From 79ffab34391933ee3b95dac7f25c0478fa2f8f1e Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 13 May 2009 15:13:42 -0400 Subject: ext4: Properly initialize the buffer_head state These struct buffer_heads are allocated on the stack (and hence are initialized with stack garbage). They are only used to call a get_blocks() function, so that's mostly OK, but b_state must be initialized to be 0 so we don't have any unexpected BH_* flags set by accident, such as BH_Unwritten or BH_Delay. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index e3a55eb8b26..a953214f282 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3150,6 +3150,7 @@ retry: ret = PTR_ERR(handle); break; } + map_bh.b_state = 0; ret = ext4_get_blocks_wrap(handle, inode, block, max_blocks, &map_bh, EXT4_CREATE_UNINITIALIZED_EXT, 0, 0); -- cgit v1.2.3-70-g09d2 From 29fa89d088941d79765d60f22d5ccdd6b8696e11 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 12 May 2009 16:30:27 -0400 Subject: ext4: Mark the unwritten buffer_head as mapped during write_begin Setting BH_Unwritten buffer_heads as BH_Mapped avoids multiple (unnecessary) calls to get_block() during the call to the write(2) system call. Setting BH_Unwritten buffer heads as BH_Mapped requires that the writepages() functions can handle BH_Unwritten buffer_heads. After this commit, things work as follows: ext4_ext_get_block() returns unmapped, unwritten, buffer head when called with create = 0 for prealloc space. This makes sure we handle the read path and non-delayed allocation case correctly. Even though the buffer head is marked unmapped we have valid b_blocknr and b_bdev values in the buffer_head. ext4_da_get_block_prep() called for block resrevation will now return mapped, unwritten, new buffer_head for prealloc space. This avoids multiple calls to get_block() for write to same offset. By making such buffers as BH_New, we also assure that sub-block zeroing of buffered writes happens correctly. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 4 +-- fs/ext4/inode.c | 82 +++++++++++++++++++++++++++++++++++-------------------- 2 files changed, 54 insertions(+), 32 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index a953214f282..ea5c47608ce 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2872,6 +2872,8 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, if (create == EXT4_CREATE_UNINITIALIZED_EXT) goto out; if (!create) { + if (allocated > max_blocks) + allocated = max_blocks; /* * We have blocks reserved already. We * return allocated blocks so that delalloc @@ -2879,8 +2881,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, * the buffer head will be unmapped so that * a read from the block returns 0s. */ - if (allocated > max_blocks) - allocated = max_blocks; set_buffer_unwritten(bh_result); bh_result->b_bdev = inode->i_sb->s_bdev; bh_result->b_blocknr = newblock; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d7ad0bb73cd..96f3366f59f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1852,7 +1852,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd) * @logical - first logical block to start assignment with * * the function goes through all passed space and put actual disk - * block numbers into buffer heads, dropping BH_Delay + * block numbers into buffer heads, dropping BH_Delay and BH_Unwritten */ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical, struct buffer_head *exbh) @@ -1902,16 +1902,24 @@ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical, do { if (cur_logical >= logical + blocks) break; - if (buffer_delay(bh)) { - bh->b_blocknr = pblock; - clear_buffer_delay(bh); - bh->b_bdev = inode->i_sb->s_bdev; - } else if (buffer_unwritten(bh)) { - bh->b_blocknr = pblock; - clear_buffer_unwritten(bh); - set_buffer_mapped(bh); - set_buffer_new(bh); - bh->b_bdev = inode->i_sb->s_bdev; + + if (buffer_delay(bh) || + buffer_unwritten(bh)) { + + BUG_ON(bh->b_bdev != inode->i_sb->s_bdev); + + if (buffer_delay(bh)) { + clear_buffer_delay(bh); + bh->b_blocknr = pblock; + } else { + /* + * unwritten already should have + * blocknr assigned. Verify that + */ + clear_buffer_unwritten(bh); + BUG_ON(bh->b_blocknr != pblock); + } + } else if (buffer_mapped(bh)) BUG_ON(bh->b_blocknr != pblock); @@ -2053,7 +2061,8 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) * We consider only non-mapped and non-allocated blocks */ if ((mpd->b_state & (1 << BH_Mapped)) && - !(mpd->b_state & (1 << BH_Delay))) + !(mpd->b_state & (1 << BH_Delay)) && + !(mpd->b_state & (1 << BH_Unwritten))) return 0; /* * We need to make sure the BH_Delay flag is passed down to @@ -2205,6 +2214,17 @@ flush_it: return; } +static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) +{ + /* + * unmapped buffer is possible for holes. + * delay buffer is possible with delayed allocation. + * We also need to consider unwritten buffer as unmapped. + */ + return (!buffer_mapped(bh) || buffer_delay(bh) || + buffer_unwritten(bh)) && buffer_dirty(bh); +} + /* * __mpage_da_writepage - finds extent of pages and blocks * @@ -2289,8 +2309,7 @@ static int __mpage_da_writepage(struct page *page, * Otherwise we won't make progress * with the page in ext4_da_writepage */ - if (buffer_dirty(bh) && - (!buffer_mapped(bh) || buffer_delay(bh))) { + if (ext4_bh_unmapped_or_delay(NULL, bh)) { mpage_add_bh_to_extent(mpd, logical, bh->b_size, bh->b_state); @@ -2318,6 +2337,14 @@ static int __mpage_da_writepage(struct page *page, /* * this is a special callback for ->write_begin() only * it's intention is to return mapped block or reserve space + * + * For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set. + * We also have b_blocknr = -1 and b_bdev initialized properly + * + * For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set. + * We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev + * initialized properly. + * */ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) @@ -2353,28 +2380,23 @@ 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)) + if (buffer_unwritten(bh_result)) { + /* A delayed write to unwritten bh should + * be marked new and mapped. Mapped ensures + * that we don't do get_block multiple times + * when we write to the same offset and new + * ensures that we do proper zero out for + * partial write. + */ set_buffer_new(bh_result); + set_buffer_mapped(bh_result); + } ret = 0; } return ret; } -static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) -{ - /* - * unmapped buffer is possible for holes. - * delay buffer is possible with delayed allocation - */ - return ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh)); -} - static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { @@ -2828,7 +2850,7 @@ static int ext4_da_should_update_i_disksize(struct page *page, for (i = 0; i < idx; i++) bh = bh->b_this_page; - if (!buffer_mapped(bh) || (buffer_delay(bh))) + if (!buffer_mapped(bh) || (buffer_delay(bh)) || buffer_unwritten(bh)) return 0; return 1; } -- cgit v1.2.3-70-g09d2 From c9877b205f6ce7943bb95281342f4001cc1c00ec Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Fri, 1 May 2009 23:32:06 -0400 Subject: ext4: fix for fiemap last-block test Carl Henrik Lunde reported and debugged this; the test for the last allocated block was comparing bytes to blocks in this test: if (logical + length - 1 == EXT_MAX_BLOCK || ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK) flags |= FIEMAP_EXTENT_LAST; so any extent which ended right at 4G was stopping the extent walk. Just replacing these values with the extent block & length should fix it. Also give blksize_bits a saner type, and reverse the order of the tests to make the more likely case tested first. Signed-off-by: Eric Sandeen Reported-by: Carl Henrik Lunde Tested-by: Carl Henrik Lunde Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index ea5c47608ce..5f7295287de 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3196,7 +3196,7 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path, void *data) { struct fiemap_extent_info *fieinfo = data; - unsigned long blksize_bits = inode->i_sb->s_blocksize_bits; + unsigned char blksize_bits = inode->i_sb->s_blocksize_bits; __u64 logical; __u64 physical; __u64 length; @@ -3243,8 +3243,8 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path, * * XXX this might miss a single-block extent at EXT_MAX_BLOCK */ - if (logical + length - 1 == EXT_MAX_BLOCK || - ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK) + if (ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK || + newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) flags |= FIEMAP_EXTENT_LAST; error = fiemap_fill_next_extent(fieinfo, logical, physical, -- cgit v1.2.3-70-g09d2 From eefd7f03b86b8a319890e7fac5a6fcc7f8694b76 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 2 May 2009 19:05:37 -0400 Subject: ext4: fix the length returned by fiemap for an unallocated extent If the file's blocks have not yet been allocated because of delayed allocation, the length of the extent returned by fiemap is incorrect. This commit fixes this bug. Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 5f7295287de..4fec6b74638 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3244,8 +3244,15 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path, * XXX this might miss a single-block extent at EXT_MAX_BLOCK */ if (ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK || - newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) + newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) { + loff_t size = i_size_read(inode); + loff_t bs = EXT4_BLOCK_SIZE(inode->i_sb); + flags |= FIEMAP_EXTENT_LAST; + if ((flags & FIEMAP_EXTENT_DELALLOC) && + logical+length > size) + length = (size - logical + bs - 1) & ~(bs-1); + } error = fiemap_fill_next_extent(fieinfo, logical, physical, length, flags); -- cgit v1.2.3-70-g09d2 From 12b7ac176831df1aa58a787e67c3e5d698b30163 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 14 May 2009 00:57:44 -0400 Subject: ext4: Rename ext4_get_blocks_wrap() to be ext4_get_blocks() Another function rename for clarity's sake. The _wrap prefix simply confuses people, and didn't add much people trying to follow the code paths. Signed-off-by: "Theodore Ts'o" --- fs/ext4/dir.c | 3 +-- fs/ext4/ext4.h | 8 ++++---- fs/ext4/extents.c | 6 +++--- fs/ext4/inode.c | 35 +++++++++++++++++------------------ 4 files changed, 25 insertions(+), 27 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index b64789929a6..052d6378f99 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -131,8 +131,7 @@ static int ext4_readdir(struct file *filp, struct buffer_head *bh = NULL; map_bh.b_state = 0; - err = ext4_get_blocks_wrap(NULL, inode, blk, 1, &map_bh, - 0, 0, 0); + err = ext4_get_blocks(NULL, inode, blk, 1, &map_bh, 0, 0, 0); if (err > 0) { pgoff_t index = map_bh.b_blocknr >> (PAGE_CACHE_SHIFT - inode->i_blkbits); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 89190ae671f..5dc8368e46b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1617,10 +1617,10 @@ extern void ext4_ext_init(struct super_block *); extern void ext4_ext_release(struct super_block *); extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len); -extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, - sector_t block, unsigned int max_blocks, - struct buffer_head *bh, int create, - int extend_disksize, int flag); +extern int ext4_get_blocks(handle_t *handle, struct inode *inode, + sector_t block, unsigned int max_blocks, + struct buffer_head *bh, int create, + int extend_disksize, int flag); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 4fec6b74638..7e7d02dd273 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3151,9 +3151,9 @@ retry: break; } map_bh.b_state = 0; - ret = ext4_get_blocks_wrap(handle, inode, block, - max_blocks, &map_bh, - EXT4_CREATE_UNINITIALIZED_EXT, 0, 0); + ret = ext4_get_blocks(handle, inode, block, + max_blocks, &map_bh, + EXT4_CREATE_UNINITIALIZED_EXT, 0, 0); if (ret <= 0) { #ifdef EXT4FS_DEBUG WARN_ON(ret <= 0); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f758e8021d1..a9a9b9b77e8 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1121,7 +1121,7 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) } /* - * The ext4_get_blocks_wrap() function try to look up the requested blocks, + * The ext4_get_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. * * Otherwise it takes the write lock of the i_data_sem and allocate blocks @@ -1142,9 +1142,9 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) * * It returns the error in case of allocation failure. */ -int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, - unsigned int max_blocks, struct buffer_head *bh, - int create, int extend_disksize, int flag) +int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, + unsigned int max_blocks, struct buffer_head *bh, + int create, int extend_disksize, int flag) { int retval; @@ -1268,8 +1268,8 @@ int ext4_get_block(struct inode *inode, sector_t iblock, started = 1; } - ret = ext4_get_blocks_wrap(handle, inode, iblock, - max_blocks, bh_result, create, 0, 0); + ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result, + create, 0, 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; @@ -1294,10 +1294,9 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, dummy.b_state = 0; dummy.b_blocknr = -1000; buffer_trace_init(&dummy.b_history); - err = ext4_get_blocks_wrap(handle, inode, block, 1, - &dummy, create, 1, 0); + err = ext4_get_blocks(handle, inode, block, 1, &dummy, create, 1, 0); /* - * ext4_get_blocks_wrap() returns number of blocks + * ext4_get_blocks() returns number of blocks * mapped. 0 in case of a HOLE. */ if (err > 0) { @@ -2009,8 +2008,8 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, handle = ext4_journal_current_handle(); BUG_ON(!handle); - ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks, - bh_result, 1, 0, EXT4_DELALLOC_RSVED); + ret = ext4_get_blocks(handle, inode, iblock, max_blocks, + bh_result, 1, 0, EXT4_DELALLOC_RSVED); if (ret <= 0) return ret; @@ -2067,11 +2066,11 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) /* * We need to make sure the BH_Delay flag is passed down to * ext4_da_get_block_write(), since it calls - * ext4_get_blocks_wrap() with the EXT4_DELALLOC_RSVED flag. - * This flag causes ext4_get_blocks_wrap() to call + * ext4_get_blocks() with the EXT4_DELALLOC_RSVED flag. + * This flag causes ext4_get_blocks() to call * ext4_da_update_reserve_space() if the passed buffer head * has the BH_Delay flag set. In the future, once we clean up - * the interfaces to ext4_get_blocks_wrap(), we should pass in + * the interfaces to ext4_get_blocks(), we should pass in * a separate flag which requests that the delayed allocation * statistics should be updated, instead of depending on the * state information getting passed down via the map_bh's @@ -2363,7 +2362,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * preallocated blocks are unmapped but should treated * the same as allocated blocks. */ - ret = ext4_get_blocks_wrap(NULL, inode, iblock, 1, bh_result, 0, 0, 0); + ret = ext4_get_blocks(NULL, inode, iblock, 1, bh_result, 0, 0, 0); if ((ret == 0) && !buffer_delay(bh_result)) { /* the block isn't (pre)allocated yet, let's reserve space */ /* @@ -2407,8 +2406,8 @@ static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock, * we don't want to do block allocation in writepage * so call get_block_wrap with create = 0 */ - ret = ext4_get_blocks_wrap(NULL, inode, iblock, max_blocks, - bh_result, 0, 0, 0); + ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, + bh_result, 0, 0, 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; @@ -5034,7 +5033,7 @@ int ext4_writepage_trans_blocks(struct inode *inode) * Calculate the journal credits for a chunk of data modification. * * This is called from DIO, fallocate or whoever calling - * ext4_get_blocks_wrap() to map/allocate a chunk of contigous disk blocks. + * ext4_get_blocks() to map/allocate a chunk of contigous disk blocks. * * journal buffers for data blocks are not included here, as DIO * and fallocate do no need to journal data buffers. -- cgit v1.2.3-70-g09d2 From c21770573319922e3f3fcb331cfaa290c49f1c81 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 14 May 2009 00:58:52 -0400 Subject: ext4: Define a new set of flags for ext4_get_blocks() The functions ext4_get_blocks(), ext4_ext_get_blocks(), and ext4_ind_get_blocks() used an ad-hoc set of integer variables used as boolean flags passed in as arguments. Use a single flags parameter and a setandard set of bitfield flags instead. This saves space on the call stack, and it also makes the code a bit more understandable. Signed-off-by: "Theodore Ts'o" --- fs/ext4/dir.c | 2 +- fs/ext4/ext4.h | 22 ++++++++++++++------- fs/ext4/extents.c | 22 ++++++++++----------- fs/ext4/inode.c | 57 +++++++++++++++++++++++++++++-------------------------- 4 files changed, 57 insertions(+), 46 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 052d6378f99..9dc93168e26 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -131,7 +131,7 @@ static int ext4_readdir(struct file *filp, struct buffer_head *bh = NULL; map_bh.b_state = 0; - err = ext4_get_blocks(NULL, inode, blk, 1, &map_bh, 0, 0, 0); + err = ext4_get_blocks(NULL, inode, blk, 1, &map_bh, 0); if (err > 0) { pgoff_t index = map_bh.b_blocknr >> (PAGE_CACHE_SHIFT - inode->i_blkbits); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 5dc8368e46b..17feb4ac633 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -314,10 +314,20 @@ struct ext4_new_group_data { }; /* - * Following is used by preallocation code to tell get_blocks() that we - * want uninitialzed extents. + * Flags used by ext4_get_blocks() */ -#define EXT4_CREATE_UNINITIALIZED_EXT 2 + /* Allocate any needed blocks and/or convert an unitialized + extent to be an initialized ext4 */ +#define EXT4_GET_BLOCKS_CREATE 1 + /* Request the creation of an unitialized extent */ +#define EXT4_GET_BLOCKS_UNINIT_EXT 2 +#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\ + EXT4_GET_BLOCKS_CREATE) + /* Update the ext4_inode_info i_disksize field */ +#define EXT4_GET_BLOCKS_EXTEND_DISKSIZE 4 + /* Caller is from the delayed allocation writeout path, + so the filesystem blocks have already been accounted for */ +#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 8 /* * ioctl commands @@ -1610,8 +1620,7 @@ extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk); extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, ext4_lblk_t iblock, unsigned int max_blocks, - struct buffer_head *bh_result, - int create, int extend_disksize); + struct buffer_head *bh_result, int flags); extern void ext4_ext_truncate(struct inode *); extern void ext4_ext_init(struct super_block *); extern void ext4_ext_release(struct super_block *); @@ -1619,8 +1628,7 @@ extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len); extern int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, unsigned int max_blocks, - struct buffer_head *bh, int create, - int extend_disksize, int flag); + struct buffer_head *bh, int flags); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 7e7d02dd273..27c383c7b43 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2784,7 +2784,7 @@ fix_extent_len: int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, ext4_lblk_t iblock, unsigned int max_blocks, struct buffer_head *bh_result, - int create, int extend_disksize) + int flags) { struct ext4_ext_path *path = NULL; struct ext4_extent_header *eh; @@ -2803,7 +2803,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, cache_type = ext4_ext_in_cache(inode, iblock, &newex); if (cache_type) { if (cache_type == EXT4_EXT_CACHE_GAP) { - if (!create) { + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { /* * block isn't allocated yet and * user doesn't want to allocate it @@ -2869,9 +2869,9 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, EXT4_EXT_CACHE_EXTENT); goto out; } - if (create == EXT4_CREATE_UNINITIALIZED_EXT) + if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) goto out; - if (!create) { + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { if (allocated > max_blocks) allocated = max_blocks; /* @@ -2903,7 +2903,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, * requested block isn't allocated yet; * we couldn't try to create block if create flag is zero */ - if (!create) { + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { /* * put just found gap into cache to speed up * subsequent requests @@ -2932,10 +2932,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, * EXT_UNINIT_MAX_LEN. */ if (max_blocks > EXT_INIT_MAX_LEN && - create != EXT4_CREATE_UNINITIALIZED_EXT) + !