mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Liang, Kan" <kan.liang@linux.intel.com>
To: weilin.wang@intel.com, Ian Rogers <irogers@google.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
	Adrian Hunter <adrian.hunter@intel.com>
Cc: linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
	Perry Taylor <perry.taylor@intel.com>,
	Samantha Alt <samantha.alt@intel.com>,
	Caleb Biggers <caleb.biggers@intel.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Yang Jihong <yangjihong1@huawei.com>
Subject: Re: [RFC PATCH v2 07/17] perf stat: Add functions to set counter bitmaps for hardware-grouping method
Date: Mon, 30 Oct 2023 11:32:03 -0400	[thread overview]
Message-ID: <ba847510-bdc4-4298-8d9c-10933023e712@linux.intel.com> (raw)
In-Reply-To: <20231014015202.1175377-8-weilin.wang@intel.com>



On 2023-10-13 9:51 p.m., weilin.wang@intel.com wrote:
> From: Weilin Wang <weilin.wang@intel.com>
> 
> Add metricgroup__event_info data structure to represent an event in the
> metric grouping context; the list of counters and the PMU name an event
> should be collected with.
> 
> Add functions to parse event counter info from pmu-events and generate a
> list of metricgroup__event_info data to prepare grouping.
> 
> Signed-off-by: Weilin Wang <weilin.wang@intel.com>
> ---
>  tools/perf/util/metricgroup.c | 196 +++++++++++++++++++++++++++++++++-
>  tools/perf/util/metricgroup.h |  27 +++++
>  2 files changed, 220 insertions(+), 3 deletions(-)
> 
> diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
> index 8d4e29eb1..6af8a7341 100644
> --- a/tools/perf/util/metricgroup.c
> +++ b/tools/perf/util/metricgroup.c
> @@ -1432,6 +1432,182 @@ static int build_combined_expr_ctx(const struct list_head *metric_list,
>  	return ret;
>  }
>  
> +/**
> + * set_counter_bitmap - The counter bit mapping: [8-15,0-7], e.g. the GP0 is the
> + * 8th bit and GP7 is the 1st bit in this 16-bits bitmap. It is helpful for
> + * assigning GP4-7 before GP0-3 because some events can be collected using GP0-3
> + * only on some platforms.

The bitmap looks weird. Can we use the normal bitmap and always search
from the last set bit to find the available counter?


> + */
> +static int set_counter_bitmap(int pos, unsigned long *bitmap)
> +{
> +	if (pos >= NR_COUNTERS || pos < 0)
> +		return -EINVAL;
> +	if (pos <= 7)
> +		pos = TRANSFER_FIRST_BYTE(pos);
> +	else
> +		pos = TRANSFER_SEC_BYTE(pos);
> +	*bitmap |= 1ul << pos;
> +	return 0;
> +}
> +
> +static int parse_fixed_counter(const char *counter,
> +			      unsigned long *bitmap,
> +			      bool *fixed)
> +{
> +	int ret = -ENOENT;
> +	//TODO: this pattern is different on some other platforms
> +	const char *pattern = "Fixed counter ";
> +	int pos = 0;
> +
> +	if (!strncmp(counter, pattern, strlen(pattern))) {
> +		pos = atoi(counter + strlen(pattern));
> +		ret = set_counter_bitmap(pos, bitmap);
> +		if (ret)
> +			return ret;
> +		*fixed = true;
> +		return 0;
> +	}
> +	return ret;
> +}
> +
> +/**
> + * parse_counter - Parse event counter info from pmu-events and set up bitmap
> + * accordingly.
> + *
> + * @counter: counter info string to be parsed.
> + * @bitmap: bitmap to set based on counter info parsed.
> + * @fixed: is set to true if the event uses fixed counter.
> + */
> +static int parse_counter(const char *counter,
> +			unsigned long *bitmap,
> +			bool *fixed)
> +{
> +	int ret = 0;
> +	char *p;
> +	char *tok;
> +	int pos = 0;
> +
> +	ret = parse_fixed_counter(counter, bitmap, fixed);
> +	// ret==0 means matched with fixed counter

Move the comments to the above of parse_fixed_counter().
Uses /**/.

