PM-runtime: Fix deadlock with ktime_get()

A deadlock has been seen when swicthing clocksources which use
PM-runtime.  The call path is:

change_clocksource
    ...
    write_seqcount_begin
    ...
    timekeeping_update
        ...
        sh_cmt_clocksource_enable
            ...
            rpm_resume
                pm_runtime_mark_last_busy
                    ktime_get
                        do
                            read_seqcount_begin
                        while read_seqcount_retry
    ....
    write_seqcount_end

Although we should be safe because we haven't yet changed the
clocksource at that time, we can't do that because of seqcount
protection.

Use ktime_get_mono_fast_ns() instead which is lock safe for such
cases.

With ktime_get_mono_fast_ns, the timestamp is not guaranteed to be
monotonic across an update and as a result can goes backward.
According to update_fast_timekeeper() description: "In the worst
case, this can result is a slightly wrong timestamp (a few
nanoseconds)". For PM-runtime autosuspend, this means only that
the suspend decision may be slightly suboptimal.

Fixes: 8234f6734c5d ("PM-runtime: Switch autosuspend over to using hrtimers")
Reported-by: Biju Das <biju.das@bp.renesas.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 457be03b744d276c9279b2a41686afdc49a05e20..0ea2139c50d875d0fdce8e9fb55374fd6bdc337b 100644 (file)
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -130,7 +130,7 @@ u64 pm_runtime_autosuspend_expiration(struct device *dev)
 {
        int autosuspend_delay;
        u64 last_busy, expires = 0;
-       u64 now = ktime_to_ns(ktime_get());
+       u64 now = ktime_get_mono_fast_ns();
 
        if (!dev->power.use_autosuspend)
                goto out;
@@ -909,7 +909,7 @@ static enum hrtimer_restart  pm_suspend_timer_fn(struct hrtimer *timer)
         * If 'expires' is after the current time, we've been called
         * too early.
         */
-       if (expires > 0 && expires < ktime_to_ns(ktime_get())) {
+       if (expires > 0 && expires < ktime_get_mono_fast_ns()) {
                dev->power.timer_expires = 0;
                rpm_suspend(dev, dev->power.timer_autosuspends ?
                    (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC);
@@ -928,7 +928,7 @@ static enum hrtimer_restart  pm_suspend_timer_fn(struct hrtimer *timer)
 int pm_schedule_suspend(struct device *dev, unsigned int delay)
 {
        unsigned long flags;
-       ktime_t expires;
+       u64 expires;
        int retval;
 
        spin_lock_irqsave(&dev->power.lock, flags);
@@ -945,8 +945,8 @@ int pm_schedule_suspend(struct device *dev, unsigned int delay)
        /* Other scheduled or pending requests need to be canceled. */
        pm_runtime_cancel_pending(dev);
 
-       expires = ktime_add(ktime_get(), ms_to_ktime(delay));
-       dev->power.timer_expires = ktime_to_ns(expires);
+       expires = ktime_get_mono_fast_ns() + (u64)delay * NSEC_PER_MSEC;
+       dev->power.timer_expires = expires;
        dev->power.timer_autosuspends = 0;
        hrtimer_start(&dev->power.suspend_timer, expires, HRTIMER_MODE_ABS);
 

diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 54af4eef169f3e6b8e775a2352a83f99cfa36b37..fed5be706bc9410dfd4b5593e2ea71b73067c00b 100644 (file)
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -105,7 +105,7 @@ static inline bool pm_runtime_callbacks_present(struct device *dev)
 
 static inline void pm_runtime_mark_last_busy(struct device *dev)
 {
-       WRITE_ONCE(dev->power.last_busy, ktime_to_ns(ktime_get()));
+       WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns());
 }
 
 static inline bool pm_runtime_is_irq_safe(struct device *dev)