Merge branch 'devel-stable' into for-next

Conflicts:
	arch/arm/kernel/perf_event_cpu.c

15 files changed, 730 insertions, 855 deletions

diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c
index 5f8a52ac7edf..a923524d1040 100644
--- a/arch/arm/common/mcpm_entry.c
+++ b/arch/arm/common/mcpm_entry.c
@@ -20,6 +20,126 @@
 #include <asm/cputype.h>
 #include <asm/suspend.h>
 
+/*
+ * The public API for this code is documented in arch/arm/include/asm/mcpm.h.
+ * For a comprehensive description of the main algorithm used here, please
+ * see Documentation/arm/cluster-pm-race-avoidance.txt.
+ */
+
+struct sync_struct mcpm_sync;
+
+/*
+ * __mcpm_cpu_going_down: Indicates that the cpu is being torn down.
+ *    This must be called at the point of committing to teardown of a CPU.
+ *    The CPU cache (SCTRL.C bit) is expected to still be active.
+ */
+static void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster)
+{
+	mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_GOING_DOWN;
+	sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu);
+}
+
+/*
+ * __mcpm_cpu_down: Indicates that cpu teardown is complete and that the
+ *    cluster can be torn down without disrupting this CPU.
+ *    To avoid deadlocks, this must be called before a CPU is powered down.
+ *    The CPU cache (SCTRL.C bit) is expected to be off.
+ *    However L2 cache might or might not be active.
+ */
+static void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster)
+{
+	dmb();
+	mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_DOWN;
+	sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu);
+	sev();
+}
+
+/*
+ * __mcpm_outbound_leave_critical: Leave the cluster teardown critical section.
+ * @state: the final state of the cluster:
+ *     CLUSTER_UP: no destructive teardown was done and the cluster has been
+ *         restored to the previous state (CPU cache still active); or
+ *     CLUSTER_DOWN: the cluster has been torn-down, ready for power-off
+ *         (CPU cache disabled, L2 cache either enabled or disabled).
+ */
+static void __mcpm_outbound_leave_critical(unsigned int cluster, int state)
+{
+	dmb();
+	mcpm_sync.clusters[cluster].cluster = state;
+	sync_cache_w(&mcpm_sync.clusters[cluster].cluster);
+	sev();
+}
+
+/*
+ * __mcpm_outbound_enter_critical: Enter the cluster teardown critical section.
+ * This function should be called by the last man, after local CPU teardown
+ * is complete.  CPU cache expected to be active.
+ *
+ * Returns:
+ *     false: the critical section was not entered because an inbound CPU was
+ *         observed, or the cluster is already being set up;
+ *     true: the critical section was entered: it is now safe to tear down the
+ *         cluster.
+ */
+static bool __mcpm_outbound_enter_critical(unsigned int cpu, unsigned int cluster)
+{
+	unsigned int i;
+	struct mcpm_sync_struct *c = &mcpm_sync.clusters[cluster];
+
+	/* Warn inbound CPUs that the cluster is being torn down: */
+	c->cluster = CLUSTER_GOING_DOWN;
+	sync_cache_w(&c->cluster);
+
+	/* Back out if the inbound cluster is already in the critical region: */
+	sync_cache_r(&c->inbound);
+	if (c->inbound == INBOUND_COMING_UP)
+		goto abort;
+
+	/*
+	 * Wait for all CPUs to get out of the GOING_DOWN state, so that local
+	 * teardown is complete on each CPU before tearing down the cluster.
+	 *
+	 * If any CPU has been woken up again from the DOWN state, then we
+	 * shouldn't be taking the cluster down at all: abort in that case.
+	 */
+	sync_cache_r(&c->cpus);
+	for (i = 0; i < MAX_CPUS_PER_CLUSTER; i++) {
+		int cpustate;
+
+		if (i == cpu)
+			continue;
+
+		while (1) {
+			cpustate = c->cpus[i].cpu;
+			if (cpustate != CPU_GOING_DOWN)
+				break;
+
+			wfe();
+			sync_cache_r(&c->cpus[i].cpu);
+		}
+
+		switch (cpustate) {
+		case CPU_DOWN:
+			continue;
+
+		default:
+			goto abort;
+		}
+	}
+
+	return true;
+
+abort:
+	__mcpm_outbound_leave_critical(cluster, CLUSTER_UP);
+	return false;
+}
+
+static int __mcpm_cluster_state(unsigned int cluster)
+{
+	sync_cache_r(&mcpm_sync.clusters[cluster].cluster);
+	return mcpm_sync.clusters[cluster].cluster;
+}
+
 extern unsigned long mcpm_entry_vectors[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER];
 
