linux-kernel - Re: [PATCH v2 -tip] perf probe: Add fastpath to do lookup by function name

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]
Message-ID: <4D8BEC71.1040404@hitachi.com>
Date:	Fri, 25 Mar 2011 10:14:25 +0900
From:	Masami Hiramatsu <masami.hiramatsu.pt@...achi.com>
To:	Lin Ming <ming.m.lin@...el.com>
Cc:	Arnaldo Carvalho de Melo <acme@...radead.org>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Ingo Molnar <mingo@...e.hu>,
	linux-kernel <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v2 -tip] perf probe: Add fastpath to do lookup by function
 name

(2011/03/24 23:09), Lin Ming wrote:
> v2 -> v1:
> - Don't compare file names with cu_find_realpath(...), instead, compare them
>   with the name returned by dwarf_decl_file(sp_die) 
> 
> The vmlinux file may have thousands of CUs.
> We can lookup function name from .debug_pubnames section
> to avoid the slow loop on CUs.
> 
> ./perf stat -r 10 -- ./perf probe -k /home/mlin/vmlinux \
>         -s /home/mlin/linux-2.6 \
> 	--line csum_partial_copy_to_user > tmp.log
> 
> before patch applied
> =====================
>         364.535892 task-clock-msecs         #      0.997 CPUs
>                  0 context-switches         #      0.000 M/sec
>                  0 CPU-migrations           #      0.000 M/sec
>             29,993 page-faults              #      0.082 M/sec
>        865,862,109 cycles                   #   2375.245 M/sec
>      1,255,259,630 instructions             #      1.450 IPC
>        252,400,884 branches                 #    692.390 M/sec
>          3,429,376 branch-misses            #      1.359 %
>          1,386,990 cache-references         #      3.805 M/sec
>            687,188 cache-misses             #      1.885 M/sec
> 
>         0.365792170  seconds time elapsed
> 
> after patch applied
> =====================
>          89.896405 task-clock-msecs         #      0.991 CPUs
>                  1 context-switches         #      0.000 M/sec
>                  0 CPU-migrations           #      0.000 M/sec
>             10,145 page-faults              #      0.113 M/sec
>        214,553,875 cycles                   #   2386.679 M/sec
>        226,915,559 instructions             #      1.058 IPC
>         44,536,614 branches                 #    495.422 M/sec
>            613,074 branch-misses            #      1.377 %
>            860,787 cache-references         #      9.575 M/sec
>            442,380 cache-misses             #      4.921 M/sec
> 
>         0.090716032  seconds time elapsed

Thanks! Looks very good :)

Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@...achi.com>

> 
> Signed-off-by: Lin Ming <ming.m.lin@...el.com>
> ---
>  tools/perf/util/probe-finder.c |   39 +++++++++++++++++++++++++++++++++++++++
>  tools/perf/util/probe-finder.h |    1 +
>  2 files changed, 40 insertions(+), 0 deletions(-)
> 
> diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
> index 194f9e2..5cf044c 100644
> --- a/tools/perf/util/probe-finder.c
> +++ b/tools/perf/util/probe-finder.c
> @@ -1876,6 +1876,31 @@ static int find_line_range_by_func(struct line_finder *lf)
>  	return param.retval;
>  }
>  
> +static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data)
> +{
> +	struct line_finder *lf = data;
> +	struct line_range *lr = lf->lr;
> +
> +	if (dwarf_offdie(dbg, gl->die_offset, &lf->sp_die)) {
> +		if (dwarf_tag(&lf->sp_die) != DW_TAG_subprogram)
> +			return DWARF_CB_OK;
> +
> +		if (die_compare_name(&lf->sp_die, lr->function)) {
> +			if (!dwarf_offdie(dbg, gl->cu_offset, &lf->cu_die))
> +				return DWARF_CB_OK;
> +
> +			if (lr->file &&
> +			    strtailcmp(lr->file, dwarf_decl_file(&lf->sp_die)))
> +				return DWARF_CB_OK;
> +
> +			lf->found = 1;
> +			return DWARF_CB_ABORT;
> +		}
> +	}
> +
> +	return DWARF_CB_OK;
> +}
> +
>  int find_line_range(int fd, struct line_range *lr)
>  {
>  	struct line_finder lf = {.lr = lr, .found = 0};
> @@ -1895,6 +1920,19 @@ int find_line_range(int fd, struct line_range *lr)
>  		return -EBADF;
>  	}
>  
> +	/* Fastpath: lookup by function name from .debug_pubnames section */
> +	if (lr->function) {
> +		struct dwarf_callback_param param = {.data = (void *)&lf, .retval = 0};
> +
> +		dwarf_getpubnames(dbg, pubname_search_cb, &lf, 0);
> +		if (lf.found) {
> +			lf.found = 0;
> +			line_range_search_cb(&lf.sp_die, &param);
> +			if (lf.found)
> +				goto found;
> +		}
> +	}
> +
>  	/* Loop on CUs (Compilation Unit) */
>  	while (!lf.found && ret >= 0) {
>  		if (dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) != 0)
> @@ -1923,6 +1961,7 @@ int find_line_range(int fd, struct line_range *lr)
>  		off = noff;
>  	}
>  
> +found:
>  	/* Store comp_dir */
>  	if (lf.found) {
>  		comp_dir = cu_get_comp_dir(&lf.cu_die);
> diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
> index beaefc3..4bc56a4 100644
> --- a/tools/perf/util/probe-finder.h
> +++ b/tools/perf/util/probe-finder.h
> @@ -83,6 +83,7 @@ struct line_finder {
>  	int			lno_s;		/* Start line number */
>  	int			lno_e;		/* End line number */
>  	Dwarf_Die		cu_die;		/* Current CU */
> +	Dwarf_Die		sp_die;
>  	int			found;
>  };
>  


-- 
Masami HIRAMATSU
2nd Dept. Linux Technology Center
Hitachi, Ltd., Systems Development Laboratory
E-mail: masami.hiramatsu.pt@...achi.com
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/