From 334fd34d76f237c0ee58dfc400d2c4e34d660544 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 29 Jun 2017 11:43:20 -0700 Subject: vfs: Add page_cache_seek_hole_data helper Both ext4 and xfs implement seeking for the next hole or piece of data in unwritten extents by scanning the page cache, and both versions share the same bug when iterating the buffers of a page: the start offset into the page isn't taken into account, so when a page fits more than two filesystem blocks, things will go wrong. For example, on a filesystem with a block size of 1k, the following command will fail: xfs_io -f -c "falloc 0 4k" \ -c "pwrite 1k 1k" \ -c "pwrite 3k 1k" \ -c "seek -a -r 0" foo In this example, neither lseek(fd, 1024, SEEK_HOLE) nor lseek(fd, 2048, SEEK_DATA) will return the correct result. Introduce a generic vfs helper for seeking in the page cache that gets this right. The next commits will replace the filesystem specific implementations. Signed-off-by: Andreas Gruenbacher [hch: dropped the export] Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/buffer_head.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/buffer_head.h') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index bd029e52ef5e..ad4e024ce17e 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -201,6 +201,8 @@ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); int bh_submit_read(struct buffer_head *bh); +loff_t page_cache_seek_hole_data(struct inode *inode, loff_t offset, + loff_t length, int whence); extern int buffer_heads_over_limit; -- cgit v1.2.3 From 87354e5de04fe727227ff619af164202adcfa4d4 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 6 Jul 2017 07:02:21 -0400 Subject: buffer: set errors in mapping at the time that the error occurs I noticed on xfs that I could still sometimes get back an error on fsync on a fd that was opened after the error condition had been cleared. The problem is that the buffer code sets the write_io_error flag and then later checks that flag to set the error in the mapping. That flag perisists for quite a while however. If the file is later opened with O_TRUNC, the buffers will then be invalidated and the mapping's error set such that a subsequent fsync will return error. I think this is incorrect, as there was no writeback between the open and fsync. Add a new mark_buffer_write_io_error operation that sets the flag and the error in the mapping at the same time. Replace all calls to set_buffer_write_io_error with mark_buffer_write_io_error, and remove the places that check this flag in order to set the error in the mapping. This sets the error in the mapping earlier, at the time that it's first detected. Signed-off-by: Jeff Layton Reviewed-by: Jan Kara Reviewed-by: Carlos Maiolino --- fs/buffer.c | 20 +++++++++++++------- fs/gfs2/lops.c | 2 +- include/linux/buffer_head.h | 1 + 3 files changed, 15 insertions(+), 8 deletions(-) (limited to 'include/linux/buffer_head.h') diff --git a/fs/buffer.c b/fs/buffer.c index 4be8b914a222..b946149e8214 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -178,7 +178,7 @@ void end_buffer_write_sync(struct buffer_head *bh, int uptodate) set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost sync page write"); - set_buffer_write_io_error(bh); + mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } unlock_buffer(bh); @@ -352,8 +352,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost async page write"); - mapping_set_error(page->mapping, -EIO); - set_buffer_write_io_error(bh); + mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); SetPageError(page); } @@ -481,8 +480,6 @@ static void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); WARN_ON(!bh->b_assoc_map); - if (buffer_write_io_error(bh)) - mapping_set_error(bh->b_assoc_map, -EIO); bh->b_assoc_map = NULL; } @@ -1181,6 +1178,17 @@ void mark_buffer_dirty(struct buffer_head *bh) } EXPORT_SYMBOL(mark_buffer_dirty); +void mark_buffer_write_io_error(struct buffer_head *bh) +{ + set_buffer_write_io_error(bh); + /* FIXME: do we need to set this in both places? */ + if (bh->b_page && bh->b_page->mapping) + mapping_set_error(bh->b_page->mapping, -EIO); + if (bh->b_assoc_map) + mapping_set_error(bh->b_assoc_map, -EIO); +} +EXPORT_SYMBOL(mark_buffer_write_io_error); + /* * Decrement a buffer_head's reference count. If all buffers against a page * have zero reference count, are clean and unlocked, and if the page is clean @@ -3279,8 +3287,6 @@ drop_buffers(struct page *page, struct buffer_head **buffers_to_free) bh = head; do { - if (buffer_write_io_error(bh) && page->mapping) - mapping_set_error(page->mapping, -EIO); if (buffer_busy(bh)) goto failed; bh = bh->b_this_page; diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index b1f9144b42c7..cd7857ab1a6a 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -182,7 +182,7 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, bh = bh->b_this_page; do { if (error) - set_buffer_write_io_error(bh); + mark_buffer_write_io_error(bh); unlock_buffer(bh); next = bh->b_this_page; size -= bh->b_size; diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index bd029e52ef5e..e0abeba3ced7 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -149,6 +149,7 @@ void buffer_check_dirty_writeback(struct page *page, */ void mark_buffer_dirty(struct buffer_head *bh); +void mark_buffer_write_io_error(struct buffer_head *bh); void init_buffer(struct buffer_head *, bh_end_io_t *, void *); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, -- cgit v1.2.3