Merge branch 'will/for-next/perf' into for-next/core

* will/for-next/perf:
  arm64: pmuv3: use arm_pmu ACPI framework
  arm64: pmuv3: handle !PMUv3 when probing
  drivers/perf: arm_pmu: add ACPI framework
  arm64: add function to get a cpu's MADT GICC table
  drivers/perf: arm_pmu: split out platform device probe logic
  drivers/perf: arm_pmu: move irq request/free into probe
  drivers/perf: arm_pmu: split cpu-local irq request/free
  drivers/perf: arm_pmu: rename irq request/free functions
  drivers/perf: arm_pmu: handle no platform_device
  drivers/perf: arm_pmu: simplify cpu_pmu_request_irqs()
  drivers/perf: arm_pmu: factor out pmu registration
  drivers/perf: arm_pmu: fold init into alloc
  drivers/perf: arm_pmu: define armpmu_init_fn
  drivers/perf: arm_pmu: remove pointless PMU disabling
  perf: qcom: Add L3 cache PMU driver
  drivers/perf: arm_pmu: split irq request from enable
  drivers/perf: arm_pmu: manage interrupts per-cpu
  drivers/perf: arm_pmu: rework per-cpu allocation
  MAINTAINERS: Add file patterns for perf device tree bindings

Documentation/perf/qcom_l3_pmu.txt

@@ -0,0 +1,25 @@
+Qualcomm Datacenter Technologies L3 Cache Performance Monitoring Unit (PMU)
+===========================================================================
+
+This driver supports the L3 cache PMUs found in Qualcomm Datacenter Technologies
+Centriq SoCs. The L3 cache on these SOCs is composed of multiple slices, shared
+by all cores within a socket. Each slice is exposed as a separate uncore perf
+PMU with device name l3cache_<socket>_<instance>. User space is responsible
+for aggregating across slices.
+
+The driver provides a description of its available events and configuration
+options in sysfs, see /sys/devices/l3cache*. Given that these are uncore PMUs
+the driver also exposes a "cpumask" sysfs attribute which contains a mask
+consisting of one CPU per socket which will be used to handle all the PMU
+events on that socket.
+
+The hardware implements 32bit event counters and has a flat 8bit event space
+exposed via the "event" format attribute. In addition to the 32bit physical
+counters the driver supports virtual 64bit hardware counters by using hardware
+counter chaining. This feature is exposed via the "lc" (long counter) format
+flag. E.g.:
+
+  perf stat -e l3cache_0_0/read-miss,lc/
+
+Given that these are uncore PMUs the driver does not support sampling, therefore
+"perf record" will not work. Per-task perf sessions are not supported.

MAINTAINERS

@@ -976,6 +976,7 @@ F:	arch/arm*/include/asm/perf_event.h
 F:	drivers/perf/*
 F:	include/linux/perf/arm_pmu.h
 F:	Documentation/devicetree/bindings/arm/pmu.txt
+F:	Documentation/devicetree/bindings/perf/
 
 ARM PORT
 M:	Russell King <linux@armlinux.org.uk>

arch/arm64/include/asm/acpi.h

@@ -85,6 +85,8 @@ static inline bool acpi_has_cpu_in_madt(void)
 	return true;
 }
 
+struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu);
+
 static inline void arch_fix_phys_package_id(int num, u32 slot) { }
 void __init acpi_init_cpus(void);
 

arch/arm64/kernel/perf_event.c

@@ -957,11 +957,26 @@ static int armv8_vulcan_map_event(struct perf_event *event)
 				ARMV8_PMU_EVTYPE_EVENT);
 }
 
+struct armv8pmu_probe_info {
+	struct arm_pmu *pmu;
+	bool present;
+};
+
 static void __armv8pmu_probe_pmu(void *info)
 {
-	struct arm_pmu *cpu_pmu = info;
+	struct armv8pmu_probe_info *probe = info;
+	struct arm_pmu *cpu_pmu = probe->pmu;
+	u64 dfr0, pmuver;
 	u32 pmceid[2];
 
