diff mbox

[V2,5/6] cpufreq: governor: replace per-cpu delayed work with timers

Message ID 20151204061101.GA3430@ubuntu
State New
Headers show

Commit Message

Viresh Kumar Dec. 4, 2015, 6:11 a.m. UTC 
On 04-12-15, 02:18, Rafael J. Wysocki wrote:
> > +	shared->skip_work--;

> 

> Is there any reason for incrementing and decrementing this instead of setting

> it to either 0 or 1 (or maybe either 'true' or 'false' for that matter)?

> 

> If my reading of the patch is correct, it can only be either 0 or 1 anyway, right?


No. It can be 0, 1 or 2.

If the timer handler is running on any CPU, we increment skip_work, so
its value is 1. If at the same time, we try to stop the governor, we
increment it again and its value is 2 now.

Once timer-handler finishes, it decrements it and its value become 1.
Which guarantees that no other timer handler starts executing at this
point of time and we can safely do gov_cancel_timers(). And once we
are sure that we don't have any work/timer left, we make it 0 (as we
aren't sure of the current value, which can be 0 (if the timer handler
wasn't running when we stopped the governor) or 1 (if the timer
handler was running while stopping the governor)).

Hope this clarifies it.

> > +static void dbs_timer_handler(unsigned long data)

> > +{

> > +	struct cpu_dbs_info *cdbs = (struct cpu_dbs_info *)data;

> > +	struct cpu_common_dbs_info *shared = cdbs->shared;

> > +	struct cpufreq_policy *policy;

> > +	unsigned long flags;

> > +

> > +	spin_lock_irqsave(&shared->timer_lock, flags);

> > +	policy = shared->policy;

> 

> Why do we need policy here?

> 

> > +

> > +	/*

> > +	 * Timer handler isn't allowed to queue work at the moment, because:

> > +	 * - Another timer handler has done that

> > +	 * - We are stopping the governor

> > +	 * - Or we are updating the sampling rate of ondemand governor

> > +	 */

> > +	if (shared->skip_work)

> > +		goto unlock;

> > +

> > +	shared->skip_work++;

> > +	queue_work(system_wq, &shared->work);

> >  

> >  unlock:

> 

> What about writing the above as

> 

> 	if (!shared->work_in_progress) {

> 		shared->work_in_progress = true;

> 		queue_work(system_wq, &shared->work);

> 	}

> 

> and then you won't need the unlock label.


Here is a diff for that:

I will resend this patch now.

-- 
viresh
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Comments

Viresh Kumar Dec. 5, 2015, 4:10 a.m. UTC | #1 
On 05-12-15, 03:14, Rafael J. Wysocki wrote:
> Well, almost, but not quite yet, because now the question is what prevents

> gov_cancel_work() from racing with dbs_work_handler().

> 

> If you can guarantee that they'll never run in parallel with each other,


They can run in parallel and that's how we fix it now:
- raising skip_work to 2 makes sure that no new timer-handler can
  queue a new work.
- After raising the value of skip_work to 2, we do cancel_work_sync().
  Which will make sure that the work-handler has finished after
  cancel_work_sync() has returned.
- At this point of time we are sure that the works and their handlers
  are completely killed.
- All that is left is to kill all timer-handler (which might have
  gotten queued from the work handler, before it finished).
- And we do that with gov_cancel_timers().
- And then we are in safe state, where we are guaranteed that there
  are no leftovers.

> you probably don't need the whole counter dance.  Otherwise, dbs_work_handler()

> should decrement the counter under the spinlock after all I suppose.


Its not required because we don't have any race around that decrement
operation.

-- 
viresh
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index a3f9bc9b98e9..c9e420bd0eec 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -265,11 +265,9 @@  static void dbs_timer_handler(unsigned long data)
 {
        struct cpu_dbs_info *cdbs = (struct cpu_dbs_info *)data;
        struct cpu_common_dbs_info *shared = cdbs->shared;
-       struct cpufreq_policy *policy;
        unsigned long flags;
 
        spin_lock_irqsave(&shared->timer_lock, flags);
-       policy = shared->policy;
 
        /*
         * Timer handler isn't allowed to queue work at the moment, because:
@@ -277,13 +275,11 @@  static void dbs_timer_handler(unsigned long data)
         * - We are stopping the governor
         * - Or we are updating the sampling rate of ondemand governor
         */
-       if (shared->skip_work)
-               goto unlock;
-
-       shared->skip_work++;
-       queue_work(system_wq, &shared->work);
+       if (!shared->skip_work) {
+               shared->skip_work++;
+               queue_work(system_wq, &shared->work);
+       }
 
-unlock:
        spin_unlock_irqrestore(&shared->timer_lock, flags);
 }