--- zzzz-none-000/linux-3.10.107/arch/arm64/kernel/perf_event.c 2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/arch/arm64/kernel/perf_event.c 2021-02-04 17:41:59.000000000 +0000
@@ -18,569 +18,12 @@
* You should have received a copy of the GNU General Public License
* along with this program. If not, see .
*/
-#define pr_fmt(fmt) "hw perfevents: " fmt
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-
-#include
-#include
#include
-#include
-#include
-
-/*
- * ARMv8 supports a maximum of 32 events.
- * The cycle counter is included in this total.
- */
-#define ARMPMU_MAX_HWEVENTS 32
-
-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);
-
-#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
-
-/* Set at runtime when we know what CPU type we are. */
-static struct arm_pmu *cpu_pmu;
-
-int
-armpmu_get_max_events(void)
-{
- int max_events = 0;
-
- if (cpu_pmu != NULL)
- max_events = cpu_pmu->num_events;
-
- return max_events;
-}
-EXPORT_SYMBOL_GPL(armpmu_get_max_events);
-
-int perf_num_counters(void)
-{
- return armpmu_get_max_events();
-}
-EXPORT_SYMBOL_GPL(perf_num_counters);
-
-#define HW_OP_UNSUPPORTED 0xFFFF
-
-#define C(_x) \
- PERF_COUNT_HW_CACHE_##_x
-
-#define CACHE_OP_UNSUPPORTED 0xFFFF
-
-static int
-armpmu_map_cache_event(const unsigned (*cache_map)
- [PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX],
- u64 config)
-{
- unsigned int cache_type, cache_op, cache_result, ret;
-
- cache_type = (config >> 0) & 0xff;
- if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
- return -EINVAL;
-
- cache_op = (config >> 8) & 0xff;
- if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
- return -EINVAL;
-
- cache_result = (config >> 16) & 0xff;
- if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
- return -EINVAL;
-
- ret = (int)(*cache_map)[cache_type][cache_op][cache_result];
-
- if (ret == CACHE_OP_UNSUPPORTED)
- return -ENOENT;
-
- return ret;
-}
-
-static int
-armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
-{
- int mapping;
-
- if (config >= PERF_COUNT_HW_MAX)
- return -EINVAL;
-
- mapping = (*event_map)[config];
- return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
-}
-
-static int
-armpmu_map_raw_event(u32 raw_event_mask, u64 config)
-{
- return (int)(config & raw_event_mask);
-}
-
-static int map_cpu_event(struct perf_event *event,
- const unsigned (*event_map)[PERF_COUNT_HW_MAX],
- const unsigned (*cache_map)
- [PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX],
- u32 raw_event_mask)
-{
- u64 config = event->attr.config;
-
- switch (event->attr.type) {
- case PERF_TYPE_HARDWARE:
- return armpmu_map_event(event_map, config);
- case PERF_TYPE_HW_CACHE:
- return armpmu_map_cache_event(cache_map, config);
- case PERF_TYPE_RAW:
- return armpmu_map_raw_event(raw_event_mask, config);
- }
-
- return -ENOENT;
-}
-
-int
-armpmu_event_set_period(struct perf_event *event,
- struct hw_perf_event *hwc,
- int idx)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- s64 left = local64_read(&hwc->period_left);
- s64 period = hwc->sample_period;
- int ret = 0;
-
- if (unlikely(left <= -period)) {
- left = period;
- local64_set(&hwc->period_left, left);
- hwc->last_period = period;
- ret = 1;
- }
-
- if (unlikely(left <= 0)) {
- left += period;
- local64_set(&hwc->period_left, left);
- hwc->last_period = period;
- ret = 1;
- }
-
- if (left > (s64)armpmu->max_period)
- left = armpmu->max_period;
-
- local64_set(&hwc->prev_count, (u64)-left);
-
- armpmu->write_counter(idx, (u64)(-left) & 0xffffffff);
-
- perf_event_update_userpage(event);
-
- return ret;
-}
-
-u64
-armpmu_event_update(struct perf_event *event,
- struct hw_perf_event *hwc,
- int idx)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- u64 delta, prev_raw_count, new_raw_count;
-
-again:
- prev_raw_count = local64_read(&hwc->prev_count);
- new_raw_count = armpmu->read_counter(idx);
-
- if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
- new_raw_count) != prev_raw_count)
- goto again;
-
- delta = (new_raw_count - prev_raw_count) & armpmu->max_period;
-
- local64_add(delta, &event->count);
- local64_sub(delta, &hwc->period_left);
-
- return new_raw_count;
-}
-
-static void
-armpmu_read(struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
-
- /* Don't read disabled counters! */
- if (hwc->idx < 0)
- return;
-
- armpmu_event_update(event, hwc, hwc->idx);
-}
-
-static void
-armpmu_stop(struct perf_event *event, int flags)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct hw_perf_event *hwc = &event->hw;
-
- /*
- * ARM pmu always has to update the counter, so ignore
- * PERF_EF_UPDATE, see comments in armpmu_start().
- */
- if (!(hwc->state & PERF_HES_STOPPED)) {
- armpmu->disable(hwc, hwc->idx);
- barrier(); /* why? */
- armpmu_event_update(event, hwc, hwc->idx);
- hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
- }
-}
-
-static void
-armpmu_start(struct perf_event *event, int flags)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct hw_perf_event *hwc = &event->hw;
-
- /*
- * ARM pmu always has to reprogram the period, so ignore
- * PERF_EF_RELOAD, see the comment below.
- */
- if (flags & PERF_EF_RELOAD)
- WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
-
- hwc->state = 0;
- /*
- * Set the period again. Some counters can't be stopped, so when we
- * were stopped we simply disabled the IRQ source and the counter
- * may have been left counting. If we don't do this step then we may
- * get an interrupt too soon or *way* too late if the overflow has
- * happened since disabling.
- */
- armpmu_event_set_period(event, hwc, hwc->idx);
- armpmu->enable(hwc, hwc->idx);
-}
-
-static void
-armpmu_del(struct perf_event *event, int flags)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct pmu_hw_events *hw_events = armpmu->get_hw_events();
- struct hw_perf_event *hwc = &event->hw;
- int idx = hwc->idx;
-
- WARN_ON(idx < 0);
-
- armpmu_stop(event, PERF_EF_UPDATE);
- hw_events->events[idx] = NULL;
- clear_bit(idx, hw_events->used_mask);
-
- perf_event_update_userpage(event);
-}
-
-static int
-armpmu_add(struct perf_event *event, int flags)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct pmu_hw_events *hw_events = armpmu->get_hw_events();
- struct hw_perf_event *hwc = &event->hw;
- int idx;
- int err = 0;
-
- perf_pmu_disable(event->pmu);
-
- /* If we don't have a space for the counter then finish early. */
- idx = armpmu->get_event_idx(hw_events, hwc);
- if (idx < 0) {
- err = idx;
- goto out;
- }
-
- /*
- * If there is an event in the counter we are going to use then make
- * sure it is disabled.
- */
- event->hw.idx = idx;
- armpmu->disable(hwc, idx);
- hw_events->events[idx] = event;
-
- hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
- if (flags & PERF_EF_START)
- armpmu_start(event, PERF_EF_RELOAD);
-
- /* Propagate our changes to the userspace mapping. */
- perf_event_update_userpage(event);
-
-out:
- perf_pmu_enable(event->pmu);
- return err;
-}
-
-static int
-validate_event(struct pmu_hw_events *hw_events,
- struct perf_event *event)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct hw_perf_event fake_event = event->hw;
- struct pmu *leader_pmu = event->group_leader->pmu;
-
- if (is_software_event(event))
- return 1;
-
- if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
- return 1;
-
- if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
- return 1;
-
- return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
-}
-
-static int
-validate_group(struct perf_event *event)
-{
- struct perf_event *sibling, *leader = event->group_leader;
- struct pmu_hw_events fake_pmu;
- DECLARE_BITMAP(fake_used_mask, ARMPMU_MAX_HWEVENTS);
-
- /*
- * Initialise the fake PMU. We only need to populate the
- * used_mask for the purposes of validation.
