Re: [PATCH 4/5] drm/i915: Make scatter-gather helper available to the driver

From: Chris Wilson <chris@chris-wilson.co.uk>
To: Daniel Vetter <daniel@ffwll.ch>
Cc: Intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH 4/5] drm/i915: Make scatter-gather helper available to the driver
Date: Mon, 3 Nov 2014 20:30:20 +0000	[thread overview]
Message-ID: <20141103203020.GB13658@nuc-i3427.alporthouse.com> (raw)
In-Reply-To: <20141103160555.GA26941@phenom.ffwll.local>

On Mon, Nov 03, 2014 at 05:05:55PM +0100, Daniel Vetter wrote:
> On Thu, Oct 30, 2014 at 04:39:37PM +0000, Tvrtko Ursulin wrote:
> > From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> > 
> > It will be used by other call sites shortly.
> > 
> > Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> > ---
> >  drivers/gpu/drm/i915/i915_dma.c         | 38 +++++++++++++++++++++++++++++
> >  drivers/gpu/drm/i915/i915_gem_userptr.c | 43 ++-------------------------------
> >  drivers/gpu/drm/i915/intel_drv.h        |  4 +++
> >  3 files changed, 44 insertions(+), 41 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
> > index 5b157bb..0b34571 100644
> > --- a/drivers/gpu/drm/i915/i915_dma.c
> > +++ b/drivers/gpu/drm/i915/i915_dma.c
> > @@ -2070,3 +2070,41 @@ int i915_driver_device_is_agp(struct drm_device *dev)
> >  {
> >  	return 1;
> >  }
> > +
> > +#if IS_ENABLED(CONFIG_SWIOTLB)
> > +#define swiotlb_active() swiotlb_nr_tbl()
> > +#else
> > +#define swiotlb_active() 0
> > +#endif
> > +
> > +int i915_st_set_pages(struct sg_table **st, struct page **pvec, int num_pages)
> > +{
> > +	struct scatterlist *sg;
> > +	int ret, n;
> > +
> > +	*st = kmalloc(sizeof(**st), GFP_KERNEL);
> > +	if (*st == NULL)
> > +		return -ENOMEM;
> > +
> > +	if (swiotlb_active()) {
> > +		ret = sg_alloc_table(*st, num_pages, GFP_KERNEL);
> > +		if (ret)
> > +			goto err;
> > +
> > +		for_each_sg((*st)->sgl, sg, num_pages, n)
> > +			sg_set_page(sg, pvec[n], PAGE_SIZE, 0);
> > +	} else {
> > +		ret = sg_alloc_table_from_pages(*st, pvec, num_pages,
> > +						0, num_pages << PAGE_SHIFT,
> > +						GFP_KERNEL);
> > +		if (ret)
> > +			goto err;
> > +	}
> 
> Ok, I don't really understand why we don't just always use
> sg_alloc_table_from_pages undconditionally - if swiotlb _ever_ gets in
> between us and the hw, everything will pretty much fall apart.
> 
> git blame doesn't shed light on this particular issue. Chris?

This is Imre's work...
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx