[PATCH 0/3] perf: arm-spe: Fix addresses of synthesized Arm SPE events

[PATCH 0/3] perf: arm-spe: Fix addresses of synthesized Arm SPE events

[Timothy Hayes]

This patch set fixes problems related to address in synthesized events from SPE.

Committer testing:

perf record --no-bpf-event -e arm_spe_0/pa_enable=1/ -- sleep 1
perf inject -i perf.data -o perf-inj.data --itrace --strip
perf script -i perf-inj.data --fields hw:+addr,+phys_addr

Before:
	sleep 49337 [004] 20133.731889:          1             l1d-access:  ffffcbebcde1d5b8 [unknown] ([unknown])
	sleep 49337 [004] 20133.731889:          1             tlb-access:  ffffcbebcde1d5b8 [unknown] ([unknown])
	sleep 49337 [004] 20133.731889:          1                 memory:  ffffcbebcde1d5b8 [unknown] ([unknown])

After:
	sleep 49337 [004] 20133.731889:          1             l1d-access: ffff800034123970 ffffcbebcde1d5b8 [unknown] ([unknown])       153d19970
	sleep 49337 [004] 20133.731889:          1             tlb-access: ffff800034123970 ffffcbebcde1d5b8 [unknown] ([unknown])       153d19970
	sleep 49337 [004] 20133.731889:          1                 memory: ffff800034123970 ffffcbebcde1d5b8 [unknown] ([unknown])       153d19970

tools/perf/arch/arm64/util/arm-spe.c                   | 10 ++++++++++
tools/perf/tests/attr/README                           |  1 +
tools/perf/tests/attr/test-record-spe-physical-address | 12 ++++++++++++
tools/perf/util/arm-spe.c                              |  5 +++--
4 files changed, 26 insertions(+), 2 deletions(-)

[PATCH 1/3] perf: arm-spe: Fix addresses of synthesized SPE events

[Timothy Hayes]

This patch corrects a bug whereby synthesized events from SPE
samples are missing virtual addresses.

Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>
---
 tools/perf/util/arm-spe.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index d2b64e3f588b..151cc38a171c 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -1036,7 +1036,7 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
 	attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
 	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
 			    PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
-			    PERF_SAMPLE_WEIGHT;
+			    PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR;
 	if (spe->timeless_decoding)
 		attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
 	else
-- 
2.25.1

[PATCH 2/3] perf: arm-spe: Fix SPE events with phys addresses

[Timothy Hayes]

This patch corrects a bug whereby SPE collection is invoked with
pa_enable=1 but synthesized events fail to show physical addresses.

Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>
---
 tools/perf/arch/arm64/util/arm-spe.c | 10 ++++++++++
 tools/perf/util/arm-spe.c            |  3 ++-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index af4d63af8072..e8b577d33e53 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -148,6 +148,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	bool privileged = perf_event_paranoid_check(-1);
 	struct evsel *tracking_evsel;
 	int err;
+	u64 bit;
 
 	sper->evlist = evlist;
 
@@ -245,6 +246,15 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	 */
 	evsel__set_sample_bit(arm_spe_evsel, DATA_SRC);
 
+	/*
+	 * The PHYS_ADDR flag does not affect the driver behaviour, it is used to
+	 * inform that the resulting output's SPE samples contain physical addresses
+	 * where applicable.
+	 */
+	bit = perf_pmu__format_bits(&arm_spe_pmu->format, "pa_enable");
+	if (arm_spe_evsel->core.attr.config & bit)
+		evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR);
+
 	/* Add dummy event to keep tracking */
 	err = parse_events(evlist, "dummy:u", NULL);
 	if (err)
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 151cc38a171c..1a80151baed9 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -1033,7 +1033,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
 	memset(&attr, 0, sizeof(struct perf_event_attr));
 	attr.size = sizeof(struct perf_event_attr);
 	attr.type = PERF_TYPE_HARDWARE;
-	attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
+	attr.sample_type = evsel->core.attr.sample_type &
+				(PERF_SAMPLE_MASK | PERF_SAMPLE_PHYS_ADDR);
 	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
 			    PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
 			    PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR;
-- 
2.25.1

[PATCH 3/3] perf test: Add perf_event_attr test for Arm SPE

[Timothy Hayes]

Adds a perf_event_attr test for Arm SPE in which the presence of
physical addresses are checked when SPE unit is run with pa_enable=1.

Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>
---
 tools/perf/tests/attr/README                         |  1 +
 .../perf/tests/attr/test-record-spe-physical-address | 12 ++++++++++++
 2 files changed, 13 insertions(+)
 create mode 100644 tools/perf/tests/attr/test-record-spe-physical-address

diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
index 454505d343fa..eb3f7d4bb324 100644
--- a/tools/perf/tests/attr/README
+++ b/tools/perf/tests/attr/README
@@ -60,6 +60,7 @@ Following tests are defined (with perf commands):
   perf record -R kill                           (test-record-raw)
   perf record -c 2 -e arm_spe_0// -- kill       (test-record-spe-period)
   perf record -e arm_spe_0/period=3/ -- kill    (test-record-spe-period-term)
+  perf record -e arm_spe_0/pa_enable=1/ -- kill (test-record-spe-physical-address)
   perf stat -e cycles kill                      (test-stat-basic)
   perf stat kill                                (test-stat-default)
   perf stat -d kill                             (test-stat-detailed-1)
diff --git a/tools/perf/tests/attr/test-record-spe-physical-address b/tools/perf/tests/attr/test-record-spe-physical-address
new file mode 100644
index 000000000000..7ebcf5012ce3
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-spe-physical-address
@@ -0,0 +1,12 @@
+[config]
+command = record
+args    = --no-bpf-event -e arm_spe_0/pa_enable=1/ -- kill >/dev/null 2>&1
+ret     = 1
+arch    = aarch64
+
+[event-10:base-record-spe]
+# 622727 is the decimal of IP|TID|TIME|CPU|IDENTIFIER|DATA_SRC|PHYS_ADDR
+sample_type=622727
+
+# dummy event
+[event-1:base-record-spe]
\ No newline at end of file
-- 
2.25.1

Re: [PATCH 1/3] perf: arm-spe: Fix addresses of synthesized SPE events

[Leo Yan]

On Thu, Apr 21, 2022 at 05:52:03PM +0100, Timothy Hayes wrote:
> This patch corrects a bug whereby synthesized events from SPE
> samples are missing virtual addresses.
> 
> Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>

Reviewed-by: Leo Yan <leo.yan@linaro.org>

> ---
>  tools/perf/util/arm-spe.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
> index d2b64e3f588b..151cc38a171c 100644
> --- a/tools/perf/util/arm-spe.c
> +++ b/tools/perf/util/arm-spe.c
> @@ -1036,7 +1036,7 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
>  	attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
>  	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
>  			    PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
> -			    PERF_SAMPLE_WEIGHT;
> +			    PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR;
>  	if (spe->timeless_decoding)
>  		attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
>  	else
> -- 
> 2.25.1
> 

Re: [PATCH 2/3] perf: arm-spe: Fix SPE events with phys addresses

[Leo Yan]

