Skip to contentSkip to conversation

perf/urgent fixes

GIT PULL New Arnaldo Carvalho de Melo 2 participants 11 messages Dec 16, 2019 – Dec 17, 2019 perf events

lore
Share & tools
lore

Arnaldo Carvalho de Melo

author maintainer
#0 lore raw

Hi Ingo/Thomas,

Please consider pulling,

Best regards,

- Arnaldo

The following changes since commit 761bfc33dd7504de951aa7b9db27a3cc5df1fde6:

Merge remote-tracking branch 'torvalds/master' into perf/urgent (2019-12-11 09:58:16 -0300)

are available in the Git repository at:

git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-urgent-for-mingo-5.5-20191216

for you to fetch changes up to 58b3bafff8257c6946df5d6aeb215b8ac839ed2a:

perf vendor events s390: Remove name from L1D_RO_EXCL_WRITES description (2019-12-16 13:40:26 -0300)

----------------------------------------------------------------
perf/urgent fixes:

perf top:

Arnaldo Carvalho de Melo:

- Do not bail out when perf_env__read_cpuid() returns ENOSYS, which has been reported happening on aarch64.

perf metricgroup:

Kajol Jain:

- Fix printing event names of metric group with multiple events

vendor events:

x86:

Ravi Bangoria:

- Fix Kernel_Utilization metric.

s390:

Ed Maste:

- Fix counter long description for DTLB1_GPAGE_WRITES and L1D_RO_EXCL_WRITES.

perf header:

Michael Petlan:

- Fix false warning when there are no duplicate cache entries

libtraceevent:

Sudip Mukherjee:

- Allow custom libdir path

API headers:

Arnaldo Carvalho de Melo:

- Sync linux/kvm.h with the kernel sources.

----------------------------------------------------------------
Arnaldo Carvalho de Melo (3):
tools headers kvm: Sync linux/kvm.h with the kernel sources perf arch: Make the default get_cpuid() return compatible error perf top: Do not bail out when perf_env__read_cpuid() returns ENOSYS

Ed Maste (2):
perf vendor events s390: Fix counter long description for DTLB1_GPAGE_WRITES perf vendor events s390: Remove name from L1D_RO_EXCL_WRITES description

Kajol Jain (1):
perf metricgroup: Fix printing event names of metric group with multiple events

Michael Petlan (1):
perf header: Fix false warning when there are no duplicate cache entries

Ravi Bangoria (1):
perf/x86/pmu-events: Fix Kernel_Utilization metric

Sudip Mukherjee (1):
libtraceevent: Allow custom libdir path

 tools/include/uapi/linux/kvm.h                     |  1 +
 tools/lib/traceevent/Makefile                      |  5 +++--
 tools/lib/traceevent/plugins/Makefile              |  5 +++--
 tools/perf/builtin-top.c                           | 10 +++++++---
 .../perf/pmu-events/arch/s390/cf_z13/extended.json |  2 +-
 .../perf/pmu-events/arch/s390/cf_z14/extended.json |  2 +-
 .../pmu-events/arch/x86/broadwell/bdw-metrics.json |  2 +-
 .../arch/x86/broadwellde/bdwde-metrics.json        |  2 +-
 .../arch/x86/broadwellx/bdx-metrics.json           |  2 +-
 .../arch/x86/cascadelakex/clx-metrics.json         |  2 +-
 .../pmu-events/arch/x86/haswell/hsw-metrics.json   |  2 +-
 .../pmu-events/arch/x86/haswellx/hsx-metrics.json  |  2 +-
 .../pmu-events/arch/x86/ivybridge/ivb-metrics.json |  2 +-
 .../pmu-events/arch/x86/ivytown/ivt-metrics.json   |  2 +-
 .../pmu-events/arch/x86/jaketown/jkt-metrics.json  |  2 +-
 .../arch/x86/sandybridge/snb-metrics.json          |  2 +-
 .../pmu-events/arch/x86/skylake/skl-metrics.json   |  2 +-
 .../pmu-events/arch/x86/skylakex/skx-metrics.json  |  2 +-
 tools/perf/util/header.c                           | 23 +++++++---------------
 tools/perf/util/metricgroup.c                      |  7 +++++--
 20 files changed, 40 insertions(+), 39 deletions(-)
author maintainer
#1 lore raw

