To implement steal time, we need the hypervisor to pass the guest information about how much time was spent running other processes outside the VM. This is per-vcpu, and using the kvmclock structure for that is an abuse we decided not to make. In this patchset, I am introducing a new msr, KVM_MSR_STEAL_TIME, that holds the memory area address containing information about steal time This patch contains the hypervisor part for it. I am keeping it separate from the headers to facilitate backports to people who wants to backport the kernel part but not the hypervisor, or the other way around. Signed-off-by: Glauber Costa <glommer@xxxxxxxxxx> CC: Rik van Riel <riel@xxxxxxxxxx> CC: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx> CC: Peter Zijlstra <peterz@xxxxxxxxxxxxx> CC: Avi Kivity <avi@xxxxxxxxxx> --- arch/x86/include/asm/kvm_host.h | 5 +++++ arch/x86/kvm/x86.c | 39 +++++++++++++++++++++++++++++++++++++-- 2 files changed, 42 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ffd7f8d..be6e0e2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -377,6 +377,11 @@ struct kvm_vcpu_arch { unsigned int hw_tsc_khz; unsigned int time_offset; struct page *time_page; + + gpa_t stime; + struct kvm_steal_time steal; + u64 this_time_out; + u64 last_host_tsc; u64 last_guest_tsc; u64 last_kernel_ns; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7a326cb..7f14900 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -787,12 +787,12 @@ EXPORT_SYMBOL_GPL(kvm_get_dr); * kvm-specific. Those are put in the beginning of the list. */ -#define KVM_SAVE_MSRS_BEGIN 8 +#define KVM_SAVE_MSRS_BEGIN 9 static u32 msrs_to_save[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, - HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, + HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 @@ -1546,6 +1546,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (kvm_pv_enable_async_pf(vcpu, data)) return 1; break; + case MSR_KVM_STEAL_TIME: + + if (!(data & 1)) { + vcpu->arch.stime = 0; + break; + } + + vcpu->arch.stime = data & ~1; + break; + case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1: @@ -1831,6 +1841,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_KVM_ASYNC_PF_EN: data = vcpu->arch.apf.msr_val; break; + case MSR_KVM_STEAL_TIME: + data = vcpu->arch.stime; + break; case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: case MSR_IA32_MCG_CAP: @@ -1993,6 +2006,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_X86_ROBUST_SINGLESTEP: case KVM_CAP_XSAVE: case KVM_CAP_ASYNC_PF: + case KVM_CAP_STEAL_TIME: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -2108,6 +2122,9 @@ static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { + struct kvm_steal_time *st; + st = (struct kvm_steal_time *)vcpu->arch.stime; + /* Address WBINVD may be executed by guest */ if (need_emulate_wbinvd(vcpu)) { if (kvm_x86_ops->has_wbinvd_exit()) @@ -2133,6 +2150,21 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_migrate_timers(vcpu); vcpu->cpu = cpu; } + + if (vcpu->arch.this_time_out) { + u64 to = (get_kernel_ns() - vcpu->arch.this_time_out); + + kvm_read_guest(vcpu->kvm, (gpa_t)st, &vcpu->arch.steal, + sizeof(*st)); + + vcpu->arch.steal.steal += to; + vcpu->arch.steal.version += 2; + + kvm_write_guest(vcpu->kvm, (gpa_t)st, &vcpu->arch.steal, + sizeof(*st)); + /* is it possible to have 2 loads in sequence? */ + vcpu->arch.this_time_out = 0; + } } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -2140,6 +2172,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); vcpu->arch.last_host_tsc = native_read_tsc(); + vcpu->arch.this_time_out = get_kernel_ns(); } static int is_efer_nx(void) @@ -5882,6 +5915,8 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) kvmclock_reset(vcpu); + vcpu->arch.stime = 0; + kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; -- 1.7.2.3 -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html