[PATCH 0/6] PMUv3 event handling improvements

[PATCH 0/6] PMUv3 event handling improvements

[Will Deacon]

Hi all,

Following on-list discussion with Ganapat [1], I found and fixed a few
issues with the arm64 PMUv3 code:

  - We don't reject standalone CHAIN events requested in a 32-bit perf event
  - We don't interpret the upper 32 bits of the PMCEID registers for 8.1 events
  - We have duplicate cache events for read and write, which is very confusing
  - Our events are straddled between arm_pmu.c and arm_pmu.h and aren't in
    numerical order
  - We don't advertise a bunch fo new events that have been added since v8.0

This series addresses all of these problems.

Cheers,

Will

[1] http://lkml.kernel.org/r/CAKTKpr6SQUc9EgdYL2N32a=szUmSs82Mbb4y89htbVQhTPp2rQ at mail.gmail.com

--->8

Will Deacon (6):
  arm64: perf: Reject stand-alone CHAIN events for PMUv3
  arm64: perf: Terminate PMU assignment statements with semicolons
  arm64: perf: Add support for Armv8.1 PMCEID register format
  arm64: perf: Remove duplicate generic cache events
  arm64: perf: Move event definitions into perf_event.h
  arm64: perf: Hook up new events

 arch/arm64/include/asm/perf_event.h | 164 ++++++++++++++++++++++++--
 arch/arm64/kernel/perf_event.c      | 225 ++++++++++--------------------------
 drivers/perf/arm_pmu.c              |   8 +-
 include/linux/perf/arm_pmu.h        |   5 +-
 4 files changed, 225 insertions(+), 177 deletions(-)

-- 
2.1.4

[PATCH 1/6] arm64: perf: Reject stand-alone CHAIN events for PMUv3

[Will Deacon]

It doesn't make sense for a perf event to be configured as a CHAIN event
in isolation, so extend the arm_pmu structure with a ->filter_match()
function to allow the backend PMU implementation to reject CHAIN events
early.

Cc: <stable@vger.kernel.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/perf_event.c | 7 +++++++
 drivers/perf/arm_pmu.c         | 8 +++++++-
 include/linux/perf/arm_pmu.h   | 1 +
 3 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 8e38d5267f22..e213f8e867f6 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -966,6 +966,12 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 	return 0;
 }
 
+static int armv8pmu_filter_match(struct perf_event *event)
+{
+	unsigned long evtype = event->hw.config_base & ARMV8_PMU_EVTYPE_EVENT;
+	return evtype != ARMV8_PMUV3_PERFCTR_CHAIN;
+}
+
 static void armv8pmu_reset(void *info)
 {
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
@@ -1114,6 +1120,7 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->stop			= armv8pmu_stop,
 	cpu_pmu->reset			= armv8pmu_reset,
 	cpu_pmu->set_event_filter	= armv8pmu_set_event_filter;
+	cpu_pmu->filter_match		= armv8pmu_filter_match;
 
 	return 0;
 }
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 7f01f6f60b87..d0b7dd8fb184 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -485,7 +485,13 @@ static int armpmu_filter_match(struct perf_event *event)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	unsigned int cpu = smp_processor_id();
-	return cpumask_test_cpu(cpu, &armpmu->supported_cpus);
+	int ret;
+
+	ret = cpumask_test_cpu(cpu, &armpmu->supported_cpus);
+	if (ret && armpmu->filter_match)
+		return armpmu->filter_match(event);
+
+	return ret;
 }
 
 static ssize_t armpmu_cpumask_show(struct device *dev,
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 10f92e1d8e7b..bf309ff6f244 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -99,6 +99,7 @@ struct arm_pmu {
 	void		(*stop)(struct arm_pmu *);
 	void		(*reset)(void *);
 	int		(*map_event)(struct perf_event *event);
+	int		(*filter_match)(struct perf_event *event);
 	int		num_events;
 	bool		secure_access; /* 32-bit ARM only */
 #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40
-- 
2.1.4

[PATCH 1/6] arm64: perf: Reject stand-alone CHAIN events for PMUv3

[Will Deacon]

It doesn't make sense for a perf event to be configured as a CHAIN event
in isolation, so extend the arm_pmu structure with a ->filter_match()
function to allow the backend PMU implementation to reject CHAIN events
early.

Cc: <stable@vger.kernel.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/perf_event.c | 7 +++++++
 drivers/perf/arm_pmu.c         | 8 +++++++-
 include/linux/perf/arm_pmu.h   | 1 +
 3 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 8e38d5267f22..e213f8e867f6 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -966,6 +966,12 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 	return 0;
 }
 
