summaryrefslogtreecommitdiff
path: root/arch/arm64/kernel/perf_event.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/kernel/perf_event.c')
-rw-r--r--arch/arm64/kernel/perf_event.c89
1 files changed, 70 insertions, 19 deletions
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 4d7879484cec..462f9a9cc44b 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -13,12 +13,15 @@
#include <asm/sysreg.h>
#include <asm/virt.h>
+#include <clocksource/arm_arch_timer.h>
+
#include <linux/acpi.h>
#include <linux/clocksource.h>
#include <linux/kvm_host.h>
#include <linux/of.h>
#include <linux/perf/arm_pmu.h>
#include <linux/platform_device.h>
+#include <linux/sched_clock.h>
#include <linux/smp.h>
/* ARMv8 Cortex-A53 specific event types. */
@@ -155,7 +158,7 @@ armv8pmu_events_sysfs_show(struct device *dev,
pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
- return sprintf(page, "event=0x%03llx\n", pmu_attr->id);
+ return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
}
#define ARMV8_EVENT_ATTR(name, config) \
@@ -222,10 +225,29 @@ static struct attribute *armv8_pmuv3_event_attrs[] = {
ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD),
ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD),
ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD),
+ ARMV8_EVENT_ATTR(l1d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD),
+ ARMV8_EVENT_ATTR(op_retired, ARMV8_PMUV3_PERFCTR_OP_RETIRED),
+ ARMV8_EVENT_ATTR(op_spec, ARMV8_PMUV3_PERFCTR_OP_SPEC),
+ ARMV8_EVENT_ATTR(stall, ARMV8_PMUV3_PERFCTR_STALL),
+ ARMV8_EVENT_ATTR(stall_slot_backend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND),
+ ARMV8_EVENT_ATTR(stall_slot_frontend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND),
+ ARMV8_EVENT_ATTR(stall_slot, ARMV8_PMUV3_PERFCTR_STALL_SLOT),
ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP),
ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED),
ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE),
ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION),
+ ARMV8_EVENT_ATTR(cnt_cycles, ARMV8_AMU_PERFCTR_CNT_CYCLES),
+ ARMV8_EVENT_ATTR(stall_backend_mem, ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM),
+ ARMV8_EVENT_ATTR(l1i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS),
+ ARMV8_EVENT_ATTR(l2d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD),
+ ARMV8_EVENT_ATTR(l2i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS),
+ ARMV8_EVENT_ATTR(l3d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD),
+ ARMV8_EVENT_ATTR(ldst_align_lat, ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT),
+ ARMV8_EVENT_ATTR(ld_align_lat, ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT),
+ ARMV8_EVENT_ATTR(st_align_lat, ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT),
+ ARMV8_EVENT_ATTR(mem_access_checked, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED),
+ ARMV8_EVENT_ATTR(mem_access_checked_rd, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD),
+ ARMV8_EVENT_ATTR(mem_access_checked_wr, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR),
NULL,
};
@@ -244,10 +266,13 @@ armv8pmu_event_attr_is_visible(struct kobject *kobj,
test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap))
return attr->mode;
- pmu_attr->id -= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
- if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
- test_bit(pmu_attr->id, cpu_pmu->pmceid_ext_bitmap))
- return attr->mode;
+ if (pmu_attr->id >= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE) {
+ u64 id = pmu_attr->id - ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
+
+ if (id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
+ test_bit(id, cpu_pmu->pmceid_ext_bitmap))
+ return attr->mode;
+ }
return 0;
}
@@ -1165,28 +1190,54 @@ device_initcall(armv8_pmu_driver_init)
void arch_perf_update_userpage(struct perf_event *event,
struct perf_event_mmap_page *userpg, u64 now)
{
- u32 freq;
- u32 shift;
+ struct clock_read_data *rd;
+ unsigned int seq;
+ u64 ns;
- /*
- * Internal timekeeping for enabled/running/stopped times
- * is always computed with the sched_clock.
- */
- freq = arch_timer_get_rate();
- userpg->cap_user_time = 1;
+ userpg->cap_user_time = 0;
+ userpg->cap_user_time_zero = 0;
+ userpg->cap_user_time_short = 0;
+
+ do {
+ rd = sched_clock_read_begin(&seq);
+
+ if (rd->read_sched_clock != arch_timer_read_counter)
+ return;
+
+ userpg->time_mult = rd->mult;
+ userpg->time_shift = rd->shift;
+ userpg->time_zero = rd->epoch_ns;
+ userpg->time_cycles = rd->epoch_cyc;
+ userpg->time_mask = rd->sched_clock_mask;
+
+ /*
+ * Subtract the cycle base, such that software that
+ * doesn't know about cap_user_time_short still 'works'
+ * assuming no wraps.
+ */
+ ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift);
+ userpg->time_zero -= ns;
+
+ } while (sched_clock_read_retry(seq));
+
+ userpg->time_offset = userpg->time_zero - now;
- clocks_calc_mult_shift(&userpg->time_mult, &shift, freq,
- NSEC_PER_SEC, 0);
/*
* time_shift is not expected to be greater than 31 due to
* the original published conversion algorithm shifting a
* 32-bit value (now specifies a 64-bit value) - refer
* perf_event_mmap_page documentation in perf_event.h.
*/
- if (shift == 32) {
- shift = 31;
+ if (userpg->time_shift == 32) {
+ userpg->time_shift = 31;
userpg->time_mult >>= 1;
}
- userpg->time_shift = (u16)shift;
- userpg->time_offset = -now;
+
+ /*
+ * Internal timekeeping for enabled/running/stopped times
+ * is always computed with the sched_clock.
+ */
+ userpg->cap_user_time = 1;
+ userpg->cap_user_time_zero = 1;
+ userpg->cap_user_time_short = 1;
}