| 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
| ||
|
Message-ID: <ad0b8f56-8613-44d1-b37a-d05e2a4f6529@linux.intel.com>
Date: Thu, 15 Aug 2024 14:42:20 +0800
From: "Mi, Dapeng" <dapeng1.mi@...ux.intel.com>
To: Arnaldo Carvalho de Melo <acme@...nel.org>
Cc: Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...hat.com>,
Namhyung Kim <namhyung@...nel.org>, Ian Rogers <irogers@...gle.com>,
Adrian Hunter <adrian.hunter@...el.com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Kan Liang <kan.liang@...ux.intel.com>, linux-perf-users@...r.kernel.org,
linux-kernel@...r.kernel.org, Yongwei Ma <yongwei.ma@...el.com>,
Dapeng Mi <dapeng1.mi@...el.com>
Subject: Re: [Patch v3 1/5] perf x86/topdown: Complete topdown slots/metrics
events check
On 8/12/2024 9:41 PM, Arnaldo Carvalho de Melo wrote:
> On Fri, Jul 12, 2024 at 05:03:35PM +0000, Dapeng Mi wrote:
>> It's not complete to check whether an event is a topdown slots or
>> topdown metrics event by only comparing the event name since user
>> may assign the event by RAW format, e.g.
>>
>> perf stat -e '{instructions,cpu/r400/,cpu/r8300/}' sleep 1
>>
>> Performance counter stats for 'sleep 1':
>>
>> <not counted> instructions
>> <not counted> cpu/r400/
>> <not supported> cpu/r8300/
>>
>> 1.002917796 seconds time elapsed
>>
>> 0.002955000 seconds user
>> 0.000000000 seconds sys
>>
>> The RAW format slots and topdown-be-bound events are not recognized and
>> not regroup the events, and eventually cause error.
>>
>> Thus add two helpers arch_is_topdown_slots()/arch_is_topdown_metrics()
>> to detect whether an event is topdown slots/metrics event by comparing
>> the event config directly, and use these two helpers to replace the
>> original event name comparisons.
> Looks ok, I made a comment below, please take a look
>
>> Signed-off-by: Dapeng Mi <dapeng1.mi@...ux.intel.com>
>> ---
>> tools/perf/arch/x86/util/evlist.c | 8 ++---
>> tools/perf/arch/x86/util/evsel.c | 3 +-
>> tools/perf/arch/x86/util/topdown.c | 48 +++++++++++++++++++++++++++++-
>> tools/perf/arch/x86/util/topdown.h | 2 ++
>> 4 files changed, 55 insertions(+), 6 deletions(-)
>>
>> diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
>> index b1ce0c52d88d..332e8907f43e 100644
>> --- a/tools/perf/arch/x86/util/evlist.c
>> +++ b/tools/perf/arch/x86/util/evlist.c
>> @@ -78,14 +78,14 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
>> if (topdown_sys_has_perf_metrics() &&
>> (arch_evsel__must_be_in_group(lhs) || arch_evsel__must_be_in_group(rhs))) {
>> /* Ensure the topdown slots comes first. */
>> - if (strcasestr(lhs->name, "slots") && !strcasestr(lhs->name, "uops_retired.slots"))
>> + if (arch_is_topdown_slots(lhs))
>> return -1;
>> - if (strcasestr(rhs->name, "slots") && !strcasestr(rhs->name, "uops_retired.slots"))
>> + if (arch_is_topdown_slots(rhs))
>> return 1;
>> /* Followed by topdown events. */
>> - if (strcasestr(lhs->name, "topdown") && !strcasestr(rhs->name, "topdown"))
>> + if (arch_is_topdown_metrics(lhs) && !arch_is_topdown_metrics(rhs))
>> return -1;
>> - if (!strcasestr(lhs->name, "topdown") && strcasestr(rhs->name, "topdown"))
>> + if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs))
>> return 1;
>> }
>>
>> diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
>> index 090d0f371891..181f2ba0bb2a 100644
>> --- a/tools/perf/arch/x86/util/evsel.c
>> +++ b/tools/perf/arch/x86/util/evsel.c
>> @@ -6,6 +6,7 @@
>> #include "util/pmu.h"
>> #include "util/pmus.h"
>> #include "linux/string.h"
>> +#include "topdown.h"
>> #include "evsel.h"
>> #include "util/debug.h"
>> #include "env.h"
>> @@ -44,7 +45,7 @@ bool arch_evsel__must_be_in_group(const struct evsel *evsel)
>> strcasestr(evsel->name, "uops_retired.slots"))
>> return false;
>>
>> - return strcasestr(evsel->name, "topdown") || strcasestr(evsel->name, "slots");
>> + return arch_is_topdown_metrics(evsel) || arch_is_topdown_slots(evsel);
>> }
>>
>> int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
>> diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c
>> index 3f9a267d4501..49f25d67ed77 100644
>> --- a/tools/perf/arch/x86/util/topdown.c
>> +++ b/tools/perf/arch/x86/util/topdown.c
>> @@ -32,6 +32,52 @@ bool topdown_sys_has_perf_metrics(void)
>> }
>>
>> #define TOPDOWN_SLOTS 0x0400
>> +bool arch_is_topdown_slots(const struct evsel *evsel)
>> +{
>> + if (evsel->core.attr.config == TOPDOWN_SLOTS)
>> + return true;
>> +
>> + return false;
>> +}
>> +
>> +static int compare_topdown_event(void *vstate, struct pmu_event_info *info)
>> +{
>> + int *config = vstate;
>> + int event = 0;
>> + int umask = 0;
>> + char *str;
>> +
>> + if (!strcasestr(info->name, "topdown"))
>> + return 0;
>> +
>> + str = strcasestr(info->str, "event=");
>> + if (str)
>> + sscanf(str, "event=%x", &event);
>> +
>> + str = strcasestr(info->str, "umask=");
>> + if (str)
>> + sscanf(str, "umask=%x", &umask);
>> +
>> + if (event == 0 && *config == (event | umask << 8))
>> + return 1;
>> +
>> + return 0;
>> +}
>> +
>> +bool arch_is_topdown_metrics(const struct evsel *evsel)
>> +{
>> + struct perf_pmu *pmu = evsel__find_pmu(evsel);
>> + int config = evsel->core.attr.config;
> Humm, can we cache this information? I.e. have some evsel->is_topdown:1
> bit to avoid having to traverse all events if we call this multiple
> times for the same evsel?
Arnaldo, I tried to add a variable in evsel structure to represent if the
evsel is a topdown metrics event, but unfortunately the helper argument
"evsel" has "const" qualifier, it forces the "evsel" structure can't be
modified. If we want to add this optimization, the entire call-chain
functions have to be modified and this would reduce the security of code as
well. Since this helper is not in a performance critical patch, I suppose
it won't introduce too much performance hit as the traverse. I would drop
this optimization and keep the original code.
>
> - Arnaldo
>
>> + if (!pmu || !pmu->is_core)
>> + return false;
>> +
>> + if (perf_pmu__for_each_event(pmu, false, &config,
>> + compare_topdown_event))
>> + return true;
>> +
>> + return false;
>> +}
>>
>> /*
>> * Check whether a topdown group supports sample-read.
>> @@ -44,7 +90,7 @@ bool arch_topdown_sample_read(struct evsel *leader)
>> if (!evsel__sys_has_perf_metrics(leader))
>> return false;
>>
>> - if (leader->core.attr.config == TOPDOWN_SLOTS)
>> + if (arch_is_topdown_slots(leader))
>> return true;
>>
>> return false;
>> diff --git a/tools/perf/arch/x86/util/topdown.h b/tools/perf/arch/x86/util/topdown.h
>> index 46bf9273e572..1bae9b1822d7 100644
>> --- a/tools/perf/arch/x86/util/topdown.h
>> +++ b/tools/perf/arch/x86/util/topdown.h
>> @@ -3,5 +3,7 @@
>> #define _TOPDOWN_H 1
>>
>> bool topdown_sys_has_perf_metrics(void);
>> +bool arch_is_topdown_slots(const struct evsel *evsel);
>> +bool arch_is_topdown_metrics(const struct evsel *evsel);
>>
>> #endif
>> --
>> 2.40.1
>>
Powered by blists - more mailing lists