Hi Timothy,

On Thu, Apr 21, 2022 at 05:52:04PM +0100, Timothy Hayes wrote:
> This patch corrects a bug whereby SPE collection is invoked with
> pa_enable=1 but synthesized events fail to show physical addresses.
> 
> Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>
> ---
>  tools/perf/arch/arm64/util/arm-spe.c | 10 ++++++++++
>  tools/perf/util/arm-spe.c            |  3 ++-
>  2 files changed, 12 insertions(+), 1 deletion(-)
> 
> diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
> index af4d63af8072..e8b577d33e53 100644
> --- a/tools/perf/arch/arm64/util/arm-spe.c
> +++ b/tools/perf/arch/arm64/util/arm-spe.c
> @@ -148,6 +148,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
>  	bool privileged = perf_event_paranoid_check(-1);
>  	struct evsel *tracking_evsel;
>  	int err;
> +	u64 bit;
>  
>  	sper->evlist = evlist;
>  
> @@ -245,6 +246,15 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
>  	 */
>  	evsel__set_sample_bit(arm_spe_evsel, DATA_SRC);
>  
> +	/*
> +	 * The PHYS_ADDR flag does not affect the driver behaviour, it is used to
> +	 * inform that the resulting output's SPE samples contain physical addresses
> +	 * where applicable.
> +	 */
> +	bit = perf_pmu__format_bits(&arm_spe_pmu->format, "pa_enable");
> +	if (arm_spe_evsel->core.attr.config & bit)
> +		evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR);
> +
>  	/* Add dummy event to keep tracking */
>  	err = parse_events(evlist, "dummy:u", NULL);
>  	if (err)
> diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
> index 151cc38a171c..1a80151baed9 100644
> --- a/tools/perf/util/arm-spe.c
> +++ b/tools/perf/util/arm-spe.c
> @@ -1033,7 +1033,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
>  	memset(&attr, 0, sizeof(struct perf_event_attr));
>  	attr.size = sizeof(struct perf_event_attr);
>  	attr.type = PERF_TYPE_HARDWARE;
> -	attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
> +	attr.sample_type = evsel->core.attr.sample_type &
> +				(PERF_SAMPLE_MASK | PERF_SAMPLE_PHYS_ADDR);

I verified this patch and I can confirm the physical address can be
dumped successfully.

I have a more general question, seems to me, we need to change the
macro PERF_SAMPLE_MASK in the file util/event.h as below, so
here doesn't need to 'or' the flag PERF_SAMPLE_PHYS_ADDR anymore.

@Arnaldo, @Jiri, could you confirm if this is the right way to move
forward?  I am not sure why PERF_SAMPLE_MASK doesn't contain the bit
PERF_SAMPLE_PHYS_ADDR in current code.

diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index cdd72e05fd28..c905ac32ebad 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -39,7 +39,7 @@ struct perf_event_attr;
         PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |          \
        PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |        \
         PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD |         \
-        PERF_SAMPLE_IDENTIFIER)
+        PERF_SAMPLE_IDENTIFIER | PERF_SAMPLE_PHYS_ADDR)

Thanks,
Leo

>  	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
>  			    PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
>  			    PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR;
> -- 
> 2.25.1
> 

Re: [PATCH 3/3] perf test: Add perf_event_attr test for Arm SPE

[Leo Yan]

On Thu, Apr 21, 2022 at 05:52:05PM +0100, Timothy Hayes wrote:
> Adds a perf_event_attr test for Arm SPE in which the presence of
> physical addresses are checked when SPE unit is run with pa_enable=1.
> 
> Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>

Reviewed-by: Leo Yan <leo.yan@linaro.org>
Tested-by: Leo Yan <leo.yan@linaro.org>

> ---
>  tools/perf/tests/attr/README                         |  1 +
>  .../perf/tests/attr/test-record-spe-physical-address | 12 ++++++++++++
>  2 files changed, 13 insertions(+)
>  create mode 100644 tools/perf/tests/attr/test-record-spe-physical-address
> 
> diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
> index 454505d343fa..eb3f7d4bb324 100644
> --- a/tools/perf/tests/attr/README
> +++ b/tools/perf/tests/attr/README
> @@ -60,6 +60,7 @@ Following tests are defined (with perf commands):
>    perf record -R kill                           (test-record-raw)
>    perf record -c 2 -e arm_spe_0// -- kill       (test-record-spe-period)
>    perf record -e arm_spe_0/period=3/ -- kill    (test-record-spe-period-term)
> +  perf record -e arm_spe_0/pa_enable=1/ -- kill (test-record-spe-physical-address)
>    perf stat -e cycles kill                      (test-stat-basic)
>    perf stat kill                                (test-stat-default)
>    perf stat -d kill                             (test-stat-detailed-1)
> diff --git a/tools/perf/tests/attr/test-record-spe-physical-address b/tools/perf/tests/attr/test-record-spe-physical-address
> new file mode 100644
> index 000000000000..7ebcf5012ce3
> --- /dev/null
> +++ b/tools/perf/tests/attr/test-record-spe-physical-address
> @@ -0,0 +1,12 @@
> +[config]
> +command = record
> +args    = --no-bpf-event -e arm_spe_0/pa_enable=1/ -- kill >/dev/null 2>&1
> +ret     = 1
> +arch    = aarch64
> +
> +[event-10:base-record-spe]
> +# 622727 is the decimal of IP|TID|TIME|CPU|IDENTIFIER|DATA_SRC|PHYS_ADDR
> +sample_type=622727
> +
> +# dummy event
> +[event-1:base-record-spe]
> \ No newline at end of file
> -- 
> 2.25.1
> 

