From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755985AbbJHKZZ (ORCPT ); Thu, 8 Oct 2015 06:25:25 -0400 Received: from mx1.redhat.com ([209.132.183.28]:46652 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755285AbbJHKZX (ORCPT ); Thu, 8 Oct 2015 06:25:23 -0400 Date: Thu, 8 Oct 2015 15:55:20 +0530 From: Pratyush Anand To: Jungseok Lee Cc: catalin.marinas@arm.com, will.deacon@arm.com, linux-arm-kernel@lists.infradead.org, james.morse@arm.com, takahiro.akashi@linaro.org, mark.rutland@arm.com, barami97@gmail.com, linux-kernel@vger.kernel.org Subject: Re: [PATCH v4 1/2] arm64: Introduce IRQ stack Message-ID: <20151008102520.GA10912@dhcppc13.redhat.com> References: <1444231692-32722-1-git-send-email-jungseoklee85@gmail.com> <1444231692-32722-2-git-send-email-jungseoklee85@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1444231692-32722-2-git-send-email-jungseoklee85@gmail.com> User-Agent: Mutt/1.5.24 (2015-08-30) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Jungseok, On 07/10/2015:03:28:11 PM, Jungseok Lee wrote: > Currently, kernel context and interrupts are handled using a single > kernel stack navigated by sp_el1. This forces a system to use 16KB > stack, not 8KB one. This restriction makes low memory platforms suffer > from memory pressure accompanied by performance degradation. How will it behave on 64K Page system? There, it would take atleast 64K per cpu, right? > +int alloc_irq_stack(unsigned int cpu) > +{ > + void *stack; > + > + if (per_cpu(irq_stacks, cpu).stack) > + return 0; > + > + stack = (void *)__get_free_pages(THREADINFO_GFP, THREAD_SIZE_ORDER); Above would not compile for 64K pages as THREAD_SIZE_ORDER is only defined for non 64K. This need to be fixed. ~Pratyush From mboxrd@z Thu Jan 1 00:00:00 1970 From: panand@redhat.com (Pratyush Anand) Date: Thu, 8 Oct 2015 15:55:20 +0530 Subject: [PATCH v4 1/2] arm64: Introduce IRQ stack In-Reply-To: <1444231692-32722-2-git-send-email-jungseoklee85@gmail.com> References: <1444231692-32722-1-git-send-email-jungseoklee85@gmail.com> <1444231692-32722-2-git-send-email-jungseoklee85@gmail.com> Message-ID: <20151008102520.GA10912@dhcppc13.redhat.com> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org Hi Jungseok, On 07/10/2015:03:28:11 PM, Jungseok Lee wrote: > Currently, kernel context and interrupts are handled using a single > kernel stack navigated by sp_el1. This forces a system to use 16KB > stack, not 8KB one. This restriction makes low memory platforms suffer > from memory pressure accompanied by performance degradation. How will it behave on 64K Page system? There, it would take atleast 64K per cpu, right? > +int alloc_irq_stack(unsigned int cpu) > +{ > + void *stack; > + > + if (per_cpu(irq_stacks, cpu).stack) > + return 0; > + > + stack = (void *)__get_free_pages(THREADINFO_GFP, THREAD_SIZE_ORDER); Above would not compile for 64K pages as THREAD_SIZE_ORDER is only defined for non 64K. This need to be fixed. ~Pratyush