From 0f0ff9a9f3fa2ec6f427603fd521d5f3a0b076d1 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 1 Jul 2015 23:37:46 -0400 Subject: ext4: fix fencepost error in lazytime optimization Commit 8f4d8558391: "ext4: fix lazytime optimization" was not a complete fix. In the case where the inode number is a multiple of 16, and we could still end up updating an inode with dirty timestamps written to the wrong inode on disk. Oops. This can be easily reproduced by using generic/005 with a file system with metadata_csum and lazytime enabled. Signed-off-by: Theodore Ts'o Cc: stable@vger.kernel.org --- fs/ext4/inode.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e057c6fcc227..4ad73d3c1003 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4348,7 +4348,12 @@ static void ext4_update_other_inodes_time(struct super_block *sb, int inode_size = EXT4_INODE_SIZE(sb); oi.orig_ino = orig_ino; - ino = (orig_ino & ~(inodes_per_block - 1)) + 1; + /* + * Calculate the first inode in the inode table block. Inode + * numbers are one-based. That is, the first inode in a block + * (assuming 4k blocks and 256 byte inodes) is (n*16 + 1). + */ + ino = ((orig_ino - 1) & ~(inodes_per_block - 1)) + 1; for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) { if (ino == orig_ino) continue; -- cgit v1.2.3 From 9705acd63b125dee8b15c705216d7186daea4625 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Fri, 3 Jul 2015 21:13:55 -0400 Subject: ext4: fix reservation release on invalidatepage for delalloc fs On delalloc enabled file system on invalidatepage operation in ext4_da_page_release_reservation() we want to clear the delayed buffer and remove the extent covering the delayed buffer from the extent status tree. However currently there is a bug where on the systems with page size > block size we will always remove extents from the start of the page regardless where the actual delayed buffers are positioned in the page. This leads to the errors like this: EXT4-fs warning (device loop0): ext4_da_release_space:1225: ext4_da_release_space: ino 13, to_free 1 with only 0 reserved data blocks This however can cause data loss on writeback time if the file system is in ENOSPC condition because we're releasing reservation for someones else delayed buffer. Fix this by only removing extents that corresponds to the part of the page we want to invalidate. This problem is reproducible by the following fio receipt (however I was only able to reproduce it with fio-2.1 or older. [global] bs=8k iodepth=1024 iodepth_batch=60 randrepeat=1 size=1m directory=/mnt/test numjobs=20 [job1] ioengine=sync bs=1k direct=1 rw=randread filename=file1:file2 [job2] ioengine=libaio rw=randwrite direct=1 filename=file1:file2 [job3] bs=1k ioengine=posixaio rw=randwrite direct=1 filename=file1:file2 [job5] bs=1k ioengine=sync rw=randread filename=file1:file2 [job7] ioengine=libaio rw=randwrite filename=file1:file2 [job8] ioengine=posixaio rw=randwrite filename=file1:file2 [job10] ioengine=mmap rw=randwrite bs=1k filename=file1:file2 [job11] ioengine=mmap rw=randwrite direct=1 filename=file1:file2 Signed-off-by: Lukas Czerner Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara Cc: stable@vger.kernel.org --- fs/ext4/inode.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4ad73d3c1003..2334e86d7447 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1330,7 +1330,7 @@ static void ext4_da_page_release_reservation(struct page *page, unsigned int offset, unsigned int length) { - int to_release = 0; + int to_release = 0, contiguous_blks = 0; struct buffer_head *head, *bh; unsigned int curr_off = 0; struct inode *inode = page->mapping->host; @@ -1351,14 +1351,23 @@ static void ext4_da_page_release_reservation(struct page *page, if ((offset <= curr_off) && (buffer_delay(bh))) { to_release++; + contiguous_blks++; clear_buffer_delay(bh); + } else if (contiguous_blks) { + lblk = page->index << + (PAGE_CACHE_SHIFT - inode->i_blkbits); + lblk += (curr_off >> inode->i_blkbits) - + contiguous_blks; + ext4_es_remove_extent(inode, lblk, contiguous_blks); + contiguous_blks = 0; } curr_off = next_off; } while ((bh = bh->b_this_page) != head); - if (to_release) { + if (contiguous_blks) { lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - ext4_es_remove_extent(inode, lblk, to_release); + lblk += (curr_off >> inode->i_blkbits) - contiguous_blks; + ext4_es_remove_extent(inode, lblk, contiguous_blks); } /* If we have released all the blocks belonging to a cluster, then we -- cgit v1.2.3