diff options
authorPaolo Bonzini <>2016-03-08 12:13:39 +0100
committerPaolo Bonzini <>2016-03-10 11:26:07 +0100
commit844a5fe219cf472060315971e15cbf97674a3324 (patch)
parent313f636d5c490c9741d3f750dc8da33029edbc6b (diff)
KVM: MMU: fix ept=0/pte.u=1/pte.w=0/CR0.WP=0/CR4.SMEP=1/EFER.NX=0 combo
Yes, all of these are needed. :) This is admittedly a bit odd, but kvm-unit-tests access.flat tests this if you run it with "-cpu host" and of course ept=0. KVM runs the guest with CR0.WP=1, so it must handle supervisor writes specially when pte.u=1/pte.w=0/CR0.WP=0. Such writes cause a fault when U=1 and W=0 in the SPTE, but they must succeed because CR0.WP=0. When KVM gets the fault, it sets U=0 and W=1 in the shadow PTE and restarts execution. This will still cause a user write to fault, while supervisor writes will succeed. User reads will fault spuriously now, and KVM will then flip U and W again in the SPTE (U=1, W=0). User reads will be enabled and supervisor writes disabled, going back to the originary situation where supervisor writes fault spuriously. When SMEP is in effect, however, U=0 will enable kernel execution of this page. To avoid this, KVM also sets NX=1 in the shadow PTE together with U=0. If the guest has not enabled NX, the result is a continuous stream of page faults due to the NX bit being reserved. The fix is to force EFER.NX=1 even if the CPU is taking care of the EFER switch. (All machines with SMEP have the CPU_LOAD_IA32_EFER vm-entry control, so they do not use user-return notifiers for EFER---if they did, EFER.NX would be forced to the same value as the host). There is another bug in the reserved bit check, which I've split to a separate patch for easier application to stable kernels. Cc: Cc: Andy Lutomirski <> Reviewed-by: Xiao Guangrong <> Fixes: f6577a5fa15d82217ca73c74cd2dcbc0f6c781dd Signed-off-by: Paolo Bonzini <>
2 files changed, 25 insertions, 14 deletions
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index daf9c0f742d2..c81731096a43 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -358,7 +358,8 @@ In the first case there are two additional complications:
- if CR4.SMEP is enabled: since we've turned the page into a kernel page,
the kernel may now execute it. We handle this by also setting spte.nx.
If we get a user fetch or read fault, we'll change spte.u=1 and
- spte.nx=gpte.nx back.
+ spte.nx=gpte.nx back. For this to work, KVM forces EFER.NX to 1 when
+ shadow paging is in use.
- if CR4.SMAP is disabled: since the page has been changed to a kernel
page, it can not be reused when CR4.SMAP is enabled. We set
CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 6e51493ff4f9..9bd8f44baded 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1857,26 +1857,31 @@ static void reload_tss(void)
static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
- u64 guest_efer;
- u64 ignore_bits;
+ u64 guest_efer = vmx->vcpu.arch.efer;
+ u64 ignore_bits = 0;
- guest_efer = vmx->vcpu.arch.efer;
+ if (!enable_ept) {
+ /*
+ * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing
+ * host CPUID is more efficient than testing guest CPUID
+ * or CR4. Host SMEP is anyway a requirement for guest SMEP.
+ */
+ if (boot_cpu_has(X86_FEATURE_SMEP))
+ guest_efer |= EFER_NX;
+ else if (!(guest_efer & EFER_NX))
+ ignore_bits |= EFER_NX;
+ }
- * NX is emulated; LMA and LME handled by hardware; SCE meaningless
- * outside long mode
+ * LMA and LME handled by hardware; SCE meaningless outside long mode.
- ignore_bits = EFER_NX | EFER_SCE;
+ ignore_bits |= EFER_SCE;
#ifdef CONFIG_X86_64
ignore_bits |= EFER_LMA | EFER_LME;
/* SCE is meaningful only in long mode on Intel */
if (guest_efer & EFER_LMA)
ignore_bits &= ~(u64)EFER_SCE;
- guest_efer &= ~ignore_bits;
- guest_efer |= host_efer & ignore_bits;
- vmx->guest_msrs[efer_offset].data = guest_efer;
- vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
clear_atomic_switch_msr(vmx, MSR_EFER);
@@ -1887,16 +1892,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
if (cpu_has_load_ia32_efer ||
(enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) {
- guest_efer = vmx->vcpu.arch.efer;
if (!(guest_efer & EFER_LMA))
guest_efer &= ~EFER_LME;
if (guest_efer != host_efer)
add_atomic_switch_msr(vmx, MSR_EFER,
guest_efer, host_efer);
return false;
- }
+ } else {
+ guest_efer &= ~ignore_bits;
+ guest_efer |= host_efer & ignore_bits;
- return true;
+ vmx->guest_msrs[efer_offset].data = guest_efer;
+ vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
+ return true;
+ }
static unsigned long segment_base(u16 selector)