ARMv8 provides for a virtual counter-timer offset that is added to guest views of the virtual counter-timer (CNTVOFF_EL2). To date, KVM has not provided userspace with any perception of this, and instead affords a value-based scheme of migrating the virtual counter-timer by directly reading/writing the guest's CNTVCT_EL0. This is problematic because counters continue to elapse while the register is being written, meaning it is possible for drift to sneak in to the guest's time scale. This is exacerbated by the fact that KVM will calculate an appropriate CNTVOFF_EL2 every time the register is written, which will be broadcast to all virtual CPUs. The only possible way to avoid causing guest time to drift is to restore counter-timers by offset. Implement initial support for KVM_{GET,SET}_SYSTEM_COUNTER_STATE ioctls to migrate the value of CNTVOFF_EL2. These ioctls yield precise control of the virtual counter-timers to userspace, allowing it to define its own heuristics for managing vCPU offsets. Reviewed-by: Jim Mattson <jmattson@xxxxxxxxxx> Reviewed-by: Jing Zhang <jingzhangos@xxxxxxxxxx> Reviewed-by: Peter Shier <pshier@xxxxxxxxxx> Signed-off-by: Oliver Upton <oupton@xxxxxxxxxx> --- arch/arm64/include/asm/kvm_host.h | 5 +++++ arch/arm64/include/uapi/asm/kvm.h | 10 ++++++++++ arch/arm64/kvm/arch_timer.c | 22 ++++++++++++++++++++++ arch/arm64/kvm/arm.c | 25 +++++++++++++++++++++++++ 4 files changed, 62 insertions(+) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7cd7d5c8c4bc..31107d5e61af 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -781,4 +781,9 @@ void __init kvm_hyp_reserve(void); static inline void kvm_hyp_reserve(void) { } #endif +int kvm_arm_vcpu_get_system_counter_state(struct kvm_vcpu *vcpu, + struct kvm_system_counter_state *state); +int kvm_arm_vcpu_set_system_counter_state(struct kvm_vcpu *vcpu, + struct kvm_system_counter_state *state); + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 24223adae150..d3987089c524 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -184,6 +184,16 @@ struct kvm_vcpu_events { __u32 reserved[12]; }; +/* for KVM_{GET,SET}_SYSTEM_COUNTER_STATE */ +struct kvm_system_counter_state { + /* indicates what fields are valid in the structure */ + __u32 flags; + __u32 pad; + /* guest counter-timer offset, relative to host cntpct_el0 */ + __u64 cntvoff; + __u64 rsvd[7]; +}; + /* If you need to interpret the index values, here is the key: */ #define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 #define KVM_REG_ARM_COPROC_SHIFT 16 diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 74e0699661e9..955a7a183362 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -1259,3 +1259,25 @@ int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) return -ENXIO; } + +int kvm_arm_vcpu_get_system_counter_state(struct kvm_vcpu *vcpu, + struct kvm_system_counter_state *state) +{ + if (state->flags) + return -EINVAL; + + state->cntvoff = timer_get_offset(vcpu_vtimer(vcpu)); + + return 0; +} + +int kvm_arm_vcpu_set_system_counter_state(struct kvm_vcpu *vcpu, + struct kvm_system_counter_state *state) +{ + if (state->flags) + return -EINVAL; + + timer_set_offset(vcpu_vtimer(vcpu), state->cntvoff); + + return 0; +} diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 1126eae27400..b78ffb4db9dd 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -207,6 +207,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_PTP_KVM: + case KVM_CAP_SYSTEM_COUNTER_STATE: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: @@ -1273,6 +1274,30 @@ long kvm_arch_vcpu_ioctl(struct file *filp, return kvm_arm_vcpu_finalize(vcpu, what); } + case KVM_GET_SYSTEM_COUNTER_STATE: { + struct kvm_system_counter_state state; + + if (copy_from_user(&state, argp, sizeof(state))) + return -EFAULT; + + r = kvm_arm_vcpu_get_system_counter_state(vcpu, &state); + if (r) + break; + + if (copy_to_user(argp, &state, sizeof(state))) + return -EFAULT; + + break; + } + case KVM_SET_SYSTEM_COUNTER_STATE: { + struct kvm_system_counter_state state; + + if (copy_from_user(&state, argp, sizeof(state))) + return -EFAULT; + + r = kvm_arm_vcpu_set_system_counter_state(vcpu, &state); + break; + } default: r = -EINVAL; } -- 2.32.0.rc1.229.g3e70b5a671-goog