 void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr)
@@ -78,16 +198,11 @@ int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster)
 	bool cpu_is_down, cluster_is_down;
 	int ret = 0;
 
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
 	if (!platform_ops)
 		return -EUNATCH; /* try not to shadow power_up errors */
 	might_sleep();
 
-	/* backward compatibility callback */
-	if (platform_ops->power_up)
-		return platform_ops->power_up(cpu, cluster);
-
-	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
-
 	/*
 	 * Since this is called with IRQs enabled, and no arch_spin_lock_irq
 	 * variant exists, we need to disable IRQs manually here.
@@ -128,29 +243,17 @@ void mcpm_cpu_power_down(void)
 	bool cpu_going_down, last_man;
 	phys_reset_t phys_reset;
 
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
 	if (WARN_ON_ONCE(!platform_ops))
 	       return;
 	BUG_ON(!irqs_disabled());
 
-	/*
-	 * Do this before calling into the power_down method,
-	 * as it might not always be safe to do afterwards.
-	 */
 	setup_mm_for_reboot();
 
-	/* backward compatibility callback */
-	if (platform_ops->power_down) {
-		platform_ops->power_down();
-		goto not_dead;
-	}
-
-	mpidr = read_cpuid_mpidr();
-	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
-	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
-
 	__mcpm_cpu_going_down(cpu, cluster);
-
 	arch_spin_lock(&mcpm_lock);
 	BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
 
@@ -187,7 +290,6 @@ void mcpm_cpu_power_down(void)
 	if (cpu_going_down)
 		wfi();
 
-not_dead:
 	/*
 	 * It is possible for a power_up request to happen concurrently
 	 * with a power_down request for the same CPU. In this case the
@@ -219,22 +321,11 @@ int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster)
 	return ret;
 }
 
-void mcpm_cpu_suspend(u64 expected_residency)
+void mcpm_cpu_suspend(void)
 {
 	if (WARN_ON_ONCE(!platform_ops))
 		return;
 
-	/* backward compatibility callback */
-	if (platform_ops->suspend) {
-		phys_reset_t phys_reset;
-		BUG_ON(!irqs_disabled());
-		setup_mm_for_reboot();
-		platform_ops->suspend(expected_residency);
-		phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
-		phys_reset(virt_to_phys(mcpm_entry_point));
-		BUG();
-	}
-
 	/* Some platforms might have to enable special resume modes, etc. */
 	if (platform_ops->cpu_suspend_prepare) {
 		unsigned int mpidr = read_cpuid_mpidr();
@@ -256,12 +347,6 @@ int mcpm_cpu_powered_up(void)
 	if (!platform_ops)
 		return -EUNATCH;
 
-	/* backward compatibility callback */
-	if (platform_ops->powered_up) {
-		platform_ops->powered_up();
-		return 0;
-	}
-
 	mpidr = read_cpuid_mpidr();
 	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
 	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
@@ -334,120 +419,6 @@ int __init mcpm_loopback(void (*cache_disable)(void))
 
