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=-5.5 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,NICE_REPLY_A,SPF_HELO_NONE, SPF_PASS,URIBL_BLOCKED,USER_AGENT_SANE_1 autolearn=no 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 5D420C433E0 for ; Tue, 9 Feb 2021 09:18:06 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id C9CE164EBD for ; Tue, 9 Feb 2021 09:18:05 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org C9CE164EBD Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=hisilicon.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 272416B0005; Tue, 9 Feb 2021 04:18:05 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 2232E6B006C; Tue, 9 Feb 2021 04:18:05 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 1382C6B006E; Tue, 9 Feb 2021 04:18:05 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0012.hostedemail.com [216.40.44.12]) by kanga.kvack.org (Postfix) with ESMTP id F11876B0005 for ; Tue, 9 Feb 2021 04:18:04 -0500 (EST) Received: from smtpin09.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay03.hostedemail.com (Postfix) with ESMTP id BA8CA824805A for ; Tue, 9 Feb 2021 09:18:04 +0000 (UTC) X-FDA: 77798177688.09.mass92_1a01fe127606 Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin09.hostedemail.com (Postfix) with ESMTP id 97073184B1FD2 for ; Tue, 9 Feb 2021 09:18:04 +0000 (UTC) X-HE-Tag: mass92_1a01fe127606 X-Filterd-Recvd-Size: 4047 Received: from szxga04-in.huawei.com (szxga04-in.huawei.com [45.249.212.190]) by imf39.hostedemail.com (Postfix) with ESMTP for ; Tue, 9 Feb 2021 09:18:03 +0000 (UTC) Received: from DGGEMS403-HUB.china.huawei.com (unknown [172.30.72.58]) by szxga04-in.huawei.com (SkyGuard) with ESMTP id 4DZchc0Dr5z165bR; Tue, 9 Feb 2021 17:16:32 +0800 (CST) Received: from [127.0.0.1] (10.40.188.87) by DGGEMS403-HUB.china.huawei.com (10.3.19.203) with Microsoft SMTP Server id 14.3.498.0; Tue, 9 Feb 2021 17:17:46 +0800 Subject: Re: [RFC PATCH v3 1/2] mempinfd: Add new syscall to provide memory pin To: Andy Lutomirski References: <1612685884-19514-2-git-send-email-wangzhou1@hisilicon.com> CC: , , , , , Andrew Morton , Alexander Viro , , , , , , , , , Sihang Chen From: Zhou Wang Message-ID: <2e6cf99f-beb6-9bef-1316-5e58fb0aa86e@hisilicon.com> Date: Tue, 9 Feb 2021 17:17:46 +0800 User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:45.0) Gecko/20100101 Thunderbird/45.7.1 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset="utf-8" X-Originating-IP: [10.40.188.87] X-CFilter-Loop: Reflected Content-Transfer-Encoding: quoted-printable X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: On 2021/2/8 6:02, Andy Lutomirski wrote: >=20 >=20 >> On Feb 7, 2021, at 12:31 AM, Zhou Wang wrote= : >> >> =EF=BB=BFSVA(share virtual address) offers a way for device to share p= rocess virtual >> address space safely, which makes more convenient for user space devic= e >> driver coding. However, IO page faults may happen when doing DMA >> operations. As the latency of IO page fault is relatively big, DMA >> performance will be affected severely when there are IO page faults. >> From a long term view, DMA performance will be not stable. >> >> In high-performance I/O cases, accelerators might want to perform >> I/O on a memory without IO page faults which can result in dramaticall= y >> increased latency. Current memory related APIs could not achieve this >> requirement, e.g. mlock can only avoid memory to swap to backup device= , >> page migration can still trigger IO page fault. >> >> Various drivers working under traditional non-SVA mode are using >> their own specific ioctl to do pin. Such ioctl can be seen in v4l2, >> gpu, infiniband, media, vfio, etc. Drivers are usually doing dma >> mapping while doing pin. >> >> But, in SVA mode, pin could be a common need which isn't necessarily >> bound with any drivers, and neither is dma mapping needed by drivers >> since devices are using the virtual address of CPU. Thus, It is better >> to introduce a new common syscall for it. >> >> This patch leverages the design of userfaultfd and adds mempinfd for p= in >> to avoid messing up mm_struct. A fd will be got by mempinfd, then user >> space can do pin/unpin pages by ioctls of this fd, all pinned pages un= der >> one file will be unpinned in file release process. Like pin page cases= in >> other places, can_do_mlock is used to check permission and input >> parameters. >=20 >=20 > Can you document what the syscall does? Will add related document in Documentation/vm. >=20 > Userfaultfd is an fd because one program controls another. Is mempinfd= like this? We use mempinfd like: (see patch 2/2) fd =3D mempinfd(); va =3D malloc(size); struct mem_pin_address addr; addr.va =3D va; addr.size =3D size; ioctl(fd, MEM_CMD_PIN, &addr); ioctl(fd, MEM_CMD_UNPIN, &addr); close(fd); Best, Zhou > . >=20