+	dfr0 = read_sysreg(id_aa64dfr0_el1);
+	pmuver = cpuid_feature_extract_unsigned_field(dfr0,
+			ID_AA64DFR0_PMUVER_SHIFT);
+	if (pmuver != 1)
+		return;
+
+	probe->present = true;
+
 	/* Read the nb of CNTx counters supported from PMNC */
 	cpu_pmu->num_events = (armv8pmu_pmcr_read() >> ARMV8_PMU_PMCR_N_SHIFT)
 		& ARMV8_PMU_PMCR_N_MASK;
@@ -979,13 +994,27 @@ static void __armv8pmu_probe_pmu(void *info)
 
 static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
 {
-	return smp_call_function_any(&cpu_pmu->supported_cpus,
+	struct armv8pmu_probe_info probe = {
+		.pmu = cpu_pmu,
+		.present = false,
+	};
+	int ret;
+
+	ret = smp_call_function_any(&cpu_pmu->supported_cpus,
 				    __armv8pmu_probe_pmu,
-				    cpu_pmu, 1);
+				    &probe, 1);
+	if (ret)
+		return ret;
+
+	return probe.present ? 0 : -ENODEV;
 }
 
-static void armv8_pmu_init(struct arm_pmu *cpu_pmu)
+static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
 {
+	int ret = armv8pmu_probe_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,
@@ -997,78 +1026,104 @@ 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;
+
+	return 0;
 }
 
 static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu)
 {
-	armv8_pmu_init(cpu_pmu);
+	int ret = armv8_pmu_init(cpu_pmu);
+	if (ret)
+		return ret;
+
 	cpu_pmu->name			= "armv8_pmuv3";
 	cpu_pmu->map_event		= armv8_pmuv3_map_event;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
 		&armv8_pmuv3_events_attr_group;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
 		&armv8_pmuv3_format_attr_group;
-	return armv8pmu_probe_pmu(cpu_pmu);
+
+	return 0;
 }
 
 static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	armv8_pmu_init(cpu_pmu);
+	int ret = armv8_pmu_init(cpu_pmu);
+	if (ret)
+		return ret;
+
 	cpu_pmu->name			= "armv8_cortex_a53";
 	cpu_pmu->map_event		= armv8_a53_map_event;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
 		&armv8_pmuv3_events_attr_group;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
 		&armv8_pmuv3_format_attr_group;
-	return armv8pmu_probe_pmu(cpu_pmu);
+
+	return 0;
 }
 
 static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	armv8_pmu_init(cpu_pmu);
+	int ret = armv8_pmu_init(cpu_pmu);
+	if (ret)
+		return ret;
+
 	cpu_pmu->name			= "armv8_cortex_a57";
 	cpu_pmu->map_event		= armv8_a57_map_event;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
 		&armv8_pmuv3_events_attr_group;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
 		&armv8_pmuv3_format_attr_group;
-	return armv8pmu_probe_pmu(cpu_pmu);
+
+	return 0;
 }
 
 static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	armv8_pmu_init(cpu_pmu);
+	int ret = armv8_pmu_init(cpu_pmu);
+	if (ret)
+		return ret;
+
 	cpu_pmu->name			= "armv8_cortex_a72";
 	cpu_pmu->map_event		= armv8_a57_map_event;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
 		&armv8_pmuv3_events_attr_group;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
 		&armv8_pmuv3_format_attr_group;
-	return armv8pmu_probe_pmu(cpu_pmu);
+
+	return 0;
 }
 
 static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	armv8_pmu_init(cpu_pmu);
+	int ret = armv8_pmu_init(cpu_pmu);
+	if (ret)
+		return ret;
+
 	cpu_pmu->name			= "armv8_cavium_thunder";
 	cpu_pmu->map_event		= armv8_thunder_map_event;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
 		&armv8_pmuv3_events_attr_group;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
 		&armv8_pmuv3_format_attr_group;
-	return armv8pmu_probe_pmu(cpu_pmu);
+
+	return 0;
 }
 
 static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	armv8_pmu_init(cpu_pmu);
+	int ret = armv8_pmu_init(cpu_pmu);
+	if (ret)
+		return ret;
+
 	cpu_pmu->name			= "armv8_brcm_vulcan";
 	cpu_pmu->map_event		= armv8_vulcan_map_event;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
 		&armv8_pmuv3_events_attr_group;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
 		&armv8_pmuv3_format_attr_group;
-	return armv8pmu_probe_pmu(cpu_pmu);
+
+	return 0;
 }
 
 static const struct of_device_id armv8_pmu_of_device_ids[] = {
@@ -1081,24 +1136,9 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = {
 	{},
 };
 