 #endif
 
-struct sync_struct mcpm_sync;
-
-/*
- * __mcpm_cpu_going_down: Indicates that the cpu is being torn down.
- *    This must be called at the point of committing to teardown of a CPU.
- *    The CPU cache (SCTRL.C bit) is expected to still be active.
- */
-void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster)
-{
-	mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_GOING_DOWN;
-	sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu);
-}
-
-/*
- * __mcpm_cpu_down: Indicates that cpu teardown is complete and that the
- *    cluster can be torn down without disrupting this CPU.
- *    To avoid deadlocks, this must be called before a CPU is powered down.
- *    The CPU cache (SCTRL.C bit) is expected to be off.
- *    However L2 cache might or might not be active.
- */
-void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster)
-{
-	dmb();
-	mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_DOWN;
-	sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu);
-	sev();
-}
-
-/*
- * __mcpm_outbound_leave_critical: Leave the cluster teardown critical section.
- * @state: the final state of the cluster:
- *     CLUSTER_UP: no destructive teardown was done and the cluster has been
- *         restored to the previous state (CPU cache still active); or
- *     CLUSTER_DOWN: the cluster has been torn-down, ready for power-off
- *         (CPU cache disabled, L2 cache either enabled or disabled).
- */
-void __mcpm_outbound_leave_critical(unsigned int cluster, int state)
-{
-	dmb();
-	mcpm_sync.clusters[cluster].cluster = state;
-	sync_cache_w(&mcpm_sync.clusters[cluster].cluster);
-	sev();
-}
-
-/*
- * __mcpm_outbound_enter_critical: Enter the cluster teardown critical section.
- * This function should be called by the last man, after local CPU teardown
- * is complete.  CPU cache expected to be active.
- *
- * Returns:
- *     false: the critical section was not entered because an inbound CPU was
- *         observed, or the cluster is already being set up;
- *     true: the critical section was entered: it is now safe to tear down the
- *         cluster.
- */
-bool __mcpm_outbound_enter_critical(unsigned int cpu, unsigned int cluster)
-{
-	unsigned int i;
-	struct mcpm_sync_struct *c = &mcpm_sync.clusters[cluster];
-
-	/* Warn inbound CPUs that the cluster is being torn down: */
-	c->cluster = CLUSTER_GOING_DOWN;
-	sync_cache_w(&c->cluster);
-
-	/* Back out if the inbound cluster is already in the critical region: */
-	sync_cache_r(&c->inbound);
-	if (c->inbound == INBOUND_COMING_UP)
-		goto abort;
-
-	/*
-	 * Wait for all CPUs to get out of the GOING_DOWN state, so that local
-	 * teardown is complete on each CPU before tearing down the cluster.
-	 *
-	 * If any CPU has been woken up again from the DOWN state, then we
-	 * shouldn't be taking the cluster down at all: abort in that case.
-	 */
-	sync_cache_r(&c->cpus);
-	for (i = 0; i < MAX_CPUS_PER_CLUSTER; i++) {
-		int cpustate;
-
-		if (i == cpu)
-			continue;
-
-		while (1) {
-			cpustate = c->cpus[i].cpu;
-			if (cpustate != CPU_GOING_DOWN)
-				break;
-
-			wfe();
-			sync_cache_r(&c->cpus[i].cpu);
-		}
-
-		switch (cpustate) {
-		case CPU_DOWN:
-			continue;
-
-		default:
-			goto abort;
-		}
-	}
-
-	return true;
-
-abort:
-	__mcpm_outbound_leave_critical(cluster, CLUSTER_UP);
-	return false;
-}
-
-int __mcpm_cluster_state(unsigned int cluster)
-{
-	sync_cache_r(&mcpm_sync.clusters[cluster].cluster);
-	return mcpm_sync.clusters[cluster].cluster;
-}
-
 extern unsigned long mcpm_power_up_setup_phys;
 
