[Intel-gfx] [PATCH v2] drm/i915: Fallback to using unmappable memory for scanout

[Chris Wilson]

On Thu, Mar 19, 2015 at 05:35:17PM +0100, Daniel Vetter wrote:
> On Thu, Mar 19, 2015 at 11:29:40AM +0000, Chris Wilson wrote:
> > The existing ABI says that scanouts are pinned into the mappable region
> > so that legacy clients (e.g. old Xorg or plymouthd) can write directly
> > into the scanout through a GTT mapping. However if the surface does not
> > fit into the mappable region, we are better off just trying to fit it
> > anywhere and hoping for the best. (Any userspace that is cappable of
> > using ginormous scanouts is also likely not to rely on pure GTT
> > updates.) In the future, there may even be a kernel mediated method for
> > the legacy clients.
> > 
> > v2: Skip fence pinning when not mappable.
> > 
> > Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> > Cc: Satyanantha, Rama Gopal M <rama.gopal.m.satyanantha at intel.com>
> > Cc: Deepak S <deepak.s at linux.intel.com>
> > Cc: Damien Lespiau <damien.lespiau at intel.com>
> > Cc: Daniel Vetter <daniel.vetter at ffwll.ch>
> > ---
> >  drivers/gpu/drm/i915/i915_gem.c      |  7 ++++++-
> >  drivers/gpu/drm/i915/intel_display.c | 23 +++++++++++++----------
> >  2 files changed, 19 insertions(+), 11 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> > index 9e498e0bbf22..9a1de848e450 100644
> > --- a/drivers/gpu/drm/i915/i915_gem.c
> > +++ b/drivers/gpu/drm/i915/i915_gem.c
> > @@ -4034,10 +4034,15 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
> >  
> >  	/* As the user may map the buffer once pinned in the display plane
> >  	 * (e.g. libkms for the bootup splash), we have to ensure that we
> > -	 * always use map_and_fenceable for all scanout buffers.
> > +	 * always use map_and_fenceable for all scanout buffers. However,
> > +	 * it may simply be too big to fit into mappable, in which case
> > +	 * put it anyway and hope that userspace can cope (but always first
> > +	 * try to preserve the existing ABI).
> >  	 */
> >  	ret = i915_gem_obj_ggtt_pin(obj, alignment, PIN_MAPPABLE);
> >  	if (ret)
> > +		ret = i915_gem_obj_ggtt_pin(obj, alignment, 0);
> > +	if (ret)
> >  		goto err_unpin_display;
> >  
> >  	i915_gem_object_flush_cpu_write_domain(obj);
> > diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> > index d621ebecd33e..628aace63b43 100644
> > --- a/drivers/gpu/drm/i915/intel_display.c
> > +++ b/drivers/gpu/drm/i915/intel_display.c
> > @@ -2308,16 +2308,18 @@ intel_pin_and_fence_fb_obj(struct drm_plane *plane,
> >  	if (ret)
> >  		goto err_interruptible;
> >  
> > -	/* Install a fence for tiled scan-out. Pre-i965 always needs a
> > -	 * fence, whereas 965+ only requires a fence if using
> > -	 * framebuffer compression.  For simplicity, we always install
> > -	 * a fence as the cost is not that onerous.
> > -	 */
> > -	ret = i915_gem_object_get_fence(obj);
> > -	if (ret)
> > -		goto err_unpin;
> > +	if (obj->map_and_fenceable) {
> > +		/* Install a fence for tiled scan-out. Pre-i965 always needs a
> > +		 * fence, whereas 965+ only requires a fence if using
> > +		 * framebuffer compression.  For simplicity, we always, when
> > +		 * possible, install a fence as the cost is not that onerous.
> > +		 */
> > +		ret = i915_gem_object_get_fence(obj);
> > +		if (ret)
> > +			goto err_unpin;
> 
> FBC still assumes that a fence is there (and with Paulo's recent rework
> that's made even more explicit). I think we need a change in the fbc
> frontbuffer tracking integration to not filter out GTT invalidates if the
> buffer isn't mappable. Paulo?

I checked that we have such a check in the fbc enable code. I think if
we have a framebuffer that won't fit in the GTT, we are reasonably sure
it won't be FBC compatible. On the other hand, if we have 4
framebuffers...

if (obj->tiling_mode != I915_TILING_X ||
    obj->fence_reg == I915_FENCE_REG_NONE) {
	if (set_no_fbc_reason(dev_priv, FBC_NOT_TILED))
		DRM_DEBUG_KMS("framebuffer not tiled or fenced, disabling compression\n");

I think it is preferrable that the system continues to run in a degraded
mode in such circumstances than fail entirely.
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre