[PATCH v2 5/5] arm64/perf: Extend event mask for ARMv8.1

From: Jan Glauber
Date: Fri Jan 29 2016 - 03:30:01 EST

Next message: Oleksij Rempel: "[PATCH] irqchip: mxs: add missing set_handle_irq()"
Previous message: Ingo Molnar: "Re: [PATCH 1/2] x86/lib/copy_user_64.S: Handle 4-byte uncached copy"
In reply to: Jan Glauber: "Re: [PATCH v2 5/5] arm64/perf: Extend event mask for ARMv8.1"
Next in thread: David Daney: "Re: [PATCH v2 5/5] arm64/perf: Extend event mask for ARMv8.1"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

ARMv8.1 increases the PMU event number space. Detect the
presence of this PMUv3 type and extend the event mask.

The event mask is moved to struct arm_pmu so different event masks
can exist, depending on the PMU type.

Signed-off-by: Jan Glauber <jglauber@xxxxxxxxxx>
---
arch/arm/kernel/perf_event_v6.c | 6 ++++--
arch/arm/kernel/perf_event_v7.c | 29 +++++++++++++++++++----------
arch/arm/kernel/perf_event_xscale.c | 4 +++-
arch/arm64/kernel/perf_event.c | 33 +++++++++++++++++++--------------
drivers/perf/arm_pmu.c | 5 +++--
include/linux/perf/arm_pmu.h | 4 ++--
6 files changed, 50 insertions(+), 31 deletions(-)

diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index 09413e7..d6769f5 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -481,7 +481,7 @@ static void armv6mpcore_pmu_disable_event(struct perf_event *event)
static int armv6_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &armv6_perf_map,
- &armv6_perf_cache_map, 0xFF);
+ &armv6_perf_cache_map);
}

static void armv6pmu_init(struct arm_pmu *cpu_pmu)
@@ -494,6 +494,7 @@ static void armv6pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->get_event_idx = armv6pmu_get_event_idx;
cpu_pmu->start = armv6pmu_start;
cpu_pmu->stop = armv6pmu_stop;
+ cpu_pmu->event_mask = 0xFF;
cpu_pmu->map_event = armv6_map_event;
cpu_pmu->num_events = 3;
cpu_pmu->max_period = (1LLU << 32) - 1;
@@ -531,7 +532,7 @@ static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu)
static int armv6mpcore_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &armv6mpcore_perf_map,
- &armv6mpcore_perf_cache_map, 0xFF);
+ &armv6mpcore_perf_cache_map);
}

static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
@@ -545,6 +546,7 @@ static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->get_event_idx = armv6pmu_get_event_idx;
cpu_pmu->start = armv6pmu_start;
cpu_pmu->stop = armv6pmu_stop;
+ cpu_pmu->event_mask = 0xFF;
cpu_pmu->map_event = armv6mpcore_map_event;
cpu_pmu->num_events = 3;
cpu_pmu->max_period = (1LLU << 32) - 1;
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 4152158..8aab098 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -1042,7 +1042,7 @@ static int armv7pmu_get_event_idx(struct pmu_hw_events *cpuc,
int idx;
struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
struct hw_perf_event *hwc = &event->hw;
- unsigned long evtype = hwc->config_base & ARMV7_EVTYPE_EVENT;
+ unsigned long evtype = hwc->config_base & cpu_pmu->event_mask;

/* Always place a cycle counter into the cycle counter. */
if (evtype == ARMV7_PERFCTR_CPU_CYCLES) {
@@ -1109,55 +1109,55 @@ static void armv7pmu_reset(void *info)
static int armv7_a8_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &armv7_a8_perf_map,
- &armv7_a8_perf_cache_map, 0xFF);
+ &armv7_a8_perf_cache_map);
}

static int armv7_a9_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &armv7_a9_perf_map,
- &armv7_a9_perf_cache_map, 0xFF);
+ &armv7_a9_perf_cache_map);
}

static int armv7_a5_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &armv7_a5_perf_map,
- &armv7_a5_perf_cache_map, 0xFF);
+ &armv7_a5_perf_cache_map);
}

static int armv7_a15_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &armv7_a15_perf_map,
- &armv7_a15_perf_cache_map, 0xFF);
+ &armv7_a15_perf_cache_map);
}

static int armv7_a7_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &armv7_a7_perf_map,
- &armv7_a7_perf_cache_map, 0xFF);
+ &armv7_a7_perf_cache_map);
}

static int armv7_a12_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &armv7_a12_perf_map,
- &armv7_a12_perf_cache_map, 0xFF);
+ &armv7_a12_perf_cache_map);
}

static int krait_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &krait_perf_map,
- &krait_perf_cache_map, 0xFFFFF);
+ &krait_perf_cache_map);
}

static int krait_map_event_no_branch(struct perf_event *event)
{
return armpmu_map_event(event, &krait_perf_map_no_branch,
- &krait_perf_cache_map, 0xFFFFF);
+ &krait_perf_cache_map);
}

