From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Vetter Subject: Re: [PATCH 10/10] drm/i915: kill gen4 gpu reset code Date: Fri, 27 Apr 2012 21:17:02 +0200 Message-ID: <20120427191702.GJ5147@phenom.ffwll.local> References: <1335532667-10597-1-git-send-email-daniel.vetter@ffwll.ch> <1335532667-10597-10-git-send-email-daniel.vetter@ffwll.ch> <87bomd2eoj.fsf@eliezer.anholt.net> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mail-wg0-f41.google.com (mail-wg0-f41.google.com [74.125.82.41]) by gabe.freedesktop.org (Postfix) with ESMTP id 63FAF9F020 for ; Fri, 27 Apr 2012 12:16:03 -0700 (PDT) Received: by wgbds1 with SMTP id ds1so752432wgb.0 for ; Fri, 27 Apr 2012 12:16:02 -0700 (PDT) Content-Disposition: inline In-Reply-To: <87bomd2eoj.fsf@eliezer.anholt.net> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: intel-gfx-bounces+gcfxdi-intel-gfx=m.gmane.org@lists.freedesktop.org Errors-To: intel-gfx-bounces+gcfxdi-intel-gfx=m.gmane.org@lists.freedesktop.org To: Eric Anholt Cc: Daniel Vetter , Intel Graphics Development List-Id: intel-gfx@lists.freedesktop.org On Fri, Apr 27, 2012 at 11:49:16AM -0700, Eric Anholt wrote: > On Fri, 27 Apr 2012 15:17:47 +0200, Daniel Vetter wrote: > > It's busted. Compared to ilk, snb and ivb where I've run the i-g-t > > hangman test in a loop for a few hours, my gm45 never managed to reset > > the gpu. And Chris Wilson confirmed on irc that he's never seen a case > > where the gen4 gpu reset code actually helped. > > I remember originally when the hangcheck stuff landed, on a 965gm > running compiz, dragging a window with a bad shader around and seeing a > stutter as it reset the hardware successfully before crashing soon after > (then turning off the hanging plugin and continuing to use the system). I'm confused - so hangcheck once indeed managed to reset a i965gm gpu or never? -Daniel -- Daniel Vetter Mail: daniel@ffwll.ch Mobile: +41 (0)79 365 57 48