From mboxrd@z Thu Jan 1 00:00:00 1970 From: Antonino Daplas Subject: RE: Adding an fb_sync() operation to fb_ops Date: 04 Jun 2002 07:53:06 +0800 Sender: linux-fbdev-devel-admin@lists.sourceforge.net Message-ID: <1023148432.541.1.camel@daplas> Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Return-path: Received: from [203.167.79.9] (helo=willow.compass.com.ph) by usw-sf-list1.sourceforge.net with esmtp (Exim 3.31-VA-mm2 #1 (Debian)) id 17F1db-0004Dj-00 for ; Mon, 03 Jun 2002 16:53:24 -0700 Errors-To: linux-fbdev-devel-admin@lists.sourceforge.net List-Help: List-Post: List-Subscribe: , List-Id: List-Unsubscribe: , List-Archive: Content-Type: text/plain; charset="us-ascii" To: Matthew J Sottek Cc: fbdev On Mon, 2002-06-03 at 23:49, Sottek, Matthew J wrote: > > So here is the obvious problem case. > > Application mmap's the framebuffer. > Application Draws some pixels into the framebuffer. > Application issues an ioctl that would lead to a blit, the command is put > in a ring buffer but hasn't happened yet. > The application draws some more pixels (via the mmap) in a region that > intersects the previously blitted region. > The hardware gets around to the blit command and overwrites the pixels you > just put in the frambuffer. > > And it does not have to happen outside the kernel. Within the kernel too. For instance, a particular accelerator may only support fillrect and copyarea, but not imageblit (neofb). It has no choice but to mix in cfb_imageblit and the sync problem will arise unless the accelerator forces a sync -- which neofb does by the way. Tony _______________________________________________________________ Don't miss the 2002 Sprint PCS Application Developer's Conference August 25-28 in Las Vegas -- http://devcon.sprintpcs.com/adp/index.cfm