- */
- memset(fake_used_mask, 0, sizeof(fake_used_mask));
- fake_pmu.used_mask = fake_used_mask;
-
- if (!validate_event(&fake_pmu, leader))
- return -EINVAL;
-
- list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
- if (!validate_event(&fake_pmu, sibling))
- return -EINVAL;
- }
-
- if (!validate_event(&fake_pmu, event))
- return -EINVAL;
-
- return 0;
-}
-
-static void
-armpmu_release_hardware(struct arm_pmu *armpmu)
-{
- int i, irq, irqs;
- struct platform_device *pmu_device = armpmu->plat_device;
-
- irqs = min(pmu_device->num_resources, num_possible_cpus());
-
- for (i = 0; i < irqs; ++i) {
- if (!cpumask_test_and_clear_cpu(i, &armpmu->active_irqs))
- continue;
- irq = platform_get_irq(pmu_device, i);
- if (irq >= 0)
- free_irq(irq, armpmu);
- }
-}
-
-static int
-armpmu_reserve_hardware(struct arm_pmu *armpmu)
-{
- int i, err, irq, irqs;
- struct platform_device *pmu_device = armpmu->plat_device;
-
- if (!pmu_device) {
- pr_err("no PMU device registered\n");
- return -ENODEV;
- }
-
- irqs = min(pmu_device->num_resources, num_possible_cpus());
- if (irqs < 1) {
- pr_err("no irqs for PMUs defined\n");
- 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, armpmu->handle_irq,
- IRQF_NOBALANCING,
- "arm-pmu", armpmu);
- if (err) {
- pr_err("unable to request IRQ%d for ARM PMU counters\n",
- irq);
- armpmu_release_hardware(armpmu);
- return err;
- }
-
- cpumask_set_cpu(i, &armpmu->active_irqs);
- }
-
- return 0;
-}
-
-static void
-hw_perf_event_destroy(struct perf_event *event)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- atomic_t *active_events = &armpmu->active_events;
- struct mutex *pmu_reserve_mutex = &armpmu->reserve_mutex;
-
- if (atomic_dec_and_mutex_lock(active_events, pmu_reserve_mutex)) {
- armpmu_release_hardware(armpmu);
- mutex_unlock(pmu_reserve_mutex);
- }
-}
-
-static int
-event_requires_mode_exclusion(struct perf_event_attr *attr)
-{
- return attr->exclude_idle || attr->exclude_user ||
- attr->exclude_kernel || attr->exclude_hv;
-}
-
-static int
-__hw_perf_event_init(struct perf_event *event)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct hw_perf_event *hwc = &event->hw;
- int mapping, err;
-
- mapping = armpmu->map_event(event);
-
- if (mapping < 0) {
- pr_debug("event %x:%llx not supported\n", event->attr.type,
- event->attr.config);
- return mapping;
- }
-
- /*
- * We don't assign an index until we actually place the event onto
- * hardware. Use -1 to signify that we haven't decided where to put it
- * yet. For SMP systems, each core has it's own PMU so we can't do any
- * clever allocation or constraints checking at this point.
- */
- hwc->idx = -1;
- hwc->config_base = 0;
- hwc->config = 0;
- hwc->event_base = 0;
-
- /*
- * Check whether we need to exclude the counter from certain modes.
- */
- if ((!armpmu->set_event_filter ||
- armpmu->set_event_filter(hwc, &event->attr)) &&
- event_requires_mode_exclusion(&event->attr)) {
- pr_debug("ARM performance counters do not support mode exclusion\n");
- return -EPERM;
- }
- /*
- * Store the event encoding into the config_base field.
- */
- hwc->config_base |= (unsigned long)mapping;
-
- if (!hwc->sample_period) {
- /*
- * For non-sampling runs, limit the sample_period to half
- * of the counter width. That way, the new counter value
- * is far less likely to overtake the previous one unless
- * you have some serious IRQ latency issues.
- */
- hwc->sample_period = armpmu->max_period >> 1;
- hwc->last_period = hwc->sample_period;
- local64_set(&hwc->period_left, hwc->sample_period);
- }
-
- err = 0;
- if (event->group_leader != event) {
- err = validate_group(event);
- if (err)
- return -EINVAL;
- }
-
- return err;
-}
-
-static int armpmu_event_init(struct perf_event *event)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- int err = 0;
- atomic_t *active_events = &armpmu->active_events;
-
- if (armpmu->map_event(event) == -ENOENT)
- return -ENOENT;
-
- event->destroy = hw_perf_event_destroy;
-
- if (!atomic_inc_not_zero(active_events)) {
- mutex_lock(&armpmu->reserve_mutex);
- if (atomic_read(active_events) == 0)
- err = armpmu_reserve_hardware(armpmu);
-
- if (!err)
- atomic_inc(active_events);
- mutex_unlock(&armpmu->reserve_mutex);
- }
-
- if (err)
- return err;
-
- err = __hw_perf_event_init(event);
- if (err)
- hw_perf_event_destroy(event);
-
- return err;
-}
-
-static void armpmu_enable(struct pmu *pmu)
-{
- struct arm_pmu *armpmu = to_arm_pmu(pmu);
- struct pmu_hw_events *hw_events = armpmu->get_hw_events();
- int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events);
-
- if (enabled)
- armpmu->start();
-}
-
-static void armpmu_disable(struct pmu *pmu)
-{
- struct arm_pmu *armpmu = to_arm_pmu(pmu);
- armpmu->stop();
-}
-
-static void __init armpmu_init(struct arm_pmu *armpmu)
-{
- atomic_set(&armpmu->active_events, 0);
- mutex_init(&armpmu->reserve_mutex);
-
- armpmu->pmu = (struct pmu) {
- .pmu_enable = armpmu_enable,
- .pmu_disable = armpmu_disable,
- .event_init = armpmu_event_init,
- .add = armpmu_add,
- .del = armpmu_del,
- .start = armpmu_start,
- .stop = armpmu_stop,
- .read = armpmu_read,
- };
-}
-
-int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type)
-{
- armpmu_init(armpmu);
- return perf_pmu_register(&armpmu->pmu, name, type);
-}
+#include
+#include
+#include
/*
* ARMv8 PMUv3 Performance Events handling code.
