From patchwork Mon Jun 22 15:24:57 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Goldwyn Rodrigues X-Patchwork-Id: 11618215 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 8875017C5 for ; Mon, 22 Jun 2020 15:25:34 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 7A17B206D7 for ; Mon, 22 Jun 2020 15:25:34 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729525AbgFVPZd (ORCPT ); Mon, 22 Jun 2020 11:25:33 -0400 Received: from mx2.suse.de ([195.135.220.15]:52448 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1729374AbgFVPZc (ORCPT ); Mon, 22 Jun 2020 11:25:32 -0400 X-Virus-Scanned: by amavisd-new at test-mx.suse.de Received: from relay2.suse.de (unknown [195.135.221.27]) by mx2.suse.de (Postfix) with ESMTP id 84AC9C209; Mon, 22 Jun 2020 15:25:29 +0000 (UTC) From: Goldwyn Rodrigues To: linux-fsdevel@vger.kernel.org Cc: linux-btrfs@vger.kernel.org, hch@lst.de, darrick.wong@oracle.com, david@fromorbit.com, dsterba@suse.cz, jthumshirn@suse.de, fdmanana@gmail.com, Goldwyn Rodrigues Subject: [PATCH 6/6] btrfs: split btrfs_direct_IO to read and write part Date: Mon, 22 Jun 2020 10:24:57 -0500 Message-Id: <20200622152457.7118-7-rgoldwyn@suse.de> X-Mailer: git-send-email 2.25.0 In-Reply-To: <20200622152457.7118-1-rgoldwyn@suse.de> References: <20200622152457.7118-1-rgoldwyn@suse.de> MIME-Version: 1.0 Sender: linux-btrfs-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-btrfs@vger.kernel.org From: Goldwyn Rodrigues The read and write versions don't have anything in common except for the call to iomap_dio_rw. So split this function, and merge each half into its only caller. Originally proposed by Christoph Hellwig Signed-off-by: Goldwyn Rodrigues --- fs/btrfs/ctree.h | 3 ++ fs/btrfs/file.c | 95 +++++++++++++++++++++++++++++++++++++++++++----- fs/btrfs/inode.c | 86 +------------------------------------------ 3 files changed, 90 insertions(+), 94 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 47b8874eddff..161533040978 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -28,6 +28,7 @@ #include #include #include +#include #include "extent-io-tree.h" #include "extent_io.h" #include "extent_map.h" @@ -2934,6 +2935,8 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start, u64 end, int uptodate); extern const struct dentry_operations btrfs_dentry_operations; ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter); +extern const struct iomap_ops btrfs_dio_iomap_ops; +extern const struct iomap_dio_ops btrfs_dops; /* ioctl.c */ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index dff89d04fd16..7f75adf70bcd 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1809,21 +1809,65 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, return num_written ? num_written : ret; } -static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) +static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info, + const struct iov_iter *iter, loff_t offset) +{ + const unsigned int blocksize_mask = fs_info->sectorsize - 1; + + if (offset & blocksize_mask) + return -EINVAL; + + if (iov_iter_alignment(iter) & blocksize_mask) + return -EINVAL; + + return 0; +} + +static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - loff_t pos; - ssize_t written; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + loff_t pos = iocb->ki_pos; + ssize_t written = 0; ssize_t written_buffered; loff_t endbyte; int err; + size_t count = 0; + bool relock = false; + int flags = IOMAP_DIOF_PGINVALID_FAIL; + + if (check_direct_IO(fs_info, from, pos)) + goto buffered; - written = btrfs_direct_IO(iocb, from); + count = iov_iter_count(from); + /* + * If the write DIO is beyond the EOF, we need update the isize, but it + * is protected by i_mutex. So we can not unlock the i_mutex at this + * case. + */ + if (pos + count <= inode->i_size) { + inode_unlock(inode); + relock = true; + } else if (iocb->ki_flags & IOCB_NOWAIT) { + return -EAGAIN; + } + + if (is_sync_kiocb(iocb)) + flags |= IOMAP_DIOF_WAIT_FOR_COMPLETION; + + down_read(&BTRFS_I(inode)->dio_sem); + written = iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dops, + flags); + up_read(&BTRFS_I(inode)->dio_sem); + + if (relock) + inode_lock(inode); if (written < 0 || !iov_iter_count(from)) return written; +buffered: pos = iocb->ki_pos; written_buffered = btrfs_buffered_write(iocb, from); if (written_buffered < 0) { @@ -1962,7 +2006,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, atomic_inc(&BTRFS_I(inode)->sync_writers); if (iocb->ki_flags & IOCB_DIRECT) { - num_written = __btrfs_direct_write(iocb, from); + num_written = btrfs_direct_write(iocb, from); } else { num_written = btrfs_buffered_write(iocb, from); if (num_written > 0) @@ -3476,16 +3520,47 @@ static int btrfs_file_open(struct inode *inode, struct file *filp) return generic_file_open(inode, filp); } +static int check_direct_read(struct btrfs_fs_info *fs_info, + const struct iov_iter *iter, loff_t offset) +{ + int ret; + int i, seg; + + ret = check_direct_IO(fs_info, iter, offset); + if (ret < 0) + return ret; + + for (seg = 0; seg < iter->nr_segs; seg++) + for (i = seg + 1; i < iter->nr_segs; i++) + if (iter->iov[seg].iov_base == iter->iov[i].iov_base) + return -EINVAL; + return 0; +} + +static ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to) +{ + struct inode *inode = file_inode(iocb->ki_filp); + ssize_t ret; + int flags = IOMAP_DIOF_PGINVALID_FAIL; + + if (check_direct_read(btrfs_sb(inode->i_sb), to, iocb->ki_pos)) + return 0; + + if (is_sync_kiocb(iocb)) + flags |= IOMAP_DIOF_WAIT_FOR_COMPLETION; + + inode_lock_shared(inode); + ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dops, flags); + inode_unlock_shared(inode); + return ret; +} + static ssize_t btrfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { ssize_t ret = 0; if (iocb->ki_flags & IOCB_DIRECT) { - struct inode *inode = file_inode(iocb->ki_filp); - - inode_lock_shared(inode); - ret = btrfs_direct_IO(iocb, to); - inode_unlock_shared(inode); + ret = btrfs_direct_read(iocb, to); if (ret < 0) return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index edce0d77253b..31ac8c682f19 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -29,7 +29,6 @@ #include #include #include -#include #include #include "misc.h" #include "ctree.h" @@ -7820,96 +7819,15 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, return BLK_QC_T_NONE; } -static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info, - const struct iov_iter *iter, loff_t offset) -{ - int seg; - int i; - unsigned int blocksize_mask = fs_info->sectorsize - 1; - ssize_t retval = -EINVAL; - - if (offset & blocksize_mask) - goto out; - - if (iov_iter_alignment(iter) & blocksize_mask) - goto out; - - /* If this is a write we don't need to check anymore */ - if (iov_iter_rw(iter) != READ || !iter_is_iovec(iter)) - return 0; - /* - * Check to make sure we don't have duplicate iov_base's in this - * iovec, if so return EINVAL, otherwise we'll get csum errors - * when reading back. - */ - for (seg = 0; seg < iter->nr_segs; seg++) { - for (i = seg + 1; i < iter->nr_segs; i++) { - if (iter->iov[seg].iov_base == iter->iov[i].iov_base) - goto out; - } - } - retval = 0; -out: - return retval; -} - -static const struct iomap_ops btrfs_dio_iomap_ops = { +const struct iomap_ops btrfs_dio_iomap_ops = { .iomap_begin = btrfs_dio_iomap_begin, .iomap_end = btrfs_dio_iomap_end, }; -static const struct iomap_dio_ops btrfs_dops = { +const struct iomap_dio_ops btrfs_dops = { .submit_io = btrfs_submit_direct, }; -ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) -{ - struct file *file = iocb->ki_filp; - struct inode *inode = file->f_mapping->host; - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct extent_changeset *data_reserved = NULL; - loff_t offset = iocb->ki_pos; - size_t count = 0; - bool relock = false; - ssize_t ret; - int flags = IOMAP_DIOF_PGINVALID_FAIL; - - if (check_direct_IO(fs_info, iter, offset)) - return 0; - - count = iov_iter_count(iter); - if (iov_iter_rw(iter) == WRITE) { - /* - * If the write DIO is beyond the EOF, we need update - * the isize, but it is protected by i_mutex. So we can - * not unlock the i_mutex at this case. - */ - if (offset + count <= inode->i_size) { - inode_unlock(inode); - relock = true; - } else if (iocb->ki_flags & IOCB_NOWAIT) { - ret = -EAGAIN; - goto out; - } - down_read(&BTRFS_I(inode)->dio_sem); - } - - if (is_sync_kiocb(iocb)) - flags |= IOMAP_DIOF_WAIT_FOR_COMPLETION; - - ret = iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dops, - flags); - - if (iov_iter_rw(iter) == WRITE) { - up_read(&BTRFS_I(inode)->dio_sem); - } -out: - if (relock) - inode_lock(inode); - extent_changeset_free(data_reserved); - return ret; -} - static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) {