Skip to contentSkip to conversation

powerpc/perf: Add json file metric support for the hv_24x7 socket/chip level events

PATCH Superseded Kajol Jain 3 participants 21 messages Mar 9, 2020 – Mar 13, 2020

Subsystems (2)

v4 of 10 Superseded Latest is v10 →

lore
Share & tools
lore

Kajol Jain

author
#0 lore raw

v4 cover powerpc/perf: Add json file metric support for the hv_24x7 socket/chip level events

First patch of the patchset fix inconsistent results we are getting when we run multiple 24x7 events.

Patchset adds json file metric support for the hv_24x7 socket/chip level events. "hv_24x7" pmu interface events needs system dependent parameter like socket/chip/core. For example, hv_24x7 chip level events needs specific chip-id to which the data is requested should be added as part of pmu events.

So to enable JSON file support to "hv_24x7" interface, patchset expose total number of sockets and chips per-socket details in sysfs files (sockets, chips) under "/sys/devices/hv_24x7/interface/".

To get sockets and number of chips per sockets, patchset adds a rtas call with token "PROCESSOR_MODULE_INFO" to get these details. Patchset also handles partition migration case to re-init these system depended parameters by adding proper calls in post_mobility_fixup() (mobility.c).

Patch 6 & 8 of the patchset handles perf tool plumbing needed to replace the "?" character in the metric expression to proper value and hv_24x7 json metric file for different Socket/chip resources.

Patch set also enable Hz/hz prinitg for --metric-only option to print metric data for bus frequency.

Applied and tested all these patches cleanly on top of jiri's flex changes with the changes done by Kan Liang for "Support metric group constraint" patchset and made required changes.

Changelog:
v3 -> v4
- Made changes suggested by jiri.
- Apply these patch on top of Kan liang changes.

v2 -> v3
- Remove setting event_count to 0 part in function 'h_24x7_event_read' with comment rather then adding 0 to event_count value. Suggested by: Sukadev Bhattiprolu

- Apply tool side changes require to replace "?" on Jiri's flex patch series and made all require changes to make it compatible with added flex change.

v1 -> v2
- Rename hv-24x7 metric json file as nest_metrics.json

Kajol Jain (8):
powerpc/perf/hv-24x7: Fix inconsistent output values incase multiple
hv-24x7 events run
powerpc/hv-24x7: Add rtas call in hv-24x7 driver to get processor
details
powerpc/hv-24x7: Add sysfs files inside hv-24x7 device to show
processor details
Documentation/ABI: Add ABI documentation for chips and sockets powerpc/hv-24x7: Update post_mobility_fixup() to handle migration perf/tools: Enhance JSON/metric infrastructure to handle "?" tools/perf: Enable Hz/hz prinitg for --metric-only option perf/tools/pmu-events/powerpc: Add hv_24x7 socket/chip level metric
events

 .../sysfs-bus-event_source-devices-hv_24x7    |  14 ++
 arch/powerpc/perf/hv-24x7.c                   | 104 +++++++++++++--
 arch/powerpc/platforms/pseries/mobility.c     |  12 ++
 arch/powerpc/platforms/pseries/pseries.h      |   3 +
 tools/perf/arch/powerpc/util/header.c         |  22 ++++
 .../arch/powerpc/power9/nest_metrics.json     |  19 +++
 tools/perf/util/expr.h                        |   1 +
 tools/perf/util/expr.l                        |  19 ++-
 tools/perf/util/metricgroup.c                 | 124 ++++++++++++++----
 tools/perf/util/metricgroup.h                 |   1 +
 tools/perf/util/stat-display.c                |   2 -
 tools/perf/util/stat-shadow.c                 |   8 ++
 12 files changed, 290 insertions(+), 39 deletions(-)
 create mode 100644 tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json
Signature · 1 line
2.18.1
author
#1 lore raw

PATCH v4 1/8 powerpc/perf/hv-24x7: Fix inconsistent output values incase multiple hv-24x7 events run

Commit 2b206ee6b0df ("powerpc/perf/hv-24x7: Display change in counter values")' added to print _change_ in the counter value rather then raw value for 24x7 counters. Incase of transactions, the event count is set to 0 at the beginning of the transaction. It also sets the event's prev_count to the raw value at the time of initialization. Because of setting event count to 0, we are seeing some weird behaviour, whenever we run multiple 24x7 events at a time.

For example:

command#: ./perf stat -e "{hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/,

			   hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/}"
	  		   -C 0 -I 1000 sleep 100

     1.000121704                120 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/
     1.000121704                  5 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/
     2.000357733                  8 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/
     2.000357733                 10 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/
     3.000495215 18,446,744,073,709,551,616 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/
     3.000495215 18,446,744,073,709,551,616 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/
     4.000641884                 56 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/
     4.000641884 18,446,744,073,709,551,616 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/
     5.000791887 18,446,744,073,709,551,616 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/

Getting these large values in case we do -I.

As we are setting event_count to 0, for interval case, overall event_count is not coming in incremental order. As we may can get new delta lesser then previous count. Because of which when we print intervals, we are getting negative value which create these large values.

This patch removes part where we set event_count to 0 in function 'h_24x7_event_read'. There won't be much impact as we do set event->hw.prev_count to the raw value at the time of initialization to print change value.

With this patch
In power9 platform

command#: ./perf stat -e "{hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/,

		           hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/}"
			   -C 0 -I 1000 sleep 100

     1.000117685                 93 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/
     1.000117685                  1 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/
     2.000349331                 98 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/
     2.000349331                  2 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/
     3.000495900                131 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/
     3.000495900                  4 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/
     4.000645920                204 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/
     4.000645920                 61 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=1/
     4.284169997                 22 hv_24x7/PM_MCS01_128B_RD_DISP_PORT01,chip=0/
---
 arch/powerpc/perf/hv-24x7.c | 10 ----------
 1 file changed, 10 deletions(-)
arch/powerpc/perf/hv-24x7.c +0 -10
index 573e0b309c0c..48e8f4b17b91 100644
@@ -1400,16 +1400,6 @@ static void h_24x7_event_read(struct perf_event *event)
 			h24x7hw = &get_cpu_var(hv_24x7_hw);
 			h24x7hw->events[i] = event;
 			put_cpu_var(h24x7hw);
-			/*
-			 * Clear the event count so we can compute the _change_
-			 * in the 24x7 raw counter value at the end of the txn.
-			 *
-			 * Note that we could alternatively read the 24x7 value
-			 * now and save its value in event->hw.prev_count. But
-			 * that would require issuing a hcall, which would then
-			 * defeat the purpose of using the txn interface.
-			 */
-			local64_set(&event->count, 0);
 		}
 
 		put_cpu_var(hv_24x7_reqb);
Signature · 1 line
2.18.1
author
#2 lore raw

PATCH v4 2/8 powerpc/hv-24x7: Add rtas call in hv-24x7 driver to get processor details

In reply to Kajol Jain

For hv_24x7 socket/chip level events, specific chip-id to which the data requested should be added as part of pmu events. But number of chips/socket in the system details are not exposed.

Patch implements read_sys_info_pseries() to get system parameter values like number of sockets and chips per socket. Rtas_call with token "PROCESSOR_MODULE_INFO"
is used to get these values.

Sub-sequent patch exports these values via sysfs.

Patch also make these parameters default to 1.

---
 arch/powerpc/perf/hv-24x7.c              | 72 ++++++++++++++++++++++++
 arch/powerpc/platforms/pseries/pseries.h |  3 +
 2 files changed, 75 insertions(+)
arch/powerpc/perf/hv-24x7.c +72 -0
index 48e8f4b17b91..9ae00f29bd21 100644
@@ -20,6 +20,11 @@
 #include <asm/io.h>
 #include <linux/byteorder/generic.h>
 
+#ifdef CONFIG_PPC_RTAS
+#include <asm/rtas.h>
+#include <../../platforms/pseries/pseries.h>
+#endif
+
 #include "hv-24x7.h"
 #include "hv-24x7-catalog.h"
 #include "hv-common.h"
@@ -57,6 +62,69 @@ static bool is_physical_domain(unsigned domain)
 	}
 }
 
