From: Ingo Molnar <mingo@elte.hu>
To: Jaswinder Singh Rajput <jaswinder@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>,
x86 maintainers <x86@kernel.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH -tip RESEND] x86: perf_counter fix L1-data-Cache-Store-Referencees for AMD
Date: Sat, 20 Jun 2009 19:43:28 +0200 [thread overview]
Message-ID: <20090620174328.GA2422@elte.hu> (raw)
In-Reply-To: <1245484165.3102.6.camel@localhost.localdomain>
* Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:
> Fix AMD's Data Cache Refills from System event.
>
> By this patch :
>
> ./tools/perf/perf stat -e l1d -e l1d-misses -e l1d-write -e l1d-prefetch -e l1d-prefetch-miss -e l1i -e l1i-misses -e l1i-prefetch -e l2 -e l2-misses -e l2-write -e dtlb -e dtlb-misses -e itlb -e itlb-misses -e bpu -e bpu-misses ls /dev/ > /dev/null
>
> Performance counter stats for 'ls /dev/':
>
> 2499484 L1-data-Cache-Load-Referencees (scaled from 3.97%)
> 70347 L1-data-Cache-Load-Misses (scaled from 7.30%)
> 9360 L1-data-Cache-Store-Referencees (scaled from 8.64%)
> 32804 L1-data-Cache-Prefetch-Referencees (scaled from 17.72%)
> 7693 L1-data-Cache-Prefetch-Misses (scaled from 22.97%)
> 2180945 L1-instruction-Cache-Load-Referencees (scaled from 28.48%)
> 14518 L1-instruction-Cache-Load-Misses (scaled from 35.00%)
> 2405 L1-instruction-Cache-Prefetch-Referencees (scaled from 34.89%)
> 71387 L2-Cache-Load-Referencees (scaled from 34.94%)
> 18732 L2-Cache-Load-Misses (scaled from 34.92%)
> 79918 L2-Cache-Store-Referencees (scaled from 36.02%)
> 1295294 Data-TLB-Cache-Load-Referencees (scaled from 35.99%)
> 30896 Data-TLB-Cache-Load-Misses (scaled from 33.36%)
> 1222030 Instruction-TLB-Cache-Load-Referencees (scaled from 29.46%)
> 357 Instruction-TLB-Cache-Load-Misses (scaled from 20.46%)
> 530888 Branch-Cache-Load-Referencees (scaled from 11.48%)
> 8638 Branch-Cache-Load-Misses (scaled from 5.09%)
>
> 0.011295149 seconds time elapsed.
>
> Earlier it always shows value 0.
>
> Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
> ---
> arch/x86/kernel/cpu/perf_counter.c | 2 +-
> 1 files changed, 1 insertions(+), 1 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
> index ce1ae3f..37facc5 100644
> --- a/arch/x86/kernel/cpu/perf_counter.c
> +++ b/arch/x86/kernel/cpu/perf_counter.c
> @@ -401,7 +401,7 @@ static const u64 amd_hw_cache_event_ids
> [ C(RESULT_MISS) ] = 0x0041, /* Data Cache Misses */
> },
> [ C(OP_WRITE) ] = {
> - [ C(RESULT_ACCESS) ] = 0x0042, /* Data Cache Refills from L2 */
> + [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
> [ C(RESULT_MISS) ] = 0,
> },
> [ C(OP_PREFETCH) ] = {
Applied to tip:perfcounters/urgent, thanks Jaswinder!
Ingo
next prev parent reply other threads:[~2009-06-20 17:43 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-06-18 13:28 [PATCH -tip] x86: perf_counter fix L1-data-Cache-Store-Referencees for AMD Jaswinder Singh Rajput
2009-06-20 7:49 ` [PATCH -tip RESEND] " Jaswinder Singh Rajput
2009-06-20 17:43 ` Ingo Molnar [this message]
2009-06-20 17:45 ` [tip:perfcounters/urgent] perf_counter, x8: Fix " tip-bot for Jaswinder Singh Rajput
2009-06-21 11:27 ` tip-bot for Jaswinder Singh Rajput
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20090620174328.GA2422@elte.hu \
--to=mingo@elte.hu \
--cc=jaswinder@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox