diff options
author | Oliver Upton <oliver.upton@linux.dev> | 2023-10-30 23:24:07 +0300 |
---|---|---|
committer | Oliver Upton <oliver.upton@linux.dev> | 2023-10-30 23:24:19 +0300 |
commit | 123f42f0ad6815014f54d0cc6eb9039c46ee2907 (patch) | |
tree | de36850d1b225790272b9690650f18d6384830a5 /arch/arm64 | |
parent | 53ce49ea75602b51a1feb3844d535ced42b2d8c2 (diff) | |
parent | 62708be351fe7b06be6f6fd30e95c94095bf21d3 (diff) | |
download | linux-123f42f0ad6815014f54d0cc6eb9039c46ee2907.tar.xz |
Merge branch kvm-arm64/pmu_pmcr_n into kvmarm/next
* kvm-arm64/pmu_pmcr_n:
: User-defined PMC limit, courtesy Raghavendra Rao Ananta
:
: Certain VMMs may want to reserve some PMCs for host use while running a
: KVM guest. This was a bit difficult before, as KVM advertised all
: supported counters to the guest. Userspace can now limit the number of
: advertised PMCs by writing to PMCR_EL0.N, as KVM's sysreg and PMU
: emulation enforce the specified limit for handling guest accesses.
KVM: selftests: aarch64: vPMU test for validating user accesses
KVM: selftests: aarch64: vPMU register test for unimplemented counters
KVM: selftests: aarch64: vPMU register test for implemented counters
KVM: selftests: aarch64: Introduce vpmu_counter_access test
tools: Import arm_pmuv3.h
KVM: arm64: PMU: Allow userspace to limit PMCR_EL0.N for the guest
KVM: arm64: Sanitize PM{C,I}NTEN{SET,CLR}, PMOVS{SET,CLR} before first run
KVM: arm64: Add {get,set}_user for PM{C,I}NTEN{SET,CLR}, PMOVS{SET,CLR}
KVM: arm64: PMU: Set PMCR_EL0.N for vCPU based on the associated PMU
KVM: arm64: PMU: Add a helper to read a vCPU's PMCR_EL0
KVM: arm64: Select default PMU in KVM_ARM_VCPU_INIT handler
KVM: arm64: PMU: Introduce helpers to set the guest's PMU
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Diffstat (limited to 'arch/arm64')
-rw-r--r-- | arch/arm64/include/asm/kvm_host.h | 3 | ||||
-rw-r--r-- | arch/arm64/kvm/arm.c | 22 | ||||
-rw-r--r-- | arch/arm64/kvm/pmu-emul.c | 107 | ||||
-rw-r--r-- | arch/arm64/kvm/sys_regs.c | 127 |
4 files changed, 204 insertions, 55 deletions
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 846a7706e925..5653d3553e3e 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -290,6 +290,9 @@ struct kvm_arch { cpumask_var_t supported_cpus; + /* PMCR_EL0.N value for the guest */ + u8 pmcr_n; + /* Hypercall features firmware registers' descriptor */ struct kvm_smccc_features smccc_feat; struct maple_tree smccc_filter; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index c6cad400490f..317964bad1e1 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -857,8 +857,7 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_RELOAD_PMU, vcpu)) - kvm_pmu_handle_pmcr(vcpu, - __vcpu_sys_reg(vcpu, PMCR_EL0)); + kvm_vcpu_reload_pmu(vcpu); if (kvm_check_request(KVM_REQ_RESYNC_PMU_EL0, vcpu)) kvm_vcpu_pmu_restore_guest(vcpu); @@ -1319,6 +1318,21 @@ static bool kvm_vcpu_init_changed(struct kvm_vcpu *vcpu, KVM_VCPU_MAX_FEATURES); } +static int kvm_setup_vcpu(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + int ret = 0; + + /* + * When the vCPU has a PMU, but no PMU is set for the guest + * yet, set the default one. + */ + if (kvm_vcpu_has_pmu(vcpu) && !kvm->arch.arm_pmu) + ret = kvm_arm_set_default_pmu(kvm); + + return ret; +} + static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { @@ -1334,6 +1348,10 @@ static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu, bitmap_copy(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES); + ret = kvm_setup_vcpu(vcpu); + if (ret) + goto out_unlock; + /* Now we know what it is, we can reset it. */ kvm_reset_vcpu(vcpu); diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 845993bab9d2..fe99b3dab6ce 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -89,7 +89,7 @@ static bool kvm_pmc_is_64bit(struct kvm_pmc *pmc) static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc) { - u64 val = __vcpu_sys_reg(kvm_pmc_to_vcpu(pmc), PMCR_EL0); + u64 val = kvm_vcpu_read_pmcr(kvm_pmc_to_vcpu(pmc)); return (pmc->idx < ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LP)) || (pmc->idx == ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LC)); @@ -267,7 +267,7 