[PATCH 06/12] perf, tools, stat: Basic support for TopDown in perf stat

[Andi Kleen]

From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

Add basic plumbing for TopDown in perf stat

Add a new --topdown options to enable events.
When --topdown is specified set up events for all topdown
events supported by the kernel.
Add topdown-* as a special case to the event parser, as is
needed for all events containing -.

The actual code to compute the metrics is in follow-on patches.

v2: Use standard sysctl read function.
v3: Move x86 specific code to arch/
v4: Enable --metric-only implicitly for topdown.
v5: Add --single-thread option to not force per core mode
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
 tools/perf/Documentation/perf-stat.txt |  24 +++++++
 tools/perf/arch/x86/util/Build         |   1 +
 tools/perf/arch/x86/util/group.c       |  27 ++++++++
 tools/perf/builtin-stat.c              | 122 +++++++++++++++++++++++++++++++--
 tools/perf/util/group.h                |   7 ++
 tools/perf/util/parse-events.l         |   1 +
 6 files changed, 176 insertions(+), 6 deletions(-)
 create mode 100644 tools/perf/arch/x86/util/group.c
 create mode 100644 tools/perf/util/group.h

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 51e3c5a..0afb844 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -196,6 +196,30 @@ Aggregate counts per physical processor for system-wide mode measurements.
 --no-aggr::
 Do not aggregate counts across all monitored CPUs.
 
+--topdown::
+Print top down level 1 metrics if supported by the CPU. This allows to
+determine bottle necks in the CPU pipeline for CPU bound workloads,
+by breaking it down into frontend bound, backend bound, bad speculation
+and retiring. Metrics are only printed when they cross a threshold.
+
+The top down metrics may be collected per core instead of per
+CPU thread. In this case per core mode is automatically enabled
+and -a may need to be set, requiring root rights or
+perf.perf_event_paranoid=-1.
+
+This enable --metric-only, unless overriden with --no-metric-only.
+
+To interpret the results it is usually needed to know on which
+CPUs the workload runs on. If needed the CPUs can be forced using
+taskset.
+
+--single-thread::
+Don't force global per core mode with --topdown. The workload should
+work single threaded, otherwise the results may be unpredictable.
+
+This is generally only possible when the CPU does not use Hyper Threading
+or the secondary CPU threads have been offlined through
+/sys/devices/system/cpu/cpu*/online
 
 EXAMPLES
 --------
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 4659703..4cd8a16 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -3,6 +3,7 @@ libperf-y += tsc.o
 libperf-y += pmu.o
 libperf-y += kvm-stat.o
 libperf-y += perf_regs.o
+libperf-y += group.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
diff --git a/tools/perf/arch/x86/util/group.c b/tools/perf/arch/x86/util/group.c
new file mode 100644
index 0000000..f3039b5
--- /dev/null
+++ b/tools/perf/arch/x86/util/group.c
@@ -0,0 +1,27 @@
+#include <stdio.h>
+#include "api/fs/fs.h"
+#include "util/group.h"
+
+/*
+ * Check whether we can use a group for top down.
+ * Without a group may get bad results due to multiplexing.
+ */
+bool check_group(bool *warn)
+{
+	int n;
+
+	if (sysctl__read_int("kernel/nmi_watchdog", &n) < 0)
+		return false;
+	if (n > 0) {
+		*warn = true;
+		return false;
+	}
+	return true;
+}
+
+void group_warn(void)
+{
+	fprintf(stderr,
+		"nmi_watchdog enabled with topdown. May give wrong results.\n"
+		"Disable with echo 0 > /proc/sys/kernel/nmi_watchdog\n");
+}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 6d0f4f6..fe627f3 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -59,10 +59,9 @@
 #include "util/thread.h"
 #include "util/thread_map.h"
 #include "util/counts.h"
-#include "util/session.h"
-#include "util/tool.h"
-#include "asm/bug.h"
+#include "util/group.h"
 
+#include <api/fs/fs.h>
 #include <stdlib.h>
 #include <sys/prctl.h>
 #include <locale.h>
@@ -98,6 +97,15 @@ static const char * transaction_limited_attrs = {
 	"}"
 };
 
+static const char * topdown_attrs[] = {
+	"topdown-total-slots",
+	"topdown-fetch-bubbles",
+	"topdown-slots-retired",
+	"topdown-recovery-bubbles",
+	"topdown-slots-issued",
+	NULL,
+};
+
 static struct perf_evlist	*evsel_list;
 
 static struct target target = {
@@ -112,6 +120,8 @@ static volatile pid_t		child_pid			= -1;
 static bool			null_run			=  false;
 static int			detailed_run			=  0;
 static bool			transaction_run;
+static bool			topdown_run			= false;
+static bool			single_thread			= false;
 static bool			big_num				=  true;
 static int			big_num_opt			=  -1;
 static const char		*csv_sep			= NULL;
@@ -124,6 +134,7 @@ static unsigned int		initial_delay			= 0;
 static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
 static bool			metric_only			= false;
+static bool			force_metric_only		= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
@@ -1504,6 +1515,14 @@ static int stat__set_big_num(const struct option *opt __maybe_unused,
 	return 0;
 }
 
