mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ingo Molnar <mingo@kernel.org>
Cc: linux-kernel@vger.kernel.org,
	Adrian Hunter <adrian.hunter@intel.com>,
	Andi Kleen <ak@linux.intel.com>,
	Arnaldo Carvalho de Melo <acme@redhat.com>
Subject: [PATCH 18/30] perf script: Add synthesized Intel PT power and ptwrite events
Date: Fri, 30 Jun 2017 19:25:02 -0300	[thread overview]
Message-ID: <20170630222514.11832-19-acme@kernel.org> (raw)
In-Reply-To: <20170630222514.11832-1-acme@kernel.org>

From: Adrian Hunter <adrian.hunter@intel.com>

Add definitions for synthesized Intel PT events for power and ptwrite.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/r/1498811802-2301-1-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 114 +++++++++++++++++++++++++++++++++++++++++-
 tools/perf/util/event.h     | 118 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 231 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index e87b480bbdd0..b458a0cc3544 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1203,10 +1203,122 @@ static void print_sample_bpf_output(struct perf_sample *sample)
 		       (char *)(sample->raw_data));
 }
 
-static void print_sample_synth(struct perf_sample *sample __maybe_unused,
+static void print_sample_spacing(int len, int spacing)
+{
+	if (len > 0 && len < spacing)
+		printf("%*s", spacing - len, "");
+}
+
+static void print_sample_pt_spacing(int len)
+{
+	print_sample_spacing(len, 34);
+}
+
+static void print_sample_synth_ptwrite(struct perf_sample *sample)
+{
+	struct perf_synth_intel_ptwrite *data = perf_sample__synth_ptr(sample);
+	int len;
+
+	if (perf_sample__bad_synth_size(sample, *data))
+		return;
+
+	len = printf(" IP: %u payload: %#" PRIx64 " ",
+		     data->ip, le64_to_cpu(data->payload));
+	print_sample_pt_spacing(len);
+}
+
+static void print_sample_synth_mwait(struct perf_sample *sample)
+{
+	struct perf_synth_intel_mwait *data = perf_sample__synth_ptr(sample);
+	int len;
+
+	if (perf_sample__bad_synth_size(sample, *data))
+		return;
+
+	len = printf(" hints: %#x extensions: %#x ",
+		     data->hints, data->extensions);
+	print_sample_pt_spacing(len);
+}
+
+static void print_sample_synth_pwre(struct perf_sample *sample)
+{
+	struct perf_synth_intel_pwre *data = perf_sample__synth_ptr(sample);
+	int len;
+
+	if (perf_sample__bad_synth_size(sample, *data))
+		return;
+
+	len = printf(" hw: %u cstate: %u sub-cstate: %u ",
+		     data->hw, data->cstate, data->subcstate);
+	print_sample_pt_spacing(len);
+}
+
+static void print_sample_synth_exstop(struct perf_sample *sample)
+{
+	struct perf_synth_intel_exstop *data = perf_sample__synth_ptr(sample);
+	int len;
+
+	if (perf_sample__bad_synth_size(sample, *data))
+		return;
+
+	len = printf(" IP: %u ", data->ip);
+	print_sample_pt_spacing(len);
+}
+
+static void print_sample_synth_pwrx(struct perf_sample *sample)
+{
+	struct perf_synth_intel_pwrx *data = perf_sample__synth_ptr(sample);
+	int len;
+
+	if (perf_sample__bad_synth_size(sample, *data))
+		return;
+
+	len = printf(" deepest cstate: %u last cstate: %u wake reason: %#x ",
+		     data->deepest_cstate, data->last_cstate,
+		     data->wake_reason);
+	print_sample_pt_spacing(len);
+}
+
+static void print_sample_synth_cbr(struct perf_sample *sample)
+{
+	struct perf_synth_intel_cbr *data = perf_sample__synth_ptr(sample);
+	unsigned int percent, freq;
+	int len;
+
+	if (perf_sample__bad_synth_size(sample, *data))
+		return;
+
+	freq = (le32_to_cpu(data->freq) + 500) / 1000;
+	len = printf(" cbr: %2u freq: %4u MHz ", data->cbr, freq);
+	if (data->max_nonturbo) {
+		percent = (5 + (1000 * data->cbr) / data->max_nonturbo) / 10;
+		len += printf("(%3u%%) ", percent);
+	}
+	print_sample_pt_spacing(len);
+}
+
+static void print_sample_synth(struct perf_sample *sample,
 			       struct perf_evsel *evsel)
 {
 	switch (evsel->attr.config) {
+	case PERF_SYNTH_INTEL_PTWRITE:
+		print_sample_synth_ptwrite(sample);
+		break;
+	case PERF_SYNTH_INTEL_MWAIT:
+		print_sample_synth_mwait(sample);
+		break;
+	case PERF_SYNTH_INTEL_PWRE:
+		print_sample_synth_pwre(sample);
+		break;
+	case PERF_SYNTH_INTEL_EXSTOP:
+		print_sample_synth_exstop(sample);
+		break;
+	case PERF_SYNTH_INTEL_PWRX:
+		print_sample_synth_pwrx(sample);
+		break;
+	case PERF_SYNTH_INTEL_CBR:
+		print_sample_synth_cbr(sample);
+		break;
 	default:
 		break;
 	}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 855733c2adcf..9967c87af7a6 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -255,6 +255,124 @@ enum auxtrace_error_type {
 /* Attribute type for custom synthesized events */
 #define PERF_TYPE_SYNTH		(INT_MAX + 1U)
 