Re: [PATCH 1/3] perf: arm-spe: Fix addresses of synthesized SPE events

[Leo Yan]

On Sun, Apr 24, 2022 at 08:28:31PM +0800, Leo Yan wrote:
> On Thu, Apr 21, 2022 at 05:52:03PM +0100, Timothy Hayes wrote:
> > This patch corrects a bug whereby synthesized events from SPE
> > samples are missing virtual addresses.
> > 
> > Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>
> 
> Reviewed-by: Leo Yan <leo.yan@linaro.org>

Supplement for fixed tag:

Since patches 01, 02 are fixing bugs, please add fixed tag [1]:

Fixes: 54f7815efef7 ("perf arm-spe: Fill address info for samples")

Thanks,
Leo

[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/process/submitting-patches.rst#n138

Re: [PATCH 2/3] perf: arm-spe: Fix SPE events with phys addresses

[James Clark]

On 24/04/2022 13:59, Leo Yan wrote:
> Hi Timothy,
> 
> On Thu, Apr 21, 2022 at 05:52:04PM +0100, Timothy Hayes wrote:
>> This patch corrects a bug whereby SPE collection is invoked with
>> pa_enable=1 but synthesized events fail to show physical addresses.
>>
>> Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>
>> ---
>>  tools/perf/arch/arm64/util/arm-spe.c | 10 ++++++++++
>>  tools/perf/util/arm-spe.c            |  3 ++-
>>  2 files changed, 12 insertions(+), 1 deletion(-)
>>
>> diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
>> index af4d63af8072..e8b577d33e53 100644
>> --- a/tools/perf/arch/arm64/util/arm-spe.c
>> +++ b/tools/perf/arch/arm64/util/arm-spe.c
>> @@ -148,6 +148,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
>>  	bool privileged = perf_event_paranoid_check(-1);
>>  	struct evsel *tracking_evsel;
>>  	int err;
>> +	u64 bit;
>>  
>>  	sper->evlist = evlist;
>>  
>> @@ -245,6 +246,15 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
>>  	 */
>>  	evsel__set_sample_bit(arm_spe_evsel, DATA_SRC);
>>  
>> +	/*
>> +	 * The PHYS_ADDR flag does not affect the driver behaviour, it is used to
>> +	 * inform that the resulting output's SPE samples contain physical addresses
>> +	 * where applicable.
>> +	 */
>> +	bit = perf_pmu__format_bits(&arm_spe_pmu->format, "pa_enable");
>> +	if (arm_spe_evsel->core.attr.config & bit)
>> +		evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR);
>> +
>>  	/* Add dummy event to keep tracking */
>>  	err = parse_events(evlist, "dummy:u", NULL);
>>  	if (err)
>> diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
>> index 151cc38a171c..1a80151baed9 100644
>> --- a/tools/perf/util/arm-spe.c
>> +++ b/tools/perf/util/arm-spe.c
>> @@ -1033,7 +1033,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
>>  	memset(&attr, 0, sizeof(struct perf_event_attr));
>>  	attr.size = sizeof(struct perf_event_attr);
>>  	attr.type = PERF_TYPE_HARDWARE;
>> -	attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
>> +	attr.sample_type = evsel->core.attr.sample_type &
>> +				(PERF_SAMPLE_MASK | PERF_SAMPLE_PHYS_ADDR);
> 
> I verified this patch and I can confirm the physical address can be
> dumped successfully.
> 
> I have a more general question, seems to me, we need to change the
> macro PERF_SAMPLE_MASK in the file util/event.h as below, so
> here doesn't need to 'or' the flag PERF_SAMPLE_PHYS_ADDR anymore.
> 
> @Arnaldo, @Jiri, could you confirm if this is the right way to move
> forward?  I am not sure why PERF_SAMPLE_MASK doesn't contain the bit
> PERF_SAMPLE_PHYS_ADDR in current code.

