1. Patchew
  2. linux
  3. View series

[PATCH v2] perf script: Fix output type for dynamically allocated core PMU's

Thomas Falcon posted 1 patch 1 year ago
There is a newer version of this series
tools/perf/builtin-script.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
[PATCH v2] perf script: Fix output type for dynamically allocated core PMU's
Posted by Thomas Falcon 1 year ago 
perf script output may show different fields on different core PMU's
that exist on heterogeneous platforms. For example,

perf record -e "{cpu_core/mem-loads-aux/,cpu_core/event=0xcd,\
umask=0x01,ldlat=3,name=MEM_UOPS_RETIRED.LOAD_LATENCY/}:upp"\
-c10000 -W -d -a -- sleep 1

perf script:

chromium-browse   46572 [002] 544966.882384:      10000 	cpu_core/MEM_UOPS_RETIRED.LOAD_LATENCY/: 7ffdf1391b0c     10268100142 \
 |OP LOAD|LVL L1 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK    N/A    5   7    0   7fad7c47425d [unknown] (/usr/lib64/libglib-2.0.so.0.8000.3)

perf record -e cpu_atom/event=0xd0,umask=0x05,ldlat=3,\
name=MEM_UOPS_RETIRED.LOAD_LATENCY/upp -c10000 -W -d -a -- sleep 1

perf script:

gnome-control-c  534224 [023] 544951.816227:      10000 cpu_atom/MEM_UOPS_RETIRED.LOAD_LATENCY/:   7f0aaaa0aae0  [unknown] (/usr/lib64/libglib-2.0.so.0.8000.3)

Some fields, such as data_src, are not included by default.

The cause is that while one PMU may be assigned a type such as
PERF_TYPE_RAW, other core PMU's are dynamically allocated at boot time.
If this value does not match an existing PERF_TYPE_X value,
output_type(perf_event_attr.type) will return OUTPUT_TYPE_OTHER.

Instead search for a core PMU with a matching perf_event_attr type
and, if one is found, return PERF_TYPE_RAW to match output of other
core PMU's.

Suggested-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Thomas Falcon <thomas.falcon@intel.com>
---
v2: restrict pmu lookup to platforms with more than one core pmu
---
 tools/perf/builtin-script.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9e47905f75a6..459794c737ce 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -384,6 +384,18 @@ static int evsel_script__fprintf(struct evsel_script *es, FILE *fp)
 		       st.st_size / 1024.0 / 1024.0, es->filename, es->samples);
 }
 
+static bool output_type_many_core_pmus(unsigned int type)
+{
+	struct perf_pmu *pmu;
+
+	if (perf_pmus__num_core_pmus() > 1) {
+		pmu = perf_pmus__find_by_type(type);
+		if (pmu && pmu->is_core)
+			return true;
+	}
+	return false;
+}
+
 static inline int output_type(unsigned int type)
 {
 	switch (type) {
@@ -394,6 +406,9 @@ static inline int output_type(unsigned int type)
 			return type;
 	}
 
+	if (output_type_many_core_pmus(type))
+		return PERF_TYPE_RAW;
+
 	return OUTPUT_TYPE_OTHER;
 }
 
-- 
2.47.1
Re: [PATCH v2] perf script: Fix output type for dynamically allocated core PMU's
Posted by Liang, Kan 1 year ago 

On 2024-12-13 3:11 p.m., Thomas Falcon wrote:
> perf script output may show different fields on different core PMU's
> that exist on heterogeneous platforms. For example,
> 
> perf record -e "{cpu_core/mem-loads-aux/,cpu_core/event=0xcd,\
> umask=0x01,ldlat=3,name=MEM_UOPS_RETIRED.LOAD_LATENCY/}:upp"\
> -c10000 -W -d -a -- sleep 1
> 
> perf script:
> 
> chromium-browse   46572 [002] 544966.882384:      10000 	cpu_core/MEM_UOPS_RETIRED.LOAD_LATENCY/: 7ffdf1391b0c     10268100142 \
>  |OP LOAD|LVL L1 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK    N/A    5   7    0   7fad7c47425d [unknown] (/usr/lib64/libglib-2.0.so.0.8000.3)
> 
> perf record -e cpu_atom/event=0xd0,umask=0x05,ldlat=3,\
> name=MEM_UOPS_RETIRED.LOAD_LATENCY/upp -c10000 -W -d -a -- sleep 1
> 
> perf script:
> 
> gnome-control-c  534224 [023] 544951.816227:      10000 cpu_atom/MEM_UOPS_RETIRED.LOAD_LATENCY/:   7f0aaaa0aae0  [unknown] (/usr/lib64/libglib-2.0.so.0.8000.3)
> 
> Some fields, such as data_src, are not included by default.
> 
> The cause is that while one PMU may be assigned a type such as
> PERF_TYPE_RAW, other core PMU's are dynamically allocated at boot time.
> If this value does not match an existing PERF_TYPE_X value,
> output_type(perf_event_attr.type) will return OUTPUT_TYPE_OTHER.
> 
> Instead search for a core PMU with a matching perf_event_attr type
> and, if one is found, return PERF_TYPE_RAW to match output of other
> core PMU's.
> 
> Suggested-by: Kan Liang <kan.liang@intel.com>
> Signed-off-by: Thomas Falcon <thomas.falcon@intel.com>
> ---
> v2: restrict pmu lookup to platforms with more than one core pmu
> ---
>  tools/perf/builtin-script.c | 15 +++++++++++++++
>  1 file changed, 15 insertions(+)
> 
> diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
> index 9e47905f75a6..459794c737ce 100644
> --- a/tools/perf/builtin-script.c
> +++ b/tools/perf/builtin-script.c
> @@ -384,6 +384,18 @@ static int evsel_script__fprintf(struct evsel_script *es, FILE *fp)
>  		       st.st_size / 1024.0 / 1024.0, es->filename, es->samples);
>  }
>  
> +static bool output_type_many_core_pmus(unsigned int type)
> +{
> +	struct perf_pmu *pmu;
> +
> +	if (perf_pmus__num_core_pmus() > 1) {
> +		pmu = perf_pmus__find_by_type(type);
> +		if (pmu && pmu->is_core)> +			return true;

