From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from gate.crashing.org (gate.crashing.org [63.228.1.57]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id 157D2DE16B for ; Wed, 20 Aug 2008 15:29:04 +1000 (EST) Subject: Re: [PATCH 2/2] powerpc - Make the irq reverse mapping radix tree lockless From: Benjamin Herrenschmidt To: Sebastien Dugue In-Reply-To: <1218029429-21114-3-git-send-email-sebastien.dugue@bull.net> References: <1218029429-21114-1-git-send-email-sebastien.dugue@bull.net> <1218029429-21114-3-git-send-email-sebastien.dugue@bull.net> Content-Type: text/plain Date: Wed, 20 Aug 2008 15:23:01 +1000 Message-Id: <1219209781.21386.25.camel@pasglop> Mime-Version: 1.0 Cc: dwalker@mvista.com, tinytim@us.ibm.com, linux-rt-users@vger.kernel.org, linux-kernel@vger.kernel.org, rostedt@goodmis.org, jean-pierre.dion@bull.net, linuxppc-dev@ozlabs.org, paulus@samba.org, gilles.carry@ext.bull.net, tglx@linutronix.de Reply-To: benh@kernel.crashing.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , BTW. It would be good to try to turn the GFP_ATOMIC into GFP_KERNEL, maybe using a semaphore instead of a lock to protect insertion vs. initialisation. The old scheme was fine because if the atomic allocation failed, it could fallback to the linear search and try again on the next interrupt. Not anymore. Ben. From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755305AbYHTFgi (ORCPT ); Wed, 20 Aug 2008 01:36:38 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752396AbYHTFgN (ORCPT ); Wed, 20 Aug 2008 01:36:13 -0400 Received: from gate.crashing.org ([63.228.1.57]:53452 "EHLO gate.crashing.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752087AbYHTFgM (ORCPT ); Wed, 20 Aug 2008 01:36:12 -0400 Subject: Re: [PATCH 2/2] powerpc - Make the irq reverse mapping radix tree lockless From: Benjamin Herrenschmidt Reply-To: benh@kernel.crashing.org To: Sebastien Dugue Cc: linuxppc-dev@ozlabs.org, linux-kernel@vger.kernel.org, linux-rt-users@vger.kernel.org, paulus@samba.org, michael@ellerman.id.au, jean-pierre.dion@bull.net, gilles.carry@ext.bull.net, tinytim@us.ibm.com, tglx@linutronix.de, rostedt@goodmis.org, dwalker@mvista.com In-Reply-To: <1218029429-21114-3-git-send-email-sebastien.dugue@bull.net> References: <1218029429-21114-1-git-send-email-sebastien.dugue@bull.net> <1218029429-21114-3-git-send-email-sebastien.dugue@bull.net> Content-Type: text/plain Date: Wed, 20 Aug 2008 15:23:01 +1000 Message-Id: <1219209781.21386.25.camel@pasglop> Mime-Version: 1.0 X-Mailer: Evolution 2.22.3.1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org BTW. It would be good to try to turn the GFP_ATOMIC into GFP_KERNEL, maybe using a semaphore instead of a lock to protect insertion vs. initialisation. The old scheme was fine because if the atomic allocation failed, it could fallback to the linear search and try again on the next interrupt. Not anymore. Ben.