From bead02204e9806807bb290137b1ccabfcb4b16fd Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 13 Nov 2022 16:38:18 +0000 Subject: KVM: arm64: PMU: Align chained counter implementation with architecture pseudocode Ricardo recently pointed out that the PMU chained counter emulation in KVM wasn't quite behaving like the one on actual hardware, in the sense that a chained counter would expose an overflow on both halves of a chained counter, while KVM would only expose the overflow on the top half. The difference is subtle, but significant. What does the architecture say (DDI0087 H.a): - Up to PMUv3p4, all counters but the cycle counter are 32bit - A 32bit counter that overflows generates a CHAIN event on the adjacent counter after exposing its own overflow status - The CHAIN event is accounted if the counter is correctly configured (CHAIN event selected and counter enabled) This all means that our current implementation (which uses 64bit perf events) prevents us from emulating this overflow on the lower half. How to fix this? By implementing the above, to the letter. This largely results in code deletion, removing the notions of "counter pair", "chained counters", and "canonical counter". The code is further restructured to make the CHAIN handling similar to SWINC, as the two are now extremely similar in behaviour. Reported-by: Ricardo Koller Signed-off-by: Marc Zyngier Reviewed-by: Reiji Watanabe Link: https://lore.kernel.org/r/20221113163832.3154370-3-maz@kernel.org --- include/kvm/arm_pmu.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/kvm') diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index c0b868ce6a8f..96b192139a23 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -11,7 +11,6 @@ #include #define ARMV8_PMU_CYCLE_IDX (ARMV8_PMU_MAX_COUNTERS - 1) -#define ARMV8_PMU_MAX_COUNTER_PAIRS ((ARMV8_PMU_MAX_COUNTERS + 1) >> 1) #ifdef CONFIG_HW_PERF_EVENTS @@ -29,7 +28,6 @@ struct kvm_pmu { struct irq_work overflow_work; struct kvm_pmu_events events; struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS]; - DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS); int irq_num; bool created; bool irq_level; -- cgit v1.2.3 From 3d0dba5764b94308b8c4257ad64e383f11ce0c92 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 13 Nov 2022 16:38:26 +0000 Subject: KVM: arm64: PMU: Move the ID_AA64DFR0_EL1.PMUver limit to VM creation As further patches will enable the selection of a PMU revision from userspace, sample the supported PMU revision at VM creation time, rather than building each time the ID_AA64DFR0_EL1 register is accessed. This shouldn't result in any change in behaviour. Reviewed-by: Reiji Watanabe Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221113163832.3154370-11-maz@kernel.org --- arch/arm64/include/asm/kvm_host.h | 4 ++++ arch/arm64/kvm/arm.c | 6 ++++++ arch/arm64/kvm/pmu-emul.c | 11 +++++++++++ arch/arm64/kvm/sys_regs.c | 36 ++++++++++++++++++++++++++++-------- include/kvm/arm_pmu.h | 6 ++++++ 5 files changed, 55 insertions(+), 8 deletions(-) (limited to 'include/kvm') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 45e2136322ba..cc44e3bc528d 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -163,6 +163,10 @@ struct kvm_arch { u8 pfr0_csv2; u8 pfr0_csv3; + struct { + u8 imp:4; + u8 unimp:4; + } dfr0_pmuver; /* Hypercall features firmware registers' descriptor */ struct kvm_smccc_features smccc_feat; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 94d33e296e10..f956aab438c7 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -164,6 +164,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) set_default_spectre(kvm); kvm_arm_init_hypercalls(kvm); + /* + * Initialise the default PMUver before there is a chance to + * create an actual PMU. + */ + kvm->arch.dfr0_pmuver.imp = kvm_arm_pmu_get_pmuver_limit(); + return ret; out_free_stage2_pgd: kvm_free_stage2_pgd(&kvm->arch.mmu); diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 7a945fa6dd03..94ca2d17a4e4 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -1047,3 +1047,14 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) return -ENXIO; } + +u8 kvm_arm_pmu_get_pmuver_limit(void) +{ + u64 tmp; + + tmp = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1); + tmp = cpuid_feature_cap_perfmon_field(tmp, + ID_AA64DFR0_EL1_PMUVer_SHIFT, + ID_AA64DFR0_EL1_PMUVer_V3P4); + return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp); +} diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index f4a7c5abcbca..297b4fcbf969 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1062,6 +1062,27 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu, return true; } +static u8 vcpu_pmuver(const struct kvm_vcpu *vcpu) +{ + if (kvm_vcpu_has_pmu(vcpu)) + return vcpu->kvm->arch.dfr0_pmuver.imp; + + return vcpu->kvm->arch.dfr0_pmuver.unimp; +} + +static u8 pmuver_to_perfmon(u8 pmuver) +{ + switch (pmuver) { + case ID_AA64DFR0_EL1_PMUVer_IMP: + return ID_DFR0_PERFMON_8_0; + case ID_AA64DFR0_EL1_PMUVer_IMP_DEF: + return