+#ifdef CONFIG_PPC_RTAS
+#define PROCESSOR_MODULE_INFO   43
+#define PROCESSOR_MAX_LENGTH	(8 * 1024)
+
+static int strbe16toh(const char *buf, int offset)
+{
+	return (buf[offset] << 8) + buf[offset + 1];
+}
+
+static u32		physsockets;	/* Physical sockets */
+static u32		physchips;	/* Physical chips */
+
+/*
+ * Function read_sys_info_pseries() make a rtas_call which require
+ * data buffer of size 8K. As standard 'rtas_data_buf' is of size
+ * 4K, we are adding new local buffer 'rtas_local_data_buf'.
+ */
+char rtas_local_data_buf[PROCESSOR_MAX_LENGTH] __cacheline_aligned;
+
+/*
+ * read_sys_info_pseries()
+ * Retrieve the number of sockets and chips per socket details
+ * through the get-system-parameter rtas call.
+ */
+void read_sys_info_pseries(void)
+{
+	int call_status, len, ntypes;
+
+	/*
+	 * Making system parameter: chips and sockets default to 1.
+	 */
+	physsockets = 1;
+	physchips = 1;
+	memset(rtas_local_data_buf, 0, PROCESSOR_MAX_LENGTH);
+	spin_lock(&rtas_data_buf_lock);
+
+	call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+				NULL,
+				PROCESSOR_MODULE_INFO,
+				__pa(rtas_local_data_buf),
+				PROCESSOR_MAX_LENGTH);
+
+	spin_unlock(&rtas_data_buf_lock);
+
+	if (call_status != 0) {
+		pr_info("%s %s Error calling get-system-parameter (0x%x)\n",
+			__FILE__, __func__, call_status);
+	} else {
+		rtas_local_data_buf[PROCESSOR_MAX_LENGTH - 1] = '\0';
+		len = strbe16toh(rtas_local_data_buf, 0);
+		if (len < 6)
+			return;
+
+		ntypes = strbe16toh(rtas_local_data_buf, 2);
+
+		if (!ntypes)
+			return;
+		physsockets = strbe16toh(rtas_local_data_buf, 4);
+		physchips = strbe16toh(rtas_local_data_buf, 6);
+	}
+}
+#endif /* CONFIG_PPC_RTAS */
+
 /* Domains for which more than one result element are returned for each event. */
 static bool domain_needs_aggregation(unsigned int domain)
 {
@@ -1605,6 +1673,10 @@ static int hv_24x7_init(void)
 	if (r)
 		return r;
 
+#ifdef CONFIG_PPC_RTAS
+	read_sys_info_pseries();
+#endif
+
 	return 0;
 }
 
arch/powerpc/platforms/pseries/pseries.h +3 -0
index 13fa370a87e4..1727559ce304 100644
@@ -19,6 +19,9 @@ extern void request_event_sources_irqs(struct device_node *np,
 struct pt_regs;
 
 extern int pSeries_system_reset_exception(struct pt_regs *regs);
+#ifdef CONFIG_PPC_RTAS
+extern void read_sys_info_pseries(void);
+#endif
 extern int pSeries_machine_check_exception(struct pt_regs *regs);
 extern long pseries_machine_check_realmode(struct pt_regs *regs);
 
Signature · 1 line
2.18.1
author
#3 lore raw

PATCH v4 3/8 powerpc/hv-24x7: Add sysfs files inside hv-24x7 device to show processor details

In reply to Kajol Jain

To expose the system dependent parameter like total number of sockets and numbers of chips per socket, patch adds two sysfs files. "sockets" and "chips" are added to /sys/devices/hv_24x7/interface/ of the "hv_24x7" pmu.

---
 arch/powerpc/perf/hv-24x7.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)
arch/powerpc/perf/hv-24x7.c +22 -0
index 9ae00f29bd21..a31bd5b88f7a 100644
@@ -454,6 +454,20 @@ static ssize_t device_show_string(struct device *dev,
 	return sprintf(buf, "%s\n", (char *)d->var);
 }
 
+#ifdef CONFIG_PPC_RTAS
+static ssize_t sockets_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", physsockets);
+}
+
+static ssize_t chips_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	return sprintf(buf, "%d\n", physchips);
+}
+#endif
+
 static struct attribute *device_str_attr_create_(char *name, char *str)
 {
 	struct dev_ext_attribute *attr = kzalloc(sizeof(*attr), GFP_KERNEL);
@@ -1100,6 +1114,10 @@ PAGE_0_ATTR(catalog_len, "%lld\n",
 		(unsigned long long)be32_to_cpu(page_0->length) * 4096);
 static BIN_ATTR_RO(catalog, 0/* real length varies */);
 static DEVICE_ATTR_RO(domains);
+#ifdef CONFIG_PPC_RTAS
+static DEVICE_ATTR_RO(sockets);
+static DEVICE_ATTR_RO(chips);
+#endif
 
 static struct bin_attribute *if_bin_attrs[] = {
 	&bin_attr_catalog,
@@ -1110,6 +1128,10 @@ static struct attribute *if_attrs[] = {
 	&dev_attr_catalog_len.attr,
 	&dev_attr_catalog_version.attr,
 	&dev_attr_domains.attr,
+#ifdef CONFIG_PPC_RTAS
+	&dev_attr_sockets.attr,
+	&dev_attr_chips.attr,
+#endif
 	NULL,
 };
 
Signature · 1 line
2.18.1
author
#4 lore raw

PATCH v4 4/8 Documentation/ABI: Add ABI documentation for chips and sockets

In reply to Kajol Jain

Add documentation for the following sysfs files:
/sys/devices/hv_24x7/interface/chips,
/sys/devices/hv_24x7/interface/sockets

---
 .../testing/sysfs-bus-event_source-devices-hv_24x7 | 14 ++++++++++++++
 1 file changed, 14 insertions(+)
Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 +14 -0
index ec27c6c9e737..e17e5b444a1c 100644
@@ -22,6 +22,20 @@ Description:
 		Exposes the "version" field of the 24x7 catalog. This is also
 		extractable from the provided binary "catalog" sysfs entry.
 
+What:		/sys/devices/hv_24x7/interface/sockets
+Date:		March 2020
+Contact:	Linux on PowerPC Developer List <[email protected]>
+Description:	read only
+		This sysfs interface exposes the number of sockets present in the
+		system.
+
+What:		/sys/devices/hv_24x7/interface/chips
+Date:		March 2020
+Contact:	Linux on PowerPC Developer List <[email protected]>
+Description:	read only
+		This sysfs interface exposes the number of chips per socket
+		present in the system.
+
 What:		/sys/bus/event_source/devices/hv_24x7/event_descs/<event-name>
 Date:		February 2014
 Contact:	Linux on PowerPC Developer List <[email protected]>
Signature · 1 line
2.18.1
author
#5 lore raw

PATCH v4 5/8 powerpc/hv-24x7: Update post_mobility_fixup() to handle migration

In reply to Kajol Jain

Function 'read_sys_info_pseries()' is added to get system parameter values like number of sockets and chips per socket.
and it gets these details via rtas_call with token "PROCESSOR_MODULE_INFO".

Incase lpar migrate from one system to another, system parameter details like chips per sockets or number of sockets might change. So, it needs to be re-initialized otherwise, these values corresponds to previous system values.
This patch adds a call to 'read_sys_info_pseries()' from 'post-mobility_fixup()' to re-init the physsockets and physchips values.

---
 arch/powerpc/platforms/pseries/mobility.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)
arch/powerpc/platforms/pseries/mobility.c +12 -0
index b571285f6c14..226accd6218b 100644
@@ -371,6 +371,18 @@ void post_mobility_fixup(void)
 	/* Possibly switch to a new RFI flush type */
 	pseries_setup_rfi_flush();
 
+	/*
+	 * Incase lpar migrate from one system to another, system
+	 * parameter details like chips per sockets and number of sockets
+	 * might change. So, it needs to be re-initialized otherwise these
+	 * values corresponds to previous system.
+	 * Here, adding a call to read_sys_info_pseries() declared in
+	 * platforms/pseries/pseries.h to re-init the physsockets and
+	 * physchips value.
+	 */
+	if (IS_ENABLED(CONFIG_HV_PERF_CTRS) && IS_ENABLED(CONFIG_PPC_RTAS))
+		read_sys_info_pseries();
+
 	return;
 }
 
Signature · 1 line
2.18.1
author
#6 lore raw

PATCH v4 6/8 perf/tools: Enhance JSON/metric infrastructure to handle "?"

In reply to Kajol Jain

Patch enhances current metric infrastructure to handle "?" in the metric expression. The "?" can be use for parameters whose value not known while creating metric events and which can be replace later at runtime to the proper value. It also add flexibility to create multiple events out of single metric event added in json file.

Patch adds function 'arch_get_runtimeparam' which is a arch specific function, returns the count of metric events need to be created. By default it return 1.

One loop is added in function 'metricgroup__add_metric', which create multiple events at run time depend on return value of 'arch_get_runtimeparam' and merge that event in 'group_list'.

This infrastructure needed for hv_24x7 socket/chip level events. "hv_24x7" chip level events needs specific chip-id to which the data is requested. Function 'arch_get_runtimeparam' implemented in header.c which extract number of sockets from sysfs file "sockets" under "/sys/devices/hv_24x7/interface/".

