[PATCH v10 28/33] KVM: arm64: Emulate trapped PMSWINC_EL0 writes for Partitioned PMU

From: Colton Lewis

Date: Thu Nov 19 2026 - 13:55:21 EST


Even with a Partitioned PMU, guest writes to PMSWINC_EL0 trap to EL2 in
four cases:
1. Hosts without FEAT_FGT, where MDCR_EL2.TPM remains set.
2. Before lazy PMU activation (VCPU_PMU_ACCESS_FREE, MDCR_EL2.TPM == 1).
3. Nested L2 execution when L1 sub-partitions counters (vHPMN < N_L1),
where MDCR_EL2.TPM is forced to protect L1's hypervisor counters.
4. Nested L1 execution when L1 sub-partitions counters (vHPMN < N_L1),
where HDFGWTR_EL2.PMSWINC_EL0 must trap software increments so an
even counter at vHPMN - 1 cannot chain across the sub-partition
boundary into L1 counter vHPMN in hardware, and so ovf32_mask
counter biasing is preserved.

Trapped PMSWINC_EL0 writes cannot simply execute MSR PMSWINC_EL0 at
physical EL2 because L0 runs with physical MDCR_EL2.HPMD == 1 and clears
PMEVTYPER<n>_EL0.NSH on guest counters, causing hardware to ignore the
software increment (and when not loaded on the CPU, guest counters live
only in sys_regs[]).

Update kvm_pmu_counter_increment() and kvm_pmu_counter_can_chain() in
arch/arm64/kvm/pmu-emul.c to check per-counter enablement
(kvm_pmu_counter_is_enabled(), covering both PMCR_EL0.E and
MDCR_EL2.HPME), current guest EL filtering for SW_INCR, and
nr_pmu_counters / sub-partition chaining boundaries. Reuse
kvm_pmu_software_increment() from kvm_pmu_direct_swinc() by flushing
live hardware state if loaded, applying the software increment to
sys_regs[], and reloading hardware.

Signed-off-by: Colton Lewis <coltonlewis@xxxxxxxxxx>
---
arch/arm64/kvm/config.c | 2 +-
arch/arm64/kvm/pmu-direct.c | 34 ++++++++++
arch/arm64/kvm/pmu-emul.c | 120 +++++++++++++++++++++---------------
arch/arm64/kvm/sys_regs.c | 5 +-
include/kvm/arm_pmu.h | 3 +
5 files changed, 113 insertions(+), 51 deletions(-)

diff --git a/arch/arm64/kvm/config.c b/arch/arm64/kvm/config.c
index a523dde1b57a7..0ec74e45fdbf6 100644
--- a/arch/arm64/kvm/config.c
+++ b/arch/arm64/kvm/config.c
@@ -1826,7 +1826,7 @@ static void __compute_hdfgwtr(struct kvm_vcpu *vcpu)
set |= HDFGWTR_EL2_PMUSERENR_EL0;

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

diff --git a/arch/arm64/kvm/pmu-direct.c b/arch/arm64/kvm/pmu-direct.c
index b7bec06b36b0a..6382233e54c71 100644
--- a/arch/arm64/kvm/pmu-direct.c
+++ b/arch/arm64/kvm/pmu-direct.c
@@ -931,6 +931,40 @@ void kvm_pmu_put(struct kvm_vcpu *vcpu)
__kvm_pmu_put(vcpu, release);
}

+/**
+ * kvm_pmu_direct_swinc() - Emulate trapped PMSWINC_EL0 writes
+ * @vcpu: Pointer to vcpu struct
+ * @val: Accessible counter bitmask written to PMSWINC_EL0
+ *
+ * Executing MSR PMSWINC_EL0 at physical EL2 is ignored by hardware because
+ * physical MDCR_EL2.HPMD is set and guest PMEVTYPER<n>_EL0.NSH is cleared.
+ * Flush live hardware state if loaded, apply kvm_pmu_software_increment(),
+ * and reload hardware.
+ */
+void kvm_pmu_direct_swinc(struct kvm_vcpu *vcpu, u64 val)
+{
+ bool was_loaded;
+
+ guard(preempt)();
+
+ val &= kvm_vcpu_pmu_guest_counter_mask(vcpu) &
+ ~BIT_ULL(ARMV8_PMU_CYCLE_IDX);
+ if (!val)
+ return;
+
+ was_loaded = kvm_pmu_part_on_cpu(vcpu);
+ if (was_loaded)
+ __kvm_pmu_put(vcpu, false);
+
+ kvm_pmu_software_increment(vcpu, val);
+
+ if (was_loaded)
+ __kvm_pmu_load(vcpu, false);
+
+ if (kvm_pmu_part_overflow_status(vcpu))
+ kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
+}
+
/**
* kvm_pmu_reload_part() - Reload partitioned PMU traps, filters, and state
* @vcpu: Pointer to struct kvm_vcpu
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index a72bdc5a0b3ea..b9096e5a4f11d 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -19,7 +19,6 @@

