[PATCH v10 30/33] KVM: arm64: Support zero event counters on Partitioned PMU without HPMN0

From: Colton Lewis

Date: Thu Nov 19 2026 - 13:55:11 EST


Programming MDCR_EL2.HPMN to 0 is CONSTRAINED UNPREDICTABLE on CPUs that
do not implement FEAT_HPMN0, preventing userspace from configuring a
cycle-counter-only Partitioned PMU guest (nr_pmu_counters == 0) on those
platforms if HPMN is set directly from nr_pmu_counters.

Support nr_pmu_counters == 0 without FEAT_HPMN0 whenever the PMU has at
least two general-purpose counters by setting physical MDCR_EL2.HPMN = 1
(via kvm_arm_pmu_part_hpmn()), reserving and quiescing physical counter 0
alongside PMCCNTR_EL0 on vCPU load so host perf uses counters 1..N-1,
keeping MDCR_EL2.TPMCR set so trapped PMCR_EL0 reads report N == 0, and
enabling fine-grained traps on PMEVCNTRn_EL0, PMCNTEN, PMINTEN, and
PMSWINC_EL0 so counter 0 remains completely hidden from the guest while
PMCCNTR_EL0 accesses stay untrapped on FEAT_FGT hosts.

Signed-off-by: Colton Lewis <coltonlewis@xxxxxxxxxx>
---
arch/arm64/kvm/config.c | 16 ++++++++++----
arch/arm64/kvm/debug.c | 12 ++++++-----
arch/arm64/kvm/pmu-direct.c | 42 ++++++++++++++++++++++++++++++-------
arch/arm64/kvm/pmu.c | 15 +++++++++++--
include/kvm/arm_pmu.h | 6 ++++++
5 files changed, 73 insertions(+), 18 deletions(-)

diff --git a/arch/arm64/kvm/config.c b/arch/arm64/kvm/config.c
index 0ec74e45fdbf6..bbe940f6266aa 100644
--- a/arch/arm64/kvm/config.c
+++ b/arch/arm64/kvm/config.c
@@ -1791,6 +1791,8 @@ static void __compute_hdfgrtr(struct kvm_vcpu *vcpu)
__compute_fgt(vcpu, HDFGRTR_EL2);

if (kvm_pmu_is_partitioned(vcpu->kvm)) {
+ unsigned int n = vcpu->kvm->arch.nr_pmu_counters;
+ bool hide_gp0 = kvm_arm_pmu_part_hpmn(n) != n;
u64 set = HDFGRTR_EL2_PMOVS |
HDFGRTR_EL2_PMCCFILTR_EL0 |
HDFGRTR_EL2_PMEVTYPERn_EL0 |
@@ -1801,10 +1803,12 @@ static void __compute_hdfgrtr(struct kvm_vcpu *vcpu)
(__vcpu_sys_reg(vcpu, MDCR_EL2) & MDCR_EL2_TPM))
set |= HDFGRTR_EL2_PMUSERENR_EL0;

- if (kvm_pmu_hyp_counter_mask(vcpu))
+ if (kvm_pmu_hyp_counter_mask(vcpu) || hide_gp0)
set |= HDFGRTR_EL2_PMCNTEN;
- if (kvm_pmu_part_ovf32_mask(vcpu))
+ if (kvm_pmu_part_ovf32_mask(vcpu) || hide_gp0)
set |= HDFGRTR_EL2_PMEVCNTRn_EL0;
+ if (hide_gp0)
+ set |= HDFGRTR_EL2_PMINTEN;

*vcpu_fgt(vcpu, HDFGRTR_EL2) |= set & ~hdfgrtr_masks.res0;
}
@@ -1818,6 +1822,8 @@ static void __compute_hdfgwtr(struct kvm_vcpu *vcpu)
*vcpu_fgt(vcpu, HDFGWTR_EL2) |= HDFGWTR_EL2_MDSCR_EL1;

if (kvm_pmu_is_partitioned(vcpu->kvm)) {
+ unsigned int n = vcpu->kvm->arch.nr_pmu_counters;
+ bool hide_gp0 = kvm_arm_pmu_part_hpmn(n) != n;
u64 set = HDFGWTR_EL2_PMOVS |
HDFGWTR_EL2_PMCCFILTR_EL0 |
HDFGWTR_EL2_PMEVTYPERn_EL0;
@@ -1825,10 +1831,12 @@ static void __compute_hdfgwtr(struct kvm_vcpu *vcpu)
if (is_hyp_ctxt(vcpu))
set |= HDFGWTR_EL2_PMUSERENR_EL0;

