linux-kernel - Re: [PATCH] perf mem/c2c: Fix perf_mem

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: <20190128110722.GB15461@krava>
Date:   Mon, 28 Jan 2019 12:07:22 +0100
From:   Jiri Olsa <jolsa@...hat.com>
To:     Ravi Bangoria <ravi.bangoria@...ux.ibm.com>
Cc:     acme@...nel.org, namhyung@...nel.org, dzickus@...hat.com,
        fowles@...each.com, jmario@...hat.com,
        linux-kernel@...r.kernel.org, mpe@...erman.id.au,
        linuxppc-dev@...ts.ozlabs.org, maddy@...ux.vnet.ibm.com
Subject: Re: [PATCH] perf mem/c2c: Fix perf_mem_events to support powerpc

On Mon, Jan 14, 2019 at 09:44:02AM +0530, Ravi Bangoria wrote:

SNIP

> diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
> new file mode 100644
> index 0000000..5b4dcfe
> --- /dev/null
> +++ b/tools/perf/arch/x86/util/mem-events.c
> @@ -0,0 +1,25 @@
> +// SPDX-License-Identifier: GPL-2.0
> +#include "mem-events.h"
> +
> +struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
> +	PERF_MEM_EVENT("ldlat-loads", "cpu/mem-loads,ldlat=%u/P", "mem-loads"),
> +	PERF_MEM_EVENT("ldlat-stores", "cpu/mem-stores/P", "mem-stores"),
> +};
> +
> +static char mem_loads_name[100];
> +static bool mem_loads_name__init;
> +
> +char *perf_mem_events__name(int i)
> +{
> +	if (i == PERF_MEM_EVENTS__LOAD) {
> +		if (!mem_loads_name__init) {
> +			mem_loads_name__init = true;
> +			scnprintf(mem_loads_name, sizeof(mem_loads_name),
> +				  perf_mem_events[i].name,
> +				  perf_mem_events__loads_ldlat);
> +		}
> +		return mem_loads_name;
> +	}
> +
> +	return (char *)perf_mem_events[i].name;
> +}
> diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
> index 93f74d8..1ffefd3 100644
> --- a/tools/perf/util/mem-events.c
> +++ b/tools/perf/util/mem-events.c
> @@ -15,31 +15,13 @@
>  
>  unsigned int perf_mem_events__loads_ldlat = 30;
>  
> -#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
> -
> -struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
> -	E("ldlat-loads",	"cpu/mem-loads,ldlat=%u/P",	"mem-loads"),
> -	E("ldlat-stores",	"cpu/mem-stores/P",		"mem-stores"),
> +struct perf_mem_event __weak perf_mem_events[PERF_MEM_EVENTS__MAX] = {
> +	PERF_MEM_EVENT("ldlat-loads", "cpu/mem-loads/P", "mem-loads"),
> +	PERF_MEM_EVENT("ldlat-stores", "cpu/mem-stores/P", "mem-stores"),
>  };

I dont think perf_mem_events array needs to be overloaded as well,
the perf_mem_events__name function should be enough no?

thanks,
jirka