From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752056AbdFSPRD (ORCPT ); Mon, 19 Jun 2017 11:17:03 -0400 Received: from mail.linuxfoundation.org ([140.211.169.12]:40568 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750999AbdFSPRB (ORCPT ); Mon, 19 Jun 2017 11:17:01 -0400 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Chris Wilson , "J. R. Okajima" , Joonas Lahtinen , Hugh Dickins , Andrea Arcangeli , Tvrtko Ursulin , Jani Nikula Subject: [PATCH 4.11 15/78] drm/i915: Do not sync RCU during shrinking Date: Mon, 19 Jun 2017 23:15:15 +0800 Message-Id: <20170619151029.961168107@linuxfoundation.org> X-Mailer: git-send-email 2.13.1 In-Reply-To: <20170619151029.408399976@linuxfoundation.org> References: <20170619151029.408399976@linuxfoundation.org> User-Agent: quilt/0.65 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 4.11-stable review patch. If anyone has any objections, please let me know. ------------------ From: Joonas Lahtinen commit 4681ee21d62cfed4364e09ec50ee8e88185dd628 upstream. Due to the complex dependencies between workqueues and RCU, which are not easily detected by lockdep, do not synchronize RCU during shrinking. On low-on-memory systems (mem=1G for example), the RCU sync leads to all system workqueus freezing and unrelated lockdep splats are displayed according to reports. GIT bisecting done by J. R. Okajima points to the commit where RCU syncing was extended. RCU sync gains us very little benefit in real life scenarios where the amount of memory used by object backing storage is dominant over the metadata under RCU, so drop it altogether. " Yeeeaah, if core could just, go ahead and reclaim RCU queues, that'd be great. " - Chris Wilson, 2016 (0eafec6d3244) v2: More information to commit message. v3: Remove "grep _rcu_" escapee from i915_gem_shrink_all (Andrea) Fixes: c053b5a506d3 ("drm/i915: Don't call synchronize_rcu_expedited under struct_mutex") Suggested-by: Chris Wilson Reported-by: J. R. Okajima Signed-off-by: Joonas Lahtinen Reviewed-by: Chris Wilson Tested-by: Hugh Dickins Tested-by: Andrea Arcangeli Cc: Chris Wilson Cc: Tvrtko Ursulin Cc: J. R. Okajima Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Jani Nikula (cherry picked from commit 73cc0b9aa9afa5ba65d92e46ded61d29430d72a4) Signed-off-by: Jani Nikula Link: http://patchwork.freedesktop.org/patch/msgid/1495097379-573-1-git-send-email-joonas.lahtinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_gem_shrinker.c | 5 ----- 1 file changed, 5 deletions(-) --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -59,9 +59,6 @@ static void i915_gem_shrinker_unlock(str return; mutex_unlock(&dev->struct_mutex); - - /* expedite the RCU grace period to free some request slabs */ - synchronize_rcu_expedited(); } static bool any_vma_pinned(struct drm_i915_gem_object *obj) @@ -271,8 +268,6 @@ unsigned long i915_gem_shrink_all(struct I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_ACTIVE); - synchronize_rcu(); /* wait for our earlier RCU delayed slab frees */ - return freed; }