[PATCH v6 RESEND] libbpf: kprobe.multi: Filter with available_filter_functions

[PATCH v6 RESEND] libbpf: kprobe.multi: Filter with available_filter_functions

[Jackie Liu]

From: Jackie Liu <liuyun01@kylinos.cn>

When using regular expression matching with "kprobe multi", it scans all
the functions under "/proc/kallsyms" that can be matched. However, not all
of them can be traced by kprobe.multi. If any one of the functions fails
to be traced, it will result in the failure of all functions. The best
approach is to filter out the functions that cannot be traced to ensure
proper tracking of the functions.

Use available_filter_functions check first, if failed, fallback to
kallsyms.

Here is the test eBPF program [1].
[1] https://github.com/JackieLiu1/ketones/commit/a9e76d1ba57390e533b8b3eadde97f7a4535e867

Suggested-by: Jiri Olsa <olsajiri@gmail.com>
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
---
 tools/lib/bpf/libbpf.c | 100 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 93 insertions(+), 7 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ad1ec893b41b..0914b7e98e30 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -10106,6 +10106,12 @@ static const char *tracefs_uprobe_events(void)
 	return use_debugfs() ? DEBUGFS"/uprobe_events" : TRACEFS"/uprobe_events";
 }
 
+static const char *tracefs_available_filter_functions(void)
+{
+	return use_debugfs() ? DEBUGFS"/available_filter_functions" :
+			       TRACEFS"/available_filter_functions";
+}
+
 static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz,
 					 const char *kfunc_name, size_t offset)
 {
@@ -10417,13 +10423,14 @@ static bool glob_match(const char *str, const char *pat)
 struct kprobe_multi_resolve {
 	const char *pattern;
 	unsigned long *addrs;
+	const char **syms;
 	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)
+kallsyms_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;
@@ -10440,6 +10447,77 @@ resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type,
 	return 0;
 }
 
+static int ftrace_resolve_kprobe_multi_cb(const char *sym_name, void *ctx)
+{
+	struct kprobe_multi_resolve *res = ctx;
+	int err;
+	char *name;
+
+	if (!glob_match(sym_name, res->pattern))
+		return 0;
+
+	err = libbpf_ensure_mem((void **) &res->syms, &res->cap,
+				sizeof(const char *), res->cnt + 1);
+	if (err)
+		return err;
+
+	name = strdup(sym_name);
+	if (!name)
+		return -errno;
+
+	res->syms[res->cnt++] = name;
+	return 0;
+}
+
+typedef int (*available_kprobe_cb_t)(const char *sym_name, void *ctx);
+
+static int
+libbpf_available_kprobes_parse(available_kprobe_cb_t cb, void *ctx)
+{
+	char sym_name[256];
+	FILE *f;
+	int ret, err = 0;
+	const char *available_path = tracefs_available_filter_functions();
+
+	f = fopen(available_path, "r");
+	if (!f) {
+		err = -errno;
+		pr_warn("failed to open %s, fallback to /proc/kallsyms.\n",
+			available_path);
+		return err;
+	}
+
+	while (true) {
+		ret = fscanf(f, "%255s%*[^\n]\n", sym_name);
+		if (ret == EOF && feof(f))
+			break;
+		if (ret != 1) {
+			pr_warn("failed to read available kprobe entry: %d\n",
+				ret);
+			err = -EINVAL;
+			break;
+		}
+
+		err = cb(sym_name, ctx);
+		if (err)
+			break;
+	}
+
+	fclose(f);
+	return err;
+}
+
+static void kprobe_multi_resolve_free(struct kprobe_multi_resolve *res)
+{
+	while (res->syms && res->cnt)
+		free((char *)res->syms[--res->cnt]);
+
+	free(res->syms);
+	free(res->addrs);
+	/* reset cap to zero, when fallback */
+	res->cap = 0;
+}
+
 struct bpf_link *
 bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 				      const char *pattern,
@@ -10476,13 +10554,21 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 		return libbpf_err_ptr(-EINVAL);
 
 	if (pattern) {
-		err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res);
-		if (err)
-			goto error;
+		err = libbpf_available_kprobes_parse(ftrace_resolve_kprobe_multi_cb,
+						     &res);
+		if (err) {
+			/* fallback to kallsyms */
+			kprobe_multi_resolve_free(&res);
+			err = libbpf_kallsyms_parse(kallsyms_resolve_kprobe_multi_cb,
+						    &res);
+			if (err)
+				goto error;
+		}
 		if (!res.cnt) {
 			err = -ENOENT;
 			goto error;
 		}
+		syms = res.syms;
 		addrs = res.addrs;
 		cnt = res.cnt;
 	}
@@ -10511,12 +10597,12 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 		goto error;
 	}
 	link->fd = link_fd;
-	free(res.addrs);
+	kprobe_multi_resolve_free(&res);
 	return link;
 
 error:
 	free(link);
-	free(res.addrs);
+	kprobe_multi_resolve_free(&res);
 	return libbpf_err_ptr(err);
 }
 