I think there is a reason that PERF_SAMPLE_MASK is a subset of all the
bits. This comment below suggests it. Is it so the mask only includes fields
that are 64bits? That makes the __evsel__sample_size() function a simple
multiplication of a count of all the fields that are 64bits.

  static int
  perf_event__check_size(union perf_event *event, unsigned int sample_size)
  {
	/*
	 * The evsel's sample_size is based on PERF_SAMPLE_MASK which includes
	 * up to PERF_SAMPLE_PERIOD.  After that overflow() must be used to
	 * check the format does not go past the end of the event.
	 */
	if (sample_size + sizeof(event->header) > event->header.size)
		return -EFAULT;

	return 0;
  }

Having said that, the mask was updated once to add PERF_SAMPLE_IDENTIFIER to
it, so that comment is slightly out of date now.


> 
> diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
> index cdd72e05fd28..c905ac32ebad 100644
> --- a/tools/perf/util/event.h
> +++ b/tools/perf/util/event.h
> @@ -39,7 +39,7 @@ struct perf_event_attr;
>          PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |          \
>         PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |        \
>          PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD |         \
> -        PERF_SAMPLE_IDENTIFIER)
> +        PERF_SAMPLE_IDENTIFIER | PERF_SAMPLE_PHYS_ADDR)
> 
> Thanks,
> Leo
> 
>>  	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
>>  			    PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
>>  			    PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR;
>> -- 
>> 2.25.1
>>

Re: [PATCH 2/3] perf: arm-spe: Fix SPE events with phys addresses

[Leo Yan]

On Mon, Apr 25, 2022 at 10:12:36AM +0100, James Clark wrote:

[...]

> >> diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
> >> index 151cc38a171c..1a80151baed9 100644
> >> --- a/tools/perf/util/arm-spe.c
> >> +++ b/tools/perf/util/arm-spe.c
> >> @@ -1033,7 +1033,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
> >>  	memset(&attr, 0, sizeof(struct perf_event_attr));
> >>  	attr.size = sizeof(struct perf_event_attr);
> >>  	attr.type = PERF_TYPE_HARDWARE;
> >> -	attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
> >> +	attr.sample_type = evsel->core.attr.sample_type &
> >> +				(PERF_SAMPLE_MASK | PERF_SAMPLE_PHYS_ADDR);
> > 
> > I verified this patch and I can confirm the physical address can be
> > dumped successfully.
> > 
> > I have a more general question, seems to me, we need to change the
> > macro PERF_SAMPLE_MASK in the file util/event.h as below, so
> > here doesn't need to 'or' the flag PERF_SAMPLE_PHYS_ADDR anymore.
> > 
> > @Arnaldo, @Jiri, could you confirm if this is the right way to move
> > forward?  I am not sure why PERF_SAMPLE_MASK doesn't contain the bit
> > PERF_SAMPLE_PHYS_ADDR in current code.
> 
> I think there is a reason that PERF_SAMPLE_MASK is a subset of all the
> bits. This comment below suggests it. Is it so the mask only includes fields
> that are 64bits? That makes the __evsel__sample_size() function a simple
> multiplication of a count of all the fields that are 64bits.

After reading code, seems the conclusion "a count of all the fields
that are 64bits" is not valid.  PERF_SAMPLE_MASK contains bits
PERF_SAMPLE_IP and PERF_SAMPLE_TID, the corresponding fields 'pid'
and 'tid' in the structure perf_sample are u32 type.

