From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from userp2120.oracle.com ([156.151.31.85]:55374 "EHLO userp2120.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727625AbeJEHmJ (ORCPT ); Fri, 5 Oct 2018 03:42:09 -0400 Subject: [PATCH 11/15] vfs: allow short clone and dedupe operations From: "Darrick J. Wong" To: david@fromorbit.com, darrick.wong@oracle.com Cc: linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-btrfs@vger.kernel.org, ocfs2-devel@oss.oracle.com, sandeen@redhat.com Date: Thu, 04 Oct 2018 17:45:54 -0700 Message-ID: <153870035471.29072.15690301164025555492.stgit@magnolia> In-Reply-To: <153870027422.29072.7433543674436957232.stgit@magnolia> References: <153870027422.29072.7433543674436957232.stgit@magnolia> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: linux-fsdevel-owner@vger.kernel.org List-ID: From: Darrick J. Wong Allow the clone and dedupe prep function to shorten the request if the caller can handle it. Signed-off-by: Darrick J. Wong --- fs/read_write.c | 8 ++------ include/linux/fs.h | 2 +- mm/filemap.c | 19 +++++++++++++++---- 3 files changed, 18 insertions(+), 11 deletions(-) diff --git a/fs/read_write.c b/fs/read_write.c index 4eaea52f70a8..292d68c2f47c 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1726,7 +1726,6 @@ int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); - uint64_t nlen; loff_t isize; bool same_inode = (inode_in == inode_out); bool is_dedupe = (flags & CLONERANGE_DEDUPE); @@ -1758,13 +1757,10 @@ int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, } /* Check that we don't violate system file offset limits. */ - nlen = *len; - ret = generic_clone_checks(file_in, pos_in, file_out, pos_out, &nlen, - is_dedupe); + ret = generic_clone_checks(file_in, pos_in, file_out, pos_out, len, + flags); if (ret) return ret; - if (nlen != *len) - return -EINVAL; /* Wait for the completion of any pending IOs on both files */ inode_dio_wait(inode_in); diff --git a/include/linux/fs.h b/include/linux/fs.h index ae5685c31270..eb35363478e5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2988,7 +2988,7 @@ 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_clone_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *count, bool is_dedupe); + uint64_t *count, unsigned int flags); 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 f74391721234..013451b8017f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2983,7 +2983,7 @@ EXPORT_SYMBOL(generic_write_checks); */ int generic_clone_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *req_count, bool is_dedupe) + uint64_t *req_count, unsigned int flags) { struct inode *inode_in = file_in->f_mapping->host; struct inode *inode_out = file_out->f_mapping->host; @@ -3005,7 +3005,7 @@ int generic_clone_checks(struct file *file_in, loff_t pos_in, size_out = i_size_read(inode_out); /* Dedupe requires both ranges to be within EOF. */ - if (is_dedupe && + if ((flags & CLONERANGE_DEDUPE) && (pos_in >= size_in || pos_in + count > size_in || pos_out >= size_out || pos_out + count > size_out)) return -EINVAL; @@ -3056,8 +3056,12 @@ int generic_clone_checks(struct file *file_in, loff_t pos_in, if (pos_in + count == size_in) { bcount = ALIGN(size_in, bs) - pos_in; } else { - if (!IS_ALIGNED(count, bs)) - return -EINVAL; + if (!IS_ALIGNED(count, bs)) { + if (flags & CLONERANGE_SHORT) + count = ALIGN_DOWN(count, bs); + else + return -EINVAL; + } bcount = count; } @@ -3068,6 +3072,13 @@ int generic_clone_checks(struct file *file_in, loff_t pos_in, pos_out < pos_in + bcount) return -EINVAL; + /* + * We shortened the request but the caller can't deal with that, so + * bounce the request back to userspace. + */ + if (*req_count != count && !(flags & CLONERANGE_SHORT)) + return -EINVAL; + *req_count = count; return 0; }