sched/membarrier: Return -ENOMEM to userspace on memory allocation failure

Remove the IPI fallback code from membarrier to deal with very
infrequent cpumask memory allocation failure. Use GFP_KERNEL rather
than GFP_NOWAIT, and relax the blocking guarantees for the expedited
membarrier system call commands, allowing it to block if waiting for
memory to be made available.

In addition, now -ENOMEM can be returned to user-space if the cpumask
memory allocation fails.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King - ARM Linux admin <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20190919173705.2181-8-mathieu.desnoyers@efficios.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/membarrier.c

@@ -66,7 +66,6 @@ void membarrier_exec_mmap(struct mm_struct *mm)
 static int membarrier_global_expedited(void)
 {
 	int cpu;
-	bool fallback = false;
 	cpumask_var_t tmpmask;
 
 	if (num_online_cpus() == 1)
@@ -78,15 +77,8 @@ static int membarrier_global_expedited(void)
 	 */
 	smp_mb();	/* system call entry is not a mb. */
 
-	/*
+	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
-	 * Expedited membarrier commands guarantee that they won't
+		return -ENOMEM;
-	 * block, hence the GFP_NOWAIT allocation flag and fallback
-	 * implementation.
-	 */
-	if (!zalloc_cpumask_var(&tmpmask, GFP_NOWAIT)) {
-		/* Fallback for OOM. */
-		fallback = true;
-	}
 
 	cpus_read_lock();
 	rcu_read_lock();
@@ -117,18 +109,15 @@ static int membarrier_global_expedited(void)
 		if (p->flags & PF_KTHREAD)
 			continue;
 
-		if (!fallback)
+		__cpumask_set_cpu(cpu, tmpmask);
-			__cpumask_set_cpu(cpu, tmpmask);
-		else
-			smp_call_function_single(cpu, ipi_mb, NULL, 1);
 	}
 	rcu_read_unlock();
-	if (!fallback) {
+
-		preempt_disable();
+	preempt_disable();
-		smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+	smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
-		preempt_enable();
+	preempt_enable();
-		free_cpumask_var(tmpmask);
+
-	}
+	free_cpumask_var(tmpmask);
 	cpus_read_unlock();
 
 	/*
@@ -143,7 +132,6 @@ static int membarrier_global_expedited(void)
 static int membarrier_private_expedited(int flags)
 {
 	int cpu;
-	bool fallback = false;
 	cpumask_var_t tmpmask;
 	struct mm_struct *mm = current->mm;
 
@@ -168,15 +156,8 @@ static int membarrier_private_expedited(int flags)
 	 */
 	smp_mb();	/* system call entry is not a mb. */
 
-	/*
+	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
-	 * Expedited membarrier commands guarantee that they won't
+		return -ENOMEM;
-	 * block, hence the GFP_NOWAIT allocation flag and fallback
-	 * implementation.
-	 */
-	if (!zalloc_cpumask_var(&tmpmask, GFP_NOWAIT)) {
-		/* Fallback for OOM. */
-		fallback = true;
-	}
 
 	cpus_read_lock();
 	rcu_read_lock();
@@ -195,20 +176,16 @@ static int membarrier_private_expedited(int flags)
 			continue;
 		rcu_read_lock();
 		p = rcu_dereference(cpu_rq(cpu)->curr);
-		if (p && p->mm == mm) {
+		if (p && p->mm == mm)
-			if (!fallback)
+			__cpumask_set_cpu(cpu, tmpmask);
-				__cpumask_set_cpu(cpu, tmpmask);
-			else
-				smp_call_function_single(cpu, ipi_mb, NULL, 1);
-		}
 	}
 	rcu_read_unlock();
-	if (!fallback) {
+
-		preempt_disable();
+	preempt_disable();
-		smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+	smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
-		preempt_enable();
+	preempt_enable();
-		free_cpumask_var(tmpmask);
+
-	}
+	free_cpumask_var(tmpmask);
 	cpus_read_unlock();
 
 	/*
@@ -264,7 +241,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm)
 		struct rq *rq = cpu_rq(cpu);
 		struct task_struct *p;
 
-		p = rcu_dereference(&rq->curr);
+		p = rcu_dereference(rq->curr);
 		if (p && p->mm == mm)
 			__cpumask_set_cpu(cpu, tmpmask);
 	}