From 03cdadb04077b9311bbc67d98cc5401aff76482d Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 26 Feb 2016 15:19:43 -0800 Subject: block: disable block device DAX by default The recent *sync enabling discovered that we are inserting into the block_device pagecache counter to the expectations of the dirty data tracking for dax mappings. This can lead to data corruption. We want to support DAX for block devices eventually, but it requires wider changes to properly manage the pagecache. dump_stack+0x85/0xc2 dax_writeback_mapping_range+0x60/0xe0 blkdev_writepages+0x3f/0x50 do_writepages+0x21/0x30 __filemap_fdatawrite_range+0xc6/0x100 filemap_write_and_wait+0x4a/0xa0 set_blocksize+0x70/0xd0 sb_set_blocksize+0x1d/0x50 ext4_fill_super+0x75b/0x3360 mount_bdev+0x180/0x1b0 ext4_mount+0x15/0x20 mount_fs+0x38/0x170 Mark the support broken so its disabled by default, but otherwise still available for testing. Signed-off-by: Dan Williams Signed-off-by: Ross Zwisler Reported-by: Ross Zwisler Suggested-by: Dave Chinner Reviewed-by: Jan Kara Cc: Jens Axboe Cc: Matthew Wilcox Cc: Al Viro Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/block_dev.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index 39b3a174a425..31c6d1090f11 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1201,7 +1201,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = disk; bdev->bd_queue = disk->queue; bdev->bd_contains = bdev; - bdev->bd_inode->i_flags = disk->fops->direct_access ? S_DAX : 0; + if (IS_ENABLED(CONFIG_BLK_DEV_DAX) && disk->fops->direct_access) + bdev->bd_inode->i_flags = S_DAX; + else + bdev->bd_inode->i_flags = 0; + if (!partno) { ret = -ENXIO; bdev->bd_part = disk_get_part(disk, partno); -- cgit v1.2.3 From 7f6d5b529b7dfe2fca30cbf4bc81e16575090025 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 26 Feb 2016 15:19:55 -0800 Subject: dax: move writeback calls into the filesystems Previously calls to dax_writeback_mapping_range() for all DAX filesystems (ext2, ext4 & xfs) were centralized in filemap_write_and_wait_range(). dax_writeback_mapping_range() needs a struct block_device, and it used to get that from inode->i_sb->s_bdev. This is correct for normal inodes mounted on ext2, ext4 and XFS filesystems, but is incorrect for DAX raw block devices and for XFS real-time files. Instead, call dax_writeback_mapping_range() directly from the filesystem ->writepages function so that it can supply us with a valid block device. This also fixes DAX code to properly flush caches in response to sync(2). Signed-off-by: Ross Zwisler Signed-off-by: Jan Kara Cc: Al Viro Cc: Dan Williams Cc: Dave Chinner Cc: Jens Axboe Cc: Matthew Wilcox Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/block_dev.c | 13 ++++++++++++- fs/dax.c | 12 +++++++----- fs/ext2/inode.c | 8 ++++++++ fs/ext4/inode.c | 4 ++++ fs/xfs/xfs_aops.c | 4 ++++ include/linux/dax.h | 6 ++++-- mm/filemap.c | 12 ++++-------- 7 files changed, 43 insertions(+), 16 deletions(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index 31c6d1090f11..826b164a4b5b 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1697,13 +1697,24 @@ static int blkdev_releasepage(struct page *page, gfp_t wait) return try_to_free_buffers(page); } +static int blkdev_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + if (dax_mapping(mapping)) { + struct block_device *bdev = I_BDEV(mapping->host); + + return dax_writeback_mapping_range(mapping, bdev, wbc); + } + return generic_writepages(mapping, wbc); +} + static const struct address_space_operations def_blk_aops = { .readpage = blkdev_readpage, .readpages = blkdev_readpages, .writepage = blkdev_writepage, .write_begin = blkdev_write_begin, .write_end = blkdev_write_end, - .writepages = generic_writepages, + .writepages = blkdev_writepages, .releasepage = blkdev_releasepage, .direct_IO = blkdev_direct_IO, .is_dirty_writeback = buffer_check_dirty_writeback, diff --git a/fs/dax.c b/fs/dax.c index 9a173dd8c4a3..711172450da6 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -484,11 +484,10 @@ static int dax_writeback_one(struct block_device *bdev, * end]. This is required by data integrity operations to ensure file data is * on persistent storage prior to completion of the operation. */ -int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, - loff_t end) +int dax_writeback_mapping_range(struct address_space *mapping, + struct block_device *bdev, struct writeback_control *wbc) { struct inode *inode = mapping->host; - struct block_device *bdev = inode->i_sb->s_bdev; pgoff_t start_index, end_index, pmd_index; pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; @@ -499,8 +498,11 @@ int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT)) return -EIO; - start_index = start >> PAGE_CACHE_SHIFT; - end_index = end >> PAGE_CACHE_SHIFT; + if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL) + return 0; + + start_index = wbc->range_start >> PAGE_CACHE_SHIFT; + end_index = wbc->range_end >> PAGE_CACHE_SHIFT; pmd_index = DAX_PMD_INDEX(start_index); rcu_read_lock(); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 4467cbd75f24..6bd58e6ff038 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -876,6 +876,14 @@ ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) static int ext2_writepages(struct address_space *mapping, struct writeback_control *wbc) { +#ifdef CONFIG_FS_DAX + if (dax_mapping(mapping)) { + return dax_writeback_mapping_range(mapping, + mapping->host->i_sb->s_bdev, + wbc); + } +#endif + return mpage_writepages(mapping, wbc, ext2_get_block); } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5708e689e63d..aee960b1af34 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2478,6 +2478,10 @@ static int ext4_writepages(struct address_space *mapping, trace_ext4_writepages(inode, wbc); + if (dax_mapping(mapping)) + return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, + wbc); + /* * No pages to write? This is mainly a kludge to avoid starting * a transaction for special inodes like journal inode on last iput() diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index fc20518e2398..a9ebabfe7587 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1208,6 +1208,10 @@ xfs_vm_writepages( struct writeback_control *wbc) { xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED); + if (dax_mapping(mapping)) + return dax_writeback_mapping_range(mapping, + xfs_find_bdev_for_inode(mapping->host), wbc); + return generic_writepages(mapping, wbc); } diff --git a/include/linux/dax.h b/include/linux/dax.h index 7b6bcedb980f..636dd59ab505 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -52,6 +52,8 @@ static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); } -int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, - loff_t end); + +struct writeback_control; +int dax_writeback_mapping_range(struct address_space *mapping, + struct block_device *bdev, struct writeback_control *wbc); #endif diff --git a/mm/filemap.c b/mm/filemap.c index 23edccecadb0..3461d97ecb30 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -446,7 +446,8 @@ int filemap_write_and_wait(struct address_space *mapping) { int err = 0; - if (mapping->nrpages) { + if ((!dax_mapping(mapping) && mapping->nrpages) || + (dax_mapping(mapping) && mapping->nrexceptional)) { err = filemap_fdatawrite(mapping); /* * Even if the above returned error, the pages may be @@ -482,13 +483,8 @@ int filemap_write_and_wait_range(struct address_space *mapping, { int err = 0; - if (dax_mapping(mapping) && mapping->nrexceptional) { - err = dax_writeback_mapping_range(mapping, lstart, lend); - if (err) - return err; - } - - if (mapping->nrpages) { + if ((!dax_mapping(mapping) && mapping->nrpages) || + (dax_mapping(mapping) && mapping->nrexceptional)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ -- cgit v1.2.3