From: Adrian Hunter <adrian.hunter@intel.com>
To: Namhyung Kim <namhyung@kernel.org>, Ian Rogers <irogers@google.com>
Cc: "Peter Zijlstra" <peterz@infradead.org>,
"Ingo Molnar" <mingo@redhat.com>,
"Arnaldo Carvalho de Melo" <acme@kernel.org>,
"Mark Rutland" <mark.rutland@arm.com>,
"Alexander Shishkin" <alexander.shishkin@linux.intel.com>,
"Jiri Olsa" <jolsa@kernel.org>,
"Thomas Gleixner" <tglx@linutronix.de>,
"Darren Hart" <dvhart@infradead.org>,
"Davidlohr Bueso" <dave@stgolabs.net>,
"André Almeida" <andrealmeid@igalia.com>,
"Nathan Chancellor" <nathan@kernel.org>,
"Nick Desaulniers" <ndesaulniers@google.com>,
"Tom Rix" <trix@redhat.com>, "Weiguo Li" <liwg06@foxmail.com>,
"Athira Rajeev" <atrajeev@linux.vnet.ibm.com>,
"Thomas Richter" <tmricht@linux.ibm.com>,
"Ravi Bangoria" <ravi.bangoria@amd.com>,
"Dario Petrillo" <dario.pk1@gmail.com>,
Hewenliang <hewenliang4@huawei.com>,
yaowenbin <yaowenbin1@huawei.com>,
"Wenyu Liu" <liuwenyu7@huawei.com>,
"Song Liu" <songliubraving@fb.com>,
"Andrii Nakryiko" <andrii@kernel.org>,
"Dave Marchevsky" <davemarchevsky@fb.com>,
"Leo Yan" <leo.yan@linaro.org>,
"Kim Phillips" <kim.phillips@amd.com>,
"Pavithra Gurushankar" <gpavithrasha@gmail.com>,
"Alexandre Truong" <alexandre.truong@arm.com>,
"Quentin Monnet" <quentin@isovalent.com>,
"William Cohen" <wcohen@redhat.com>,
"Andres Freund" <andres@anarazel.de>,
"Martin Liška" <mliska@suse.cz>,
"Colin Ian King" <colin.king@intel.com>,
"James Clark" <james.clark@arm.com>,
"Fangrui Song" <maskray@google.com>,
"Stephane Eranian" <eranian@google.com>,
"Kajol Jain" <kjain@linux.ibm.com>,
"Alexey Bayduraev" <alexey.v.bayduraev@linux.intel.com>,
"Riccardo Mancini" <rickyman7@gmail.com>,
"Andi Kleen" <ak@linux.intel.com>,
"Masami Hiramatsu" <mhiramat@kernel.org>,
"Zechuan Chen" <chenzechuan1@huawei.com>,
"Jason Wang" <wangborong@cdjrlc.com>,
"Christophe JAILLET" <christophe.jaillet@wanadoo.fr>,
"Remi Bernon" <rbernon@codeweavers.com>,
linux-kernel <linux-kernel@vger.kernel.org>,
linux-perf-users <linux-perf-users@vger.kernel.org>,
bpf <bpf@vger.kernel.org>,
llvm@lists.linux.dev
Subject: Re: [PATCH v3 16/18] perf sched: Fixes for thread safety analysis
Date: Fri, 26 Aug 2022 22:35:53 +0300 [thread overview]
Message-ID: <5a0b4083-084a-56b3-a6a1-0fad1100a316@intel.com> (raw)
In-Reply-To: <CAM9d7cgcLHYded1w4h22F_KWcHUpuxqak7Ny02Awj1WDFLynDQ@mail.gmail.com>
On 26/08/22 21:26, Namhyung Kim wrote:
> On Fri, Aug 26, 2022 at 10:48 AM Ian Rogers <irogers@google.com> wrote:
>>
>> On Fri, Aug 26, 2022 at 10:41 AM Adrian Hunter <adrian.hunter@intel.com> wrote:
>>>
>>> On 26/08/22 19:06, Ian Rogers wrote:
>>>> On Fri, Aug 26, 2022 at 5:12 AM Adrian Hunter <adrian.hunter@intel.com> wrote:
>>>>>
>>>>> On 24/08/22 18:38, Ian Rogers wrote:
>>>>>> Add annotations to describe lock behavior. Add unlocks so that mutexes
>>>>>> aren't conditionally held on exit from perf_sched__replay. Add an exit
>>>>>> variable so that thread_func can terminate, rather than leaving the
>>>>>> threads blocked on mutexes.
