From: Daniel Vetter Subject: Re: [PATCH] drm/i915: Implement dma-buf mmap() on systems with LLC Date: Wed, 5 Mar 2014 15:11:59 +0100 Message-ID: <20140305141159.GX17001@phenom.ffwll.local> References: <1393271449-4385-1-git-send-email-robert.bradford@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mail-ea0-f182.google.com (mail-ea0-f182.google.com [209.85.215.182]) by gabe.freedesktop.org (Postfix) with ESMTP id 498AAFA70C for ; Wed, 5 Mar 2014 06:12:09 -0800 (PST) Received: by mail-ea0-f182.google.com with SMTP id b10so1069659eae.13 for ; Wed, 05 Mar 2014 06:12:07 -0800 (PST) Content-Disposition: inline In-Reply-To: <1393271449-4385-1-git-send-email-robert.bradford@intel.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: intel-gfx-bounces@lists.freedesktop.org Errors-To: intel-gfx-bounces@lists.freedesktop.org To: Rob Bradford Cc: intel-gfx@lists.freedesktop.org List-Id: intel-gfx@lists.freedesktop.org On Mon, Feb 24, 2014 at 07:50:49PM +0000, Rob Bradford wrote: > From: Rob Bradford > > The LLC check echoes the check made by i915_gem_fault() which will > handle the mapping the pages through the GTT. > > The aim is that this is functionally equivalent to using the > I915_GEM_MMAP_GTT ioctl and then mmaping using the offset returned. > > Signed-off-by: Rob Bradford > --- > drivers/gpu/drm/i915/i915_gem_dmabuf.c | 20 +++++++++++++++++++- > 1 file changed, 19 insertions(+), 1 deletion(-) > > diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c > index 9bb533e..55ff592 100644 > --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c > +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c > @@ -197,7 +197,25 @@ static void i915_gem_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_n > > static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma) > { > - return -EINVAL; > + struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf); > + struct drm_device *dev = obj->base.dev; > + int ret; > + > + if (!HAS_LLC(dev)) > + return -EINVAL; > + > + ret = i915_mutex_lock_interruptible(dev); > + if (ret) > + goto unlock; > + > + ret = drm_gem_mmap_obj(&obj->base, vma_pages(vma) << PAGE_SHIFT, vma); The gtt memory mapping you're forwarding here to is actually always coherent, so the LLC test is redundant. The only issue is if you try to gtt mmap a coherent BO on pre-snb, iirc that can hang. Another thing is the pte shootdown. I think to make that work you need to frob the vma -> mapping association a bit so that unmap_mapping_range works correctly. A testcase which dma-buf mmaps more data than we have cpu accessible gtt space should easily hit this. Which brings up the last bit: This needs a prime_mmap testcase in igt ... Cheers, Daniel > + > + if (ret) > + goto unlock; > + > +unlock: > + mutex_unlock(&dev->struct_mutex); > + return ret; > } > > static int i915_gem_begin_cpu_access(struct dma_buf *dma_buf, size_t start, size_t length, enum dma_data_direction direction) > -- > 1.8.3.1 > > _______________________________________________ > Intel-gfx mailing list > Intel-gfx@lists.freedesktop.org > http://lists.freedesktop.org/mailman/listinfo/intel-gfx -- Daniel Vetter Software Engineer, Intel Corporation +41 (0) 79 365 57 48 - http://blog.ffwll.ch