delayacct: Use raw_spinlocks

[ Upstream commit 02acc80d19edb0d5684c997b2004ad19f9f5236e ]

try_to_wake_up() might invoke delayacct_blkio_end() while holding the
pi_lock (which is a raw_spinlock_t). delayacct_blkio_end() acquires
task_delay_info.lock which is a spinlock_t. This causes a might sleep splat
on -RT where non raw spinlocks are converted to 'sleeping' spinlocks.

task_delay_info.lock is only held for a short amount of time so it's not a
problem latency wise to make convert it to a raw spinlock.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Balbir Singh <bsingharora@gmail.com>
Link: https://lkml.kernel.org/r/20180423161024.6710-1-bigeasy@linutronix.de
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 41ee6de..31c865d 100644 (file)
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -29,7 +29,7 @@
 
 #ifdef CONFIG_TASK_DELAY_ACCT
 struct task_delay_info {
-       spinlock_t      lock;
+       raw_spinlock_t  lock;
        unsigned int    flags;  /* Private per-task flags */
 
        /* For each stat XXX, add following, aligned appropriately

diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index e2764d7..ca8ac28 100644 (file)
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -44,23 +44,24 @@ void __delayacct_tsk_init(struct task_struct *tsk)
 {
        tsk->delays = kmem_cache_zalloc(delayacct_cache, GFP_KERNEL);
        if (tsk->delays)
-               spin_lock_init(&tsk->delays->lock);
+               raw_spin_lock_init(&tsk->delays->lock);
 }
 
 /*
  * Finish delay accounting for a statistic using its timestamps (@start),
  * accumalator (@total) and @count
  */
-static void delayacct_end(spinlock_t *lock, u64 *start, u64 *total, u32 *count)
+static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total,
+                         u32 *count)
 {
        s64 ns = ktime_get_ns() - *start;
        unsigned long flags;
 
        if (ns > 0) {
-               spin_lock_irqsave(lock, flags);
+               raw_spin_lock_irqsave(lock, flags);
                *total += ns;
                (*count)++;
-               spin_unlock_irqrestore(lock, flags);
+               raw_spin_unlock_irqrestore(lock, flags);
        }
 }
 
@@ -127,7 +128,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 
        /* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */
 
-       spin_lock_irqsave(&tsk->delays->lock, flags);
+       raw_spin_lock_irqsave(&tsk->delays->lock, flags);
        tmp = d->blkio_delay_total + tsk->delays->blkio_delay;
        d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp;
        tmp = d->swapin_delay_total + tsk->delays->swapin_delay;
@@ -137,7 +138,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
        d->blkio_count += tsk->delays->blkio_count;
        d->swapin_count += tsk->delays->swapin_count;
        d->freepages_count += tsk->delays->freepages_count;
-       spin_unlock_irqrestore(&tsk->delays->lock, flags);
+       raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
 
        return 0;
 }
@@ -147,10 +148,10 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk)
        __u64 ret;
        unsigned long flags;
 
-       spin_lock_irqsave(&tsk->delays->lock, flags);
+       raw_spin_lock_irqsave(&tsk->delays->lock, flags);
        ret = nsec_to_clock_t(tsk->delays->blkio_delay +
                                tsk->delays->swapin_delay);
-       spin_unlock_irqrestore(&tsk->delays->lock, flags);
+       raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
        return ret;
 }