All of lore.kernel.org
 help / color / mirror / Atom feed
From: kan.liang@linux.intel.com
To: peterz@infradead.org, acme@redhat.com, mingo@kernel.org,
	linux-kernel@vger.kernel.org
Cc: jolsa@kernel.org, namhyung@kernel.org,
	vitaly.slobodskoy@intel.com, pavel.gerasimov@intel.com,
	ak@linux.intel.com, eranian@google.com, mpe@ellerman.id.au,
	Kan Liang <kan.liang@linux.intel.com>
Subject: [PATCH V4 06/13] perf header: Support CPU PMU capabilities
Date: Tue, 19 Nov 2019 06:34:04 -0800	[thread overview]
Message-ID: <20191119143411.3482-7-kan.liang@linux.intel.com> (raw)
In-Reply-To: <20191119143411.3482-1-kan.liang@linux.intel.com>

From: Kan Liang <kan.liang@linux.intel.com>

To stitch LBR call stack, the max LBR information is required. So the
CPU PMU capabilities information has to be stored in perf header.

Add a new feature HEADER_CPU_PMU_CAPS for CPU PMU capabilities.
Retrieve all CPU PMU capabilities, not just max LBR information.

Add variable max_branches to facilitate future usage.

The CPU PMU capabilities information is only useful for LBR call stack
mode. Clear the feature for perf stat and other perf record mode.

Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
 .../Documentation/perf.data-file-format.txt   |  16 +++
 tools/perf/builtin-record.c                   |   3 +
 tools/perf/builtin-stat.c                     |   1 +
 tools/perf/util/env.h                         |   3 +
 tools/perf/util/header.c                      | 110 ++++++++++++++++++
 tools/perf/util/header.h                      |   1 +
 6 files changed, 134 insertions(+)

diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index b0152e1095c5..b6472e463284 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -373,6 +373,22 @@ struct {
 Indicates that trace contains records of PERF_RECORD_COMPRESSED type
 that have perf_events records in compressed form.
 
+	HEADER_CPU_PMU_CAPS = 28,
+
+	A list of cpu PMU capabilities. The format of data is as below.
+
+struct {
+	u32 nr_cpu_pmu_caps;
+	{
+		char	name[];
+		char	value[];
+	} [nr_cpu_pmu_caps]
+};
+
+
+Example:
+ cpu pmu capabilities: branches=32, max_precise=3, pmu_name=icelake
+
 	other bits are reserved and should ignored for now
 	HEADER_FEAT_BITS	= 256,
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index b95c000c1ed9..b53e19eb4b6c 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1106,6 +1106,9 @@ static void record__init_features(struct record *rec)
 	if (!record__comp_enabled(rec))
 		perf_header__clear_feat(&session->header, HEADER_COMPRESSED);
 
+	if (!callchain_param.enabled || (callchain_param.record_mode != CALLCHAIN_LBR))
+		perf_header__clear_feat(&session->header, HEADER_CPU_PMU_CAPS);
+
 	perf_header__clear_feat(&session->header, HEADER_STAT);
 }
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 5964e808d73d..ed2d0aa7a861 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1471,6 +1471,7 @@ static void init_features(struct perf_session *session)
 	perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
 	perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
 	perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
+	perf_header__clear_feat(&session->header, HEADER_CPU_PMU_CAPS);
 }
 
 static int __cmd_record(int argc, const char **argv)
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 11d05ae3606a..d286d478b4d8 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -48,6 +48,7 @@ struct perf_env {
 	char			*cpuid;
 	unsigned long long	total_mem;
 	unsigned int		msr_pmu_type;
+	unsigned int		max_branches;
 
 	int			nr_cmdline;
 	int			nr_sibling_cores;
@@ -57,12 +58,14 @@ struct perf_env {
 	int			nr_memory_nodes;
 	int			nr_pmu_mappings;
 	int			nr_groups;
+	int			nr_cpu_pmu_caps;
 	char			*cmdline;
 	const char		**cmdline_argv;
 	char			*sibling_cores;
 	char			*sibling_dies;
 	char			*sibling_threads;
 	char			*pmu_mappings;
+	char			*cpu_pmu_caps;
 	struct cpu_topology_map	*cpu;
 	struct cpu_cache_level	*caches;
 	int			 caches_cnt;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 7ed481c9bcdf..6d32e5f1192c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1404,6 +1404,39 @@ static int write_compressed(struct feat_fd *ff __maybe_unused,
 	return do_write(ff, &(ff->ph->env.comp_mmap_len), sizeof(ff->ph->env.comp_mmap_len));
 }
 
+static int write_cpu_pmu_caps(struct feat_fd *ff,
+			      struct evlist *evlist __maybe_unused)
+{
+	struct perf_pmu_caps *caps = NULL;
+	struct perf_pmu *cpu_pmu;
+	int nr_caps;
+	int ret;
+
+	cpu_pmu = perf_pmu__find("cpu");
+	if (!cpu_pmu)
+		return -ENOENT;
+
+	nr_caps = perf_pmu__caps_parse(cpu_pmu);
+	if (nr_caps < 0)
+		return nr_caps;
+
+	ret = do_write(ff, &nr_caps, sizeof(nr_caps));
+	if (ret < 0)
+		return ret;
+
+	while ((caps = perf_pmu__scan_caps(cpu_pmu, caps))) {
+		ret = do_write_string(ff, caps->name);
+		if (ret < 0)
+			return ret;
+
+		ret = do_write_string(ff, caps->value);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
+}
+
 static void print_hostname(struct feat_fd *ff, FILE *fp)
 {
 	fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname);
@@ -1819,6 +1852,28 @@ static void print_compressed(struct feat_fd *ff, FILE *fp)
 		ff->ph->env.comp_level, ff->ph->env.comp_ratio);
 }
 