---
 tools/perf/arch/powerpc/util/header.c |  22 +++++
 tools/perf/util/expr.h                |   1 +
 tools/perf/util/expr.l                |  19 +++-
 tools/perf/util/metricgroup.c         | 124 ++++++++++++++++++++------
 tools/perf/util/metricgroup.h         |   1 +
 tools/perf/util/stat-shadow.c         |   8 ++
 6 files changed, 148 insertions(+), 27 deletions(-)
tools/perf/arch/powerpc/util/header.c +22 -0
index 3b4cdfc5efd6..036f6b2ce202 100644
@@ -7,6 +7,11 @@
 #include <string.h>
 #include <linux/stringify.h>
 #include "header.h"
+#include "metricgroup.h"
+#include "evlist.h"
+#include <dirent.h>
+#include "pmu.h"
+#include <api/fs/fs.h>
 
 #define mfspr(rn)       ({unsigned long rval; \
 			 asm volatile("mfspr %0," __stringify(rn) \
@@ -16,6 +21,8 @@
 #define PVR_VER(pvr)    (((pvr) >>  16) & 0xFFFF) /* Version field */
 #define PVR_REV(pvr)    (((pvr) >>   0) & 0xFFFF) /* Revison field */
 
+#define SOCKETS_INFO_FILE_PATH "/devices/hv_24x7/interface/"
+
 int
 get_cpuid(char *buffer, size_t sz)
 {
@@ -44,3 +51,18 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 
 	return bufp;
 }
+
+int arch_get_runtimeparam(void)
+{
+	int count;
+	char path[PATH_MAX];
+	char filename[] = "sockets";
+
+	snprintf(path, PATH_MAX,
+		 SOCKETS_INFO_FILE_PATH "%s", filename);
+
+	if (sysfs__read_ull(path, (unsigned long long *)&count) < 0)
+		return 1;
+	else
+		return count;
+}
tools/perf/util/expr.h +1 -0
index 9377538f4097..d17664e628db 100644
@@ -15,6 +15,7 @@ struct parse_ctx {
 	struct parse_id ids[MAX_PARSE_ID];
 };
 
+int expr__runtimeparam;
 void expr__ctx_init(struct parse_ctx *ctx);
 void expr__add_id(struct parse_ctx *ctx, const char *id, double val);
 int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr);
tools/perf/util/expr.l +17 -2
index 1928f2a3dddc..ec4b00671f67 100644
@@ -45,6 +45,21 @@ static char *normalize(char *str)
 			*dst++ = '/';
 		else if (*str == '\\')
 			*dst++ = *++str;
+        else if (*str == '?') {
+
+			int size = snprintf(NULL, 0, "%d", expr__runtimeparam);
+			char * paramval = (char *)malloc(size);
+			int i = 0;
+
+			if(!paramval)
+				*dst++ = '0';
+			else {
+				sprintf(paramval, "%d", expr__runtimeparam);
+				while(i < size)
+					*dst++ = paramval[i++];
+				free(paramval);
+			}
+		}
 		else
 			*dst++ = *str;
 		str++;
@@ -72,8 +87,8 @@ number		[0-9]+
 
 sch		[-,=]
 spec		\\{sch}
-sym		[0-9a-zA-Z_\.:@]+
-symbol		{spec}*{sym}*{spec}*{sym}*
+sym		[0-9a-zA-Z_\.:@?]+
+symbol		{spec}*{sym}*{spec}*{sym}*{spec}*{sym}
 
 %%
 	{
tools/perf/util/metricgroup.c +99 -25

140 lines not on this page · raw message

tools/perf/util/metricgroup.h +1 -0
index 475c7f912864..81224ba1270d 100644
@@ -34,4 +34,5 @@ int metricgroup__parse_groups(const struct option *opt,
 void metricgroup__print(bool metrics, bool groups, char *filter,
 			bool raw, bool details);
 bool metricgroup__has_metric(const char *metric);
+int arch_get_runtimeparam(void);
 #endif
tools/perf/util/stat-shadow.c +8 -0
index 0fd713d3674f..92c4c9abbaa0 100644
@@ -777,6 +777,14 @@ static void generic_metric(struct perf_stat_config *config,
 	}
 
 	if (!metric_events[i]) {
+
+		if (strstr(metric_expr, "?")) {
+			char *tmp = strrchr(metric_name, '_');
+
+			tmp++;
+			expr__runtimeparam = strtol(tmp, &tmp, 10);
+		}
+
 		if (expr__parse(&ratio, &pctx, metric_expr) == 0) {
 			char *unit;
 			char metric_bf[64];
Signature · 1 line
2.18.1
#7 lore raw

Re: [PATCH v4 6/8] perf/tools: Enhance JSON/metric infrastructure to handle "?"

Em Mon, Mar 09, 2020 at 11:55:50AM +0530, Kajol Jain escreveu:

Quoted 63 lines

Patch enhances current metric infrastructure to handle "?" in the metric expression. The "?" can be use for parameters whose value not known while creating metric events and which can be replace later at runtime to the proper value. It also add flexibility to create multiple events out of single metric event added in json file.

Patch adds function 'arch_get_runtimeparam' which is a arch specific function, returns the count of metric events need to be created. By default it return 1.

One loop is added in function 'metricgroup__add_metric', which create multiple events at run time depend on return value of 'arch_get_runtimeparam' and merge that event in 'group_list'.

This infrastructure needed for hv_24x7 socket/chip level events. "hv_24x7" chip level events needs specific chip-id to which the data is requested. Function 'arch_get_runtimeparam' implemented in header.c which extract number of sockets from sysfs file "sockets" under "/sys/devices/hv_24x7/interface/".

---
 tools/perf/arch/powerpc/util/header.c |  22 +++++
 tools/perf/util/expr.h                |   1 +
 tools/perf/util/expr.l                |  19 +++-
 tools/perf/util/metricgroup.c         | 124 ++++++++++++++++++++------
 tools/perf/util/metricgroup.h         |   1 +
 tools/perf/util/stat-shadow.c         |   8 ++
 6 files changed, 148 insertions(+), 27 deletions(-)
tools/perf/arch/powerpc/util/header.c +11 -0
index 3b4cdfc5efd6..036f6b2ce202 100644
@@ -7,6 +7,11 @@
 #include <string.h>
 #include <linux/stringify.h>
 #include "header.h"
+#include "metricgroup.h"
+#include "evlist.h"
+#include <dirent.h>
+#include "pmu.h"
+#include <api/fs/fs.h>
 
 #define mfspr(rn)       ({unsigned long rval; \
 			 asm volatile("mfspr %0," __stringify(rn) \
@@ -16,6 +21,8 @@
 #define PVR_VER(pvr)    (((pvr) >>  16) & 0xFFFF) /* Version field */
 #define PVR_REV(pvr)    (((pvr) >>   0) & 0xFFFF) /* Revison field */
 
+#define SOCKETS_INFO_FILE_PATH "/devices/hv_24x7/interface/"
+
 int
 get_cpuid(char *buffer, size_t sz)
 {
@@ -44,3 +51,18 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 
 	return bufp;
 }
+
+int arch_get_runtimeparam(void)
+{
+	int count;

tools/perf/arch/powerpc/util/header.c get_cpuid_str(struct perf_pmu *pmu __maybe_unused) · line 67

Quoted 10 lines
tools/perf/arch/powerpc/util/header.c +10 -0
+	char path[PATH_MAX];
+	char filename[] = "sockets";
+
+	snprintf(path, PATH_MAX,
+		 SOCKETS_INFO_FILE_PATH "%s", filename);
+
+	if (sysfs__read_ull(path, (unsigned long long *)&count) < 0)
+		return 1;
+	else
+		return count;

Why this cast dance? We have sysfs__read_int(path, &count).

Also this is more compact:

	return sysfs__read_int(path, &count) < 0 ? 1 : count;
Quoted 18 lines
tools/perf/arch/powerpc/util/header.c +1 -0
+}
tools/perf/util/expr.h +1 -0
index 9377538f4097..d17664e628db 100644
@@ -15,6 +15,7 @@ struct parse_ctx {
 	struct parse_id ids[MAX_PARSE_ID];
 };
 
+int expr__runtimeparam;
 void expr__ctx_init(struct parse_ctx *ctx);
 void expr__add_id(struct parse_ctx *ctx, const char *id, double val);
 int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr);
tools/perf/util/expr.l +0 -0
index 1928f2a3dddc..ec4b00671f67 100644

tools/perf/util/expr.l static char *normalize(char *str) · line 50

Quoted 6 lines
tools/perf/util/expr.l +3 -0
@@ -45,6 +45,21 @@ static char *normalize(char *str)
 			*dst++ = '/';
 		else if (*str == '\\')
 			*dst++ = *++str;
+        else if (*str == '?') {
+
+			int size = snprintf(NULL, 0, "%d", expr__runtimeparam);

TIL that C99 allows for a NULL str to format and return the number of bytes it would write if the string was large enough... wonders never cease :-)

tools/perf/util/expr.l static char *normalize(char *str) · line 51

Quoted 1 line
tools/perf/util/expr.l +1 -0
+			char * paramval = (char *)malloc(size);

No need for the cast, malloc returns void *, or has that changed? 8-) and please no space before the variable name.

