[PATCH V2 02/10] KVM: X86: Synchronize the shadow pagetable before link it

[Lai Jiangshan]

From: Lai Jiangshan <laijs@xxxxxxxxxxxxxxxxx>

If gpte is changed from non-present to present, the guest doesn't need
to flush tlb per SDM.  So the host must synchronze sp before
link it.  Otherwise the guest might use a wrong mapping.

For example: the guest first changes a level-1 pagetable, and then
links its parent to a new place where the original gpte is non-present.
Finally the guest can access the remapped area without flushing
the tlb.  The guest's behavior should be allowed per SDM, but the host
kvm mmu makes it wrong.

Fixes: 4731d4c7a077 ("KVM: MMU: out of sync shadow core")
Signed-off-by: Lai Jiangshan <laijs@xxxxxxxxxxxxxxxxx>
---
Changed from V1:
	Don't loop, but just return when it needs to break.

 arch/x86/kvm/mmu/mmu.c         | 15 ++++++++-------
 arch/x86/kvm/mmu/paging_tmpl.h | 22 ++++++++++++++++++++++
 2 files changed, 30 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 26f6bd238a77..3c1b069a7bcf 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2024,8 +2024,8 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents)
 	} while (!sp->unsync_children);
 }
 
-static void mmu_sync_children(struct kvm_vcpu *vcpu,
-			      struct kvm_mmu_page *parent)
+static int mmu_sync_children(struct kvm_vcpu *vcpu,
+			     struct kvm_mmu_page *parent, bool can_yield)
 {
 	int i;
 	struct kvm_mmu_page *sp;
@@ -2052,12 +2052,16 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu,
 		}
 		if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) {
 			kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
+			if (!can_yield)
+				return -EINTR;
+
 			cond_resched_rwlock_write(&vcpu->kvm->mmu_lock);
 			flush = false;
 		}
 	}
 
 	kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
+	return 0;
 }
 
 static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
@@ -2143,9 +2147,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 		}
 
-		if (sp->unsync_children)
-			kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
-
 		__clear_sp_write_flooding_count(sp);
 
 trace_get_page:
@@ -3642,7 +3643,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 		write_lock(&vcpu->kvm->mmu_lock);
 		kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
 
-		mmu_sync_children(vcpu, sp);
+		mmu_sync_children(vcpu, sp, true);
 
 		kvm_mmu_audit(vcpu, AUDIT_POST_SYNC);
 		write_unlock(&vcpu->kvm->mmu_lock);
@@ -3658,7 +3659,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 		if (IS_VALID_PAE_ROOT(root)) {
 			root &= PT64_BASE_ADDR_MASK;
 			sp = to_shadow_page(root);
-			mmu_sync_children(vcpu, sp);
+			mmu_sync_children(vcpu, sp, true);
 		}
 	}
 
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 5962d4f8a72e..87374cfd82be 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -704,6 +704,28 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 			access = gw->pt_access[it.level - 2];
 			sp = kvm_mmu_get_page(vcpu, table_gfn, fault->addr,
 					      it.level-1, false, access);
+			/*
+			 * We must synchronize the pagetable before link it
+			 * because the guest doens't need to flush tlb when
+			 * gpte is changed from non-present to present.
+			 * Otherwise, the guest may use the wrong mapping.
+			 *
+			 * For PG_LEVEL_4K, kvm_mmu_get_page() has already
+			 * synchronized it transiently via kvm_sync_page().
+			 *
+			 * For higher level pagetable, we synchronize it
+			 * via slower mmu_sync_children().  If it needs to
+			 * break, returns RET_PF_RETRY and will retry on
+			 * next #PF.  It had already made some progress.
+			 *
+			 * It also makes KVM_REQ_MMU_SYNC request if the @sp
+			 * is linked on a different addr to expedite it.
+			 */
+			if (sp->unsync_children &&
+			    mmu_sync_children(vcpu, sp, false)) {
+				kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
+				return RET_PF_RETRY;
+			}
 		}
 
 		/*
-- 
2.19.1.6.gb485710b