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu) { - u64 val = __vcpu_sys_reg(vcpu, PMCR_EL0) >> ARMV8_PMU_PMCR_N_SHIFT; + u64 val = kvm_vcpu_read_pmcr(vcpu) >> ARMV8_PMU_PMCR_N_SHIFT; val &= ARMV8_PMU_PMCR_N_MASK; if (val == 0) @@ -289,7 +289,7 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) if (!kvm_vcpu_has_pmu(vcpu)) return; - if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) || !val) + if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) || !val) return; for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { @@ -341,7 +341,7 @@ static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu) { u64 reg = 0; - if ((__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) { + if ((kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) { reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0); reg &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1); @@ -443,7 +443,7 @@ static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu, { int i; - if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) + if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) return; /* Weed out disabled counters */ @@ -586,7 +586,7 @@ 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); - return (__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) && + return (kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) && (__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx)); } @@ -735,10 +735,9 @@ static struct arm_pmu *kvm_pmu_probe_armpmu(void) * It is still necessary to get a valid cpu, though, to probe for the * default PMU instance as userspace is not required to specify a PMU * type. In order to uphold the preexisting behavior KVM selects the - * PMU instance for the core where the first call to the - * KVM_ARM_VCPU_PMU_V3_CTRL attribute group occurs. A dependent use case - * would be a user with disdain of all things big.LITTLE that affines - * the VMM to a particular cluster of cores. + * PMU instance for the core during vcpu init. A dependent use + * case would be a user with disdain of all things big.LITTLE that + * affines the VMM to a particular cluster of cores. * * In any case, userspace should just do the sane thing and use the UAPI * to select a PMU type directly. But, be wary of the baggage being @@ -804,6 +803,17 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) return val & mask; } +void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) +{ + u64 mask = kvm_pmu_valid_counter_mask(vcpu); + + kvm_pmu_handle_pmcr(vcpu, kvm_vcpu_read_pmcr(vcpu)); + + __vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask; + __vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask; + __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask; +} + int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) { if (!kvm_vcpu_has_pmu(vcpu)) @@ -892,6 +902,52 @@ static bool pmu_irq_is_valid(struct kvm *kvm, int irq) return true; } +/** + * kvm_arm_pmu_get_max_counters - Return the max number of PMU counters. + * @kvm: The kvm pointer + */ +u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm) +{ + struct arm_pmu *arm_pmu = kvm->arch.arm_pmu; + + /* + * The arm_pmu->num_events considers the cycle counter as well. + * Ignore that and return only the general-purpose counters. + */ + return arm_pmu->num_events - 1; +} + +static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu) +{ + lockdep_assert_held(&kvm->arch.config_lock); + + kvm->arch.arm_pmu = arm_pmu; + kvm->arch.pmcr_n = kvm_arm_pmu_get_max_counters(kvm); +} + +/** + * kvm_arm_set_default_pmu - No PMU set, get the default one. + * @kvm: The kvm pointer + * + * The observant among you will notice that the supported_cpus + * mask does not get updated for the default PMU even though it + * is quite possible the selected instance supports only a + * subset of cores in the system. This is intentional, and + * upholds the preexisting behavior on heterogeneous systems + * where vCPUs can be scheduled on any core but the guest + * counters could stop working. + */ +int kvm_arm_set_default_pmu(struct kvm *kvm) +{ + struct arm_pmu *arm_pmu = kvm_pmu_probe_armpmu(); + + if (!arm_pmu) + return -ENODEV; + + kvm_arm_set_pmu(kvm, arm_pmu); + return 