linux-kernel - Re: [PATCH 3/5] perf record: Read and inject LOST

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: <86ca3041-3327-622c-1c23-67fc6af412f6@intel.com>
Date:   Thu, 1 Sep 2022 14:22:45 +0300
From:   Adrian Hunter <adrian.hunter@...el.com>
To:     Namhyung Kim <namhyung@...nel.org>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Jiri Olsa <jolsa@...nel.org>
Cc:     Ingo Molnar <mingo@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        LKML <linux-kernel@...r.kernel.org>,
        Ian Rogers <irogers@...gle.com>,
        linux-perf-users@...r.kernel.org
Subject: Re: [PATCH 3/5] perf record: Read and inject LOST_SAMPLES events

On 1/09/22 00:03, Namhyung Kim wrote:
> When there are lost samples, it can read the number of PERF_FORMAT_LOST and
> convert it to PERF_RECORD_LOST_SAMPLES and write to the data file at the end.
> 
> Signed-off-by: Namhyung Kim <namhyung@...nel.org>
> ---
>  tools/perf/builtin-record.c | 60 +++++++++++++++++++++++++++++++++++++
>  1 file changed, 60 insertions(+)
> 
> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> index bce8c941d558..cb9881543a07 100644
> --- a/tools/perf/builtin-record.c
> +++ b/tools/perf/builtin-record.c
> @@ -10,6 +10,7 @@
>  
>  #include "util/build-id.h"
>  #include <subcmd/parse-options.h>
> +#include <internal/xyarray.h>
>  #include "util/parse-events.h"
>  #include "util/config.h"
>  
> @@ -1852,6 +1853,64 @@ record__switch_output(struct record *rec, bool at_exit)
>  	return fd;
>  }
>  
> +static void __record__read_lost_samples(struct record *rec, struct evsel *evsel,
> +					struct perf_record_lost_samples *lost,
> +					int size, int cpu_idx, int thread_idx)
> +{
> +	struct perf_counts_values count;
> +	struct perf_sample_id *sid;
> +	struct perf_sample sample = {};
> +
> +	if (perf_evsel__read(&evsel->core, cpu_idx, thread_idx, &count) < 0) {
> +		pr_err("read LOST count failed\n");
> +		return;
> +	}
> +
> +	if (count.lost == 0)
> +		return;
> +
> +	lost->lost = count.lost;
> +	if (evsel->core.ids) {
> +		sid = xyarray__entry(evsel->core.sample_id, cpu_idx, thread_idx);
> +		sample.id = sid->id;
> +	}
> +
> +	perf_event__synthesize_id_sample((void *)(lost + 1),
> +					 evsel->core.attr.sample_type, &sample);

The ID sample size can vary with sample_type and is not necessarily the same as
machine->id_hdr_size.

The following might be more robust:

	id_hdr_size = perf_event__synthesize_id_sample((void *)(lost + 1), evsel->core.attr.sample_type, &sample);
	lost->header.size = sizeof(*lost) + id_hdr_size;

> +	record__write(rec, NULL, lost, size);
> +}
> +
> +static void record__read_lost_samples(struct record *rec)
> +{
> +	struct perf_session *session = rec->session;
> +	struct machine *machine = &session->machines.host;
> +	struct perf_record_lost_samples *lost;
> +	struct evsel *evsel;
> +	int size = sizeof(*lost) + machine->id_hdr_size;

  -	int size = sizeof(*lost) + machine->id_hdr_size;

> +
> +	lost = zalloc(size);

	lost = zalloc(PERF_SAMPLE_MAX_SIZE);


> +	lost->header.type = PERF_RECORD_LOST_SAMPLES;
> +	lost->header.size = size;

  -	lost->header.size = size;

> +
> +	evlist__for_each_entry(session->evlist, evsel) {
> +		struct xyarray *xy = evsel->core.sample_id;
> +
> +		if (xyarray__max_x(evsel->core.fd) != xyarray__max_x(xy) ||
> +		    xyarray__max_y(evsel->core.fd) != xyarray__max_y(xy)) {
> +			pr_debug("Unmatched FD vs. sample ID: skip reading LOST count\n");
> +			continue;
> +		}
> +
> +		for (int x = 0; x < xyarray__max_x(xy); x++) {
> +			for (int y = 0; y < xyarray__max_y(xy); y++) {
> +				__record__read_lost_samples(rec, evsel, lost,
> +							    size, x, y);
> +			}
> +		}
> +	}
> +
> +}
> +
>  static volatile int workload_exec_errno;
>  
>  /*
> @@ -2710,6 +2769,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
>  	if (rec->off_cpu)
>  		rec->bytes_written += off_cpu_write(rec->session);
>  
> +	record__read_lost_samples(rec);
>  	record__synthesize(rec, true);
>  	/* this will be recalculated during process_buildids() */
>  	rec->samples = 0;