linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Cc: peterz@infradead.org, maddy@linux.vnet.ibm.com,
	linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v21 03/19] perf, tools: Use pmu_events table to create aliases
Date: Tue, 27 Sep 2016 10:16:00 -0300	[thread overview]
Message-ID: <20160927131600.GM5588@kernel.org> (raw)
In-Reply-To: <1473978296-20712-4-git-send-email-sukadev@linux.vnet.ibm.com>

Em Thu, Sep 15, 2016 at 03:24:40PM -0700, Sukadev Bhattiprolu escreveu:
> At run time (when 'perf' is starting up), locate the specific table
> of PMU events that corresponds to the current CPU. Using that table,
> create aliases for the each of the PMU events in the CPU. The use
> these aliases to parse the user specified perf event.
> 
> In short this would allow the user to specify events using their
> aliases rather than raw event codes.
> 
> Based on input and some earlier patches from Andi Kleen, Jiri Olsa.

this took a long time so I'll try to go chainsawing some stuff along the
way, like why introduce a function that returns an error just to ignore
it, even more using a ugly (void) cast?

- Arnaldo
 
> Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
> Acked-by: Jiri Olsa <jolsa@redhat.com>
> Acked-by: Ingo Molnar <mingo@kernel.org>
> ---
> 
> Changelog[v4]
> 	- Split off unrelated code into separate patches.
> Changelog[v3]
> 	- [Jiri Olsa] Fix memory leak in cpuid
> Changelog[v2]
> 	- [Andi Kleen] Replace pmu_events_map->vfm with a generic "cpuid".
> ---
>  tools/perf/util/header.h |  1 +
>  tools/perf/util/pmu.c    | 61 ++++++++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 62 insertions(+)
> 
> diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
> index d306ca1..d30109b 100644
> --- a/tools/perf/util/header.h
> +++ b/tools/perf/util/header.h
> @@ -151,4 +151,5 @@ int write_padded(int fd, const void *bf, size_t count, size_t count_aligned);
>   */
>  int get_cpuid(char *buffer, size_t sz);
>  
> +char *get_cpuid_str(void);
>  #endif /* __PERF_HEADER_H */
> diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
> index 2babcdf..c842886 100644
> --- a/tools/perf/util/pmu.c
> +++ b/tools/perf/util/pmu.c
> @@ -12,6 +12,8 @@
>  #include "pmu.h"
>  #include "parse-events.h"
>  #include "cpumap.h"
> +#include "header.h"
> +#include "pmu-events/pmu-events.h"
>  
>  struct perf_pmu_format {
>  	char *name;
> @@ -473,6 +475,62 @@ static struct cpu_map *pmu_cpumask(const char *name)
>  	return cpus;
>  }
>  
> +/*
> + * Return the CPU id as a raw string.
> + *
> + * Each architecture should provide a more precise id string that
> + * can be use to match the architecture's "mapfile".
> + */
> +char * __weak get_cpuid_str(void)
> +{
> +	return NULL;
> +}
> +
> +/*
> + * From the pmu_events_map, find the table of PMU events that corresponds
> + * to the current running CPU. Then, add all PMU events from that table
> + * as aliases.
> + */
> +static int pmu_add_cpu_aliases(struct list_head *head)
> +{
> +	int i;
> +	struct pmu_events_map *map;
> +	struct pmu_event *pe;
> +	char *cpuid;
> +
> +	cpuid = get_cpuid_str();
> +	if (!cpuid)
> +		return 0;
> +
> +	i = 0;
> +	while (1) {
> +		map = &pmu_events_map[i++];
> +		if (!map->table)
> +			goto out;
> +
> +		if (!strcmp(map->cpuid, cpuid))
> +			break;
> +	}
> +
> +	/*
> +	 * Found a matching PMU events table. Create aliases
> +	 */
> +	i = 0;
> +	while (1) {
> +		pe = &map->table[i++];
> +		if (!pe->name)
> +			break;
> +
> +		/* need type casts to override 'const' */
> +		__perf_pmu__new_alias(head, NULL, (char *)pe->name,
> +				(char *)pe->desc, (char *)pe->event);
> +	}
> +
> +out:
> +	free(cpuid);
> +	return 0;
> +}
> +
>  struct perf_event_attr * __weak
>  perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
>  {
> @@ -497,6 +555,9 @@ static struct perf_pmu *pmu_lookup(const char *name)
>  	if (pmu_aliases(name, &aliases))
>  		return NULL;
>  
> +	if (!strcmp(name, "cpu"))
> +		(void)pmu_add_cpu_aliases(&aliases);
> +
>  	if (pmu_type(name, &type))
>  		return NULL;
>  
> -- 
> 1.8.3.1

