linux-kernel - Re: [PATCH bpf-next v5] selftests/bpf: trace

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 17 Aug 2023 10:21:15 +0200
From:   Jiri Olsa <olsajiri@...il.com>
To:     Rong Tao <rtoax@...mail.com>
Cc:     sdf@...gle.com, daniel@...earbox.net, andrii@...nel.org,
        rongtao@...tc.cn, Alexei Starovoitov <ast@...nel.org>,
        Martin KaFai Lau <martin.lau@...ux.dev>,
        Song Liu <song@...nel.org>,
        Yonghong Song <yonghong.song@...ux.dev>,
        John Fastabend <john.fastabend@...il.com>,
        KP Singh <kpsingh@...nel.org>, Hao Luo <haoluo@...gle.com>,
        Mykola Lysenko <mykolal@...com>, Shuah Khan <shuah@...nel.org>,
        "open list:BPF [GENERAL] (Safe Dynamic Programs and Tools)" 
        <bpf@...r.kernel.org>,
        "open list:KERNEL SELFTEST FRAMEWORK" 
        <linux-kselftest@...r.kernel.org>,
        open list <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH bpf-next v5] selftests/bpf: trace_helpers.c: optimize
 kallsyms cache

On Thu, Aug 17, 2023 at 01:03:45PM +0800, Rong Tao wrote:
> From: Rong Tao <rongtao@...tc.cn>
> 
> Static ksyms often have problems because the number of symbols exceeds the
> MAX_SYMS limit. Like changing the MAX_SYMS from 300000 to 400000 in
> commit e76a014334a6("selftests/bpf: Bump and validate MAX_SYMS") solves
> the problem somewhat, but it's not the perfect way.
> 
> This commit uses dynamic memory allocation, which completely solves the
> problem caused by the limitation of the number of kallsyms.
> 
> Acked-by: Stanislav Fomichev <sdf@...gle.com>
> Signed-off-by: Rong Tao <rongtao@...tc.cn>
> ---
> v5: Release the allocated memory once the load_kallsyms_refresh() upon error
>     given it's dynamically allocated.
> v4: https://lore.kernel.org/lkml/tencent_59C74613113F0C728524B2A82FE5540A5E09@qq.com/
>     Make sure most cases we don't need the realloc() path to begin with,
>     and check strdup() return value.
> v3: https://lore.kernel.org/lkml/tencent_50B4B2622FE7546A5FF9464310650C008509@qq.com/
>     Do not use structs and judge ksyms__add_symbol function return value.
> v2: https://lore.kernel.org/lkml/tencent_B655EE5E5D463110D70CD2846AB3262EED09@qq.com/
>     Do the usual len/capacity scheme here to amortize the cost of realloc, and
>     don't free symbols.
> v1: https://lore.kernel.org/lkml/tencent_AB461510B10CD484E0B2F62E3754165F2909@qq.com/
> ---
>  tools/testing/selftests/bpf/trace_helpers.c | 62 +++++++++++++++++----
>  1 file changed, 52 insertions(+), 10 deletions(-)
> 
> diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
> index f83d9f65c65b..0053ba22f0cb 100644
> --- a/tools/testing/selftests/bpf/trace_helpers.c
> +++ b/tools/testing/selftests/bpf/trace_helpers.c
> @@ -18,10 +18,47 @@
>  #define TRACEFS_PIPE	"/sys/kernel/tracing/trace_pipe"
>  #define DEBUGFS_PIPE	"/sys/kernel/debug/tracing/trace_pipe"
>  
> -#define MAX_SYMS 400000
> -static struct ksym syms[MAX_SYMS];
> +static struct ksym *syms;
> +static int sym_cap;
>  static int sym_cnt;
>  
> +static int ksyms__add_symbol(const char *name, unsigned long addr)
> +{
> +	void *tmp;
> +	unsigned int new_cap;
> +
> +	if (sym_cnt + 1 > sym_cap) {
> +		new_cap = sym_cap * 4 / 3;
> +		tmp = realloc(syms, sizeof(struct ksym) * new_cap);
> +		if (!tmp)
> +			return -ENOMEM;
> +		syms = tmp;
> +		sym_cap = new_cap;
> +	}

sorry I did not notice earlier, but we have helper for realloc

  libbpf_ensure_mem

check the usage for example in prog_tests/kprobe_multi_test.c

> +
> +	tmp = strdup(name);
> +	if (!tmp)
> +		return -ENOMEM;
> +	syms[sym_cnt].addr = addr;
> +	syms[sym_cnt].name = tmp;
> +
> +	sym_cnt++;
> +
> +	return 0;
> +}
> +
> +static void ksyms__free(void)
> +{
> +	unsigned int i;
> +
> +	if (!syms)
> +		return;
> +
> +	for (i = 0; i < sym_cnt; i++)
> +		free(syms[i].name);
> +	free(syms);
> +}
> +
>  static int ksym_cmp(const void *p1, const void *p2)
>  {
>  	return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
> @@ -33,9 +70,14 @@ int load_kallsyms_refresh(void)
>  	char func[256], buf[256];
>  	char symbol;
>  	void *addr;
> -	int i = 0;
> +	int ret;
>  
> +	/* Make sure most cases we don't need the realloc() path to begin with */
> +	sym_cap = 400000;
>  	sym_cnt = 0;
> +	syms = malloc(sizeof(struct ksym) * sym_cap);
> +	if (!syms)
> +		return -ENOMEM;

libbpf_ensure_mem will also take care of first allocation and the capacity increase

jirka

>  
>  	f = fopen("/proc/kallsyms", "r");
>  	if (!f)
> @@ -46,17 +88,17 @@ int load_kallsyms_refresh(void)
>  			break;
>  		if (!addr)
>  			continue;
> -		if (i >= MAX_SYMS)
> -			return -EFBIG;
> -
> -		syms[i].addr = (long) addr;
> -		syms[i].name = strdup(func);
> -		i++;
> +		ret = ksyms__add_symbol(func, (unsigned long)addr);
> +		if (ret)
> +			goto error;
>  	}
>  	fclose(f);
> -	sym_cnt = i;
>  	qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
>  	return 0;
> +
> +error:
> +	ksyms__free();
> +	return ret;
>  }
>  
>  int load_kallsyms(void)
> -- 
> 2.39.3
> 
>