@@ -626,128 +69,123 @@
ARMV8_PMUV3_PERFCTR_BUS_CYCLES = 0x1D,
};
+/* ARMv8 Cortex-A53 specific event types. */
+enum armv8_a53_pmu_perf_types {
+ ARMV8_A53_PERFCTR_PREFETCH_LINEFILL = 0xC2,
+};
+
+/* ARMv8 Cortex-A57 specific event types. */
+enum armv8_a57_perf_types {
+ ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD = 0x40,
+ ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST = 0x41,
+ ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD = 0x42,
+ ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST = 0x43,
+ ARMV8_A57_PERFCTR_DTLB_REFILL_LD = 0x4c,
+ ARMV8_A57_PERFCTR_DTLB_REFILL_ST = 0x4d,
+};
+
/* PMUv3 HW events mapping. */
static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
+ PERF_MAP_ALL_UNSUPPORTED,
+ [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
+ [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+ [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+ [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+};
+
+/* ARM Cortex-A53 HW events mapping. */
+static const unsigned armv8_a53_perf_map[PERF_COUNT_HW_MAX] = {
+ PERF_MAP_ALL_UNSUPPORTED,
+ [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
+ [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+ [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_PC_WRITE,
+ [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+ [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
+};
+
+static const unsigned armv8_a57_perf_map[PERF_COUNT_HW_MAX] = {
+ PERF_MAP_ALL_UNSUPPORTED,
[PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
[PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED,
[PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
[PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
- [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED,
- [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = HW_OP_UNSUPPORTED,
- [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = HW_OP_UNSUPPORTED,
+ [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
};
static const unsigned armv8_pmuv3_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)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
- [C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
- [C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(L1I)] = {
- [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,
- },
- },
- [C(LL)] = {
- [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,
- },
- },
- [C(DTLB)] = {
- [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,
- },
- },
- [C(ITLB)] = {
- [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,
- },
- },
- [C(BPU)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
- [C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
- [C(RESULT_MISS)] = ARMV8_PMUV3_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,
- },
- },
+ PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+ [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+ [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+
+ [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+ [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+ [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+ [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
};
+static const unsigned armv8_a53_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+ [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+ [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+ [C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_A53_PERFCTR_PREFETCH_LINEFILL,
+
+ [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS,
+ [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL,
+
+ [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_ITLB_REFILL,
+
+ [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+ [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+ [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+ [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+};
+
+static const unsigned armv8_a57_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+ [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD,
+ [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST,
+
+ [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS,
+ [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL,
+
+ [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_A57_PERFCTR_DTLB_REFILL_LD,
+ [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_A57_PERFCTR_DTLB_REFILL_ST,
+
+ [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_ITLB_REFILL,
+
+ [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+ [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+ [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+ [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+};
+
+
/*
* Perf Events' indices
*/
#define ARMV8_IDX_CYCLE_COUNTER 0
