VMX initializes the TSC offset for each vcpu at different times, and also reinitializes it for vcpus other than 0 on APIC SIPI message.
This bug causes the TSC's to appear unsynchronized in the guest, even if the host is good. Older Linux kernels don't handle the situation very well, so gettimeofday is likely to go backwards in time: http://www.mail-archive.com/[email protected]/msg02955.html http://sourceforge.net/tracker/index.php?func=detail&aid=2025534&group_id=180599&atid=893831 Fix it by initializating the offset of each vcpu relative to vm creation time, and moving it from vmx_vcpu_reset to vmx_vcpu_setup, out of the APIC MP init path. Signed-off-by: Marcelo Tosatti <[EMAIL PROTECTED]> Index: kvm/arch/x86/include/asm/kvm_host.h =================================================================== --- kvm.orig/arch/x86/include/asm/kvm_host.h +++ kvm/arch/x86/include/asm/kvm_host.h @@ -378,6 +378,7 @@ struct kvm_arch{ unsigned long irq_sources_bitmap; unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; + u64 vm_init_tsc; }; struct kvm_vm_stat { Index: kvm/arch/x86/kvm/vmx.c =================================================================== --- kvm.orig/arch/x86/kvm/vmx.c +++ kvm/arch/x86/kvm/vmx.c @@ -856,11 +856,8 @@ static u64 guest_read_tsc(void) * writes 'guest_tsc' into guest's timestamp counter "register" * guest_tsc = host_tsc + tsc_offset ==> tsc_offset = guest_tsc - host_tsc */ -static void guest_write_tsc(u64 guest_tsc) +static void guest_write_tsc(u64 guest_tsc, u64 host_tsc) { - u64 host_tsc; - - rdtscll(host_tsc); vmcs_write64(TSC_OFFSET, guest_tsc - host_tsc); } @@ -924,6 +921,7 @@ static int vmx_set_msr(struct kvm_vcpu * { struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_msr_entry *msr; + u64 host_tsc; int ret = 0; switch (msr_index) { @@ -949,7 +947,8 @@ static int vmx_set_msr(struct kvm_vcpu * vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_TIME_STAMP_COUNTER: - guest_write_tsc(data); + rdtscll(host_tsc); + guest_write_tsc(data, host_tsc); break; case MSR_P6_PERFCTR0: case MSR_P6_PERFCTR1: @@ -2239,6 +2238,7 @@ static int vmx_vcpu_setup(struct vcpu_vm vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK); + guest_write_tsc(0, vmx->vcpu.kvm->arch.vm_init_tsc); return 0; } @@ -2331,8 +2331,6 @@ static int vmx_vcpu_reset(struct kvm_vcp vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); - guest_write_tsc(0); - /* Special registers */ vmcs_write64(GUEST_IA32_DEBUGCTL, 0); Index: kvm/arch/x86/kvm/x86.c =================================================================== --- kvm.orig/arch/x86/kvm/x86.c +++ kvm/arch/x86/kvm/x86.c @@ -4122,6 +4122,8 @@ struct kvm *kvm_arch_create_vm(void) /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); + rdtscll(kvm->arch.vm_init_tsc); + return kvm; } -- -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