+static void print_cpu_pmu_caps(struct feat_fd *ff, FILE *fp)
+{
+	const char *delimiter = "# cpu pmu capabilities: ";
+	char *str;
+	u32 nr_caps;
+
+	nr_caps = ff->ph->env.nr_cpu_pmu_caps;
+	if (!nr_caps) {
+		fprintf(fp, "# cpu pmu capabilities: not available\n");
+		return;
+	}
+
+	str = ff->ph->env.cpu_pmu_caps;
+	while (nr_caps--) {
+		fprintf(fp, "%s%s", delimiter, str);
+		delimiter = ", ";
+		str += strlen(str) + 1;
+	}
+
+	fprintf(fp, "\n");
+}
+
 static void print_pmu_mappings(struct feat_fd *ff, FILE *fp)
 {
 	const char *delimiter = "# pmu mappings: ";
@@ -2856,6 +2911,60 @@ static int process_compressed(struct feat_fd *ff,
 	return 0;
 }
 
+static int process_cpu_pmu_caps(struct feat_fd *ff,
+				void *data __maybe_unused)
+{
+	char *name, *value;
+	struct strbuf sb;
+	u32 nr_caps;
+
+	if (do_read_u32(ff, &nr_caps))
+		return -1;
+
+	if (!nr_caps) {
+		pr_debug("cpu pmu capabilities not available\n");
+		return 0;
+	}
+
+	ff->ph->env.nr_cpu_pmu_caps = nr_caps;
+
+	if (strbuf_init(&sb, 128) < 0)
+		return -1;
+
+	while (nr_caps--) {
+		name = do_read_string(ff);
+		if (!name)
+			goto error;
+
+		value = do_read_string(ff);
+		if (!value)
+			goto free_name;
+
+		if (strbuf_addf(&sb, "%s=%s", name, value) < 0)
+			goto free_value;
+
+		/* include a NULL character at the end */
+		if (strbuf_add(&sb, "", 1) < 0)
+			goto free_value;
+
+		if (!strcmp(name, "branches"))
+			ff->ph->env.max_branches = atoi(value);
+
+		free(value);
+		free(name);
+	}
+	ff->ph->env.cpu_pmu_caps = strbuf_detach(&sb, NULL);
+	return 0;
+
+free_value:
+	free(value);
+free_name:
+	free(name);
+error:
+	strbuf_release(&sb);
+	return -1;
+}
+
 #define FEAT_OPR(n, func, __full_only) \
 	[HEADER_##n] = {					\
 		.name	    = __stringify(n),			\
@@ -2913,6 +3022,7 @@ const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPR(BPF_PROG_INFO, bpf_prog_info,  false),
 	FEAT_OPR(BPF_BTF,       bpf_btf,        false),
 	FEAT_OPR(COMPRESSED,	compressed,	false),
+	FEAT_OPR(CPU_PMU_CAPS,	cpu_pmu_caps,	false),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 840f95cee349..650bd1c7a99b 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -43,6 +43,7 @@ enum {
 	HEADER_BPF_PROG_INFO,
 	HEADER_BPF_BTF,
 	HEADER_COMPRESSED,
+	HEADER_CPU_PMU_CAPS,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
-- 
2.17.1


  parent reply	other threads:[~2019-11-19 14:35 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-19 14:33 [PATCH V4 00/13] Stitch LBR call stack kan.liang
2019-11-19 14:33 ` [PATCH V4 01/13] perf/core: Add new branch sample type for LBR TOS kan.liang
2019-11-19 19:02   ` Stephane Eranian
2019-11-19 22:25     ` Liang, Kan
2019-11-19 22:51       ` Stephane Eranian
2019-11-20 15:06         ` Liang, Kan
2019-11-19 14:34 ` [PATCH V4 02/13] perf/x86/intel: Output LBR TOS information kan.liang
2019-11-19 14:34 ` [PATCH V4 03/13] perf tools: Support new branch sample type for LBR TOS kan.liang
2019-11-19 19:00   ` Stephane Eranian
2019-11-19 21:31     ` Peter Zijlstra
2019-11-19 22:17       ` Liang, Kan
2019-11-19 14:34 ` [PATCH V4 04/13] perf header: Add check for event attr kan.liang
2019-11-19 14:34 ` [PATCH V4 05/13] perf pmu: Add support for PMU capabilities kan.liang
2019-11-19 14:34 ` kan.liang [this message]
2019-11-19 14:34 ` [PATCH V4 07/13] perf machine: Refine the function for LBR call stack reconstruction kan.liang
2019-11-19 14:34 ` [PATCH V4 08/13] perf tools: Stitch LBR call stack kan.liang
2019-11-19 14:34 ` [PATCH V4 09/13] perf report: Add option to enable the LBR stitching approach kan.liang
2019-11-19 14:34 ` [PATCH V4 10/13] perf script: " kan.liang
2019-11-19 14:34 ` [PATCH V4 11/13] perf top: " kan.liang
2019-11-19 14:34 ` [PATCH V4 12/13] perf c2c: " kan.liang
2019-11-19 14:34 ` [RFC PATCH V4 13/13] perf hist: Add fast path for duplicate entries check approach kan.liang

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=20191119143411.3482-7-kan.liang@linux.intel.com \
    --to=kan.liang@linux.intel.com \
    --cc=acme@redhat.com \
    --cc=ak@linux.intel.com \
    --cc=eranian@google.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=mpe@ellerman.id.au \
    --cc=namhyung@kernel.org \
    --cc=pavel.gerasimov@intel.com \
    --cc=peterz@infradead.org \
    --cc=vitaly.slobodskoy@intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.