Re: [PATCH v7 2/2] drivers/perf: hisi: Add driver for HiSilicon PCIe PMU

From: liuqi (BA)
Date: Mon Jun 28 2021 - 06:50:03 EST




On 2021/6/26 19:44, John Garry wrote:
On 26/06/2021 03:13, liuqi (BA) wrote:


On 2021/6/25 23:53, John Garry wrote:
On 24/06/2021 11:59, Qi Liu wrote:
+
+/*
+ * Events with the "dl" suffix in their names count performance in DL layer,
+ * otherswise, events count performance in TL layer.
+ */
+static struct attribute *hisi_pcie_pmu_events_attr[] = {
+    HISI_PCIE_PMU_EVENT_ATTR(bw_rx_mwr, 0x010004),
+    HISI_PCIE_PMU_EVENT_ATTR(bw_rx_mrd, 0x100005),
+    HISI_PCIE_PMU_EVENT_ATTR(bw_tx_mwr, 0x010005),
+    HISI_PCIE_PMU_EVENT_ATTR(bw_tx_mrd, 0x200004),
+    HISI_PCIE_PMU_EVENT_ATTR(lat_rx_mwr, 0x000010),
+    HISI_PCIE_PMU_EVENT_ATTR(lat_rx_mrd, 0x020010),
+    HISI_PCIE_PMU_EVENT_ATTR(lat_tx_mrd, 0x000011),
+    HISI_PCIE_PMU_EVENT_ATTR(bw_rx_dl, 0x010084),
+    HISI_PCIE_PMU_EVENT_ATTR(bw_tx_dl, 0x030084),
+    NULL
+};
+
+static struct attribute_group hisi_pcie_pmu_events_group = {
+    .name = "events",
+    .attrs = hisi_pcie_pmu_events_attr,
+};
+
+static struct attribute *hisi_pcie_pmu_format_attr[] = {
+    HISI_PCIE_PMU_FORMAT_ATTR(event, "config:0-15"),
+    HISI_PCIE_PMU_FORMAT_ATTR(subevent, "config:16-23"),
+    HISI_PCIE_PMU_FORMAT_ATTR(thr_len, "config1:0-3"),
+    HISI_PCIE_PMU_FORMAT_ATTR(thr_mode, "config1:4"),
+    HISI_PCIE_PMU_FORMAT_ATTR(trig_len, "config1:5-8"),
+    HISI_PCIE_PMU_FORMAT_ATTR(trig_mode, "config1:9"),
+    HISI_PCIE_PMU_FORMAT_ATTR(port, "config2:0-15"),
+    HISI_PCIE_PMU_FORMAT_ATTR(bdf, "config2:16-31"),
+    NULL
+};

I am just wondering how this now works.

So if the user programs the following:
./perf stat -v -e hisi_pcieX/lat_rx_mrd/

Then the value (incremented) in HISI_PCIE_CNT (I think that's the right one) is returned as the event count. But one would expect bandwidth from that event, while we only return here the delay cycles - how is the count in HISI_PCIE_CNT_EXT exposed, so userspace can do the calc for bw?



Hi Qi,


Hardware counter and ext_counter work together for bandwidth, latency,
bus utilization and buffer occupancy events. For example, for latency
events(idx = 0x10), counter counts total delay cycles and ext_counter
counts PCIe packets number.

As we don't want PMU driver to process these two data, "delay cycles"
can be treated as an event(id = 0x10), "packets number" as another event
(id = 0x10 << 8), and driver could export these data separately.

if the user want to calculate latency of rx memory read, they should:
./perf stat -v -e '{hisi_pcieX/event=0x10, subevent=0x01/,hisi_pcieX/event=0x0400, subevent=0x01/

and for bandwidth event:
./perf stat -v -e '{hisi_pcieX/event=0x4, subevent=0x02/,hisi_pcieX/event=0x1000, subevent=0x02/

Hi John,
I would suggest supporting a perf metric for this then, which would be like:

{
   "BriefDescription": "Latency for inbound traffic...",
   "MetricName": "hisi_pcie_lat_rx_mrd",
   "MetricExpr": "hisi_pcieX@event\\=0x4@subevent\\=0x02 \ hisi_pcieX@event\\=0x1000@subevent\\=0x02 \",
   "Unit": "hisi_pci",
   "Compat": "v1"
},

(syntax may be incorrect - illustration only)

yes, we could add these metrics in json file, thanks.

Then the value in HISI_PCIE_CNT and HISI_PCIE_EXT_CNT returned separately, and userspace could do the calculation.

But I am still curious about lat_rx_mrd and the other events which we continue to advertise. They don't really provide latency or bandwidth on their own, but only half the necessary data. So I doubt their purpose.

So how about changing the event name to show the real purpose of this event, like changing "bw_rx_mrd" to "flux_rx_mrd", and changing "lat_rx_mrd" to "delay_rx_mrd"?

Thanks, Qi

Thanks,
John

.