From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-1.0 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, MAILING_LIST_MULTI,SPF_PASS autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id E24FDC46471 for ; Sun, 5 Aug 2018 14:36:11 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 8B6DF217B4 for ; Sun, 5 Aug 2018 14:36:11 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 8B6DF217B4 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=redhat.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726282AbeHEQky (ORCPT ); Sun, 5 Aug 2018 12:40:54 -0400 Received: from mx3-rdu2.redhat.com ([66.187.233.73]:51940 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726191AbeHEQky (ORCPT ); Sun, 5 Aug 2018 12:40:54 -0400 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 3B0754021700; Sun, 5 Aug 2018 14:36:05 +0000 (UTC) Received: from file01.intranet.prod.int.rdu2.redhat.com (file01.intranet.prod.int.rdu2.redhat.com [10.11.5.7]) by smtp.corp.redhat.com (Postfix) with ESMTPS id A875D7C5F; Sun, 5 Aug 2018 14:36:04 +0000 (UTC) Received: from file01.intranet.prod.int.rdu2.redhat.com (localhost [127.0.0.1]) by file01.intranet.prod.int.rdu2.redhat.com (8.14.4/8.14.4) with ESMTP id w75Ea4Jw025496; Sun, 5 Aug 2018 10:36:04 -0400 Received: from localhost (mpatocka@localhost) by file01.intranet.prod.int.rdu2.redhat.com (8.14.4/8.14.4/Submit) with ESMTP id w75Ea10C025475; Sun, 5 Aug 2018 10:36:02 -0400 X-Authentication-Warning: file01.intranet.prod.int.rdu2.redhat.com: mpatocka owned process doing -bs Date: Sun, 5 Aug 2018 10:36:01 -0400 (EDT) From: Mikulas Patocka X-X-Sender: mpatocka@file01.intranet.prod.int.rdu2.redhat.com To: David Laight cc: "'Ard Biesheuvel'" , Ramana Radhakrishnan , Florian Weimer , Thomas Petazzoni , GNU C Library , Andrew Pinski , Catalin Marinas , Will Deacon , Russell King , LKML , linux-arm-kernel Subject: RE: framebuffer corruption due to overlapping stp instructions on arm64 In-Reply-To: Message-ID: References: <9acdacdb-3bd5-b71a-3003-e48132ee1371@redhat.com> User-Agent: Alpine 2.02 (LRH 1266 2009-07-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Scanned-By: MIMEDefang 2.79 on 10.11.54.5 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.11.55.5]); Sun, 05 Aug 2018 14:36:05 +0000 (UTC) X-Greylist: inspected by milter-greylist-4.5.16 (mx1.redhat.com [10.11.55.5]); Sun, 05 Aug 2018 14:36:05 +0000 (UTC) for IP:'10.11.54.5' DOMAIN:'int-mx05.intmail.prod.int.rdu2.redhat.com' HELO:'smtp.corp.redhat.com' FROM:'mpatocka@redhat.com' RCPT:'' Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 3 Aug 2018, David Laight wrote: > From: Mikulas Patocka > > Sent: 03 August 2018 13:05 > ... > > > Even on x86 using memcpy() on PCIe memory (maybe mmap()ed into userspace) > > > isn't a good idea. > > > In the kernel memcpy_to/fromio() ought to be a better choice but that > > > is just an alternate name for memcpy(). > > > > > > The problem on x86 is that memcpy() is likely to be implemented as > > > 'rep movsb' on modern cpu - relying on the cpu hardware to perform > > > cache-line sized transfers (etc). > > > Unfortunately on uncached locations it has to revert to byte copies. > > > So PCIe transfers (especially reads) are very slow. > > > > > > The transfers need to use the largest size register available. > > > > > > David > > > > On x86, the framebuffer is mapped as write-combining memory type, so "rep > > movsb" could merge the byte writes to larger chunks. I don't have a cpu > > with the ERMS feature - could anyone try it if rep movsb works worse or > > better than explicit writes to the framebuffer? > > I don't think 'write combining' can help reads, and memcpy_to/fromio() There's an instruction movntdqa (and vmovntdqa) that can actually do prefetch on write-combining memory type. It's the only instruction that can do it. It this instruction is used on non-write-combining memory type, it behaves like movdqa. > are likely to be used for normal memory mapped io areas. > > David I benchmarked it on a processor with ERMS - for writes to the framebuffer, there's no difference between memcpy, 8-byte writes, rep stosb, rep stosq, mmx, sse, avx - all this method achieve 16-17 GB/s For reading from the framebuffer: 323 MB/s - memcpy (using avx2) 91 MB/s - explicit 8-byte reads 249 MB/s - rep movsq 307 MB/s - rep movsb 90 MB/s - mmx 176 MB/s - sse 4750 MB/s - sse movntdqa 330 MB/s - avx 5369 MB/s - avx vmovntdqa So - it may make sense to introduce a function memcpy_from_framebuffer() that uses movntdqa or vmovntdqa on CPUs that support it. Mikulas From mboxrd@z Thu Jan 1 00:00:00 1970 From: mpatocka@redhat.com (Mikulas Patocka) Date: Sun, 5 Aug 2018 10:36:01 -0400 (EDT) Subject: framebuffer corruption due to overlapping stp instructions on arm64 In-Reply-To: References: <9acdacdb-3bd5-b71a-3003-e48132ee1371@redhat.com> Message-ID: To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Fri, 3 Aug 2018, David Laight wrote: > From: Mikulas Patocka > > Sent: 03 August 2018 13:05 > ... > > > Even on x86 using memcpy() on PCIe memory (maybe mmap()ed into userspace) > > > isn't a good idea. > > > In the kernel memcpy_to/fromio() ought to be a better choice but that > > > is just an alternate name for memcpy(). > > > > > > The problem on x86 is that memcpy() is likely to be implemented as > > > 'rep movsb' on modern cpu - relying on the cpu hardware to perform > > > cache-line sized transfers (etc). > > > Unfortunately on uncached locations it has to revert to byte copies. > > > So PCIe transfers (especially reads) are very slow. > > > > > > The transfers need to use the largest size register available. > > > > > > David > > > > On x86, the framebuffer is mapped as write-combining memory type, so "rep > > movsb" could merge the byte writes to larger chunks. I don't have a cpu > > with the ERMS feature - could anyone try it if rep movsb works worse or > > better than explicit writes to the framebuffer? > > I don't think 'write combining' can help reads, and memcpy_to/fromio() There's an instruction movntdqa (and vmovntdqa) that can actually do prefetch on write-combining memory type. It's the only instruction that can do it. It this instruction is used on non-write-combining memory type, it behaves like movdqa. > are likely to be used for normal memory mapped io areas. > > David I benchmarked it on a processor with ERMS - for writes to the framebuffer, there's no difference between memcpy, 8-byte writes, rep stosb, rep stosq, mmx, sse, avx - all this method achieve 16-17 GB/s For reading from the framebuffer: 323 MB/s - memcpy (using avx2) 91 MB/s - explicit 8-byte reads 249 MB/s - rep movsq 307 MB/s - rep movsb 90 MB/s - mmx 176 MB/s - sse 4750 MB/s - sse movntdqa 330 MB/s - avx 5369 MB/s - avx vmovntdqa So - it may make sense to introduce a function memcpy_from_framebuffer() that uses movntdqa or vmovntdqa on CPUs that support it. Mikulas