[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20220516152022.00001ab9@Huawei.com>
Date: Mon, 16 May 2022 15:20:22 +0100
From: Jonathan Cameron <Jonathan.Cameron@...wei.com>
To: Yicong Yang <yangyicong@...ilicon.com>
CC: <gregkh@...uxfoundation.org>, <alexander.shishkin@...ux.intel.com>,
<leo.yan@...aro.org>, <james.clark@....com>, <will@...nel.org>,
<robin.murphy@....com>, <acme@...nel.org>, <john.garry@...wei.com>,
<helgaas@...nel.org>, <lorenzo.pieralisi@....com>,
<mathieu.poirier@...aro.org>, <suzuki.poulose@....com>,
<mark.rutland@....com>, <joro@...tes.org>,
<shameerali.kolothum.thodi@...wei.com>, <peterz@...radead.org>,
<mingo@...hat.com>, <linux-kernel@...r.kernel.org>,
<linux-arm-kernel@...ts.infradead.org>,
<linux-pci@...r.kernel.org>, <linux-perf-users@...r.kernel.org>,
<iommu@...ts.linux-foundation.org>, <prime.zeng@...wei.com>,
<liuqi115@...wei.com>, <zhangshaokun@...ilicon.com>,
<linuxarm@...wei.com>
Subject: Re: [PATCH v8 5/8] perf tool: Add support for HiSilicon PCIe Tune
and Trace device driver
On Mon, 16 May 2022 20:52:20 +0800
Yicong Yang <yangyicong@...ilicon.com> wrote:
> From: Qi Liu <liuqi115@...wei.com>
>
> HiSilicon PCIe tune and trace device (PTT) could dynamically tune
> the PCIe link's events, and trace the TLP headers).
>
> This patch add support for PTT device in perf tool, so users could
> use 'perf record' to get TLP headers trace data.
>
> Signed-off-by: Qi Liu <liuqi115@...wei.com>
> Signed-off-by: Yicong Yang <yangyicong@...ilicon.com>
One query inline.
> diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
> index 384c7cfda0fd..297fffedf45e 100644
> --- a/tools/perf/arch/arm/util/auxtrace.c
> +++ b/tools/perf/arch/arm/util/auxtrace.c
...
> static struct perf_pmu *find_pmu_for_event(struct perf_pmu **pmus,
> int pmu_nr, struct evsel *evsel)
> {
> @@ -71,17 +120,21 @@ struct auxtrace_record
> {
> struct perf_pmu *cs_etm_pmu = NULL;
> struct perf_pmu **arm_spe_pmus = NULL;
> + struct perf_pmu **hisi_ptt_pmus = NULL;
> struct evsel *evsel;
> struct perf_pmu *found_etm = NULL;
> struct perf_pmu *found_spe = NULL;
> + struct perf_pmu *found_ptt = NULL;
> int auxtrace_event_cnt = 0;
> int nr_spes = 0;
> + int nr_ptts = 0;
>
> if (!evlist)
> return NULL;
>
> cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME);
> arm_spe_pmus = find_all_arm_spe_pmus(&nr_spes, err);
> + hisi_ptt_pmus = find_all_hisi_ptt_pmus(&nr_ptts, err);
>
> evlist__for_each_entry(evlist, evsel) {
> if (cs_etm_pmu && !found_etm)
> @@ -89,9 +142,13 @@ struct auxtrace_record
>
> if (arm_spe_pmus && !found_spe)
> found_spe = find_pmu_for_event(arm_spe_pmus, nr_spes, evsel);
> +
> + if (arm_spe_pmus && !found_spe)
if (hisi_ptt_pmus && !found_ptt) ?
Otherwise, I'm not sure what the purpose of the checking against spe is.
> + found_ptt = find_pmu_for_event(hisi_ptt_pmus, nr_ptts, evsel);
> }
>
> free(arm_spe_pmus);
> + free(hisi_ptt_pmus);
>
> if (found_etm)
> auxtrace_event_cnt++;
> @@ -99,6 +156,9 @@ struct auxtrace_record
> if (found_spe)
> auxtrace_event_cnt++;
>
> + if (found_ptt)
> + auxtrace_event_cnt++;
> +
> if (auxtrace_event_cnt > 1) {
> pr_err("Concurrent AUX trace operation not currently supported\n");
> *err = -EOPNOTSUPP;
> @@ -111,6 +171,9 @@ struct auxtrace_record
> #if defined(__aarch64__)
> if (found_spe)
> return arm_spe_recording_init(err, found_spe);
> +
> + if (found_ptt)
> + return hisi_ptt_recording_init(err, found_ptt);
> #endif
>
Powered by blists - more mailing lists