Merge branch 'for-next/perf' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux

Support for the Cluster PMU part of the ARM DynamIQ Shared Unit (DSU).

* 'for-next/perf' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux:
  perf: ARM DynamIQ Shared Unit PMU support
  dt-bindings: Document devicetree binding for ARM DSU PMU
  arm_pmu: Use of_cpu_node_to_id helper
  arm64: Use of_cpu_node_to_id helper for CPU topology parsing
  irqchip: gic-v3: Use of_cpu_node_to_id helper
  coresight: of: Use of_cpu_node_to_id helper
  of: Add helper for mapping device node to logical CPU number
  perf: Export perf_event_update_userpage

Documentation/devicetree/bindings/arm/arm-dsu-pmu.txt

+* ARM DynamIQ Shared Unit (DSU) Performance Monitor Unit (PMU)
+
+ARM DyanmIQ Shared Unit (DSU) integrates one or more CPU cores
+with a shared L3 memory system, control logic and external interfaces to
+form a multicore cluster. The PMU enables to gather various statistics on
+the operations of the DSU. The PMU provides independent 32bit counters that
+can count any of the supported events, along with a 64bit cycle counter.
+The PMU is accessed via CPU system registers and has no MMIO component.
+
+** DSU PMU required properties:
+
+- compatible	: should be one of :
+
+		"arm,dsu-pmu"
+
+- interrupts	: Exactly 1 SPI must be listed.
+
+- cpus		: List of phandles for the CPUs connected to this DSU instance.
+
+
+** Example:
+
+dsu-pmu-0 {
+	compatible = "arm,dsu-pmu";
+	interrupts = <GIC_SPI 02 IRQ_TYPE_LEVEL_HIGH>;
+	cpus = <&cpu_0>, <&cpu_1>;
+};

Documentation/perf/arm_dsu_pmu.txt

+ARM DynamIQ Shared Unit (DSU) PMU
+==================================
+
+ARM DynamIQ Shared Unit integrates one or more cores with an L3 memory system,
+control logic and external interfaces to form a multicore cluster. The PMU
+allows counting the various events related to the L3 cache, Snoop Control Unit
+etc, using 32bit independent counters. It also provides a 64bit cycle counter.
+
+The PMU can only be accessed via CPU system registers and are common to the
+cores connected to the same DSU. Like most of the other uncore PMUs, DSU
+PMU doesn't support process specific events and cannot be used in sampling mode.
+
+The DSU provides a bitmap for a subset of implemented events via hardware
+registers. There is no way for the driver to determine if the other events
+are available or not. Hence the driver exposes only those events advertised
+by the DSU, in "events" directory under :
+
+  /sys/bus/event_sources/devices/arm_dsu_<N>/
+
+The user should refer to the TRM of the product to figure out the supported events
+and use the raw event code for the unlisted events.
+
+The driver also exposes the CPUs connected to the DSU instance in "associated_cpus".
+
+
+e.g usage :
+
+	perf stat -a -e arm_dsu_0/cycles/

