[PATCH] clustered IPI cleanups

This one fixes up the IPI code to do something more sensible.  Sorry,
was just too ugly to leave it alone ...  but I did keep it seperated out
;-) Though this is not an equivalent transform it will only affect
NUMA-Q & summit - same op twice because some twit just split it out in
the last patch for both NUMA-Q & Summit.

Because clustered apic logical mode can't do arbitrary broadcasts of
addressing (it's not just a bitmap), I have to do send IPI instructions
as a sequence of unicasts.  However, there's already a loop in the
generic send_IPI_mask code to do that ...  there's no need to call
send_IPI_mask once for each CPU.  The comment I wrote at the time even
noted that this was silly.

include/asm-i386/mach-numaq/mach_ipi.h

@@ -10,30 +10,15 @@ static inline void send_IPI_mask(int mask, int vector)
 
 static inline void send_IPI_allbutself(int vector)
 {
-	int cpu;
-	/*
-	 * if there are no other CPUs in the system then we get an APIC send 
-	 * error if we try to broadcast, thus avoid sending IPIs in this case.
-	 */
-	if (!(num_online_cpus() > 1))
-		return;
+	unsigned long mask = cpu_online_map & ~(1 << smp_processor_id());
 
-	/* Pointless. Use send_IPI_mask to do this instead */
-	for (cpu = 0; cpu < NR_CPUS; ++cpu)
-		if (cpu_online(cpu) && cpu != smp_processor_id())
-			send_IPI_mask(1 << cpu, vector);
-
-	return;
+	if (mask)
+		send_IPI_mask(mask, vector);
 }
 
 static inline void send_IPI_all(int vector)
 {
-	int cpu;
-
-	/* Pointless. Use send_IPI_mask to do this instead */
-	for (cpu = 0; cpu < NR_CPUS; ++cpu)
-		if (cpu_online(cpu))
-			send_IPI_mask(1 << cpu, vector);
+	send_IPI_mask(cpu_online_map, vector);
 }
 
 #endif /* __ASM_MACH_IPI_H */

include/asm-i386/mach-summit/mach_ipi.h

@@ -10,30 +10,15 @@ static inline void send_IPI_mask(int mask, int vector)
 
 static inline void send_IPI_allbutself(int vector)
 {
-	int cpu;
-	/*
-	 * if there are no other CPUs in the system then we get an APIC send 
-	 * error if we try to broadcast, thus avoid sending IPIs in this case.
-	 */
-	if (!(num_online_cpus() > 1))
-		return;
+	unsigned long mask = cpu_online_map & ~(1 << smp_processor_id());
 
-	/* Pointless. Use send_IPI_mask to do this instead */
-	for (cpu = 0; cpu < NR_CPUS; ++cpu)
-		if (cpu_online(cpu) && cpu != smp_processor_id())
-			send_IPI_mask(1 << cpu, vector);
-
-	return;
+	if (mask)
+		send_IPI_mask(mask, vector);
 }
 
 static inline void send_IPI_all(int vector)
 {
-	int cpu;
-
-	/* Pointless. Use send_IPI_mask to do this instead */
-	for (cpu = 0; cpu < NR_CPUS; ++cpu)
-		if (cpu_online(cpu))
-			send_IPI_mask(1 << cpu, vector);
+	send_IPI_mask(cpu_online_map, vector);
 }
 
 #endif /* __ASM_MACH_IPI_H */