-- 
2.25.1

Re: [PATCH v6 RESEND] libbpf: kprobe.multi: Filter with available_filter_functions

[Jiri Olsa]

On Fri, May 26, 2023 at 11:50:26PM +0800, Jackie Liu wrote:
> From: Jackie Liu <liuyun01@kylinos.cn>
> 
> When using regular expression matching with "kprobe multi", it scans all
> the functions under "/proc/kallsyms" that can be matched. However, not all
> of them can be traced by kprobe.multi. If any one of the functions fails
> to be traced, it will result in the failure of all functions. The best
> approach is to filter out the functions that cannot be traced to ensure
> proper tracking of the functions.
> 
> Use available_filter_functions check first, if failed, fallback to
> kallsyms.
> 
> Here is the test eBPF program [1].
> [1] https://github.com/JackieLiu1/ketones/commit/a9e76d1ba57390e533b8b3eadde97f7a4535e867
> 
> Suggested-by: Jiri Olsa <olsajiri@gmail.com>
> Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
> ---
>  tools/lib/bpf/libbpf.c | 100 ++++++++++++++++++++++++++++++++++++++---
>  1 file changed, 93 insertions(+), 7 deletions(-)
> 
> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> index ad1ec893b41b..0914b7e98e30 100644
> --- a/tools/lib/bpf/libbpf.c
> +++ b/tools/lib/bpf/libbpf.c
> @@ -10106,6 +10106,12 @@ static const char *tracefs_uprobe_events(void)
>  	return use_debugfs() ? DEBUGFS"/uprobe_events" : TRACEFS"/uprobe_events";
>  }
>  
> +static const char *tracefs_available_filter_functions(void)
> +{
> +	return use_debugfs() ? DEBUGFS"/available_filter_functions" :
> +			       TRACEFS"/available_filter_functions";
> +}
> +
>  static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz,
>  					 const char *kfunc_name, size_t offset)
>  {
> @@ -10417,13 +10423,14 @@ static bool glob_match(const char *str, const char *pat)
>  struct kprobe_multi_resolve {
>  	const char *pattern;
>  	unsigned long *addrs;
> +	const char **syms;
>  	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)
> +kallsyms_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;
> @@ -10440,6 +10447,77 @@ resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type,
>  	return 0;
>  }
>  
> +static int ftrace_resolve_kprobe_multi_cb(const char *sym_name, void *ctx)
> +{
> +	struct kprobe_multi_resolve *res = ctx;
> +	int err;
> +	char *name;
> +
> +	if (!glob_match(sym_name, res->pattern))
> +		return 0;
> +
> +	err = libbpf_ensure_mem((void **) &res->syms, &res->cap,
> +				sizeof(const char *), res->cnt + 1);
> +	if (err)
> +		return err;
> +
> +	name = strdup(sym_name);
> +	if (!name)
> +		return -errno;
> +
> +	res->syms[res->cnt++] = name;
> +	return 0;
> +}
> +
> +typedef int (*available_kprobe_cb_t)(const char *sym_name, void *ctx);
> +
> +static int
> +libbpf_available_kprobes_parse(available_kprobe_cb_t cb, void *ctx)
> +{
> +	char sym_name[256];
> +	FILE *f;
> +	int ret, err = 0;
> +	const char *available_path = tracefs_available_filter_functions();
> +
> +	f = fopen(available_path, "r");
> +	if (!f) {
> +		err = -errno;
> +		pr_warn("failed to open %s, fallback to /proc/kallsyms.\n",
> +			available_path);
> +		return err;
> +	}
> +
> +	while (true) {
> +		ret = fscanf(f, "%255s%*[^\n]\n", sym_name);
> +		if (ret == EOF && feof(f))
> +			break;
> +		if (ret != 1) {
> +			pr_warn("failed to read available kprobe entry: %d\n",
> +				ret);
> +			err = -EINVAL;
> +			break;
> +		}
> +
> +		err = cb(sym_name, ctx);
> +		if (err)
> +			break;
> +	}
> +
> +	fclose(f);
> +	return err;
> +}
> +
> +static void kprobe_multi_resolve_free(struct kprobe_multi_resolve *res)
> +{
> +	while (res->syms && res->cnt)
> +		free((char *)res->syms[--res->cnt]);
> +
> +	free(res->syms);
> +	free(res->addrs);