Humm this is all complicated, why not use asprintf and have something like:

tools/perf/util/expr.l static char *normalize(char *str) · line 61

Quoted 10 lines
tools/perf/util/expr.l +10 -0
+			int i = 0;
+
+			if(!paramval)
+				*dst++ = '0';
+			else {
+				sprintf(paramval, "%d", expr__runtimeparam);
+				while(i < size)
+					*dst++ = paramval[i++];
+				free(paramval);
+			}
			char *paramval;
			int size = asprintf(&paramval, "%d", expr__runtimeparam);

			if (size < 0)
				*dst++ = '0';
			else {
				while (i < size)
					*dst++ = paramval[i++];
				free(paramval);
			}
Quoted 52 lines
tools/perf/util/expr.l +3 -2
+		}
 		else
 			*dst++ = *str;
 		str++;
@@ -72,8 +87,8 @@ number		[0-9]+
 
 sch		[-,=]
 spec		\\{sch}
-sym		[0-9a-zA-Z_\.:@]+
-symbol		{spec}*{sym}*{spec}*{sym}*
+sym		[0-9a-zA-Z_\.:@?]+
+symbol		{spec}*{sym}*{spec}*{sym}*{spec}*{sym}
 
 %%
 	{
tools/perf/util/metricgroup.c +29 -0
index c3a8c701609a..11eeeb929b91 100644
@@ -474,6 +474,98 @@ static bool metricgroup__has_constraint(struct pmu_event *pe)
 	return false;
 }
 
+int __weak arch_get_runtimeparam(void)
+{
+	return 1;
+}
+
+static int metricgroup__add_metric_runtime_param(struct strbuf *events,
+			struct list_head *group_list, struct pmu_event *pe)
+{
+	int i, count;
+	int ret = -EINVAL;
+
+	count = arch_get_runtimeparam();
+
+	/* This loop is added to create multiple
+	 * events depend on count value and add
+	 * those events to group_list.
+	 */
+
+	for (i = 0; i < count; i++) {
+		const char **ids;
+		int idnum;
+		struct egroup *eg;
+		char value[PATH_MAX];
+
+		expr__runtimeparam = i;
+
+		if (expr__find_other(pe->metric_expr,
+					NULL, &ids, &idnum) < 0)
+			return ret;

tools/perf/util/metricgroup.c static bool metricgroup__has_constraint(struct pmu_event *pe) · line 515

Quoted 10 lines
tools/perf/util/metricgroup.c +10 -0
+
+		if (events->len > 0)
+			strbuf_addf(events, ",");
+
+		if (metricgroup__has_constraint(pe))
+			metricgroup__add_metric_non_group(events, ids, idnum);
+		else
+			metricgroup__add_metric_weak_group(events, ids, idnum);
+
+		eg = malloc(sizeof(struct egroup));

Shorter form that works even if you change that type:

+ eg = malloc(sizeof(*eg));

tools/perf/util/metricgroup.c static bool metricgroup__has_constraint(struct pmu_event *pe) · line 523

Quoted 8 lines
tools/perf/util/metricgroup.c +8 -0
+		if (!eg) {
+			ret = -ENOMEM;
+			return ret;
+		}
+		sprintf(value, "%s%c%d", pe->metric_name, '_', i);
+		eg->ids = ids;
+		eg->idnum = idnum;
+		eg->metric_name = strdup(value);

Please check strdup() return just like you checked the malloc(sizeof(struct egroup)).

Quoted 11 lines
tools/perf/util/metricgroup.c +11 -0
+		eg->metric_expr = pe->metric_expr;
+		eg->metric_unit = pe->unit;
+		list_add_tail(&eg->nd, group_list);
+		ret = 0;
+
+		if (ret != 0)
+			break;
+	}
+	return ret;
+}
+static int metricgroup__add_metric_param(struct strbuf *events,

tools/perf/util/metricgroup.c static bool metricgroup__has_constraint(struct pmu_event *pe) · line 544

Quoted 10 lines
tools/perf/util/metricgroup.c +10 -0
+			struct list_head *group_list, struct pmu_event *pe)
+{
+
+	const char **ids;
+	int idnum;
+	struct egroup *eg;
+	int ret = -EINVAL;
+
+	if (expr__find_other(pe->metric_expr,
+					     NULL, &ids, &idnum) < 0)

Why break the above in two lines?

tools/perf/util/metricgroup.c static bool metricgroup__has_constraint(struct pmu_event *pe) · line 515

Quoted 10 lines
tools/perf/util/metricgroup.c +10 -0
+		return ret;
+	if (events->len > 0)
+		strbuf_addf(events, ",");
+
+	if (metricgroup__has_constraint(pe))
+		metricgroup__add_metric_non_group(events, ids, idnum);
+	else
+		metricgroup__add_metric_weak_group(events, ids, idnum);
+
+	eg = malloc(sizeof(struct egroup));

Ditto

Quoted 32 lines
tools/perf/util/metricgroup.c +14 -8
+	if (!eg)
+		ret = -ENOMEM;
+
+	eg->ids = ids;
+	eg->idnum = idnum;
+	eg->metric_name = pe->metric_name;
+	eg->metric_expr = pe->metric_expr;
+	eg->metric_unit = pe->unit;
+	list_add_tail(&eg->nd, group_list);
+	ret = 0;
+
+	return ret;
+}
+
 static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 				   struct list_head *group_list)
 {
@@ -493,35 +585,17 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 			continue;
 		if (match_metric(pe->metric_group, metric) ||
 		    match_metric(pe->metric_name, metric)) {
-			const char **ids;
-			int idnum;
-			struct egroup *eg;
 
 			pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
 
-			if (expr__find_other(pe->metric_expr,
-					     NULL, &ids, &idnum) < 0)
-				continue;
-			if (events->len > 0)
-				strbuf_addf(events, ",");

tools/perf/util/metricgroup.c static int metricgroup__add_metric(const char *metric, struct strbuf *events, · line 513

Quoted 10 lines
tools/perf/util/metricgroup.c +3 -6
-
-			if (metricgroup__has_constraint(pe))
-				metricgroup__add_metric_non_group(events, ids, idnum);
+			if (strstr(pe->metric_expr, "?"))
+				ret = metricgroup__add_metric_runtime_param(events,
+							group_list, pe);
 			else
-				metricgroup__add_metric_weak_group(events, ids, idnum);
-
-			eg = malloc(sizeof(struct egroup));
                                             *eg
Quoted 33 lines
tools/perf/util/metricgroup.c +4 -11
-			if (!eg) {
-				ret = -ENOMEM;
-				break;
-			}
-			eg->ids = ids;
-			eg->idnum = idnum;
-			eg->metric_name = pe->metric_name;
-			eg->metric_expr = pe->metric_expr;
-			eg->metric_unit = pe->unit;
-			list_add_tail(&eg->nd, group_list);
-			ret = 0;
+				ret = metricgroup__add_metric_param(events,
+							group_list, pe);
+			if (ret == -EINVAL)
+				continue;
 		}
 	}
 	return ret;
tools/perf/util/metricgroup.h +1 -0
index 475c7f912864..81224ba1270d 100644
@@ -34,4 +34,5 @@ int metricgroup__parse_groups(const struct option *opt,
 void metricgroup__print(bool metrics, bool groups, char *filter,
 			bool raw, bool details);
 bool metricgroup__has_metric(const char *metric);
+int arch_get_runtimeparam(void);
 #endif
tools/perf/util/stat-shadow.c +0 -0
index 0fd713d3674f..92c4c9abbaa0 100644

tools/perf/util/stat-shadow.c static void generic_metric(struct perf_stat_config *config, · line 783

Quoted 7 lines
tools/perf/util/stat-shadow.c +4 -0
@@ -777,6 +777,14 @@ static void generic_metric(struct perf_stat_config *config,
 	}
 
 	if (!metric_events[i]) {
+
+		if (strstr(metric_expr, "?")) {
+			char *tmp = strrchr(metric_name, '_');
+

So at this point a metric name is guaranteed to have a _?

Quoted 10 lines
tools/perf/util/stat-shadow.c +4 -0
+			tmp++;
+			expr__runtimeparam = strtol(tmp, &tmp, 10);
+		}
+
 		if (expr__parse(&ratio, &pctx, metric_expr) == 0) {
 			char *unit;
 			char metric_bf[64];
Signature · 1 line
2.18.1
Signature · 1 line
- Arnaldo
author
#8 lore raw

Re: [PATCH v4 6/8] perf/tools: Enhance JSON/metric infrastructure to handle "?"

Quoted 77 lines · Arnaldo Carvalho de Melo

Em Mon, Mar 09, 2020 at 11:55:50AM +0530, Kajol Jain escreveu:

Quoted 63 lines

Patch enhances current metric infrastructure to handle "?" in the metric expression. The "?" can be use for parameters whose value not known while creating metric events and which can be replace later at runtime to the proper value. It also add flexibility to create multiple events out of single metric event added in json file.

Patch adds function 'arch_get_runtimeparam' which is a arch specific function, returns the count of metric events need to be created. By default it return 1.

One loop is added in function 'metricgroup__add_metric', which create multiple events at run time depend on return value of 'arch_get_runtimeparam' and merge that event in 'group_list'.

This infrastructure needed for hv_24x7 socket/chip level events. "hv_24x7" chip level events needs specific chip-id to which the data is requested. Function 'arch_get_runtimeparam' implemented in header.c which extract number of sockets from sysfs file "sockets" under "/sys/devices/hv_24x7/interface/".

