ARM: perf: support percpu irqs for the CPU PMU

Some CPU PMUs are wired up with one PPI for all the CPUs instead
of with a different SPI for each CPU. Add support for these
devices.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
This commit is contained in:
Stephen Boyd 2014-02-07 21:01:19 +00:00 committed by Will Deacon
parent 6d0abeca32
commit bbd6455937
2 changed files with 79 additions and 30 deletions

View File

@ -16,6 +16,8 @@
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/uaccess.h>
#include <linux/irq.h>
#include <linux/irqdesc.h>
#include <asm/irq_regs.h>
#include <asm/pmu.h>
@ -295,9 +297,15 @@ validate_group(struct perf_event *event)
static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
{
struct arm_pmu *armpmu = (struct arm_pmu *) dev;
struct platform_device *plat_device = armpmu->plat_device;
struct arm_pmu_platdata *plat = dev_get_platdata(&plat_device->dev);
struct arm_pmu *armpmu;
struct platform_device *plat_device;
struct arm_pmu_platdata *plat;
if (irq_is_percpu(irq))
dev = *(void **)dev;
armpmu = dev;
plat_device = armpmu->plat_device;
plat = dev_get_platdata(&plat_device->dev);
if (plat && plat->handle_irq)
return plat->handle_irq(irq, dev, armpmu->handle_irq);

View File

@ -25,6 +25,8 @@
#include <linux/platform_device.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>
@ -33,6 +35,7 @@
/* Set at runtime when we know what CPU type we are. */
static struct arm_pmu *cpu_pmu;
static DEFINE_PER_CPU(struct arm_pmu *, percpu_pmu);
static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
@ -71,6 +74,26 @@ static struct pmu_hw_events *cpu_pmu_get_cpu_events(void)
return this_cpu_ptr(&cpu_hw_events);
}
static void cpu_pmu_enable_percpu_irq(void *data)
{
struct arm_pmu *cpu_pmu = data;
struct platform_device *pmu_device = cpu_pmu->plat_device;
int irq = platform_get_irq(pmu_device, 0);
enable_percpu_irq(irq, IRQ_TYPE_NONE);
cpumask_set_cpu(smp_processor_id(), &cpu_pmu->active_irqs);
}
static void cpu_pmu_disable_percpu_irq(void *data)
{
struct arm_pmu *cpu_pmu = data;
struct platform_device *pmu_device = cpu_pmu->plat_device;
int irq = platform_get_irq(pmu_device, 0);
cpumask_clear_cpu(smp_processor_id(), &cpu_pmu->active_irqs);
disable_percpu_irq(irq);
}
static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
{
int i, irq, irqs;
@ -78,12 +101,18 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
irqs = min(pmu_device->num_resources, num_possible_cpus());
for (i = 0; i < irqs; ++i) {
if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
continue;
irq = platform_get_irq(pmu_device, i);
if (irq >= 0)
free_irq(irq, cpu_pmu);
irq = platform_get_irq(pmu_device, 0);
if (irq >= 0 && irq_is_percpu(irq)) {
on_each_cpu(cpu_pmu_disable_percpu_irq, cpu_pmu, 1);
free_percpu_irq(irq, &percpu_pmu);
} else {
for (i = 0; i < irqs; ++i) {
if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
continue;
irq = platform_get_irq(pmu_device, i);
if (irq >= 0)
free_irq(irq, cpu_pmu);
}
}
}
@ -101,33 +130,44 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
return -ENODEV;
}
for (i = 0; i < irqs; ++i) {
err = 0;
irq = platform_get_irq(pmu_device, i);
if (irq < 0)
continue;
/*
* 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(i)) && irqs > 1) {
pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
irq, i);
continue;
}
err = request_irq(irq, handler,
IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
cpu_pmu);
irq = platform_get_irq(pmu_device, 0);
if (irq >= 0 && irq_is_percpu(irq)) {
err = request_percpu_irq(irq, handler, "arm-pmu", &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, cpu_pmu, 1);
} else {
for (i = 0; i < irqs; ++i) {
err = 0;
irq = platform_get_irq(pmu_device, i);
if (irq < 0)
continue;
cpumask_set_cpu(i, &cpu_pmu->active_irqs);
/*
* 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(i)) && irqs > 1) {
pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
irq, i);
continue;
}
err = request_irq(irq, handler,
IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
cpu_pmu);
if (err) {
pr_err("unable to request IRQ%d for ARM PMU counters\n",
irq);
return err;
}
cpumask_set_cpu(i, &cpu_pmu->active_irqs);
}
}
return 0;
@ -141,6 +181,7 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
events->events = per_cpu(hw_events, cpu);
events->used_mask = per_cpu(used_mask, cpu);
raw_spin_lock_init(&events->pmu_lock);
per_cpu(percpu_pmu, cpu) = cpu_pmu;
}
cpu_pmu->get_hw_events = cpu_pmu_get_cpu_events;