#define ARMV8_IDX_COUNTER0 1
-#define ARMV8_IDX_COUNTER_LAST (ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
+#define ARMV8_IDX_COUNTER_LAST(cpu_pmu) \
+ (ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
#define ARMV8_MAX_COUNTERS 32
#define ARMV8_COUNTER_MASK (ARMV8_MAX_COUNTERS - 1)
@@ -784,8 +222,8 @@
/*
* PMXEVTYPER: Event selection reg
*/
-#define ARMV8_EVTYPE_MASK 0xc80000ff /* Mask for writable bits */
-#define ARMV8_EVTYPE_EVENT 0xff /* Mask for EVENT bits */
+#define ARMV8_EVTYPE_MASK 0xc80003ff /* Mask for writable bits */
+#define ARMV8_EVTYPE_EVENT 0x3ff /* Mask for EVENT bits */
/*
* Event filters for PMUv3
@@ -813,49 +251,34 @@
return pmovsr & ARMV8_OVERFLOWED_MASK;
}
-static inline int armv8pmu_counter_valid(int idx)
+static inline int armv8pmu_counter_valid(struct arm_pmu *cpu_pmu, int idx)
{
- return idx >= ARMV8_IDX_CYCLE_COUNTER && idx <= ARMV8_IDX_COUNTER_LAST;
+ return idx >= ARMV8_IDX_CYCLE_COUNTER &&
+ idx <= ARMV8_IDX_COUNTER_LAST(cpu_pmu);
}
static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
{
- int ret = 0;
- u32 counter;
-
- if (!armv8pmu_counter_valid(idx)) {
- pr_err("CPU%u checking wrong counter %d overflow status\n",
- smp_processor_id(), idx);
- } else {
- counter = ARMV8_IDX_TO_COUNTER(idx);
- ret = pmnc & BIT(counter);
- }
-
- return ret;
+ return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx));
}
static inline int armv8pmu_select_counter(int idx)
{
- u32 counter;
-
- if (!armv8pmu_counter_valid(idx)) {
- pr_err("CPU%u selecting wrong PMNC counter %d\n",
- smp_processor_id(), idx);
- return -EINVAL;
- }
-
- counter = ARMV8_IDX_TO_COUNTER(idx);
+ u32 counter = ARMV8_IDX_TO_COUNTER(idx);
asm volatile("msr pmselr_el0, %0" :: "r" (counter));
isb();
return idx;
}
-static inline u32 armv8pmu_read_counter(int idx)
+static inline u32 armv8pmu_read_counter(struct perf_event *event)
{
+ struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
u32 value = 0;
- if (!armv8pmu_counter_valid(idx))
+ if (!armv8pmu_counter_valid(cpu_pmu, idx))
pr_err("CPU%u reading wrong counter %d\n",
smp_processor_id(), idx);
else if (idx == ARMV8_IDX_CYCLE_COUNTER)
@@ -866,9 +289,13 @@
return value;
}
-static inline void armv8pmu_write_counter(int idx, u32 value)
+static inline void armv8pmu_write_counter(struct perf_event *event, u32 value)
{
- if (!armv8pmu_counter_valid(idx))
+ struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
+
+ if (!armv8pmu_counter_valid(cpu_pmu, idx))
pr_err("CPU%u writing wrong counter %d\n",
smp_processor_id(), idx);
else if (idx == ARMV8_IDX_CYCLE_COUNTER)
@@ -887,65 +314,34 @@
static inline int armv8pmu_enable_counter(int idx)
{
- u32 counter;
-
- if (!armv8pmu_counter_valid(idx)) {
- pr_err("CPU%u enabling wrong PMNC counter %d\n",
- smp_processor_id(), idx);
- return -EINVAL;
- }
-
- counter = ARMV8_IDX_TO_COUNTER(idx);
+ u32 counter = ARMV8_IDX_TO_COUNTER(idx);
asm volatile("msr pmcntenset_el0, %0" :: "r" (BIT(counter)));
return idx;
}
static inline int armv8pmu_disable_counter(int idx)
{
- u32 counter;
-
- if (!armv8pmu_counter_valid(idx)) {
- pr_err("CPU%u disabling wrong PMNC counter %d\n",
- smp_processor_id(), idx);
- return -EINVAL;
- }
-
- counter = ARMV8_IDX_TO_COUNTER(idx);
+ u32 counter = ARMV8_IDX_TO_COUNTER(idx);
asm volatile("msr pmcntenclr_el0, %0" :: "r" (BIT(counter)));
return idx;
}
static inline int armv8pmu_enable_intens(int idx)
{
- u32 counter;
-
- if (!armv8pmu_counter_valid(idx)) {
- pr_err("CPU%u enabling wrong PMNC counter IRQ enable %d\n",
- smp_processor_id(), idx);
- return -EINVAL;
- }
-
- counter = ARMV8_IDX_TO_COUNTER(idx);
+ u32 counter = ARMV8_IDX_TO_COUNTER(idx);
asm volatile("msr pmintenset_el1, %0" :: "r" (BIT(counter)));
return idx;
}
static inline int armv8pmu_disable_intens(int idx)
{
- u32 counter;
-
- if (!armv8pmu_counter_valid(idx)) {
- pr_err("CPU%u disabling wrong PMNC counter IRQ enable %d\n",
- smp_processor_id(), idx);
- return -EINVAL;
- }
-
- counter = ARMV8_IDX_TO_COUNTER(idx);
+ u32 counter = ARMV8_IDX_TO_COUNTER(idx);
asm volatile("msr pmintenclr_el1, %0" :: "r" (BIT(counter)));
isb();
/* Clear the overflow flag in case an interrupt is pending. */
asm volatile("msr pmovsclr_el0, %0" :: "r" (BIT(counter)));
isb();
+
return idx;
}
@@ -963,10 +359,13 @@
return value;
}
-static void armv8pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void armv8pmu_enable_event(struct perf_event *event)
{
unsigned long flags;
- struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+ struct hw_perf_event *hwc = &event->hw;
+ struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+ struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+ int idx = hwc->idx;
/*
* Enable counter and interrupt, and set the counter to count
@@ -997,10 +396,13 @@
raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