PATCH 1/9 tools headers kvm: Sync linux/kvm.h with the kernel sources

From: Arnaldo Carvalho de Melo <[email protected]>

To pick up the changes from:

22945688acd4 ("KVM: PPC: Book3S HV: Support reset of secure guest")

No tools changes are caused by this, as the only defines so far used from these files are for syscall arg pretty printing are:

  $ grep KVM tools/perf/trace/beauty/*.sh
  tools/perf/trace/beauty/kvm_ioctl.sh:regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
  $

This addresses these tools/perf build warnings:

Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h' diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h

---
 tools/include/uapi/linux/kvm.h | 1 +
 1 file changed, 1 insertion(+)
tools/include/uapi/linux/kvm.h +1 -0
index e6f17c8e2dba..f0a16b4adbbd 100644
@@ -1348,6 +1348,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)
 /* Available with KVM_CAP_PMU_EVENT_FILTER */
 #define KVM_SET_PMU_EVENT_FILTER  _IOW(KVMIO,  0xb2, struct kvm_pmu_event_filter)
+#define KVM_PPC_SVM_OFF		  _IO(KVMIO,  0xb3)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
Signature · 1 line
2.21.0
author maintainer
#2 lore raw

PATCH 2/9 perf arch: Make the default get_cpuid() return compatible error

In reply to Arnaldo Carvalho de Melo

From: Arnaldo Carvalho de Melo <[email protected]>

Some of the functions calling get_cpuid() propagate back the error it returns, and all are using errno (positive) values, make the weak default get_cpuid() function return ENOSYS to be consistent and to allow checking if this is an arch not providing this function or if a provided one is having trouble getting the cpuid, to decide if the warning should be provided to the user or just a debug message should be emitted.

---
 tools/perf/util/header.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/header.c +1 -1
index becc2d109423..4d39a75551a0 100644
@@ -850,7 +850,7 @@ int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
  */
 int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused)
 {
-	return -1;
+	return ENOSYS; /* Not implemented */
 }
 
 static int write_cpuid(struct feat_fd *ff,
Signature · 1 line
2.21.0
author maintainer
#3 lore raw

PATCH 3/9 perf top: Do not bail out when perf_env__read_cpuid() returns ENOSYS

In reply to Arnaldo Carvalho de Melo

From: Arnaldo Carvalho de Melo <[email protected]>

'perf top' stopped working on hw architectures that do not provide a get_cpuid() implementation and thus fallback to the weak get_cpuid() default function.

This is done because at annotation time we may need it in the arch specific annotation init routine, but that is only being used by arches that do provide a get_cpuid() implementation:

  $ find tools/  -name "*.[ch]" | xargs grep 'evlist->env'
  tools/perf/builtin-top.c:	top.evlist->env = &perf_env;
  tools/perf/util/evsel.c:		return evsel->evlist->env;
  tools/perf/util/s390-cpumsf.c:	sf->machine_type = s390_cpumsf_get_type(session->evlist->env->cpuid);
  tools/perf/util/header.c:	session->evlist->env = &header->env;
  tools/perf/util/sample-raw.c:	const char *arch_pf = perf_env__arch(evlist->env);
  $
  $ find tools/perf/arch  -name "*.[ch]" | xargs grep -w get_cpuid
  tools/perf/arch/x86/util/auxtrace.c:	ret = get_cpuid(buffer, sizeof(buffer));
  tools/perf/arch/x86/util/header.c:get_cpuid(char *buffer, size_t sz)
  tools/perf/arch/powerpc/util/header.c:get_cpuid(char *buffer, size_t sz)
  tools/perf/arch/s390/util/header.c: * Implementation of get_cpuid().
  tools/perf/arch/s390/util/header.c:int get_cpuid(char *buffer, size_t sz)
  tools/perf/arch/s390/util/header.c:	if (buf && get_cpuid(buf, 128))
  $

For 'report' or 'script', i.e. tools working on perf.data files, that is setup while reading the header, its just top that needs to explicitely read it at tool start.

