alistair23-linux/kernel/sched/swait.c
Boqun Feng 35a2897c2a sched/wait: Remove the lockless swait_active() check in swake_up*()
Steven Rostedt reported a potential race in RCU core because of
swake_up():

        CPU0                            CPU1
        ----                            ----
                                __call_rcu_core() {

                                 spin_lock(rnp_root)
                                 need_wake = __rcu_start_gp() {
                                  rcu_start_gp_advanced() {
                                   gp_flags = FLAG_INIT
                                  }
                                 }

 rcu_gp_kthread() {
   swait_event_interruptible(wq,
        gp_flags & FLAG_INIT) {
   spin_lock(q->lock)

                                *fetch wq->task_list here! *

   list_add(wq->task_list, q->task_list)
   spin_unlock(q->lock);

   *fetch old value of gp_flags here *

                                 spin_unlock(rnp_root)

                                 rcu_gp_kthread_wake() {
                                  swake_up(wq) {
                                   swait_active(wq) {
                                    list_empty(wq->task_list)

                                   } * return false *

  if (condition) * false *
    schedule();

In this case, a wakeup is missed, which could cause the rcu_gp_kthread
waits for a long time.

The reason of this is that we do a lockless swait_active() check in
swake_up(). To fix this, we can either 1) add a smp_mb() in swake_up()
before swait_active() to provide the proper order or 2) simply remove
the swait_active() in swake_up().

The solution 2 not only fixes this problem but also keeps the swait and
wait API as close as possible, as wake_up() doesn't provide a full
barrier and doesn't do a lockless check of the wait queue either.
Moreover, there are users already using swait_active() to do their quick
checks for the wait queues, so it make less sense that swake_up() and
swake_up_all() do this on their own.

This patch then removes the lockless swait_active() check in swake_up()
and swake_up_all().

Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Krister Johansen <kjlx@templeofstupid.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170615041828.zk3a3sfyudm5p6nl@tardis
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-08-10 12:28:53 +02:00

118 lines
2.9 KiB
C

#include <linux/sched/signal.h>
#include <linux/swait.h>
void __init_swait_queue_head(struct swait_queue_head *q, const char *name,
struct lock_class_key *key)
{
raw_spin_lock_init(&q->lock);
lockdep_set_class_and_name(&q->lock, key, name);
INIT_LIST_HEAD(&q->task_list);
}
EXPORT_SYMBOL(__init_swait_queue_head);
/*
* The thing about the wake_up_state() return value; I think we can ignore it.
*
* If for some reason it would return 0, that means the previously waiting
* task is already running, so it will observe condition true (or has already).
*/
void swake_up_locked(struct swait_queue_head *q)
{
struct swait_queue *curr;
if (list_empty(&q->task_list))
return;
curr = list_first_entry(&q->task_list, typeof(*curr), task_list);
wake_up_process(curr->task);
list_del_init(&curr->task_list);
}
EXPORT_SYMBOL(swake_up_locked);
void swake_up(struct swait_queue_head *q)
{
unsigned long flags;
raw_spin_lock_irqsave(&q->lock, flags);
swake_up_locked(q);
raw_spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(swake_up);
/*
* Does not allow usage from IRQ disabled, since we must be able to
* release IRQs to guarantee bounded hold time.
*/
void swake_up_all(struct swait_queue_head *q)
{
struct swait_queue *curr;
LIST_HEAD(tmp);
raw_spin_lock_irq(&q->lock);
list_splice_init(&q->task_list, &tmp);
while (!list_empty(&tmp)) {
curr = list_first_entry(&tmp, typeof(*curr), task_list);
wake_up_state(curr->task, TASK_NORMAL);
list_del_init(&curr->task_list);
if (list_empty(&tmp))
break;
raw_spin_unlock_irq(&q->lock);
raw_spin_lock_irq(&q->lock);
}
raw_spin_unlock_irq(&q->lock);
}
EXPORT_SYMBOL(swake_up_all);
void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
{
wait->task = current;
if (list_empty(&wait->task_list))
list_add(&wait->task_list, &q->task_list);
}
void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state)
{
unsigned long flags;
raw_spin_lock_irqsave(&q->lock, flags);
__prepare_to_swait(q, wait);
set_current_state(state);
raw_spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(prepare_to_swait);
long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state)
{
if (signal_pending_state(state, current))
return -ERESTARTSYS;
prepare_to_swait(q, wait, state);
return 0;
}
EXPORT_SYMBOL(prepare_to_swait_event);
void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait)
{
__set_current_state(TASK_RUNNING);
if (!list_empty(&wait->task_list))
list_del_init(&wait->task_list);
}
void finish_swait(struct swait_queue_head *q, struct swait_queue *wait)
{
unsigned long flags;
__set_current_state(TASK_RUNNING);
if (!list_empty_careful(&wait->task_list)) {
raw_spin_lock_irqsave(&q->lock, flags);
list_del_init(&wait->task_list);
raw_spin_unlock_irqrestore(&q->lock, flags);
}
}
EXPORT_SYMBOL(finish_swait);