ID_DFR0_PERFMON_IMP_DEF; + default: + /* Anything ARMv8.1+ and NI have the same value. For now. */ + return pmuver; + } +} + /* Read a sanitised cpufeature ID register by sys_reg_desc */ static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r) { @@ -1111,18 +1132,17 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r /* Limit debug to ARMv8.0 */ val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer); val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer), 6); - /* Limit guests to PMUv3 for ARMv8.4 */ - val = cpuid_feature_cap_perfmon_field(val, - ID_AA64DFR0_EL1_PMUVer_SHIFT, - kvm_vcpu_has_pmu(vcpu) ? ID_AA64DFR0_EL1_PMUVer_V3P4 : 0); + /* Set PMUver to the required version */ + val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer); + val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), + vcpu_pmuver(vcpu)); /* Hide SPE from guests */ val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMSVer); break; case SYS_ID_DFR0_EL1: - /* Limit guests to PMUv3 for ARMv8.4 */ - val = cpuid_feature_cap_perfmon_field(val, - ID_DFR0_PERFMON_SHIFT, - kvm_vcpu_has_pmu(vcpu) ? ID_DFR0_PERFMON_8_4 : 0); + val &= ~ARM64_FEATURE_MASK(ID_DFR0_PERFMON); + val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_DFR0_PERFMON), + pmuver_to_perfmon(vcpu_pmuver(vcpu))); break; } diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 96b192139a23..812f729c9108 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -89,6 +89,8 @@ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu); vcpu->arch.pmu.events = *kvm_get_pmu_events(); \ } while (0) +u8 kvm_arm_pmu_get_pmuver_limit(void); + #else struct kvm_pmu { }; @@ -154,6 +156,10 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) static inline void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {} +static inline u8 kvm_arm_pmu_get_pmuver_limit(void) +{ + return 0; +} #endif -- cgit v1.2.3 From 11af4c37165e36a6090172ded5d06acdf15206da Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 13 Nov 2022 16:38:29 +0000 Subject: KVM: arm64: PMU: Implement PMUv3p5 long counter support PMUv3p5 (which is mandatory with ARMv8.5) comes with some extra features: - All counters are 64bit - The overflow point is controlled by the PMCR_EL0.LP bit Add the required checks in the helpers that control counter width and overflow, as well as the sysreg handling for the LP bit. A new kvm_pmu_is_3p5() helper makes it easy to spot the PMUv3p5 specific handling. Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221113163832.3154370-14-maz@kernel.org --- arch/arm64/kvm/pmu-emul.c | 8 +++++--- arch/arm64/kvm/sys_regs.c | 4 ++++ include/kvm/arm_pmu.h | 7 +++++++ 3 files changed, 16 insertions(+), 3 deletions(-) (limited to 'include/kvm') diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 94ca2d17a4e4..7e25ff73cbba 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -52,13 +52,15 @@ static u32 kvm_pmu_event_mask(struct kvm *kvm) */ static bool kvm_pmu_idx_is_64bit(struct kvm_vcpu *vcpu, u64 select_idx) { - return (select_idx == ARMV8_PMU_CYCLE_IDX); + return (select_idx == ARMV8_PMU_CYCLE_IDX || kvm_pmu_is_3p5(vcpu)); } static bool kvm_pmu_idx_has_64bit_overflow(struct kvm_vcpu *vcpu, u64 select_idx) { - return (select_idx == ARMV8_PMU_CYCLE_IDX && - __vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_LC); + u64 val = __vcpu_sys_reg(vcpu, PMCR_EL0); + + return (select_idx < ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LP)) || + (select_idx == ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LC)); } static bool kvm_pmu_counter_can_chain(struct kvm_vcpu *vcpu, u64 idx) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index b8ac58723459..67eac0f747be 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -654,6 +654,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E); if (!kvm_supports_32bit_el0()) val |= ARMV8_PMU_PMCR_LC; + if (!kvm_pmu_is_3p5(vcpu)) + val &= ~ARMV8_PMU_PMCR_LP; __vcpu_sys_reg(vcpu, r->reg) = val; } @@ -703,6 +705,8 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, val |= p->regval & ARMV8_PMU_PMCR_MASK; if (!kvm_supports_32bit_el0()) val |= ARMV8_PMU_PMCR_LC; + if (!kvm_pmu_is_3p5(vcpu)) + val &= ~ARMV8_PMU_PMCR_LP; __vcpu_sys_reg(vcpu, PMCR_EL0) = val; kvm_pmu_handle_pmcr(vcpu, val); kvm_vcpu_pmu_restore_guest(vcpu); diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 812f729c9108..628775334d5e 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -89,6 +89,12 @@ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu); vcpu->arch.pmu.events = *kvm_get_pmu_events(); \ } while (0) +/* + * Evaluates as true when emulating PMUv3p5, and false otherwise. + */ +#define kvm_pmu_is_3p5(vcpu) \ + (vcpu->kvm->arch.dfr0_pmuver.imp >= ID_AA64DFR0_EL1_PMUVer_V3P5) + u8 kvm_arm_pmu_get_pmuver_limit(void); #else @@ -153,6 +159,7 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) } #define kvm_vcpu_has_pmu(vcpu) ({ false; }) +#define kvm_pmu_is_3p5(vcpu) ({ false; }) static inline void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {} -- cgit v1.2.3