Fixes 608127f73779 ("perf top: Initialize perf_env->cpuid, needed by the per arch annotation init routine")
Cc Adrian Hunter <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Will Deacon <[email protected]>
---
 tools/perf/builtin-top.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)
tools/perf/builtin-top.c +7 -3
index dc80044bc46f..795e353de095 100644
@@ -1568,9 +1568,13 @@ int cmd_top(int argc, const char **argv)
 	 */
 	status = perf_env__read_cpuid(&perf_env);
 	if (status) {
-		pr_err("Couldn't read the cpuid for this machine: %s\n",
-		       str_error_r(errno, errbuf, sizeof(errbuf)));
-		goto out_delete_evlist;
+		/*
+		 * Some arches do not provide a get_cpuid(), so just use pr_debug, otherwise
+		 * warn the user explicitely.
+		 */
+		eprintf(status == ENOSYS ? 1 : 0, verbose,
+			"Couldn't read the cpuid for this machine: %s\n",
+			str_error_r(errno, errbuf, sizeof(errbuf)));
 	}
 	top.evlist->env = &perf_env;
 
Signature · 1 line
2.21.0
author maintainer
#4 lore raw

PATCH 4/9 perf/x86/pmu-events: Fix Kernel_Utilization metric

In reply to Arnaldo Carvalho de Melo

From: Ravi Bangoria <[email protected]>

Kernel Utilization should divide ref cycles spent in kernel with total ref cycles.

---
 tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json     | 2 +-
 tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json | 2 +-
 tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json    | 2 +-
 tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json  | 2 +-
 tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json       | 2 +-
 tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json      | 2 +-
 tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json     | 2 +-
 tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json       | 2 +-
 tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json      | 2 +-
 tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json   | 2 +-
 tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json       | 2 +-
 tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json      | 2 +-
 12 files changed, 12 insertions(+), 12 deletions(-)
tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +1 -1
index bc7151d639d7..45a34ce4fe89 100644
@@ -297,7 +297,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +1 -1
index 49c5f123d811..961fe4395758 100644
@@ -115,7 +115,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +1 -1
index 113d19e92678..746734ce09be 100644
@@ -297,7 +297,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +1 -1
index 2ba32af9bc36..f94653229dd4 100644
@@ -315,7 +315,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +1 -1
index c80f16fde6d0..5402cd3120f9 100644
@@ -267,7 +267,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +1 -1
index e501729c3dd1..832f3cb40b34 100644
@@ -267,7 +267,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +1 -1
index e2446966b651..d69b2a8fc0bc 100644
@@ -285,7 +285,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +1 -1
index 9294769dec64..5f465fd81315 100644
@@ -285,7 +285,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +1 -1
index 603ff9c2e9a1..3e909b306003 100644
@@ -171,7 +171,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +1 -1
index c6b485b3a2cb..50c053235752 100644
@@ -171,7 +171,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +1 -1
index 0ca539bb60f6..e7feb60f9fa9 100644
@@ -303,7 +303,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +1 -1
index 047d7e11aa6f..21d7a0c2c2e8 100644
@@ -315,7 +315,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
Signature · 1 line
2.21.0
author maintainer
#5 lore raw

PATCH 5/9 perf metricgroup: Fix printing event names of metric group with multiple events

In reply to Arnaldo Carvalho de Melo

From: Kajol Jain <[email protected]>

Commit f01642e4912b ("perf metricgroup: Support multiple events for metricgroup") introduced support for multiple events in a metric group. But with the current upstream, metric events names are not printed properly

In power9 platform:

command:# ./perf stat --metric-only -M translation -C 0 -I 1000 sleep 2

     1.000208486
     2.000368863
     2.001400558

Similarly in skylake platform:

command:./perf stat --metric-only -M Power -I 1000

     1.000579994
     2.002189493

With current upstream version, issue is with event name comparison logic in find_evsel_group(). Current logic is to compare events belonging to a metric group to the events in perf_evlist. Since the break statement is missing in the loop used for comparison between metric group and perf_evlist events, the loop continues to execute even after getting a pattern match, and end up in discarding the matches.

