[PATCH 03/12] KVM: MMU: lazily drop large spte

[Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>]

Currently, kvm zaps the large spte if write-protected is needed, the later
read can fault on that spte. Actually, we can make the large spte readonly
instead of making them un-present, the page fault caused by read access can
be avoided

The idea is from Avi:
| As I mentioned before, write-protecting a large spte is a good idea,
| since it moves some work from protect-time to fault-time, so it reduces
| jitter.  This removes the need for the return value.

[
  It has fixed the issue reported in 6b73a9606 by stopping fast page fault
  marking the large spte to writable
]

Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
---
 arch/x86/kvm/mmu.c | 36 +++++++++++++++++-------------------
 1 file changed, 17 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index cf163ca..35d4b50 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1181,8 +1181,7 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
 
 /*
  * Write-protect on the specified @sptep, @pt_protect indicates whether
- * spte writ-protection is caused by protecting shadow page table.
- * @flush indicates whether tlb need be flushed.
+ * spte write-protection is caused by protecting shadow page table.
  *
  * Note: write protection is difference between drity logging and spte
  * protection:
@@ -1191,10 +1190,9 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
  * - for spte protection, the spte can be writable only after unsync-ing
  *   shadow page.
  *
- * Return true if the spte is dropped.
+ * Return true if tlb need be flushed.
  */
-static bool
-spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect)
+static bool spte_write_protect(struct kvm *kvm, u64 *sptep, bool pt_protect)
 {
 	u64 spte = *sptep;
 
@@ -1204,17 +1202,11 @@ spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect)
 
 	rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep);
 
-	if (__drop_large_spte(kvm, sptep)) {
-		*flush |= true;
-		return true;
-	}
-
 	if (pt_protect)
 		spte &= ~SPTE_MMU_WRITEABLE;
 	spte = spte & ~PT_WRITABLE_MASK;
 
-	*flush |= mmu_spte_update(sptep, spte);
-	return false;
+	return mmu_spte_update(sptep, spte);
 }
 
 static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp,
@@ -1226,11 +1218,8 @@ static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp,
 
 	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
 		BUG_ON(!(*sptep & PT_PRESENT_MASK));
-		if (spte_write_protect(kvm, sptep, &flush, pt_protect)) {
-			sptep = rmap_get_first(*rmapp, &iter);
-			continue;
-		}
 
+		flush |= spte_write_protect(kvm, sptep, pt_protect);
 		sptep = rmap_get_next(&iter);
 	}
 
@@ -2701,6 +2690,8 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 			break;
 		}
 
+		drop_large_spte(vcpu, iterator.sptep);
+
 		if (!is_shadow_present_pte(*iterator.sptep)) {
 			u64 base_addr = iterator.addr;
 
@@ -2855,7 +2846,7 @@ fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
  * - false: let the real page fault path to fix it.
  */
 static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
-			    u32 error_code)
+			    u32 error_code, bool force_pt_level)
 {
 	struct kvm_shadow_walk_iterator iterator;
 	struct kvm_mmu_page *sp;
@@ -2884,6 +2875,13 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 		goto exit;
 
 	/*
+	 * Can not map the large spte to writable if the page is dirty
+	 * logged.
+	 */
+	if (sp->role.level > PT_PAGE_TABLE_LEVEL && force_pt_level)
+		goto exit;
+
+	/*
 	 * Check if it is a spurious fault caused by TLB lazily flushed.
 	 *
 	 * Need not check the access of upper level table entries since
@@ -2944,7 +2942,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
 	} else
 		level = PT_PAGE_TABLE_LEVEL;
 
-	if (fast_page_fault(vcpu, v, level, error_code))
+	if (fast_page_fault(vcpu, v, level, error_code, force_pt_level))
 		return 0;
 
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
@@ -3422,7 +3420,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 	} else
 		level = PT_PAGE_TABLE_LEVEL;
 
-	if (fast_page_fault(vcpu, gpa, level, error_code))
+	if (fast_page_fault(vcpu, gpa, level, error_code, force_pt_level))
 		return 0;
 
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
-- 
1.8.1.4