linux-kernel - Re: [PATCH] perf script: Fix printing 'phys

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: <1c38c70b-d165-acf9-1c98-eeb234fbbe99@arm.com>
Date:   Fri, 21 Jan 2022 11:24:57 +0000
From:   German Gomez <german.gomez@....com>
To:     Wei Li <liwei391@...wei.com>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Jiri Olsa <jolsa@...hat.com>,
        Namhyung Kim <namhyung@...nel.org>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
        guohanjun@...wei.com, jinyao5@...wei.com
Subject: Re: [PATCH] perf script: Fix printing 'phys_addr' failure issue

Hi Wei,

This looks good to me. As a followup we could also fix the 'weight'
field, which was introduced recently.

On 21/01/2022 06:59, Wei Li wrote:
> From: Yao Jin <jinyao5@...wei.com>
>
> Perf script was failed to print the phys_addr for SPE profiling.
> One 'dummy' event is added by SPE profiling but it doesn't have PHYS_ADDR
> attribute set, perf script then exits with error.
>
> Now referring to 'addr', use evsel__do_check_stype() to check the type.
>
> Before:
>
>   # perf record -e arm_spe_0/branch_filter=0,ts_enable=1,pa_enable=1,load_filter=1,jitter=0,\
> 		store_filter=0,min_latency=0,event_filter=2/ -p 4064384 -- sleep 3
>   # perf script -F pid,tid,addr,phys_addr
>   Samples for 'dummy:u' event do not have PHYS_ADDR attribute set. Cannot print 'phys_addr' field.
>
> After:
>
>   # perf record -e arm_spe_0/branch_filter=0,ts_enable=1,pa_enable=1,load_filter=1,jitter=0,\
> 		store_filter=0,min_latency=0,event_filter=2/ -p 4064384 -- sleep 3
>   # perf script -F pid,tid,addr,phys_addr
>   4064384/4064384 ffff802f921be0d0      2f921be0d0
>   4064384/4064384 ffff802f921be0d0      2f921be0d0
>
> Signed-off-by: Yao Jin <jinyao5@...wei.com>
> Signed-off-by: Wei Li <liwei391@...wei.com>

Reviewed-by: German Gomez <german.gomez@....com>

Also it looks like the SPE samples are also missing the PHYS_ADDR flag.
I think we'll need to fix the consistency of the flags.

Many thanks,
German

> ---
>  tools/perf/builtin-script.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
> index ecd4f99a6c14..abae8184e171 100644
> --- a/tools/perf/builtin-script.c
> +++ b/tools/perf/builtin-script.c
> @@ -515,7 +515,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
>  		return -EINVAL;
>  
>  	if (PRINT_FIELD(PHYS_ADDR) &&
> -	    evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR))
> +	    evsel__do_check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR, allow_user_set))
>  		return -EINVAL;
>  
>  	if (PRINT_FIELD(DATA_PAGE_SIZE) &&