Incase of single metric event belongs to metric group, its working fine, because in case of single event once it compare all events it reaches to end of perf_evlist.

Example for single metric event in power9 platform:

command:# ./perf stat --metric-only -M branches_per_inst -I 1000 sleep 1

     1.000094653                  0.2
     1.001337059                  0.0

This patch fixes the issue by making sure once we found all events belongs to that metric event matched in find_evsel_group(), we successfully break from that loop by adding corresponding condition.

With this patch:
In power9 platform:

command:# ./perf stat --metric-only -M translation -C 0 -I 1000 sleep 2
result:#
time derat_4k_miss_rate_percent derat_4k_miss_ratio derat_miss_ratio derat_64k_miss_rate_percent derat_64k_miss_ratio dslb_miss_rate_percent islb_miss_rate_percent
1.000135672 0.0 0.3 1.0 0.0 0.2 0.0 0.0
2.000380617 0.0 0.0 0.0 0.0 0.0 0.0 0.0

command:# ./perf stat --metric-only -M Power -I 1000

Similarly in skylake platform:
result:#
time Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
1.000563580 0.3 0.0 2.6 44.2 21.9 0.0 0.0 0.0
2.002235027 0.4 0.0 2.7 43.0 20.7 0.0 0.0 0.0

Committer testing:

Before:

  [root@seventh ~]# perf stat --metric-only -M Power -I 1000
  #           time
       1.000383223
       2.001168182
       3.001968545
       4.002741200
       5.003442022
  ^C     5.777687244

[root@seventh ~]#

After the patch:

  [root@seventh ~]# perf stat --metric-only -M Power -I 1000
  #           time    Turbo_Utilization    C3_Core_Residency    C6_Core_Residency    C7_Core_Residency     C2_Pkg_Residency     C3_Pkg_Residency     C6_Pkg_Residency     C7_Pkg_Residency
       1.000406577                  0.4                  0.1                  1.4                 97.0                  0.0                  0.0                  0.0                  0.0
       2.001481572                  0.3                  0.0                  0.6                 97.9                  0.0                  0.0                  0.0                  0.0
       3.002332585                  0.2                  0.0                  1.0                 97.5                  0.0                  0.0                  0.0                  0.0
       4.003196624                  0.2                  0.0                  0.3                 98.6                  0.0                  0.0                  0.0                  0.0
       5.004063851                  0.3                  0.0                  0.7                 97.7                  0.0                  0.0                  0.0                  0.0
  ^C     5.471260276                  0.2                  0.0                  0.5                 49.3                  0.0                  0.0                  0.0                  0.0

[root@seventh ~]#
[root@seventh ~]# dmesg | grep -i skylake

  [    0.187807] Performance Events: PEBS fmt3+, Skylake events, 32-deep LBR, full-width counters, Intel PMU driver.
  [root@seventh ~]#
Fixes f01642e4912b ("perf metricgroup: Support multiple events for metricgroup")
Cc Alexander Shishkin <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Anju T Sudhakar <[email protected]>
Cc Jin Yao <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Kan Liang <[email protected]>
Cc Madhavan Srinivasan <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 tools/perf/util/metricgroup.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)
tools/perf/util/metricgroup.c +5 -2
index 6a4d350d5cdb..02aee946b6c1 100644
@@ -103,8 +103,11 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
 		if (!strcmp(ev->name, ids[i])) {
 			if (!metric_events[i])
 				metric_events[i] = ev;
+			i++;
+			if (i == idnum)
+				break;
 		} else {
-			if (++i == idnum) {
+			if (i + 1 == idnum) {
 				/* Discard the whole match and start again */
 				i = 0;
 				memset(metric_events, 0,
@@ -124,7 +127,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
 		}
 	}
 
