linux-kernel - Re: [PATCH v12 05/16] perf record: Introduce thread local variable

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]

Date:   Sun, 5 Dec 2021 16:14:32 +0100
From:   Jiri Olsa <jolsa@...hat.com>
To:     Alexey Bayduraev <alexey.v.bayduraev@...ux.intel.com>
Cc:     Arnaldo Carvalho de Melo <acme@...nel.org>,
        Namhyung Kim <namhyung@...nel.org>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        linux-kernel <linux-kernel@...r.kernel.org>,
        Andi Kleen <ak@...ux.intel.com>,
        Adrian Hunter <adrian.hunter@...el.com>,
        Alexander Antonov <alexander.antonov@...ux.intel.com>,
        Alexei Budankov <abudankov@...wei.com>,
        Riccardo Mancini <rickyman7@...il.com>
Subject: Re: [PATCH v12 05/16] perf record: Introduce thread local variable

On Tue, Nov 23, 2021 at 05:08:01PM +0300, Alexey Bayduraev wrote:

SNIP

>  
> +	if (record__start_threads(rec))
> +		goto out_free_threads;
> +
>  	/*
>  	 * When perf is starting the traced process, all the events
>  	 * (apart from group members) have enable_on_exec=1 set,
> @@ -2122,7 +2175,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
>  	trigger_ready(&switch_output_trigger);
>  	perf_hooks__invoke_record_start();
>  	for (;;) {
> -		unsigned long long hits = rec->samples;
> +		unsigned long long hits = thread->samples;
>  
>  		/*
>  		 * rec->evlist->bkw_mmap_state is possible to be
> @@ -2176,8 +2229,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
>  
>  			if (!quiet)
>  				fprintf(stderr, "[ perf record: dump data: Woken up %ld times ]\n",
> -					waking);
> -			waking = 0;
> +					record__waking(rec));
> +			thread->waking = 0;
>  			fd = record__switch_output(rec, false);
>  			if (fd < 0) {
>  				pr_err("Failed to switch to new file\n");
> @@ -2191,20 +2244,24 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
>  				alarm(rec->switch_output.time);
>  		}
>  
> -		if (hits == rec->samples) {
> +		if (hits == thread->samples) {
>  			if (done || draining)
>  				break;
> -			err = evlist__poll(rec->evlist, -1);
> +			err = fdarray__poll(&thread->pollfd, -1);
>  			/*
>  			 * Propagate error, only if there's any. Ignore positive
>  			 * number of returned events and interrupt error.
>  			 */
>  			if (err > 0 || (err < 0 && errno == EINTR))
>  				err = 0;
> -			waking++;
> +			thread->waking++;
>  
> -			if (evlist__filter_pollfd(rec->evlist, POLLERR | POLLHUP) == 0)
> +			if (fdarray__filter(&thread->pollfd, POLLERR | POLLHUP,
> +					    record__thread_munmap_filtered, NULL) == 0)
>  				draining = true;
> +
> +			evlist__ctlfd_update(rec->evlist,
> +				&thread->pollfd.entries[thread->ctlfd_pos]);

hm, why is this needed? we only switch to record_thread data, right?
there should not be any processing change

jirka

>  		}
>  
>  		if (evlist__ctlfd_process(rec->evlist, &cmd) > 0) {
> @@ -2258,15 +2315,18 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
>  	}
>  
>  	if (!quiet)
> -		fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
> +		fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n",
> +			record__waking(rec));
>  
>  	if (target__none(&rec->opts.target))
>  		record__synthesize_workload(rec, true);
>  
>  out_child:
> -	evlist__finalize_ctlfd(rec->evlist);
> +	record__stop_threads(rec);
>  	record__mmap_read_all(rec, true);
> +out_free_threads:
>  	record__free_thread_data(rec);
> +	evlist__finalize_ctlfd(rec->evlist);
>  	record__aio_mmap_read_sync(rec);
>  
>  	if (rec->session->bytes_transferred && rec->session->bytes_compressed) {
> @@ -3158,17 +3218,6 @@ int cmd_record(int argc, const char **argv)
>  
>  	symbol__init(NULL);
>  
> -	if (rec->opts.affinity != PERF_AFFINITY_SYS) {
> -		rec->affinity_mask.nbits = cpu__max_cpu();
> -		rec->affinity_mask.bits = bitmap_zalloc(rec->affinity_mask.nbits);
> -		if (!rec->affinity_mask.bits) {
> -			pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits);
> -			err = -ENOMEM;
> -			goto out_opts;
> -		}
> -		pr_debug2("thread mask[%zd]: empty\n", rec->affinity_mask.nbits);
> -	}
> -
>  	err = record__auxtrace_init(rec);
>  	if (err)
>  		goto out;
> @@ -3313,7 +3362,6 @@ int cmd_record(int argc, const char **argv)
>  
>  	err = __cmd_record(&record, argc, argv);
>  out:
> -	bitmap_free(rec->affinity_mask.bits);
>  	evlist__delete(rec->evlist);
>  	symbol__exit();
>  	auxtrace_record__free(rec->itr);
> -- 
> 2.19.0
>