I think we also need to zero the res->syms pointer, so the final
kprobe_multi_resolve_free won't try to release it again
perhaps use zfree for both syms and addrs

other than this it looks ok to me:

Acked-by: Jiri Olsa <jolsa@kernel.org>

thanks,
jirka

> +	/* reset cap to zero, when fallback */
> +	res->cap = 0;
> +}
> +
>  struct bpf_link *
>  bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
>  				      const char *pattern,
> @@ -10476,13 +10554,21 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
>  		return libbpf_err_ptr(-EINVAL);
>  
>  	if (pattern) {
> -		err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res);
> -		if (err)
> -			goto error;
> +		err = libbpf_available_kprobes_parse(ftrace_resolve_kprobe_multi_cb,
> +						     &res);
> +		if (err) {
> +			/* fallback to kallsyms */
> +			kprobe_multi_resolve_free(&res);
> +			err = libbpf_kallsyms_parse(kallsyms_resolve_kprobe_multi_cb,
> +						    &res);
> +			if (err)
> +				goto error;
> +		}
>  		if (!res.cnt) {
>  			err = -ENOENT;
>  			goto error;
>  		}
> +		syms = res.syms;
>  		addrs = res.addrs;
>  		cnt = res.cnt;
>  	}
> @@ -10511,12 +10597,12 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
>  		goto error;
>  	}
>  	link->fd = link_fd;
> -	free(res.addrs);
> +	kprobe_multi_resolve_free(&res);
>  	return link;
>  
>  error:
>  	free(link);
> -	free(res.addrs);
> +	kprobe_multi_resolve_free(&res);
>  	return libbpf_err_ptr(err);
>  }
>  
> -- 
> 2.25.1
> 

Re: [PATCH v6 RESEND] libbpf: kprobe.multi: Filter with available_filter_functions

[Jackie Liu]

Hi Jiri.


May 29, 2023 9:23 PM, "Jiri Olsa" <olsajiri@gmail.com> 写到:

