[PATCH v4 RESEND 2/5] KVM: x86: hyperv: optimize 'all cpus' case in kvm_hv_flush_tlb()

[Vitaly Kuznetsov]

We can use 'NULL' to represent 'all cpus' case in
kvm_make_vcpus_request_mask() and avoid building vCPU mask with
all vCPUs.

Suggested-by: Radim KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
Reviewed-by: Roman Kagan <rkagan@xxxxxxxxxxxxx>
---
 arch/x86/kvm/hyperv.c | 42 +++++++++++++++++++++++-------------------
 virt/kvm/kvm_main.c   |  6 ++----
 2 files changed, 25 insertions(+), 23 deletions(-)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 0cd597b0f754..b45ce136be2f 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1325,35 +1325,39 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
 
 	cpumask_clear(&hv_current->tlb_lush);
 
+	if (all_cpus) {
+		kvm_make_vcpus_request_mask(kvm,
+				    KVM_REQ_TLB_FLUSH | KVM_REQUEST_NO_WAKEUP,
+				    NULL, &hv_current->tlb_lush);
+		goto ret_success;
+	}
+
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
 		int bank = hv->vp_index / 64, sbank = 0;
 
-		if (!all_cpus) {
-			/* Banks >64 can't be represented */
-			if (bank >= 64)
-				continue;
-
-			/* Non-ex hypercalls can only address first 64 vCPUs */
-			if (!ex && bank)
-				continue;
+		/* Banks >64 can't be represented */
+		if (bank >= 64)
+			continue;
 
-			if (ex) {
-				/*
-				 * Check is the bank of this vCPU is in sparse
-				 * set and get the sparse bank number.
-				 */
-				sbank = get_sparse_bank_no(valid_bank_mask,
-							   bank);
+		/* Non-ex hypercalls can only address first 64 vCPUs */
+		if (!ex && bank)
+			continue;
 
-				if (sbank < 0)
-					continue;
-			}
+		if (ex) {
+			/*
+			 * Check is the bank of this vCPU is in sparse
+			 * set and get the sparse bank number.
+			 */
+			sbank = get_sparse_bank_no(valid_bank_mask, bank);
 
-			if (!(sparse_banks[sbank] & BIT_ULL(hv->vp_index % 64)))
+			if (sbank < 0)
 				continue;
 		}
 
+		if (!(sparse_banks[sbank] & BIT_ULL(hv->vp_index % 64)))
+			continue;
+
 		/*
 		 * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we
 		 * can't analyze it here, flush TLB regardless of the specified
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f83239ac8be1..3340f8128dc8 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -218,7 +218,7 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
 	me = get_cpu();
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (!test_bit(i, vcpu_bitmap))
+		if (vcpu_bitmap && !test_bit(i, vcpu_bitmap))
 			continue;
 
 		kvm_make_request(req, vcpu);
@@ -242,12 +242,10 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
 {
 	cpumask_var_t cpus;
 	bool called;
-	static unsigned long vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]
-		= {[0 ... BITS_TO_LONGS(KVM_MAX_VCPUS)-1] = ULONG_MAX};
 
 	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
 
-	called = kvm_make_vcpus_request_mask(kvm, req, vcpu_bitmap, cpus);
+	called = kvm_make_vcpus_request_mask(kvm, req, NULL, cpus);
 
 	free_cpumask_var(cpus);
 	return called;
-- 
2.14.4