[Intel-gfx] [CI 16/20] drm/i915: Only query timestamp when measuring elapsed time

[Tvrtko Ursulin]

On 20/05/16 13:20, Chris Wilson wrote:
> On Thu, May 19, 2016 at 04:44:03PM +0100, Tvrtko Ursulin wrote:
>>
>> On 19/05/16 12:32, Chris Wilson wrote:
>>> Avoid the two calls to ktime_get_raw_ns() (at best it reads the TSC) as
>>> we only need to compute the elapsed time for a timed wait.
>>>
>>> v2: Eliminate the unused local variable reducing the function size by 64
>>> bytes (using the storage space on the callers stack rather than adding
>>> to our stack frame)
>>>
>>> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
>>> ---
>>>   drivers/gpu/drm/i915/i915_gem.c | 14 +++++---------
>>>   1 file changed, 5 insertions(+), 9 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
>>> index b48a3b46e86f..2c254cf49c15 100644
>>> --- a/drivers/gpu/drm/i915/i915_gem.c
>>> +++ b/drivers/gpu/drm/i915/i915_gem.c
>>> @@ -1215,7 +1215,6 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
>>>   	int state = interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE;
>>>   	struct intel_wait wait;
>>>   	unsigned long timeout_remain;
>>> -	s64 before = 0; /* Only to silence a compiler warning. */
>>>   	int ret = 0;
>>>
>>>   	might_sleep();
>>> @@ -1234,12 +1233,9 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
>>>   		if (*timeout == 0)
>>>   			return -ETIME;
>>>
>>> +		/* Record current time in case interrupted, or wedged */
>>>   		timeout_remain = nsecs_to_jiffies_timeout(*timeout);
>>> -
>>> -		/*
>>> -		 * Record current time in case interrupted by signal, or wedged.
>>> -		 */
>>> -		before = ktime_get_raw_ns();
>>> +		*timeout += ktime_get_raw_ns();
>>>   	}
>>>
>>>   	trace_i915_gem_request_wait_begin(req);
>>> @@ -1296,9 +1292,9 @@ complete:
>>>   	trace_i915_gem_request_wait_end(req);
>>>
>>>   	if (timeout) {
>>> -		s64 tres = *timeout - (ktime_get_raw_ns() - before);
>>> -
>>> -		*timeout = tres < 0 ? 0 : tres;
>>> +		*timeout -= ktime_get_raw_ns();
>>> +		if (*timeout < 0)
>>> +			*timeout = 0;
>>>
>>>   		/*
>>>   		 * Apparently ktime isn't accurate enough and occasionally has a
>>>
>>
>> I think this is bad, better have a local than play games with
>> callers storage.
>
> It's smaller faster code :-)

You know I am normally all for that but this one I cannot approve.

Regards,

Tvrtko