From mboxrd@z Thu Jan 1 00:00:00 1970 From: Chris Wilson Subject: [PATCH 7/7] drm/i915/execlists: Apply a full mb before execution for Braswell Date: Sat, 1 Dec 2018 09:52:31 +0000 Message-ID: <20181201095231.324-7-chris@chris-wilson.co.uk> References: <20181201095231.324-1-chris@chris-wilson.co.uk> Mime-Version: 1.0 Content-Transfer-Encoding: 8bit Return-path: In-Reply-To: <20181201095231.324-1-chris@chris-wilson.co.uk> Sender: stable-owner@vger.kernel.org To: intel-gfx@lists.freedesktop.org Cc: Chris Wilson , Mika Kuoppala , Tvrtko Ursulin , Joonas Lahtinen , stable@vger.kernel.org List-Id: intel-gfx@lists.freedesktop.org Braswell is really picky about having our writes posted to memory before we execute or else the GPU may see stale values. A wmb() is insufficient as it only ensures the writes are visible to other cores, we need a full mb() to ensure the writes are in memory and visible to the GPU. The most frequent failure in flushing before execution is that we see stale PTE values and execute the wrong pages. References: 987abd5c62f9 ("drm/i915/execlists: Force write serialisation into context image vs execution") Signed-off-by: Chris Wilson Cc: Mika Kuoppala Cc: Tvrtko Ursulin Cc: Joonas Lahtinen Cc: stable@vger.kernel.org --- drivers/gpu/drm/i915/intel_lrc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 0a690c557113..cad1228f6503 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -379,8 +379,12 @@ static u64 execlists_update_context(struct i915_request *rq) * may not be visible to the HW prior to the completion of the UC * register write and that we may begin execution from the context * before its image is complete leading to invalid PD chasing. + * + * Furthermore, Braswell wants a full mb to be sure that the writes + * are coherent in memory (visible to the GPU) prior to execution, + * and not just visible to other CPUs (as is the result of wmb). */ - wmb(); + mb(); return ce->lrc_desc; } -- 2.20.0.rc1