---
 tools/perf/arch/powerpc/util/header.c |  22 +++++
 tools/perf/util/expr.h                |   1 +
 tools/perf/util/expr.l                |  19 +++-
 tools/perf/util/metricgroup.c         | 124 ++++++++++++++++++++------
 tools/perf/util/metricgroup.h         |   1 +
 tools/perf/util/stat-shadow.c         |   8 ++
 6 files changed, 148 insertions(+), 27 deletions(-)
tools/perf/arch/powerpc/util/header.c +11 -0
index 3b4cdfc5efd6..036f6b2ce202 100644
@@ -7,6 +7,11 @@
 #include <string.h>
 #include <linux/stringify.h>
 #include "header.h"
+#include "metricgroup.h"
+#include "evlist.h"
+#include <dirent.h>
+#include "pmu.h"
+#include <api/fs/fs.h>
 
 #define mfspr(rn)       ({unsigned long rval; \
 			 asm volatile("mfspr %0," __stringify(rn) \
@@ -16,6 +21,8 @@
 #define PVR_VER(pvr)    (((pvr) >>  16) & 0xFFFF) /* Version field */
 #define PVR_REV(pvr)    (((pvr) >>   0) & 0xFFFF) /* Revison field */
 
+#define SOCKETS_INFO_FILE_PATH "/devices/hv_24x7/interface/"
+
 int
 get_cpuid(char *buffer, size_t sz)
 {
@@ -44,3 +51,18 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 
 	return bufp;
 }
+
+int arch_get_runtimeparam(void)
+{
+	int count;

tools/perf/arch/powerpc/util/header.c get_cpuid_str(struct perf_pmu *pmu __maybe_unused) · line 67

Quoted 10 lines
tools/perf/arch/powerpc/util/header.c +10 -0
+	char path[PATH_MAX];
+	char filename[] = "sockets";
+
+	snprintf(path, PATH_MAX,
+		 SOCKETS_INFO_FILE_PATH "%s", filename);
+
+	if (sysfs__read_ull(path, (unsigned long long *)&count) < 0)
+		return 1;
+	else
+		return count;

Why this cast dance? We have sysfs__read_int(path, &count).

Quoted 3 lines

Also this is more compact:

	return sysfs__read_int(path, &count) < 0 ? 1 : count;

Hi Arnaldo,
Yes it will be better to use like that.

Quoted 30 lines
Quoted 19 lines
tools/perf/arch/powerpc/util/header.c +1 -0
+}
tools/perf/util/expr.h +1 -0
index 9377538f4097..d17664e628db 100644
@@ -15,6 +15,7 @@ struct parse_ctx {
 	struct parse_id ids[MAX_PARSE_ID];
 };
 
+int expr__runtimeparam;
 void expr__ctx_init(struct parse_ctx *ctx);
 void expr__add_id(struct parse_ctx *ctx, const char *id, double val);
 int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr);
tools/perf/util/expr.l +0 -0
index 1928f2a3dddc..ec4b00671f67 100644

tools/perf/util/expr.l static char *normalize(char *str) · line 50

Quoted 6 lines
tools/perf/util/expr.l +3 -0
@@ -45,6 +45,21 @@ static char *normalize(char *str)
 			*dst++ = '/';
 		else if (*str == '\\')
 			*dst++ = *++str;
+        else if (*str == '?') {
+
+			int size = snprintf(NULL, 0, "%d", expr__runtimeparam);

TIL that C99 allows for a NULL str to format and return the number of bytes it would write if the string was large enough... wonders never cease :-)

Quoted 5 lines

tools/perf/util/expr.l static char *normalize(char *str) · line 51

Quoted 1 line
tools/perf/util/expr.l +1 -0
+			char * paramval = (char *)malloc(size);

No need for the cast, malloc returns void *, or has that changed? 8-) and please no space before the variable name.

Okk, Will take care of that.

Quoted 93 lines

Humm this is all complicated, why not use asprintf and have something like:

tools/perf/util/expr.l static char *normalize(char *str) · line 61

Quoted 10 lines
tools/perf/util/expr.l +10 -0
+			int i = 0;
+
+			if(!paramval)
+				*dst++ = '0';
+			else {
+				sprintf(paramval, "%d", expr__runtimeparam);
+				while(i < size)
+					*dst++ = paramval[i++];
+				free(paramval);
+			}
			char *paramval;
			int size = asprintf(&paramval, "%d", expr__runtimeparam);

			if (size < 0)
				*dst++ = '0';
			else {
				while (i < size)
					*dst++ = paramval[i++];
				free(paramval);
			}
Quoted 52 lines
tools/perf/util/expr.l +3 -2
+		}
 		else
 			*dst++ = *str;
 		str++;
@@ -72,8 +87,8 @@ number		[0-9]+
 
 sch		[-,=]
 spec		\\{sch}
-sym		[0-9a-zA-Z_\.:@]+
-symbol		{spec}*{sym}*{spec}*{sym}*
+sym		[0-9a-zA-Z_\.:@?]+
+symbol		{spec}*{sym}*{spec}*{sym}*{spec}*{sym}
 
 %%
 	{
tools/perf/util/metricgroup.c +29 -0
index c3a8c701609a..11eeeb929b91 100644
@@ -474,6 +474,98 @@ static bool metricgroup__has_constraint(struct pmu_event *pe)
 	return false;
 }
 
+int __weak arch_get_runtimeparam(void)
+{
+	return 1;
+}
+
+static int metricgroup__add_metric_runtime_param(struct strbuf *events,
+			struct list_head *group_list, struct pmu_event *pe)
+{
+	int i, count;
+	int ret = -EINVAL;
+
+	count = arch_get_runtimeparam();
+
+	/* This loop is added to create multiple
+	 * events depend on count value and add
+	 * those events to group_list.
+	 */
+
+	for (i = 0; i < count; i++) {
+		const char **ids;
+		int idnum;
+		struct egroup *eg;
+		char value[PATH_MAX];
+
+		expr__runtimeparam = i;
+
+		if (expr__find_other(pe->metric_expr,
+					NULL, &ids, &idnum) < 0)
+			return ret;

tools/perf/util/metricgroup.c static bool metricgroup__has_constraint(struct pmu_event *pe) · line 515

Quoted 10 lines
tools/perf/util/metricgroup.c +10 -0
+
+		if (events->len > 0)
+			strbuf_addf(events, ",");
+
+		if (metricgroup__has_constraint(pe))
+			metricgroup__add_metric_non_group(events, ids, idnum);
+		else
+			metricgroup__add_metric_weak_group(events, ids, idnum);
+
+		eg = malloc(sizeof(struct egroup));

Shorter form that works even if you change that type:

(quoted diff) +1 -0
+		eg = malloc(sizeof(*eg));
Quoted 10 lines

tools/perf/util/metricgroup.c static bool metricgroup__has_constraint(struct pmu_event *pe) · line 523

Quoted 8 lines
tools/perf/util/metricgroup.c +8 -0
+		if (!eg) {
+			ret = -ENOMEM;
+			return ret;
+		}
+		sprintf(value, "%s%c%d", pe->metric_name, '_', i);
+		eg->ids = ids;
+		eg->idnum = idnum;
+		eg->metric_name = strdup(value);

Please check strdup() return just like you checked the malloc(sizeof(struct egroup)).

Right, I missed that part, will update it.

Quoted 117 lines
Quoted 12 lines
tools/perf/util/metricgroup.c +11 -0
+		eg->metric_expr = pe->metric_expr;
+		eg->metric_unit = pe->unit;
+		list_add_tail(&eg->nd, group_list);
+		ret = 0;
+
+		if (ret != 0)
+			break;
+	}
+	return ret;
+}
+static int metricgroup__add_metric_param(struct strbuf *events,

tools/perf/util/metricgroup.c static bool metricgroup__has_constraint(struct pmu_event *pe) · line 544

Quoted 10 lines
tools/perf/util/metricgroup.c +10 -0
+			struct list_head *group_list, struct pmu_event *pe)
+{
+
+	const char **ids;
+	int idnum;
+	struct egroup *eg;
+	int ret = -EINVAL;
+
+	if (expr__find_other(pe->metric_expr,
+					     NULL, &ids, &idnum) < 0)

Why break the above in two lines?

tools/perf/util/metricgroup.c static bool metricgroup__has_constraint(struct pmu_event *pe) · line 515

Quoted 10 lines
tools/perf/util/metricgroup.c +10 -0
+		return ret;
+	if (events->len > 0)
+		strbuf_addf(events, ",");
+
+	if (metricgroup__has_constraint(pe))
+		metricgroup__add_metric_non_group(events, ids, idnum);
+	else
+		metricgroup__add_metric_weak_group(events, ids, idnum);
+
+	eg = malloc(sizeof(struct egroup));