+static int armv8pmu_filter_match(struct perf_event *event)
+{
+	unsigned long evtype = event->hw.config_base & ARMV8_PMU_EVTYPE_EVENT;
+	return evtype != ARMV8_PMUV3_PERFCTR_CHAIN;
+}
+
 static void armv8pmu_reset(void *info)
 {
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
@@ -1114,6 +1120,7 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->stop			= armv8pmu_stop,
 	cpu_pmu->reset			= armv8pmu_reset,
 	cpu_pmu->set_event_filter	= armv8pmu_set_event_filter;
+	cpu_pmu->filter_match		= armv8pmu_filter_match;
 
 	return 0;
 }
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 7f01f6f60b87..d0b7dd8fb184 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -485,7 +485,13 @@ static int armpmu_filter_match(struct perf_event *event)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	unsigned int cpu = smp_processor_id();
-	return cpumask_test_cpu(cpu, &armpmu->supported_cpus);
+	int ret;
+
+	ret = cpumask_test_cpu(cpu, &armpmu->supported_cpus);
+	if (ret && armpmu->filter_match)
+		return armpmu->filter_match(event);
+
+	return ret;
 }
 
 static ssize_t armpmu_cpumask_show(struct device *dev,
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 10f92e1d8e7b..bf309ff6f244 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -99,6 +99,7 @@ struct arm_pmu {
 	void		(*stop)(struct arm_pmu *);
 	void		(*reset)(void *);
 	int		(*map_event)(struct perf_event *event);
+	int		(*filter_match)(struct perf_event *event);
 	int		num_events;
 	bool		secure_access; /* 32-bit ARM only */
 #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40
-- 
2.1.4

[PATCH 1/6] arm64: perf: Reject stand-alone CHAIN events for PMUv3

[Suzuki K Poulose]

Hi Will

On 10/10/18 17:31, Will Deacon wrote:
> It doesn't make sense for a perf event to be configured as a CHAIN event
> in isolation, so extend the arm_pmu structure with a ->filter_match()
> function to allow the backend PMU implementation to reject CHAIN events
> early.
> 
> Cc: <stable@vger.kernel.org>
> Signed-off-by: Will Deacon <will.deacon@arm.com>



> ---
>   arch/arm64/kernel/perf_event.c | 7 +++++++
>   drivers/perf/arm_pmu.c         | 8 +++++++-
>   include/linux/perf/arm_pmu.h   | 1 +
>   3 files changed, 15 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
> index 8e38d5267f22..e213f8e867f6 100644
> --- a/arch/arm64/kernel/perf_event.c
> +++ b/arch/arm64/kernel/perf_event.c
> @@ -966,6 +966,12 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
>   	return 0;
>   }
>   
> +static int armv8pmu_filter_match(struct perf_event *event)
> +{
> +	unsigned long evtype = event->hw.config_base & ARMV8_PMU_EVTYPE_EVENT;
> +	return evtype != ARMV8_PMUV3_PERFCTR_CHAIN;
> +}
> +

The patch looks correct. I guess we could handle it via the existing
map_event(), avoiding another arch specific callback.

Either way,

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>

Re: [PATCH 1/6] arm64: perf: Reject stand-alone CHAIN events for PMUv3

[Suzuki K Poulose]

Hi Will

On 10/10/18 17:31, Will Deacon wrote:
> It doesn't make sense for a perf event to be configured as a CHAIN event
> in isolation, so extend the arm_pmu structure with a ->filter_match()
> function to allow the backend PMU implementation to reject CHAIN events
> early.
> 
> Cc: <stable@vger.kernel.org>
> Signed-off-by: Will Deacon <will.deacon@arm.com>



> ---
>   arch/arm64/kernel/perf_event.c | 7 +++++++
>   drivers/perf/arm_pmu.c         | 8 +++++++-
>   include/linux/perf/arm_pmu.h   | 1 +
>   3 files changed, 15 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
> index 8e38d5267f22..e213f8e867f6 100644
> --- a/arch/arm64/kernel/perf_event.c
> +++ b/arch/arm64/kernel/perf_event.c
> @@ -966,6 +966,12 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
>   	return 0;
>   }
>   
> +static int armv8pmu_filter_match(struct perf_event *event)
> +{
> +	unsigned long evtype = event->hw.config_base & ARMV8_PMU_EVTYPE_EVENT;
> +	return evtype != ARMV8_PMUV3_PERFCTR_CHAIN;
> +}
> +

The patch looks correct. I guess we could handle it via the existing
map_event(), avoiding another arch specific callback.

Either way,

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>

[PATCH 1/6] arm64: perf: Reject stand-alone CHAIN events for PMUv3

[Will Deacon]

On Wed, Oct 10, 2018 at 06:30:13PM +0100, Suzuki K Poulose wrote:
> On 10/10/18 17:31, Will Deacon wrote:
> >It doesn't make sense for a perf event to be configured as a CHAIN event
> >in isolation, so extend the arm_pmu structure with a ->filter_match()
> >function to allow the backend PMU implementation to reject CHAIN events
> >early.
> >
> >Cc: <stable@vger.kernel.org>
> >Signed-off-by: Will Deacon <will.deacon@arm.com>
> 
> 
> 
> >---
> >  arch/arm64/kernel/perf_event.c | 7 +++++++
> >  drivers/perf/arm_pmu.c         | 8 +++++++-
> >  include/linux/perf/arm_pmu.h   | 1 +
> >  3 files changed, 15 insertions(+), 1 deletion(-)
> >
> >diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
> >index 8e38d5267f22..e213f8e867f6 100644
> >--- a/arch/arm64/kernel/perf_event.c
> >+++ b/arch/arm64/kernel/perf_event.c
> >@@ -966,6 +966,12 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
> >  	return 0;
> >  }
> >+static int armv8pmu_filter_match(struct perf_event *event)
> >+{
> >+	unsigned long evtype = event->hw.config_base & ARMV8_PMU_EVTYPE_EVENT;
> >+	return evtype != ARMV8_PMUV3_PERFCTR_CHAIN;
> >+}
> >+
> 
> The patch looks correct. I guess we could handle it via the existing
> map_event(), avoiding another arch specific callback.