static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc);
static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc);
-static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc);

static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc)
{
@@ -48,6 +47,9 @@ static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc)
struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
u64 val = kvm_vcpu_read_pmcr(vcpu);

+ if (!kvm_pmc_is_64bit(pmc))
+ return false;
+
if (kvm_pmu_counter_is_hyp(vcpu, pmc->idx))
return __vcpu_sys_reg(vcpu, MDCR_EL2) & MDCR_EL2_HLP;

@@ -57,8 +59,13 @@ static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc)

static bool kvm_pmu_counter_can_chain(struct kvm_pmc *pmc)
{
- return (!(pmc->idx & 1) && (pmc->idx + 1) < ARMV8_PMU_CYCLE_IDX &&
- !kvm_pmc_has_64bit_overflow(pmc));
+ struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+
+ return !(pmc->idx & 1) &&
+ (pmc->idx + 1) < vcpu->kvm->arch.nr_pmu_counters &&
+ kvm_pmu_counter_is_hyp(vcpu, pmc->idx) ==
+ kvm_pmu_counter_is_hyp(vcpu, pmc->idx + 1) &&
+ !kvm_pmc_has_64bit_overflow(pmc);
}

static u32 counter_index_to_reg(u64 idx)
@@ -76,6 +83,60 @@ static u64 kvm_pmc_read_evtreg(const struct kvm_pmc *pmc)
return __vcpu_sys_reg(kvm_pmc_to_vcpu(pmc), counter_index_to_evtreg(pmc->idx));
}

+static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc)
+{
+ struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+ unsigned int mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2);
+
+ if (!(__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx)))
+ return false;
+
+ if (kvm_pmu_counter_is_hyp(vcpu, pmc->idx))
+ return mdcr & MDCR_EL2_HPME;
+
+ return kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E;
+}
+
+static bool kvm_pmc_counts_at_el0(struct kvm_pmc *pmc)
+{
+ u64 evtreg = kvm_pmc_read_evtreg(pmc);
+ bool nsu = evtreg & ARMV8_PMU_EXCLUDE_NS_EL0;
+ bool u = evtreg & ARMV8_PMU_EXCLUDE_EL0;
+
+ return u == nsu;
+}
+
+static bool kvm_pmc_counts_at_el1(struct kvm_pmc *pmc)
+{
+ u64 evtreg = kvm_pmc_read_evtreg(pmc);
+ bool nsk = evtreg & ARMV8_PMU_EXCLUDE_NS_EL1;
+ bool p = evtreg & ARMV8_PMU_EXCLUDE_EL1;
+
+ return p == nsk;
+}
+
+static bool kvm_pmc_counts_at_el2(struct kvm_pmc *pmc)
+{
+ struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+ u64 mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2);
+
+ if (!kvm_pmu_counter_is_hyp(vcpu, pmc->idx) && (mdcr & MDCR_EL2_HPMD))
+ return false;
+
+ return kvm_pmc_read_evtreg(pmc) & ARMV8_PMU_INCLUDE_EL2;
+}
+
+static bool kvm_pmc_counts_at_current_el(struct kvm_pmc *pmc)
+{
+ struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+
+ if (!vcpu_mode_priv(vcpu))
+ return kvm_pmc_counts_at_el0(pmc);
+ if (unlikely(is_hyp_ctxt(vcpu)))
+ return kvm_pmc_counts_at_el2(pmc);
+ return kvm_pmc_counts_at_el1(pmc);
+}
+
static u64 kvm_pmu_get_pmc_value(struct kvm_pmc *pmc)
{
struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
@@ -321,9 +382,6 @@ static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu,
{
int i;