Ditto

Quoted 32 lines
tools/perf/util/metricgroup.c +14 -8
+	if (!eg)
+		ret = -ENOMEM;
+
+	eg->ids = ids;
+	eg->idnum = idnum;
+	eg->metric_name = pe->metric_name;
+	eg->metric_expr = pe->metric_expr;
+	eg->metric_unit = pe->unit;
+	list_add_tail(&eg->nd, group_list);
+	ret = 0;
+
+	return ret;
+}
+
 static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 				   struct list_head *group_list)
 {
@@ -493,35 +585,17 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 			continue;
 		if (match_metric(pe->metric_group, metric) ||
 		    match_metric(pe->metric_name, metric)) {
-			const char **ids;
-			int idnum;
-			struct egroup *eg;
 
 			pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
 
-			if (expr__find_other(pe->metric_expr,
-					     NULL, &ids, &idnum) < 0)
-				continue;
-			if (events->len > 0)
-				strbuf_addf(events, ",");

tools/perf/util/metricgroup.c static int metricgroup__add_metric(const char *metric, struct strbuf *events, · line 513

Quoted 10 lines
tools/perf/util/metricgroup.c +3 -6
-
-			if (metricgroup__has_constraint(pe))
-				metricgroup__add_metric_non_group(events, ids, idnum);
+			if (strstr(pe->metric_expr, "?"))
+				ret = metricgroup__add_metric_runtime_param(events,
+							group_list, pe);
 			else
-				metricgroup__add_metric_weak_group(events, ids, idnum);
-
-			eg = malloc(sizeof(struct egroup));
                                             *eg
Quoted 35 lines
tools/perf/util/metricgroup.c +4 -11
-			if (!eg) {
-				ret = -ENOMEM;
-				break;
-			}
-			eg->ids = ids;
-			eg->idnum = idnum;
-			eg->metric_name = pe->metric_name;
-			eg->metric_expr = pe->metric_expr;
-			eg->metric_unit = pe->unit;
-			list_add_tail(&eg->nd, group_list);
-			ret = 0;
+				ret = metricgroup__add_metric_param(events,
+							group_list, pe);
+			if (ret == -EINVAL)
+				continue;
 		}
 	}
 	return ret;
tools/perf/util/metricgroup.h +1 -0
index 475c7f912864..81224ba1270d 100644
@@ -34,4 +34,5 @@ int metricgroup__parse_groups(const struct option *opt,
 void metricgroup__print(bool metrics, bool groups, char *filter,
 			bool raw, bool details);
 bool metricgroup__has_metric(const char *metric);
+int arch_get_runtimeparam(void);
 #endif
tools/perf/util/stat-shadow.c +0 -0
index 0fd713d3674f..92c4c9abbaa0 100644
@@ -777,6 +777,14 @@ static void generic_metric(struct perf_stat_config *config,
 	}
 
Quoted 7 lines

tools/perf/util/stat-shadow.c static void generic_metric(struct perf_stat_config *config, · line 783

Quoted 5 lines
tools/perf/util/stat-shadow.c +4 -0
 	if (!metric_events[i]) {
+
+		if (strstr(metric_expr, "?")) {
+			char *tmp = strrchr(metric_name, '_');
+

So at this point a metric name is guaranteed to have a _?

Yes, because we are appending '_' with parameter value in metric name when we adding these events in 'group_list'. So, I added it, because we can have multiple values of that runtime_parameter, so by appending it in metric name, we can understand to which event the counter data belongs. Thanks for reviewing the patch, I will send updated patch.

Thanks,
Kajol

Quoted 12 lines
Quoted 11 lines
tools/perf/util/stat-shadow.c +4 -0
+			tmp++;
+			expr__runtimeparam = strtol(tmp, &tmp, 10);
+		}
+
 		if (expr__parse(&ratio, &pctx, metric_expr) == 0) {
 			char *unit;
 			char metric_bf[64];
Signature · 1 line
2.18.1
#9 lore raw

Re: [PATCH v4 6/8] perf/tools: Enhance JSON/metric infrastructure to handle "?"

In reply to Arnaldo Carvalho de Melo

On Tue, Mar 10, 2020 at 03:34:55PM -0300, Arnaldo Carvalho de Melo wrote:

SNIP

Quoted 27 lines
Quoted 27 lines
tools/perf/arch/powerpc/util/header.c +7 -0
index 3b4cdfc5efd6..036f6b2ce202 100644
@@ -7,6 +7,11 @@
 #include <string.h>
 #include <linux/stringify.h>
 #include "header.h"
+#include "metricgroup.h"
+#include "evlist.h"
+#include <dirent.h>
+#include "pmu.h"
+#include <api/fs/fs.h>
 
 #define mfspr(rn)       ({unsigned long rval; \
 			 asm volatile("mfspr %0," __stringify(rn) \
@@ -16,6 +21,8 @@
 #define PVR_VER(pvr)    (((pvr) >>  16) & 0xFFFF) /* Version field */
 #define PVR_REV(pvr)    (((pvr) >>   0) & 0xFFFF) /* Revison field */
 
+#define SOCKETS_INFO_FILE_PATH "/devices/hv_24x7/interface/"
+
 int
 get_cpuid(char *buffer, size_t sz)
 {
@@ -44,3 +51,18 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 
Quoted 11 lines

tools/perf/arch/powerpc/util/header.c get_cpuid_str(struct perf_pmu *pmu __maybe_unused) · line 62

Quoted 11 lines
tools/perf/arch/powerpc/util/header.c +9 -0
 	return bufp;
 }
+
+int arch_get_runtimeparam(void)
+{
+	int count;
+	char path[PATH_MAX];
+	char filename[] = "sockets";
+
+	snprintf(path, PATH_MAX,
+		 SOCKETS_INFO_FILE_PATH "%s", filename);

also, what's the point of using snprintf in here?

jirka

#10 lore raw

Re: [PATCH v4 6/8] perf/tools: Enhance JSON/metric infrastructure to handle "?"

In reply to Kajol Jain

On Mon, Mar 09, 2020 at 11:55:50AM +0530, Kajol Jain wrote:

SNIP

Quoted 23 lines
tools/perf/util/metricgroup.c +15 -0
index c3a8c701609a..11eeeb929b91 100644
@@ -474,6 +474,98 @@ static bool metricgroup__has_constraint(struct pmu_event *pe)
 	return false;
 }
 
+int __weak arch_get_runtimeparam(void)
+{
+	return 1;
+}
+
+static int metricgroup__add_metric_runtime_param(struct strbuf *events,
+			struct list_head *group_list, struct pmu_event *pe)
+{
+	int i, count;
+	int ret = -EINVAL;
+
+	count = arch_get_runtimeparam();
+
+	/* This loop is added to create multiple
+	 * events depend on count value and add

tools/perf/util/metricgroup.c static bool metricgroup__has_constraint(struct pmu_event *pe) · line 501

Quoted 10 lines
tools/perf/util/metricgroup.c +10 -0
+	 * those events to group_list.
+	 */
+
+	for (i = 0; i < count; i++) {
+		const char **ids;
+		int idnum;
+		struct egroup *eg;
+		char value[PATH_MAX];
+
+		expr__runtimeparam = i;

so the expr__runtimeparam is always set before we call the expr parsing function - wither expr__find_other or expr__parse,

and it's used inside the normalize flexer function, which has access to the passed context.. so I don't see a reason why expr__runtimeparam couldn't be added in struct parse_ctx and used from there..

while in this, perhaps we should rename parse_ctx to expr_ctx, to keep the namespace straight (in separate patch)

thanks,
jirka

#11 lore raw

Re: [PATCH v4 6/8] perf/tools: Enhance JSON/metric infrastructure to handle "?"

In reply to Kajol Jain

On Mon, Mar 09, 2020 at 11:55:50AM +0530, Kajol Jain wrote:

SNIP

tools/perf/util/expr.l static char *normalize(char *str) · line 49

Quoted 10 lines
tools/perf/util/expr.l +2 -0
index 1928f2a3dddc..ec4b00671f67 100644
@@ -45,6 +45,21 @@ static char *normalize(char *str)
 			*dst++ = '/';
 		else if (*str == '\\')
 			*dst++ = *++str;
+        else if (*str == '?') {
+

extra line ^^^

jirka

Quoted 5 lines
tools/perf/util/expr.l +5 -0
+			int size = snprintf(NULL, 0, "%d", expr__runtimeparam);
+			char * paramval = (char *)malloc(size);
+			int i = 0;
+
+			if(!paramval)

SNIP

#12 lore raw

Re: [PATCH v4 6/8] perf/tools: Enhance JSON/metric infrastructure to handle "?"