I initially implemented it using ->map_event(), but that has weird
interactions with groups where other events in the group following the
CHAIN event will not count, but previous events will. This means that the
perf behaviour depends on the order in which you specify the events, which
is really confusing!

> Either way,
> 
> Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>

Thanks.

Will

Re: [PATCH 1/6] arm64: perf: Reject stand-alone CHAIN events for PMUv3

[Will Deacon]

On Wed, Oct 10, 2018 at 06:30:13PM +0100, Suzuki K Poulose wrote:
> On 10/10/18 17:31, Will Deacon wrote:
> >It doesn't make sense for a perf event to be configured as a CHAIN event
> >in isolation, so extend the arm_pmu structure with a ->filter_match()
> >function to allow the backend PMU implementation to reject CHAIN events
> >early.
> >
> >Cc: <stable@vger.kernel.org>
> >Signed-off-by: Will Deacon <will.deacon@arm.com>
> 
> 
> 
> >---
> >  arch/arm64/kernel/perf_event.c | 7 +++++++
> >  drivers/perf/arm_pmu.c         | 8 +++++++-
> >  include/linux/perf/arm_pmu.h   | 1 +
> >  3 files changed, 15 insertions(+), 1 deletion(-)
> >
> >diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
> >index 8e38d5267f22..e213f8e867f6 100644
> >--- a/arch/arm64/kernel/perf_event.c
> >+++ b/arch/arm64/kernel/perf_event.c
> >@@ -966,6 +966,12 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
> >  	return 0;
> >  }
> >+static int armv8pmu_filter_match(struct perf_event *event)
> >+{
> >+	unsigned long evtype = event->hw.config_base & ARMV8_PMU_EVTYPE_EVENT;
> >+	return evtype != ARMV8_PMUV3_PERFCTR_CHAIN;
> >+}
> >+
> 
> The patch looks correct. I guess we could handle it via the existing
> map_event(), avoiding another arch specific callback.

I initially implemented it using ->map_event(), but that has weird
interactions with groups where other events in the group following the
CHAIN event will not count, but previous events will. This means that the
perf behaviour depends on the order in which you specify the events, which
is really confusing!

> Either way,
> 
> Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>

Thanks.

Will

[PATCH 2/6] arm64: perf: Terminate PMU assignment statements with semicolons

[Will Deacon]

As a hangover from when this code used a designated initialiser, we've
been using commas to terminate the arm_pmu field assignments. Whilst
harmless, it's also weird, so replace them with semicolons instead.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/perf_event.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index e213f8e867f6..ac1c5c41501d 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1109,16 +1109,16 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
 	if (ret)
 		return ret;
 
-	cpu_pmu->handle_irq		= armv8pmu_handle_irq,
-	cpu_pmu->enable			= armv8pmu_enable_event,
-	cpu_pmu->disable		= armv8pmu_disable_event,
-	cpu_pmu->read_counter		= armv8pmu_read_counter,
-	cpu_pmu->write_counter		= armv8pmu_write_counter,
-	cpu_pmu->get_event_idx		= armv8pmu_get_event_idx,
-	cpu_pmu->clear_event_idx	= armv8pmu_clear_event_idx,
-	cpu_pmu->start			= armv8pmu_start,
-	cpu_pmu->stop			= armv8pmu_stop,
-	cpu_pmu->reset			= armv8pmu_reset,
+	cpu_pmu->handle_irq		= armv8pmu_handle_irq;
+	cpu_pmu->enable			= armv8pmu_enable_event;
+	cpu_pmu->disable		= armv8pmu_disable_event;
+	cpu_pmu->read_counter		= armv8pmu_read_counter;
+	cpu_pmu->write_counter		= armv8pmu_write_counter;
+	cpu_pmu->get_event_idx		= armv8pmu_get_event_idx;
+	cpu_pmu->clear_event_idx	= armv8pmu_clear_event_idx;
+	cpu_pmu->start			= armv8pmu_start;
+	cpu_pmu->stop			= armv8pmu_stop;
+	cpu_pmu->reset			= armv8pmu_reset;
 	cpu_pmu->set_event_filter	= armv8pmu_set_event_filter;
 	cpu_pmu->filter_match		= armv8pmu_filter_match;
 
-- 
2.1.4

[PATCH 3/6] arm64: perf: Add support for Armv8.1 PMCEID register format

[Will Deacon]

Armv8.1 allocated the upper 32-bits of the PMCEID registers to describe
the common architectural and microarchitecture events beginning at 0x4000.

