[PATCH v10 22/33] KVM: arm64: Apply dynamic guest counter reservations
From: Colton Lewis
Date: Thu Nov 19 2026 - 13:54:45 EST
Reserve and release guest PMU counters dynamically during vCPU load and
put rather than statically at VM creation.
Add kvm_pmu_set_guest_counters() in arch/arm64/kvm/pmu-direct.c, called
from __kvm_pmu_load() and __kvm_pmu_put() with local interrupts
disabled. When the requested guest counter mask collides with active
host events in cpuc->used_mask (or when releasing counters after
squeezing a host event), invoke perf_pmu_resched_update() with
kvm_pmu_update_mask() to update per-CPU cpuc->cntr_mask between
scheduling host events out and back in; otherwise update cpuc->cntr_mask
directly. Warn once in armpmu_add() if a pinned host event fails counter
allocation while guest counters are reserved.
Skip releasing and re-reserving host counters across nested ERET and
nested exception transitions (IN_NESTED_ERET and IN_NESTED_EXCEPTION)
since the vCPU remains on the same physical CPU.
Signed-off-by: Colton Lewis <coltonlewis@xxxxxxxxxx>
---
arch/arm64/kvm/pmu-direct.c | 118 ++++++++++++++++++++++++++++++-----
drivers/perf/arm_pmu.c | 9 ++-
include/linux/perf/arm_pmu.h | 1 +
3 files changed, 113 insertions(+), 15 deletions(-)
diff --git a/arch/arm64/kvm/pmu-direct.c b/arch/arm64/kvm/pmu-direct.c
index ace3e8e781538..cc4ff00d6f41e 100644
--- a/arch/arm64/kvm/pmu-direct.c
+++ b/arch/arm64/kvm/pmu-direct.c
@@ -154,6 +154,70 @@ static u64 kvm_pmu_direct_pmcr_read(struct kvm_vcpu *vcpu)
return u64_replace_bits(pmcr, n, ARMV8_PMU_PMCR_N);
}
+/* Callback to update counter mask between perf scheduling */
+static void kvm_pmu_update_mask(struct pmu *pmu, void *data)
+{
+ struct arm_pmu *arm_pmu = to_arm_pmu(pmu);
+ struct pmu_hw_events *cpuc = this_cpu_ptr(arm_pmu->hw_events);
+ unsigned long *new_mask = data;
+
+ bitmap_copy(cpuc->cntr_mask, new_mask, ARMPMU_MAX_HWEVENTS);
+}
+
+/**
+ * kvm_pmu_set_guest_counters() - Handle dynamic counter reservations
+ * @cpu_pmu: struct arm_pmu to potentially modify
+ * @guest_mask: new guest mask for the pmu
+ *
+ * Check if guest counters will interfere with current host events and
+ * call into perf_pmu_resched_update if a reschedule is required.
+ */
+static void kvm_pmu_set_guest_counters(struct arm_pmu *cpu_pmu, u64 guest_mask)
+{
+ struct pmu_hw_events *cpuc;
+ DECLARE_BITMAP(guest_bitmap, ARMPMU_MAX_HWEVENTS);
+ DECLARE_BITMAP(new_mask, ARMPMU_MAX_HWEVENTS);
+ unsigned long flags;
+ bool need_resched = false;
+
+ if (!cpu_pmu)
+ return;
+
+ local_irq_save(flags);
+ cpuc = this_cpu_ptr(cpu_pmu->hw_events);
+
+ bitmap_from_arr64(guest_bitmap, &guest_mask, ARMPMU_MAX_HWEVENTS);
+ bitmap_copy(new_mask, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS);
+
+ if (guest_mask) {
+ /* Subtract guest counters from available host mask */
+ bitmap_andnot(new_mask, new_mask, guest_bitmap, ARMPMU_MAX_HWEVENTS);
+
+ /* Did we collide with an active host event? */
+ if (bitmap_intersects(cpuc->used_mask, guest_bitmap, ARMPMU_MAX_HWEVENTS)) {
+ need_resched = true;
+ cpuc->host_squeezed = true;
+ }
+ } else {
+ /*
+ * Restoring to full mask.
+ * Only resched if we previously squeezed an event.
+ */
+ if (cpuc->host_squeezed) {
+ need_resched = true;
+ cpuc->host_squeezed = false;
+ }
+ }
+
+ if (need_resched)
+ /* Collision: run full perf reschedule */
+ perf_pmu_resched_update(&cpu_pmu->pmu, kvm_pmu_update_mask, new_mask);
+ else
+ /* Host was never using guest counters anyway */
+ bitmap_copy(cpuc->cntr_mask, new_mask, ARMPMU_MAX_HWEVENTS);
+ local_irq_restore(flags);
+}
+
static u64 kvm_pmu_direct_cntr_read(struct kvm_vcpu *vcpu, u8 idx)
{
lockdep_assert_preemption_disabled();
@@ -422,15 +486,7 @@ static void kvm_pmu_apply_event_filter(struct kvm_vcpu *vcpu)
kvm_pmu_apply_single_event_filter(vcpu, i);
}
-/**
- * kvm_pmu_load() - Load untrapped PMU registers
- * @vcpu: Pointer to struct kvm_vcpu
- *
- * Load all untrapped PMU registers from the VCPU into the PCPU. Mask
- * to only bits belonging to guest-reserved counters and leave
- * host-reserved counters alone in bitmask registers.