In reply to Kajol Jain

On Mon, Mar 09, 2020 at 11:55:50AM +0530, Kajol Jain wrote:

SNIP

Quoted 39 lines
tools/perf/util/metricgroup.c +39 -0
+static int metricgroup__add_metric_runtime_param(struct strbuf *events,
+			struct list_head *group_list, struct pmu_event *pe)
+{
+	int i, count;
+	int ret = -EINVAL;
+
+	count = arch_get_runtimeparam();
+
+	/* This loop is added to create multiple
+	 * events depend on count value and add
+	 * those events to group_list.
+	 */
+
+	for (i = 0; i < count; i++) {
+		const char **ids;
+		int idnum;
+		struct egroup *eg;
+		char value[PATH_MAX];
+
+		expr__runtimeparam = i;
+
+		if (expr__find_other(pe->metric_expr,
+					NULL, &ids, &idnum) < 0)
+			return ret;
+
+		if (events->len > 0)
+			strbuf_addf(events, ",");
+
+		if (metricgroup__has_constraint(pe))
+			metricgroup__add_metric_non_group(events, ids, idnum);
+		else
+			metricgroup__add_metric_weak_group(events, ids, idnum);
+
+		eg = malloc(sizeof(struct egroup));
+		if (!eg) {
+			ret = -ENOMEM;
+			return ret;
+		}
+		sprintf(value, "%s%c%d", pe->metric_name, '_', i);

tools/perf/util/metricgroup.c static bool metricgroup__has_constraint(struct pmu_event *pe) · line 530

Quoted 10 lines
tools/perf/util/metricgroup.c +10 -0
+		eg->ids = ids;
+		eg->idnum = idnum;
+		eg->metric_name = strdup(value);
+		eg->metric_expr = pe->metric_expr;
+		eg->metric_unit = pe->unit;
+		list_add_tail(&eg->nd, group_list);
+		ret = 0;
+
+		if (ret != 0)
+			break;

the inside loop is essentialy what you factor out to metricgroup__add_metric_param right? please nove addition of metricgroup__add_metric_param function into separate patch

jirka

Quoted 37 lines
tools/perf/util/metricgroup.c +37 -0
+	}
+	return ret;
+}
+static int metricgroup__add_metric_param(struct strbuf *events,
+			struct list_head *group_list, struct pmu_event *pe)
+{
+
+	const char **ids;
+	int idnum;
+	struct egroup *eg;
+	int ret = -EINVAL;
+
+	if (expr__find_other(pe->metric_expr,
+					     NULL, &ids, &idnum) < 0)
+		return ret;
+	if (events->len > 0)
+		strbuf_addf(events, ",");
+
+	if (metricgroup__has_constraint(pe))
+		metricgroup__add_metric_non_group(events, ids, idnum);
+	else
+		metricgroup__add_metric_weak_group(events, ids, idnum);
+
+	eg = malloc(sizeof(struct egroup));
+	if (!eg)
+		ret = -ENOMEM;
+
+	eg->ids = ids;
+	eg->idnum = idnum;
+	eg->metric_name = pe->metric_name;
+	eg->metric_expr = pe->metric_expr;
+	eg->metric_unit = pe->unit;
+	list_add_tail(&eg->nd, group_list);
+	ret = 0;
+
+	return ret;
+}

SNIP

author
#13 lore raw

Re: [PATCH v4 6/8] perf/tools: Enhance JSON/metric infrastructure to handle "?"

Quoted 59 lines · Jiri Olsa

On Mon, Mar 09, 2020 at 11:55:50AM +0530, Kajol Jain wrote:

SNIP

Quoted 39 lines
tools/perf/util/metricgroup.c +39 -0
+static int metricgroup__add_metric_runtime_param(struct strbuf *events,
+			struct list_head *group_list, struct pmu_event *pe)
+{
+	int i, count;
+	int ret = -EINVAL;
+
+	count = arch_get_runtimeparam();
+
+	/* This loop is added to create multiple
+	 * events depend on count value and add
+	 * those events to group_list.
+	 */
+
+	for (i = 0; i < count; i++) {
+		const char **ids;
+		int idnum;
+		struct egroup *eg;
+		char value[PATH_MAX];
+
+		expr__runtimeparam = i;
+
+		if (expr__find_other(pe->metric_expr,
+					NULL, &ids, &idnum) < 0)
+			return ret;
+
+		if (events->len > 0)
+			strbuf_addf(events, ",");
+
+		if (metricgroup__has_constraint(pe))
+			metricgroup__add_metric_non_group(events, ids, idnum);
+		else
+			metricgroup__add_metric_weak_group(events, ids, idnum);
+
+		eg = malloc(sizeof(struct egroup));
+		if (!eg) {
+			ret = -ENOMEM;
+			return ret;
+		}
+		sprintf(value, "%s%c%d", pe->metric_name, '_', i);

tools/perf/util/metricgroup.c static bool metricgroup__has_constraint(struct pmu_event *pe) · line 530

Quoted 10 lines
tools/perf/util/metricgroup.c +10 -0
+		eg->ids = ids;
+		eg->idnum = idnum;
+		eg->metric_name = strdup(value);
+		eg->metric_expr = pe->metric_expr;
+		eg->metric_unit = pe->unit;
+		list_add_tail(&eg->nd, group_list);
+		ret = 0;
+
+		if (ret != 0)
+			break;

the inside loop is essentialy what you factor out to metricgroup__add_metric_param right? please nove addition of metricgroup__add_metric_param function into separate patch

Quoted 2 lines

jirka

Ok will put it in seperate patch.

Thanks,
kajol

Quoted 41 lines
Quoted 38 lines
tools/perf/util/metricgroup.c +37 -0
+	}
+	return ret;
+}
+static int metricgroup__add_metric_param(struct strbuf *events,
+			struct list_head *group_list, struct pmu_event *pe)
+{
+
+	const char **ids;
+	int idnum;
+	struct egroup *eg;
+	int ret = -EINVAL;
+
+	if (expr__find_other(pe->metric_expr,
+					     NULL, &ids, &idnum) < 0)
+		return ret;
+	if (events->len > 0)
+		strbuf_addf(events, ",");
+
+	if (metricgroup__has_constraint(pe))
+		metricgroup__add_metric_non_group(events, ids, idnum);
+	else
+		metricgroup__add_metric_weak_group(events, ids, idnum);
+
+	eg = malloc(sizeof(struct egroup));
+	if (!eg)
+		ret = -ENOMEM;
+
+	eg->ids = ids;
+	eg->idnum = idnum;
+	eg->metric_name = pe->metric_name;
+	eg->metric_expr = pe->metric_expr;
+	eg->metric_unit = pe->unit;
+	list_add_tail(&eg->nd, group_list);
+	ret = 0;
+
+	return ret;
+}

SNIP

#14 lore raw

Re: [PATCH v4 6/8] perf/tools: Enhance JSON/metric infrastructure to handle "?"

In reply to Kajol Jain

On Mon, Mar 09, 2020 at 11:55:50AM +0530, Kajol Jain wrote:

SNIP

Quoted 17 lines
tools/perf/util/expr.h +1 -0
index 9377538f4097..d17664e628db 100644
@@ -15,6 +15,7 @@ struct parse_ctx {
 	struct parse_id ids[MAX_PARSE_ID];
 };
 
+int expr__runtimeparam;
 void expr__ctx_init(struct parse_ctx *ctx);
 void expr__add_id(struct parse_ctx *ctx, const char *id, double val);
 int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr);
tools/perf/util/expr.l +0 -0
index 1928f2a3dddc..ec4b00671f67 100644

tools/perf/util/expr.l static char *normalize(char *str) · line 51

Quoted 7 lines
tools/perf/util/expr.l +4 -0
@@ -45,6 +45,21 @@ static char *normalize(char *str)
 			*dst++ = '/';
 		else if (*str == '\\')
 			*dst++ = *++str;
+        else if (*str == '?') {
+
+			int size = snprintf(NULL, 0, "%d", expr__runtimeparam);
+			char * paramval = (char *)malloc(size);

can't we agree that any reasonable number in here
wouldn't cross 20 bytes in string or so and use
buffer for that instead of that malloc exercise?

thanks,
jirka

Quoted 11 lines
tools/perf/util/expr.l +11 -0
+			int i = 0;
+
+			if(!paramval)
+				*dst++ = '0';
+			else {
+				sprintf(paramval, "%d", expr__runtimeparam);
+				while(i < size)
+					*dst++ = paramval[i++];
+				free(paramval);
+			}
+		}

SNIP

author
#15 lore raw

PATCH v4 7/8 tools/perf: Enable Hz/hz prinitg for --metric-only option

In reply to Kajol Jain

Commit 54b5091606c18 ("perf stat: Implement --metric-only mode") added function 'valid_only_metric()' which drops "Hz" or "hz", if it is part of "ScaleUnit". This patch enable it since hv_24x7 supports couple of frequency events.

---
 tools/perf/util/stat-display.c | 2 --
 1 file changed, 2 deletions(-)
tools/perf/util/stat-display.c +0 -2
index 16efdba1973a..ecdebfcdd379 100644
@@ -237,8 +237,6 @@ static bool valid_only_metric(const char *unit)
 	if (!unit)
 		return false;
 	if (strstr(unit, "/sec") ||
-	    strstr(unit, "hz") ||
-	    strstr(unit, "Hz") ||
 	    strstr(unit, "CPUs utilized"))
 		return false;
 	return true;
Signature · 1 line
2.18.1
author
#16 lore raw

PATCH v4 8/8 perf/tools/pmu-events/powerpc: Add hv_24x7 socket/chip level metric events

In reply to Kajol Jain

The hv_24×7 feature in IBM® POWER9™ processor-based servers provide the facility to continuously collect large numbers of hardware performance metrics efficiently and accurately.
This patch adds hv_24x7 metric file for different Socket/chip resources.

