[PATCH 0/3] ARM: perf: updates for 3.15

[PATCH 0/3] ARM: perf: updates for 3.15

[Will Deacon]

Hello,

Here is a handful of ARM perf patches that I plan to push for 3.15 that
I don't think have previously been on the list. I've also got Stephen
Boyd's series adding support for Krait, but they've already been reviewed
here.

Cheers,

Will

--->8

Albin Tonnerre (1):
  ARM: perf: add support for the Cortex-A12 PMU

Mark Rutland (1):
  ARM: perf: remove unused PMU probing code

Will Deacon (1):
  ARM: perf: hook up perf_sample_event_took around pmu irq handling

 Documentation/devicetree/bindings/arm/pmu.txt |   1 +
 arch/arm/kernel/perf_event.c                  |  11 +-
 arch/arm/kernel/perf_event_cpu.c              |  10 +-
 arch/arm/kernel/perf_event_v7.c               | 158 ++++++++++++++++++++++++++
 4 files changed, 169 insertions(+), 11 deletions(-)

-- 
1.8.2.2

[PATCH 1/3] ARM: perf: hook up perf_sample_event_took around pmu irq handling

[Will Deacon]

Since we indirect all of our PMU IRQ handling through a dispatcher, it's
trivial to hook up perf_sample_event_took to prevent applications such
as oprofile from generating interrupt storms due to an unrealisticly
low sample period.

Reported-by: Robert Richter <rric@kernel.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm/kernel/perf_event.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 361a1aaee7c8..a6bc431cde70 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -302,6 +302,8 @@ static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
 	struct arm_pmu *armpmu;
 	struct platform_device *plat_device;
 	struct arm_pmu_platdata *plat;
+	int ret;
+	u64 start_clock, finish_clock;
 
 	if (irq_is_percpu(irq))
 		dev = *(void **)dev;
@@ -309,10 +311,15 @@ static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
 	plat_device = armpmu->plat_device;
 	plat = dev_get_platdata(&plat_device->dev);
 
+	start_clock = sched_clock();
 	if (plat && plat->handle_irq)
-		return plat->handle_irq(irq, dev, armpmu->handle_irq);
+		ret = plat->handle_irq(irq, dev, armpmu->handle_irq);
 	else
-		return armpmu->handle_irq(irq, dev);
+		ret = armpmu->handle_irq(irq, dev);
+	finish_clock = sched_clock();
+
+	perf_sample_event_took(finish_clock - start_clock);
+	return ret;
 }
 
 static void
-- 
1.8.2.2

[PATCH 2/3] ARM: perf: remove unused PMU probing code

[Will Deacon]

From: Mark Rutland <mark.rutland@arm.com>

The ARM perf backend can discover the type of PMU it needs to drive
either from DT or by probing a CPU it is running on. For
Cortex-A{5,7,15} there are no platforms in mainline not using dt, and
this probing won't work well for big.LITTLE systems with heterogeneous
PMUs.

This patch drops the probing for those CPUs, relying on information from
dt instead. Future platforms should describe their PMU(s) with dt.

Suggested-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm/kernel/perf_event_cpu.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index ed571d386c0b..326cb58de2f8 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -267,15 +267,6 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 		case ARM_CPU_PART_CORTEX_A9:
 			ret = armv7_a9_pmu_init(pmu);
 			break;
-		case ARM_CPU_PART_CORTEX_A5:
-			ret = armv7_a5_pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_CORTEX_A15:
-			ret = armv7_a15_pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_CORTEX_A7:
-			ret = armv7_a7_pmu_init(pmu);
-			break;
 		}
 	/* Intel CPUs [xscale]. */
 	} else if (implementor == ARM_CPU_IMP_INTEL) {
-- 
1.8.2.2

[PATCH 3/3] ARM: perf: add support for the Cortex-A12 PMU

[Will Deacon]

From: Albin Tonnerre <albin.tonnerre@arm.com>

Cortex-A12 implements Performance Monitors compliant with the PMUv2
architecture.

This patch adds support for the Cortex-A12 PMU to the ARM perf backend.

