sched/membarrier: reduce the ability to hammer on sys_membarrier

commit 944d5fe50f3f03daacfea16300e656a1691c4a23 upstream.

On some systems, sys_membarrier can be very expensive, causing overall
slowdowns for everything.  So put a lock on the path in order to
serialize the accesses to prevent the ability for this to be called at
too high of a frequency and saturate the machine.

Reviewed-and-tested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Fixes: 22e4ebb975 ("membarrier: Provide expedited private command")
Fixes: c5f58bd58f ("membarrier: Provide GLOBAL_EXPEDITED command")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

kernel/sched/membarrier.c

@@ -161,6 +161,9 @@
 	| MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK		\
 	| MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
 
+static DEFINE_MUTEX(membarrier_ipi_mutex);
+#define SERIALIZE_IPI() guard(mutex)(&membarrier_ipi_mutex)
+
 static void ipi_mb(void *info)
 {
 	smp_mb();	/* IPIs should be serializing but paranoid. */
@@ -258,6 +261,7 @@ static int membarrier_global_expedited(void)
 	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
 		return -ENOMEM;
 
+	SERIALIZE_IPI();
 	cpus_read_lock();
 	rcu_read_lock();
 	for_each_online_cpu(cpu) {
@@ -346,6 +350,7 @@ static int membarrier_private_expedited(int flags, int cpu_id)
 	if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
 		return -ENOMEM;
 
+	SERIALIZE_IPI();
 	cpus_read_lock();
 
 	if (cpu_id >= 0) {
@@ -459,6 +464,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm)
 	 * between threads which are users of @mm has its membarrier state
 	 * updated.
 	 */
+	SERIALIZE_IPI();
 	cpus_read_lock();
 	rcu_read_lock();
 	for_each_online_cpu(cpu) {