Result:

power9 platform:

command:# ./perf stat --metric-only -M Memory_RD_BW_Chip -C 0 -I 1000

     1.000096188                      0.9                      0.3
     2.000285720                      0.5                      0.1
     3.000424990                      0.4                      0.1

command:# ./perf stat --metric-only -M PowerBUS_Frequency -C 0 -I 1000

     1.000097981                        2.3                        2.3
     2.000291713                        2.3                        2.3
     3.000421719                        2.3                        2.3
     4.000550912                        2.3                        2.3
---
 .../arch/powerpc/power9/nest_metrics.json     | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json
tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json new file +19 -0
new file mode 100644
index 000000000000..ac38f5540ac6
@@ -0,0 +1,19 @@
+[
+    {
+        "MetricExpr": "(hv_24x7@PM_MCS01_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS01_128B_RD_DISP_PORT23\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT23\\,chip\\=?@)",
+        "MetricName": "Memory_RD_BW_Chip",
+        "MetricGroup": "Memory_BW",
+        "ScaleUnit": "1.6e-2MB"
+    },
+    {
+    "MetricExpr": "(hv_24x7@PM_MCS01_128B_WR_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS01_128B_WR_DISP_PORT23\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_WR_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_WR_DISP_PORT23\\,chip\\=?@ )",
+        "MetricName": "Memory_WR_BW_Chip",
+        "MetricGroup": "Memory_BW",
+        "ScaleUnit": "1.6e-2MB"
+    },
+    {
+    "MetricExpr": "(hv_24x7@PM_PB_CYC\\,chip\\=?@ )",
+        "MetricName": "PowerBUS_Frequency",
+        "ScaleUnit": "2.5e-7GHz"
+    }
+]
Signature · 1 line
2.18.1
#17 lore raw
In reply to Kajol Jain
Quoted 25 lines · Kajol Jain

First patch of the patchset fix inconsistent results we are getting when we run multiple 24x7 events.

Patchset adds json file metric support for the hv_24x7 socket/chip level events. "hv_24x7" pmu interface events needs system dependent parameter like socket/chip/core. For example, hv_24x7 chip level events needs specific chip-id to which the data is requested should be added as part of pmu events.

So to enable JSON file support to "hv_24x7" interface, patchset expose total number of sockets and chips per-socket details in sysfs files (sockets, chips) under "/sys/devices/hv_24x7/interface/".

To get sockets and number of chips per sockets, patchset adds a rtas call with token "PROCESSOR_MODULE_INFO" to get these details. Patchset also handles partition migration case to re-init these system depended parameters by adding proper calls in post_mobility_fixup() (mobility.c).

Patch 6 & 8 of the patchset handles perf tool plumbing needed to replace the "?" character in the metric expression to proper value and hv_24x7 json metric file for different Socket/chip resources.

Patch set also enable Hz/hz prinitg for --metric-only option to print metric data for bus frequency.

Quoted 7 lines

Applied and tested all these patches cleanly on top of jiri's flex changes with the changes done by Kan Liang for "Support metric group constraint" patchset and made required changes.

Changelog:
v3 -> v4
- Made changes suggested by jiri.

could you please mention them next time? ;-)

Quoted 1 line

- Apply these patch on top of Kan liang changes.

Arnaldo, could you please pull the expr flex changes and Kan's metric group constraint changes? it's both prereq of this patchset

thanks,
jirka

#18 lore raw

Sure, will do it today

Quoted 55 lines · Jiri Olsa
Quoted 1 line · Kajol Jain

First patch of the patchset fix inconsistent results we are getting

when

Quoted 3 lines

we run multiple 24x7 events.

Patchset adds json file metric support for the hv_24x7 socket/chip

level

Quoted 1 line

events. "hv_24x7" pmu interface events needs system dependent

parameter

Quoted 2 lines

like socket/chip/core. For example, hv_24x7 chip level events needs specific chip-id to which the data is requested should be added as

part

Quoted 3 lines

of pmu events.

So to enable JSON file support to "hv_24x7" interface, patchset

expose

Quoted 4 lines

total number of sockets and chips per-socket details in sysfs files (sockets, chips) under "/sys/devices/hv_24x7/interface/".

To get sockets and number of chips per sockets, patchset adds a rtas

call

Quoted 1 line

with token "PROCESSOR_MODULE_INFO" to get these details. Patchset

also

Quoted 2 lines

handles partition migration case to re-init these system depended parameters by adding proper calls in post_mobility_fixup()

(mobility.c).

Quoted 2 lines

Patch 6 & 8 of the patchset handles perf tool plumbing needed to

replace

Quoted 1 line

the "?" character in the metric expression to proper value and

hv_24x7

Quoted 6 lines

json metric file for different Socket/chip resources.

Patch set also enable Hz/hz prinitg for --metric-only option to print metric data for bus frequency.

Applied and tested all these patches cleanly on top of jiri's flex

changes

Quoted 1 line

with the changes done by Kan Liang for "Support metric group

constraint"

Quoted 5 lines

patchset and made required changes.

Changelog:
v3 -> v4
- Made changes suggested by jiri.

could you please mention them next time? ;-)

Quoted 1 line

- Apply these patch on top of Kan liang changes.

Arnaldo, could you please pull the expr flex changes and Kan's metric group constraint changes? it's both prereq of this patchset

thanks,
jirka

Signature · 1 line
Sent from my Android device with K-9 Mail. Please excuse my brevity.
#19 lore raw
In reply to Jiri Olsa

Em Mon, Mar 09, 2020 at 10:35:06AM +0100, Jiri Olsa escreveu:

Quoted 34 lines · Kajol Jain
Quoted 25 lines

First patch of the patchset fix inconsistent results we are getting when we run multiple 24x7 events.

Patchset adds json file metric support for the hv_24x7 socket/chip level events. "hv_24x7" pmu interface events needs system dependent parameter like socket/chip/core. For example, hv_24x7 chip level events needs specific chip-id to which the data is requested should be added as part of pmu events.

So to enable JSON file support to "hv_24x7" interface, patchset expose total number of sockets and chips per-socket details in sysfs files (sockets, chips) under "/sys/devices/hv_24x7/interface/".

To get sockets and number of chips per sockets, patchset adds a rtas call with token "PROCESSOR_MODULE_INFO" to get these details. Patchset also handles partition migration case to re-init these system depended parameters by adding proper calls in post_mobility_fixup() (mobility.c).

Patch 6 & 8 of the patchset handles perf tool plumbing needed to replace the "?" character in the metric expression to proper value and hv_24x7 json metric file for different Socket/chip resources.

Patch set also enable Hz/hz prinitg for --metric-only option to print metric data for bus frequency.

Quoted 7 lines

Applied and tested all these patches cleanly on top of jiri's flex changes with the changes done by Kan Liang for "Support metric group constraint" patchset and made required changes.

Changelog:
v3 -> v4
- Made changes suggested by jiri.

Quoted 6 lines

could you please mention them next time? ;-)

Quoted 1 line

- Apply these patch on top of Kan liang changes.

Arnaldo, could you please pull the expr flex changes and Kan's metric group constraint changes? it's both prereq of this patchset

Both are now in my perf/core branch, will go upstream soon, should I go and pickup the perf tooling bits in this patchkit?

- Arnaldo

#20 lore raw
Quoted 37 lines · Arnaldo Carvalho de Melo

Em Mon, Mar 09, 2020 at 10:35:06AM +0100, Jiri Olsa escreveu:

Quoted 36 lines · Kajol Jain
Quoted 25 lines

First patch of the patchset fix inconsistent results we are getting when we run multiple 24x7 events.

Patchset adds json file metric support for the hv_24x7 socket/chip level events. "hv_24x7" pmu interface events needs system dependent parameter like socket/chip/core. For example, hv_24x7 chip level events needs specific chip-id to which the data is requested should be added as part of pmu events.

So to enable JSON file support to "hv_24x7" interface, patchset expose total number of sockets and chips per-socket details in sysfs files (sockets, chips) under "/sys/devices/hv_24x7/interface/".

To get sockets and number of chips per sockets, patchset adds a rtas call with token "PROCESSOR_MODULE_INFO" to get these details. Patchset also handles partition migration case to re-init these system depended parameters by adding proper calls in post_mobility_fixup() (mobility.c).

Patch 6 & 8 of the patchset handles perf tool plumbing needed to replace the "?" character in the metric expression to proper value and hv_24x7 json metric file for different Socket/chip resources.

Patch set also enable Hz/hz prinitg for --metric-only option to print metric data for bus frequency.

Quoted 7 lines

Applied and tested all these patches cleanly on top of jiri's flex changes with the changes done by Kan Liang for "Support metric group constraint" patchset and made required changes.

Changelog:
v3 -> v4
- Made changes suggested by jiri.

could you please mention them next time? ;-)

Quoted 7 lines
Quoted 4 lines
Quoted 1 line

- Apply these patch on top of Kan liang changes.

Arnaldo, could you please pull the expr flex changes and Kan's metric group constraint changes? it's both prereq of this patchset

Both are now in my perf/core branch, will go upstream soon, should I go and pickup the perf tooling bits in this patchkit?

Kajol mentioned there are still some issues with the global variable, I plan to check on it this week

thanks,
jirka