From 63d71450c8d817649a79e37d685523f988b9cc98 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Fri, 1 Sep 2017 17:58:47 +0900 Subject: btrfs: clear ordered flag on cleaning up ordered extents Commit 524272607e88 ("btrfs: Handle delalloc error correctly to avoid ordered extent hang") introduced btrfs_cleanup_ordered_extents() to cleanup submitted ordered extents. However, it does not clear the ordered bit (Private2) of corresponding pages. Thus, the following BUG occurs from free_pages_check_bad() (on btrfs/125 with nospace_cache). BUG: Bad page state in process btrfs pfn:3fa787 page:ffffdf2acfe9e1c0 count:0 mapcount:0 mapping: (null) index:0xd flags: 0x8000000000002008(uptodate|private_2) raw: 8000000000002008 0000000000000000 000000000000000d 00000000ffffffff raw: ffffdf2acf5c1b20 ffffb443802238b0 0000000000000000 0000000000000000 page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set bad because of flags: 0x2000(private_2) This patch clears the flag same as other places calling btrfs_dec_test_ordered_pending() for every page in the specified range. Fixes: 524272607e88 ("btrfs: Handle delalloc error correctly to avoid ordered extent hang") Cc: # 4.12 Signed-off-by: Naohiro Aota Reviewed-by: Qu Wenruo Reviewed-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/inode.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d184a46e46c4..455c0f22fe2d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -135,6 +135,18 @@ static inline void btrfs_cleanup_ordered_extents(struct inode *inode, const u64 offset, const u64 bytes) { + unsigned long index = offset >> PAGE_SHIFT; + unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT; + struct page *page; + + while (index <= end_index) { + page = find_get_page(inode->i_mapping, index); + index++; + if (!page) + continue; + ClearPagePrivate2(page); + put_page(page); + } return __endio_write_update_ordered(inode, offset + PAGE_SIZE, bytes - PAGE_SIZE, false); } -- cgit v1.2.3-70-g09d2 From 67c003f90fd68062d92a7ffade36f9b2a9098bd8 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Fri, 1 Sep 2017 17:59:07 +0900 Subject: btrfs: finish ordered extent cleaning if no progress is found __endio_write_update_ordered() repeats the search until it reaches the end of the specified range. This works well with direct IO path, because before the function is called, it's ensured that there are ordered extents filling whole the range. It's not the case, however, when it's called from run_delalloc_range(): it is possible to have error in the midle of the loop in e.g. run_delalloc_nocow(), so that there exisits the range not covered by any ordered extents. By cleaning such "uncomplete" range, __endio_write_update_ordered() stucks at offset where there're no ordered extents. Since the ordered extents are created from head to tail, we can stop the search if there are no offset progress. Fixes: 524272607e88 ("btrfs: Handle delalloc error correctly to avoid ordered extent hang") Cc: # 4.12 Signed-off-by: Naohiro Aota Reviewed-by: Qu Wenruo Reviewed-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/inode.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 455c0f22fe2d..f78c5640c6dc 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8396,6 +8396,7 @@ static void __endio_write_update_ordered(struct inode *inode, btrfs_work_func_t func; u64 ordered_offset = offset; u64 ordered_bytes = bytes; + u64 last_offset; int ret; if (btrfs_is_free_space_inode(BTRFS_I(inode))) { @@ -8407,6 +8408,7 @@ static void __endio_write_update_ordered(struct inode *inode, } again: + last_offset = ordered_offset; ret = btrfs_dec_test_first_ordered_pending(inode, &ordered, &ordered_offset, ordered_bytes, @@ -8417,6 +8419,12 @@ again: btrfs_init_work(&ordered->work, func, finish_ordered_fn, NULL, NULL); btrfs_queue_work(wq, &ordered->work); out_test: + /* + * If btrfs_dec_test_ordered_pending does not find any ordered extent + * in the range, we can exit. + */ + if (ordered_offset == last_offset) + return; /* * our bio might span multiple ordered extents. If we haven't * completed the accounting for the whole dio, go back and try again -- cgit v1.2.3-70-g09d2 From 99c4e3b96c797f047be4e6b7c03cfca01959f146 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Fri, 15 Sep 2017 15:06:51 -0600 Subject: Btrfs: fix unexpected result when dio reading corrupted blocks commit 4246a0b63bd8 ("block: add a bi_error field to struct bio") changed the logic of how dio read endio reports errors. For single stripe dio read, %bio->bi_status reflects the error before verifying checksum, and now we're updating it when data block matches with its checksum, while in the mismatching case, %bio->bi_status is not updated to relfect that. When some blocks in a file have been corrupted on disk, reading such a file ends up with 1) checksum errors are reported in kernel log 2) read(2) returns successfully with some content being 0x01. In order to fix it, we need to report its checksum mismatch error to the upper layer (dio layer in this case) as well. Fixes: 4246a0b63bd8 ("block: add a bi_error field to struct bio") Signed-off-by: Liu Bo Reported-by: Goffredo Baroncelli Tested-by: Goffredo Baroncelli Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f78c5640c6dc..c242d0230db9 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8366,11 +8366,8 @@ static void btrfs_endio_direct_read(struct bio *bio) struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); blk_status_t err = bio->bi_status; - if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) { + if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) err = btrfs_subio_endio_read(inode, io_bio, err); - if (!err) - bio->bi_status = 0; - } unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset, dip->logical_offset + dip->bytes - 1); @@ -8378,7 +8375,7 @@ static void btrfs_endio_direct_read(struct bio *bio) kfree(dip); - dio_bio->bi_status = bio->bi_status; + dio_bio->bi_status = err; dio_end_io(dio_bio); if (io_bio->end_io) -- cgit v1.2.3-70-g09d2