-static void armv8pmu_disable_event(struct hw_perf_event *hwc, int idx)
+static void armv8pmu_disable_event(struct perf_event *event)
{
unsigned long flags;
- struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+ struct hw_perf_event *hwc = &event->hw;
+ struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+ struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+ int idx = hwc->idx;
/*
* Disable counter and interrupt
@@ -1024,7 +426,8 @@
{
u32 pmovsr;
struct perf_sample_data data;
- struct pmu_hw_events *cpuc;
+ struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev;
+ struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
struct pt_regs *regs;
int idx;
@@ -1044,7 +447,6 @@
*/
regs = get_irq_regs();
- cpuc = &__get_cpu_var(cpu_hw_events);
for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
struct perf_event *event = cpuc->events[idx];
struct hw_perf_event *hwc;
@@ -1061,13 +463,13 @@
continue;
hwc = &event->hw;
- armpmu_event_update(event, hwc, idx);
+ armpmu_event_update(event);
perf_sample_data_init(&data, 0, hwc->last_period);
- if (!armpmu_event_set_period(event, hwc, idx))
+ if (!armpmu_event_set_period(event))
continue;
if (perf_event_overflow(event, &data, regs))
- cpu_pmu->disable(hwc, idx);
+ cpu_pmu->disable(event);
}
/*
@@ -1082,10 +484,10 @@
return IRQ_HANDLED;
}
-static void armv8pmu_start(void)
+static void armv8pmu_start(struct arm_pmu *cpu_pmu)
{
unsigned long flags;
- struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+ struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
raw_spin_lock_irqsave(&events->pmu_lock, flags);
/* Enable all counters */
@@ -1093,10 +495,10 @@
raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
-static void armv8pmu_stop(void)
+static void armv8pmu_stop(struct arm_pmu *cpu_pmu)
{
unsigned long flags;
- struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+ struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
raw_spin_lock_irqsave(&events->pmu_lock, flags);
/* Disable all counters */
@@ -1105,10 +507,12 @@
}
static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
- struct hw_perf_event *event)
+ struct perf_event *event)
{
int idx;
- unsigned long evtype = event->config_base & ARMV8_EVTYPE_EVENT;
+ struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned long evtype = hwc->config_base & ARMV8_EVTYPE_EVENT;
/* Always place a cycle counter into the cycle counter. */
if (evtype == ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES) {
@@ -1159,253 +563,119 @@
static void armv8pmu_reset(void *info)
{
+ struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
u32 idx, nb_cnt = cpu_pmu->num_events;
/* The counter and interrupt enable registers are unknown at reset. */
- for (idx = ARMV8_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx)
- armv8pmu_disable_event(NULL, idx);
+ for (idx = ARMV8_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) {
+ armv8pmu_disable_counter(idx);
+ armv8pmu_disable_intens(idx);
+ }
/* Initialize & Reset PMNC: C and P bits. */
armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C);
-
- /* Disable access from userspace. */
- asm volatile("msr pmuserenr_el0, %0" :: "r" (0));
}
static int armv8_pmuv3_map_event(struct perf_event *event)
{
- return map_cpu_event(event, &armv8_pmuv3_perf_map,
- &armv8_pmuv3_perf_cache_map, 0xFF);
+ return armpmu_map_event(event, &armv8_pmuv3_perf_map,
+ &armv8_pmuv3_perf_cache_map,
+ ARMV8_EVTYPE_EVENT);
}
-static struct arm_pmu armv8pmu = {
- .handle_irq = armv8pmu_handle_irq,
- .enable = armv8pmu_enable_event,
- .disable = armv8pmu_disable_event,
- .read_counter = armv8pmu_read_counter,
- .write_counter = armv8pmu_write_counter,
- .get_event_idx = armv8pmu_get_event_idx,
- .start = armv8pmu_start,
- .stop = armv8pmu_stop,
- .reset = armv8pmu_reset,
- .max_period = (1LLU << 32) - 1,
-};
-
-static u32 __init armv8pmu_read_num_pmnc_events(void)
+static int armv8_a53_map_event(struct perf_event *event)
{
- u32 nb_cnt;
-
- /* Read the nb of CNTx counters supported from PMNC */
- nb_cnt = (armv8pmu_pmcr_read() >> ARMV8_PMCR_N_SHIFT) & ARMV8_PMCR_N_MASK;
-
- /* Add the CPU cycles counter and return */
- return nb_cnt + 1;
+ return armpmu_map_event(event, &armv8_a53_perf_map,
+ &armv8_a53_perf_cache_map,
+ ARMV8_EVTYPE_EVENT);
}
-static struct arm_pmu *__init armv8_pmuv3_pmu_init(void)
+static int armv8_a57_map_event(struct perf_event *event)
{
- armv8pmu.name = "arm/armv8-pmuv3";
- armv8pmu.map_event = armv8_pmuv3_map_event;
- armv8pmu.num_events = armv8pmu_read_num_pmnc_events();
- armv8pmu.set_event_filter = armv8pmu_set_event_filter;
- return &armv8pmu;
+ return armpmu_map_event(event, &armv8_a57_perf_map,
+ &armv8_a57_perf_cache_map,
+ ARMV8_EVTYPE_EVENT);
}
-/*
- * Ensure the PMU has sane values out of reset.