-	if (i != idnum - 1) {
+	if (i != idnum) {
 		/* Not whole match */
 		return NULL;
 	}
Signature · 1 line
2.21.0
author maintainer
#6 lore raw

PATCH 6/9 perf header: Fix false warning when there are no duplicate cache entries

In reply to Arnaldo Carvalho de Melo

From: Michael Petlan <[email protected]>

Before this patch, perf expected that there might be NPROC*4 unique cache entries at max, however, it also expected that some of them would be shared and/or of the same size, thus the final number of entries would be reduced to be lower than NPROC*4. In case the number of entries hadn't been reduced (was NPROC*4), the warning was printed.

However, some systems might have unusual cache topology, such as the following two-processor KVM guest:

cpu level shared_cpu_list size
0 1 0 32K
0 1 0 64K
0 2 0 512K
0 3 0 8192K
1 1 1 32K
1 1 1 64K
1 2 1 512K
1 3 1 8192K

This KVM guest has 8 (NPROC*4) unique cache entries, which used to make perf printing the message, although there actually aren't "way too many cpu caches".

v2: Removing unused argument.

v3: Unifying the way we obtain number of cpus.

v4: Removed '& UINT_MAX' construct which is redundant.

LPU-Reference: [email protected]

---
 tools/perf/util/header.c | 21 ++++++---------------
 1 file changed, 6 insertions(+), 15 deletions(-)
tools/perf/util/header.c +6 -15
index 4d39a75551a0..93ad27830e2b 100644
@@ -1089,21 +1089,18 @@ static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c)
 	fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map);
 }
 
-static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
+#define MAX_CACHE_LVL 4
+
+static int build_caches(struct cpu_cache_level caches[], u32 *cntp)
 {
 	u32 i, cnt = 0;
-	long ncpus;
 	u32 nr, cpu;
 	u16 level;
 
-	ncpus = sysconf(_SC_NPROCESSORS_CONF);
-	if (ncpus < 0)
-		return -1;
-
-	nr = (u32)(ncpus & UINT_MAX);
+	nr = cpu__max_cpu();
 
 	for (cpu = 0; cpu < nr; cpu++) {
-		for (level = 0; level < 10; level++) {
+		for (level = 0; level < MAX_CACHE_LVL; level++) {
 			struct cpu_cache_level c;
 			int err;
 
@@ -1123,18 +1120,12 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
 				caches[cnt++] = c;
 			else
 				cpu_cache_level__free(&c);
-
-			if (WARN_ONCE(cnt == size, "way too many cpu caches.."))
-				goto out;
 		}
 	}
- out:
 	*cntp = cnt;
 	return 0;
 }
 
-#define MAX_CACHE_LVL 4
-
 static int write_cache(struct feat_fd *ff,
 		       struct evlist *evlist __maybe_unused)
 {
@@ -1143,7 +1134,7 @@ static int write_cache(struct feat_fd *ff,
 	u32 cnt = 0, i, version = 1;
 	int ret;
 
-	ret = build_caches(caches, max_caches, &cnt);
+	ret = build_caches(caches, &cnt);
 	if (ret)
 		goto out;
 
Signature · 1 line
2.21.0
author maintainer
#7 lore raw

PATCH 7/9 libtraceevent: Allow custom libdir path

In reply to Arnaldo Carvalho de Melo

From: Sudip Mukherjee <[email protected]>

When I use prefix=/usr and try to install libtraceevent in my laptop it tries to install in /usr/lib64. I am not having any folder as /usr/lib64 and also the debian policy doesnot allow installing in /usr/lib64. It should be in /usr/lib/x86_64-linux-gnu/.