 int __init mcpm_sync_init(
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index 50b378f59e08..acd4983d9b1f 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -137,17 +137,12 @@ int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster);
 /**
  * mcpm_cpu_suspend - bring the calling CPU in a suspended state
  *
- * @expected_residency: duration in microseconds the CPU is expected
- *			to remain suspended, or 0 if unknown/infinity.
- *
- * The calling CPU is suspended.  The expected residency argument is used
- * as a hint by the platform specific backend to implement the appropriate
- * sleep state level according to the knowledge it has on wake-up latency
- * for the given hardware.
+ * The calling CPU is suspended.  This is similar to mcpm_cpu_power_down()
+ * except for possible extra platform specific configuration steps to allow
+ * an asynchronous wake-up e.g. with a pending interrupt.
  *
  * If this CPU is found to be the "last man standing" in the cluster
- * then the cluster may be prepared for power-down too, if the expected
- * residency makes it worthwhile.
+ * then the cluster may be prepared for power-down too.
  *
  * This must be called with interrupts disabled.
  *
@@ -157,7 +152,7 @@ int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster);
  * This will return if mcpm_platform_register() has not been called
  * previously in which case the caller should take appropriate action.
  */
-void mcpm_cpu_suspend(u64 expected_residency);
+void mcpm_cpu_suspend(void);
 
 /**
  * mcpm_cpu_powered_up - housekeeping workafter a CPU has been powered up
@@ -234,12 +229,6 @@ struct mcpm_platform_ops {
 	void (*cpu_is_up)(unsigned int cpu, unsigned int cluster);
 	void (*cluster_is_up)(unsigned int cluster);
 	int (*wait_for_powerdown)(unsigned int cpu, unsigned int cluster);
-
-	/* deprecated callbacks */
-	int (*power_up)(unsigned int cpu, unsigned int cluster);
-	void (*power_down)(void);
-	void (*suspend)(u64);
-	void (*powered_up)(void);
 };
 
 /**
@@ -251,35 +240,6 @@ struct mcpm_platform_ops {
  */
 int __init mcpm_platform_register(const struct mcpm_platform_ops *ops);
 
-/* Synchronisation structures for coordinating safe cluster setup/teardown: */
-
-/*
- * When modifying this structure, make sure you update the MCPM_SYNC_ defines
- * to match.
- */
-struct mcpm_sync_struct {
-	/* individual CPU states */
-	struct {
-		s8 cpu __aligned(__CACHE_WRITEBACK_GRANULE);
-	} cpus[MAX_CPUS_PER_CLUSTER];
-
-	/* cluster state */
-	s8 cluster __aligned(__CACHE_WRITEBACK_GRANULE);
-
-	/* inbound-side state */
-	s8 inbound __aligned(__CACHE_WRITEBACK_GRANULE);
-};
-
-struct sync_struct {
-	struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS];
-};
-
-void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster);
-void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster);
-void __mcpm_outbound_leave_critical(unsigned int cluster, int state);
-bool __mcpm_outbound_enter_critical(unsigned int this_cpu, unsigned int cluster);
-int __mcpm_cluster_state(unsigned int cluster);
-
 /**
  * mcpm_sync_init - Initialize the cluster synchronization support
  *
@@ -318,6 +278,29 @@ int __init mcpm_loopback(void (*cache_disable)(void));
 
 void __init mcpm_smp_set_ops(void);
 
+/*
+ * Synchronisation structures for coordinating safe cluster setup/teardown.
+ * This is private to the MCPM core code and shared between C and assembly.
+ * When modifying this structure, make sure you update the MCPM_SYNC_ defines
+ * to match.
+ */
+struct mcpm_sync_struct {
+	/* individual CPU states */
+	struct {
+		s8 cpu __aligned(__CACHE_WRITEBACK_GRANULE);
+	} cpus[MAX_CPUS_PER_CLUSTER];
+
+	/* cluster state */
+	s8 cluster __aligned(__CACHE_WRITEBACK_GRANULE);
+
+	/* inbound-side state */
+	s8 inbound __aligned(__CACHE_WRITEBACK_GRANULE);
+};
+
+struct sync_struct {
+	struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS];
+};
+
 #else
 
