Re: [PATCH AUTOSEL for 4.4 016/115] drm: Defer disabling the vblank IRQ until the next interrupt (for instant-off)

[Ben Hutchings]

On Thu, 2018-03-29 at 19:42 +0300, Ville SyrjÃlà wrote:
> On Thu, Mar 29, 2018 at 05:32:13PM +0100, Ben Hutchings wrote:
> > On Sat, 2018-03-03 at 22:30 +0000, Sasha Levin wrote:
> > > > > > From: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
> > > 
> > > [ Upstream commit 608b20506941969ea30d8c08dc9ae02bb87dbf7d ]
> > 
> > I think we need this one too:
> > 
> > commit 75cff0837c14eaf632efabb8d7ab9eec6394d20d
> > Author: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
> > Date:ÂÂÂFri Mar 24 17:30:58 2017 +0000
> > 
> > ÂÂÂÂdrm: Make the decision to keep vblank irq enabled earlier
> 
> Why are we backporting optimizations anyway?

That's a good question.  I don't know the reasoning behind picking the
first commit (608b20506941).  I'm only suggesting the second commit
because it appears to be an important fix for the first.

Ben.

> > 
> > Ben.
> > 
> > > On vblank instant-off systems, we can get into a situation where the cost
> > > of enabling and disabling the vblank IRQ around a drmWaitVblank query
> > > dominates. And with the advent of even deeper hardware sleep state,
> > > touching registers becomes ever more expensive.ÂÂHowever, we know that if
> > > the user wants the current vblank counter, they are also very likely to
> > > immediately queue a vblank wait and so we can keep the interrupt around
> > > and only turn it off if we have no further vblank requests queued within
> > > the interrupt interval.
> > > 
> > > After vblank event delivery, this patch adds a shadow of one vblank where
> > > the interrupt is kept alive for the user to query and queue another vblank
> > > event. Similarly, if the user is using blocking drmWaitVblanks, the
> > > interrupt will be disabled on the IRQ following the wait completion.
> > > However, if the user is simply querying the current vblank counter and
> > > timestamp, the interrupt will be disabled after every IRQ and the user
> > > will enabled it again on the first query following the IRQ.
> > > 
> > > v2: Mario Kleiner -
> > > After testing this, one more thing that would make sense is to move
> > > the disable block at the end of drm_handle_vblank() instead of at the
> > > top.
> > > 
> > > Turns out that if high precision timestaming is disabled or doesn't
> > > work for some reason (as can be simulated by echo 0 >
> > > /sys/module/drm/parameters/timestamp_precision_usec), then with your
> > > delayed disable code at its current place, the vblank counter won't
> > > increment anymore at all for instant queries, ie. with your other
> > > "instant query" patches. Clients which repeatedly query the counter
> > > and wait for it to progress will simply hang, spinning in an endless
> > > query loop. There's that comment in vblank_disable_and_save:
> > > 
> > > "* Skip this step if there isn't any high precision timestamp
> > > Â* available. In that case we can't account for this and just
> > > Â* hope for the best.
> > > Â*/
> > > 
> > > With the disable happening after leading edge of vblank (== hw counter
> > > increment already happened) but before the vblank counter/timestamp
> > > handling in drm_handle_vblank, that step is needed to keep the counter
> > > progressing, so skipping it is bad.
> > > 
> > > Now without high precision timestamping support, a kms driver must not
> > > set dev->vblank_disable_immediate = true, as this would cause problems
> > > for clients, so this shouldn't matter, but it would be good to still
> > > make this robust against a future kms driver which might have
> > > unreliable high precision timestamping, e.g., high precision
> > > timestamping that intermittently doesn't work.
> > > 
> > > v3: Patch before coffee needs extra coffee.
> > > 
> > > Testcase: igt/kms_vblank
> > > Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
> > > Cc: Ville SyrjÃlà <ville.syrjala@xxxxxxxxxxxxxxx>
> > > Cc: Daniel Vetter <daniel@xxxxxxxx>
> > > Cc: Michel DÃnzer <michel@xxxxxxxxxxx>
> > > Cc: Laurent Pinchart <laurent.pinchart@xxxxxxxxxxxxxxxx>
> > > Cc: Dave Airlie <airlied@xxxxxxxxxx>,
> > > Cc: Mario Kleiner <mario.kleiner.de@xxxxxxxxx>
> > > Reviewed-by: Ville SyrjÃlà <ville.syrjala@xxxxxxxxxxxxxxx>
> > > Signed-off-by: Daniel Vetter <daniel.vetter@xxxxxxxx>
> > > Link: http://patchwork.freedesktop.org/patch/msgid/20170315204027.20160-1-chris@xxxxxxxxxxxxxxxxxx
> > > Signed-off-by: Sasha Levin <alexander.levin@xxxxxxxxxxxxx>
> > > ---
> > > Âdrivers/gpu/drm/drm_irq.c | 14 ++++++++++++--
> > > Â1 file changed, 12 insertions(+), 2 deletions(-)
> > > 
> > > diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
> > > index 8090989185b2..4ddbc49125cd 100644
> > > --- a/drivers/gpu/drm/drm_irq.c
> > > +++ b/drivers/gpu/drm/drm_irq.c
> > > @@ -1271,9 +1271,9 @@ void drm_vblank_put(struct drm_device *dev, unsigned int pipe)
> > > Â	if (atomic_dec_and_test(&vblank->refcount)) {
> > > Â		if (drm_vblank_offdelay == 0)
> > > Â			return;
> > > -		else if (dev->vblank_disable_immediate || drm_vblank_offdelay < 0)
> > > +		else if (drm_vblank_offdelay < 0)
> > > Â			vblank_disable_fn((unsigned long)vblank);
> > > -		else
> > > +		else if (!dev->vblank_disable_immediate)
> > > Â			mod_timer(&vblank->disable_timer,
> > > Â				ÂÂjiffies + ((drm_vblank_offdelay * HZ)/1000));
> > > Â	}
> > > @@ -1902,6 +1902,16 @@ bool drm_handle_vblank(struct drm_device *dev, unsigned int pipe)
> > > Â	wake_up(&vblank->queue);
> > > Â	drm_handle_vblank_events(dev, pipe);
> > > Â
> > > +	/* With instant-off, we defer disabling the interrupt until after
> > > +	Â* we finish processing the following vblank. The disable has to
> > > +	Â* be last (after drm_handle_vblank_events) so that the timestamp
> > > +	Â* is always accurate.
> > > +	Â*/
> > > +	if (dev->vblank_disable_immediate &&
> > > +	ÂÂÂÂdrm_vblank_offdelay > 0 &&
> > > +	ÂÂÂÂ!atomic_read(&vblank->refcount))
> > > +		vblank_disable_fn((unsigned long)vblank);
> > > +
> > > Â	spin_unlock_irqrestore(&dev->event_lock, irqflags);
> > > Â
> > > Â	return true;
> > > --Â
> > > 2.14.1
> > 
> > --Â
> > Ben Hutchings
> > Software Developer, Codethink Ltd.
> 
> 
-- 
Ben Hutchings
Software Developer, Codethink Ltd.