- if (kvm_pmu_hyp_counter_mask(vcpu))
+ if (kvm_pmu_hyp_counter_mask(vcpu) || hide_gp0)
set |= HDFGWTR_EL2_PMCNTEN | HDFGWTR_EL2_PMSWINC_EL0;
- if (kvm_pmu_part_ovf32_mask(vcpu))
+ if (kvm_pmu_part_ovf32_mask(vcpu) || hide_gp0)
set |= HDFGWTR_EL2_PMEVCNTRn_EL0;
+ if (hide_gp0)
+ set |= HDFGWTR_EL2_PMINTEN;

*vcpu_fgt(vcpu, HDFGWTR_EL2) |= set & ~hdfgwtr_masks.res0;
}
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index b89f46cb59955..73d157f5b8f6f 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -58,11 +58,11 @@ void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu)
if (kvm_pmu_is_partitioned(vcpu->kvm) && vcpu->arch.pmu.loaded_on_cpu) {
u8 nr_host_cntr = *host_data_ptr(nr_event_counters);
u8 nr_guest_cntr = vcpu->kvm->arch.nr_pmu_counters;
+ u8 guest_hpmn = kvm_arm_pmu_part_hpmn(nr_guest_cntr);

if (cpumask_test_cpu(smp_processor_id(),
vcpu->kvm->arch.supported_cpus) &&
- nr_guest_cntr < nr_host_cntr &&
- (cpus_have_final_cap(ARM64_HAS_HPMN0) || nr_guest_cntr > 0)) {
+ guest_hpmn < nr_host_cntr) {
u64 hpmn = FIELD_GET(MDCR_EL2_HPMN, read_sysreg(mdcr_el2));
bool hpme;

@@ -81,14 +81,16 @@ void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu)
* Take out the coarse grain traps if we are using
* fine grain traps and enforce counter access with
* HPMN. Keep TPMCR when L1 sub-partitions its counters
- * so PMCR_EL0 reads and writes trap for multiplexing.
+ * or when guest_hpmn > nr_guest_cntr (!FEAT_HPMN0 with
+ * 0 event counters) so PMCR_EL0 accesses trap.
*/
mdcr &= ~MDCR_EL2_HPMN;
- mdcr |= FIELD_PREP(MDCR_EL2_HPMN, nr_guest_cntr);
+ mdcr |= FIELD_PREP(MDCR_EL2_HPMN, guest_hpmn);

if (cpus_have_final_cap(ARM64_HAS_FGT)) {
mdcr &= ~MDCR_EL2_TPM;
- if (!kvm_pmu_hyp_counter_mask(vcpu))
+ if (!kvm_pmu_hyp_counter_mask(vcpu) &&
+ guest_hpmn == nr_guest_cntr)
mdcr &= ~MDCR_EL2_TPMCR;
}
}
diff --git a/arch/arm64/kvm/pmu-direct.c b/arch/arm64/kvm/pmu-direct.c
index 6382233e54c71..7b8f0a69641bc 100644
--- a/arch/arm64/kvm/pmu-direct.c
+++ b/arch/arm64/kvm/pmu-direct.c
@@ -89,6 +89,22 @@ static u64 kvm_vcpu_pmu_guest_counter_mask(struct kvm_vcpu *vcpu)
return 0;
}

+static u64 kvm_vcpu_pmu_reserved_counter_mask(struct kvm_vcpu *vcpu)
+{
+ if (vcpu && kvm_pmu_is_partitioned(vcpu->kvm)) {
+ u64 mask = ARMV8_PMU_CNT_MASK_C;
+ unsigned int hpmn =
+ kvm_arm_pmu_part_hpmn(vcpu->kvm->arch.nr_pmu_counters);
+
+ if (hpmn > 0)
+ mask |= GENMASK_ULL(hpmn - 1, 0);
+
+ return mask;
+ }
+
+ return 0;
+}
+
static void kvm_pmu_set_guest_owned(struct kvm_vcpu *vcpu);

/**
@@ -372,8 +388,12 @@ static u64 kvm_pmu_direct_pmcr_read(struct kvm_vcpu *vcpu)
if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5))
pmcr &= ~ARMV8_PMU_PMCR_LP;

