[RFC V2 5/9] Modify the page fault path to meet the direct build EPT requirement

[yulei.kernel@xxxxxxxxx]

From: Yulei Zhang <yulei.kernel@xxxxxxxxx>

Refine the fast page fault code so that it can be used in either
normal ept mode or direct build EPT mode.

Signed-off-by: Yulei Zhang <yuleixzhang@xxxxxxxxxxx>
---
 arch/x86/kvm/mmu/mmu.c | 28 ++++++++++++++++++++--------
 1 file changed, 20 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index f2124f52b286..fda6c4196854 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3443,12 +3443,13 @@ static bool page_fault_can_be_fast(u32 error_code)
  * someone else modified the SPTE from its original value.
  */
 static bool
-fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, gpa_t gpa,
 			u64 *sptep, u64 old_spte, u64 new_spte)
 {
 	gfn_t gfn;
 
-	WARN_ON(!sp->role.direct);
+	WARN_ON(!vcpu->arch.direct_build_tdp &&
+		(!sptep_to_sp(sptep)->role.direct));
 
 	/*
 	 * Theoretically we could also set dirty bit (and flush TLB) here in
@@ -3470,7 +3471,8 @@ fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 		 * The gfn of direct spte is stable since it is
 		 * calculated by sp->gfn.
 		 */
-		gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt);
+
+		gfn = gpa >> PAGE_SHIFT;
 		kvm_vcpu_mark_page_dirty(vcpu, gfn);
 	}
 
@@ -3498,10 +3500,10 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 			    u32 error_code)
 {
 	struct kvm_shadow_walk_iterator iterator;
-	struct kvm_mmu_page *sp;
 	bool fault_handled = false;
 	u64 spte = 0ull;
 	uint retry_count = 0;
+	int pte_level = 0;
 
 	if (!page_fault_can_be_fast(error_code))
 		return false;
@@ -3515,8 +3517,15 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 			if (!is_shadow_present_pte(spte))
 				break;
 
-		sp = sptep_to_sp(iterator.sptep);
-		if (!is_last_spte(spte, sp->role.level))
+		if (iterator.level < PG_LEVEL_4K)
+			pte_level  = PG_LEVEL_4K;
+		else
+			pte_level = iterator.level;
+
+		WARN_ON(!vcpu->arch.direct_build_tdp &&
+			(pte_level != sptep_to_sp(iterator.sptep)->role.level));
+
+		if (!is_last_spte(spte, pte_level))
 			break;
 
 		/*
@@ -3559,7 +3568,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 			 *
 			 * See the comments in kvm_arch_commit_memory_region().
 			 */
-			if (sp->role.level > PG_LEVEL_4K)
+			if (pte_level > PG_LEVEL_4K)
 				break;
 		}
 
@@ -3573,7 +3582,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 		 * since the gfn is not stable for indirect shadow page. See
 		 * Documentation/virt/kvm/locking.rst to get more detail.
 		 */
-		fault_handled = fast_pf_fix_direct_spte(vcpu, sp,
+		fault_handled = fast_pf_fix_direct_spte(vcpu, cr2_or_gpa,
 							iterator.sptep, spte,
 							new_spte);
 		if (fault_handled)
@@ -4106,6 +4115,9 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 	if (fast_page_fault(vcpu, gpa, error_code))
 		return RET_PF_RETRY;
 
+	if (vcpu->arch.direct_build_tdp)
+		return RET_PF_EMULATE;
+
 	r = mmu_topup_memory_caches(vcpu, false);
 	if (r)
 		return r;
-- 
2.17.1