Add support for these registers to our probing code, so that we can
advertise the SPE events when they are supported by the CPU.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/perf_event.c | 25 ++++++++++++++++++-------
 include/linux/perf/arm_pmu.h   |  4 +++-
 2 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index ac1c5c41501d..1a783df6f234 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -183,12 +183,10 @@
 #define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_ACCESS		0xEC
 #define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS		0xED
 
-/* PMUv3 HW events mapping. */
-
 /*
  * ARMv8 Architectural defined events, not all of these may
- * be supported on any given implementation. Undefined events will
- * be disabled at run-time.
+ * be supported on any given implementation. Unsupported events will
+ * be disabled at run-time based on the PMCEID registers.
  */
 static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
 	PERF_MAP_ALL_UNSUPPORTED,
@@ -434,7 +432,13 @@ armv8pmu_event_attr_is_visible(struct kobject *kobj,
 
 	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);
 
-	if (test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap))
+	if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
+	    test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap))
+		return attr->mode;
+
+	pmu_attr->id -= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
+	if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
+	    test_bit(pmu_attr->id, cpu_pmu->pmceid_ext_bitmap))
 		return attr->mode;
 
 	return 0;
@@ -1061,6 +1065,7 @@ static void __armv8pmu_probe_pmu(void *info)
 	struct armv8pmu_probe_info *probe = info;
 	struct arm_pmu *cpu_pmu = probe->pmu;
 	u64 dfr0;
+	u64 pmceid_raw[2];
 	u32 pmceid[2];
 	int pmuver;
 
@@ -1079,11 +1084,17 @@ static void __armv8pmu_probe_pmu(void *info)
 	/* Add the CPU cycles counter */
 	cpu_pmu->num_events += 1;
 
-	pmceid[0] = read_sysreg(pmceid0_el0);
-	pmceid[1] = read_sysreg(pmceid1_el0);
+	pmceid[0] = pmceid_raw[0] = read_sysreg(pmceid0_el0);
+	pmceid[1] = pmceid_raw[1] = read_sysreg(pmceid1_el0);
 
 	bitmap_from_arr32(cpu_pmu->pmceid_bitmap,
 			     pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS);
+
+	pmceid[0] = pmceid_raw[0] >> 32;
+	pmceid[1] = pmceid_raw[1] >> 32;
+
+	bitmap_from_arr32(cpu_pmu->pmceid_ext_bitmap,
+			     pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS);
 }
 
 static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index bf309ff6f244..4641e850b204 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -102,8 +102,10 @@ struct arm_pmu {
 	int		(*filter_match)(struct perf_event *event);
 	int		num_events;
 	bool		secure_access; /* 32-bit ARM only */
-#define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40
+#define ARMV8_PMUV3_MAX_COMMON_EVENTS		0x40
 	DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
+#define ARMV8_PMUV3_EXT_COMMON_EVENT_BASE	0x4000
+	DECLARE_BITMAP(pmceid_ext_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
 	struct platform_device	*plat_device;
 	struct pmu_hw_events	__percpu *hw_events;
 	struct hlist_node	node;
-- 
2.1.4

[PATCH 4/6] arm64: perf: Remove duplicate generic cache events

[Will Deacon]

We cannot distinguish reads from writes in our generic cache events, so
drop the WRITE entries and leave the READ entries pointing to the combined
read/write events, as is done by other CPUs and architectures.

Reported-by: Ganapatrao Kulkarni <Ganapatrao.Kulkarni@cavium.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/perf_event.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 1a783df6f234..3005a29472e2 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -208,8 +208,6 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 
 	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE,
 	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
-	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE,
-	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
 
 	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1I_CACHE,
 	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL,
@@ -222,8 +220,6 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 
 	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_BR_PRED,
 	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
-	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_BR_PRED,
-	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
 };
 
 static const unsigned armv8_a53_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
-- 
2.1.4

[PATCH 5/6] arm64: perf: Move event definitions into perf_event.h

[Will Deacon]

The PMU event numbers are split between perf_event.h and perf_event.c,
which makes it difficult to spot any gaps in the numbers which may be
allocated in the future.

This patch sorts the events numerically, adds some missing events and
moves the definitions into perf_event.h.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/perf_event.h | 164 +++++++++++++++++++++++++++++++++---
 arch/arm64/kernel/perf_event.c      | 145 +------------------------------
 2 files changed, 155 insertions(+), 154 deletions(-)

diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index f9ccc36d3dc3..6bad0f6173df 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -24,6 +24,160 @@
 #define	ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
 
