linux-kernel - Re: [PATCH v21 03/19] perf, tools: Use pmu

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: <20160927131600.GM5588@kernel.org>
Date:   Tue, 27 Sep 2016 10:16:00 -0300
From:   Arnaldo Carvalho de Melo <acme@...nel.org>
To:     Sukadev Bhattiprolu <sukadev@...ux.vnet.ibm.com>
Cc:     peterz@...radead.org, maddy@...ux.vnet.ibm.com,
        linuxppc-dev@...ts.ozlabs.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v21 03/19] perf, tools: Use pmu_events table to create
 aliases

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@...ux.vnet.ibm.com>
> Acked-by: Jiri Olsa <jolsa@...hat.com>
> Acked-by: Ingo Molnar <mingo@...nel.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