Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnad:
 "The main RCU related changes in this cycle were:

   - Removal of spin_unlock_wait()
   - SRCU updates
   - RCU torture-test updates
   - RCU Documentation updates
   - Extend the sys_membarrier() ABI with the MEMBARRIER_CMD_PRIVATE_EXPEDITED variant
   - Miscellaneous RCU fixes
   - CPU-hotplug fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (63 commits)
  arch: Remove spin_unlock_wait() arch-specific definitions
  locking: Remove spin_unlock_wait() generic definitions
  drivers/ata: Replace spin_unlock_wait() with lock/unlock pair
  ipc: Replace spin_unlock_wait() with lock/unlock pair
  exit: Replace spin_unlock_wait() with lock/unlock pair
  completion: Replace spin_unlock_wait() with lock/unlock pair
  doc: Set down RCU's scheduling-clock-interrupt needs
  doc: No longer allowed to use rcu_dereference on non-pointers
  doc: Add RCU files to docbook-generation files
  doc: Update memory-barriers.txt for read-to-write dependencies
  doc: Update RCU documentation
  membarrier: Provide expedited private command
  rcu: Remove exports from rcu_idle_exit() and rcu_idle_enter()
  rcu: Add warning to rcu_idle_enter() for irqs enabled
  rcu: Make rcu_idle_enter() rely on callers disabling irqs
  rcu: Add assertions verifying blocked-tasks list
  rcu/tracing: Set disable_rcu_irq_enter on rcu_eqs_exit()
  rcu: Add TPS() protection for _rcu_barrier_trace strings
  rcu: Use idle versions of swait to make idle-hack clear
  swait: Add idle variants which don't contribute to load average
  ...

kernel/sched/Makefile

@@ -25,3 +25,4 @@ obj-$(CONFIG_SCHED_DEBUG) += debug.o
 obj-$(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

kernel/sched/completion.c

@@ -300,6 +300,8 @@ EXPORT_SYMBOL(try_wait_for_completion);
  */
 bool completion_done(struct completion *x)
 {
+	unsigned long flags;
+
 	if (!READ_ONCE(x->done))
 		return false;
 
@@ -307,14 +309,9 @@ bool completion_done(struct completion *x)
 	 * If ->done, we need to wait for complete() to release ->wait.lock
 	 * otherwise we can end up freeing the completion before complete()
 	 * is done referencing it.
-	 *
-	 * The RMB pairs with complete()'s RELEASE of ->wait.lock and orders
-	 * the loads of ->done and ->wait.lock such that we cannot observe
-	 * the lock before complete() acquires it while observing the ->done
-	 * after it's acquired the lock.
 	 */
-	smp_rmb();
-	spin_unlock_wait(&x->wait.lock);
+	spin_lock_irqsave(&x->wait.lock, flags);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
 	return true;
 }
 EXPORT_SYMBOL(completion_done);

kernel/sched/core.c

@@ -951,8 +951,13 @@ struct migration_arg {
 static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
 				 struct task_struct *p, int dest_cpu)
 {
-	if (unlikely(!cpu_active(dest_cpu)))
-		return rq;
+	if (p->flags & PF_KTHREAD) {
+		if (unlikely(!cpu_online(dest_cpu)))
+			return rq;
+	} else {
+		if (unlikely(!cpu_active(dest_cpu)))
+			return rq;
+	}
 
 	/* Affinity changed (again). */
 	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
@@ -2635,6 +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();
 
@@ -3324,6 +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);
@@ -3352,8 +3382,8 @@ void __noreturn do_task_dead(void)
 	 * To avoid it, we have to wait for releasing tsk->pi_lock which
 	 * is held by try_to_wake_up()
 	 */
-	smp_mb();
-	raw_spin_unlock_wait(&current->pi_lock);
+	raw_spin_lock_irq(&current->pi_lock);
+	raw_spin_unlock_irq(&current->pi_lock);
 
 	/* Causes final put_task_struct in finish_task_switch(): */
 	__set_current_state(TASK_DEAD);

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;
+	}
+}