+static int enable_metric_only(const struct option *opt __maybe_unused,
+			      const char *s __maybe_unused, int unset)
+{
+	force_metric_only = true;
+	metric_only = !unset;
+	return 0;
+}
+
 static const struct option stat_options[] = {
 	OPT_BOOLEAN('T', "transaction", &transaction_run,
 		    "hardware transaction statistics"),
@@ -1562,8 +1581,12 @@ static const struct option stat_options[] = {
 		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_UINTEGER('D', "delay", &initial_delay,
 		     "ms to wait before starting measurement after program start"),
-	OPT_BOOLEAN(0, "metric-only", &metric_only,
-			"Only print computed metrics. No raw values"),
+	OPT_CALLBACK_NOOPT(0, "metric-only", &metric_only, NULL,
+			"Only print computed metrics. No raw values", enable_metric_only),
+	OPT_BOOLEAN(0, "topdown", &topdown_run,
+			"measure topdown level 1 statistics"),
+	OPT_BOOLEAN(0, "single-thread", &single_thread,
+			"don't force per core mode"),
 	OPT_END()
 };
 
@@ -1756,12 +1779,61 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
 	return 0;
 }
 
+static void filter_events(const char **attr, char **str, bool use_group)
+{
+	int off = 0;
+	int i;
+	int len = 0;
+	char *s;
+
+	for (i = 0; attr[i]; i++) {
+		if (pmu_have_event("cpu", attr[i])) {
+			len += strlen(attr[i]) + 1;
+			attr[i - off] = attr[i];
+		} else
+			off++;
+	}
+	attr[i - off] = NULL;
+
+	*str = malloc(len + 1 + 2);
+	if (!*str)
+		return;
+	s = *str;
+	if (i - off == 0) {
+		*s = 0;
+		return;
+	}
+	if (use_group)
+		*s++ = '{';
+	for (i = 0; attr[i]; i++) {
+		strcpy(s, attr[i]);
+		s += strlen(s);
+		*s++ = ',';
+	}
+	if (use_group) {
+		s[-1] = '}';
+		*s = 0;
+	} else
+		s[-1] = 0;
+}
+
+__weak bool check_group(bool *warn)
+{
+	*warn = false;
+	return false;
+}
+
+__weak void group_warn(void)
+{
+}
+
 /*
  * Add default attributes, if there were no attributes specified or
  * if -d/--detailed, -d -d or -d -d -d is used:
  */
 static int add_default_attributes(void)
 {
+	int err;
 	struct perf_event_attr default_attrs[] = {
 
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK		},
@@ -1874,7 +1946,6 @@ static int add_default_attributes(void)
 		return 0;
 
 	if (transaction_run) {
-		int err;
 		if (pmu_have_event("cpu", "cycles-ct") &&
 		    pmu_have_event("cpu", "el-start"))
 			err = parse_events(evsel_list, transaction_attrs, NULL);
@@ -1887,6 +1958,36 @@ static int add_default_attributes(void)
 		return 0;
 	}
 
+	if (topdown_run) {
+		char *str = NULL;
+		bool warn = false;
+
+		if (!force_metric_only)
+			metric_only = true;
+		filter_events(topdown_attrs, &str, check_group(&warn));
+		if (topdown_attrs[0] && str) {
+			if (warn)
+				group_warn();
+			err = parse_events(evsel_list, str, NULL);
+			if (err) {
+				fprintf(stderr,
+					"Cannot set up top down events %s: %d\n",
+					str, err);
+				free(str);
+				return -1;
+			}
+		} else {
+			fprintf(stderr, "System does not support topdown\n");
+			return -1;
+		}
+		free(str);
+		/*
+		 * Right now combining with the other attributes breaks group
+		 * semantics.
+		 */
+		return 0;
+	}
+
 	if (!evsel_list->nr_entries) {
 		if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
 			return -1;
@@ -2281,6 +2382,15 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	evlist__for_each (evsel_list, counter) {
 		/* Enable per core mode if only a single event requires it. */
 		if (counter->aggr_per_core) {
+			if (counter->aggr_per_core == 1 &&
+				single_thread)
+				continue;
+			else if (counter->aggr_per_core == 2 &&
+				single_thread) {
+				pr_err("single thread mode cannot be used with Hyper Threading enabled\n");
+				goto out;
+			}
+
 			if (stat_config.aggr_mode != AGGR_GLOBAL &&
 			    stat_config.aggr_mode != AGGR_CORE) {
 				pr_err("per core event configuration requires per core mode\n");
diff --git a/tools/perf/util/group.h b/tools/perf/util/group.h
new file mode 100644
index 0000000..daad3ff
--- /dev/null
+++ b/tools/perf/util/group.h
@@ -0,0 +1,7 @@
+#ifndef GROUP_H
+#define GROUP_H 1
+
+bool check_group(bool *warn);
+void group_warn(void);
+
+#endif
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 58c5831..3e65d61 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -248,6 +248,7 @@ cycles-ct					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
 cycles-t					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
 mem-loads					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
 mem-stores					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+topdown-[a-z-]+					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
 
 L1-dcache|l1-d|l1d|L1-data		|
 L1-icache|l1-i|l1i|L1-instruction	|
-- 
2.4.3