arch/arm64/include/asm/arm_dsu_pmu.h

+/*
+ * ARM DynamIQ Shared Unit (DSU) PMU Low level register access routines.
+ *
+ * Copyright (C) ARM Limited, 2017.
+ *
+ * Author: Suzuki K Poulose <suzuki.poulose@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2, as published by the Free Software Foundation.
+ */
+
+#include <linux/bitops.h>
+#include <linux/build_bug.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/barrier.h>
+#include <asm/sysreg.h>
+
+
+#define CLUSTERPMCR_EL1			sys_reg(3, 0, 15, 5, 0)
+#define CLUSTERPMCNTENSET_EL1		sys_reg(3, 0, 15, 5, 1)
+#define CLUSTERPMCNTENCLR_EL1		sys_reg(3, 0, 15, 5, 2)
+#define CLUSTERPMOVSSET_EL1		sys_reg(3, 0, 15, 5, 3)
+#define CLUSTERPMOVSCLR_EL1		sys_reg(3, 0, 15, 5, 4)
+#define CLUSTERPMSELR_EL1		sys_reg(3, 0, 15, 5, 5)
+#define CLUSTERPMINTENSET_EL1		sys_reg(3, 0, 15, 5, 6)
+#define CLUSTERPMINTENCLR_EL1		sys_reg(3, 0, 15, 5, 7)
+#define CLUSTERPMCCNTR_EL1		sys_reg(3, 0, 15, 6, 0)
+#define CLUSTERPMXEVTYPER_EL1		sys_reg(3, 0, 15, 6, 1)
+#define CLUSTERPMXEVCNTR_EL1		sys_reg(3, 0, 15, 6, 2)
+#define CLUSTERPMMDCR_EL1		sys_reg(3, 0, 15, 6, 3)
+#define CLUSTERPMCEID0_EL1		sys_reg(3, 0, 15, 6, 4)
+#define CLUSTERPMCEID1_EL1		sys_reg(3, 0, 15, 6, 5)
+
+static inline u32 __dsu_pmu_read_pmcr(void)
+{
+	return read_sysreg_s(CLUSTERPMCR_EL1);
+}
+
+static inline void __dsu_pmu_write_pmcr(u32 val)
+{
+	write_sysreg_s(val, CLUSTERPMCR_EL1);
+	isb();
+}
+
+static inline u32 __dsu_pmu_get_reset_overflow(void)
+{
+	u32 val = read_sysreg_s(CLUSTERPMOVSCLR_EL1);
+	/* Clear the bit */
+	write_sysreg_s(val, CLUSTERPMOVSCLR_EL1);
+	isb();
+	return val;
+}
+
+static inline void __dsu_pmu_select_counter(int counter)
+{
+	write_sysreg_s(counter, CLUSTERPMSELR_EL1);
+	isb();
+}
+
+static inline u64 __dsu_pmu_read_counter(int counter)
+{
+	__dsu_pmu_select_counter(counter);
+	return read_sysreg_s(CLUSTERPMXEVCNTR_EL1);
+}
+
+static inline void __dsu_pmu_write_counter(int counter, u64 val)
+{
+	__dsu_pmu_select_counter(counter);
+	write_sysreg_s(val, CLUSTERPMXEVCNTR_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_set_event(int counter, u32 event)
+{
+	__dsu_pmu_select_counter(counter);
+	write_sysreg_s(event, CLUSTERPMXEVTYPER_EL1);
+	isb();
+}
+
+static inline u64 __dsu_pmu_read_pmccntr(void)
+{
+	return read_sysreg_s(CLUSTERPMCCNTR_EL1);
+}
+
+static inline void __dsu_pmu_write_pmccntr(u64 val)
+{
+	write_sysreg_s(val, CLUSTERPMCCNTR_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_disable_counter(int counter)
+{
+	write_sysreg_s(BIT(counter), CLUSTERPMCNTENCLR_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_enable_counter(int counter)
+{
+	write_sysreg_s(BIT(counter), CLUSTERPMCNTENSET_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_counter_interrupt_enable(int counter)
+{
+	write_sysreg_s(BIT(counter), CLUSTERPMINTENSET_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_counter_interrupt_disable(int counter)
+{
+	write_sysreg_s(BIT(counter), CLUSTERPMINTENCLR_EL1);
+	isb();
+}
+
+
+static inline u32 __dsu_pmu_read_pmceid(int n)
+{
+	switch (n) {
+	case 0:
+		return read_sysreg_s(CLUSTERPMCEID0_EL1);
+	case 1:
+		return read_sysreg_s(CLUSTERPMCEID1_EL1);
+	default:
+		BUILD_BUG();
+		return 0;
+	}
+}

arch/arm64/kernel/topology.c

@@ -37,18 +37,14 @@ static int __init get_cpu_for_node(struct device_node *node)
 	if (!cpu_node)
 		return -1;
 
-	for_each_possible_cpu(cpu) {
-		if (of_get_cpu_node(cpu, NULL) == cpu_node) {
-			topology_parse_cpu_capacity(cpu_node, cpu);
-			of_node_put(cpu_node);
-			return cpu;
-		}
-	}
-
-	pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
+	cpu = of_cpu_node_to_id(cpu_node);
+	if (cpu >= 0)
+		topology_parse_cpu_capacity(cpu_node, cpu);
+	else
+		pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
 
 	of_node_put(cpu_node);
-	return -1;
+	return cpu;
 }
 
 static int __init parse_core(struct device_node *core, int cluster_id,

drivers/hwtracing/coresight/of_coresight.c

@@ -104,26 +104,17 @@ static int of_coresight_alloc_memory(struct device *dev,
 int of_coresight_get_cpu(const struct device_node *node)
 {
 	int cpu;
-	bool found;
-	struct device_node *dn, *np;
+	struct device_node *dn;
 
 	dn = of_parse_phandle(node, "cpu", 0);
-
 	/* Affinity defaults to CPU0 */
 	if (!dn)
 		return 0;
-
-	for_each_possible_cpu(cpu) {
-		np = of_cpu_device_node_get(cpu);
-		found = (dn == np);
-		of_node_put(np);
-		if (found)
-			break;
-	}
+	cpu = of_cpu_node_to_id(dn);
 	of_node_put(dn);
 
 	/* Affinity to CPU0 if no cpu nodes are found */
-	return found ? cpu : 0;
+	return (cpu < 0) ? 0 : cpu;
 }
 EXPORT_SYMBOL_GPL(of_coresight_get_cpu);
 

drivers/irqchip/irq-gic-v3.c

@@ -1070,31 +1070,6 @@ static int __init gic_validate_dist_version(void __iomem *dist_base)
 	return 0;
 }
 