0; +} + static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id) { struct kvm *kvm = vcpu->kvm; @@ -911,7 +967,7 @@ static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id) break; } - kvm->arch.arm_pmu = arm_pmu; + kvm_arm_set_pmu(kvm, arm_pmu); cpumask_copy(kvm->arch.supported_cpus, &arm_pmu->supported_cpus); ret = 0; break; @@ -934,23 +990,6 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) if (vcpu->arch.pmu.created) return -EBUSY; - if (!kvm->arch.arm_pmu) { - /* - * No PMU set, get the default one. - * - * The observant among you will notice that the supported_cpus - * mask does not get updated for the default PMU even though it - * is quite possible the selected instance supports only a - * subset of cores in the system. This is intentional, and - * upholds the preexisting behavior on heterogeneous systems - * where vCPUs can be scheduled on any core but the guest - * counters could stop working. - */ - kvm->arch.arm_pmu = kvm_pmu_probe_armpmu(); - if (!kvm->arch.arm_pmu) - return -ENODEV; - } - switch (attr->attr) { case KVM_ARM_VCPU_PMU_V3_IRQ: { int __user *uaddr = (int __user *)(long)attr->addr; @@ -1090,3 +1129,15 @@ u8 kvm_arm_pmu_get_pmuver_limit(void) ID_AA64DFR0_EL1_PMUVer_V3P5); return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp); } + +/** + * kvm_vcpu_read_pmcr - Read PMCR_EL0 register for the vCPU + * @vcpu: The vcpu pointer + */ +u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu) +{ + u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0) & + ~(ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT); + + return pmcr | ((u64)vcpu->kvm->arch.pmcr_n << ARMV8_PMU_PMCR_N_SHIFT); +} diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index d541ce9f48b9..1a21c526e5e2 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -719,14 +719,9 @@ static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu, static u64 reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { - u64 n, mask = BIT(ARMV8_PMU_CYCLE_IDX); + u64 mask = BIT(ARMV8_PMU_CYCLE_IDX); + u8 n = vcpu->kvm->arch.pmcr_n; - /* No PMU available, any PMU reg may UNDEF... */ - if (!kvm_arm_support_pmu_v3()) - return 0; - - n = read_sysreg(pmcr_el0) >> ARMV8_PMU_PMCR_N_SHIFT; - n &= ARMV8_PMU_PMCR_N_MASK; if (n) mask |= GENMASK(n - 1, 0); @@ -766,17 +761,15 @@ static u64 reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) static u64 reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { - u64 pmcr; - - /* No PMU available, PMCR_EL0 may UNDEF... */ - if (!kvm_arm_support_pmu_v3()) - return 0; + u64 pmcr = 0; - /* Only preserve PMCR_EL0.N, and reset the rest to 0 */ - pmcr = read_sysreg(pmcr_el0) & (ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT); if (!kvm_supports_32bit_el0()) pmcr |= ARMV8_PMU_PMCR_LC; + /* + * The value of PMCR.N field is included when the + * vCPU register is read via kvm_vcpu_read_pmcr(). + */ __vcpu_sys_reg(vcpu, r->reg) = pmcr; return __vcpu_sys_reg(vcpu, r->reg); @@ -826,7 +819,7 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, * Only update writeable bits of PMCR (continuing into * kvm_pmu_handle_pmcr() as well) */ - val = __vcpu_sys_reg(vcpu, PMCR_EL0); + val = kvm_vcpu_read_pmcr(vcpu); val &= ~ARMV8_PMU_PMCR_MASK; val |= p->regval & ARMV8_PMU_PMCR_MASK; if (!kvm_supports_32bit_el0()) @@ -834,7 +827,7 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, kvm_pmu_handle_pmcr(vcpu, val); } else { /* PMCR.P & PMCR.C are RAZ */ - val = __vcpu_sys_reg(vcpu, PMCR_EL0) + val = kvm_vcpu_read_pmcr(vcpu) & ~(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C); p->regval = val; } @@ -883,7 +876,7 @@ static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx) { u64 pmcr, val; - pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0); + pmcr = kvm_vcpu_read_pmcr(vcpu); val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK; if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) { kvm_inject_undefined(vcpu); @@ -998,6 +991,39 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return true; } +static int set_pmreg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) +{ + bool set; + + val &= kvm_pmu_valid_counter_mask(vcpu); + + switch (r->reg) { + case PMOVSSET_EL0: + /* CRm[1] being set indicates a SET register, and CLR otherwise */ + set = r->CRm & 2; + break; + default: + /* Op2[0] being set indicates a SET register, and CLR otherwise */ + set = r->Op2 & 1; + break; + } + + if (set) + __vcpu_sys_reg(vcpu, r->reg) |= val; + else + __vcpu_sys_reg(vcpu, r->reg) &= ~val; + + return 0; +} + +static int get_pmreg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) +{ + u64 mask = kvm_pmu_valid_counter_mask(vcpu); + + *val = __vcpu_sys_reg(vcpu, r->reg) & mask; + return 0; +} + static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { @@ -1107,6 +1133,51 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return true; } +static int get_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, + u64 *val) +{ + *val = kvm_vcpu_read_pmcr(vcpu); + return 0; +} + +static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, + u64 val) +{ + u8 new_n = (val >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK; + struct kvm *kvm = vcpu->kvm; + + mutex_lock(&kvm->arch.config_lock); + + /* + * The vCPU can't have more counters than the PMU hardware + * implements. Ignore this error to maintain compatibility + * with the existing KVM behavior. + */ + if (!kvm_vm_has_ran_once(kvm) && + new_n <= kvm_arm_pmu_get_max_counters(kvm)) + kvm->arch.pmcr_n = new_n; + + mutex_unlock(&kvm->arch.config_lock); + + /* + * Ignore writes to RES0 bits, read only bits that are cleared on + * vCPU reset, and writable bits that KVM doesn't support yet. + * (i.e. only PMCR.N and bits [7:0] are mutable from userspace) + * The LP bit is RES0 when FEAT_PMUv3p5 is not supported on the vCPU. + * But, we leave the bit as it is here, as the vCPU's PMUver might + * be changed later (NOTE: the bit will be cleared on first vCPU run + * if necessary). + */ + val &= ARMV8_PMU_PMCR_MASK; + + /* The LC bit is RES1 when AArch32 is not supported */ + if (!kvm_supports_32bit_el0()) + val |= ARMV8_PMU_PMCR_LC; + + __vcpu_sys_reg(vcpu, r->reg) = val; + return 0; +} + /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */ #define DBG_BCR_BVR_WCR_WVR_EL1(n) \ { SYS_DESC(SYS_DBGBVRn_EL1(n)), \ @@ -2188,9 +2259,11 @@ static const struct sys_reg_desc sys_reg_descs[] = { /* PMBIDR_EL1 is not trapped */ { PMU_SYS_REG(PMINTENSET_EL1), - .access = access_pminten, .reg = PMINTENSET_EL1 }, + .access = access_pminten, .reg = PMINTENSET_EL1, + .get_user = get_pmreg, .set_user = set_pmreg }, { PMU_SYS_REG(PMINTENCLR_EL1), - .access = access_pminten, .reg = PMINTENSET_EL1 }, + .access = access_pminten, .reg = PMINTENSET_EL1, + .get_user = get_pmreg, .set_user = set_pmreg }, { SYS_DESC(SYS_PMMIR_EL1), trap_raz_wi }, { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 }, @@ -2238,14 +2311,17 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CTR_EL0), access_ctr }, { SYS_DESC(SYS_SVCR), undef_access }, - { PMU_SYS_REG(PMCR_EL0), .access = access_pmcr, - .reset = reset_pmcr, .reg = PMCR_EL0 }, + { PMU_SYS_REG(PMCR_EL0), .access = access_pmcr, .reset = reset_pmcr, + .reg = PMCR_EL0, .get_user = get_pmcr, .set_user = set_pmcr }, { PMU_SYS_REG(PMCNTENSET_EL0), - .access = access_pmcnten, .reg = PMCNTENSET_EL0 }, + .access = access_pmcnten, .reg = PMCNTENSET_EL0, + .get_user = get_pmreg, .set_user = set_pmreg }, { PMU_SYS_REG(PMCNTENCLR_EL0), - .access = access_pmcnten, .reg = PMCNTENSET_EL0 }, + .access = access_pmcnten, .reg = PMCNTENSET_EL0, + .get_user = get_pmreg, .set_user = set_pmreg }, { PMU_SYS_REG(PMOVSCLR_EL0), - .access = access_pmovs, .reg = PMOVSSET_EL0 }, + .access = access_pmovs, .reg = PMOVSSET_EL0, + .get_user = get_pmreg, .set_user = set_pmreg }, /* * PM_SWINC_EL0 is exposed to userspace as RAZ/WI, as it was * previously (and pointlessly) advertised in the past... @@ -2273,7 +2349,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { PMU_SYS_REG(PMUSERENR_EL0), .access = access_pmuserenr, .reset = reset_val, .reg = PMUSERENR_EL0, .val = 0 }, { PMU_SYS_REG(PMOVSSET_EL0), - .access = access_pmovs, .reg = PMOVSSET_EL0 }, + .access = access_pmovs, .reg = PMOVSSET_EL0, + .get_user = get_pmreg, .set_user = set_pmreg }, { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, |