[PATCH v2] KVM: x86: count actual tlb flushes

[Liang Chen <liangchen.linux@gmail.com>]

- we count KVM_REQ_TLB_FLUSH requests, not actual flushes
(KVM can have multiple requests for one flush)
- flushes from kvm_flush_remote_tlbs aren't counted
- it's easy to make a direct request by mistake

Solve these by postponing the counting to kvm_check_request(),
and refactor the code to use kvm_make_request again.

Signed-off-by: Liang Chen <liangchen.linux@gmail.com>
---
Changes since v2:

* Instead of calling kvm_mmu_flush_tlb everywhere to make sure the
stat is always incremented, postponing the counting to
kvm_check_request.

(The idea comes from Radim. Much of the work is indeed done by him
and is included in this patch, otherwise I couldn't start working
on the followup work as I promised early. As I'm new to kvm
development, please let me know if I am doing wrong here.)

 arch/x86/include/asm/kvm_host.h |  1 -
 arch/x86/kvm/mmu.c              | 17 +++++------------
 arch/x86/kvm/vmx.c              |  2 +-
 arch/x86/kvm/x86.c              | 10 ++++++++--
 4 files changed, 14 insertions(+), 16 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7c492ed..77ade89 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -917,7 +917,6 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 
 int fx_init(struct kvm_vcpu *vcpu);
 
-void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu);
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		       const u8 *new, int bytes);
 int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9314678..acc2d0c5 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1749,7 +1749,7 @@ static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 		return 1;
 	}
 
-	kvm_mmu_flush_tlb(vcpu);
+	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	return 0;
 }
 
@@ -1802,7 +1802,7 @@ static void kvm_sync_pages(struct kvm_vcpu *vcpu,  gfn_t gfn)
 
 	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
 	if (flush)
-		kvm_mmu_flush_tlb(vcpu);
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 }
 
 struct mmu_page_path {
@@ -2536,7 +2536,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	      true, host_writable)) {
 		if (write_fault)
 			*emulate = 1;
-		kvm_mmu_flush_tlb(vcpu);
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	}
 
 	if (unlikely(is_mmio_spte(*sptep) && emulate))
@@ -3450,13 +3450,6 @@ static void nonpaging_init_context(struct kvm_vcpu *vcpu,
 	context->nx = false;
 }
 
-void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
-{
-	++vcpu->stat.tlb_flush;
-	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
-}
-EXPORT_SYMBOL_GPL(kvm_mmu_flush_tlb);
-
 void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu)
 {
 	mmu_free_roots(vcpu);
@@ -3962,7 +3955,7 @@ static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page,
 	if (remote_flush)
 		kvm_flush_remote_tlbs(vcpu->kvm);
 	else if (local_flush)
-		kvm_mmu_flush_tlb(vcpu);
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 }
 
 static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
@@ -4223,7 +4216,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
 {
 	vcpu->arch.mmu.invlpg(vcpu, gva);
-	kvm_mmu_flush_tlb(vcpu);
+	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	++vcpu->stat.invlpg;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index bfe11cf..bb0a7ab 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6617,7 +6617,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	switch (type) {
 	case VMX_EPT_EXTENT_GLOBAL:
 		kvm_mmu_sync_roots(vcpu);
-		kvm_mmu_flush_tlb(vcpu);
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 		nested_vmx_succeed(vcpu);
 		break;
 	default:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8f1e22d..f9fca52f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -726,7 +726,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 	if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
 		kvm_mmu_sync_roots(vcpu);
-		kvm_mmu_flush_tlb(vcpu);
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 		return 0;
 	}
 
@@ -5989,6 +5989,12 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 	kvm_apic_update_tmr(vcpu, tmr);
 }
 
+static void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
+{
+	++vcpu->stat.tlb_flush;
+	kvm_x86_ops->tlb_flush(vcpu);
+}
+
 /*
  * Returns 1 to let __vcpu_run() continue the guest execution loop without
  * exiting to the userspace.  Otherwise, the value will be returned to the
@@ -6018,7 +6024,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu))
 			kvm_mmu_sync_roots(vcpu);
 		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
-			kvm_x86_ops->tlb_flush(vcpu);
+			kvm_mmu_flush_tlb(vcpu);
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
 			r = 0;
-- 
1.9.1