[PATCH v2 RFC] x86/kvm/mmu: make mmu->prev_roots cache work for NPT case

[Vitaly Kuznetsov <vkuznets@redhat.com>]

Alternative patch: remove the filtering from kvm_mmu_get_page() and check
for direct on call sites. cr4_pae setting in kvm_calc_mmu_role_common()
can be preserved for consistency.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
 arch/x86/kvm/mmu.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index f2d1d230d5b8..7fb8118f2af6 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2420,8 +2420,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	role = vcpu->arch.mmu->mmu_role.base;
 	role.level = level;
 	role.direct = direct;
-	if (role.direct)
-		role.cr4_pae = 0;
 	role.access = access;
 	if (!vcpu->arch.mmu->direct_map
 	    && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) {
@@ -5176,7 +5174,7 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa,
 		 gpa, bytes, sp->role.word);
 
 	offset = offset_in_page(gpa);
-	pte_size = sp->role.cr4_pae ? 8 : 4;
+	pte_size = (sp->role.cr4_pae && !sp->role.direct) ? 8 : 4;
 
 	/*
 	 * Sometimes, the OS only writes the last one bytes to update status
@@ -5200,7 +5198,7 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte)
 	page_offset = offset_in_page(gpa);
 	level = sp->role.level;
 	*nspte = 1;
-	if (!sp->role.cr4_pae) {
+	if (!sp->role.cr4_pae || sp->role.direct) {
 		page_offset <<= 1;	/* 32->64 */
 		/*
 		 * A 32-bit pde maps 4MB while the shadow pdes map
-- 
2.20.1