 /* 
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index d9cf138fd7d4..4f9dec489931 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -19,4 +19,11 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs)	perf_misc_flags(regs)
 #endif
 
+#define perf_arch_fetch_caller_regs(regs, __ip) { \
+	(regs)->ARM_pc = (__ip); \
+	(regs)->ARM_fp = (unsigned long) __builtin_frame_address(0); \
+	(regs)->ARM_sp = current_stack_pointer; \
+	(regs)->ARM_cpsr = SVC_MODE; \
+}
+
 #endif /* __ARM_PERF_EVENT_H__ */
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index 675e4ab79f68..3fc87dfd77e6 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -24,22 +24,10 @@
  *	interrupt and passed the address of the low level handler,
  *	and can be used to implement any platform specific handling
  *	before or after calling it.
- * @runtime_resume: an optional handler which will be called by the
- *	runtime PM framework following a call to pm_runtime_get().
- *	Note that if pm_runtime_get() is called more than once in
- *	succession this handler will only be called once.
- * @runtime_suspend: an optional handler which will be called by the
- *	runtime PM framework following a call to pm_runtime_put().
- *	Note that if pm_runtime_get() is called more than once in
- *	succession this handler will only be called following the
- *	final call to pm_runtime_put() that actually disables the
- *	hardware.
  */
 struct arm_pmu_platdata {
 	irqreturn_t (*handle_irq)(int irq, void *dev,
 				  irq_handler_t pmu_handler);
-	int (*runtime_resume)(struct device *dev);
-	int (*runtime_suspend)(struct device *dev);
 };
 
 #ifdef CONFIG_HW_PERF_EVENTS
@@ -92,6 +80,7 @@ struct pmu_hw_events {
 struct arm_pmu {
 	struct pmu	pmu;
 	cpumask_t	active_irqs;
+	cpumask_t	supported_cpus;
 	int		*irq_affinity;
 	char		*name;
 	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
@@ -122,8 +111,6 @@ struct arm_pmu {
 
 #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
 
-extern const struct dev_pm_ops armpmu_dev_pm_ops;
-
 int armpmu_register(struct arm_pmu *armpmu, int type);
 
 u64 armpmu_event_update(struct perf_event *event);
@@ -158,6 +145,10 @@ struct pmu_probe_info {
 #define XSCALE_PMU_PROBE(_version, _fn) \
 	PMU_PROBE(ARM_CPU_IMP_INTEL << 24 | _version, ARM_PMU_XSCALE_MASK, _fn)
 
+int arm_pmu_device_probe(struct platform_device *pdev,
+			 const struct of_device_id *of_table,
+			 const struct pmu_probe_info *probe_table);
+
 #endif /* CONFIG_HW_PERF_EVENTS */
 
 #endif /* __ARM_PMU_H__ */
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 32c0990d1968..e69f7a19735d 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -71,7 +71,9 @@ obj-$(CONFIG_CPU_PJ4)		+= pj4-cp0.o
 obj-$(CONFIG_CPU_PJ4B)		+= pj4-cp0.o
 obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_regs.o perf_callchain.o
-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o perf_event_cpu.o
+obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o \
+				   perf_event_xscale.o perf_event_v6.o \
+				   perf_event_v7.o
 CFLAGS_pj4-cp0.o		:= -marm
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 4a86a0133ac3..357f57ea83f4 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -11,12 +11,18 @@
  */
 #define pr_fmt(fmt) "hw perfevents: " fmt
 
+#include <linux/bitmap.h>
+#include <linux/cpumask.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
-#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
 #include <linux/irq.h>
 #include <linux/irqdesc.h>
 
