From 9c1ee184a30394e54165fa4c15923cabd952c106 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 13 May 2009 18:36:58 -0400 Subject: ext4: Fix sub-block zeroing for writes into preallocated extents We need to mark the buffer_head mapping preallocated space as new during write_begin. Otherwise we don't zero out the page cache content properly for a partial write. This will cause file corruption with preallocation. Now that we mark the buffer_head new we also need to have a valid buffer_head blocknr so that unmap_underlying_metadata() unmaps the correct block. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e91f978c7f12..d4b634ae06bd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2323,6 +2323,13 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, set_buffer_delay(bh_result); } else if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); + /* + * With sub-block writes into unwritten extents + * we also need to mark the buffer as new so that + * the unwritten parts of the buffer gets correctly zeroed. + */ + if (buffer_unwritten(bh_result)) + set_buffer_new(bh_result); ret = 0; } -- cgit v1.2.2 From 33b9817e2ae097c7b8d256e3510ac6c54fc6d9d0 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 12 May 2009 14:40:37 -0400 Subject: ext4: Use a fake block number for delayed new buffer_head Use a very large unsigned number (~0xffff) as as the fake block number for the delayed new buffer. The VFS should never try to write out this number, but if it does, this will make it obvious. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d4b634ae06bd..0ac31a06422b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2297,6 +2297,10 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int ret = 0; + sector_t invalid_block = ~((sector_t) 0xffff); + + if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es)) + invalid_block = ~0; BUG_ON(create == 0); BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize); @@ -2318,7 +2322,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, /* not enough space to reserve */ return ret; - map_bh(bh_result, inode->i_sb, 0); + map_bh(bh_result, inode->i_sb, invalid_block); set_buffer_new(bh_result); set_buffer_delay(bh_result); } else if (ret > 0) { -- cgit v1.2.2 From 2a8964d63d50dd2d65d71d342bc7fb6ef4117614 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 14 May 2009 17:05:39 -0400 Subject: ext4: Clear the unwritten buffer_head flag after the extent is initialized The BH_Unwritten flag indicates that the buffer is allocated on disk but has not been written; that is, the disk was part of a persistent preallocation area. That flag should only be set when a get_blocks() function is looking up a inode's logical to physical block mapping. When ext4_get_blocks_wrap() is called with create=1, the uninitialized extent is converted into an initialized one, so the BH_Unwritten flag is no longer appropriate. Hence, we need to make sure the BH_Unwritten is not left set, since the combination of BH_Mapped and BH_Unwritten is not allowed; among other things, it will result ext4's get_block() to be called over and over again during the write_begin phase of write(2). Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0ac31a06422b..2a9ffd528dd1 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1149,6 +1149,7 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, int retval; clear_buffer_mapped(bh); + clear_buffer_unwritten(bh); /* * Try to see if we can get the block without requesting @@ -1178,6 +1179,18 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, if (retval > 0 && buffer_mapped(bh)) return retval; + /* + * When we call get_blocks without the create flag, the + * BH_Unwritten flag could have gotten set if the blocks + * requested were part of a uninitialized extent. We need to + * clear this flag now that we are committed to convert all or + * part of the uninitialized extent to be an initialized + * extent. This is because we need to avoid the combination + * of BH_Unwritten and BH_Mapped flags being simultaneously + * set on the buffer_head. + */ + clear_buffer_unwritten(bh); + /* * New blocks allocate and/or writing to uninitialized extent * will possibly result in updating i_data, so we take -- cgit v1.2.2