- * This requires SMP to be available, so exists as a separate initcall.
- */
-static int __init
-cpu_pmu_reset(void)
+static void armv8pmu_read_num_pmnc_events(void *info)
{
- if (cpu_pmu && cpu_pmu->reset)
- return on_each_cpu(cpu_pmu->reset, NULL, 1);
- return 0;
-}
-arch_initcall(cpu_pmu_reset);
+ int *nb_cnt = info;
-/*
- * PMU platform driver and devicetree bindings.
- */
-static struct of_device_id armpmu_of_device_ids[] = {
- {.compatible = "arm,armv8-pmuv3"},
- {},
-};
-
-static int armpmu_device_probe(struct platform_device *pdev)
-{
- if (!cpu_pmu)
- return -ENODEV;
+ /* Read the nb of CNTx counters supported from PMNC */
+ *nb_cnt = (armv8pmu_pmcr_read() >> ARMV8_PMCR_N_SHIFT) & ARMV8_PMCR_N_MASK;
- cpu_pmu->plat_device = pdev;
- return 0;
+ /* Add the CPU cycles counter */
+ *nb_cnt += 1;
}
-static struct platform_driver armpmu_driver = {
- .driver = {
- .name = "arm-pmu",
- .of_match_table = armpmu_of_device_ids,
- },
- .probe = armpmu_device_probe,
-};
-
-static int __init register_pmu_driver(void)
+static int armv8pmu_probe_num_events(struct arm_pmu *arm_pmu)
{
- return platform_driver_register(&armpmu_driver);
+ return smp_call_function_any(&arm_pmu->supported_cpus,
+ armv8pmu_read_num_pmnc_events,
+ &arm_pmu->num_events, 1);
}
-device_initcall(register_pmu_driver);
-static struct pmu_hw_events *armpmu_get_cpu_events(void)
+static void armv8_pmu_init(struct arm_pmu *cpu_pmu)
{
- return &__get_cpu_var(cpu_hw_events);
+ cpu_pmu->handle_irq = armv8pmu_handle_irq,
+ cpu_pmu->enable = armv8pmu_enable_event,
+ cpu_pmu->disable = armv8pmu_disable_event,
+ cpu_pmu->read_counter = armv8pmu_read_counter,
+ cpu_pmu->write_counter = armv8pmu_write_counter,
+ cpu_pmu->get_event_idx = armv8pmu_get_event_idx,
+ cpu_pmu->start = armv8pmu_start,
+ cpu_pmu->stop = armv8pmu_stop,
+ cpu_pmu->reset = armv8pmu_reset,
+ cpu_pmu->max_period = (1LLU << 32) - 1,
+ cpu_pmu->set_event_filter = armv8pmu_set_event_filter;
}
-static void __init cpu_pmu_init(struct arm_pmu *armpmu)
+static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu)
{
- int cpu;
- for_each_possible_cpu(cpu) {
- struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
- events->events = per_cpu(hw_events, cpu);
- events->used_mask = per_cpu(used_mask, cpu);
- raw_spin_lock_init(&events->pmu_lock);
- }
- armpmu->get_hw_events = armpmu_get_cpu_events;
+ armv8_pmu_init(cpu_pmu);
+ cpu_pmu->name = "armv8_pmuv3";
+ cpu_pmu->map_event = armv8_pmuv3_map_event;
+ return armv8pmu_probe_num_events(cpu_pmu);
}
-static int __init init_hw_perf_events(void)
+static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
{
- u64 dfr = read_cpuid(ID_AA64DFR0_EL1);
-
- switch ((dfr >> 8) & 0xf) {
- case 0x1: /* PMUv3 */
- cpu_pmu = armv8_pmuv3_pmu_init();
- break;
- }
-
- if (cpu_pmu) {
- pr_info("enabled with %s PMU driver, %d counters available\n",
- cpu_pmu->name, cpu_pmu->num_events);
- cpu_pmu_init(cpu_pmu);
- armpmu_register(cpu_pmu, "cpu", PERF_TYPE_RAW);
- } else {
- pr_info("no hardware support available\n");
- }
-
- return 0;
+ armv8_pmu_init(cpu_pmu);
+ cpu_pmu->name = "armv8_cortex_a53";
+ cpu_pmu->map_event = armv8_a53_map_event;
+ return armv8pmu_probe_num_events(cpu_pmu);
}
-early_initcall(init_hw_perf_events);
-
-/*
- * Callchain handling code.
