[02/29] vfs: check file ranges before cloning files

Message ID	153981626908.5568.2941448247165011813.stgit@magnolia (mailing list archive)
State	New, archived
Headers	show Return-Path: <linux-nfs-owner@kernel.org> Subject: [PATCH 02/29] vfs: check file ranges before cloning files From: "Darrick J. Wong" <darrick.wong@oracle.com> To: david@fromorbit.com, darrick.wong@oracle.com Cc: sandeen@redhat.com, linux-nfs@vger.kernel.org, linux-cifs@vger.kernel.org, Amir Goldstein <amir73il@gmail.com>, linux-unionfs@vger.kernel.org, linux-xfs@vger.kernel.org, linux-mm@kvack.org, linux-btrfs@vger.kernel.org, linux-fsdevel@vger.kernel.org, Christoph Hellwig <hch@lst.de>, ocfs2-devel@oss.oracle.com Date: Wed, 17 Oct 2018 15:44:29 -0700 Message-ID: <153981626908.5568.2941448247165011813.stgit@magnolia> In-Reply-To: <153981625504.5568.2708520119290577378.stgit@magnolia> References: <153981625504.5568.2708520119290577378.stgit@magnolia> User-Agent: StGit/0.17.1-dirty MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: linux-nfs-owner@vger.kernel.org Precedence: bulk
Series	fs: fixes for serious clone/dedupe problems \| expand [v6,00/29] fs: fixes for serious clone/dedupe problems [01/29] vfs: vfs_clone_file_prep_inodes should return EINVAL for a clone from beyond EOF [02/29] vfs: check file ranges before cloning files [03/29] vfs: exit early from zero length remap operations [04/29] vfs: strengthen checking of file range inputs to generic_remap_checks [05/29] vfs: avoid problematic remapping requests into partial EOF block [06/29] vfs: skip zero-length dedupe requests [07/29] vfs: rename vfs_clone_file_prep to be more descriptive [08/29] vfs: rename clone_verify_area to remap_verify_area [09/29] vfs: combine the clone and dedupe into a single remap_file_range [10/29] vfs: pass remap flags to generic_remap_file_range_prep [11/29] vfs: pass remap flags to generic_remap_checks [12/29] vfs: remap helper should update destination inode metadata [13/29] vfs: make remap_file_range functions take and return bytes completed [14/29] vfs: plumb remap flags through the vfs clone functions [15/29] vfs: plumb remap flags through the vfs dedupe functions [16/29] vfs: enable remap callers that can handle short operations [17/29] vfs: hide file range comparison function [18/29] vfs: clean up generic_remap_file_range_prep return value [19/29] ocfs2: truncate page cache for clone destination file before remapping [20/29] ocfs2: fix pagecache truncation prior to reflink [21/29] ocfs2: support partial clone range and dedupe range [22/29] ocfs2: remove ocfs2_reflink_remap_range [23/29] xfs: add a per-xfs trace_printk macro [24/29] xfs: fix pagecache truncation prior to reflink [25/29] xfs: clean up xfs_reflink_remap_blocks call site [26/29] xfs: support returning partial reflink results [27/29] xfs: remove redundant remap partial EOF block checks [28/29] xfs: remove xfs_reflink_remap_range [29/29] xfs: remove [cm]time update from reflink calls

diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 7a5ee145c733..19e03936c5e1 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4850,7 +4850,7 @@ int ocfs2_reflink_remap_range(struct file *file_in, (OCFS2_I(inode_out)->ip_flags & OCFS2_INODE_SYSTEM_FILE)) goto out_unlock; - ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out, + ret = vfs_clone_file_prep(file_in, pos_in, file_out, pos_out, &len, is_dedupe); if (ret <= 0) goto out_unlock; diff --git a/fs/read_write.c b/fs/read_write.c index 260797b01851..d6e8e242a15f 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1717,13 +1717,12 @@ static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write) * Returns: 0 for "nothing to clone", 1 for "something to clone", or * the usual negative error code. */ -int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, - struct inode *inode_out, loff_t pos_out, - u64 *len, bool is_dedupe) +int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *len, bool is_dedupe) { - loff_t bs = inode_out->i_sb->s_blocksize; - loff_t blen; - loff_t isize; + struct inode *inode_in = file_inode(file_in); + struct inode *inode_out = file_inode(file_out); bool same_inode = (inode_in == inode_out); int ret; @@ -1740,10 +1739,10 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; - isize = i_size_read(inode_in); - /* Zero length dedupe exits immediately; reflink goes to EOF. */ if (*len == 0) { + loff_t isize = i_size_read(inode_in); + if (is_dedupe || pos_in == isize) return 0; if (pos_in > isize) @@ -1751,36 +1750,11 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, *len = isize - pos_in; } - /* Ensure offsets don't wrap and the input is inside i_size */ - if (pos_in + *len < pos_in || pos_out + *len < pos_out || - pos_in + *len > isize) - return -EINVAL; - - /* Don't allow dedupe past EOF in the dest file */ - if (is_dedupe) { - loff_t disize; - - disize = i_size_read(inode_out); - if (pos_out >= disize || pos_out + *len > disize) - return -EINVAL; - } - - /* If we're linking to EOF, continue to the block boundary. */ - if (pos_in + *len == isize) - blen = ALIGN(isize, bs) - pos_in; - else - blen = *len; - - /* Only reflink if we're aligned to block boundaries */ - if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || - !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) - return -EINVAL; - - /* Don't allow overlapped reflink within the same file */ - if (same_inode) { - if (pos_out + blen > pos_in && pos_out < pos_in + blen) - return -EINVAL; - } + /* Check that we don't violate system file offset limits. */ + ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len, + is_dedupe); + if (ret) + return ret; /* Wait for the completion of any pending IOs on both files */ inode_dio_wait(inode_in); @@ -1813,7 +1787,7 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, return 1; } -EXPORT_SYMBOL(vfs_clone_file_prep_inodes); +EXPORT_SYMBOL(vfs_clone_file_prep); int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len) @@ -1851,9 +1825,6 @@ int do_clone_file_range(struct file *file_in, loff_t pos_in, if (ret) return ret; - if (pos_in + len > i_size_read(inode_in)) - return -EINVAL; - ret = file_in->f_op->clone_file_range(file_in, pos_in, file_out, pos_out, len); if (!ret) { diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 42ea7bab9144..281d5f53f2ec 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1326,7 +1326,7 @@ xfs_reflink_remap_prep( if (IS_DAX(inode_in) || IS_DAX(inode_out)) goto out_unlock; - ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out, + ret = vfs_clone_file_prep(file_in, pos_in, file_out, pos_out, len, is_dedupe); if (ret <= 0) goto out_unlock; diff --git a/include/linux/fs.h b/include/linux/fs.h index 897eae8faee1..ba93a6e7dac4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1825,9 +1825,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); -extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, - struct inode *inode_out, loff_t pos_out, - u64 *len, bool is_dedupe); +extern int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *count, bool is_dedupe); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, @@ -2967,6 +2967,9 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); +extern int generic_remap_checks(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + uint64_t *count, bool is_dedupe); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/mm/filemap.c b/mm/filemap.c index 52517f28e6f4..47e6bfd45a91 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2974,6 +2974,75 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) } EXPORT_SYMBOL(generic_write_checks); +/* + * Performs necessary checks before doing a clone. + * + * Can adjust amount of bytes to clone. + * Returns appropriate error code that caller should return or + * zero in case the clone should be allowed. + */ +int generic_remap_checks(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + uint64_t *req_count, bool is_dedupe) +{ + struct inode *inode_in = file_in->f_mapping->host; + struct inode *inode_out = file_out->f_mapping->host; + uint64_t count = *req_count; + uint64_t bcount; + loff_t size_in, size_out; + loff_t bs = inode_out->i_sb->s_blocksize; + + /* The start of both ranges must be aligned to an fs block. */ + if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs)) + return -EINVAL; + + /* Ensure offsets don't wrap. */ + if (pos_in + count < pos_in || pos_out + count < pos_out) + return -EINVAL; + + size_in = i_size_read(inode_in); + size_out = i_size_read(inode_out); + + /* Dedupe requires both ranges to be within EOF. */ + if (is_dedupe && + (pos_in >= size_in || pos_in + count > size_in || + pos_out >= size_out || pos_out + count > size_out)) + return -EINVAL; + + /* Ensure the infile range is within the infile. */ + if (pos_in >= size_in) + return -EINVAL; + count = min(count, size_in - (uint64_t)pos_in); + + /* + * If the user wanted us to link to the infile's EOF, round up to the + * next block boundary for this check. + * + * Otherwise, make sure the count is also block-aligned, having + * already confirmed the starting offsets' block alignment. + */ + if (pos_in + count == size_in) { + bcount = ALIGN(size_in, bs) - pos_in; + } else { + if (!IS_ALIGNED(count, bs)) + return -EINVAL; + + bcount = count; + } + + /* Don't allow overlapped cloning within the same file. */ + if (inode_in == inode_out && + pos_out + bcount > pos_in && + pos_out < pos_in + bcount) + return -EINVAL; + + /* For now we don't support changing the length. */ + if (*req_count != count) + return -EINVAL; + + return 0; +} + int pagecache_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata)

[02/29] vfs: check file ranges before cloning files

Commit Message

Patch