Save and restore the guest PMU registers that are untrapped when the PMU is partitioned: - PMEVCNTRn_EL0 - PMCCNTR_EL0 - PMSELR_EL0 (when MDCR_EL2.TPM is clear) - PMUSERENR_EL0 (when MDCR_EL2.TPM is clear) - PMCR_EL0 - PMCNTENSET_EL0 / PMCNTENCLR_EL0 - PMINTENSET_EL1 / PMINTENCLR_EL1 Mask counter bitmaps to guest-reserved counters so host-owned counters in HPMN..N-1 are left untouched. Clear hardware guest overflow flags on load before enabling PMINTENSET_EL1 to avoid spurious interrupts, flush pending hardware guest overflow flags into shadow PMOVSSET_EL0 on put, and restore physical PMCR_EL0.E from MDCR_EL2.HPME on put so active host perf events continue counting. PMEVTYPER_EL0 and PMCCFILTR_EL0 are loaded in the next patch after applying the KVM PMU event filter. A subsequent patch makes these swaps lazy until the guest enables the PMU. Signed-off-by: Colton Lewis --- arch/arm64/kvm/arm.c | 4 +- arch/arm64/kvm/pmu-direct.c | 175 ++++++++++++++++++++++++++++++++++++ include/kvm/arm_pmu.h | 6 +- 3 files changed, 183 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 157bf4b812020..fc420d8f0e4fe 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -767,6 +767,7 @@ static void vhe_vcpu_load(struct kvm_vcpu *vcpu) kvm_vcpu_load_fgt(vcpu); kvm_vcpu_load_vhe(vcpu); kvm_arch_vcpu_load_fp(vcpu); + kvm_pmu_load(vcpu); kvm_vcpu_pmu_restore_guest(vcpu); vcpu_load_pvtime(vcpu); @@ -821,12 +822,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void vhe_vcpu_put(struct kvm_vcpu *vcpu) { + kvm_pmu_put(vcpu); + kvm_vcpu_pmu_restore_host(vcpu); kvm_vcpu_put_debug(vcpu); kvm_arch_vcpu_put_fp(vcpu); kvm_vcpu_put_vhe(vcpu); kvm_timer_vcpu_put(vcpu); kvm_vgic_put(vcpu); - kvm_vcpu_pmu_restore_host(vcpu); if (vcpu_has_nv(vcpu)) kvm_vcpu_put_hw_mmu(vcpu); diff --git a/arch/arm64/kvm/pmu-direct.c b/arch/arm64/kvm/pmu-direct.c index 13f5bcc2a9084..5c8a8c42e353d 100644 --- a/arch/arm64/kvm/pmu-direct.c +++ b/arch/arm64/kvm/pmu-direct.c @@ -344,3 +344,178 @@ u64 kvm_pmu_guest_counter_mask(void) { return kvm_vcpu_pmu_guest_counter_mask(kvm_get_running_vcpu()); } + +/** + * 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) +{ + struct arm_pmu *pmu = vcpu->kvm->arch.arm_pmu; + unsigned long guest_counters; + unsigned long flags; + u64 mask; + u8 i; + u64 val; + + /* + * If we aren't guest-owned then we know the guest isn't using + * the PMU anyway, so no need to bother with the swap. + */ + if (!kvm_pmu_is_partitioned(vcpu->kvm) || !vcpu->wants_to_run || !pmu) + return; + + local_irq_save(flags); + if (!cpumask_test_cpu(smp_processor_id(), &pmu->supported_cpus)) { + local_irq_restore(flags); + return; + } + + guest_counters = kvm_vcpu_pmu_guest_counter_mask(vcpu); + + for_each_set_bit(i, &guest_counters, ARMPMU_MAX_HWEVENTS) { + val = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i); + + if (i == ARMV8_PMU_CYCLE_IDX) + write_pmccntr(val); + else + write_pmevcntrn(i, val); + } + + if (!(vcpu->arch.mdcr_el2 & MDCR_EL2_TPM)) { + val = __vcpu_sys_reg(vcpu, PMSELR_EL0); + write_sysreg(val, pmselr_el0); + + val = __vcpu_sys_reg(vcpu, PMUSERENR_EL0) & + ARMV8_PMU_USERENR_MASK; + write_sysreg(val, pmuserenr_el0); + } + + /* Save only the stateful writable bits. */ + val = __vcpu_sys_reg(vcpu, PMCR_EL0); + mask = ARMV8_PMU_PMCR_MASK & + ~(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C); + if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)) + mask &= ~ARMV8_PMU_PMCR_LP; + write_sysreg(val & mask, pmcr_el0); + + /* + * When handling these: + * 1. Apply only the bits for guest counters (indicated by mask) + * 2. Use the different registers for set and clear + */ + mask = guest_counters; + + /* + * Clear the hardware overflow flags so there is no chance of + * creating spurious interrupts. The hardware