 /*
+ * Common architectural and microarchitectural event numbers.
+ */
+#define ARMV8_PMUV3_PERFCTR_SW_INCR				0x00
+#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL			0x01
+#define ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL			0x02
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL			0x03
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE				0x04
+#define ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL			0x05
+#define ARMV8_PMUV3_PERFCTR_LD_RETIRED				0x06
+#define ARMV8_PMUV3_PERFCTR_ST_RETIRED				0x07
+#define ARMV8_PMUV3_PERFCTR_INST_RETIRED			0x08
+#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN				0x09
+#define ARMV8_PMUV3_PERFCTR_EXC_RETURN				0x0A
+#define ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED			0x0B
+#define ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED			0x0C
+#define ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED			0x0D
+#define ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED			0x0E
+#define ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED		0x0F
+#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED				0x10
+#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES				0x11
+#define ARMV8_PMUV3_PERFCTR_BR_PRED				0x12
+#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS				0x13
+#define ARMV8_PMUV3_PERFCTR_L1I_CACHE				0x14
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB			0x15
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE				0x16
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL			0x17
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB			0x18
+#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS				0x19
+#define ARMV8_PMUV3_PERFCTR_MEMORY_ERROR			0x1A
+#define ARMV8_PMUV3_PERFCTR_INST_SPEC				0x1B
+#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED			0x1C
+#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES				0x1D
+#define ARMV8_PMUV3_PERFCTR_CHAIN				0x1E
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE			0x1F
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE			0x20
+#define ARMV8_PMUV3_PERFCTR_BR_RETIRED				0x21
+#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED			0x22
+#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND			0x23
+#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND			0x24
+#define ARMV8_PMUV3_PERFCTR_L1D_TLB				0x25
+#define ARMV8_PMUV3_PERFCTR_L1I_TLB				0x26
+#define ARMV8_PMUV3_PERFCTR_L2I_CACHE				0x27
+#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL			0x28
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE			0x29
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL			0x2A
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE				0x2B
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB			0x2C
+#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL			0x2D
+#define ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL			0x2E
+#define ARMV8_PMUV3_PERFCTR_L2D_TLB				0x2F
+#define ARMV8_PMUV3_PERFCTR_L2I_TLB				0x30
+#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS			0x31
+#define ARMV8_PMUV3_PERFCTR_LL_CACHE				0x32
+#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS			0x33
+#define ARMV8_PMUV3_PERFCTR_DTLB_WALK				0x34
+#define ARMV8_PMUV3_PERFCTR_ITLB_WALK				0x35
+#define ARMV8_PMUV3_PERFCTR_LL_CACHE_RD				0x36
+#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD			0x37
+#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD			0x38
+
+/* Statistical profiling extension microarchitectural events */
+#define	ARMV8_SPE_PERFCTR_SAMPLE_POP				0x4000
+#define	ARMV8_SPE_PERFCTR_SAMPLE_FEED				0x4000
+#define	ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE			0x4000
+#define	ARMV8_SPE_PERFCTR_SAMPLE_COLLISION			0x4000
+
+/* ARMv8 recommended implementation defined event types */
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD			0x40
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR			0x41
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD		0x42
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR		0x43
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_INNER		0x44
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_OUTER		0x45
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_VICTIM		0x46
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_CLEAN			0x47
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_INVAL			0x48
+
+#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD			0x4C
+#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR			0x4D
+#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD				0x4E
+#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR				0x4F
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_RD			0x50
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WR			0x51
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_RD		0x52
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_WR		0x53
+
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_VICTIM		0x56
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_CLEAN			0x57
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_INVAL			0x58
+
+#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_RD			0x5C
+#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_WR			0x5D
+#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_RD				0x5E
+#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_WR				0x5F
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD			0x60
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR			0x61
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_SHARED			0x62
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NOT_SHARED		0x63
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NORMAL			0x64
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_PERIPH			0x65
+#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_RD			0x66
+#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_WR			0x67
+#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LD_SPEC			0x68
+#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_ST_SPEC			0x69
+#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LDST_SPEC		0x6A
+
+#define ARMV8_IMPDEF_PERFCTR_LDREX_SPEC				0x6C
+#define ARMV8_IMPDEF_PERFCTR_STREX_PASS_SPEC			0x6D
+#define ARMV8_IMPDEF_PERFCTR_STREX_FAIL_SPEC			0x6E
+#define ARMV8_IMPDEF_PERFCTR_STREX_SPEC				0x6F
+#define ARMV8_IMPDEF_PERFCTR_LD_SPEC				0x70
+#define ARMV8_IMPDEF_PERFCTR_ST_SPEC				0x71
+#define ARMV8_IMPDEF_PERFCTR_LDST_SPEC				0x72
+#define ARMV8_IMPDEF_PERFCTR_DP_SPEC				0x73
+#define ARMV8_IMPDEF_PERFCTR_ASE_SPEC				0x74
+#define ARMV8_IMPDEF_PERFCTR_VFP_SPEC				0x75
+#define ARMV8_IMPDEF_PERFCTR_PC_WRITE_SPEC			0x76
+#define ARMV8_IMPDEF_PERFCTR_CRYPTO_SPEC			0x77
+#define ARMV8_IMPDEF_PERFCTR_BR_IMMED_SPEC			0x78
+#define ARMV8_IMPDEF_PERFCTR_BR_RETURN_SPEC			0x79
+#define ARMV8_IMPDEF_PERFCTR_BR_INDIRECT_SPEC			0x7A
+
+#define ARMV8_IMPDEF_PERFCTR_ISB_SPEC				0x7C
+#define ARMV8_IMPDEF_PERFCTR_DSB_SPEC				0x7D
+#define ARMV8_IMPDEF_PERFCTR_DMB_SPEC				0x7E
+
+#define ARMV8_IMPDEF_PERFCTR_EXC_UNDEF				0x81
+#define ARMV8_IMPDEF_PERFCTR_EXC_SVC				0x82
+#define ARMV8_IMPDEF_PERFCTR_EXC_PABORT				0x83
+#define ARMV8_IMPDEF_PERFCTR_EXC_DABORT				0x84
+
+#define ARMV8_IMPDEF_PERFCTR_EXC_IRQ				0x86
+#define ARMV8_IMPDEF_PERFCTR_EXC_FIQ				0x87
+#define ARMV8_IMPDEF_PERFCTR_EXC_SMC				0x88
+
+#define ARMV8_IMPDEF_PERFCTR_EXC_HVC				0x8A
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_PABORT			0x8B
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_DABORT			0x8C
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_OTHER			0x8D
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_IRQ			0x8E
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_FIQ			0x8F
+#define ARMV8_IMPDEF_PERFCTR_RC_LD_SPEC				0x90
+#define ARMV8_IMPDEF_PERFCTR_RC_ST_SPEC				0x91
+
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_RD			0xA0
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WR			0xA1
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_RD		0xA2
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_WR		0xA3
+
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_VICTIM		0xA6
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_CLEAN			0xA7
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_INVAL			0xA8
+
+/*
  * Per-CPU PMCR: config reg
  */
 #define ARMV8_PMU_PMCR_E	(1 << 0) /* Enable all counters */
@@ -50,16 +204,6 @@
 #define	ARMV8_PMU_EVTYPE_EVENT	0xffff		/* Mask for EVENT bits */
 