> +	if (ret == 0)
> +		return ret;
> +
> +	p = strdup(counter);
> +	tok = strtok(p, ",");
> +	if (!tok)
> +		return -ENOENT;
> +
> +	while (tok) {
> +		pos = atoi(tok);
> +		ret = set_counter_bitmap(pos, bitmap);
> +		if (ret)
> +			return ret;
> +		tok = strtok(NULL, ",");
> +	}
> +	return 0;
> +}
> +
> +static struct metricgroup__event_info *event_info__new(const char *name,
> +						      const char *pmu_name,
> +						      const char *counter,
> +						      bool free_counter)
> +{
> +	int ret = 0;
> +	char *bit_buf = malloc(NR_COUNTERS);
> +	bool fixed_counter = false;
> +	struct metricgroup__event_info *e;
> +
> +	e = zalloc(sizeof(*e));
> +	if (!e)
> +		return NULL;
> +	if (!pmu_name)
> +		pmu_name = "core";
> +
> +	e->name = name;
> +	e->free_counter = free_counter;
> +	e->pmu_name = strdup(pmu_name);
> +	if (free_counter) {
> +		ret = set_counter_bitmap(0, e->counters);
> +		if (ret)
> +			return NULL;
> +	} else {
> +		ret = parse_counter(counter, e->counters, &fixed_counter);
> +		if (ret)
> +			return NULL;
> +		e->fixed_counter = fixed_counter;
> +	}
> +
> +	bitmap_scnprintf(e->counters, NR_COUNTERS, bit_buf, NR_COUNTERS);
> +	pr_debug("Event %s requires pmu %s counter: %s bitmap %s, [pmu=%s]\n",
> +		e->name, e->pmu_name, counter, bit_buf, pmu_name);
> +
> +	return e;
> +}
> +
> +struct metricgroup__add_metric_event_data {
> +	struct list_head *list;
> +	/* pure event name, exclude umask and other info*/
> +	const char *event_name;
> +	/* event name and umask if applicable*/
> +	const char *event_id;
> +};
> +
> +static int metricgroup__add_metric_event_callback(const struct pmu_event *pe,
> +						 const struct pmu_events_table *table __maybe_unused,
> +						 void *data)
> +{
> +	struct metricgroup__event_info *event;
> +	struct metricgroup__add_metric_event_data *d = data;
> +
> +	if (!strcasecmp(pe->name, d->event_name)) {
> +		event = event_info__new(d->event_id, pe->pmu, pe->counter, /*free_counter=*/false);
> +		if (!event)
> +			return -ENOMEM;
> +		list_add(&event->nd, d->list);
> +	}
> +
> +	return 0;
> +}
> +
> +/**
> + * get_metricgroup_events - Find counter requirement of events from the
> + * pmu_events table
> + * @full_id: the full event identifiers.
> + * @table: pmu_events table that is searched for event data.
> + * @event_info_list: the list that the new event counter info added to.
> + */
> +static int get_metricgroup_events(const char *full_id,
> +				 const struct pmu_events_table *table,
> +				 struct list_head *event_info_list)
> +{
> +	LIST_HEAD(list);
> +	int ret = 0;
> +	const char *id;
> +	const char *rsep, *sep = strchr(full_id, '@');
> +
> +	if (sep) {
> +		rsep = strchr(full_id, ',');
> +		id = strndup(sep + 1, rsep - sep - 1);
> +		if (ret)
> +			goto out;
> +	} else {
> +		id = full_id;
> +	}
> +	{
> +		struct metricgroup__add_metric_event_data data = {
> +			.list = &list,
> +			.event_name = id,
> +			.event_id = full_id,
> +		};
> +		ret = pmu_events_table_for_each_event(table,
> +				metricgroup__add_metric_event_callback, &data);
> +	}

Please remove the useless {}

Thanks,
Kan
> +
> +out:
> +	list_splice(&list, event_info_list);
> +	return ret;
> +}
> +
>  /**
>   * hw_aware_build_grouping - Build event groupings by reading counter
>   * requirement of the events and counter available on the system from
> @@ -1445,9 +1621,25 @@ static int hw_aware_build_grouping(struct expr_parse_ctx *ctx __maybe_unused,
>  				  const char *modifier __maybe_unused)
>  {
>  	int ret = 0;
> +	struct hashmap_entry *cur;
> +	LIST_HEAD(pmu_info_list);
> +	LIST_HEAD(event_info_list);
> +	size_t bkt;
> +	const struct pmu_events_table *etable = pmu_events_table__find();
> +
> +#define RETURN_IF_NON_ZERO(x) do { if (x) return x; } while (0)
> +	hashmap__for_each_entry(ctx->ids, cur, bkt) {
> +		const char *id = cur->pkey;
> +
> +		pr_debug("found event %s\n", id);
> +
> +		ret = get_metricgroup_events(id, etable, &event_info_list);
> +		if (ret)
> +			return ret;
> +	}
>  
> -	pr_debug("This is a placeholder\n");
>  	return ret;
> +#undef RETURN_IF_NON_ZERO
>  }
>  
>  static void group_str_free(struct metricgroup__group_strs *g)
> @@ -1521,8 +1713,6 @@ static int hw_aware_parse_ids(struct perf_pmu *fake_pmu,
>  	*out_evlist = parsed_evlist;
>  	parsed_evlist = NULL;
>  err_out:
> -	parse_events_error__exit(&parse_error);
> -	evlist__delete(parsed_evlist);
>  	metricgroup__free_grouping_strs(&groupings);
>  	return ret;
>  }
> diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
> index 89809df85..3704545c9 100644
> --- a/tools/perf/util/metricgroup.h
> +++ b/tools/perf/util/metricgroup.h
> @@ -5,6 +5,7 @@
>  #include <linux/list.h>
>  #include <linux/rbtree.h>
>  #include <stdbool.h>
> +#include <linux/bitmap.h>
>  #include "pmu-events/pmu-events.h"
>  #include "strbuf.h"
>  
> @@ -67,6 +68,32 @@ struct metric_expr {
>  	int runtime;
>  };
>  
> +/* Maximum number of counters per PMU*/
> +#define NR_COUNTERS	16
> +/*
> + * Transfer bit position in the bitmap to ensure start assigning counter from
> + * the last GP counter to the first.
> + * bit15 <---> bit0
> + * [GP8-GP15] [GP0-GP7]
> + */
> +#define TRANSFER_FIRST_BYTE(pos) (7 - pos)
> +#define TRANSFER_SEC_BYTE(pos) (23 - pos)
> +
> +/**
> + * An event used in a metric. This info is for metric grouping.
> + */
> +struct metricgroup__event_info {
> +	struct list_head nd;
> +	/** The name of the event. */
> +	const char *name;
> +	/** The name of the pmu the event be collected on. */
> +	const char *pmu_name;
> +	bool fixed_counter;
> +	bool free_counter;
> +	/** The counters the event allowed to be collected on. */
> +	DECLARE_BITMAP(counters, NR_COUNTERS);
> +};
> +
>  /**
>   * Each group is one node in the group string list.
>   */