+/* Attribute config for custom synthesized events */
+enum perf_synth_id {
+	PERF_SYNTH_INTEL_PTWRITE,
+	PERF_SYNTH_INTEL_MWAIT,
+	PERF_SYNTH_INTEL_PWRE,
+	PERF_SYNTH_INTEL_EXSTOP,
+	PERF_SYNTH_INTEL_PWRX,
+	PERF_SYNTH_INTEL_CBR,
+};
+
+/*
+ * Raw data formats for synthesized events. Note that 4 bytes of padding are
+ * present to match the 'size' member of PERF_SAMPLE_RAW data which is always
+ * 8-byte aligned. That means we must dereference raw_data with an offset of 4.
+ * Refer perf_sample__synth_ptr() and perf_synth__raw_data().  It also means the
+ * structure sizes are 4 bytes bigger than the raw_size, refer
+ * perf_synth__raw_size().
+ */
+
+struct perf_synth_intel_ptwrite {
+	u32 padding;
+	union {
+		struct {
+			u32	ip		:  1,
+				reserved	: 31;
+		};
+		u32	flags;
+	};
+	u64	payload;
+};
+
+struct perf_synth_intel_mwait {
+	u32 padding;
+	u32 reserved;
+	union {
+		struct {
+			u64	hints		:  8,
+				reserved1	: 24,
+				extensions	:  2,
+				reserved2	: 30;
+		};
+		u64	payload;
+	};
+};
+
+struct perf_synth_intel_pwre {
+	u32 padding;
+	u32 reserved;
+	union {
+		struct {
+			u64	reserved1	:  7,
+				hw		:  1,
+				subcstate	:  4,
+				cstate		:  4,
+				reserved2	: 48;
+		};
+		u64	payload;
+	};
+};
+
+struct perf_synth_intel_exstop {
+	u32 padding;
+	union {
+		struct {
+			u32	ip		:  1,
+				reserved	: 31;
+		};
+		u32	flags;
+	};
+};
+
+struct perf_synth_intel_pwrx {
+	u32 padding;
+	u32 reserved;
+	union {
+		struct {
+			u64	deepest_cstate	:  4,
+				last_cstate	:  4,
+				wake_reason	:  4,
+				reserved1	: 52;
+		};
+		u64	payload;
+	};
+};
+
+struct perf_synth_intel_cbr {
+	u32 padding;
+	union {
+		struct {
+			u32	cbr		:  8,
+				reserved1	:  8,
+				max_nonturbo	:  8,
+				reserved2	:  8;
+		};
+		u32	flags;
+	};
+	u32 freq;
+	u32 reserved3;
+};
+
+/*
+ * raw_data is always 4 bytes from an 8-byte boundary, so subtract 4 to get
+ * 8-byte alignment.
+ */
+static inline void *perf_sample__synth_ptr(struct perf_sample *sample)
+{
+	return sample->raw_data - 4;
+}
+
+static inline void *perf_synth__raw_data(void *p)
+{
+	return p + 4;
+}
+
+#define perf_synth__raw_size(d) (sizeof(d) - 4)
+
+#define perf_sample__bad_synth_size(s, d) ((s)->raw_size < sizeof(d) - 4)
+
 /*
  * The kernel collects the number of events it couldn't send in a stretch and
  * when possible sends this number in a PERF_RECORD_LOST event. The number of
-- 
2.9.4

  parent reply	other threads:[~2017-06-30 22:26 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-06-30 22:24 [GIT PULL 00/30] perf/core improvements and fixes Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 01/30] perf tests: Add platform dependency to test 15 Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 02/30] perf help: Introduce exec_failed() to avoid code duplication Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 03/30] perf help: Elliminate dup code for reporting Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 04/30] perf help: Use pr_warning() Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 05/30] perf config: " Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 06/30] perf event-parse: " Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 07/30] perf tools: Remove warning() Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 08/30] perf tools: Replace error() with pr_err() Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 09/30] perf config: Do not die when parsing u64 or int config values Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 10/30] perf tools: Kill die() Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 11/30] perf jit: fix typo: "incalid" -> "invalid" Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 12/30] x86/insn: perf tools: Add new ptwrite instruction Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 13/30] perf script: Add 'synth' event type for synthesized events Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 14/30] tools include: Add byte-swapping macros to kernel.h Arnaldo Carvalho de Melo
2017-06-30 22:24 ` [PATCH 15/30] perf auxtrace: Add itrace option to output ptwrite events Arnaldo Carvalho de Melo
2017-06-30 22:25 ` [PATCH 16/30] perf auxtrace: Add itrace option to output power events Arnaldo Carvalho de Melo
2017-06-30 22:25 ` [PATCH 17/30] perf script: Add 'synth' field for synthesized event payloads Arnaldo Carvalho de Melo
2017-06-30 22:25 ` Arnaldo Carvalho de Melo [this message]
2017-06-30 22:25 ` [PATCH 19/30] perf intel-pt: Factor out common code synthesizing event samples Arnaldo Carvalho de Melo
2017-06-30 22:25 ` [PATCH 20/30] perf intel-pt: Remove unused instructions_sample_period Arnaldo Carvalho de Melo
2017-06-30 22:25 ` [PATCH 21/30] perf intel-pt: Join needlessly wrapped lines Arnaldo Carvalho de Melo
2017-06-30 22:25 ` [PATCH 22/30] perf intel-pt: Tidy Intel PT evsel lookup into separate function Arnaldo Carvalho de Melo
2017-06-30 22:25 ` [PATCH 23/30] perf intel-pt: Tidy messages into called function intel_pt_synth_event() Arnaldo Carvalho de Melo
2017-06-30 22:25 ` [PATCH 24/30] perf intel-pt: Factor out intel_pt_set_event_name() Arnaldo Carvalho de Melo
2017-06-30 22:25 ` [PATCH 25/30] perf intel-pt: Move code in intel_pt_synth_events() to simplify attr setting Arnaldo Carvalho de Melo
2017-06-30 22:25 ` [PATCH 26/30] perf intel-pt: Synthesize new power and "ptwrite" events Arnaldo Carvalho de Melo
2017-06-30 22:25 ` [PATCH 27/30] perf intel-pt: Add example script for power events and PTWRITE Arnaldo Carvalho de Melo
2017-06-30 22:25 ` [PATCH 28/30] perf intel-pt: Update documentation to include new ptwrite and power events Arnaldo Carvalho de Melo
2017-06-30 22:25 ` [PATCH 29/30] perf intel-pt: Do not use TSC packets for calculating CPU cycles to TSC Arnaldo Carvalho de Melo
2017-06-30 22:25 ` [PATCH 30/30] perf auxtrace: Add CPU filter support Arnaldo Carvalho de Melo
2017-07-01  8:41 ` [GIT PULL 00/30] perf/core improvements and fixes Ingo Molnar

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=20170630222514.11832-19-acme@kernel.org \
    --to=acme@kernel.org \
    --cc=acme@redhat.com \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    /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

Powered by JetHome