>>>>>>
>>>>>> Signed-off-by: Ian Rogers <irogers@google.com>
>>>>>> ---
>>>>>> tools/perf/builtin-sched.c | 46 ++++++++++++++++++++++++--------------
>>>>>> 1 file changed, 29 insertions(+), 17 deletions(-)
>>>>>>
>>>>>> diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
>>>>>> index 7e4006d6b8bc..b483ff0d432e 100644
>>>>>> --- a/tools/perf/builtin-sched.c
>>>>>> +++ b/tools/perf/builtin-sched.c
>>>>>> @@ -246,6 +246,7 @@ struct perf_sched {
>>>>>> const char *time_str;
>>>>>> struct perf_time_interval ptime;
>>>>>> struct perf_time_interval hist_time;
>>>>>> + volatile bool thread_funcs_exit;
>>>>>> };
>>>>>>
>>>>>> /* per thread run time data */
>>>>>> @@ -633,31 +634,34 @@ static void *thread_func(void *ctx)
>>>>>> prctl(PR_SET_NAME, comm2);
>>>>>> if (fd < 0)
>>>>>> return NULL;
>>>>>> -again:
>>>>>> - ret = sem_post(&this_task->ready_for_work);
>>>>>> - BUG_ON(ret);
>>>>>> - mutex_lock(&sched->start_work_mutex);
>>>>>> - mutex_unlock(&sched->start_work_mutex);
>>>>>>
>>>>>> - cpu_usage_0 = get_cpu_usage_nsec_self(fd);
>>>>>> + while (!sched->thread_funcs_exit) {
>>>>>> + ret = sem_post(&this_task->ready_for_work);
>>>>>> + BUG_ON(ret);
>>>>>> + mutex_lock(&sched->start_work_mutex);
>>>>>> + mutex_unlock(&sched->start_work_mutex);
>>>>>>
>>>>>> - for (i = 0; i < this_task->nr_events; i++) {
>>>>>> - this_task->curr_event = i;
>>>>>> - perf_sched__process_event(sched, this_task->atoms[i]);
>>>>>> - }
>>>>>> + cpu_usage_0 = get_cpu_usage_nsec_self(fd);
>>>>>>
>>>>>> - cpu_usage_1 = get_cpu_usage_nsec_self(fd);
>>>>>> - this_task->cpu_usage = cpu_usage_1 - cpu_usage_0;
>>>>>> - ret = sem_post(&this_task->work_done_sem);
>>>>>> - BUG_ON(ret);
>>>>>> + for (i = 0; i < this_task->nr_events; i++) {
>>>>>> + this_task->curr_event = i;
>>>>>> + perf_sched__process_event(sched, this_task->atoms[i]);
>>>>>> + }
>>>>>>
>>>>>> - mutex_lock(&sched->work_done_wait_mutex);
>>>>>> - mutex_unlock(&sched->work_done_wait_mutex);
>>>>>> + cpu_usage_1 = get_cpu_usage_nsec_self(fd);
>>>>>> + this_task->cpu_usage = cpu_usage_1 - cpu_usage_0;
>>>>>> + ret = sem_post(&this_task->work_done_sem);
>>>>>> + BUG_ON(ret);
>>>>>>
>>>>>> - goto again;
>>>>>> + mutex_lock(&sched->work_done_wait_mutex);
>>>>>> + mutex_unlock(&sched->work_done_wait_mutex);
>>>>>> + }
>>>>>> + return NULL;
>>>>>> }
>>>>>>
>>>>>> static void create_tasks(struct perf_sched *sched)
>>>>>> + EXCLUSIVE_LOCK_FUNCTION(sched->start_work_mutex)
>>>>>> + EXCLUSIVE_LOCK_FUNCTION(sched->work_done_wait_mutex)
>>>>>> {
>>>>>> struct task_desc *task;
>>>>>> pthread_attr_t attr;
>>>>>> @@ -687,6 +691,8 @@ static void create_tasks(struct perf_sched *sched)
>>>>>> }
>>>>>>
>>>>>> static void wait_for_tasks(struct perf_sched *sched)
>>>>>> + EXCLUSIVE_LOCKS_REQUIRED(sched->work_done_wait_mutex)
>>>>>> + EXCLUSIVE_LOCKS_REQUIRED(sched->start_work_mutex)
>>>>>> {
>>>>>> u64 cpu_usage_0, cpu_usage_1;
>>>>>> struct task_desc *task;
>>>>>> @@ -738,6 +744,8 @@ static void wait_for_tasks(struct perf_sched *sched)
>>>>>> }
>>>>>>
>>>>>> static void run_one_test(struct perf_sched *sched)
>>>>>> + EXCLUSIVE_LOCKS_REQUIRED(sched->work_done_wait_mutex)