- if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E))
- return;
-
/* Weed out disabled counters */
mask &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);

@@ -331,12 +389,19 @@ static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu,
struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i);
u64 type, reg;

+ if (!kvm_pmu_counter_is_enabled(pmc))
+ continue;
+
/* Filter on event type */
type = __vcpu_sys_reg(vcpu, counter_index_to_evtreg(i));
type &= kvm_pmu_event_mask(vcpu->kvm);
if (type != event)
continue;

+ if (event == ARMV8_PMUV3_PERFCTR_SW_INCR &&
+ !kvm_pmc_counts_at_current_el(pmc))
+ continue;
+
/* Increment this counter */
reg = __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) + 1;
if (!kvm_pmc_is_64bit(pmc))
@@ -454,49 +519,6 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
}
}

-static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc)
-{
- struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
- unsigned int mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2);
-
- if (!(__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx)))
- return false;
-
- if (kvm_pmu_counter_is_hyp(vcpu, pmc->idx))
- return mdcr & MDCR_EL2_HPME;
-
- return kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E;
-}
-
-static bool kvm_pmc_counts_at_el0(struct kvm_pmc *pmc)
-{
- u64 evtreg = kvm_pmc_read_evtreg(pmc);
- bool nsu = evtreg & ARMV8_PMU_EXCLUDE_NS_EL0;
- bool u = evtreg & ARMV8_PMU_EXCLUDE_EL0;
-
- return u == nsu;
-}
-
-static bool kvm_pmc_counts_at_el1(struct kvm_pmc *pmc)
-{
- u64 evtreg = kvm_pmc_read_evtreg(pmc);
- bool nsk = evtreg & ARMV8_PMU_EXCLUDE_NS_EL1;
- bool p = evtreg & ARMV8_PMU_EXCLUDE_EL1;
-
- return p == nsk;
-}
-
-static bool kvm_pmc_counts_at_el2(struct kvm_pmc *pmc)
-{
- struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
- u64 mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2);
-
- if (!kvm_pmu_counter_is_hyp(vcpu, pmc->idx) && (mdcr & MDCR_EL2_HPMD))
- return false;
-
- return kvm_pmc_read_evtreg(pmc) & ARMV8_PMU_INCLUDE_EL2;
-}
-
static int kvm_map_pmu_event(struct kvm *kvm, unsigned int eventsel)
{
struct arm_pmu *pmu = kvm->arch.arm_pmu;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 24dd878fb58c4..4967954f42b01 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1543,7 +1543,10 @@ static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
return false;

mask = kvm_pmu_accessible_counter_mask(vcpu);
- kvm_pmu_software_increment(vcpu, p->regval & mask);
+ if (kvm_pmu_is_partitioned(vcpu->kvm))
+ kvm_pmu_direct_swinc(vcpu, p->regval & mask);
+ else
+ kvm_pmu_software_increment(vcpu, p->regval & mask);
return true;
}

diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 13e9230c9c714..0fe4f593d3f9a 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -110,6 +110,7 @@ u64 kvm_pmu_direct_reg_read(struct kvm_vcpu *vcpu, unsigned int reg);
void kvm_pmu_direct_reg_write(struct kvm_vcpu *vcpu, unsigned int reg,
u64 val, bool set);
u64 kvm_pmu_part_ovf32_mask(struct kvm_vcpu *vcpu);
+void kvm_pmu_direct_swinc(struct kvm_vcpu *vcpu, u64 val);
void kvm_pmu_reload_part(struct kvm_vcpu *vcpu);
u64 kvm_pmu_guest_counter_mask(void);
void kvm_pmu_load(struct kvm_vcpu *vcpu);
@@ -179,6 +180,8 @@ static inline u64 kvm_pmu_part_ovf32_mask(struct kvm_vcpu *vcpu)
{
return 0;
}
+
+static inline void kvm_pmu_direct_swinc(struct kvm_vcpu *vcpu, u64 val) {}
static inline void kvm_pmu_reload_part(struct kvm_vcpu *vcpu) {}
static inline void kvm_pmu_load(struct kvm_vcpu *vcpu) {}
static inline void kvm_pmu_put(struct kvm_vcpu *vcpu) {}
--
2.56.1.708.g77570a6a1d-goog