KVM: Make kvm_make_vcpus_request_mask() use pre-allocated cpu_kick_mask

kvm_make_vcpus_request_mask() already disables preemption so just like
kvm_make_all_cpus_request_except() it can be switched to using
pre-allocated per-cpu cpumasks. This allows for improvements for both
users of the function: in Hyper-V emulation code 'tlb_flush' can now be
dropped from 'struct kvm_vcpu_hv' and kvm_make_scan_ioapic_request_mask()
gets rid of dynamic allocation.

cpumask_available() checks in kvm_make_vcpu_request() and
kvm_kick_many_cpus() can now be dropped as they checks for an impossible
condition: kvm_init() makes sure per-cpu masks are allocated.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210903075141.403071-9-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -581,7 +581,6 @@ struct kvm_vcpu_hv {
 	struct kvm_hyperv_exit exit;
 	struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT];
 	DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
-	cpumask_t tlb_flush;
 	bool enforce_cpuid;
 	struct {
 		u32 features_eax; /* HYPERV_CPUID_FEATURES.EAX */

arch/x86/kvm/hyperv.c

@@ -1754,7 +1754,6 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 	int i;
 	gpa_t gpa;
 	struct kvm *kvm = vcpu->kvm;
-	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
 	struct hv_tlb_flush_ex flush_ex;
 	struct hv_tlb_flush flush;
 	u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
@@ -1836,8 +1835,6 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 		}
 	}
 
-	cpumask_clear(&hv_vcpu->tlb_flush);
-
 	/*
 	 * 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 address space.
@@ -1849,7 +1846,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 						    vp_bitmap, vcpu_bitmap);
 
 		kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST,
-					    vcpu_mask, &hv_vcpu->tlb_flush);
+					    vcpu_mask);
 	}
 
 ret_success:

arch/x86/kvm/x86.c

@@ -9242,14 +9242,7 @@ static void process_smi(struct kvm_vcpu *vcpu)
 void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
 				       unsigned long *vcpu_bitmap)
 {
-	cpumask_var_t cpus;
-
-	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
-
-	kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC,
-				    vcpu_bitmap, cpus);
-
-	free_cpumask_var(cpus);
+	kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, vcpu_bitmap);
 }
 
 void kvm_make_scan_ioapic_request(struct kvm *kvm)

include/linux/kvm_host.h

@@ -160,7 +160,7 @@ static inline bool is_error_page(struct page *page)
 #define KVM_ARCH_REQ(nr)           KVM_ARCH_REQ_FLAGS(nr, 0)
 
 bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
-				 unsigned long *vcpu_bitmap, cpumask_var_t tmp);
+				 unsigned long *vcpu_bitmap);
 bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
 bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req,
 				      struct kvm_vcpu *except);

virt/kvm/kvm_main.c

@@ -237,15 +237,8 @@ static void ack_flush(void *_completed)
 {
 }
 
-static inline bool kvm_kick_many_cpus(cpumask_var_t tmp, bool wait)
+static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait)
 {
-	const struct cpumask *cpus;
-
-	if (likely(cpumask_available(tmp)))
-		cpus = tmp;
-	else
-		cpus = cpu_online_mask;
-
 	if (cpumask_empty(cpus))
 		return false;
 
@@ -254,7 +247,7 @@ static inline bool kvm_kick_many_cpus(cpumask_var_t tmp, bool wait)
 }
 
 static void kvm_make_vcpu_request(struct kvm *kvm, struct kvm_vcpu *vcpu,
-				  unsigned int req, cpumask_var_t tmp,
+				  unsigned int req, struct cpumask *tmp,
 				  int current_cpu)
 {
 	int cpu;
@@ -264,14 +257,6 @@ static void kvm_make_vcpu_request(struct kvm *kvm, struct kvm_vcpu *vcpu,
 	if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
 		return;
 
-	/*
-	 * tmp can be "unavailable" if cpumasks are allocated off stack as
-	 * allocation of the mask is deliberately not fatal and is handled by
-	 * falling back to kicking all online CPUs.
-	 */
-	if (!cpumask_available(tmp))
-		return;
-
 	/*
 	 * Note, the vCPU could get migrated to a different pCPU at any point
 	 * after kvm_request_needs_ipi(), which could result in sending an IPI
@@ -290,22 +275,26 @@ static void kvm_make_vcpu_request(struct kvm *kvm, struct kvm_vcpu *vcpu,
 }
 
 bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
-				 unsigned long *vcpu_bitmap, cpumask_var_t tmp)
+				 unsigned long *vcpu_bitmap)
 {
 	struct kvm_vcpu *vcpu;
+	struct cpumask *cpus;
 	int i, me;
 	bool called;
 
 	me = get_cpu();
 
+	cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask);
+	cpumask_clear(cpus);
+
 	for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) {
 		vcpu = kvm_get_vcpu(kvm, i);
 		if (!vcpu)
 			continue;
-		kvm_make_vcpu_request(kvm, vcpu, req, tmp, me);
+		kvm_make_vcpu_request(kvm, vcpu, req, cpus, me);
 	}
 
-	called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT));
+	called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT));
 	put_cpu();
 
 	return called;