 /*
- * PMUv3 event types: required events
- */
-#define ARMV8_PMUV3_PERFCTR_SW_INCR				0x00
-#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL			0x03
-#define ARMV8_PMUV3_PERFCTR_L1D_CACHE				0x04
-#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED				0x10
-#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES				0x11
-#define ARMV8_PMUV3_PERFCTR_BR_PRED				0x12
-
-/*
  * Event filters for PMUv3
  */
 #define	ARMV8_PMU_EXCLUDE_EL1	(1 << 31)
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 3005a29472e2..a6e17622bad3 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1,5 +1,5 @@
 /*
- * PMU support
+ * ARMv8 PMUv3 Performance Events handling code.
  *
  * Copyright (C) 2012 ARM Limited
  * Author: Will Deacon <will.deacon@arm.com>
@@ -30,149 +30,6 @@
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
 
-/*
- * ARMv8 PMUv3 Performance Events handling code.
- * Common event types (some are defined in asm/perf_event.h).
- */
-
-/* At least one of the following is required. */
-#define ARMV8_PMUV3_PERFCTR_INST_RETIRED			0x08
-#define ARMV8_PMUV3_PERFCTR_INST_SPEC				0x1B
-
-/* Common architectural events. */
-#define ARMV8_PMUV3_PERFCTR_LD_RETIRED				0x06
-#define ARMV8_PMUV3_PERFCTR_ST_RETIRED				0x07
-#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN				0x09
-#define ARMV8_PMUV3_PERFCTR_EXC_RETURN				0x0A
-#define ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED			0x0B
-#define ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED			0x0C
-#define ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED			0x0D
-#define ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED			0x0E
-#define ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED		0x0F
-#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED			0x1C
-#define ARMV8_PMUV3_PERFCTR_CHAIN				0x1E
-#define ARMV8_PMUV3_PERFCTR_BR_RETIRED				0x21
-
-/* Common microarchitectural events. */
-#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL			0x01
-#define ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL			0x02
-#define ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL			0x05
-#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS				0x13
-#define ARMV8_PMUV3_PERFCTR_L1I_CACHE				0x14
-#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB			0x15
-#define ARMV8_PMUV3_PERFCTR_L2D_CACHE				0x16
-#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL			0x17
-#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB			0x18
-#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS				0x19
-#define ARMV8_PMUV3_PERFCTR_MEMORY_ERROR			0x1A
-#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES				0x1D
-#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE			0x1F
-#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE			0x20
-#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED			0x22
-#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND			0x23
-#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND			0x24
-#define ARMV8_PMUV3_PERFCTR_L1D_TLB				0x25
-#define ARMV8_PMUV3_PERFCTR_L1I_TLB				0x26
-#define ARMV8_PMUV3_PERFCTR_L2I_CACHE				0x27
-#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL			0x28
-#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE			0x29
-#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL			0x2A
-#define ARMV8_PMUV3_PERFCTR_L3D_CACHE				0x2B
-#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB			0x2C
-#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL			0x2D
-#define ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL			0x2E
-#define ARMV8_PMUV3_PERFCTR_L2D_TLB				0x2F
-#define ARMV8_PMUV3_PERFCTR_L2I_TLB				0x30
-
-/* ARMv8 recommended implementation defined event types */
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD			0x40
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR			0x41
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD		0x42
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR		0x43
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_INNER		0x44
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_OUTER		0x45
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_VICTIM		0x46
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_CLEAN			0x47
-#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_INVAL			0x48
-
-#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD			0x4C
-#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR			0x4D
-#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD				0x4E
-#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR				0x4F
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_RD			0x50
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WR			0x51
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_RD		0x52
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_WR		0x53
-
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_VICTIM		0x56
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_CLEAN			0x57
-#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_INVAL			0x58
-
-#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_RD			0x5C
-#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_WR			0x5D
-#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_RD				0x5E
-#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_WR				0x5F
-
-#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD			0x60
-#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR			0x61
-#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_SHARED			0x62
-#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NOT_SHARED		0x63
-#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NORMAL			0x64
-#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_PERIPH			0x65
-
-#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_RD			0x66
-#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_WR			0x67
-#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LD_SPEC			0x68
-#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_ST_SPEC			0x69
-#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LDST_SPEC		0x6A
-
-#define ARMV8_IMPDEF_PERFCTR_LDREX_SPEC				0x6C
-#define ARMV8_IMPDEF_PERFCTR_STREX_PASS_SPEC			0x6D
-#define ARMV8_IMPDEF_PERFCTR_STREX_FAIL_SPEC			0x6E
-#define ARMV8_IMPDEF_PERFCTR_STREX_SPEC				0x6F
-#define ARMV8_IMPDEF_PERFCTR_LD_SPEC				0x70
-#define ARMV8_IMPDEF_PERFCTR_ST_SPEC				0x71
-#define ARMV8_IMPDEF_PERFCTR_LDST_SPEC				0x72
-#define ARMV8_IMPDEF_PERFCTR_DP_SPEC				0x73
-#define ARMV8_IMPDEF_PERFCTR_ASE_SPEC				0x74
-#define ARMV8_IMPDEF_PERFCTR_VFP_SPEC				0x75
-#define ARMV8_IMPDEF_PERFCTR_PC_WRITE_SPEC			0x76
-#define ARMV8_IMPDEF_PERFCTR_CRYPTO_SPEC			0x77
-#define ARMV8_IMPDEF_PERFCTR_BR_IMMED_SPEC			0x78
-#define ARMV8_IMPDEF_PERFCTR_BR_RETURN_SPEC			0x79
-#define ARMV8_IMPDEF_PERFCTR_BR_INDIRECT_SPEC			0x7A
-
-#define ARMV8_IMPDEF_PERFCTR_ISB_SPEC				0x7C
-#define ARMV8_IMPDEF_PERFCTR_DSB_SPEC				0x7D
-#define ARMV8_IMPDEF_PERFCTR_DMB_SPEC				0x7E
-
-#define ARMV8_IMPDEF_PERFCTR_EXC_UNDEF				0x81
-#define ARMV8_IMPDEF_PERFCTR_EXC_SVC				0x82
-#define ARMV8_IMPDEF_PERFCTR_EXC_PABORT				0x83
-#define ARMV8_IMPDEF_PERFCTR_EXC_DABORT				0x84
-
-#define ARMV8_IMPDEF_PERFCTR_EXC_IRQ				0x86
-#define ARMV8_IMPDEF_PERFCTR_EXC_FIQ				0x87
-#define ARMV8_IMPDEF_PERFCTR_EXC_SMC				0x88
-
-#define ARMV8_IMPDEF_PERFCTR_EXC_HVC				0x8A
-#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_PABORT			0x8B
-#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_DABORT			0x8C
-#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_OTHER			0x8D
-#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_IRQ			0x8E
-#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_FIQ			0x8F
-#define ARMV8_IMPDEF_PERFCTR_RC_LD_SPEC				0x90
-#define ARMV8_IMPDEF_PERFCTR_RC_ST_SPEC				0x91
-
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_RD			0xA0
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WR			0xA1
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_RD		0xA2
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_WR		0xA3
-
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_VICTIM		0xA6
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_CLEAN			0xA7
-#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_INVAL			0xA8
-
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2
 