- */
-void kvm_pmu_load(struct kvm_vcpu *vcpu)
+static void __kvm_pmu_load(struct kvm_vcpu *vcpu, bool reserve_counters)
{
struct arm_pmu *pmu = vcpu->kvm->arch.arm_pmu;
unsigned long guest_counters;
@@ -446,13 +502,18 @@ void kvm_pmu_load(struct kvm_vcpu *vcpu)
if (!kvm_pmu_is_partitioned(vcpu->kvm) || !vcpu->wants_to_run || !pmu)
return;
+ preempt_disable();
local_irq_save(flags);
if (!cpumask_test_cpu(smp_processor_id(), &pmu->supported_cpus)) {
local_irq_restore(flags);
+ preempt_enable();
return;
}
guest_counters = kvm_vcpu_pmu_guest_counter_mask(vcpu);
+ if (reserve_counters)
+ kvm_pmu_set_guest_counters(pmu, guest_counters);
+
kvm_pmu_apply_event_filter(vcpu);
for_each_set_bit(i, &guest_counters, ARMPMU_MAX_HWEVENTS) {
@@ -505,17 +566,26 @@ void kvm_pmu_load(struct kvm_vcpu *vcpu)
write_sysreg(~val & mask, pmintenclr_el1);
local_irq_restore(flags);
+ preempt_enable();
}
/**
- * kvm_pmu_put() - Put untrapped PMU registers
+ * kvm_pmu_load() - Load untrapped PMU registers
* @vcpu: Pointer to struct kvm_vcpu
*
- * Put all untrapped PMU registers from the PCPU into the VCPU. Mask
+ * Load all untrapped PMU registers from the VCPU into the PCPU. Mask
* to only bits belonging to guest-reserved counters and leave
* host-reserved counters alone in bitmask registers.
*/
-void kvm_pmu_put(struct kvm_vcpu *vcpu)
+void kvm_pmu_load(struct kvm_vcpu *vcpu)
+{
+ bool reserve = !vcpu_get_flag(vcpu, IN_NESTED_ERET) &&
+ !vcpu_get_flag(vcpu, IN_NESTED_EXCEPTION);
+
+ __kvm_pmu_load(vcpu, reserve);
+}
+
+static void __kvm_pmu_put(struct kvm_vcpu *vcpu, bool release_counters)
{
struct arm_pmu *pmu = vcpu->kvm->arch.arm_pmu;
unsigned long guest_counters;
@@ -533,12 +603,13 @@ void kvm_pmu_put(struct kvm_vcpu *vcpu)
if (!kvm_pmu_is_partitioned(vcpu->kvm) || !vcpu->wants_to_run || !pmu)
return;
- local_irq_save(flags);
+ preempt_disable();
if (!cpumask_test_cpu(smp_processor_id(), &pmu->supported_cpus)) {
- local_irq_restore(flags);
+ preempt_enable();
return;
}
+ local_irq_save(flags);
guest_counters = kvm_vcpu_pmu_guest_counter_mask(vcpu);
mask = guest_counters;
@@ -595,5 +666,24 @@ void kvm_pmu_put(struct kvm_vcpu *vcpu)
__vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, |=, val & mask);
write_sysreg(val & mask, pmovsclr_el0);
+ if (release_counters)
+ kvm_pmu_set_guest_counters(pmu, 0);
local_irq_restore(flags);
+ preempt_enable();
+}
+
+/**
+ * kvm_pmu_put() - Put untrapped PMU registers
+ * @vcpu: Pointer to struct kvm_vcpu
+ *
+ * Put all untrapped PMU registers from the PCPU into the VCPU. Mask
+ * to only bits belonging to guest-reserved counters and leave
+ * host-reserved counters alone in bitmask registers.
+ */
+void kvm_pmu_put(struct kvm_vcpu *vcpu)
+{
+ bool release = !vcpu_get_flag(vcpu, IN_NESTED_ERET) &&
+ !vcpu_get_flag(vcpu, IN_NESTED_EXCEPTION);
+
+ __kvm_pmu_put(vcpu, release);
}
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index b1851d1c594b1..2b5bbbd801af8 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -349,8 +349,15 @@ armpmu_add(struct perf_event *event, int flags)
/* If we don't have a space for the counter then finish early. */
idx = armpmu->get_event_idx(hw_events, event);
- if (idx < 0)
+ if (idx < 0) {
+ if (!bitmap_equal(hw_events->cntr_mask, armpmu->cntr_mask,
+ ARMPMU_MAX_HWEVENTS)) {
+ hw_events->host_squeezed = true;
+ if (event->group_leader->attr.pinned)
+ pr_warn_once("perf: Pinned host event squeezed out by KVM guest PMU partition\n");
+ }
return idx;
+ }
/* The newly-allocated counter should be empty */
WARN_ON_ONCE(hw_events->events[idx]);
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index be1e345e99a77..45658273ffa86 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -76,6 +76,7 @@ struct pmu_hw_events {
/* Active events requesting branch records */
unsigned int branch_users;
+ bool host_squeezed;
};
enum armpmu_attr_groups {
--
2.56.1.708.g77570a6a1d-goog