>   static int
>   perf_event__check_size(union perf_event *event, unsigned int sample_size)
>   {
> 	/*
> 	 * The evsel's sample_size is based on PERF_SAMPLE_MASK which includes
> 	 * up to PERF_SAMPLE_PERIOD.  After that overflow() must be used to
> 	 * check the format does not go past the end of the event.
> 	 */
> 	if (sample_size + sizeof(event->header) > event->header.size)
> 		return -EFAULT;

Okay, thanks for sharing the info, it does show that it's deliberately to
not contain all fields in PERF_SAMPLE_MASK.  If so, this patch is fine
for me:

Reviewed-by: Leo Yan <leo.yan@linaro.org>


> 	return 0;
>   }
> 
> Having said that, the mask was updated once to add PERF_SAMPLE_IDENTIFIER to
> it, so that comment is slightly out of date now.
> 
> 
> > 
> > diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
> > index cdd72e05fd28..c905ac32ebad 100644
> > --- a/tools/perf/util/event.h
> > +++ b/tools/perf/util/event.h
> > @@ -39,7 +39,7 @@ struct perf_event_attr;
> >          PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |          \
> >         PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |        \
> >          PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD |         \
> > -        PERF_SAMPLE_IDENTIFIER)
> > +        PERF_SAMPLE_IDENTIFIER | PERF_SAMPLE_PHYS_ADDR)
> > 
> > Thanks,
> > Leo
> > 
> >>  	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
> >>  			    PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
> >>  			    PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR;
> >> -- 
> >> 2.25.1
> >>

Re: [PATCH 3/3] perf test: Add perf_event_attr test for Arm SPE

[Arnaldo Carvalho de Melo]

Em Sun, Apr 24, 2022 at 10:53:07PM +0800, Leo Yan escreveu:
> On Thu, Apr 21, 2022 at 05:52:05PM +0100, Timothy Hayes wrote:
> > Adds a perf_event_attr test for Arm SPE in which the presence of
> > physical addresses are checked when SPE unit is run with pa_enable=1.
> > 
> > Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>
> 
> Reviewed-by: Leo Yan <leo.yan@linaro.org>
> Tested-by: Leo Yan <leo.yan@linaro.org>

Thanks, applied the set to perf/urgent.

- Arnaldo
 
> > ---
> >  tools/perf/tests/attr/README                         |  1 +
> >  .../perf/tests/attr/test-record-spe-physical-address | 12 ++++++++++++
> >  2 files changed, 13 insertions(+)
> >  create mode 100644 tools/perf/tests/attr/test-record-spe-physical-address
> > 
> > diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
> > index 454505d343fa..eb3f7d4bb324 100644
> > --- a/tools/perf/tests/attr/README
> > +++ b/tools/perf/tests/attr/README
> > @@ -60,6 +60,7 @@ Following tests are defined (with perf commands):
> >    perf record -R kill                           (test-record-raw)
> >    perf record -c 2 -e arm_spe_0// -- kill       (test-record-spe-period)
> >    perf record -e arm_spe_0/period=3/ -- kill    (test-record-spe-period-term)
> > +  perf record -e arm_spe_0/pa_enable=1/ -- kill (test-record-spe-physical-address)
> >    perf stat -e cycles kill                      (test-stat-basic)
> >    perf stat kill                                (test-stat-default)
> >    perf stat -d kill                             (test-stat-detailed-1)
> > diff --git a/tools/perf/tests/attr/test-record-spe-physical-address b/tools/perf/tests/attr/test-record-spe-physical-address
> > new file mode 100644
> > index 000000000000..7ebcf5012ce3
> > --- /dev/null
> > +++ b/tools/perf/tests/attr/test-record-spe-physical-address
> > @@ -0,0 +1,12 @@
> > +[config]
> > +command = record
> > +args    = --no-bpf-event -e arm_spe_0/pa_enable=1/ -- kill >/dev/null 2>&1
> > +ret     = 1
> > +arch    = aarch64
> > +
> > +[event-10:base-record-spe]
> > +# 622727 is the decimal of IP|TID|TIME|CPU|IDENTIFIER|DATA_SRC|PHYS_ADDR
> > +sample_type=622727
> > +
> > +# dummy event
> > +[event-1:base-record-spe]
> > \ No newline at end of file
> > -- 
> > 2.25.1
> > 

-- 

- Arnaldo