+#include <asm/cputype.h>
 #include <asm/irq_regs.h>
 #include <asm/pmu.h>
 
@@ -229,6 +235,10 @@ armpmu_add(struct perf_event *event, int flags)
 	int idx;
 	int err = 0;
 
+	/* An event following a process won't be stopped earlier */
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
+		return -ENOENT;
+
 	perf_pmu_disable(event->pmu);
 
 	/* If we don't have a space for the counter then finish early. */
@@ -344,20 +354,12 @@ static void
 armpmu_release_hardware(struct arm_pmu *armpmu)
 {
 	armpmu->free_irq(armpmu);
-	pm_runtime_put_sync(&armpmu->plat_device->dev);
 }
 
 static int
 armpmu_reserve_hardware(struct arm_pmu *armpmu)
 {
-	int err;
-	struct platform_device *pmu_device = armpmu->plat_device;
-
-	if (!pmu_device)
-		return -ENODEV;
-
-	pm_runtime_get_sync(&pmu_device->dev);
-	err = armpmu->request_irq(armpmu, armpmu_dispatch_irq);
+	int err = armpmu->request_irq(armpmu, armpmu_dispatch_irq);
 	if (err) {
 		armpmu_release_hardware(armpmu);
 		return err;
@@ -454,6 +456,17 @@ static int armpmu_event_init(struct perf_event *event)
 	int err = 0;
 	atomic_t *active_events = &armpmu->active_events;
 
+	/*
+	 * Reject CPU-affine events for CPUs that are of a different class to
+	 * that which this PMU handles. Process-following events (where
+	 * event->cpu == -1) can be migrated between CPUs, and thus we have to
+	 * reject them later (in armpmu_add) if they're scheduled on a
+	 * different class of CPU.
+	 */
+	if (event->cpu != -1 &&
+		!cpumask_test_cpu(event->cpu, &armpmu->supported_cpus))
+		return -ENOENT;
+
 	/* does not support taken branch sampling */
 	if (has_branch_stack(event))
 		return -EOPNOTSUPP;
@@ -489,6 +502,10 @@ static void armpmu_enable(struct pmu *pmu)
 	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
 	int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events);
 
+	/* For task-bound events we may be called on other CPUs */
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
+		return;
+
 	if (enabled)
 		armpmu->start(armpmu);
 }
@@ -496,34 +513,25 @@ static void armpmu_enable(struct pmu *pmu)
 static void armpmu_disable(struct pmu *pmu)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(pmu);
-	armpmu->stop(armpmu);
-}
-
-#ifdef CONFIG_PM
-static int armpmu_runtime_resume(struct device *dev)
-{
-	struct arm_pmu_platdata *plat = dev_get_platdata(dev);
 
-	if (plat && plat->runtime_resume)
-		return plat->runtime_resume(dev);
+	/* For task-bound events we may be called on other CPUs */
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
+		return;
 
-	return 0;
+	armpmu->stop(armpmu);
 }
 
-static int armpmu_runtime_suspend(struct device *dev)
+/*
+ * In heterogeneous systems, events are specific to a particular
+ * microarchitecture, and aren't suitable for another. Thus, only match CPUs of
+ * the same microarchitecture.
+ */
+static int armpmu_filter_match(struct perf_event *event)
 {
-	struct arm_pmu_platdata *plat = dev_get_platdata(dev);
-
-	if (plat && plat->runtime_suspend)
-		return plat->runtime_suspend(dev);
-
-	return 0;
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+	unsigned int cpu = smp_processor_id();
+	return cpumask_test_cpu(cpu, &armpmu->supported_cpus);
 }
-#endif
-
-const struct dev_pm_ops armpmu_dev_pm_ops = {
-	SET_RUNTIME_PM_OPS(armpmu_runtime_suspend, armpmu_runtime_resume, NULL)
-};
 