-- 
2.1.4

[PATCH 5/6] arm64: perf: Move event definitions into perf_event.h

[Suzuki K Poulose]

Hi Will,

On 10/10/18 17:31, Will Deacon wrote:
> The PMU event numbers are split between perf_event.h and perf_event.c,
> which makes it difficult to spot any gaps in the numbers which may be
> allocated in the future.
> 
> This patch sorts the events numerically, adds some missing events and
> moves the definitions into perf_event.h.
> 
> Signed-off-by: Will Deacon <will.deacon@arm.com>
> ---
>   arch/arm64/include/asm/perf_event.h | 164 +++++++++++++++++++++++++++++++++---
>   arch/arm64/kernel/perf_event.c      | 145 +------------------------------
>   2 files changed, 155 insertions(+), 154 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
> index f9ccc36d3dc3..6bad0f6173df 100644
> --- a/arch/arm64/include/asm/perf_event.h
> +++ b/arch/arm64/include/asm/perf_event.h
> @@ -24,6 +24,160 @@
>   #define	ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
>   
>   /*
> + * Common architectural and microarchitectural event numbers.
> + */
> +#define ARMV8_PMUV3_PERFCTR_SW_INCR				0x00
> +#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL			0x01
> +#define ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL			0x02
> +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL			0x03
> +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE				0x04
> +#define ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL			0x05
> +#define ARMV8_PMUV3_PERFCTR_LD_RETIRED				0x06
> +#define ARMV8_PMUV3_PERFCTR_ST_RETIRED				0x07
> +#define ARMV8_PMUV3_PERFCTR_INST_RETIRED			0x08
> +#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN				0x09
> +#define ARMV8_PMUV3_PERFCTR_EXC_RETURN				0x0A
> +#define ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED			0x0B
> +#define ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED			0x0C
> +#define ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED			0x0D
> +#define ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED			0x0E
> +#define ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED		0x0F
> +#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED				0x10
> +#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES				0x11
> +#define ARMV8_PMUV3_PERFCTR_BR_PRED				0x12
> +#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS				0x13
> +#define ARMV8_PMUV3_PERFCTR_L1I_CACHE				0x14
> +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB			0x15
> +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE				0x16
> +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL			0x17
> +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB			0x18
> +#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS				0x19
> +#define ARMV8_PMUV3_PERFCTR_MEMORY_ERROR			0x1A
> +#define ARMV8_PMUV3_PERFCTR_INST_SPEC				0x1B
> +#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED			0x1C
> +#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES				0x1D
> +#define ARMV8_PMUV3_PERFCTR_CHAIN				0x1E
> +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE			0x1F
> +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE			0x20
> +#define ARMV8_PMUV3_PERFCTR_BR_RETIRED				0x21
> +#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED			0x22
> +#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND			0x23
> +#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND			0x24
> +#define ARMV8_PMUV3_PERFCTR_L1D_TLB				0x25
> +#define ARMV8_PMUV3_PERFCTR_L1I_TLB				0x26
> +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE				0x27
> +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL			0x28
> +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE			0x29
> +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL			0x2A
> +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE				0x2B
> +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB			0x2C
> +#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL			0x2D
> +#define ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL			0x2E
> +#define ARMV8_PMUV3_PERFCTR_L2D_TLB				0x2F
> +#define ARMV8_PMUV3_PERFCTR_L2I_TLB				0x30
> +#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS			0x31
> +#define ARMV8_PMUV3_PERFCTR_LL_CACHE				0x32
> +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS			0x33
> +#define ARMV8_PMUV3_PERFCTR_DTLB_WALK				0x34
> +#define ARMV8_PMUV3_PERFCTR_ITLB_WALK				0x35
> +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_RD				0x36
> +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD			0x37
> +#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD			0x38
> +
> +/* Statistical profiling extension microarchitectural events */
> +#define	ARMV8_SPE_PERFCTR_SAMPLE_POP				0x4000
> +#define	ARMV8_SPE_PERFCTR_SAMPLE_FEED				0x4000
> +#define	ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE			0x4000
> +#define	ARMV8_SPE_PERFCTR_SAMPLE_COLLISION			0x4000

