KVM: x86: Convert MSR_KVM_SYSTEM_TIME to use gfn_to_hva_cache functions (CVE-2013-1797)

commit 0b79459b482e85cb7426aa7da683a9f2c97aeae1 upstream.

There is a potential use after free issue with the handling of
MSR_KVM_SYSTEM_TIME.  If the guest specifies a GPA in a movable or removable
memory such as frame buffers then KVM might continue to write to that
address even after it's removed via KVM_SET_USER_MEMORY_REGION.  KVM pins
the page in memory so it's unlikely to cause an issue, but if the user
space component re-purposes the memory previously used for the guest, then
the guest will be able to corrupt that memory.

Tested: Tested against kvmclock unit test

Signed-off-by: Andrew Honig <ahonig@google.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

2 files changed, 16 insertions, 27 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d2ac8e2ee89..1eb45de173c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -391,8 +391,8 @@ struct kvm_vcpu_arch {
 	gpa_t time;
 	struct pvclock_vcpu_time_info hv_clock;
 	unsigned int hw_tsc_khz;
-	unsigned int time_offset;
-	struct page *time_page;
+	struct gfn_to_hva_cache pv_time;
+	bool pv_time_enabled;
 	u64 last_guest_tsc;
 	u64 last_kernel_ns;
 	u64 last_tsc_nsec;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e525b9e3009..b2d5baf86da 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1073,7 +1073,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 {
 	unsigned long flags;
 	struct kvm_vcpu_arch *vcpu = &v->arch;
-	void *shared_kaddr;
 	unsigned long this_tsc_khz;
 	s64 kernel_ns, max_kernel_ns;
 	u64 tsc_timestamp;
@@ -1109,7 +1108,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	local_irq_restore(flags);
 
-	if (!vcpu->time_page)
+	if (!vcpu->pv_time_enabled)
 		return 0;
 
 	/*
@@ -1167,14 +1166,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	 */
 	vcpu->hv_clock.version += 2;
 
-	shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);
-
-	memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
-	       sizeof(vcpu->hv_clock));
-
-	kunmap_atomic(shared_kaddr, KM_USER0);
-
-	mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
+	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+				&vcpu->hv_clock,
+				sizeof(vcpu->hv_clock));
 	return 0;
 }
 
@@ -1464,10 +1458,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.time_page) {
-		kvm_release_page_dirty(vcpu->arch.time_page);
-		vcpu->arch.time_page = NULL;
-	}
+	vcpu->arch.pv_time_enabled = false;
 }
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
@@ -1527,6 +1518,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		break;
 	case MSR_KVM_SYSTEM_TIME_NEW:
 	case MSR_KVM_SYSTEM_TIME: {
+		u64 gpa_offset;
 		kvmclock_reset(vcpu);
 
 		vcpu->arch.time = data;
@@ -1536,21 +1528,17 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		if (!(data & 1))
 			break;
 
-		/* ...but clean it before doing the actual write */
-		vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
+		gpa_offset = data & ~(PAGE_MASK | 1);
 
 		/* Check that the address is 32-byte aligned. */
-		if (vcpu->arch.time_offset &
-				(sizeof(struct pvclock_vcpu_time_info) - 1))
+		if (gpa_offset & (sizeof(struct pvclock_vcpu_time_info) - 1))
 			break;
 
-		vcpu->arch.time_page =
-				gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
-
-		if (is_error_page(vcpu->arch.time_page)) {
-			kvm_release_page_clean(vcpu->arch.time_page);
-			vcpu->arch.time_page = NULL;
-		}
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+		     &vcpu->arch.pv_time, data & ~1ULL))
+			vcpu->arch.pv_time_enabled = false;
+		else
+			vcpu->arch.pv_time_enabled = true;
 		break;
 	}
 	case MSR_KVM_ASYNC_PF_EN:
@@ -6257,6 +6245,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL))
 		goto fail_free_mce_banks;
 
+	vcpu->arch.pv_time_enabled = false;
 	kvm_async_pf_hash_reset(vcpu);
 
 	return 0;