- */
-struct frame_tail {
- struct frame_tail __user *fp;
- unsigned long lr;
-} __attribute__((packed));
-/*
- * Get the return address for a single stackframe and return a pointer to the
- * next frame tail.
- */
-static struct frame_tail __user *
-user_backtrace(struct frame_tail __user *tail,
- struct perf_callchain_entry *entry)
+static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
{
- struct frame_tail buftail;
- unsigned long err;
-
- /* Also check accessibility of one struct frame_tail beyond */
- if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
- return NULL;
-
- pagefault_disable();
- err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
- pagefault_enable();
-
- if (err)
- return NULL;
-
- perf_callchain_store(entry, buftail.lr);
-
- /*
- * Frame pointers should strictly progress back up the stack
- * (towards higher addresses).
- */
- if (tail >= buftail.fp)
- return NULL;
-
- return buftail.fp;
-}
-
-void perf_callchain_user(struct perf_callchain_entry *entry,
- struct pt_regs *regs)
-{
- struct frame_tail __user *tail;
-
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
- /* We don't support guest os callchain now */
- return;
- }
-
- perf_callchain_store(entry, regs->pc);
- tail = (struct frame_tail __user *)regs->regs[29];
-
- while (entry->nr < PERF_MAX_STACK_DEPTH &&
- tail && !((unsigned long)tail & 0xf))
- tail = user_backtrace(tail, entry);
+ armv8_pmu_init(cpu_pmu);
+ cpu_pmu->name = "armv8_cortex_a57";
+ cpu_pmu->map_event = armv8_a57_map_event;
+ return armv8pmu_probe_num_events(cpu_pmu);
}
-/*
- * Gets called by walk_stackframe() for every stackframe. This will be called
- * whist unwinding the stackframe and is like a subroutine return so we use
- * the PC.
- */
-static int callchain_trace(struct stackframe *frame, void *data)
-{
- struct perf_callchain_entry *entry = data;
- perf_callchain_store(entry, frame->pc);
- return 0;
-}
+static const struct of_device_id armv8_pmu_of_device_ids[] = {
+ {.compatible = "arm,armv8-pmuv3", .data = armv8_pmuv3_init},
+ {.compatible = "arm,cortex-a53-pmu", .data = armv8_a53_pmu_init},
+ {.compatible = "arm,cortex-a57-pmu", .data = armv8_a57_pmu_init},
+ {},
+};
-void perf_callchain_kernel(struct perf_callchain_entry *entry,
- struct pt_regs *regs)
+static int armv8_pmu_device_probe(struct platform_device *pdev)
{
- struct stackframe frame;
-
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
- /* We don't support guest os callchain now */
- return;
- }
-
- frame.fp = regs->regs[29];
- frame.sp = regs->sp;
- frame.pc = regs->pc;
- walk_stackframe(&frame, callchain_trace, entry);
+ return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, NULL);
}
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
-{
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
- return perf_guest_cbs->get_guest_ip();
-
- return instruction_pointer(regs);
-}
+static struct platform_driver armv8_pmu_driver = {
+ .driver = {
+ .name = "armv8-pmu",
+ .of_match_table = armv8_pmu_of_device_ids,
+ },
+ .probe = armv8_pmu_device_probe,
+};
-unsigned long perf_misc_flags(struct pt_regs *regs)
+static int __init register_armv8_pmu_driver(void)
{
- int misc = 0;
-
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
- if (perf_guest_cbs->is_user_mode())
- misc |= PERF_RECORD_MISC_GUEST_USER;
- else
- misc |= PERF_RECORD_MISC_GUEST_KERNEL;
- } else {
- if (user_mode(regs))
- misc |= PERF_RECORD_MISC_USER;
- else
- misc |= PERF_RECORD_MISC_KERNEL;
- }
-
- return misc;
+ return platform_driver_register(&armv8_pmu_driver);
}
+device_initcall(register_armv8_pmu_driver);