diff --git a/MAINTAINERS b/MAINTAINERS
index f66488d..3b035584 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8621,7 +8621,7 @@
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
-F:	kernel/membarrier.c
+F:	kernel/sched/membarrier.c
 F:	include/uapi/linux/membarrier.h
 
 MEMORY MANAGEMENT
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 659ae80..c8f7d98 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -360,6 +360,8 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
 	 * the thread migrates to a different CPU.
+	 * This full barrier is also required by the membarrier system
+	 * call.
 	 */
 	dsb(ish);
 
diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h
index e0b108b..6d47b32 100644
--- a/include/uapi/linux/membarrier.h
+++ b/include/uapi/linux/membarrier.h
@@ -40,14 +40,33 @@
  *                          (non-running threads are de facto in such a
  *                          state). This covers threads from all processes
  *                          running on the system. This command returns 0.
+ * @MEMBARRIER_CMD_PRIVATE_EXPEDITED:
+ *                          Execute a memory barrier on each running
+ *                          thread belonging to the same process as the current
+ *                          thread. Upon return from system call, the
+ *                          caller thread is ensured that all its running
+ *                          threads siblings have passed through a state
+ *                          where all memory accesses to user-space
+ *                          addresses match program order between entry
+ *                          to and return from the system call
+ *                          (non-running threads are de facto in such a
+ *                          state). This only covers threads from the
+ *                          same processes as the caller thread. This
+ *                          command returns 0. The "expedited" commands
+ *                          complete faster than the non-expedited ones,
+ *                          they never block, but have the downside of
+ *                          causing extra overhead.
  *
  * Command to be passed to the membarrier system call. The commands need to
  * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to
  * the value 0.
  */
 enum membarrier_cmd {
-	MEMBARRIER_CMD_QUERY = 0,
-	MEMBARRIER_CMD_SHARED = (1 << 0),
+	MEMBARRIER_CMD_QUERY			= 0,
+	MEMBARRIER_CMD_SHARED			= (1 << 0),
+	/* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */
+	/* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */
+	MEMBARRIER_CMD_PRIVATE_EXPEDITED	= (1 << 3),
 };
 
 #endif /* _UAPI_LINUX_MEMBARRIER_H */
diff --git a/kernel/Makefile b/kernel/Makefile
index 4cb8e8b..9c323a6 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -108,7 +108,6 @@
 obj-$(CONFIG_JUMP_LABEL) += jump_label.o
 obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o
 obj-$(CONFIG_TORTURE_TEST) += torture.o
-obj-$(CONFIG_MEMBARRIER) += membarrier.o
 
 obj-$(CONFIG_HAS_IOMEM) += memremap.o
 
diff --git a/kernel/membarrier.c b/kernel/membarrier.c
deleted file mode 100644
index 9f9284f..0000000
--- a/kernel/membarrier.c
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * Copyright (C) 2010, 2015 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
- *
- * membarrier system call
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/syscalls.h>
-#include <linux/membarrier.h>
-#include <linux/tick.h>
-
-/*
- * Bitmask made from a "or" of all commands within enum membarrier_cmd,
- * except MEMBARRIER_CMD_QUERY.
- */
-#define MEMBARRIER_CMD_BITMASK	(MEMBARRIER_CMD_SHARED)
-
-/**
- * sys_membarrier - issue memory barriers on a set of threads
- * @cmd:   Takes command values defined in enum membarrier_cmd.
- * @flags: Currently needs to be 0. For future extensions.
- *
- * If this system call is not implemented, -ENOSYS is returned. If the
- * command specified does not exist, or if the command argument is invalid,
- * this system call returns -EINVAL. For a given command, with flags argument
- * set to 0, this system call is guaranteed to always return the same value
- * until reboot.
- *
- * All memory accesses performed in program order from each targeted thread
- * is guaranteed to be ordered with respect to sys_membarrier(). If we use
- * the semantic "barrier()" to represent a compiler barrier forcing memory
- * accesses to be performed in program order across the barrier, and
- * smp_mb() to represent explicit memory barriers forcing full memory
- * ordering across the barrier, we have the following ordering table for
- * each pair of barrier(), sys_membarrier() and smp_mb():
- *
- * The pair ordering is detailed as (O: ordered, X: not ordered):
- *
- *                        barrier()   smp_mb() sys_membarrier()
- *        barrier()          X           X            O
- *        smp_mb()           X           O            O
- *        sys_membarrier()   O           O            O
- */
-SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
-{
-	/* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */
-	if (tick_nohz_full_enabled())
-		return -ENOSYS;
-	if (unlikely(flags))
-		return -EINVAL;
-	switch (cmd) {
-	case MEMBARRIER_CMD_QUERY:
-		return MEMBARRIER_CMD_BITMASK;
-	case MEMBARRIER_CMD_SHARED:
-		if (num_online_cpus() > 1)
-			synchronize_sched();
-		return 0;
-	default:
-		return -EINVAL;
-	}
-}
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 53f0164..78f5493 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -25,3 +25,4 @@
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
 obj-$(CONFIG_CPU_FREQ) += cpufreq.o
 obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
+obj-$(CONFIG_MEMBARRIER) += membarrier.o
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bfee6ea..f77269c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2640,6 +2640,16 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	prev_state = prev->state;
 	vtime_task_switch(prev);
 	perf_event_task_sched_in(prev, current);
+	/*
+	 * The membarrier system call requires a full memory barrier
+	 * after storing to rq->curr, before going back to user-space.
+	 *
+	 * TODO: This smp_mb__after_unlock_lock can go away if PPC end
+	 * up adding a full barrier to switch_mm(), or we should figure
+	 * out if a smp_mb__after_unlock_lock is really the proper API
+	 * to use.
+	 */
+	smp_mb__after_unlock_lock();
 	finish_lock_switch(rq, prev);
 	finish_arch_post_lock_switch();
 