here is never + * the canonical version anyway. + */ + write_sysreg(mask, pmovsclr_el0); + isb(); + + val = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); + write_sysreg(val & mask, pmcntenset_el0); + write_sysreg(~val & mask, pmcntenclr_el0); + + val = __vcpu_sys_reg(vcpu, PMINTENSET_EL1); + write_sysreg(val & mask, pmintenset_el1); + write_sysreg(~val & mask, pmintenclr_el1); + + local_irq_restore(flags); +} + +/** + * 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) +{ + struct arm_pmu *pmu = vcpu->kvm->arch.arm_pmu; + unsigned long guest_counters; + unsigned long flags; + u64 pmcr_mask; + u64 mask; + u8 i; + u64 val; + + /* + * If we aren't guest-owned then we know the guest is not + * accessing the PMU anyway, so no need to bother with the + * swap. + */ + if (!kvm_pmu_is_partitioned(vcpu->kvm) || !vcpu->wants_to_run || !pmu) + return; + + local_irq_save(flags); + if (!cpumask_test_cpu(smp_processor_id(), &pmu->supported_cpus)) { + local_irq_restore(flags); + return; + } + + guest_counters = kvm_vcpu_pmu_guest_counter_mask(vcpu); + mask = guest_counters; + + /* Mask these to only save the guest relevant bits. */ + val = read_sysreg(pmcntenset_el0); + __vcpu_assign_sys_reg(vcpu, PMCNTENSET_EL0, val & mask); + + val = read_sysreg(pmintenset_el1); + __vcpu_assign_sys_reg(vcpu, PMINTENSET_EL1, val & mask); + + /* Stop guest counters and disable interrupts in hardware first. */ + write_sysreg(mask, pmcntenclr_el0); + write_sysreg(mask, pmintenclr_el1); + isb(); + + for_each_set_bit(i, &guest_counters, ARMPMU_MAX_HWEVENTS) { + if (i == ARMV8_PMU_CYCLE_IDX) { + val = read_pmccntr(); + write_pmccntr(0); + } else { + val = read_pmevcntrn(i); + write_pmevcntrn(i, 0); + } + + __vcpu_assign_sys_reg(vcpu, PMEVCNTR0_EL0 + i, val); + } + + if (!(vcpu->arch.mdcr_el2 & MDCR_EL2_TPM)) { + val = read_sysreg(pmselr_el0); + __vcpu_assign_sys_reg(vcpu, PMSELR_EL0, val); + write_sysreg(0, pmselr_el0); + + val = read_sysreg(pmuserenr_el0) & ARMV8_PMU_USERENR_MASK; + __vcpu_assign_sys_reg(vcpu, PMUSERENR_EL0, val); + write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0); + } + + val = read_sysreg(pmcr_el0); + pmcr_mask = ARMV8_PMU_PMCR_MASK; + if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)) + pmcr_mask &= ~ARMV8_PMU_PMCR_LP; + __vcpu_rmw_sys_reg(vcpu, PMCR_EL0, &=, ~ARMV8_PMU_PMCR_MASK); + __vcpu_rmw_sys_reg(vcpu, PMCR_EL0, |=, val & pmcr_mask); + + val = ARMV8_PMU_PMCR_LC; + if (pmu->pmuver >= ID_AA64DFR0_EL1_PMUVer_V3P5) + val |= ARMV8_PMU_PMCR_LP; + if (vcpu->arch.mdcr_el2 & MDCR_EL2_HPME) + val |= ARMV8_PMU_PMCR_E; + write_sysreg(val, pmcr_el0); + + /* Save pending guest hardware overflows. */ + val = read_sysreg(pmovsset_el0); + __vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, |=, val & mask); + write_sysreg(val & mask, pmovsclr_el0); + + local_irq_restore(flags); +} diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 276ab74fa0208..4580f62234128 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -102,6 +102,9 @@ 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_guest_counter_mask(void); +void kvm_pmu_load(struct kvm_vcpu *vcpu); +void kvm_pmu_put(struct kvm_vcpu *vcpu); + /* * Updates the vcpu's view of the pmu events for this cpu. * Must be called before every vcpu run after disabling interrupts, to ensure @@ -146,10 +149,11 @@ static inline u64 kvm_pmu_direct_reg_read(struct kvm_vcpu *vcpu, { return 0; } - static inline void kvm_pmu_direct_reg_write(struct kvm_vcpu *vcpu, unsigned int reg, u64 val, bool set) {} +static inline void kvm_pmu_load(struct kvm_vcpu *vcpu) {} +static inline void kvm_pmu_put(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) {} static inline void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu, -- 2.56.1.708.g77570a6a1d-goog