From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Poll about irqsafe_cpu_add and others Date: Thu, 17 Mar 2011 15:23:54 +0100 Message-ID: <1300371834.6315.93.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit Return-path: Sender: linux-kernel-owner@vger.kernel.org To: linux-kernel , linux-arch@vger.kernel.org Cc: Christoph Lameter , netdev , Netfilter Development Mailinglist List-Id: linux-arch.vger.kernel.org Hi irqsafe_cpu_{dec|inc} are used in network stack since 2.6.37 (commit 29b4433d991c88), and I would like to use irqsafe_cpu_add() in netfilter fast path too, and SNMP counters eventually (to lower ram needs by 50%) Initial support of irqsafe_ was given by Christoph in 2.6.34 It seems only x86 arch is using a native and efficient implementation. Others use irqsafe_cpu_generic_to_op() and its pair of local_irq_save() / local_irq_restore() Which other arches could use a native implementation ? What about defining a HAVE_FAST_IRQSAFE_ADD ? Thanks From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-fx0-f46.google.com ([209.85.161.46]:57866 "EHLO mail-fx0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753760Ab1CQOYP (ORCPT ); Thu, 17 Mar 2011 10:24:15 -0400 Subject: Poll about irqsafe_cpu_add and others From: Eric Dumazet Content-Type: text/plain; charset="UTF-8" Date: Thu, 17 Mar 2011 15:23:54 +0100 Message-ID: <1300371834.6315.93.camel@edumazet-laptop> Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-arch-owner@vger.kernel.org List-ID: To: linux-kernel , linux-arch@vger.kernel.org Cc: Christoph Lameter , netdev , Netfilter Development Mailinglist Message-ID: <20110317142354.VISY6mCY9O9jjTX0Ucc65CwjtlwqsnKXhFi8B41C--s@z> Hi irqsafe_cpu_{dec|inc} are used in network stack since 2.6.37 (commit 29b4433d991c88), and I would like to use irqsafe_cpu_add() in netfilter fast path too, and SNMP counters eventually (to lower ram needs by 50%) Initial support of irqsafe_ was given by Christoph in 2.6.34 It seems only x86 arch is using a native and efficient implementation. Others use irqsafe_cpu_generic_to_op() and its pair of local_irq_save() / local_irq_restore() Which other arches could use a native implementation ? What about defining a HAVE_FAST_IRQSAFE_ADD ? Thanks