One aspect worth noting is that cpumask_raise_softirq() gets brought in
sync here with cpu_raise_softirq() in that now both don't attempt to
raise a self-IPI on the processing CPU.

--- a/xen/arch/x86/acpi/cpu_idle.c
+++ b/xen/arch/x86/acpi/cpu_idle.c
@@ -340,6 +340,16 @@ void cpuidle_wakeup_mwait(cpumask_t *mas
     cpumask_andnot(mask, mask, &target);
 }
 
+bool_t arch_skip_send_event_check(unsigned int cpu)
+{
+    /*
+     * This relies on softirq_pending() and mwait_wakeup() to access data
+     * on the same cache line.
+     */
+    smp_mb();
+    return !!cpumask_test_cpu(cpu, &cpuidle_mwait_flags);
+}
+
 void mwait_idle_with_hints(unsigned int eax, unsigned int ecx)
 {
     unsigned int cpu = smp_processor_id();
@@ -359,7 +369,7 @@ void mwait_idle_with_hints(unsigned int 
      * Timer deadline passing is the event on which we will be woken via
      * cpuidle_mwait_wakeup. So check it now that the location is armed.
      */
-    if ( expires > NOW() || expires == 0 )
+    if ( (expires > NOW() || expires == 0) && !softirq_pending(cpu) )
     {
         cpumask_set_cpu(cpu, &cpuidle_mwait_flags);
         __mwait(eax, ecx);
--- a/xen/common/softirq.c
+++ b/xen/common/softirq.c
@@ -70,12 +70,14 @@ void open_softirq(int nr, softirq_handle
 
 void cpumask_raise_softirq(const cpumask_t *mask, unsigned int nr)
 {
-    int cpu;
+    unsigned int cpu, this_cpu = smp_processor_id();
     cpumask_t send_mask;
 
     cpumask_clear(&send_mask);
     for_each_cpu(cpu, mask)
-        if ( !test_and_set_bit(nr, &softirq_pending(cpu)) )
+        if ( !test_and_set_bit(nr, &softirq_pending(cpu)) &&
+             cpu != this_cpu &&
+             !arch_skip_send_event_check(cpu) )
             cpumask_set_cpu(cpu, &send_mask);
 
     smp_send_event_check_mask(&send_mask);
@@ -84,7 +86,8 @@ void cpumask_raise_softirq(const cpumask
 void cpu_raise_softirq(unsigned int cpu, unsigned int nr)
 {
     if ( !test_and_set_bit(nr, &softirq_pending(cpu))
-         && (cpu != smp_processor_id()) )
+         && (cpu != smp_processor_id())
+         && !arch_skip_send_event_check(cpu) )
         smp_send_event_check_cpu(cpu);
 }
 
--- a/xen/include/asm-arm/softirq.h
+++ b/xen/include/asm-arm/softirq.h
@@ -3,6 +3,8 @@
 
 #define NR_ARCH_SOFTIRQS       0
 
+#define arch_skip_send_event_check(cpu) 0
+
 #endif /* __ASM_SOFTIRQ_H__ */
 /*
  * Local variables:
--- a/xen/include/asm-x86/softirq.h
+++ b/xen/include/asm-x86/softirq.h
@@ -9,4 +9,6 @@
 #define PCI_SERR_SOFTIRQ       (NR_COMMON_SOFTIRQS + 4)
 #define NR_ARCH_SOFTIRQS       5
 
+bool_t arch_skip_send_event_check(unsigned int cpu);
+
 #endif /* __ASM_SOFTIRQ_H__ */