(flags & EXT4_GET_BLOCKS_UNINIT_EXT)) max_blocks = EXT_INIT_MAX_LEN; else if (max_blocks > EXT_UNINIT_MAX_LEN && - create == EXT4_CREATE_UNINITIALIZED_EXT) + (flags & EXT4_GET_BLOCKS_UNINIT_EXT)) max_blocks = EXT_UNINIT_MAX_LEN; /* Check if we can really insert (iblock)::(iblock+max_blocks) extent */ @@ -2966,7 +2966,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, /* try to insert new extent into found leaf and return */ ext4_ext_store_pblock(&newex, newblock); newex.ee_len = cpu_to_le16(ar.len); - if (create == EXT4_CREATE_UNINITIALIZED_EXT) /* Mark uninitialized */ + if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) /* Mark uninitialized */ ext4_ext_mark_uninitialized(&newex); err = ext4_ext_insert_extent(handle, inode, path, &newex); if (err) { @@ -2983,7 +2983,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, newblock = ext_pblock(&newex); allocated = ext4_ext_get_actual_len(&newex); outnew: - if (extend_disksize) { + if (flags & EXT4_GET_BLOCKS_EXTEND_DISKSIZE) { disksize = ((loff_t) iblock + ar.len) << inode->i_blkbits; if (disksize > i_size_read(inode)) disksize = i_size_read(inode); @@ -2994,7 +2994,7 @@ outnew: set_buffer_new(bh_result); /* Cache only when it is _not_ an uninitialized extent */ - if (create != EXT4_CREATE_UNINITIALIZED_EXT) + if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) ext4_ext_put_in_cache(inode, iblock, allocated, newblock, EXT4_EXT_CACHE_EXTENT); out: @@ -3153,7 +3153,7 @@ retry: map_bh.b_state = 0; ret = ext4_get_blocks(handle, inode, block, max_blocks, &map_bh, - EXT4_CREATE_UNINITIALIZED_EXT, 0, 0); + EXT4_GET_BLOCKS_CREATE_UNINIT_EXT); if (ret <= 0) { #ifdef EXT4FS_DEBUG WARN_ON(ret <= 0); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a9a9b9b77e8..8b7564dfacd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -917,7 +917,7 @@ err_out: static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, ext4_lblk_t iblock, unsigned int maxblocks, struct buffer_head *bh_result, - int create, int extend_disksize) + int flags) { int err = -EIO; ext4_lblk_t offsets[4]; @@ -934,7 +934,7 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)); - J_ASSERT(handle != NULL || create == 0); + J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0); depth = ext4_block_to_path(inode, iblock, offsets, &blocks_to_boundary); @@ -963,7 +963,7 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, } /* Next simple case - plain lookup or failed read of indirect block */ - if (!create || err == -EIO) + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO) goto cleanup; /* @@ -1002,7 +1002,7 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, * protect it if you're about to implement concurrent * ext4_get_block() -bzzz */ - if (!err && extend_disksize) { + if (!err && (flags & EXT4_GET_BLOCKS_EXTEND_DISKSIZE)) { disksize = ((loff_t) iblock + count) << inode->i_blkbits; if (disksize > i_size_read(inode)) disksize = i_size_read(inode); @@ -1144,7 +1144,7 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) */ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, unsigned int max_blocks, struct buffer_head *bh, - int create, int extend_disksize, int flag) + int flags) { int retval; @@ -1158,15 +1158,15 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, down_read((&EXT4_I(inode)->i_data_sem)); if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { retval = ext4_ext_get_blocks(handle, inode, block, max_blocks, - bh, 0, 0); + bh, 0); } else { retval = ext4_ind_get_blocks(handle, inode, block, max_blocks, - bh, 0, 0); + bh, 0); } up_read((&EXT4_I(inode)->i_data_sem)); /* If it is only a block(s) look up */ - if (!create) + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) return retval; /* @@ -1205,7 +1205,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, * let the underlying get_block() function know to * avoid double accounting */ - if (flag) + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) EXT4_I(inode)->i_delalloc_reserved_flag = 1; /* * We need to check for EXT4 here because migrate @@ -1213,10 +1213,10 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, */ if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { retval = ext4_ext_get_blocks(handle, inode, block, max_blocks, - bh, create, extend_disksize); + bh, flags); } else { retval = ext4_ind_get_blocks(handle, inode, block, - max_blocks, bh, create, extend_disksize); + max_blocks, bh, flags); if (retval > 0 && buffer_new(bh)) { /* @@ -1229,7 +1229,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, } } - if (flag) { + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { EXT4_I(inode)->i_delalloc_reserved_flag = 0; /* * Update reserved blocks/metadata blocks @@ -1269,7 +1269,7 @@ int ext4_get_block(struct inode *inode, sector_t iblock, } ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result, - create, 0, 0); + create ? EXT4_GET_BLOCKS_CREATE : 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; @@ -1288,16 +1288,19 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, { struct buffer_head dummy; int fatal = 0, err; + int flags = EXT4_GET_BLOCKS_EXTEND_DISKSIZE; J_ASSERT(handle != NULL || create == 0); dummy.b_state = 0; dummy.b_blocknr = -1000; buffer_trace_init(&dummy.b_history); - err = ext4_get_blocks(handle, inode, block, 1, &dummy, create, 1, 0); + if (create) + flags |= EXT4_GET_BLOCKS_CREATE; + err = ext4_get_blocks(handle, inode, block, 1, &dummy, flags); /* - * ext4_get_blocks() returns number of blocks - * mapped. 0 in case of a HOLE. + * ext4_get_blocks() returns number of blocks mapped. 0 in + * case of a HOLE. */ if (err > 0) { if (err > 1) @@ -1997,7 +2000,6 @@ static void ext4_print_free_blocks(struct inode *inode) return; } -#define EXT4_DELALLOC_RSVED 1 static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result) { @@ -2009,7 +2011,8 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, handle = ext4_journal_current_handle(); BUG_ON(!handle); ret = ext4_get_blocks(handle, inode, iblock, max_blocks, - bh_result, 1, 0, EXT4_DELALLOC_RSVED); + bh_result, EXT4_GET_BLOCKS_CREATE| + EXT4_GET_BLOCKS_DELALLOC_RESERVE); if (ret <= 0) return ret; @@ -2065,16 +2068,17 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) return 0; /* * We need to make sure the BH_Delay flag is passed down to - * ext4_da_get_block_write(), since it calls - * ext4_get_blocks() with the EXT4_DELALLOC_RSVED flag. - * This flag causes ext4_get_blocks() to call + * ext4_da_get_block_write(), since it calls ext4_get_blocks() + * with the EXT4_GET_BLOCKS_DELALLOC_RESERVE flag. This flag + * causes ext4_get_blocks() to call * ext4_da_update_reserve_space() if the passed buffer head * has the BH_Delay flag set. In the future, once we clean up - * the interfaces to ext4_get_blocks(), we should pass in - * a separate flag which requests that the delayed allocation + * the interfaces to ext4_get_blocks(), we should pass in a + * separate flag which requests that the delayed allocation * statistics should be updated, instead of depending on the * state information getting passed down via the map_bh's - * state bitmasks plus the magic EXT4_DELALLOC_RSVED flag. + * state bitmasks plus the magic + * EXT4_GET_BLOCKS_DELALLOC_RESERVE flag. */ new.b_state = mpd->b_state & (1 << BH_Delay); new.b_blocknr = 0; @@ -2362,7 +2366,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * preallocated blocks are unmapped but should treated * the same as allocated blocks. */ - ret = ext4_get_blocks(NULL, inode, iblock, 1, bh_result, 0, 0, 0); + ret = ext4_get_blocks(NULL, inode, iblock, 1, bh_result, 0); if ((ret == 0) && !buffer_delay(bh_result)) { /* the block isn't (pre)allocated yet, let's reserve space */ /* @@ -2406,8 +2410,7 @@ static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock, * we don't want to do block allocation in writepage * so call get_block_wrap with create = 0 */ - ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, - bh_result, 0, 0, 0); + ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, bh_result, 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; -- cgit v1.2.3-70-g09d2 From 6fd058f7791087648c683eb8572edf3be3c4c23c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 17 May 2009 15:38:01 -0400 Subject: ext4: Add a comprehensive block validity check to ext4_get_blocks() To catch filesystem bugs or corruption which could lead to the filesystem getting severly damaged, this patch adds a facility for tracking all of the filesystem metadata blocks by contiguous regions in a red-black tree. This allows quick searching of the tree to locate extents which might overlap with filesystem metadata blocks. This facility is also used by the multi-block allocator to assure that it is not allocating blocks out of the system zone, as well as by the routines used when reading indirect blocks and extents information from disk to make sure their contents are valid. Signed-off-by: "Theodore Ts'o" --- fs/ext4/Makefile | 4 +- fs/ext4/block_validity.c | 244 +++++++++++++++++++++++++++++++++++++++++++++++ fs/ext4/ext4.h | 11 +++ fs/ext4/extents.c | 22 +---- fs/ext4/inode.c | 47 +++++++-- fs/ext4/mballoc.c | 11 +-- fs/ext4/super.c | 32 ++++++- 7 files changed, 332 insertions(+), 39 deletions(-) create mode 100644 fs/ext4/block_validity.c (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index a8ff003a00f..8a34710ecf4 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -5,8 +5,8 @@ obj-$(CONFIG_EXT4_FS) += ext4.o ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \ - ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ - ext4_jbd2.o migrate.o mballoc.o + ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ + ext4_jbd2.o migrate.o mballoc.o block_validity.o ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c new file mode 100644 index 00000000000..50784ef0756 --- /dev/null +++ b/fs/ext4/block_validity.c @@ -0,0 +1,244 @@ +/* + * linux/fs/ext4/block_validity.c + * + * Copyright (C) 2009 + * Theodore Ts'o (tytso@mit.edu) + * + * Track which blocks in the filesystem are metadata blocks that + * should never be used as data blocks by files or directories. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "ext4.h" + +struct ext4_system_zone { + struct rb_node node; + ext4_fsblk_t start_blk; + unsigned int count; +}; + +static struct kmem_cache *ext4_system_zone_cachep; + +int __init init_ext4_system_zone(void) +{ + ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone, + SLAB_RECLAIM_ACCOUNT); + if (ext4_system_zone_cachep == NULL) + return -ENOMEM; + return 0; +} + +void exit_ext4_system_zone(void) +{ + kmem_cache_destroy(ext4_system_zone_cachep); +} + +static inline int can_merge(struct ext4_system_zone *entry1, + struct ext4_system_zone *entry2) +{ + if ((entry1->start_blk + entry1->count) == entry2->start_blk) + return 1; + return 0; +} + +/* + * Mark a range of blocks as belonging to the "system zone" --- that + * is, filesystem metadata blocks which should never be used by + * inodes. + */ +static int add_system_zone(struct ext4_sb_info *sbi, + ext4_fsblk_t start_blk, + unsigned int count) +{ + struct ext4_system_zone *new_entry = NULL, *entry; + struct rb_node **n = &sbi->system_blks.rb_node, *node; + struct rb_node *parent = NULL, *new_node = NULL; + + while (*n) { + parent = *n; + entry = rb_entry(parent, struct ext4_system_zone, node); + if (start_blk < entry->start_blk) + n = &(*n)->rb_left; + else if (start_blk >= (entry->start_blk + entry->count)) + n = &(*n)->rb_right; + else { + if (start_blk + count > (entry->start_blk + + entry->count)) + entry->count = (start_blk + count - + entry->start_blk); + new_node = *n; + new_entry = rb_entry(new_node, struct ext4_system_zone, + node); + break; + } + } + + if (!new_entry) { + new_entry = kmem_cache_alloc(ext4_system_zone_cachep, + GFP_KERNEL); + if (!new_entry) + return -ENOMEM; + new_entry->start_blk = start_blk; + new_entry->count = count; + new_node = &new_entry->node; + + rb_link_node(new_node, parent, n); + rb_insert_color(new_node, &sbi->system_blks); + } + + /* Can we merge to the left? */ + node = rb_prev(new_node); + if (node) { + entry = rb_entry(node, struct ext4_system_zone, node); + if (can_merge(entry, new_entry)) { + new_entry->start_blk = entry->start_blk; + new_entry->count += entry->count; + rb_erase(node, &sbi->system_blks); + kmem_cache_free(ext4_system_zone_cachep, entry); + } + } + + /* Can we merge to the right? */ + node = rb_next(new_node); + if (node) { + entry = rb_entry(node, struct ext4_system_zone, node); + if (can_merge(new_entry, entry)) { + new_entry->count += entry->count; + rb_erase(node, &sbi->system_blks); + kmem_cache_free(ext4_system_zone_cachep, entry); + } + } + return 0; +} + +static void debug_print_tree(struct ext4_sb_info *sbi) +{ + struct rb_node *node; + struct ext4_system_zone *entry; + int first = 1; + + printk(KERN_INFO "System zones: "); + node = rb_first(&sbi->system_blks); + while (node) { + entry = rb_entry(node, struct ext4_system_zone, node); + printk("%s%llu-%llu", first ? "" : ", ", + entry->start_blk, entry->start_blk + entry->count - 1); + first = 0; + node = rb_next(node); + } + printk("\n"); +} + +int ext4_setup_system_zone(struct super_block *sb) +{ + ext4_group_t ngroups = ext4_get_groups_count(sb); + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_desc *gdp; + ext4_group_t i; + int flex_size = ext4_flex_bg_size(sbi); + int ret; + + if (!test_opt(sb, BLOCK_VALIDITY)) { + if (EXT4_SB(sb)->system_blks.rb_node) + ext4_release_system_zone(sb); + return 0; + } + if (EXT4_SB(sb)->system_blks.rb_node) + return 0; + + for (i=0; i < ngroups; i++) { + if (ext4_bg_has_super(sb, i) && + ((i < 5) || ((i % flex_size) == 0))) + add_system_zone(sbi, ext4_group_first_block_no(sb, i), + sbi->s_gdb_count + 1); + gdp = ext4_get_group_desc(sb, i, NULL); + ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1); + if (ret) + return ret; + ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1); + if (ret) + return ret; + ret = add_system_zone(sbi, ext4_inode_table(sb, gdp), + sbi->s_itb_per_group); + if (ret) + return ret; + } + + if (test_opt(sb, DEBUG)) + debug_print_tree(EXT4_SB(sb)); + return 0; +} + +/* Called when the filesystem is unmounted */ +void ext4_release_system_zone(struct super_block *sb) +{ + struct rb_node *n = EXT4_SB(sb)->system_blks.rb_node; + struct rb_node *parent; + struct ext4_system_zone *entry; + + while (n) { + /* Do the node's children first */ + if (n->rb_left) { + n = n->rb_left; + continue; + } + if (n->rb_right) { + n = n->rb_right; + continue; + } + /* + * The node has no children; free it, and then zero + * out parent's link to it. Finally go to the + * beginning of the loop and try to free the parent + * node. + */ + parent = rb_parent(n); + entry = rb_entry(n, struct ext4_system_zone, node); + kmem_cache_free(ext4_system_zone_cachep, entry); + if (!parent) + EXT4_SB(sb)->system_blks.rb_node = NULL; + else if (parent->rb_left == n) + parent->rb_left = NULL; + else if (parent->rb_right == n) + parent->rb_right = NULL; + n = parent; + } + EXT4_SB(sb)->system_blks.rb_node = NULL; +} + +/* + * Returns 1 if the passed-in block region (start_blk, + * start_blk+count) is valid; 0 if some part of the block region + * overlaps with filesystem metadata blocks. + */ +int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, + unsigned int count) +{ + struct ext4_system_zone *entry; + struct rb_node *n = sbi->system_blks.rb_node; + + if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || + (start_blk + count > ext4_blocks_count(sbi->s_es))) + return 0; + while (n) { + entry = rb_entry(n, struct ext4_system_zone, node); + if (start_blk + count - 1 < entry->start_blk) + n = n->rb_left; + else if (start_blk >= (entry->start_blk + entry->count)) + n = n->rb_right; + else + return 0; + } + return 1; +} + diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d164f1294e5..4311cc85b53 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -696,6 +696,7 @@ struct ext4_inode_info { #define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */ #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ +#define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */ #ifndef _LINUX_EXT2_FS_H @@ -887,6 +888,7 @@ struct ext4_sb_info { int s_jquota_fmt; /* Format of quota to use */ #endif unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ + struct rb_root system_blks; #ifdef EXTENTS_STATS /* ext4 extents stats */ @@ -1618,6 +1620,15 @@ extern struct dentry *ext4_get_parent(struct dentry *child); extern const struct inode_operations ext4_symlink_inode_operations; extern const struct inode_operations ext4_fast_symlink_inode_operations; +/* block_validity */ +extern void ext4_release_system_zone(struct super_block *sb); +extern int ext4_setup_system_zone(struct super_block *sb); +extern int __init init_ext4_system_zone(void); +extern void exit_ext4_system_zone(void); +extern int ext4_data_block_valid(struct ext4_sb_info *sbi, + ext4_fsblk_t start_blk, + unsigned int count); + /* extents.c */ extern int ext4_ext_tree_init(handle_t *handle, struct inode *); extern int ext4_ext_writepage_trans_blocks(struct inode *, int); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 27c383c7b43..d04b779b780 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -326,32 +326,18 @@ ext4_ext_max_entries(struct inode *inode, int depth) static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) { - ext4_fsblk_t block = ext_pblock(ext), valid_block; + ext4_fsblk_t block = ext_pblock(ext); int len = ext4_ext_get_actual_len(ext); - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; - valid_block = le32_to_cpu(es->s_first_data_block) + - EXT4_SB(inode->i_sb)->s_gdb_count; - if (unlikely(block <= valid_block || - ((block + len) > ext4_blocks_count(es)))) - return 0; - else - return 1; + return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); } static int ext4_valid_extent_idx(struct inode *inode, struct ext4_extent_idx *ext_idx) { - ext4_fsblk_t block = idx_pblock(ext_idx), valid_block; - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; + ext4_fsblk_t block = idx_pblock(ext_idx); - valid_block = le32_to_cpu(es->s_first_data_block) + - EXT4_SB(inode->i_sb)->s_gdb_count; - if (unlikely(block <= valid_block || - (block >= ext4_blocks_count(es)))) - return 0; - else - return 1; + return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1); } static int ext4_valid_extent_entries(struct inode *inode, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d7b7480682b..dadd3f995db 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -372,20 +372,21 @@ static int ext4_block_to_path(struct inode *inode, } static int __ext4_check_blockref(const char *function, struct inode *inode, - __le32 *p, unsigned int max) { - - unsigned int maxblocks = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es); + __le32 *p, unsigned int max) +{ __le32 *bref = p; + unsigned int blk; + while (bref < p+max) { - if (unlikely(le32_to_cpu(*bref) >= maxblocks)) { + blk = le32_to_cpu(*bref++); + if (blk && + unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), + blk, 1))) { ext4_error(inode->i_sb, function, - "block reference %u >= max (%u) " - "in inode #%lu, offset=%d", - le32_to_cpu(*bref), maxblocks, - inode->i_ino, (int)(bref-p)); + "invalid block reference %u " + "in inode #%lu", blk, inode->i_ino); return -EIO; } - bref++; } return 0; } @@ -1125,6 +1126,21 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) ext4_discard_preallocations(inode); } +static int check_block_validity(struct inode *inode, sector_t logical, + sector_t phys, int len) +{ + if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), phys, len)) { + ext4_error(inode->i_sb, "check_block_validity", + "inode #%lu logical block %llu mapped to %llu " + "(size %d)", inode->i_ino, + (unsigned long long) logical, + (unsigned long long) phys, len); + WARN_ON(1); + return -EIO; + } + return 0; +} + /* * The ext4_get_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. @@ -1170,6 +1186,13 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, } up_read((&EXT4_I(inode)->i_data_sem)); + if (retval > 0 && buffer_mapped(bh)) { + int ret = check_block_validity(inode, block, + bh->b_blocknr, retval); + if (ret != 0) + return ret; + } + /* If it is only a block(s) look up */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) return retval; @@ -1245,6 +1268,12 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block, ext4_da_update_reserve_space(inode, retval); up_write((&EXT4_I(inode)->i_data_sem)); + if (retval > 0 && buffer_mapped(bh)) { + int ret = check_block_validity(inode, block, + bh->b_blocknr, retval); + if (ret != 0) + return ret; + } return retval; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 541bd9adffa..ed8482e22c0 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2961,15 +2961,10 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, + le32_to_cpu(es->s_first_data_block); len = ac->ac_b_ex.fe_len; - if (in_range(ext4_block_bitmap(sb, gdp), block, len) || - in_range(ext4_inode_bitmap(sb, gdp), block, len) || - in_range(block, ext4_inode_table(sb, gdp), - EXT4_SB(sb)->s_itb_per_group) || - in_range(block + len - 1, ext4_inode_table(sb, gdp), - EXT4_SB(sb)->s_itb_per_group)) { + if (!ext4_data_block_valid(sbi, block, len)) { ext4_error(sb, __func__, - "Allocating block %llu in system zone of %d group\n", - block, ac->ac_b_ex.fe_group); + "Allocating blocks %llu-%llu which overlap " + "fs metadata\n", block, block+len); /* File system mounted not to panic on error * Fix the bitmap and repeat the block allocation * We leak some of the blocks here. diff --git a/fs/ext4/super.c b/fs/ext4/super.c index dc34ed3d132..600b7ad699b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -568,6 +568,7 @@ static void ext4_put_super(struct super_block *sb) struct ext4_super_block *es = sbi->s_es; int i, err; + ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); ext4_xattr_put_super(sb); @@ -1055,6 +1056,7 @@ enum { Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize, Opt_usrquota, Opt_grpquota, Opt_i_version, Opt_stripe, Opt_delalloc, Opt_nodelalloc, + Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio }; @@ -1114,6 +1116,8 @@ static const match_table_t tokens = { {Opt_resize, "resize"}, {Opt_delalloc, "delalloc"}, {Opt_nodelalloc, "nodelalloc"}, + {Opt_block_validity, "block_validity"}, + {Opt_noblock_validity, "noblock_validity"}, {Opt_inode_readahead_blks, "inode_readahead_blks=%u"}, {Opt_journal_ioprio, "journal_ioprio=%u"}, {Opt_auto_da_alloc, "auto_da_alloc=%u"}, @@ -1508,6 +1512,12 @@ set_qf_format: case Opt_delalloc: set_opt(sbi->s_mount_opt, DELALLOC); break; + case Opt_block_validity: + set_opt(sbi->s_mount_opt, BLOCK_VALIDITY); + break; + case Opt_noblock_validity: + clear_opt(sbi->s_mount_opt, BLOCK_VALIDITY); + break; case Opt_inode_readahead_blks: if (match_int(&args[0], &option)) return 0; @@ -2826,6 +2836,13 @@ no_journal: } else if (test_opt(sb, DELALLOC)) printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n"); + err = ext4_setup_system_zone(sb); + if (err) { + printk(KERN_ERR "EXT4-fs: failed to initialize system " + "zone (%d)\n", err); + goto failed_mount4; + } + ext4_ext_init(sb); err = ext4_mb_init(sb, needs_recovery); if (err) { @@ -2875,6 +2892,7 @@ cantfind_ext4: failed_mount4: printk(KERN_ERR "EXT4-fs (device %s): mount failed\n", sb->s_id); + ext4_release_system_zone(sb); if (sbi->s_journal) { jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; @@ -3515,6 +3533,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) sb->s_flags &= ~MS_RDONLY; } } + ext4_setup_system_zone(sb); if (sbi->s_journal == NULL) ext4_commit_super(sb, 1); @@ -3927,13 +3946,16 @@ static int __init init_ext4_fs(void) { int err; + err = init_ext4_system_zone(); + if (err) + return err; ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj); if (!ext4_kset) - return -ENOMEM; + goto out4; ext4_proc_root = proc_mkdir("fs/ext4", NULL); err = init_ext4_mballoc(); if (err) - return err; + goto out3; err = init_ext4_xattr(); if (err) @@ -3958,6 +3980,11 @@ out1: exit_ext4_xattr(); out2: exit_ext4_mballoc(); +out3: + remove_proc_entry("fs/ext4", NULL); + kset_unregister(ext4_kset); +out4: + exit_ext4_system_zone(); return err; } @@ -3972,6 +3999,7 @@ static void __exit exit_ext4_fs(void) exit_ext4_mballoc(); remove_proc_entry("fs/ext4", NULL); kset_unregister(ext4_kset); + exit_ext4_system_zone(); } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); -- cgit v1.2.3-70-g09d2 From 0568c518937ee3a9b6a94d18bae9c150fe5d6832 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 17 May 2009 23:31:23 -0400 Subject: ext4: down i_data_sem only for read when walking tree for fiemap Not sure why I put this in as down_write originally; all we are doing is walking the tree, nothing will change under us and concurrent reads should be no problem. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index d04b779b780..d4e99e96fdd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3312,10 +3312,10 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, * Walk the extent tree gathering extent information. * ext4_ext_fiemap_cb will push extents back to user. */ - down_write(&EXT4_I(inode)->i_data_sem); + down_read(&EXT4_I(inode)->i_data_sem); error = ext4_ext_walk_space(inode, start_blk, len_blks, ext4_ext_fiemap_cb, fieinfo); - up_write(&EXT4_I(inode)->i_data_sem); + up_read(&EXT4_I(inode)->i_data_sem); } return error; -- cgit v1.2.3-70-g09d2 From 03f5d8bcf094a5e3b501bd2ae1553656efa8d1be Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 9 Jun 2009 00:17:05 -0400 Subject: ext4: Get rid of EXTEND_DISKSIZE flag of ext4_get_blocks_handle() Get rid of EXTEND_DISKSIZE flag of ext4_get_blocks_handle(). This seems to be a relict from some old days and setting disksize in this function does not make much sense. Currently it was set only by ext4_getblk(). Since the parameter has some effect only if create == 1, it is easy to check by grepping through the sources that the three callers which end up calling ext4_getblk() with create == 1 (ext4_append, ext4_quota_write, ext4_mkdir) do the right thing and set disksize themselves. Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 6 ++---- fs/ext4/extents.c | 9 --------- fs/ext4/inode.c | 23 +++-------------------- 3 files changed, 5 insertions(+), 33 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 4311cc85b53..59657ff7b8f 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -323,15 +323,13 @@ struct ext4_new_group_data { #define EXT4_GET_BLOCKS_UNINIT_EXT 0x0002 #define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\ EXT4_GET_BLOCKS_CREATE) - /* Update the ext4_inode_info i_disksize field */ -#define EXT4_GET_BLOCKS_EXTEND_DISKSIZE 0x0004 /* Caller is from the delayed allocation writeout path, so set the magic i_delalloc_reserve_flag after taking the inode allocation semaphore for */ -#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0008 +#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004 /* Call ext4_da_update_reserve_space() after successfully allocating the blocks */ -#define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE 0x0010 +#define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE 0x0008 /* diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index d4e99e96fdd..9c35a7b1f0a 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2779,7 +2779,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, int err = 0, depth, ret, cache_type; unsigned int allocated = 0; struct ext4_allocation_request ar; - loff_t disksize; __clear_bit(BH_New, &bh_result->b_state); ext_debug("blocks %u/%u requested for inode %u\n", @@ -2969,14 +2968,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, newblock = ext_pblock(&newex); allocated = ext4_ext_get_actual_len(&newex); outnew: - if (flags & EXT4_GET_BLOCKS_EXTEND_DISKSIZE) { - disksize = ((loff_t) iblock + ar.len) << inode->i_blkbits; - if (disksize > i_size_read(inode)) - disksize = i_size_read(inode); - if (disksize > EXT4_I(inode)->i_disksize) - EXT4_I(inode)->i_disksize = disksize; - } - set_buffer_new(bh_result); /* Cache only when it is _not_ an uninitialized extent */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 14c00fff371..17ed0d244db 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -933,11 +933,8 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, int indirect_blks; int blocks_to_boundary = 0; int depth; - struct ext4_inode_info *ei = EXT4_I(inode); int count = 0; ext4_fsblk_t first_block = 0; - loff_t disksize; - J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)); J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0); @@ -1003,19 +1000,7 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode, if (!err) err = ext4_splice_branch(handle, inode, iblock, partial, indirect_blks, count); - /* - * i_disksize growing is protected by i_data_sem. Don't forget to - * protect it if you're about to implement concurrent - * ext4_get_block() -bzzz - */ - if (!err && (flags & EXT4_GET_BLOCKS_EXTEND_DISKSIZE)) { - disksize = ((loff_t) iblock + count) << inode->i_blkbits; - if (disksize > i_size_read(inode)) - disksize = i_size_read(inode); - if (disksize > ei->i_disksize) - ei->i_disksize = disksize; - } - if (err) + else goto cleanup; set_buffer_new(bh_result); @@ -1321,7 +1306,7 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, { struct buffer_head dummy; int fatal = 0, err; - int flags = EXT4_GET_BLOCKS_EXTEND_DISKSIZE; + int flags = 0; J_ASSERT(handle != NULL || create == 0); @@ -2153,9 +2138,7 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) } /* - * Update on-disk size along with block allocation we don't - * use EXT4_GET_BLOCKS_EXTEND_DISKSIZE as size may change - * within already allocated block -bzzz + * Update on-disk size along with block allocation. */ disksize = ((loff_t) next + blks) << mpd->inode->i_blkbits; if (disksize > i_size_read(mpd->inode)) -- cgit v1.2.3-70-g09d2 From a41f20716975910d9beb90b7efc61107901492b8 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 10 Jun 2009 14:22:55 -0400 Subject: ext4: Avoid corrupting the uninitialized bit in the extent during truncate The unitialized bit was not properly getting preserved in in an extent which is partially truncated because the it was geting set to the value of the first extent to be removed or truncated as part of the truncate operation, and if there are multiple extents are getting removed or modified as part of the truncate operation, it is only the last extent which will might be partially truncated, and its uninitalized bit is not necessarily the same as the first extent to be truncated. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 9c35a7b1f0a..2593f748c3a 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2083,12 +2083,16 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, ex = EXT_LAST_EXTENT(eh); ex_ee_block = le32_to_cpu(ex->ee_block); - if (ext4_ext_is_uninitialized(ex)) - uninitialized = 1; ex_ee_len = ext4_ext_get_actual_len(ex); while (ex >= EXT_FIRST_EXTENT(eh) && ex_ee_block + ex_ee_len > start) { + + if (ext4_ext_is_uninitialized(ex)) + uninitialized = 1; + else + uninitialized = 0; + ext_debug("remove ext %lu:%u\n", ex_ee_block, ex_ee_len); path[depth].p_ext = ex; -- cgit v1.2.3-70-g09d2 From 748de6736c1e482e111f9d1b5a5d5b1787600cad Mon Sep 17 00:00:00 2001 From: Akira Fujita Date: Wed, 17 Jun 2009 19:24:03 -0400 Subject: ext4: online defrag -- Add EXT4_IOC_MOVE_EXT ioctl The EXT4_IOC_MOVE_EXT exchanges the blocks between orig_fd and donor_fd, and then write the file data of orig_fd to donor_fd. ext4_mext_move_extent() is the main fucntion of ext4 online defrag, and this patch includes all functions related to ext4 online defrag. Signed-off-by: Akira Fujita Signed-off-by: Takashi Sato Signed-off-by: Kazuya Mio Signed-off-by: "Theodore Ts'o" --- fs/ext4/Makefile | 2 +- fs/ext4/ext4.h | 15 + fs/ext4/ext4_extents.h | 4 + fs/ext4/extents.c | 4 +- fs/ext4/ioctl.c | 36 ++ fs/ext4/move_extent.c | 1320 ++++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 1378 insertions(+), 3 deletions(-) create mode 100644 fs/ext4/move_extent.c (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 8a34710ecf4..8867b2a1e5f 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -6,7 +6,7 @@ obj-$(CONFIG_EXT4_FS) += ext4.o ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \ ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ - ext4_jbd2.o migrate.o mballoc.o block_validity.o + ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index cc7d5edc38c..276a26f117e 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -352,6 +352,7 @@ struct ext4_new_group_data { /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */ /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */ #define EXT4_IOC_ALLOC_DA_BLKS _IO('f', 12) +#define EXT4_IOC_MOVE_EXT _IOWR('f', 15, struct move_extent) /* * ioctl commands in 32 bit emulation @@ -447,6 +448,15 @@ struct ext4_inode { __le32 i_version_hi; /* high 32 bits for 64-bit version */ }; +struct move_extent { + __u32 reserved; /* should be zero */ + __u32 donor_fd; /* donor file descriptor */ + __u64 orig_start; /* logical start offset in block for orig */ + __u64 donor_start; /* logical start offset in block for donor */ + __u64 len; /* block length to be moved */ + __u64 moved_len; /* moved block length */ +}; +#define MAX_DEFRAG_SIZE ((1UL<<31) - 1) #define EXT4_EPOCH_BITS 2 #define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1) @@ -1647,6 +1657,11 @@ extern int ext4_get_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, int flags); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); +/* move_extent.c */ +extern int ext4_move_extents(struct file *o_filp, struct file *d_filp, + __u64 start_orig, __u64 start_donor, + __u64 len, __u64 *moved_len); + /* * Add new method to test wether block and inode bitmaps are properly diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index f0c3ec85bd4..20a84105a10 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -221,12 +221,16 @@ static inline int ext4_ext_get_actual_len(struct ext4_extent *ext) } extern int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks); +extern ext4_fsblk_t ext_pblock(struct ext4_extent *ex); extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *); extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t); extern int ext4_extent_tree_init(handle_t *, struct inode *); extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num, struct ext4_ext_path *path); +extern int ext4_can_extents_be_merged(struct inode *inode, + struct ext4_extent *ex1, + struct ext4_extent *ex2); extern int ext4_ext_try_to_merge(struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 2593f748c3a..50322a09bd0 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -49,7 +49,7 @@ * ext_pblock: * combine low and high parts of physical block number into ext4_fsblk_t */ -static ext4_fsblk_t ext_pblock(struct ext4_extent *ex) +ext4_fsblk_t ext_pblock(struct ext4_extent *ex) { ext4_fsblk_t block; @@ -1417,7 +1417,7 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, return err; } -static int +int ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, struct ext4_extent *ex2) { diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 91e75f7a9e7..bb415408fdb 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include "ext4_jbd2.h" #include "ext4.h" @@ -213,6 +214,41 @@ setversion_out: return err; } + + case EXT4_IOC_MOVE_EXT: { + struct move_extent me; + struct file *donor_filp; + int err; + + if (copy_from_user(&me, + (struct move_extent __user *)arg, sizeof(me))) + return -EFAULT; + + donor_filp = fget(me.donor_fd); + if (!donor_filp) + return -EBADF; + + if (!capable(CAP_DAC_OVERRIDE)) { + if ((current->real_cred->fsuid != inode->i_uid) || + !(inode->i_mode & S_IRUSR) || + !(donor_filp->f_dentry->d_inode->i_mode & + S_IRUSR)) { + fput(donor_filp); + return -EACCES; + } + } + + err = ext4_move_extents(filp, donor_filp, me.orig_start, + me.donor_start, me.len, &me.moved_len); + fput(donor_filp); + + if (!err) + if (copy_to_user((struct move_extent *)arg, + &me, sizeof(me))) + return -EFAULT; + return err; + } + case EXT4_IOC_GROUP_ADD: { struct ext4_new_group_data input; struct super_block *sb = inode->i_sb; diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c new file mode 100644 index 00000000000..bbf2dd9404d --- /dev/null +++ b/fs/ext4/move_extent.c @@ -0,0 +1,1320 @@ +/* + * Copyright (c) 2008,2009 NEC Software Tohoku, Ltd. + * Written by Takashi Sato + * Akira Fujita + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include "ext4_jbd2.h" +#include "ext4_extents.h" +#include "ext4.h" + +#define get_ext_path(path, inode, block, ret) \ + do { \ + path = ext4_ext_find_extent(inode, block, path); \ + if (IS_ERR(path)) { \ + ret = PTR_ERR(path); \ + path = NULL; \ + } \ + } while (0) + +/** + * copy_extent_status - Copy the extent's initialization status + * + * @src: an extent for getting initialize status + * @dest: an extent to be set the status + */ +static void +copy_extent_status(struct ext4_extent *src, struct ext4_extent *dest) +{ + if (ext4_ext_is_uninitialized(src)) + ext4_ext_mark_uninitialized(dest); + else + dest->ee_len = cpu_to_le16(ext4_ext_get_actual_len(dest)); +} + +/** + * mext_next_extent - Search for the next extent and set it to "extent" + * + * @inode: inode which is searched + * @path: this will obtain data for the next extent + * @extent: pointer to the next extent we have just gotten + * + * Search the next extent in the array of ext4_ext_path structure (@path) + * and set it to ext4_extent structure (@extent). In addition, the member of + * @path (->p_ext) also points the next extent. Return 0 on success, 1 if + * ext4_ext_path structure refers to the last extent, or a negative error + * value on failure. + */ +static int +mext_next_extent(struct inode *inode, struct ext4_ext_path *path, + struct ext4_extent **extent) +{ + int ppos, leaf_ppos = path->p_depth; + + ppos = leaf_ppos; + if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) { + /* leaf block */ + *extent = ++path[ppos].p_ext; + return 0; + } + + while (--ppos >= 0) { + if (EXT_LAST_INDEX(path[ppos].p_hdr) > + path[ppos].p_idx) { + int cur_ppos = ppos; + + /* index block */ + path[ppos].p_idx++; + path[ppos].p_block = idx_pblock(path[ppos].p_idx); + if (path[ppos+1].p_bh) + brelse(path[ppos+1].p_bh); + path[ppos+1].p_bh = + sb_bread(inode->i_sb, path[ppos].p_block); + if (!path[ppos+1].p_bh) + return -EIO; + path[ppos+1].p_hdr = + ext_block_hdr(path[ppos+1].p_bh); + + /* Halfway index block */ + while (++cur_ppos < leaf_ppos) { + path[cur_ppos].p_idx = + EXT_FIRST_INDEX(path[cur_ppos].p_hdr); + path[cur_ppos].p_block = + idx_pblock(path[cur_ppos].p_idx); + if (path[cur_ppos+1].p_bh) + brelse(path[cur_ppos+1].p_bh); + path[cur_ppos+1].p_bh = sb_bread(inode->i_sb, + path[cur_ppos].p_block); + if (!path[cur_ppos+1].p_bh) + return -EIO; + path[cur_ppos+1].p_hdr = + ext_block_hdr(path[cur_ppos+1].p_bh); + } + + /* leaf block */ + path[leaf_ppos].p_ext = *extent = + EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr); + return 0; + } + } + /* We found the last extent */ + return 1; +} + +/** + * mext_double_down_read - Acquire two inodes' read semaphore + * + * @orig_inode: original inode structure + * @donor_inode: donor inode structure + * Acquire read semaphore of the two inodes (orig and donor) by i_ino order. + */ +static void +mext_double_down_read(struct inode *orig_inode, struct inode *donor_inode) +{ + struct inode *first = orig_inode, *second = donor_inode; + + BUG_ON(orig_inode == NULL || donor_inode == NULL); + + /* + * Use the inode number to provide the stable locking order instead + * of its address, because the C language doesn't guarantee you can + * compare pointers that don't come from the same array. + */ + if (donor_inode->i_ino < orig_inode->i_ino) { + first = donor_inode; + second = orig_inode; + } + + down_read(&EXT4_I(first)->i_data_sem); + down_read(&EXT4_I(second)->i_data_sem); +} + +/** + * mext_double_down_write - Acquire two inodes' write semaphore + * + * @orig_inode: original inode structure + * @donor_inode: donor inode structure + * Acquire write semaphore of the two inodes (orig and donor) by i_ino order. + */ +static void +mext_double_down_write(struct inode *orig_inode, struct inode *donor_inode) +{ + struct inode *first = orig_inode, *second = donor_inode; + + BUG_ON(orig_inode == NULL || donor_inode == NULL); + + /* + * Use the inode number to provide the stable locking order instead + * of its address, because the C language doesn't guarantee you can + * compare pointers that don't come from the same array. + */ + if (donor_inode->i_ino < orig_inode->i_ino) { + first = donor_inode; + second = orig_inode; + } + + down_write(&EXT4_I(first)->i_data_sem); + down_write(&EXT4_I(second)->i_data_sem); +} + +/** + * mext_double_up_read - Release two inodes' read semaphore + * + * @orig_inode: original inode structure to be released its lock first + * @donor_inode: donor inode structure to be released its lock second + * Release read semaphore of two inodes (orig and donor). + */ +static void +mext_double_up_read(struct inode *orig_inode, struct inode *donor_inode) +{ + BUG_ON(orig_inode == NULL || donor_inode == NULL); + + up_read(&EXT4_I(orig_inode)->i_data_sem); + up_read(&EXT4_I(donor_inode)->i_data_sem); +} + +/** + * mext_double_up_write - Release two inodes' write semaphore + * + * @orig_inode: original inode structure to be released its lock first + * @donor_inode: donor inode structure to be released its lock second + * Release write semaphore of two inodes (orig and donor). + */ +static void +mext_double_up_write(struct inode *orig_inode, struct inode *donor_inode) +{ + BUG_ON(orig_inode == NULL || donor_inode == NULL); + + up_write(&EXT4_I(orig_inode)->i_data_sem); + up_write(&EXT4_I(donor_inode)->i_data_sem); +} + +/** + * mext_insert_across_blocks - Insert extents across leaf block + * + * @handle: journal handle + * @orig_inode: original inode + * @o_start: first original extent to be changed + * @o_end: last original extent to be changed + * @start_ext: first new extent to be inserted + * @new_ext: middle of new extent to be inserted + * @end_ext: last new extent to be inserted + * + * Allocate a new leaf block and insert extents into it. Return 0 on success, + * or a negative error value on failure. + */ +static int +mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode, + struct ext4_extent *o_start, struct ext4_extent *o_end, + struct ext4_extent *start_ext, struct ext4_extent *new_ext, + struct ext4_extent *end_ext) +{ + struct ext4_ext_path *orig_path = NULL; + ext4_lblk_t eblock = 0; + int new_flag = 0; + int end_flag = 0; + int err = 0; + + if (start_ext->ee_len && new_ext->ee_len && end_ext->ee_len) { + if (o_start == o_end) { + + /* start_ext new_ext end_ext + * donor |---------|-----------|--------| + * orig |------------------------------| + */ + end_flag = 1; + } else { + + /* start_ext new_ext end_ext + * donor |---------|----------|---------| + * orig |---------------|--------------| + */ + o_end->ee_block = end_ext->ee_block; + o_end->ee_len = end_ext->ee_len; + ext4_ext_store_pblock(o_end, ext_pblock(end_ext)); + } + + o_start->ee_len = start_ext->ee_len; + new_flag = 1; + + } else if (start_ext->ee_len && new_ext->ee_len && + !end_ext->ee_len && o_start == o_end) { + + /* start_ext new_ext + * donor |--------------|---------------| + * orig |------------------------------| + */ + o_start->ee_len = start_ext->ee_len; + new_flag = 1; + + } else if (!start_ext->ee_len && new_ext->ee_len && + end_ext->ee_len && o_start == o_end) { + + /* new_ext end_ext + * donor |--------------|---------------| + * orig |------------------------------| + */ + o_end->ee_block = end_ext->ee_block; + o_end->ee_len = end_ext->ee_len; + ext4_ext_store_pblock(o_end, ext_pblock(end_ext)); + + /* + * Set 0 to the extent block if new_ext was + * the first block. + */ + if (new_ext->ee_block) + eblock = le32_to_cpu(new_ext->ee_block); + + new_flag = 1; + } else { + ext4_debug("ext4 move extent: Unexpected insert case\n"); + return -EIO; + } + + if (new_flag) { + get_ext_path(orig_path, orig_inode, eblock, err); + if (orig_path == NULL) + goto out; + + if (ext4_ext_insert_extent(handle, orig_inode, + orig_path, new_ext)) + goto out; + } + + if (end_flag) { + get_ext_path(orig_path, orig_inode, + le32_to_cpu(end_ext->ee_block) - 1, err); + if (orig_path == NULL) + goto out; + + if (ext4_ext_insert_extent(handle, orig_inode, + orig_path, end_ext)) + goto out; + } +out: + if (orig_path) { + ext4_ext_drop_refs(orig_path); + kfree(orig_path); + } + + return err; + +} + +/** + * mext_insert_inside_block - Insert new extent to the extent block + * + * @o_start: first original extent to be moved + * @o_end: last original extent to be moved + * @start_ext: first new extent to be inserted + * @new_ext: middle of new extent to be inserted + * @end_ext: last new extent to be inserted + * @eh: extent header of target leaf block + * @range_to_move: used to decide how to insert extent + * + * Insert extents into the leaf block. The extent (@o_start) is overwritten + * by inserted extents. + */ +static void +mext_insert_inside_block(struct ext4_extent *o_start, + struct ext4_extent *o_end, + struct ext4_extent *start_ext, + struct ext4_extent *new_ext, + struct ext4_extent *end_ext, + struct ext4_extent_header *eh, + int range_to_move) +{ + int i = 0; + unsigned long len; + + /* Move the existing extents */ + if (range_to_move && o_end < EXT_LAST_EXTENT(eh)) { + len = (unsigned long)(EXT_LAST_EXTENT(eh) + 1) - + (unsigned long)(o_end + 1); + memmove(o_end + 1 + range_to_move, o_end + 1, len); + } + + /* Insert start entry */ + if (start_ext->ee_len) + o_start[i++].ee_len = start_ext->ee_len; + + /* Insert new entry */ + if (new_ext->ee_len) { + o_start[i] = *new_ext; + ext4_ext_store_pblock(&o_start[i++], ext_pblock(new_ext)); + } + + /* Insert end entry */ + if (end_ext->ee_len) + o_start[i] = *end_ext; + + /* Increment the total entries counter on the extent block */ + le16_add_cpu(&eh->eh_entries, range_to_move); +} + +/** + * mext_insert_extents - Insert new extent + * + * @handle: journal handle + * @orig_inode: original inode + * @orig_path: path indicates first extent to be changed + * @o_start: first original extent to be changed + * @o_end: last original extent to be changed + * @start_ext: first new extent to be inserted + * @new_ext: middle of new extent to be inserted + * @end_ext: last new extent to be inserted + * + * Call the function to insert extents. If we cannot add more extents into + * the leaf block, we call mext_insert_across_blocks() to create a + * new leaf block. Otherwise call mext_insert_inside_block(). Return 0 + * on success, or a negative error value on failure. + */ +static int +mext_insert_extents(handle_t *handle, struct inode *orig_inode, + struct ext4_ext_path *orig_path, + struct ext4_extent *o_start, + struct ext4_extent *o_end, + struct ext4_extent *start_ext, + struct ext4_extent *new_ext, + struct ext4_extent *end_ext) +{ + struct ext4_extent_header *eh; + unsigned long need_slots, slots_range; + int range_to_move, depth, ret; + + /* + * The extents need to be inserted + * start_extent + new_extent + end_extent. + */ + need_slots = (start_ext->ee_len ? 1 : 0) + (end_ext->ee_len ? 1 : 0) + + (new_ext->ee_len ? 