static int scorpion_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &scorpion_perf_map,
- &scorpion_perf_cache_map, 0xFFFFF);
+ &scorpion_perf_cache_map);
}

static void armv7pmu_init(struct arm_pmu *cpu_pmu)
@@ -1196,6 +1196,7 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a8";
+ cpu_pmu->event_mask = ARMV7_EVTYPE_EVENT;
cpu_pmu->map_event = armv7_a8_map_event;
cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
return armv7_probe_num_events(cpu_pmu);
@@ -1205,6 +1206,7 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a9";
+ cpu_pmu->event_mask = ARMV7_EVTYPE_EVENT;
cpu_pmu->map_event = armv7_a9_map_event;
cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
return armv7_probe_num_events(cpu_pmu);
@@ -1214,6 +1216,7 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a5";
+ cpu_pmu->event_mask = ARMV7_EVTYPE_EVENT;
cpu_pmu->map_event = armv7_a5_map_event;
cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
return armv7_probe_num_events(cpu_pmu);
@@ -1223,6 +1226,7 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a15";
+ cpu_pmu->event_mask = ARMV7_EVTYPE_EVENT;
cpu_pmu->map_event = armv7_a15_map_event;
cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
@@ -1233,6 +1237,7 @@ static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a7";
+ cpu_pmu->event_mask = ARMV7_EVTYPE_EVENT;
cpu_pmu->map_event = armv7_a7_map_event;
cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
@@ -1243,6 +1248,7 @@ static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a12";
+ cpu_pmu->event_mask = ARMV7_EVTYPE_EVENT;
cpu_pmu->map_event = armv7_a12_map_event;
cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
@@ -1628,6 +1634,7 @@ static int krait_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_krait";
+ cpu_pmu->event_mask = 0xFFFFF;
/* Some early versions of Krait don't support PC write events */
if (of_property_read_bool(cpu_pmu->plat_device->dev.of_node,
"qcom,no-pc-write"))
@@ -1957,6 +1964,7 @@ static int scorpion_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_scorpion";
+ cpu_pmu->event_mask = 0xFFFFF;
cpu_pmu->map_event = scorpion_map_event;
cpu_pmu->reset = scorpion_pmu_reset;
cpu_pmu->enable = scorpion_pmu_enable_event;
@@ -1970,6 +1978,7 @@ static int scorpion_mp_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_scorpion_mp";
+ cpu_pmu->event_mask = 0xFFFFF;
cpu_pmu->map_event = scorpion_map_event;
cpu_pmu->reset = scorpion_pmu_reset;
cpu_pmu->enable = scorpion_pmu_enable_event;
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index aa0499e..8708691 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -358,7 +358,7 @@ static inline void xscale1pmu_write_counter(struct perf_event *event, u32 val)
static int xscale_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &xscale_perf_map,
- &xscale_perf_cache_map, 0xFF);
+ &xscale_perf_cache_map);
}

static int xscale1pmu_init(struct arm_pmu *cpu_pmu)
@@ -372,6 +372,7 @@ static int xscale1pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->get_event_idx = xscale1pmu_get_event_idx;
cpu_pmu->start = xscale1pmu_start;
cpu_pmu->stop = xscale1pmu_stop;
+ cpu_pmu->event_mask = 0xFF;
cpu_pmu->map_event = xscale_map_event;
cpu_pmu->num_events = 3;
cpu_pmu->max_period = (1LLU << 32) - 1;
@@ -742,6 +743,7 @@ static int xscale2pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->get_event_idx = xscale2pmu_get_event_idx;
cpu_pmu->start = xscale2pmu_start;
cpu_pmu->stop = xscale2pmu_stop;
+ cpu_pmu->event_mask = 0xFF;
cpu_pmu->map_event = xscale_map_event;
cpu_pmu->num_events = 5;
cpu_pmu->max_period = (1LLU << 32) - 1;
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 5e4275e..78b24cb 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -419,7 +419,7 @@ static const struct attribute_group *armv8_pmuv3_attr_groups[] = {
/*
* PMXEVTYPER: Event selection reg
*/
-#define ARMV8_EVTYPE_MASK 0xc80003ff /* Mask for writable bits */
+#define ARMV8_EVTYPE_FLT_MASK 0xc8000000 /* Writable filter bits */
#define ARMV8_EVTYPE_EVENT 0x3ff /* Mask for EVENT bits */

/*
@@ -510,10 +510,8 @@ static inline void armv8pmu_write_counter(struct perf_event *event, u32 value)

static inline void armv8pmu_write_evtype(int idx, u32 val)
{
- if (armv8pmu_select_counter(idx) == idx) {
- val &= ARMV8_EVTYPE_MASK;
+ if (armv8pmu_select_counter(idx) == idx)
asm volatile("msr pmxevtyper_el0, %0" :: "r" (val));
- }
}

static inline int armv8pmu_enable_counter(int idx)
@@ -570,6 +568,7 @@ static void armv8pmu_enable_event(struct perf_event *event)
struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
int idx = hwc->idx;
+ u32 val;

