PM: runtime: Avoid device usage count underflows

A PM-runtime device usage count underflow is potentially critical,
because it may cause a device to be suspended when it is expected to
be operational.  It is also a programming problem that would be good
to catch and warn about.

For this reason, (1) make rpm_check_suspend_allowed() return an error
when the device usage count is negative to prevent devices from being
suspended in that case, (2) introduce rpm_drop_usage_count() that will
detect device usage count underflows, warn about them and fix them up,
and (3) use it to drop the usage count in a few places instead of
atomic_dec_and_test().

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
This commit is contained in:
Rafael J. Wysocki 2022-04-13 17:30:32 +02:00
parent bd8284e968
commit 82586a7215

View File

@ -263,7 +263,7 @@ static int rpm_check_suspend_allowed(struct device *dev)
retval = -EINVAL;
else if (dev->power.disable_depth > 0)
retval = -EACCES;
else if (atomic_read(&dev->power.usage_count) > 0)
else if (atomic_read(&dev->power.usage_count))
retval = -EAGAIN;
else if (!dev->power.ignore_children &&
atomic_read(&dev->power.child_count))
@ -1039,13 +1039,33 @@ int pm_schedule_suspend(struct device *dev, unsigned int delay)
}
EXPORT_SYMBOL_GPL(pm_schedule_suspend);
static int rpm_drop_usage_count(struct device *dev)
{
int ret;
ret = atomic_sub_return(1, &dev->power.usage_count);
if (ret >= 0)
return ret;
/*
* Because rpm_resume() does not check the usage counter, it will resume
* the device even if the usage counter is 0 or negative, so it is
* sufficient to increment the usage counter here to reverse the change
* made above.
*/
atomic_inc(&dev->power.usage_count);
dev_warn(dev, "Runtime PM usage count underflow!\n");
return -EINVAL;
}
/**
* __pm_runtime_idle - Entry point for runtime idle operations.
* @dev: Device to send idle notification for.
* @rpmflags: Flag bits.
*
* If the RPM_GET_PUT flag is set, decrement the device's usage count and
* return immediately if it is larger than zero. Then carry out an idle
* return immediately if it is larger than zero (if it becomes negative, log a
* warning, increment it, and return an error). Then carry out an idle
* notification, either synchronous or asynchronous.
*
* This routine may be called in atomic context if the RPM_ASYNC flag is set,
@ -1057,7 +1077,10 @@ int __pm_runtime_idle(struct device *dev, int rpmflags)
int retval;
if (rpmflags & RPM_GET_PUT) {
if (!atomic_dec_and_test(&dev->power.usage_count)) {
retval = rpm_drop_usage_count(dev);
if (retval < 0) {
return retval;
} else if (retval > 0) {
trace_rpm_usage_rcuidle(dev, rpmflags);
return 0;
}
@ -1079,7 +1102,8 @@ EXPORT_SYMBOL_GPL(__pm_runtime_idle);
* @rpmflags: Flag bits.
*
* If the RPM_GET_PUT flag is set, decrement the device's usage count and
* return immediately if it is larger than zero. Then carry out a suspend,
* return immediately if it is larger than zero (if it becomes negative, log a
* warning, increment it, and return an error). Then carry out a suspend,
* either synchronous or asynchronous.
*
* This routine may be called in atomic context if the RPM_ASYNC flag is set,
@ -1091,7 +1115,10 @@ int __pm_runtime_suspend(struct device *dev, int rpmflags)
int retval;
if (rpmflags & RPM_GET_PUT) {
if (!atomic_dec_and_test(&dev->power.usage_count)) {
retval = rpm_drop_usage_count(dev);
if (retval < 0) {
return retval;
} else if (retval > 0) {
trace_rpm_usage_rcuidle(dev, rpmflags);
return 0;
}
@ -1527,14 +1554,17 @@ EXPORT_SYMBOL_GPL(pm_runtime_forbid);
*/
void pm_runtime_allow(struct device *dev)
{
int ret;
spin_lock_irq(&dev->power.lock);
if (dev->power.runtime_auto)
goto out;
dev->power.runtime_auto = true;
if (atomic_dec_and_test(&dev->power.usage_count))
ret = rpm_drop_usage_count(dev);
if (ret == 0)
rpm_idle(dev, RPM_AUTO | RPM_ASYNC);
else
else if (ret > 0)
trace_rpm_usage_rcuidle(dev, RPM_AUTO | RPM_ASYNC);
out: