From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: kan.liang@linux.intel.com
Cc: mingo@kernel.org, linux-kernel@vger.kernel.org,
atrajeev@linux.vnet.ibm.com, namhyung@kernel.org,
jolsa@redhat.com, ak@linux.intel.com, yao.jin@linux.intel.com,
maddy@linux.vnet.ibm.com
Subject: Re: [PATCH] perf tools: Support arch specific PERF_SAMPLE_WEIGHT_STRUCT processing
Date: Thu, 18 Feb 2021 16:07:28 -0300 [thread overview]
Message-ID: <YC668HJYFD3CoO8M@kernel.org> (raw)
In-Reply-To: <1612540912-6562-1-git-send-email-kan.liang@linux.intel.com>
Em Fri, Feb 05, 2021 at 08:01:52AM -0800, kan.liang@linux.intel.com escreveu:
> From: Kan Liang <kan.liang@linux.intel.com>
>
> For X86, the var2_w field of PERF_SAMPLE_WEIGHT_STRUCT stands for the
> instruction latency. Current perf forces the var2_w to the data->ins_lat
> in the generic code. It works well for now because X86 is the only
> architecture that supports the PERF_SAMPLE_WEIGHT_STRUCT, but it may
> bring problems once other architectures support the sample type.
> For example, the var2_w may be used to capture something else on
> PowerPC.
>
> Create two architecture specific functions to parse and synthesize
> the weight related samples. Move the X86 specific codes to the X86
> version functions. Other architectures can implement their own functions
> later separately.
Thanks, applied.
- Arnaldo
> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
> ---
> tools/perf/arch/x86/util/event.c | 25 +++++++++++++++++++++++++
> tools/perf/util/event.h | 3 +++
> tools/perf/util/evsel.c | 17 ++++++++---------
> tools/perf/util/synthetic-events.c | 12 +++++++-----
> 4 files changed, 43 insertions(+), 14 deletions(-)
>
> diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
> index 047dc00..9b31734 100644
> --- a/tools/perf/arch/x86/util/event.c
> +++ b/tools/perf/arch/x86/util/event.c
> @@ -75,3 +75,28 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
> }
>
> #endif
> +
> +void arch_perf_parse_sample_weight(struct perf_sample *data,
> + const __u64 *array, u64 type)
> +{
> + union perf_sample_weight weight;
> +
> + weight.full = *array;
> + if (type & PERF_SAMPLE_WEIGHT)
> + data->weight = weight.full;
> + else {
> + data->weight = weight.var1_dw;
> + data->ins_lat = weight.var2_w;
> + }
> +}
> +
> +void arch_perf_synthesize_sample_weight(const struct perf_sample *data,
> + __u64 *array, u64 type)
> +{
> + *array = data->weight;
> +
> + if (type & PERF_SAMPLE_WEIGHT_STRUCT) {
> + *array &= 0xffffffff;
> + *array |= ((u64)data->ins_lat << 32);
> + }
> +}
> diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
> index 60752e4..9f123aa 100644
> --- a/tools/perf/util/event.h
> +++ b/tools/perf/util/event.h
> @@ -414,4 +414,7 @@ extern unsigned int proc_map_timeout;
> #define PAGE_SIZE_NAME_LEN 32
> char *get_page_size_name(u64 size, char *str);
>
> +void arch_perf_parse_sample_weight(struct perf_sample *data, const __u64 *array, u64 type);
> +void arch_perf_synthesize_sample_weight(const struct perf_sample *data, __u64 *array, u64 type);
> +
> #endif /* __PERF_RECORD_H */
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index 30b5452..1da8903 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -2106,6 +2106,13 @@ perf_event__check_size(union perf_event *event, unsigned int sample_size)
> return 0;
> }
>
> +void __weak arch_perf_parse_sample_weight(struct perf_sample *data,
> + const __u64 *array,
> + u64 type __maybe_unused)
> +{
> + data->weight = *array;
> +}
> +
> int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
> struct perf_sample *data)
> {
> @@ -2347,16 +2354,8 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
> }
>
> if (type & PERF_SAMPLE_WEIGHT_TYPE) {
> - union perf_sample_weight weight;
> -
> OVERFLOW_CHECK_u64(array);
> - weight.full = *array;
> - if (type & PERF_SAMPLE_WEIGHT)
> - data->weight = weight.full;
> - else {
> - data->weight = weight.var1_dw;
> - data->ins_lat = weight.var2_w;
> - }
> + arch_perf_parse_sample_weight(data, array, type);
> array++;
> }
>
> diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
> index c6f9db3..412f4c3 100644
> --- a/tools/perf/util/synthetic-events.c
> +++ b/tools/perf/util/synthetic-events.c
> @@ -1507,6 +1507,12 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
> return result;
> }
>
> +void __weak arch_perf_synthesize_sample_weight(const struct perf_sample *data,
> + __u64 *array, u64 type __maybe_unused)
> +{
> + *array = data->weight;
> +}
> +
> int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format,
> const struct perf_sample *sample)
> {
> @@ -1643,11 +1649,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
> }
>
> if (type & PERF_SAMPLE_WEIGHT_TYPE) {
> - *array = sample->weight;
> - if (type & PERF_SAMPLE_WEIGHT_STRUCT) {
> - *array &= 0xffffffff;
> - *array |= ((u64)sample->ins_lat << 32);
> - }
> + arch_perf_synthesize_sample_weight(sample, array, type);
> array++;
> }
>
> --
> 2.7.4
>
--
- Arnaldo
prev parent reply other threads:[~2021-02-18 19:43 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-05 16:01 [PATCH] perf tools: Support arch specific PERF_SAMPLE_WEIGHT_STRUCT processing kan.liang
2021-02-18 19:07 ` Arnaldo Carvalho de Melo [this message]
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=YC668HJYFD3CoO8M@kernel.org \
--to=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=atrajeev@linux.vnet.ibm.com \
--cc=jolsa@redhat.com \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=maddy@linux.vnet.ibm.com \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=yao.jin@linux.intel.com \
/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