From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753815AbaIWA2K (ORCPT ); Mon, 22 Sep 2014 20:28:10 -0400 Received: from relay1.mentorg.com ([192.94.38.131]:41221 "EHLO relay1.mentorg.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752757AbaIWA2J (ORCPT ); Mon, 22 Sep 2014 20:28:09 -0400 Message-ID: <5420BE92.7050504@mentor.com> Date: Mon, 22 Sep 2014 19:28:02 -0500 From: Nathan Lynch User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.1.0 MIME-Version: 1.0 To: Russell King - ARM Linux CC: Will Deacon , Daniel Lezcano , Catalin Marinas , Christopher Covington , Doug Anderson , Lorenzo Pieralisi , Marc Zyngier , Mark Rutland , Sonny Rao , Stephen Boyd , Thomas Gleixner , "linux-arm-kernel@lists.infradead.org" , "linux-kernel@vger.kernel.org" Subject: Re: [PATCH v2 0/3] arm_arch_timer: VDSO preparation, code consolidation References: <1411052390-27238-1-git-send-email-nathan_lynch@mentor.com> <20140922153919.GQ25809@arm.com> <20140922223022.GO5182@n2100.arm.linux.org.uk> In-Reply-To: <20140922223022.GO5182@n2100.arm.linux.org.uk> Content-Type: text/plain; charset="windows-1252" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 09/22/2014 05:30 PM, Russell King - ARM Linux wrote: > On Mon, Sep 22, 2014 at 04:39:19PM +0100, Will Deacon wrote: >> On Thu, Sep 18, 2014 at 03:59:32PM +0100, Nathan Lynch wrote: >>> This series contains the necessary changes to allow architected timer >>> access from user-space on 32-bit ARM. This allows the VDSO to support >>> high resolution timestamps for clock_gettime and gettimeofday. This >>> also merges substantially similar code from arm and arm64 into the >>> core arm_arch_timer driver. >>> >>> The functional changes are: >>> - When available, CNTVCT is made readable by user space on arm, as it >>> is on arm64. >>> - The clocksource name becomes "arch_mem_counter" if CP15 access to >>> the counter is not available. >>> >>> These changes have been carried as part of the ARM VDSO patch set over >>> the last several months, but I am splitting them out here as I assume >>> they should go through the clocksource maintainers. >> >> For the series: >> >> Acked-by: Will Deacon >> >> I'm not sure which tree the arch-timer stuff usually goes through, but >> the arm/arm64 bits look fine so I'm happy for them to merged together. > > I raised a while back with Will whether there's much point to having > this on ARM. While it's useful for virtualisation, the majority of > 32-bit ARM doesn't run virtualised. So there's little point in having > the VDSO on the majority of platforms - it will just add additional > unnecessary cycles slowing down the system calls that the VDSO is > designed to try to speed up. Hmm, this patch set is merely exposing the hardware counter when it is present for the VDSO's use; I take it you have no objection to that? While the 32-bit ARM VDSO I've posted (in a different thread) exploits a facility that is required by the virtualization option in the architecture, its utility is not limited to guest operating systems. > So, my view is that this VDSO will only be of very limited use for > 32-bit ARM, and should not be exposed to userspace unless there is > a reason for it to be exposed (iow, the hardware necessary to support > it is present.) My thinking is that it should prove useful in a growing subset of v7 CPUs. It is useful today on Cortex-A15 and -A7, and I believe -A12 and -A17 implement the generic timer facility as well. Now if you're saying that we shouldn't slow down gettimeofday on systems which lack a hardware counter that can be safely exposed to userspace, I can work with that.