Quote: No package for a 64 bit architecture may install files in
/usr/lib64/ or in a subdirectory of it.

ref: https://www.debian.org/doc/debian-policy/ch-opersys.html

Make it more flexible by allowing to mention libdir_relative while installing so that distros can mention the path according to their policy or use the default one.

---
 tools/lib/traceevent/Makefile         | 5 +++--
 tools/lib/traceevent/plugins/Makefile | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)
tools/lib/traceevent/Makefile +3 -2
index c5a03356a999..c874c017c636 100644
@@ -39,11 +39,12 @@ DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
 
 LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
 ifeq ($(LP64), 1)
-  libdir_relative = lib64
+  libdir_relative_temp = lib64
 else
-  libdir_relative = lib
+  libdir_relative_temp = lib
 endif
 
+libdir_relative ?= $(libdir_relative_temp)
 prefix ?= /usr/local
 libdir = $(prefix)/$(libdir_relative)
 man_dir = $(prefix)/share/man
tools/lib/traceevent/plugins/Makefile +3 -2
index f440989fa55e..349bb81482ab 100644
@@ -32,11 +32,12 @@ DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
 
 LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
 ifeq ($(LP64), 1)
-  libdir_relative = lib64
+  libdir_relative_tmp = lib64
 else
-  libdir_relative = lib
+  libdir_relative_tmp = lib
 endif
 
+libdir_relative ?= $(libdir_relative_tmp)
 prefix ?= /usr/local
 libdir = $(prefix)/$(libdir_relative)
 
Signature · 1 line
2.21.0
author maintainer
#8 lore raw

PATCH 8/9 perf vendor events s390: Fix counter long description for DTLB1_GPAGE_WRITES

In reply to Arnaldo Carvalho de Melo

From: Ed Maste <[email protected]>

The cf_z13 counter DTLB1_GPAGE_WRITES included a prefix 'Counter:132\tName:'.

This is incorrect; remove the prefix as with 7fcfa9a2d9 for cf_z14.

Cc Alexander Shishkin <[email protected]>
Cc Greentime Hu <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Nick Hu <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Thomas Richter <[email protected]>
Cc Vincent Chen <[email protected]>
---
 tools/perf/pmu-events/arch/s390/cf_z13/extended.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/pmu-events/arch/s390/cf_z13/extended.json +1 -1
index 436ce33f1182..5da8296b667e 100644
@@ -32,7 +32,7 @@
 		"EventCode": "132",
 		"EventName": "DTLB1_GPAGE_WRITES",
 		"BriefDescription": "DTLB1 Two-Gigabyte Page Writes",
-		"PublicDescription": "Counter:132	Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page."
+		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page."
 	},
 	{
 		"Unit": "CPU-M-CF",
Signature · 1 line
2.21.0
author maintainer
#9 lore raw

PATCH 9/9 perf vendor events s390: Remove name from L1D_RO_EXCL_WRITES description

In reply to Arnaldo Carvalho de Melo

From: Ed Maste <[email protected]>

In 7fcfa9a2d9 an unintended prefix "Counter:18 Name:" was removed from the description for L1D_RO_EXCL_WRITES, but the extra name remained in the description. Remove it too.

Fixes 7fcfa9a2d9a7 ("perf list: Fix s390 counter long description for L1D_RO_EXCL_WRITES")
Cc Alexander Shishkin <[email protected]>
Cc Greentime Hu <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Nick Hu <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Thomas Richter <[email protected]>
Cc Vincent Chen <[email protected]>
---
 tools/perf/pmu-events/arch/s390/cf_z14/extended.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/pmu-events/arch/s390/cf_z14/extended.json +1 -1
index 68618152ea2c..89e070727e1b 100644
@@ -4,7 +4,7 @@
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
-		"PublicDescription": "L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
+		"PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
 		"Unit": "CPU-M-CF",
Signature · 1 line
2.21.0
#10 lore raw
In reply to Arnaldo Carvalho de Melo
Quoted 106 lines · Arnaldo Carvalho de Melo

