From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756177AbZGVDyP (ORCPT ); Tue, 21 Jul 2009 23:54:15 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755880AbZGVDyP (ORCPT ); Tue, 21 Jul 2009 23:54:15 -0400 Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:56220 "EHLO sunset.davemloft.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754319AbZGVDyO (ORCPT ); Tue, 21 Jul 2009 23:54:14 -0400 Date: Tue, 21 Jul 2009 20:54:19 -0700 (PDT) Message-Id: <20090721.205419.251322907.davem@davemloft.net> To: tj@kernel.org Cc: linux-arch@vger.kernel.org, linux-kernel@vger.kernel.org, mingo@redhat.com, benh@kernel.crashing.org, dhowells@redhat.com, npiggin@suse.de, JBeulich@novell.com, cl@linux-foundation.org, rusty@rustcorp.com.au, hpa@zytor.com, tglx@linutronix.de, akpm@linux-foundation.org, x86@kernel.org, andi@firstfloor.org Subject: Re: [PATCH 19/20] sparc64: use embedding percpu first chunk allocator From: David Miller In-Reply-To: <1248171979-29166-20-git-send-email-tj@kernel.org> References: <1248171979-29166-1-git-send-email-tj@kernel.org> <1248171979-29166-20-git-send-email-tj@kernel.org> X-Mailer: Mew version 6.2.51 on Emacs 22.1 / Mule 5.0 (SAKAKI) Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Tejun Heo Date: Tue, 21 Jul 2009 19:26:18 +0900 > sparc64 currently allocates a large page for each cpu and partially > remap them into vmalloc area much like what lpage first chunk > allocator did. As a 4M page is used for each cpu, this results in > very large unit size and also adds TLB pressure due to the double > mapping of pages in the first chunk. > > This patch converts sparc64 to use the embedding percpu first chunk > allocator which now knows how to handle NUMA configurations. This > simplifies the code a lot, doesn't incur any extra TLB pressure and > results in better utilization of address space. > > Signed-off-by: Tejun Heo Acked-by: David S. Miller