
+struct bpf_link *
+bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
+				      const char *pattern,
+				      const struct bpf_kprobe_multi_opts *opts)
+{
+	LIBBPF_OPTS(bpf_link_create_opts, lopts);
+	struct kprobe_multi_resolve res = {
+		.pattern = pattern,
+	};
+	struct bpf_link *link = NULL;
+	char errmsg[STRERR_BUFSIZE];
+	const unsigned long *addrs;
+	int err, link_fd, prog_fd;
+	const __u64 *cookies;
+	const char **syms;
+	bool retprobe;
+	size_t cnt;
+
+	if (!OPTS_VALID(opts, bpf_kprobe_multi_opts))
+		return libbpf_err_ptr(-EINVAL);
+
+	syms    = OPTS_GET(opts, syms, false);
+	addrs   = OPTS_GET(opts, addrs, false);
+	cnt     = OPTS_GET(opts, cnt, false);
+	cookies = OPTS_GET(opts, cookies, false);
+
+	if (!pattern && !addrs && !syms)
+		return libbpf_err_ptr(-EINVAL);
+	if (pattern && (addrs || syms || cookies || cnt))
+		return libbpf_err_ptr(-EINVAL);
+	if (!pattern && !cnt)
+		return libbpf_err_ptr(-EINVAL);
+	if (addrs && syms)
+		return libbpf_err_ptr(-EINVAL);
+
+	if (pattern) {
+		err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res);
+		if (err)
+			goto error;
+		if (!res.cnt) {
+			err = -ENOENT;
+			goto error;
+		}
+		addrs = res.addrs;
+		cnt = res.cnt;
+	}
+
+	retprobe = OPTS_GET(opts, retprobe, false);
+
+	lopts.kprobe_multi.syms = syms;
+	lopts.kprobe_multi.addrs = addrs;
+	lopts.kprobe_multi.cookies = cookies;
+	lopts.kprobe_multi.cnt = cnt;
+	lopts.kprobe_multi.flags = retprobe ? BPF_F_KPROBE_MULTI_RETURN : 0;
+
+	link = calloc(1, sizeof(*link));
+	if (!link) {
+		err = -ENOMEM;
+		goto error;
+	}
+	link->detach = &bpf_link__detach_fd;
+
+	prog_fd = bpf_program__fd(prog);
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &lopts);
+	if (link_fd < 0) {
+		err = -errno;
+		pr_warn("prog '%s': failed to attach: %s\n",
+			prog->name, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+		goto error;
+	}
+	link->fd = link_fd;
+	free(res.addrs);
+	return link;
+
+error:
+	free(link);
+	free(res.addrs);
+	return libbpf_err_ptr(err);
+}
+
 static int attach_kprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link)
 {
 	DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts);
@@ -10241,6 +10391,30 @@ static int attach_kprobe(const struct bpf_program *prog, long cookie, struct bpf
 	return libbpf_get_error(*link);
 }
 
+static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link)
+{
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	const char *spec;
+	char *pattern;
+	int n;
+
+	opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe.multi/");
+	if (opts.retprobe)
+		spec = prog->sec_name + sizeof("kretprobe.multi/") - 1;
+	else
+		spec = prog->sec_name + sizeof("kprobe.multi/") - 1;
+
+	n = sscanf(spec, "%m[a-zA-Z0-9_.*?]", &pattern);
+	if (n < 1) {
+		pr_warn("kprobe multi pattern is invalid: %s\n", pattern);
+		return -EINVAL;
+	}
+
+	*link = bpf_program__attach_kprobe_multi_opts(prog, pattern, &opts);
+	free(pattern);
+	return libbpf_get_error(*link);
+}
+
 static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz,
 					 const char *binary_path, uint64_t offset)
 {