  reply	other threads:[~2023-10-30 15:34 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-14  1:51 [RFC PATCH v2 00/17] Perf stat metric grouping with hardware information weilin.wang
2023-10-14  1:51 ` [RFC PATCH v2 01/17] perf stat: Add hardware-grouping cmd option to perf stat weilin.wang
2023-10-14  1:51 ` [RFC PATCH v2 02/17] perf stat: Add basic functions for the hardware-grouping stat cmd option weilin.wang
2023-10-30 15:07   ` Liang, Kan
2023-10-14  1:51 ` [RFC PATCH v2 03/17] perf pmu-events: Add functions in jevent.py to parse counter and event info for hardware aware grouping weilin.wang
2023-10-14  1:51 ` [RFC PATCH v2 04/17] perf pmu-events: Add counter info into JSON files for SapphireRapids weilin.wang
2023-10-14  1:51 ` [RFC PATCH v2 05/17] perf pmu-events: Add event counter data for Cascadelakex weilin.wang
2023-10-14  1:51 ` [RFC PATCH v2 06/17] perf pmu-events: Add event counter data for Icelakex weilin.wang
2023-10-14  1:51 ` [RFC PATCH v2 07/17] perf stat: Add functions to set counter bitmaps for hardware-grouping method weilin.wang
2023-10-30 15:32   ` Liang, Kan [this message]
2023-10-30 17:46     ` Wang, Weilin
2023-10-30 18:30       ` Liang, Kan
2023-10-14  1:51 ` [RFC PATCH v2 08/17] perf stat: Add functions to get counter info weilin.wang
2023-10-14  1:51 ` [RFC PATCH v2 09/17] perf stat: Add functions to create new group and assign events into groups for hardware-grouping method weilin.wang
2023-10-14  1:51 ` [RFC PATCH v2 10/17] perf stat: Add build string function and topdown events handling in hardware-grouping weilin.wang
2023-10-14  1:51 ` [RFC PATCH v2 11/17] perf stat: Add function to handle special events " weilin.wang
2023-10-14  1:51 ` [RFC PATCH v2 12/17] perf stat: Add function to combine metrics for hardware-grouping weilin.wang
2023-10-14  1:51 ` [RFC PATCH v2 13/17] perf stat: Handle taken alone in hardware-grouping weilin.wang
2023-10-14  1:51 ` [RFC PATCH v2 14/17] perf stat: Handle NMI " weilin.wang
2023-10-14  1:52 ` [RFC PATCH v2 15/17] perf stat: Code refactoring " weilin.wang
2023-10-14  1:52 ` [RFC PATCH v2 16/17] perf stat: Add tool events support " weilin.wang
2023-10-14  1:52 ` [RFC PATCH v2 17/17] perf pmu-events: Add event counter data for Tigerlake weilin.wang

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=ba847510-bdc4-4298-8d9c-10933023e712@linux.intel.com \
    --to=kan.liang@linux.intel.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=caleb.biggers@intel.com \
    --cc=irogers@google.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=perry.taylor@intel.com \
    --cc=peterz@infradead.org \
    --cc=samantha.alt@intel.com \
    --cc=weilin.wang@intel.com \
    --cc=yangjihong1@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

all inboxes | Powered by JetHome®