@@ -43,6 +43,7 @@ union smp_flush_state {
 		struct mm_struct *flush_mm;
 		unsigned long flush_va;
 		raw_spinlock_t tlbstate_lock;
+		int sender_cpu;
 		DECLARE_BITMAP(flush_cpumask, NR_CPUS);
 	};
 	char pad[INTERNODE_CACHE_BYTES];

@@ -116,6 +117,9 @@ EXPORT_SYMBOL_GPL(leave_mm);
  *
  * Interrupts are disabled.
  */
+#ifdef CONFIG_PARAVIRT_FLUSH_TLB
+extern void kvm_kick_cpu(int cpu);
+#endif
 
 /*
  * FIXME: use of asmlinkage is not consistent.  On x86_64 it's noop

@@ -166,6 +170,10 @@ out:
 	smp_mb__before_clear_bit();
 	cpumask_clear_cpu(cpu, to_cpumask(f->flush_cpumask));
 	smp_mb__after_clear_bit();
+#ifdef CONFIG_PARAVIRT_FLUSH_TLB
+	if (cpumask_empty(to_cpumask(f->flush_cpumask)))
+		kvm_kick_cpu(f->sender_cpu);
+#endif
 	inc_irq_stat(irq_tlb_count);
 }
 

@@ -184,7 +192,10 @@ static void flush_tlb_others_ipi(const s
 
 	f->flush_mm = mm;
 	f->flush_va = va;
+	f->sender_cpu = smp_processor_id();
 	if (cpumask_andnot(to_cpumask(f->flush_cpumask), cpumask, cpumask_of(smp_processor_id()))) {
+		int loop = 1024;
+
 		/*
 		 * We have to send the IPI only to
 		 * CPUs affected.

@@ -192,8 +203,15 @@ static void flush_tlb_others_ipi(const s
 		apic->send_IPI_mask(to_cpumask(f->flush_cpumask),
 			      INVALIDATE_TLB_VECTOR_START + sender);
 
+#ifdef CONFIG_PARAVIRT_FLUSH_TLB
+		while (!cpumask_empty(to_cpumask(f->flush_cpumask)) && --loop)
+			cpu_relax();
+		if (!loop && !cpumask_empty(to_cpumask(f->flush_cpumask)))
+			halt();
+#else
 		while (!cpumask_empty(to_cpumask(f->flush_cpumask)))
 			cpu_relax();
+#endif
 	}
 
 	f->flush_mm = NULL;

@@ -653,16 +653,17 @@ out:
 PV_CALLEE_SAVE_REGS_THUNK(kvm_lock_spinning);
 
 /* Kick a cpu by its apicid*/
-static inline void kvm_kick_cpu(int apicid)
+void kvm_kick_cpu(int cpu)
 {
+	int apicid = per_cpu(x86_cpu_to_apicid, cpu);
 	kvm_hypercall1(KVM_HC_KICK_CPU, apicid);
 }
+EXPORT_SYMBOL_GPL(kvm_kick_cpu);
 
 /* Kick vcpu waiting on @lock->head to reach value @ticket */
 static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket)
 {
 	int cpu;
-	int apicid;
 
 	add_stats(RELEASED_SLOW, 1);
 

@@ -671,8 +672,7 @@ static void kvm_unlock_kick(struct arch_
 		if (ACCESS_ONCE(w->lock) == lock &&
 		    ACCESS_ONCE(w->want) == ticket) {
 			add_stats(RELEASED_SLOW_KICKED, 1);
-			apicid = per_cpu(x86_cpu_to_apicid, cpu);
-			kvm_kick_cpu(apicid);
+			kvm_kick_cpu(cpu);
 			break;
 		}
 	}