 static void armpmu_init(struct arm_pmu *armpmu)
 {
@@ -539,15 +547,349 @@ static void armpmu_init(struct arm_pmu *armpmu)
 		.start		= armpmu_start,
 		.stop		= armpmu_stop,
 		.read		= armpmu_read,
+		.filter_match	= armpmu_filter_match,
 	};
 }
 
 int armpmu_register(struct arm_pmu *armpmu, int type)
 {
 	armpmu_init(armpmu);
-	pm_runtime_enable(&armpmu->plat_device->dev);
 	pr_info("enabled with %s PMU driver, %d counters available\n",
 			armpmu->name, armpmu->num_events);
 	return perf_pmu_register(&armpmu->pmu, armpmu->name, type);
 }
 
+/* Set at runtime when we know what CPU type we are. */
+static struct arm_pmu *__oprofile_cpu_pmu;
+
+/*
+ * Despite the names, these two functions are CPU-specific and are used
+ * by the OProfile/perf code.
+ */
+const char *perf_pmu_name(void)
+{
+	if (!__oprofile_cpu_pmu)
+		return NULL;
+
+	return __oprofile_cpu_pmu->name;
+}
+EXPORT_SYMBOL_GPL(perf_pmu_name);
+
+int perf_num_counters(void)
+{
+	int max_events = 0;
+
+	if (__oprofile_cpu_pmu != NULL)
+		max_events = __oprofile_cpu_pmu->num_events;
+
+	return max_events;
+}
+EXPORT_SYMBOL_GPL(perf_num_counters);
+
+static void cpu_pmu_enable_percpu_irq(void *data)
+{
+	int irq = *(int *)data;
+
+	enable_percpu_irq(irq, IRQ_TYPE_NONE);
+}
+
+static void cpu_pmu_disable_percpu_irq(void *data)
+{
+	int irq = *(int *)data;
+
+	disable_percpu_irq(irq);
+}
+
+static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
+{
+	int i, irq, irqs;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	struct pmu_hw_events __percpu *hw_events = cpu_pmu->hw_events;
+
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		on_each_cpu(cpu_pmu_disable_percpu_irq, &irq, 1);
+		free_percpu_irq(irq, &hw_events->percpu_pmu);
+	} else {
+		for (i = 0; i < irqs; ++i) {
+			int cpu = i;
+
+			if (cpu_pmu->irq_affinity)
+				cpu = cpu_pmu->irq_affinity[i];
+
+			if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
+				continue;
+			irq = platform_get_irq(pmu_device, i);
+			if (irq >= 0)
+				free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, cpu));
+		}
+	}
+}
+
+static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
+{
+	int i, err, irq, irqs;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	struct pmu_hw_events __percpu *hw_events = cpu_pmu->hw_events;
+
+	if (!pmu_device)
+		return -ENODEV;
+
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+	if (irqs < 1) {
+		pr_warn_once("perf/ARM: No irqs for PMU defined, sampling events not supported\n");
+		return 0;
+	}
+
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		err = request_percpu_irq(irq, handler, "arm-pmu",
+					 &hw_events->percpu_pmu);
+		if (err) {
+			pr_err("unable to request IRQ%d for ARM PMU counters\n",
+				irq);
+			return err;
+		}
+		on_each_cpu(cpu_pmu_enable_percpu_irq, &irq, 1);
+	} else {
+		for (i = 0; i < irqs; ++i) {
+			int cpu = i;
+
+			err = 0;
+			irq = platform_get_irq(pmu_device, i);
+			if (irq < 0)
+				continue;
+
+			if (cpu_pmu->irq_affinity)
+				cpu = cpu_pmu->irq_affinity[i];
+
+			/*
+			 * If we have a single PMU interrupt that we can't shift,
+			 * assume that we're running on a uniprocessor machine and
+			 * continue. Otherwise, continue without this interrupt.
+			 */
