[PATCH v10 07/33] perf: arm_pmuv3: Move counter allocation mask to per-CPU struct pmu_hw_events

From: Colton Lewis

Date: Thu Nov 19 2026 - 13:53:37 EST


In preparation for dynamic per-CPU PMU counter reservations when running
KVM guests with a partitioned PMU, move the counter allocation mask from
the global struct arm_pmu to per-CPU struct pmu_hw_events.

Initialize cpuc->cntr_mask from the static cpu_pmu->cntr_mask during PMU
probe and CPU hotplug startup, and update event counter allocation
helpers (armv8pmu_get_single_idx(), armv8pmu_get_chain_idx(), and
armv8pmu_get_event_idx()) to query the per-CPU mask.

Tested-by: James Clark <james.clark@xxxxxxxxxx>
Signed-off-by: Colton Lewis <coltonlewis@xxxxxxxxxx>
---
drivers/perf/arm_pmu.c | 9 +++++++--
drivers/perf/arm_pmuv3.c | 28 +++++++++++++++++-----------
include/linux/perf/arm_pmu.h | 1 +
3 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 1150695653892..b1851d1c594b1 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -408,9 +408,11 @@ validate_group(struct perf_event *event)

/*
* Initialise the fake PMU. We only need to populate the
- * used_mask for the purposes of validation.
+ * used_mask and cntr_mask for the purposes of validation.
*/
memset(&fake_pmu.used_mask, 0, sizeof(fake_pmu.used_mask));
+ bitmap_copy(fake_pmu.cntr_mask, to_arm_pmu(event->pmu)->cntr_mask,
+ ARMPMU_MAX_HWEVENTS);

if (!validate_event(event->pmu, &fake_pmu, leader))
return -EINVAL;
@@ -717,6 +719,7 @@ bool arm_pmu_irq_is_nmi(void)
static int arm_perf_starting_cpu(unsigned int cpu, struct hlist_node *node)
{
struct arm_pmu *pmu = hlist_entry_safe(node, struct arm_pmu, node);
+ struct pmu_hw_events *cpuc = per_cpu_ptr(pmu->hw_events, cpu);
int irq;

if (!cpumask_test_cpu(cpu, &pmu->supported_cpus))
@@ -724,6 +727,8 @@ static int arm_perf_starting_cpu(unsigned int cpu, struct hlist_node *node)
if (pmu->reset)
pmu->reset(pmu);

+ bitmap_copy(cpuc->cntr_mask, pmu->cntr_mask, ARMPMU_MAX_HWEVENTS);
+
irq = armpmu_get_cpu_irq(pmu, cpu);
if (irq)
per_cpu(cpu_irq_ops, cpu)->enable_pmuirq(irq);
@@ -753,7 +758,7 @@ static void cpu_pm_pmu_setup(struct arm_pmu *armpmu, unsigned long cmd)
struct perf_event *event;
int idx;

- for_each_set_bit(idx, armpmu->cntr_mask, ARMPMU_MAX_HWEVENTS) {
+ for_each_set_bit(idx, hw_events->cntr_mask, ARMPMU_MAX_HWEVENTS) {
event = hw_events->events[idx];
if (!event)
continue;
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 4a6c1f3bcea1f..973d4abcb3a6e 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -813,7 +813,7 @@ static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu)
write_pmuacr(mask);
} else {
/* Clear any unused counters to avoid leaking their contents */
- for_each_andnot_bit(i, cpu_pmu->cntr_mask, cpuc->used_mask,
+ for_each_andnot_bit(i, cpuc->cntr_mask, cpuc->used_mask,
ARMPMU_MAX_HWEVENTS) {
if (i == ARMV8_PMU_CYCLE_IDX)
write_pmccntr(0);
@@ -917,7 +917,7 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
* to prevent skews in group events.
*/
armv8pmu_stop(cpu_pmu);
- for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS) {
+ for_each_set_bit(idx, cpuc->cntr_mask, ARMPMU_MAX_HWEVENTS) {
struct perf_event *event = cpuc->events[idx];
struct hw_perf_event *hwc;

@@ -953,20 +953,18 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
return IRQ_HANDLED;
}

-static int armv8pmu_get_single_idx(struct pmu_hw_events *cpuc,
- struct arm_pmu *cpu_pmu)
+static int armv8pmu_get_single_idx(struct pmu_hw_events *cpuc)
{
int idx;

- for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) {
+ for_each_set_bit(idx, cpuc->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) {
if (!test_and_set_bit(idx, cpuc->used_mask))
return idx;
}
return -EAGAIN;
}

-static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc,
- struct arm_pmu *cpu_pmu)
+static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc)
{
int idx;

@@ -974,7 +972,7 @@ static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc,
* Chaining requires two consecutive event counters, where
* the lower idx must be even.
*/
- for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) {
+ for_each_set_bit(idx, cpuc->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) {
if (!(idx & 0x1))
continue;
if (!test_and_set_bit(idx, cpuc->used_mask)) {
@@ -1042,7 +1040,7 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
*/
if ((evtype == ARMV8_PMUV3_PERFCTR_INST_RETIRED) &&
!armv8pmu_event_get_threshold(&event->attr) &&
- test_bit(ARMV8_PMU_INSTR_IDX, cpu_pmu->cntr_mask) &&
+ test_bit(ARMV8_PMU_INSTR_IDX, cpuc->cntr_mask) &&
!armv8pmu_event_want_user_access(event)) {
if (!test_and_set_bit(ARMV8_PMU_INSTR_IDX, cpuc->used_mask))
return ARMV8_PMU_INSTR_IDX;
@@ -1052,9 +1050,9 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
* Otherwise use events counters
*/
if (armv8pmu_event_is_chained(event))
- return armv8pmu_get_chain_idx(cpuc, cpu_pmu);
+ return armv8pmu_get_chain_idx(cpuc);
else
- return armv8pmu_get_single_idx(cpuc, cpu_pmu);
+ return armv8pmu_get_single_idx(cpuc);
}

static void armv8pmu_clear_event_idx(struct pmu_hw_events *cpuc,
@@ -1426,6 +1424,7 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
.present = false,
};
int ret;
+ int cpu;

ret = smp_call_function_any(&cpu_pmu->supported_cpus,
__armv8pmu_probe_pmu,
@@ -1441,6 +1440,13 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
if (ret)
return ret;
}
+
+ for_each_possible_cpu(cpu) {
+ struct pmu_hw_events *cpuc = per_cpu_ptr(cpu_pmu->hw_events, cpu);
+
+ bitmap_copy(cpuc->cntr_mask, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS);
+ }
+
return 0;
}

diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 02d2c7f45b527..be1e345e99a77 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -62,6 +62,7 @@ struct pmu_hw_events {
* an event. A 0 means that the counter can be used.
*/
DECLARE_BITMAP(used_mask, ARMPMU_MAX_HWEVENTS);
+ DECLARE_BITMAP(cntr_mask, ARMPMU_MAX_HWEVENTS);

/*
* When using percpu IRQs, we need a percpu dev_id. Place it here as we
--
2.56.1.708.g77570a6a1d-goog