  reply	other threads:[~2016-09-27 13:16 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-09-15 22:24 [PATCH v21 00/20] perf, tools: Add support for PMU events in JSON format Sukadev Bhattiprolu
2016-09-15 22:24 ` [PATCH v21 01/19] perf, tools: Add jsmn `jasmine' JSON parser Sukadev Bhattiprolu
2016-09-15 22:24 ` [PATCH v21 02/19] perf, tools, jevents: Program to convert JSON file to C style file Sukadev Bhattiprolu
2016-09-15 22:24 ` [PATCH v21 03/19] perf, tools: Use pmu_events table to create aliases Sukadev Bhattiprolu
2016-09-27 13:16   ` Arnaldo Carvalho de Melo [this message]
2016-09-15 22:24 ` [PATCH v21 04/19] perf, tools: Support CPU ID matching for Powerpc Sukadev Bhattiprolu
2016-09-15 22:24 ` [PATCH v21 05/19] perf, tools: Support CPU id matching for x86 v2 Sukadev Bhattiprolu
2016-09-15 22:24 ` [PATCH v21 06/19] perf, tools: Support alias descriptions Sukadev Bhattiprolu
2016-09-27 17:41   ` Arnaldo Carvalho de Melo
2016-09-27 18:11     ` Sukadev Bhattiprolu
2016-09-28 13:57       ` Arnaldo Carvalho de Melo
2016-09-28 18:29         ` Sukadev Bhattiprolu
2016-09-28 19:08           ` Arnaldo Carvalho de Melo
2016-10-03 20:52           ` Arnaldo Carvalho de Melo
2016-09-15 22:24 ` [PATCH v21 07/19] perf, tools: Query terminal width and use in perf list Sukadev Bhattiprolu
2016-09-15 22:24 ` [PATCH v21 08/19] perf, tools: Add a --no-desc flag to " Sukadev Bhattiprolu
2016-09-15 22:24 ` [PATCH v21 09/19] perf, tools: Add override support for event list CPUID Sukadev Bhattiprolu
2016-09-15 22:24 ` [PATCH v21 10/19] perf, tools, jevents: Add support for long descriptions Sukadev Bhattiprolu
2016-09-15 22:24 ` [PATCH v21 11/19] perf, tools: Add alias " Sukadev Bhattiprolu
2016-10-04  0:20   ` Arnaldo Carvalho de Melo
2016-09-15 22:24 ` [PATCH v21 12/19] perf, tools: Support long descriptions with perf list Sukadev Bhattiprolu
2016-10-04  0:26   ` Arnaldo Carvalho de Melo
2016-09-15 22:24 ` [PATCH v21 13/19] perf, tools: Add support for event list topics Sukadev Bhattiprolu
2016-09-15 22:24 ` [PATCH v21 14/19] perf, tools, jevents: Handle header line in mapfile Sukadev Bhattiprolu
2016-10-04  0:36   ` Arnaldo Carvalho de Melo
2016-09-15 22:24 ` [PATCH v21 15/19] perf, tools: Add README for info on parsing JSON/map files Sukadev Bhattiprolu
2016-10-04  0:38   ` Arnaldo Carvalho de Melo
2016-09-15 22:24 ` [PATCH v21 16/19] perf, tools: Make alias matching case-insensitive Sukadev Bhattiprolu
2016-10-04  0:47   ` Arnaldo Carvalho de Melo
2016-10-04  0:54     ` Arnaldo Carvalho de Melo
2016-10-04  8:19       ` Jiri Olsa
2016-10-04  8:19     ` Jiri Olsa
2016-09-15 22:24 ` [PATCH v21 17/19] perf, tools, pmu-events: Fix fixed counters on Intel Sukadev Bhattiprolu
2016-09-15 22:24 ` [PATCH v21 18/19] perf, tools, pmu-events: Add Skylake frontend MSR support Sukadev Bhattiprolu
2016-09-15 22:24 ` [PATCH v21 19/19] perf, tools: Allow period= in perf stat CPU event descriptions Sukadev Bhattiprolu
2016-09-19 16:58 ` [PATCH v21 00/20] perf, tools: Add support for PMU events in JSON format Sukadev Bhattiprolu
2016-09-19 21:20 ` Arnaldo Carvalho de Melo
2016-09-19 23:31   ` Arnaldo Carvalho de Melo
2016-09-19 23:37     ` Arnaldo Carvalho de Melo
2016-09-20  0:02       ` Arnaldo Carvalho de Melo
2016-09-20  0:28         ` Arnaldo Carvalho de Melo
2016-09-22 14:56           ` Arnaldo Carvalho de Melo
2016-09-22 15:00           ` Jiri Olsa
2016-09-22 16:27             ` Jiri Olsa
2016-09-26  8:35               ` Jiri Olsa
2016-09-26 15:03                 ` Arnaldo Carvalho de Melo
2016-09-26 16:59                   ` Andi Kleen
2016-09-27 14:18                     ` Jiri Olsa
2016-09-29 22:19                       ` Arnaldo Carvalho de Melo
2016-09-30  9:10                         ` Jiri Olsa

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=20160927131600.GM5588@kernel.org \
    --to=acme@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=maddy@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=sukadev@linux.vnet.ibm.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;
as well as URLs for NNTP newsgroup(s).