Signed-off-by: Albin Tonnerre <albin.tonnerre@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 Documentation/devicetree/bindings/arm/pmu.txt |   1 +
 arch/arm/kernel/perf_event_cpu.c              |   1 +
 arch/arm/kernel/perf_event_v7.c               | 158 ++++++++++++++++++++++++++
 3 files changed, 160 insertions(+)

diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt
index ce731441e64f..fe5cef8976cb 100644
--- a/Documentation/devicetree/bindings/arm/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/pmu.txt
@@ -9,6 +9,7 @@ Required properties:
 - compatible : should be one of
 	"arm,armv8-pmuv3"
 	"arm,cortex-a15-pmu"
+	"arm,cortex-a12-pmu"
 	"arm,cortex-a9-pmu"
 	"arm,cortex-a8-pmu"
 	"arm,cortex-a7-pmu"
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 326cb58de2f8..51798d7854ac 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -222,6 +222,7 @@ static struct notifier_block cpu_pmu_hotplug_notifier = {
  */
 static struct of_device_id cpu_pmu_of_device_ids[] = {
 	{.compatible = "arm,cortex-a15-pmu",	.data = armv7_a15_pmu_init},
+	{.compatible = "arm,cortex-a12-pmu",	.data = armv7_a12_pmu_init},
 	{.compatible = "arm,cortex-a9-pmu",	.data = armv7_a9_pmu_init},
 	{.compatible = "arm,cortex-a8-pmu",	.data = armv7_a8_pmu_init},
 	{.compatible = "arm,cortex-a7-pmu",	.data = armv7_a7_pmu_init},
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 2fce4751f4c0..f4ef3981ed02 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -113,6 +113,19 @@ enum armv7_a15_perf_types {
 	ARMV7_A15_PERFCTR_PC_WRITE_SPEC			= 0x76,
 };
 
+/* ARMv7 Cortex-A12 specific event types */
+enum armv7_a12_perf_types {
+	ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ		= 0x40,
+	ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE	= 0x41,
+
+	ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ		= 0x50,
+	ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE		= 0x51,
+
+	ARMV7_A12_PERFCTR_PC_WRITE_SPEC			= 0x76,
+
+	ARMV7_A12_PERFCTR_PF_TLB_REFILL			= 0xe7,
+};
+
 /* ARMv7 Krait specific event types */
 enum krait_perf_types {
 	KRAIT_PMRESR0_GROUP0				= 0xcc,
@@ -750,6 +763,130 @@ static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 };
 
 /*
+ * Cortex-A12 HW events mapping
+ */
+static const unsigned armv7_a12_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_A12_PERFCTR_PC_WRITE_SPEC,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv7_a12_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					[PERF_COUNT_HW_CACHE_OP_MAX]
+					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		/*
+		 * Not all performance counters differentiate between read
+		 * and write accesses/misses so we're not always strictly
+		 * correct, but it's the best we can do. Writes and reads get
+		 * combined in these cases.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_A12_PERFCTR_PF_TLB_REFILL,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(NODE)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+/*
  * Krait HW events mapping
  */
 static const unsigned krait_perf_map[PERF_COUNT_HW_MAX] = {
@@ -1362,6 +1499,12 @@ static int armv7_a7_map_event(struct perf_event *event)
 				&armv7_a7_perf_cache_map, 0xFF);
 }
 
+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);
+}
+
 static int krait_map_event(struct perf_event *event)
 {
 	return armpmu_map_event(event, &krait_perf_map,
@@ -1446,6 +1589,16 @@ static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 	return 0;
 }
 
+static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv7pmu_init(cpu_pmu);
+	cpu_pmu->name		= "ARMv7 Cortex-A12";
+	cpu_pmu->map_event	= armv7_a12_map_event;
+	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
+	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
+	return 0;
+}
+
 /*
  * Krait Performance Monitor Region Event Selection Register (PMRESRn)
  *
@@ -1863,6 +2016,11 @@ static inline int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 	return -ENODEV;
 }
 
+static inline int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return -ENODEV;
+}
+
 static inline int krait_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	return -ENODEV;
-- 
1.8.2.2