This appears to be a mistake of copy-paste. The numbers must be

+#define	ARMV8_SPE_PERFCTR_SAMPLE_POP			0x4000
+#define	ARMV8_SPE_PERFCTR_SAMPLE_FEED			0x4001
+#define	ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE		0x4002
+#define	ARMV8_SPE_PERFCTR_SAMPLE_COLLISION		0x4003

Otherwise looks good to me.

Suzuki

[PATCH 5/6] arm64: perf: Move event definitions into perf_event.h

[Will Deacon]

On Wed, Oct 10, 2018 at 06:27:04PM +0100, Suzuki K Poulose wrote:
> On 10/10/18 17:31, Will Deacon wrote:
> >+/* Statistical profiling extension microarchitectural events */
> >+#define	ARMV8_SPE_PERFCTR_SAMPLE_POP				0x4000
> >+#define	ARMV8_SPE_PERFCTR_SAMPLE_FEED				0x4000
> >+#define	ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE			0x4000
> >+#define	ARMV8_SPE_PERFCTR_SAMPLE_COLLISION			0x4000
> 
> This appears to be a mistake of copy-paste. The numbers must be
> 
> +#define	ARMV8_SPE_PERFCTR_SAMPLE_POP			0x4000
> +#define	ARMV8_SPE_PERFCTR_SAMPLE_FEED			0x4001
> +#define	ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE		0x4002
> +#define	ARMV8_SPE_PERFCTR_SAMPLE_COLLISION		0x4003
> 
> Otherwise looks good to me.

Duh. Thanks.

Will

[PATCH 6/6] arm64: perf: Hook up new events

[Will Deacon]

There have been some additional events added to the PMU architecture
since Armv8.0, so expose them via our sysfs infrastructure.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/perf_event.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index a6e17622bad3..95d40cde3621 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -221,6 +221,18 @@ ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL);
 ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL);
 ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB);
 ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB);
+ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS);
+ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE);
+ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS);
+ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK);
+ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK);
+ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD);
+ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD);
+ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD);
+ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP);
+ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED);
+ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE);
+ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION);
 
 static struct attribute *armv8_pmuv3_event_attrs[] = {
 	&armv8_event_attr_sw_incr.attr.attr,
@@ -271,6 +283,18 @@ static struct attribute *armv8_pmuv3_event_attrs[] = {
 	&armv8_event_attr_l2i_tlb_refill.attr.attr,
 	&armv8_event_attr_l2d_tlb.attr.attr,
 	&armv8_event_attr_l2i_tlb.attr.attr,
+	&armv8_event_attr_remote_access.attr.attr,
+	&armv8_event_attr_ll_cache.attr.attr,
+	&armv8_event_attr_ll_cache_miss.attr.attr,
+	&armv8_event_attr_dtlb_walk.attr.attr,
+	&armv8_event_attr_itlb_walk.attr.attr,
+	&armv8_event_attr_ll_cache_rd.attr.attr,
+	&armv8_event_attr_ll_cache_miss_rd.attr.attr,
+	&armv8_event_attr_remote_access_rd.attr.attr,
+	&armv8_event_attr_sample_pop.attr.attr,
+	&armv8_event_attr_sample_feed.attr.attr,
+	&armv8_event_attr_sample_filtrate.attr.attr,
+	&armv8_event_attr_sample_collision.attr.attr,
 	NULL,
 };
 
-- 
2.1.4