Hi Ingo/Thomas,

Please consider pulling,

Best regards,

- Arnaldo

The following changes since commit 761bfc33dd7504de951aa7b9db27a3cc5df1fde6:

Merge remote-tracking branch 'torvalds/master' into perf/urgent (2019-12-11 09:58:16 -0300)

are available in the Git repository at:

git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-urgent-for-mingo-5.5-20191216

for you to fetch changes up to 58b3bafff8257c6946df5d6aeb215b8ac839ed2a:

perf vendor events s390: Remove name from L1D_RO_EXCL_WRITES description (2019-12-16 13:40:26 -0300)

----------------------------------------------------------------
perf/urgent fixes:

perf top:

Arnaldo Carvalho de Melo:

- Do not bail out when perf_env__read_cpuid() returns ENOSYS, which has been reported happening on aarch64.

perf metricgroup:

Kajol Jain:

- Fix printing event names of metric group with multiple events

vendor events:

x86:

Ravi Bangoria:

- Fix Kernel_Utilization metric.

s390:

Ed Maste:

- Fix counter long description for DTLB1_GPAGE_WRITES and L1D_RO_EXCL_WRITES.

perf header:

Michael Petlan:

- Fix false warning when there are no duplicate cache entries

libtraceevent:

Sudip Mukherjee:

- Allow custom libdir path

API headers:

Arnaldo Carvalho de Melo:

- Sync linux/kvm.h with the kernel sources.

----------------------------------------------------------------
Arnaldo Carvalho de Melo (3):
tools headers kvm: Sync linux/kvm.h with the kernel sources perf arch: Make the default get_cpuid() return compatible error perf top: Do not bail out when perf_env__read_cpuid() returns ENOSYS

Ed Maste (2):
perf vendor events s390: Fix counter long description for DTLB1_GPAGE_WRITES perf vendor events s390: Remove name from L1D_RO_EXCL_WRITES description

Kajol Jain (1):
perf metricgroup: Fix printing event names of metric group with multiple events

Michael Petlan (1):
perf header: Fix false warning when there are no duplicate cache entries

Ravi Bangoria (1):
perf/x86/pmu-events: Fix Kernel_Utilization metric

Sudip Mukherjee (1):
libtraceevent: Allow custom libdir path

 tools/include/uapi/linux/kvm.h                     |  1 +
 tools/lib/traceevent/Makefile                      |  5 +++--
 tools/lib/traceevent/plugins/Makefile              |  5 +++--
 tools/perf/builtin-top.c                           | 10 +++++++---
 .../perf/pmu-events/arch/s390/cf_z13/extended.json |  2 +-
 .../perf/pmu-events/arch/s390/cf_z14/extended.json |  2 +-
 .../pmu-events/arch/x86/broadwell/bdw-metrics.json |  2 +-
 .../arch/x86/broadwellde/bdwde-metrics.json        |  2 +-
 .../arch/x86/broadwellx/bdx-metrics.json           |  2 +-
 .../arch/x86/cascadelakex/clx-metrics.json         |  2 +-
 .../pmu-events/arch/x86/haswell/hsw-metrics.json   |  2 +-
 .../pmu-events/arch/x86/haswellx/hsx-metrics.json  |  2 +-
 .../pmu-events/arch/x86/ivybridge/ivb-metrics.json |  2 +-
Quoted 8 lines
 .../pmu-events/arch/x86/ivytown/ivt-metrics.json   |  2 +-
 .../pmu-events/arch/x86/jaketown/jkt-metrics.json  |  2 +-
 .../arch/x86/sandybridge/snb-metrics.json          |  2 +-
 .../pmu-events/arch/x86/skylake/skl-metrics.json   |  2 +-
 .../pmu-events/arch/x86/skylakex/skx-metrics.json  |  2 +-
 tools/perf/util/header.c                           | 23 +++++++---------------
 tools/perf/util/metricgroup.c                      |  7 +++++--
 20 files changed, 40 insertions(+), 39 deletions(-)

Pulled, thanks a lot Arnaldo!

Ingo