-static int get_cpu_number(struct device_node *dn)
-{
-	const __be32 *cell;
-	u64 hwid;
-	int cpu;
-
-	cell = of_get_property(dn, "reg", NULL);
-	if (!cell)
-		return -1;
-
-	hwid = of_read_number(cell, of_n_addr_cells(dn));
-
-	/*
-	 * Non affinity bits must be set to 0 in the DT
-	 */
-	if (hwid & ~MPIDR_HWID_BITMASK)
-		return -1;
-
-	for_each_possible_cpu(cpu)
-		if (cpu_logical_map(cpu) == hwid)
-			return cpu;
-
-	return -1;
-}
-
 /* Create all possible partitions at boot time */
 static void __init gic_populate_ppi_partitions(struct device_node *gic_node)
 {
@@ -1145,8 +1120,8 @@ static void __init gic_populate_ppi_partitions(struct device_node *gic_node)
 			if (WARN_ON(!cpu_node))
 				continue;
 
-			cpu = get_cpu_number(cpu_node);
-			if (WARN_ON(cpu == -1))
+			cpu = of_cpu_node_to_id(cpu_node);
+			if (WARN_ON(cpu < 0))
 				continue;
 
 			pr_cont("%pOF[%d] ", cpu_node, cpu);

drivers/of/base.c

@@ -315,6 +315,32 @@ struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
 }
 EXPORT_SYMBOL(of_get_cpu_node);
 
+/**
+ * of_cpu_node_to_id: Get the logical CPU number for a given device_node
+ *
+ * @cpu_node: Pointer to the device_node for CPU.
+ *
+ * Returns the logical CPU number of the given CPU device_node.
+ * Returns -ENODEV if the CPU is not found.
+ */
+int of_cpu_node_to_id(struct device_node *cpu_node)
+{
+	int cpu;
+	bool found = false;
+	struct device_node *np;
+
+	for_each_possible_cpu(cpu) {
+		np = of_cpu_device_node_get(cpu);
+		found = (cpu_node == np);
+		of_node_put(np);
+		if (found)
+			return cpu;
+	}
+
+	return -ENODEV;
+}
+EXPORT_SYMBOL(of_cpu_node_to_id);
+
 /**
  * __of_device_is_compatible() - Check if the node matches given constraints
  * @device: pointer to node

drivers/perf/Kconfig

@@ -17,6 +17,15 @@ config ARM_PMU_ACPI
 	depends on ARM_PMU && ACPI
 	def_bool y
 
+config ARM_DSU_PMU
+	tristate "ARM DynamIQ Shared Unit (DSU) PMU"
+	depends on ARM64
+	  help
+	  Provides support for performance monitor unit in ARM DynamIQ Shared
+	  Unit (DSU). The DSU integrates one or more cores with an L3 memory
+	  system, control logic. The PMU allows counting various events related
+	  to DSU.
+
 config HISI_PMU
        bool "HiSilicon SoC PMU"
        depends on ARM64 && ACPI

drivers/perf/Makefile

 # SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_ARM_DSU_PMU) += arm_dsu_pmu.o
 obj-$(CONFIG_ARM_PMU) += arm_pmu.o arm_pmu_platform.o
 obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o
 obj-$(CONFIG_HISI_PMU) += hisilicon/

drivers/perf/arm_pmu_platform.c

@@ -82,19 +82,10 @@ static int pmu_parse_irq_affinity(struct device_node *node, int i)
 		return -EINVAL;
 	}
 
-	/* Now look up the logical CPU number */
-	for_each_possible_cpu(cpu) {
-		struct device_node *cpu_dn;
-
-		cpu_dn = of_cpu_device_node_get(cpu);
-		of_node_put(cpu_dn);
-
-		if (dn == cpu_dn)
-			break;
-	}
-
-	if (cpu >= nr_cpu_ids) {
+	cpu = of_cpu_node_to_id(dn);
+	if (cpu < 0) {
 		pr_warn("failed to find logical CPU for %s\n", dn->name);
+		cpu = nr_cpu_ids;
 	}
 
 	of_node_put(dn);

include/linux/of.h

@@ -544,6 +544,8 @@ const char *of_prop_next_string(struct property *prop, const char *cur);
 
 bool of_console_check(struct device_node *dn, char *name, int index);
 
+extern int of_cpu_node_to_id(struct device_node *np);
+
 #else /* CONFIG_OF */
 
 static inline void of_core_init(void)
@@ -916,6 +918,11 @@ static inline void of_property_clear_flag(struct property *p, unsigned long flag
 {
 }
 
+static inline int of_cpu_node_to_id(struct device_node *np)
+{
+	return -ENODEV;
+}
+
 #define of_match_ptr(_ptr)	NULL
 #define of_match_node(_matches, _node)	NULL
 #endif /* CONFIG_OF */

kernel/events/core.c

@@ -4904,6 +4904,7 @@ void perf_event_update_userpage(struct perf_event *event)
 unlock:
 	rcu_read_unlock();
 }
+EXPORT_SYMBOL_GPL(perf_event_update_userpage);
 
 static int perf_mmap_fault(struct vm_fault *vmf)
 {