smp: Avoid sending needless IPI in smp_call_function_many()

Inter-Processor-Interrupt(IPI) is needed when a page is unmapped and the
process' mm_cpumask() shows the process has ever run on other CPUs. page
migration, page reclaim all need IPIs. The number of IPI needed to send
to different CPUs is especially large for multi-threaded workload since
mm_cpumask() is per process.

For smp_call_function_many(), whenever a CPU queues a CSD to a target
CPU, it will send an IPI to let the target CPU to handle the work.
This isn't necessary - we need only send IPI when queueing a CSD
to an empty call_single_queue.

The reason:

flush_smp_call_function_queue() that is called upon a CPU receiving an
IPI will empty the queue and then handle all of the CSDs there. So if
the target CPU's call_single_queue is not empty, we know that:
i.  An IPI for the target CPU has already been sent by 'previous queuers';
ii. flush_smp_call_function_queue() hasn't emptied that CPU's queue yet.
Thus, it's safe for us to just queue our CSD there without sending an
addtional IPI. And for the 'previous queuers', we can limit it to the
first queuer.

To demonstrate the effect of this patch, a multi-thread workload that
spawns 80 threads to equally consume 100G memory is used. This is tested
on a 2 node broadwell-EP which has 44cores/88threads and 32G memory. So
after 32G memory is used up, page reclaiming starts to happen a lot.

With this patch, IPI number dropped 88% and throughput increased about
15% for the above workload.
Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Link: http://lkml.kernel.org/r/20170519075331.GE2084@aaronlu.sh.intel.comSigned-off-by: Ingo Molnar <mingo@kernel.org>

kernel/smp.c

@@ -30,6 +30,7 @@ enum {
 struct call_function_data {
 	struct call_single_data	__percpu *csd;
 	cpumask_var_t		cpumask;
+	cpumask_var_t		cpumask_ipi;
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
@@ -45,9 +46,15 @@ int smpcfd_prepare_cpu(unsigned int cpu)
 	if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
 				     cpu_to_node(cpu)))
 		return -ENOMEM;
+	if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL,
+				     cpu_to_node(cpu))) {
+		free_cpumask_var(cfd->cpumask);
+		return -ENOMEM;
+	}
 	cfd->csd = alloc_percpu(struct call_single_data);
 	if (!cfd->csd) {
 		free_cpumask_var(cfd->cpumask);
+		free_cpumask_var(cfd->cpumask_ipi);
 		return -ENOMEM;
 	}
 
@@ -59,6 +66,7 @@ int smpcfd_dead_cpu(unsigned int cpu)
 	struct call_function_data *cfd = &per_cpu(cfd_data, cpu);
 
 	free_cpumask_var(cfd->cpumask);
+	free_cpumask_var(cfd->cpumask_ipi);
 	free_percpu(cfd->csd);
 	return 0;
 }
@@ -434,6 +442,7 @@ void smp_call_function_many(const struct cpumask *mask,
 	if (unlikely(!cpumask_weight(cfd->cpumask)))
 		return;
 
+	cpumask_clear(cfd->cpumask_ipi);
 	for_each_cpu(cpu, cfd->cpumask) {
 		struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu);
 
@@ -442,11 +451,12 @@ void smp_call_function_many(const struct cpumask *mask,
 			csd->flags |= CSD_FLAG_SYNCHRONOUS;
 		csd->func = func;
 		csd->info = info;
-		llist_add(&csd->llist, &per_cpu(call_single_queue, cpu));
+		if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
+			cpumask_set_cpu(cpu, cfd->cpumask_ipi);
 	}
 
 	/* Send a message to all CPUs in the map */
-	arch_send_call_function_ipi_mask(cfd->cpumask);
+	arch_send_call_function_ipi_mask(cfd->cpumask_ipi);
 
 	if (wait) {
 		for_each_cpu(cpu, cfd->cpumask) {