- if (vcpu_has_nv(vcpu) && !vcpu_is_el2(vcpu))
- n = FIELD_GET(MDCR_EL2_HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2));
+ if (vcpu_has_nv(vcpu) && !vcpu_is_el2(vcpu)) {
+ u64 hpmn = FIELD_GET(MDCR_EL2_HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2));
+
+ if (hpmn < n)
+ n = hpmn;
+ }

return u64_replace_bits(pmcr, n, ARMV8_PMU_PMCR_N);
}
@@ -686,6 +706,7 @@ static void kvm_pmu_apply_event_filter(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 reserved_counters;
unsigned long guest_counters;
unsigned long flags;
unsigned long daif;
@@ -710,20 +731,27 @@ static void __kvm_pmu_load(struct kvm_vcpu *vcpu, bool reserve_counters)
return;
}

+ reserved_counters = kvm_vcpu_pmu_reserved_counter_mask(vcpu);
guest_counters = kvm_vcpu_pmu_guest_counter_mask(vcpu);
if (reserve_counters)
- kvm_pmu_set_guest_counters(pmu, guest_counters);
+ kvm_pmu_set_guest_counters(pmu, reserved_counters);

daif = local_daif_save();

/*
* Ensure guest counters, interrupts, and overflow flags are quiesced
* in hardware before lowering MDCR_EL2.HPMN and marking the partition
- * live on this CPU.
+ * live on this CPU. If counter 0 is reserved solely to satisfy HPMN=1
+ * without FEAT_HPMN0, scrub and filter it so it cannot count or leak.
*/
- write_sysreg(guest_counters, pmcntenclr_el0);
- write_sysreg(guest_counters, pmintenclr_el1);
- write_sysreg(guest_counters, pmovsclr_el0);
+ write_sysreg(reserved_counters, pmcntenclr_el0);
+ write_sysreg(reserved_counters, pmintenclr_el1);
+ write_sysreg(reserved_counters, pmovsclr_el0);
+ if (reserved_counters & ~guest_counters) {
+ write_pmevcntrn(0, 0);
+ write_pmevtypern(0, ARMV8_PMU_EXCLUDE_EL0 |
+ ARMV8_PMU_EXCLUDE_EL1);
+ }
isb();

vcpu->arch.pmu.loaded_on_cpu = true;
diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c
index 9d4ad4b7bd8d5..02a1968bd6cb1 100644
--- a/arch/arm64/kvm/pmu.c
+++ b/arch/arm64/kvm/pmu.c
@@ -914,6 +914,13 @@ u64 kvm_pmu_accessible_counter_mask(struct kvm_vcpu *vcpu)
return mask & ~kvm_pmu_hyp_counter_mask(vcpu);
}

+unsigned int kvm_arm_pmu_part_hpmn(unsigned int n)
+{
+ if (!n && !cpus_have_final_cap(ARM64_HAS_HPMN0))
+ return 1;
+ return n;
+}
+
/**
* kvm_vcpu_read_pmcr - Read PMCR_EL0 register for the vCPU
* @vcpu: The vcpu pointer
@@ -923,8 +930,12 @@ u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0);
u64 n = vcpu->kvm->arch.nr_pmu_counters;

- if (vcpu_has_nv(vcpu) && !vcpu_is_el2(vcpu))
- n = FIELD_GET(MDCR_EL2_HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2));
+ if (vcpu_has_nv(vcpu) && !vcpu_is_el2(vcpu)) {
+ u64 hpmn = FIELD_GET(MDCR_EL2_HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2));
+
+ if (hpmn < n)
+ n = hpmn;
+ }

return u64_replace_bits(pmcr, n, ARMV8_PMU_PMCR_N);
}
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 0fe4f593d3f9a..bebf981855040 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -137,6 +137,7 @@ u8 kvm_arm_pmu_get_pmuver_limit(void);
u64 kvm_pmu_evtyper_mask(struct kvm *kvm);
int kvm_arm_set_default_pmu(struct kvm *kvm);
u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm);
+unsigned int kvm_arm_pmu_part_hpmn(unsigned int n);

u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu);
bool kvm_pmu_counter_is_hyp(struct kvm_vcpu *vcpu, unsigned int idx);
@@ -277,6 +278,11 @@ static inline u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm)
return 0;
}

+static inline unsigned int kvm_arm_pmu_part_hpmn(unsigned int n)
+{
+ return n;
+}
+
static inline u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
{
return 0;
--
2.56.1.708.g77570a6a1d-goog