+			if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) {
+				pr_warn("unable to set irq affinity (irq=%d, cpu=%u)\n",
+					irq, cpu);
+				continue;
+			}
+
+			err = request_irq(irq, handler,
+					  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
+					  per_cpu_ptr(&hw_events->percpu_pmu, cpu));
+			if (err) {
+				pr_err("unable to request IRQ%d for ARM PMU counters\n",
+					irq);
+				return err;
+			}
+
+			cpumask_set_cpu(cpu, &cpu_pmu->active_irqs);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * PMU hardware loses all context when a CPU goes offline.
+ * When a CPU is hotplugged back in, since some hardware registers are
+ * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading
+ * junk values out of them.
+ */
+static int cpu_pmu_notify(struct notifier_block *b, unsigned long action,
+			  void *hcpu)
+{
+	int cpu = (unsigned long)hcpu;
+	struct arm_pmu *pmu = container_of(b, struct arm_pmu, hotplug_nb);
+
+	if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
+		return NOTIFY_DONE;
+
+	if (!cpumask_test_cpu(cpu, &pmu->supported_cpus))
+		return NOTIFY_DONE;
+
+	if (pmu->reset)
+		pmu->reset(pmu);
+	else
+		return NOTIFY_DONE;
+
+	return NOTIFY_OK;
+}
+
+static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	int err;
+	int cpu;
+	struct pmu_hw_events __percpu *cpu_hw_events;
+
+	cpu_hw_events = alloc_percpu(struct pmu_hw_events);
+	if (!cpu_hw_events)
+		return -ENOMEM;
+
+	cpu_pmu->hotplug_nb.notifier_call = cpu_pmu_notify;
+	err = register_cpu_notifier(&cpu_pmu->hotplug_nb);
+	if (err)
+		goto out_hw_events;
+
+	for_each_possible_cpu(cpu) {
+		struct pmu_hw_events *events = per_cpu_ptr(cpu_hw_events, cpu);
+		raw_spin_lock_init(&events->pmu_lock);
+		events->percpu_pmu = cpu_pmu;
+	}
+
+	cpu_pmu->hw_events	= cpu_hw_events;
+	cpu_pmu->request_irq	= cpu_pmu_request_irq;
+	cpu_pmu->free_irq	= cpu_pmu_free_irq;
+
+	/* Ensure the PMU has sane values out of reset. */
+	if (cpu_pmu->reset)
+		on_each_cpu_mask(&cpu_pmu->supported_cpus, cpu_pmu->reset,
+			 cpu_pmu, 1);
+
+	/* If no interrupts available, set the corresponding capability flag */
+	if (!platform_get_irq(cpu_pmu->plat_device, 0))
+		cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
+	return 0;
+
+out_hw_events:
+	free_percpu(cpu_hw_events);
+	return err;
+}
+
+static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
+{
+	unregister_cpu_notifier(&cpu_pmu->hotplug_nb);
+	free_percpu(cpu_pmu->hw_events);
+}
+
+/*
+ * CPU PMU identification and probing.
+ */
+static int probe_current_pmu(struct arm_pmu *pmu,
+			     const struct pmu_probe_info *info)
+{
+	int cpu = get_cpu();
+	unsigned int cpuid = read_cpuid_id();
+	int ret = -ENODEV;
+
+	pr_info("probing PMU on CPU %d\n", cpu);
+
+	for (; info->init != NULL; info++) {
+		if ((cpuid & info->mask) != info->cpuid)
+			continue;
+		ret = info->init(pmu);
+		break;
+	}
+
+	put_cpu();
+	return ret;
+}
+
+static int of_pmu_irq_cfg(struct arm_pmu *pmu)
+{
+	int i, irq, *irqs;
+	struct platform_device *pdev = pmu->plat_device;
+
+	/* Don't bother with PPIs; they're already affine */
+	irq = platform_get_irq(pdev, 0);
+	if (irq >= 0 && irq_is_percpu(irq))
+		return 0;
+
+	irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);