From patchwork Mon Jul 13 09:06:05 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peng Tao X-Patchwork-Id: 6776331 Return-Path: X-Original-To: patchwork-linux-nfs@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork2.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork2.web.kernel.org (Postfix) with ESMTP id AD42EC05AC for ; Mon, 13 Jul 2015 09:07:34 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 9F8AA20690 for ; Mon, 13 Jul 2015 09:07:33 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 8855C2063C for ; Mon, 13 Jul 2015 09:07:32 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752387AbbGMJH1 (ORCPT ); Mon, 13 Jul 2015 05:07:27 -0400 Received: from mail-pd0-f176.google.com ([209.85.192.176]:34025 "EHLO mail-pd0-f176.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752371AbbGMJHX (ORCPT ); Mon, 13 Jul 2015 05:07:23 -0400 Received: by pdbep18 with SMTP id ep18so222230066pdb.1 for ; Mon, 13 Jul 2015 02:07:23 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=NHgGN3mjSa/GgSyjAKoq9i2yyUrIqtGzPOrb+9CPC48=; b=S/Lco26b/hU9XQ2G6apDHUJz+vOlh1CgpGk001/EGovoLXGyMh86jofhkTue3cbC1H q4+bwvt2FePls1RFwu3JJ3xXMUUm+BxleUAMrVnfYYMSA6ZOLReWtsd4/WCpdFf66TLR LOLezedq6hM5N1+a3rLWbvG+v1ojNkdlL9of78mO7fLXzZokmkEHW9P2sWKT3bvdryid Sec6iqGi5iIK2kv8LC7fvZkXdCRUZR+uEco+Hi7IjQHeTDWDro4mVKIwTcyNkJFGmrZy s0oNo96fKqVXmZzn7/0UJyuHvxXF7HFui/SpxBKDO2lAklMMuQoaYLytlVMBnj+SrfKb nMgA== X-Gm-Message-State: ALoCoQk9iJtXcbGY9IIsM7Dtdp/U4X+RoMoTjkY+fPB3R7Dq2zSuMRky0o5D6m3fBWi8eBdfoClv X-Received: by 10.70.92.138 with SMTP id cm10mr650561pdb.63.1436778443157; Mon, 13 Jul 2015 02:07:23 -0700 (PDT) Received: from lear.localdomain (ec2-54-65-164-9.ap-northeast-1.compute.amazonaws.com. [54.65.164.9]) by smtp.gmail.com with ESMTPSA id dp1sm17692664pbb.53.2015.07.13.02.07.19 (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Mon, 13 Jul 2015 02:07:22 -0700 (PDT) From: Peng Tao To: linux-nfs@vger.kernel.org Cc: Trond Myklebust , Anna Schumaker , Peng Tao Subject: [PATCH v2 5/8] nfs42: add NFS_IOC_CLONE ioctl Date: Mon, 13 Jul 2015 17:06:05 +0800 Message-Id: <1436778368-65447-6-git-send-email-tao.peng@primarydata.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1436778368-65447-1-git-send-email-tao.peng@primarydata.com> References: <1436778368-65447-1-git-send-email-tao.peng@primarydata.com> Sender: linux-nfs-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-nfs@vger.kernel.org X-Spam-Status: No, score=-8.3 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=ham version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP It can be called by user space to CLONE two files. Follow btrfs lead and define NFS_IOC_CLONE same as BTRFS_IOC_CLONE. Thus we don't mess up userspace with too many ioctls. Signed-off-by: Peng Tao --- fs/nfs/nfs4file.c | 102 +++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/nfs.h | 4 ++ 2 files changed, 106 insertions(+) diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index dcd39d4..dfa6620 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -4,6 +4,7 @@ * Copyright (C) 1992 Rick Sladkey */ #include +#include #include #include #include "internal.h" @@ -166,8 +167,104 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t return nfs42_proc_deallocate(filep, offset, len); return nfs42_proc_allocate(filep, offset, len); } + +static noinline long +nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd, + u64 src_off, u64 dst_off, u64 count) +{ + struct inode *dst_inode = file_inode(dst_file); + struct fd src_file; + struct inode *src_inode; + int ret; + + /* dst file must be opened for writing */ + if (!(dst_file->f_mode & FMODE_WRITE)) + return -EINVAL; + + ret = mnt_want_write_file(dst_file); + if (ret) + return ret; + + src_file = fdget(srcfd); + if (!src_file.file) { + ret = -EBADF; + goto out_drop_write; + } + + src_inode = file_inode(src_file.file); + + /* src and dst must be different files */ + ret = -EINVAL; + if (src_inode == dst_inode) + goto out_fput; + + /* src file must be opened for reading */ + if (!(src_file.file->f_mode & FMODE_READ)) + goto out_fput; + + /* src and dst must be regular files */ + ret = -EISDIR; + if (!S_ISREG(src_inode->i_mode) || !S_ISREG(dst_inode->i_mode)) + goto out_fput; + + ret = -EXDEV; + if (src_file.file->f_path.mnt != dst_file->f_path.mnt || + src_inode->i_sb != dst_inode->i_sb) + goto out_fput; + + /* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */ + if (dst_inode < src_inode) { + mutex_lock_nested(&dst_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD); + } else { + mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&dst_inode->i_mutex, I_MUTEX_CHILD); + } + + /* flush all pending writes on both src and dst so that server + * has the latest data */ + ret = nfs_sync_inode(src_inode); + if (ret) + goto out_unlock; + ret = nfs_sync_inode(dst_inode); + if (ret) + goto out_unlock; + + ret = nfs42_proc_clone(src_file.file, dst_file, src_off, dst_off, count); + + /* truncate inode page cache of the dst range so that future reads can fetch + * new data from server */ + if (!ret) + truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1); + +out_unlock: + if (dst_inode < src_inode) { + mutex_unlock(&src_inode->i_mutex); + mutex_unlock(&dst_inode->i_mutex); + } else { + mutex_unlock(&dst_inode->i_mutex); + mutex_unlock(&src_inode->i_mutex); + } +out_fput: + fdput(src_file); +out_drop_write: + mnt_drop_write_file(dst_file); + return ret; +} #endif /* CONFIG_NFS_V4_2 */ +long nfs4_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + switch (cmd) { +#ifdef CONFIG_NFS_V4_2 + case NFS_IOC_CLONE: + return nfs42_ioctl_clone(file, arg, 0, 0, 0); +#endif + } + + return -ENOTTY; +} + const struct file_operations nfs4_file_operations = { #ifdef CONFIG_NFS_V4_2 .llseek = nfs4_file_llseek, @@ -190,4 +287,9 @@ const struct file_operations nfs4_file_operations = { #endif /* CONFIG_NFS_V4_2 */ .check_flags = nfs_check_flags, .setlease = simple_nosetlease, +#ifdef CONFIG_COMPAT + .unlocked_ioctl = nfs4_ioctl, +#else + .compat_ioctl = nfs4_ioctl, +#endif /* CONFIG_COMPAT */ }; diff --git a/include/uapi/linux/nfs.h b/include/uapi/linux/nfs.h index 5199a36..d85748d 100644 --- a/include/uapi/linux/nfs.h +++ b/include/uapi/linux/nfs.h @@ -31,6 +31,10 @@ #define NFS_PIPE_DIRNAME "nfs" +/* NFS ioctls */ +/* Let's follow btrfs lead on CLONE to avoid messing userspace */ +#define NFS_IOC_CLONE _IOW(0x94, 9, int) + /* * NFS stats. The good thing with these values is that NFSv3 errors are * a superset of NFSv2 errors (with the exception of NFSERR_WFLUSH which