From 7d95eddf313c88b24f99d4ca9c2411a4b82fef33 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Sun, 21 May 2017 22:33:23 -0400 Subject: ext4: fix SEEK_HOLE Currently, SEEK_HOLE implementation in ext4 may both return that there's a hole at some offset although that offset already has data and skip some holes during a search for the next hole. The first problem is demostrated by: xfs_io -c "falloc 0 256k" -c "pwrite 0 56k" -c "seek -h 0" file wrote 57344/57344 bytes at offset 0 56 KiB, 14 ops; 0.0000 sec (2.054 GiB/sec and 538461.5385 ops/sec) Whence Result HOLE 0 Where we can see that SEEK_HOLE wrongly returned offset 0 as containing a hole although we have written data there. The second problem can be demonstrated by: xfs_io -c "falloc 0 256k" -c "pwrite 0 56k" -c "pwrite 128k 8k" -c "seek -h 0" file wrote 57344/57344 bytes at offset 0 56 KiB, 14 ops; 0.0000 sec (1.978 GiB/sec and 518518.5185 ops/sec) wrote 8192/8192 bytes at offset 131072 8 KiB, 2 ops; 0.0000 sec (2 GiB/sec and 500000.0000 ops/sec) Whence Result HOLE 139264 Where we can see that hole at offsets 56k..128k has been ignored by the SEEK_HOLE call. The underlying problem is in the ext4_find_unwritten_pgoff() which is just buggy. In some cases it fails to update returned offset when it finds a hole (when no pages are found or when the first found page has higher index than expected), in some cases conditions for detecting hole are just missing (we fail to detect a situation where indices of returned pages are not contiguous). Fix ext4_find_unwritten_pgoff() to properly detect non-contiguous page indices and also handle all cases where we got less pages then expected in one place and handle it properly there. CC: stable@vger.kernel.org Fixes: c8c0df241cc2719b1262e627f999638411934f60 CC: Zheng Liu Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/file.c | 50 ++++++++++++++------------------------------------ 1 file changed, 14 insertions(+), 36 deletions(-) (limited to 'fs/ext4/file.c') diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 831fd6beebf0..bbea2dccd584 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -484,47 +484,27 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, num = min_t(pgoff_t, end - index, PAGEVEC_SIZE); nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, (pgoff_t)num); - if (nr_pages == 0) { - if (whence == SEEK_DATA) - break; - - BUG_ON(whence != SEEK_HOLE); - /* - * If this is the first time to go into the loop and - * offset is not beyond the end offset, it will be a - * hole at this offset - */ - if (lastoff == startoff || lastoff < endoff) - found = 1; - break; - } - - /* - * If this is the first time to go into the loop and - * offset is smaller than the first page offset, it will be a - * hole at this offset. - */ - if (lastoff == startoff && whence == SEEK_HOLE && - lastoff < page_offset(pvec.pages[0])) { - found = 1; + if (nr_pages == 0) break; - } for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; struct buffer_head *bh, *head; /* - * If the current offset is not beyond the end of given - * range, it will be a hole. + * If current offset is smaller than the page offset, + * there is a hole at this offset. */ - if (lastoff < endoff && whence == SEEK_HOLE && - page->index > end) { + if (whence == SEEK_HOLE && lastoff < endoff && + lastoff < page_offset(pvec.pages[i])) { found = 1; *offset = lastoff; goto out; } + if (page->index > end) + goto out; + lock_page(page); if (unlikely(page->mapping != inode->i_mapping)) { @@ -564,20 +544,18 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, unlock_page(page); } - /* - * The no. of pages is less than our desired, that would be a - * hole in there. - */ - if (nr_pages < num && whence == SEEK_HOLE) { - found = 1; - *offset = lastoff; + /* The no. of pages is less than our desired, we are done. */ + if (nr_pages < num) break; - } index = pvec.pages[i - 1]->index + 1; pagevec_release(&pvec); } while (index <= end); + if (whence == SEEK_HOLE && lastoff < endoff) { + found = 1; + *offset = lastoff; + } out: pagevec_release(&pvec); return found; -- cgit From 3f1d5bad3fae983da07be01cff2fde13293bb7b9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Sun, 21 May 2017 22:34:23 -0400 Subject: ext4: fix off-by-in in loop termination in ext4_find_unwritten_pgoff() There is an off-by-one error in loop termination conditions in ext4_find_unwritten_pgoff() since 'end' may index a page beyond end of desired range if 'endoff' is page aligned. It doesn't have any visible effects but still it is good to fix it. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/ext4/file.c') diff --git a/fs/ext4/file.c b/fs/ext4/file.c index bbea2dccd584..2b00bf84c05b 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -474,7 +474,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, endoff = (loff_t)end_blk << blkbits; index = startoff >> PAGE_SHIFT; - end = endoff >> PAGE_SHIFT; + end = (endoff - 1) >> PAGE_SHIFT; pagevec_init(&pvec, 0); do { -- cgit From 624327f8794704c5066b11a52f9da6a09dce7f9a Mon Sep 17 00:00:00 2001 From: Eryu Guan Date: Wed, 24 May 2017 18:02:20 -0400 Subject: ext4: fix off-by-one on max nr_pages in ext4_find_unwritten_pgoff() ext4_find_unwritten_pgoff() is used to search for offset of hole or data in page range [index, end] (both inclusive), and the max number of pages to search should be at least one, if end == index. Otherwise the only page is missed and no hole or data is found, which is not correct. When block size is smaller than page size, this can be demonstrated by preallocating a file with size smaller than page size and writing data to the last block. E.g. run this xfs_io command on a 1k block size ext4 on x86_64 host. # xfs_io -fc "falloc 0 3k" -c "pwrite 2k 1k" \ -c "seek -d 0" /mnt/ext4/testfile wrote 1024/1024 bytes at offset 2048 1 KiB, 1 ops; 0.0000 sec (42.459 MiB/sec and 43478.2609 ops/sec) Whence Result DATA EOF Data at offset 2k was missed, and lseek(2) returned ENXIO. This is unconvered by generic/285 subtest 07 and 08 on ppc64 host, where pagesize is 64k. Because a recent change to generic/285 reduced the preallocated file size to smaller than 64k. Signed-off-by: Eryu Guan Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- fs/ext4/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/ext4/file.c') diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 2b00bf84c05b..02ce7e7bbdf5 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -481,7 +481,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, int i, num; unsigned long nr_pages; - num = min_t(pgoff_t, end - index, PAGEVEC_SIZE); + num = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1; nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, (pgoff_t)num); if (nr_pages == 0) -- cgit