Merge branches 'acpi-resources', 'acpi-battery', 'acpi-doc' and 'acpi-pnp'

[linux-2.6-block.git] / arch / x86 / kvm / x86.c

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e1a81267f3f632e971d1fc63cfe687be2e7c60f3..c73efcd03e294a2e5bc2ef276dc7fa4a6e9d837f 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1669,12 +1669,28 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
                &guest_hv_clock, sizeof(guest_hv_clock))))
                return 0;
 
-       /*
-        * The interface expects us to write an even number signaling that the
-        * update is finished. Since the guest won't see the intermediate
-        * state, we just increase by 2 at the end.
+       /* This VCPU is paused, but it's legal for a guest to read another
+        * VCPU's kvmclock, so we really have to follow the specification where
+        * it says that version is odd if data is being modified, and even after
+        * it is consistent.
+        *
+        * Version field updates must be kept separate.  This is because
+        * kvm_write_guest_cached might use a "rep movs" instruction, and
+        * writes within a string instruction are weakly ordered.  So there
+        * are three writes overall.
+        *
+        * As a small optimization, only write the version field in the first
+        * and third write.  The vcpu->pv_time cache is still valid, because the
+        * version field is the first in the struct.
         */
-       vcpu->hv_clock.version = guest_hv_clock.version + 2;
+       BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
+
+       vcpu->hv_clock.version = guest_hv_clock.version + 1;
+       kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+                               &vcpu->hv_clock,
+                               sizeof(vcpu->hv_clock.version));
+
+       smp_wmb();
 
        /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
        pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
@@ -1695,6 +1711,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
        kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
                                &vcpu->hv_clock,
                                sizeof(vcpu->hv_clock));
+
+       smp_wmb();
+
+       vcpu->hv_clock.version++;
+       kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+                               &vcpu->hv_clock,
+                               sizeof(vcpu->hv_clock.version));
        return 0;
 }
 
@@ -5799,7 +5822,6 @@ int kvm_arch_init(void *opaque)
        kvm_set_mmio_spte_mask();
 
        kvm_x86_ops = ops;
-       kvm_init_msr_list();
 
        kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
                        PT_DIRTY_MASK, PT64_NX_MASK, 0);
@@ -7253,7 +7275,14 @@ void kvm_arch_hardware_disable(void)
 
 int kvm_arch_hardware_setup(void)
 {
-       return kvm_x86_ops->hardware_setup();
+       int r;
+
+       r = kvm_x86_ops->hardware_setup();
+       if (r != 0)
+               return r;
+
+       kvm_init_msr_list();
+       return 0;
 }
 
 void kvm_arch_hardware_unsetup(void)