/*
* Enable counter and interrupt, and set the counter to count
@@ -585,7 +584,8 @@ static void armv8pmu_enable_event(struct perf_event *event)
/*
* Set event (if destined for PMNx counters).
*/
- armv8pmu_write_evtype(idx, hwc->config_base);
+ val = hwc->config_base & (ARMV8_EVTYPE_FLT_MASK | cpu_pmu->event_mask);
+ armv8pmu_write_evtype(idx, val);

/*
* Enable interrupt for this counter
@@ -716,7 +716,7 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
int idx;
struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
struct hw_perf_event *hwc = &event->hw;
- unsigned long evtype = hwc->config_base & ARMV8_EVTYPE_EVENT;
+ unsigned long evtype = hwc->config_base & cpu_pmu->event_mask;

/* Always place a cycle counter into the cycle counter. */
if (evtype == ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES) {
@@ -786,29 +786,25 @@ static void armv8pmu_reset(void *info)
static int armv8_pmuv3_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &armv8_pmuv3_perf_map,
- &armv8_pmuv3_perf_cache_map,
- ARMV8_EVTYPE_EVENT);
+ &armv8_pmuv3_perf_cache_map);
}

static int armv8_a53_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &armv8_a53_perf_map,
- &armv8_a53_perf_cache_map,
- ARMV8_EVTYPE_EVENT);
+ &armv8_a53_perf_cache_map);
}

static int armv8_a57_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &armv8_a57_perf_map,
- &armv8_a57_perf_cache_map,
- ARMV8_EVTYPE_EVENT);
+ &armv8_a57_perf_cache_map);
}

static int armv8_thunder_map_event(struct perf_event *event)
{
return armpmu_map_event(event, &armv8_thunder_perf_map,
- &armv8_thunder_perf_cache_map,
- ARMV8_EVTYPE_EVENT);
+ &armv8_thunder_perf_cache_map);
}

static void armv8pmu_read_num_pmnc_events(void *info)
@@ -831,6 +827,8 @@ static int armv8pmu_probe_num_events(struct arm_pmu *arm_pmu)

static void armv8_pmu_init(struct arm_pmu *cpu_pmu)
{
+ u64 id;
+
cpu_pmu->handle_irq = armv8pmu_handle_irq,
cpu_pmu->enable = armv8pmu_enable_event,
cpu_pmu->disable = armv8pmu_disable_event,
@@ -842,6 +840,13 @@ static void armv8_pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->reset = armv8pmu_reset,
cpu_pmu->max_period = (1LLU << 32) - 1,
cpu_pmu->set_event_filter = armv8pmu_set_event_filter;
+
+ /* detect ARMv8.1 PMUv3 with extended event mask */
+ id = read_cpuid(ID_AA64DFR0_EL1);
+ if (((id >> 8) & 0xf) == 4)
+ cpu_pmu->event_mask = 0xffff; /* ARMv8.1 extended events */
+ else
+ cpu_pmu->event_mask = ARMV8_EVTYPE_EVENT;
}

static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu)
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 166637f..79e681f 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -79,9 +79,10 @@ armpmu_map_event(struct perf_event *event,
const unsigned (*cache_map)
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX],
- u32 raw_event_mask)
+ [PERF_COUNT_HW_CACHE_RESULT_MAX])
{
+ struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+ u32 raw_event_mask = armpmu->event_mask;
u64 config = event->attr.config;
int type = event->attr.type;

diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 83b5e34..9a4c3a9 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -101,6 +101,7 @@ struct arm_pmu {
void (*free_irq)(struct arm_pmu *);
int (*map_event)(struct perf_event *event);
int num_events;
+ int event_mask;
atomic_t active_events;
struct mutex reserve_mutex;
u64 max_period;
@@ -119,8 +120,7 @@ int armpmu_map_event(struct perf_event *event,
const unsigned (*event_map)[PERF_COUNT_HW_MAX],
const unsigned (*cache_map)[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX],
- u32 raw_event_mask);
+ [PERF_COUNT_HW_CACHE_RESULT_MAX]);

struct pmu_probe_info {
unsigned int cpuid;
--
1.9.1

Next message: Oleksij Rempel: "[PATCH] irqchip: mxs: add missing set_handle_irq()"
Previous message: Ingo Molnar: "Re: [PATCH 1/2] x86/lib/copy_user_64.S: Handle 4-byte uncached copy"
In reply to: Jan Glauber: "Re: [PATCH v2 5/5] arm64/perf: Extend event mask for ARMv8.1"
Next in thread: David Daney: "Re: [PATCH v2 5/5] arm64/perf: Extend event mask for ARMv8.1"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]