-/*
- * Non DT systems have their micro/arch events probed at run-time.
- * A fairly complete list of generic events are provided and ones that
- * aren't supported by the current PMU are disabled.
- */
-static const struct pmu_probe_info armv8_pmu_probe_table[] = {
-	PMU_PROBE(0, 0, armv8_pmuv3_init), /* enable all defined counters */
-	{ /* sentinel value */ }
-};
-
 static int armv8_pmu_device_probe(struct platform_device *pdev)
 {
-	if (acpi_disabled)
-		return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids,
-					    NULL);
-
-	return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids,
-				    armv8_pmu_probe_table);
+	return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, NULL);
 }
 
 static struct platform_driver armv8_pmu_driver = {
@@ -1109,4 +1149,11 @@ static struct platform_driver armv8_pmu_driver = {
 	.probe		= armv8_pmu_device_probe,
 };
 
-builtin_platform_driver(armv8_pmu_driver);
+static int __init armv8_pmu_driver_init(void)
+{
+	if (acpi_disabled)
+		return platform_driver_register(&armv8_pmu_driver);
+	else
+		return arm_pmu_acpi_probe(armv8_pmuv3_init);
+}
+device_initcall(armv8_pmu_driver_init)

arch/arm64/kernel/smp.c

@@ -521,6 +521,13 @@ static bool bootcpu_valid __initdata;
 static unsigned int cpu_count = 1;
 
 #ifdef CONFIG_ACPI
+static struct acpi_madt_generic_interrupt cpu_madt_gicc[NR_CPUS];
+
+struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu)
+{
+	return &cpu_madt_gicc[cpu];
+}
+
 /*
  * acpi_map_gic_cpu_interface - parse processor MADT entry
  *
@@ -555,6 +562,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 			return;
 		}
 		bootcpu_valid = true;
+		cpu_madt_gicc[0] = *processor;
 		early_map_cpu_to_node(0, acpi_numa_get_nid(0, hwid));
 		return;
 	}
@@ -565,6 +573,8 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 	/* map the logical cpu id to cpu MPIDR */
 	cpu_logical_map(cpu_count) = hwid;
 
+	cpu_madt_gicc[cpu_count] = *processor;
+
 	/*
 	 * Set-up the ACPI parking protocol cpu entries
 	 * while initializing the cpu_logical_map to

drivers/perf/Kconfig

@@ -12,6 +12,10 @@ config ARM_PMU
 	  Say y if you want to use CPU performance monitors on ARM-based
 	  systems.
 
+config ARM_PMU_ACPI
+	depends on ARM_PMU && ACPI
+	def_bool y
+
 config QCOM_L2_PMU
 	bool "Qualcomm Technologies L2-cache PMU"
 	depends on ARCH_QCOM && ARM64 && PERF_EVENTS && ACPI
@@ -21,6 +25,16 @@ config QCOM_L2_PMU
 	  Adds the L2 cache PMU into the perf events subsystem for
 	  monitoring L2 cache events.
 
+config QCOM_L3_PMU
+	bool "Qualcomm Technologies L3-cache PMU"
+	depends on ARCH_QCOM && ARM64 && PERF_EVENTS && ACPI
+	select QCOM_IRQ_COMBINER
+	help
+	   Provides support for the L3 cache performance monitor unit (PMU)
+	   in Qualcomm Technologies processors.
+	   Adds the L3 cache PMU into the perf events subsystem for
+	   monitoring L3 cache events.
+
 config XGENE_PMU
         depends on PERF_EVENTS && ARCH_XGENE
         bool "APM X-Gene SoC PMU"

drivers/perf/Makefile

@@ -1,3 +1,5 @@
-obj-$(CONFIG_ARM_PMU) += arm_pmu.o
+obj-$(CONFIG_ARM_PMU) += arm_pmu.o arm_pmu_platform.o
+obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o
 obj-$(CONFIG_QCOM_L2_PMU)	+= qcom_l2_pmu.o
+obj-$(CONFIG_QCOM_L3_PMU) += qcom_l3_pmu.o
 obj-$(CONFIG_XGENE_PMU) += xgene_pmu.o