From mboxrd@z Thu Jan 1 00:00:00 1970 From: Maarten Lankhorst Subject: Memory eviction in ttm Date: Wed, 12 Sep 2012 14:48:19 +0200 Message-ID: <50508493.6060304@canonical.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from youngberry.canonical.com (youngberry.canonical.com [91.189.89.112]) by gabe.freedesktop.org (Postfix) with ESMTP id E094E9E7E7 for ; Wed, 12 Sep 2012 05:48:20 -0700 (PDT) List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: dri-devel-bounces+sf-dri-devel=m.gmane.org@lists.freedesktop.org Errors-To: dri-devel-bounces+sf-dri-devel=m.gmane.org@lists.freedesktop.org To: Thomas Hellstrom Cc: dri-devel@lists.freedesktop.org List-Id: dri-devel@lists.freedesktop.org Hey Thomas, I'm playing around with moving reservations from ttm to global, but how ttm ttm is handling reservations is getting in the way. The code wants to move the bo from the lru lock at the same time a reservation is made, but that seems to be slightly too strict. It would really help me if that guarantee is removed. Is it true that only the ttm_mem_evict code depends on it? And in that case wouldn't it be better to attempt to free any buffer that can be reserved without blocking first, instead of blocking on the first entry in the list? This would make integration a lot easier, since I could wait with taking the lru lock until after reservation is complete, or any time before unreserving. ~Maarten