@@ -3329,6 +3339,21 @@ static void __sched notrace __schedule(bool preempt)
 	if (likely(prev != next)) {
 		rq->nr_switches++;
 		rq->curr = next;
+		/*
+		 * The membarrier system call requires each architecture
+		 * to have a full memory barrier after updating
+		 * rq->curr, before returning to user-space. For TSO
+		 * (e.g. x86), the architecture must provide its own
+		 * barrier in switch_mm(). For weakly ordered machines
+		 * for which spin_unlock() acts as a full memory
+		 * barrier, finish_lock_switch() in common code takes
+		 * care of this barrier. For weakly ordered machines for
+		 * which spin_unlock() acts as a RELEASE barrier (only
+		 * arm64 and PowerPC), arm64 has a full barrier in
+		 * switch_to(), and PowerPC has
+		 * smp_mb__after_unlock_lock() before
+		 * finish_lock_switch().
+		 */
 		++*switch_count;
 
 		trace_sched_switch(preempt, prev, next);
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
new file mode 100644
index 0000000..a92fddc
--- /dev/null
+++ b/kernel/sched/membarrier.c
@@ -0,0 +1,152 @@
+/*
+ * Copyright (C) 2010-2017 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * membarrier system call
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/syscalls.h>
+#include <linux/membarrier.h>
+#include <linux/tick.h>
+#include <linux/cpumask.h>
+
+#include "sched.h"	/* for cpu_rq(). */
+
+/*
+ * Bitmask made from a "or" of all commands within enum membarrier_cmd,
+ * except MEMBARRIER_CMD_QUERY.
+ */
+#define MEMBARRIER_CMD_BITMASK	\
+	(MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED)
+
+static void ipi_mb(void *info)
+{
+	smp_mb();	/* IPIs should be serializing but paranoid. */
+}
+
+static void membarrier_private_expedited(void)
+{
+	int cpu;
+	bool fallback = false;
+	cpumask_var_t tmpmask;
+
+	if (num_online_cpus() == 1)
+		return;
+
+	/*
+	 * Matches memory barriers around rq->curr modification in
+	 * scheduler.
+	 */
+	smp_mb();	/* system call entry is not a mb. */
+
+	/*
+	 * Expedited membarrier commands guarantee that they won't
+	 * 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();
+	for_each_online_cpu(cpu) {
+		struct task_struct *p;
+
+		/*
+		 * Skipping the current CPU is OK even through we can be
+		 * migrated at any point. The current CPU, at the point
+		 * where we read raw_smp_processor_id(), is ensured to
+		 * be in program order with respect to the caller
+		 * thread. Therefore, we can skip this CPU from the
+		 * iteration.
+		 */
+		if (cpu == raw_smp_processor_id())
+			continue;
+		rcu_read_lock();
+		p = task_rcu_dereference(&cpu_rq(cpu)->curr);
+		if (p && p->mm == current->mm) {
+			if (!fallback)
+				__cpumask_set_cpu(cpu, tmpmask);
+			else
+				smp_call_function_single(cpu, ipi_mb, NULL, 1);
+		}
+		rcu_read_unlock();
+	}
+	if (!fallback) {
+		smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+		free_cpumask_var(tmpmask);
+	}
+	cpus_read_unlock();
+
+	/*
+	 * Memory barrier on the caller thread _after_ we finished
+	 * waiting for the last IPI. Matches memory barriers around
+	 * rq->curr modification in scheduler.
+	 */
+	smp_mb();	/* exit from system call is not a mb */
+}
+
+/**
+ * sys_membarrier - issue memory barriers on a set of threads
+ * @cmd:   Takes command values defined in enum membarrier_cmd.
+ * @flags: Currently needs to be 0. For future extensions.
+ *
+ * If this system call is not implemented, -ENOSYS is returned. If the
+ * command specified does not exist, not available on the running
+ * kernel, or if the command argument is invalid, this system call
+ * returns -EINVAL. For a given command, with flags argument set to 0,
+ * this system call is guaranteed to always return the same value until
+ * reboot.
+ *
+ * All memory accesses performed in program order from each targeted thread
+ * is guaranteed to be ordered with respect to sys_membarrier(). If we use
+ * the semantic "barrier()" to represent a compiler barrier forcing memory
+ * accesses to be performed in program order across the barrier, and
+ * smp_mb() to represent explicit memory barriers forcing full memory
+ * ordering across the barrier, we have the following ordering table for
+ * each pair of barrier(), sys_membarrier() and smp_mb():
+ *
+ * The pair ordering is detailed as (O: ordered, X: not ordered):
+ *
+ *                        barrier()   smp_mb() sys_membarrier()
+ *        barrier()          X           X            O
+ *        smp_mb()           X           O            O
+ *        sys_membarrier()   O           O            O
+ */
+SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
+{
+	if (unlikely(flags))
+		return -EINVAL;
+	switch (cmd) {
+	case MEMBARRIER_CMD_QUERY:
+	{
+		int cmd_mask = MEMBARRIER_CMD_BITMASK;
+
+		if (tick_nohz_full_enabled())
+			cmd_mask &= ~MEMBARRIER_CMD_SHARED;
+		return cmd_mask;
+	}
+	case MEMBARRIER_CMD_SHARED:
+		/* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */
+		if (tick_nohz_full_enabled())
+			return -EINVAL;
+		if (num_online_cpus() > 1)
+			synchronize_sched();
+		return 0;
+	case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
+		membarrier_private_expedited();
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}