> On Fri, May 26, 2023 at 11:50:26PM +0800, Jackie Liu wrote:
> 
>> From: Jackie Liu <liuyun01@kylinos.cn>
>> 
>> When using regular expression matching with "kprobe multi", it scans all
>> the functions under "/proc/kallsyms" that can be matched. However, not all
>> of them can be traced by kprobe.multi. If any one of the functions fails
>> to be traced, it will result in the failure of all functions. The best
>> approach is to filter out the functions that cannot be traced to ensure
>> proper tracking of the functions.
>> 
>> Use available_filter_functions check first, if failed, fallback to
>> kallsyms.
>> 
>> Here is the test eBPF program [1].
>> [1] https://github.com/JackieLiu1/ketones/commit/a9e76d1ba57390e533b8b3eadde97f7a4535e867
>> 
>> Suggested-by: Jiri Olsa <olsajiri@gmail.com>
>> Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
>> ---
>> tools/lib/bpf/libbpf.c | 100 ++++++++++++++++++++++++++++++++++++++---
>> 1 file changed, 93 insertions(+), 7 deletions(-)
>> 
>> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
>> index ad1ec893b41b..0914b7e98e30 100644
>> --- a/tools/lib/bpf/libbpf.c
>> +++ b/tools/lib/bpf/libbpf.c
>> @@ -10106,6 +10106,12 @@ static const char *tracefs_uprobe_events(void)
>> return use_debugfs() ? DEBUGFS"/uprobe_events" : TRACEFS"/uprobe_events";
>> }
>> 
>> +static const char *tracefs_available_filter_functions(void)
>> +{
>> + return use_debugfs() ? DEBUGFS"/available_filter_functions" :
>> + TRACEFS"/available_filter_functions";
>> +}
>> +
>> static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz,
>> const char *kfunc_name, size_t offset)
>> {
>> @@ -10417,13 +10423,14 @@ static bool glob_match(const char *str, const char *pat)
>> struct kprobe_multi_resolve {
>> const char *pattern;
>> unsigned long *addrs;
>> + const char **syms;
>> 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)
>> +kallsyms_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;
>> @@ -10440,6 +10447,77 @@ resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type,
>> return 0;
>> }
>> 
>> +static int ftrace_resolve_kprobe_multi_cb(const char *sym_name, void *ctx)
>> +{
>> + struct kprobe_multi_resolve *res = ctx;
>> + int err;
>> + char *name;
>> +
>> + if (!glob_match(sym_name, res->pattern))
>> + return 0;
>> +
>> + err = libbpf_ensure_mem((void **) &res->syms, &res->cap,
>> + sizeof(const char *), res->cnt + 1);
>> + if (err)
>> + return err;
>> +
>> + name = strdup(sym_name);
>> + if (!name)
>> + return -errno;
>> +
>> + res->syms[res->cnt++] = name;
>> + return 0;
>> +}
>> +
>> +typedef int (*available_kprobe_cb_t)(const char *sym_name, void *ctx);
>> +
>> +static int
>> +libbpf_available_kprobes_parse(available_kprobe_cb_t cb, void *ctx)
>> +{
>> + char sym_name[256];
>> + FILE *f;
>> + int ret, err = 0;
>> + const char *available_path = tracefs_available_filter_functions();
>> +
>> + f = fopen(available_path, "r");
>> + if (!f) {
>> + err = -errno;
>> + pr_warn("failed to open %s, fallback to /proc/kallsyms.\n",
>> + available_path);
>> + return err;
>> + }
>> +
>> + while (true) {
>> + ret = fscanf(f, "%255s%*[^\n]\n", sym_name);
>> + if (ret == EOF && feof(f))
>> + break;
>> + if (ret != 1) {
>> + pr_warn("failed to read available kprobe entry: %d\n",
>> + ret);
>> + err = -EINVAL;
>> + break;
>> + }
>> +
>> + err = cb(sym_name, ctx);
>> + if (err)
>> + break;
>> + }
>> +
>> + fclose(f);
>> + return err;
>> +}
>> +
>> +static void kprobe_multi_resolve_free(struct kprobe_multi_resolve *res)
>> +{
>> + while (res->syms && res->cnt)
>> + free((char *)res->syms[--res->cnt]);
>> +
>> + free(res->syms);
>> + free(res->addrs);
> 
> I think we also need to zero the res->syms pointer, so the final
> kprobe_multi_resolve_free won't try to release it again
> perhaps use zfree for both syms and addrs
> 
> other than this it looks ok to me:
> 
> Acked-by: Jiri Olsa <jolsa@kernel.org>

Thank you for your patient guidance and best wishes to you.

You are right, I finally decided to initialize all related variables to 0. We may indeed guarantee 
that res->cnt will become 0 now, but we will change the logic in the future to miss this.

Thanks again.

-- 
BR, Jackie Liu

> 
> thanks,
> jirka
> 
>> + /* reset cap to zero, when fallback */
>> + res->cap = 0;
>> +}
>> +
>> struct bpf_link *
>> bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
>> const char *pattern,
>> @@ -10476,13 +10554,21 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
>> return libbpf_err_ptr(-EINVAL);
>> 
>> if (pattern) {
>> - err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res);
>> - if (err)
>> - goto error;
>> + err = libbpf_available_kprobes_parse(ftrace_resolve_kprobe_multi_cb,
>> + &res);
>> + if (err) {
>> + /* fallback to kallsyms */
>> + kprobe_multi_resolve_free(&res);
>> + err = libbpf_kallsyms_parse(kallsyms_resolve_kprobe_multi_cb,
>> + &res);
>> + if (err)
>> + goto error;
>> + }
>> if (!res.cnt) {
>> err = -ENOENT;
>> goto error;
>> }
>> + syms = res.syms;
>> addrs = res.addrs;
>> cnt = res.cnt;
>> }
>> @@ -10511,12 +10597,12 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
>> goto error;
>> }
>> link->fd = link_fd;
>> - free(res.addrs);
>> + kprobe_multi_resolve_free(&res);
>> return link;
>> 
>> error:
>> free(link);
>> - free(res.addrs);
>> + kprobe_multi_resolve_free(&res);
>> return libbpf_err_ptr(err);
>> }
>> 
>> --
>> 2.25.1