I think it should be good enough to search the core_pmus.
	list_for_each_entry(pmu, &core_pmus, list) {
		if (pmu->type == type)
			return true;
	}

Thanks,
Kan
> +	}
> +	return false;
> +}
> +
>  static inline int output_type(unsigned int type)
>  {
>  	switch (type) {
> @@ -394,6 +406,9 @@ static inline int output_type(unsigned int type)
>  			return type;
>  	}
>  
> +	if (output_type_many_core_pmus(type))
> +		return PERF_TYPE_RAW;
> +
>  	return OUTPUT_TYPE_OTHER;
>  }
>
Re: [PATCH v2] perf script: Fix output type for dynamically allocated core PMU's
Posted by Falcon, Thomas 1 year ago 
On Fri, 2024-12-13 at 15:21 -0500, Liang, Kan wrote:
> 
> 
> On 2024-12-13 3:11 p.m., Thomas Falcon wrote:
> > perf script output may show different fields on different core
> > PMU's
> > that exist on heterogeneous platforms. For example,
> > 
> > perf record -e "{cpu_core/mem-loads-aux/,cpu_core/event=0xcd,\
> > umask=0x01,ldlat=3,name=MEM_UOPS_RETIRED.LOAD_LATENCY/}:upp"\
> > -c10000 -W -d -a -- sleep 1
> > 
> > perf script:
> > 
> > chromium-browse   46572 [002] 544966.882384:     
> > 10000 	cpu_core/MEM_UOPS_RETIRED.LOAD_LATENCY/: 7ffdf1391b0c     10268100142\
> >  |OP LOAD|LVL L1 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK    N/A   
> > 5   7    0   7fad7c47425d [unknown] (/usr/lib64/libglib-
> > 2.0.so.0.8000.3)
> > 
> > perf record -e cpu_atom/event=0xd0,umask=0x05,ldlat=3,\
> > name=MEM_UOPS_RETIRED.LOAD_LATENCY/upp -c10000 -W -d -a -- sleep 1
> > 
> > perf script:
> > 
> > gnome-control-c  534224 [023] 544951.816227:      10000
> > cpu_atom/MEM_UOPS_RETIRED.LOAD_LATENCY/:   7f0aaaa0aae0  [unknown]
> > (/usr/lib64/libglib-2.0.so.0.8000.3)
> > 
> > Some fields, such as data_src, are not included by default.
> > 
> > The cause is that while one PMU may be assigned a type such as
> > PERF_TYPE_RAW, other core PMU's are dynamically allocated at boot
> > time.
> > If this value does not match an existing PERF_TYPE_X value,
> > output_type(perf_event_attr.type) will return OUTPUT_TYPE_OTHER.
> > 
> > Instead search for a core PMU with a matching perf_event_attr type
> > and, if one is found, return PERF_TYPE_RAW to match output of other
> > core PMU's.
> > 
> > Suggested-by: Kan Liang <kan.liang@intel.com>
> > Signed-off-by: Thomas Falcon <thomas.falcon@intel.com>
> > ---
> > v2: restrict pmu lookup to platforms with more than one core pmu
> > ---
> >  tools/perf/builtin-script.c | 15 +++++++++++++++
> >  1 file changed, 15 insertions(+)
> > 
> > diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-
> > script.c
> > index 9e47905f75a6..459794c737ce 100644
> > --- a/tools/perf/builtin-script.c
> > +++ b/tools/perf/builtin-script.c
> > @@ -384,6 +384,18 @@ static int evsel_script__fprintf(struct
> > evsel_script *es, FILE *fp)
> >  		       st.st_size / 1024.0 / 1024.0, es->filename,
> > es->samples);
> >  }
> >  
> > +static bool output_type_many_core_pmus(unsigned int type)
> > +{
> > +	struct perf_pmu *pmu;
> > +
> > +	if (perf_pmus__num_core_pmus() > 1) {
> > +		pmu = perf_pmus__find_by_type(type);
> > +		if (pmu && pmu->is_core)>
> > +			return true;
> 
> I think it should be good enough to search the core_pmus.
> 	list_for_each_entry(pmu, &core_pmus, list) {
> 		if (pmu->type == type)
> 			return true;
> 	}
> 
> Thanks,
> Kan

Thanks, will resend with your changes.

Tom

> > +	}
> > +	return false;
> > +}
> > +
> >  static inline int output_type(unsigned int type)
> >  {
> >  	switch (type) {
> > @@ -394,6 +406,9 @@ static inline int output_type(unsigned int
> > type)
> >  			return type;
> >  	}
> >  
> > +	if (output_type_many_core_pmus(type))
> > +		return PERF_TYPE_RAW;
> > +
> >  	return OUTPUT_TYPE_OTHER;
> >  }
> >  
>

Patchew 2.1-devel-b67e4c2

© 2016 - 2025 Red Hat, Inc.