>>>>>> + EXCLUSIVE_LOCKS_REQUIRED(sched->start_work_mutex)
>>>>>> {
>>>>>> u64 T0, T1, delta, avg_delta, fluct;
>>>>>>
>>>>>> @@ -3309,11 +3317,15 @@ static int perf_sched__replay(struct perf_sched *sched)
>>>>>> print_task_traces(sched);
>>>>>> add_cross_task_wakeups(sched);
>>>>>>
>>>>>> + sched->thread_funcs_exit = false;
>>>>>> create_tasks(sched);
>>>>>> printf("------------------------------------------------------------\n");
>>>>>> for (i = 0; i < sched->replay_repeat; i++)
>>>>>> run_one_test(sched);
>>>>>>
>>>>>> + sched->thread_funcs_exit = true;
>>>>>> + mutex_unlock(&sched->start_work_mutex);
>>>>>> + mutex_unlock(&sched->work_done_wait_mutex);
>>>>>
>>>>> I think you still need to wait for the threads to exit before
>>>>> destroying the mutexes.
>>>>
>>>> This is a pre-existing issue and beyond the scope of this patch set.
>>>
>>> You added the mutex_destroy functions in patch 8, so it is still
>>> fallout from that.
>>
>> In the previous code the threads were blocked on mutexes that were
>> stack allocated and the stack memory went away. You are correct to say
>> that to those locks I added an init and destroy call. The lifetime of
>> the mutex was wrong previously and remains wrong in this change.
>
> I think you fixed the lifetime issue with sched->thread_funcs_exit here.
> All you need to do is calling pthread_join() after the mutex_unlock, no?
Like this maybe:
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index b483ff0d432e..8090c1218855 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -3326,6 +3326,13 @@ static int perf_sched__replay(struct perf_sched *sched)
sched->thread_funcs_exit = true;
mutex_unlock(&sched->start_work_mutex);
mutex_unlock(&sched->work_done_wait_mutex);
+ /* Get rid of threads so they won't be upset by mutex destruction */
+ for (i = 0; i < sched->nr_tasks; i++) {
+ int err = pthread_join(sched->tasks[i]->thread, NULL);
+
+ if (err)
+ pr_err("pthread_join() failed for task nr %lu, error %d\n", i, err);
+ }
return 0;
}
next prev parent reply other threads:[~2022-08-26 19:36 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-24 15:38 [PATCH v3 00/18] Mutex wrapper, locking and memory leak fixes Ian Rogers
2022-08-24 15:38 ` [PATCH v3 01/18] perf mutex: Wrapped usage of mutex and cond Ian Rogers
2022-08-26 8:49 ` Adrian Hunter
2022-08-24 15:38 ` [PATCH v3 02/18] perf bench: Update use of pthread mutex/cond Ian Rogers
2022-08-24 15:38 ` [PATCH v3 03/18] perf tests: Avoid pthread.h inclusion Ian Rogers
2022-08-24 15:38 ` [PATCH v3 04/18] perf hist: Update use of pthread mutex Ian Rogers
2022-08-24 15:38 ` [PATCH v3 05/18] perf bpf: Remove unused pthread.h include Ian Rogers
2022-08-24 15:38 ` [PATCH v3 06/18] perf lock: " Ian Rogers
2022-08-24 15:38 ` [PATCH v3 07/18] perf record: Update use of pthread mutex Ian Rogers
2022-08-24 15:38 ` [PATCH v3 08/18] perf sched: " Ian Rogers
2022-08-24 15:38 ` [PATCH v3 09/18] perf ui: " Ian Rogers
2022-08-26 10:11 ` Adrian Hunter
2022-08-26 16:01 ` Ian Rogers
2022-08-26 10:24 ` Adrian Hunter
2022-08-26 16:02 ` Ian Rogers
2022-08-26 17:22 ` Adrian Hunter
2022-08-26 17:45 ` Ian Rogers
2022-08-26 18:52 ` Adrian Hunter
2022-08-26 19:00 ` Namhyung Kim
