Reject KVM if entry '0' in the host's IA32_PAT MSR is not programmed to
writeback (WB) memtype. KVM subtly relies on IA32_PAT entry '0' to be
programmed to WB by leaving the PAT bits in shadow paging and NPT SPTEs
as '0'. If something other than WB is in PAT[0], at _best_ guests will
suffer very poor performance, and at worst KVM will crash the system by
breaking cache-coherency expecations (e.g. using WC for guest memory).
Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
---
arch/x86/kvm/x86.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f389691d8c04..12199c40f2bc 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9141,6 +9141,7 @@ static struct notifier_block pvclock_gtod_notifier = {
int kvm_arch_init(void *opaque)
{
struct kvm_x86_init_ops *ops = opaque;
+ u64 host_pat;
int r;
if (kvm_x86_ops.hardware_enable) {
@@ -9179,6 +9180,20 @@ int kvm_arch_init(void *opaque)
goto out;
}
+ /*
+ * KVM assumes that PAT entry '0' encodes WB memtype and simply zeroes
+ * the PAT bits in SPTEs. Bail if PAT[0] is programmed to something
+ * other than WB. Note, EPT doesn't utilize the PAT, but don't bother
+ * with an exception. PAT[0] is set to WB on RESET and also by the
+ * kernel, i.e. failure indicates a kernel bug or broken firmware.
+ */
+ if (rdmsrl_safe(MSR_IA32_CR_PAT, &host_pat) ||
+ (host_pat & GENMASK(2, 0)) != 6) {
+ pr_err("kvm: host PAT[0] is not WB\n");
+ r = -EIO;
+ goto out;
+ }
+
r = -ENOMEM;
x86_emulator_cache = kvm_alloc_emulator_cache();
--
2.37.0.170.g444d1eabd0-goog