2022-08-26 19:20 ` Adrian Hunter
2022-08-26 20:40 ` Namhyung Kim
2022-08-26 20:52 ` Ian Rogers
2022-08-27 7:11 ` Adrian Hunter
2022-08-24 15:38 ` [PATCH v3 10/18] perf mmap: Remove unnecessary pthread.h include Ian Rogers
2022-08-24 15:38 ` [PATCH v3 11/18] perf dso: Update use of pthread mutex Ian Rogers
2022-08-26 10:37 ` Adrian Hunter
2022-08-26 16:05 ` Ian Rogers
2022-08-26 17:34 ` Adrian Hunter
2022-08-26 17:46 ` Ian Rogers
2022-08-24 15:38 ` [PATCH v3 12/18] perf annotate: " Ian Rogers
2022-08-24 15:38 ` [PATCH v3 13/18] perf top: " Ian Rogers
2022-08-24 15:38 ` [PATCH v3 14/18] perf dso: Hold lock when accessing nsinfo Ian Rogers
2022-08-24 15:38 ` [PATCH v3 15/18] perf mutex: Add thread safety annotations Ian Rogers
2022-08-26 11:12 ` Adrian Hunter
2022-08-26 16:45 ` Arnaldo Carvalho de Melo
2022-08-26 17:00 ` Ian Rogers
2022-08-26 19:13 ` Arnaldo Carvalho de Melo
2022-08-24 15:38 ` [PATCH v3 16/18] perf sched: Fixes for thread safety analysis Ian Rogers
2022-08-26 12:12 ` Adrian Hunter
2022-08-26 16:06 ` Ian Rogers
2022-08-26 17:41 ` Adrian Hunter
2022-08-26 17:48 ` Ian Rogers
2022-08-26 18:26 ` Namhyung Kim
2022-08-26 19:35 ` Adrian Hunter [this message]
2022-08-26 20:48 ` Namhyung Kim
2022-08-24 15:39 ` [PATCH v3 17/18] perf top: " Ian Rogers
2022-08-24 15:39 ` [PATCH v3 18/18] perf build: Enable -Wthread-safety with clang Ian Rogers
[not found] ` <CA+JHD906M0truH7wPNZ=eJwdCA=qLhYDonUx_ZQBwJYpiX1hNg@mail.gmail.com>
2022-08-25 16:14 ` [PATCH v3 00/18] Mutex wrapper, locking and memory leak fixes Adrian Hunter
2022-08-26 12:36 ` Adrian Hunter
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=5a0b4083-084a-56b3-a6a1-0fad1100a316@intel.com \
--to=adrian.hunter@intel.com \
--cc=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=alexandre.truong@arm.com \
--cc=alexey.v.bayduraev@linux.intel.com \
--cc=andrealmeid@igalia.com \
--cc=andres@anarazel.de \
--cc=andrii@kernel.org \
--cc=atrajeev@linux.vnet.ibm.com \
--cc=bpf@vger.kernel.org \
--cc=chenzechuan1@huawei.com \
--cc=christophe.jaillet@wanadoo.fr \
--cc=colin.king@intel.com \
--cc=dario.pk1@gmail.com \
--cc=dave@stgolabs.net \
--cc=davemarchevsky@fb.com \
--cc=dvhart@infradead.org \
--cc=eranian@google.com \
--cc=gpavithrasha@gmail.com \
--cc=hewenliang4@huawei.com \
--cc=irogers@google.com \
--cc=james.clark@arm.com \
--cc=jolsa@kernel.org \
--cc=kim.phillips@amd.com \
--cc=kjain@linux.ibm.com \
--cc=leo.yan@linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=liuwenyu7@huawei.com \
--cc=liwg06@foxmail.com \
--cc=llvm@lists.linux.dev \
--cc=mark.rutland@arm.com \
--cc=maskray@google.com \
--cc=mhiramat@kernel.org \
--cc=mingo@redhat.com \
--cc=mliska@suse.cz \
--cc=namhyung@kernel.org \
--cc=nathan@kernel.org \
--cc=ndesaulniers@google.com \
--cc=peterz@infradead.org \
--cc=quentin@isovalent.com \
--cc=ravi.bangoria@amd.com \
--cc=rbernon@codeweavers.com \
--cc=rickyman7@gmail.com \
--cc=songliubraving@fb.com \
--cc=tglx@linutronix.de \
--cc=tmricht@linux.ibm.com \
--cc=trix@redhat.com \
--cc=wangborong@cdjrlc.com \
--cc=wcohen@redhat.com \
--cc=yaowenbin1@huawei.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