1 : 0); + + /* The number of slots between start and end */ + slots_range = ((unsigned long)(o_end + 1) - (unsigned long)o_start + 1) + / sizeof(struct ext4_extent); + + /* Range to move the end of extent */ + range_to_move = need_slots - slots_range; + depth = orig_path->p_depth; + orig_path += depth; + eh = orig_path->p_hdr; + + if (depth) { + /* Register to journal */ + ret = ext4_journal_get_write_access(handle, orig_path->p_bh); + if (ret) + return ret; + } + + /* Expansion */ + if (range_to_move > 0 && + (range_to_move > le16_to_cpu(eh->eh_max) + - le16_to_cpu(eh->eh_entries))) { + + ret = mext_insert_across_blocks(handle, orig_inode, o_start, + o_end, start_ext, new_ext, end_ext); + if (ret < 0) + return ret; + } else + mext_insert_inside_block(o_start, o_end, start_ext, new_ext, + end_ext, eh, range_to_move); + + if (depth) { + ret = ext4_handle_dirty_metadata(handle, orig_inode, + orig_path->p_bh); + if (ret) + return ret; + } else { + ret = ext4_mark_inode_dirty(handle, orig_inode); + if (ret < 0) + return ret; + } + + return 0; +} + +/** + * mext_leaf_block - Move one leaf extent block into the inode. + * + * @handle: journal handle + * @orig_inode: original inode + * @orig_path: path indicates first extent to be changed + * @dext: donor extent + * @from: start offset on the target file + * + * In order to insert extents into the leaf block, we must divide the extent + * in the leaf block into three extents. The one is located to be inserted + * extents, and the others are located around it. + * + * Therefore, this function creates structures to save extents of the leaf + * block, and inserts extents by calling mext_insert_extents() with + * created extents. Return 0 on success, or a negative error value on failure. + */ +static int +mext_leaf_block(handle_t *handle, struct inode *orig_inode, + struct ext4_ext_path *orig_path, struct ext4_extent *dext, + ext4_lblk_t *from) +{ + struct ext4_extent *oext, *o_start, *o_end, *prev_ext; + struct ext4_extent new_ext, start_ext, end_ext; + ext4_lblk_t new_ext_end; + ext4_fsblk_t new_phys_end; + int oext_alen, new_ext_alen, end_ext_alen; + int depth = ext_depth(orig_inode); + int ret; + + o_start = o_end = oext = orig_path[depth].p_ext; + oext_alen = ext4_ext_get_actual_len(oext); + start_ext.ee_len = end_ext.ee_len = 0; + + new_ext.ee_block = cpu_to_le32(*from); + ext4_ext_store_pblock(&new_ext, ext_pblock(dext)); + new_ext.ee_len = dext->ee_len; + new_ext_alen = ext4_ext_get_actual_len(&new_ext); + new_ext_end = le32_to_cpu(new_ext.ee_block) + new_ext_alen - 1; + new_phys_end = ext_pblock(&new_ext) + new_ext_alen - 1; + + /* + * Case: original extent is first + * oext |--------| + * new_ext |--| + * start_ext |--| + */ + if (le32_to_cpu(oext->ee_block) < le32_to_cpu(new_ext.ee_block) && + le32_to_cpu(new_ext.ee_block) < + le32_to_cpu(oext->ee_block) + oext_alen) { + start_ext.ee_len = cpu_to_le16(le32_to_cpu(new_ext.ee_block) - + le32_to_cpu(oext->ee_block)); + copy_extent_status(oext, &start_ext); + } else if (oext > EXT_FIRST_EXTENT(orig_path[depth].p_hdr)) { + prev_ext = oext - 1; + /* + * We can merge new_ext into previous extent, + * if these are contiguous and same extent type. + */ + if (ext4_can_extents_be_merged(orig_inode, prev_ext, + &new_ext)) { + o_start = prev_ext; + start_ext.ee_len = cpu_to_le16( + ext4_ext_get_actual_len(prev_ext) + + new_ext_alen); + copy_extent_status(prev_ext, &start_ext); + new_ext.ee_len = 0; + } + } + + /* + * Case: new_ext_end must be less than oext + * oext |-----------| + * new_ext |-------| + */ + BUG_ON(le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end); + + /* + * Case: new_ext is smaller than original extent + * oext |---------------| + * new_ext |-----------| + * end_ext |---| + */ + if (le32_to_cpu(oext->ee_block) <= new_ext_end && + new_ext_end < le32_to_cpu(oext->ee_block) + oext_alen - 1) { + end_ext.ee_len = + cpu_to_le16(le32_to_cpu(oext->ee_block) + + oext_alen - 1 - new_ext_end); + copy_extent_status(oext, &end_ext); + end_ext_alen = ext4_ext_get_actual_len(&end_ext); + ext4_ext_store_pblock(&end_ext, + (ext_pblock(o_end) + oext_alen - end_ext_alen)); + end_ext.ee_block = + cpu_to_le32(le32_to_cpu(o_end->ee_block) + + oext_alen - end_ext_alen); + } + + ret = mext_insert_extents(handle, orig_inode, orig_path, o_start, + o_end, &start_ext, &new_ext, &end_ext); + return ret; +} + +/** + * mext_calc_swap_extents - Calculate extents for extent swapping. + * + * @tmp_dext: the extent that will belong to the original inode + * @tmp_oext: the extent that will belong to the donor inode + * @orig_off: block offset of original inode + * @donor_off: block offset of donor inode + * @max_count: the maximun length of extents + */ +static void +mext_calc_swap_extents(struct ext4_extent *tmp_dext, + struct ext4_extent *tmp_oext, + ext4_lblk_t orig_off, ext4_lblk_t donor_off, + ext4_lblk_t max_count) +{ + ext4_lblk_t diff, orig_diff; + struct ext4_extent dext_old, oext_old; + + dext_old = *tmp_dext; + oext_old = *tmp_oext; + + /* When tmp_dext is too large, pick up the target range. */ + diff = donor_off - le32_to_cpu(tmp_dext->ee_block); + + ext4_ext_store_pblock(tmp_dext, ext_pblock(tmp_dext) + diff); + tmp_dext->ee_block = + cpu_to_le32(le32_to_cpu(tmp_dext->ee_block) + diff); + tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_dext->ee_len) - diff); + + if (max_count < ext4_ext_get_actual_len(tmp_dext)) + tmp_dext->ee_len = cpu_to_le16(max_count); + + orig_diff = orig_off - le32_to_cpu(tmp_oext->ee_block); + ext4_ext_store_pblock(tmp_oext, ext_pblock(tmp_oext) + orig_diff); + + /* Adjust extent length if donor extent is larger than orig */ + if (ext4_ext_get_actual_len(tmp_dext) > + ext4_ext_get_actual_len(tmp_oext) - orig_diff) + tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_oext->ee_len) - + orig_diff); + + tmp_oext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(tmp_dext)); + + copy_extent_status(&oext_old, tmp_dext); + copy_extent_status(&dext_old, tmp_oext); +} + +/** + * mext_replace_branches - Replace original extents with new extents + * + * @handle: journal handle + * @orig_inode: original inode + * @donor_inode: donor inode + * @from: block offset of orig_inode + * @count: block count to be replaced + * + * Replace original inode extents and donor inode extents page by page. + * We implement this replacement in the following three steps: + * 1. Save the block information of original and donor inodes into + * dummy extents. + * 2. Change the block information of original inode to point at the + * donor inode blocks. + * 3. Change the block information of donor inode to point at the saved + * original inode blocks in the dummy extents. + * + * Return 0 on success, or a negative error value on failure. + */ +static int +mext_replace_branches(handle_t *handle, struct inode *orig_inode, + struct inode *donor_inode, ext4_lblk_t from, + ext4_lblk_t count) +{ + struct ext4_ext_path *orig_path = NULL; + struct ext4_ext_path *donor_path = NULL; + struct ext4_extent *oext, *dext; + struct ext4_extent tmp_dext, tmp_oext; + ext4_lblk_t orig_off = from, donor_off = from; + int err = 0; + int depth; + int replaced_count = 0; + int dext_alen; + + mext_double_down_write(orig_inode, donor_inode); + + /* Get the original extent for the block "orig_off" */ + get_ext_path(orig_path, orig_inode, orig_off, err); + if (orig_path == NULL) + goto out; + + /* Get the donor extent for the head */ + get_ext_path(donor_path, donor_inode, donor_off, err); + if (donor_path == NULL) + goto out; + depth = ext_depth(orig_inode); + oext = orig_path[depth].p_ext; + tmp_oext = *oext; + + depth = ext_depth(donor_inode); + dext = donor_path[depth].p_ext; + tmp_dext = *dext; + + mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, + donor_off, count); + + /* Loop for the donor extents */ + while (1) { + /* The extent for donor must be found. */ + BUG_ON(!dext || donor_off != le32_to_cpu(tmp_dext.ee_block)); + + /* Set donor extent to orig extent */ + err = mext_leaf_block(handle, orig_inode, + orig_path, &tmp_dext, &orig_off); + if (err < 0) + goto out; + + /* Set orig extent to donor extent */ + err = mext_leaf_block(handle, donor_inode, + donor_path, &tmp_oext, &donor_off); + if (err < 0) + goto out; + + dext_alen = ext4_ext_get_actual_len(&tmp_dext); + replaced_count += dext_alen; + donor_off += dext_alen; + orig_off += dext_alen; + + /* Already moved the expected blocks */ + if (replaced_count >= count) + break; + + if (orig_path) + ext4_ext_drop_refs(orig_path); + get_ext_path(orig_path, orig_inode, orig_off, err); + if (orig_path == NULL) + goto out; + depth = ext_depth(orig_inode); + oext = orig_path[depth].p_ext; + if (le32_to_cpu(oext->ee_block) + + ext4_ext_get_actual_len(oext) <= orig_off) { + err = 0; + goto out; + } + tmp_oext = *oext; + + if (donor_path) + ext4_ext_drop_refs(donor_path); + get_ext_path(donor_path, donor_inode, + donor_off, err); + if (donor_path == NULL) + goto out; + depth = ext_depth(donor_inode); + dext = donor_path[depth].p_ext; + if (le32_to_cpu(dext->ee_block) + + ext4_ext_get_actual_len(dext) <= donor_off) { + err = 0; + goto out; + } + tmp_dext = *dext; + + mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off, + donor_off, + count - replaced_count); + } + +out: + if (orig_path) { + ext4_ext_drop_refs(orig_path); + kfree(orig_path); + } + if (donor_path) { + ext4_ext_drop_refs(donor_path); + kfree(donor_path); + } + + mext_double_up_write(orig_inode, donor_inode); + return err; +} + +/** + * move_extent_per_page - Move extent data per page + * + * @o_filp: file structure of original file + * @donor_inode: donor inode + * @orig_page_offset: page index on original file + * @data_offset_in_page: block index where data swapping starts + * @block_len_in_page: the number of blocks to be swapped + * @uninit: orig extent is uninitialized or not + * + * Save the data in original inode blocks and replace original inode extents + * with donor inode extents by calling mext_replace_branches(). + * Finally, write out the saved data in new original inode blocks. Return 0 + * on success, or a negative error value on failure. + */ +static int +move_extent_par_page(struct file *o_filp, struct inode *donor_inode, + pgoff_t orig_page_offset, int data_offset_in_page, + int block_len_in_page, int uninit) +{ + struct inode *orig_inode = o_filp->f_dentry->d_inode; + struct address_space *mapping = orig_inode->i_mapping; + struct buffer_head *bh; + struct page *page = NULL; + const struct address_space_operations *a_ops = mapping->a_ops; + handle_t *handle; + ext4_lblk_t orig_blk_offset; + long long offs = orig_page_offset << PAGE_CACHE_SHIFT; + unsigned long blocksize = orig_inode->i_sb->s_blocksize; + unsigned int w_flags = 0; + unsigned int tmp_data_len, data_len; + void *fsdata; + int ret, i, jblocks; + int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; + + /* + * It needs twice the amount of ordinary journal buffers because + * inode and donor_inode may change each different metadata blocks. + */ + jblocks = ext4_writepage_trans_blocks(orig_inode) * 2; + handle = ext4_journal_start(orig_inode, jblocks); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + return ret; + } + + if (segment_eq(get_fs(), KERNEL_DS)) + w_flags |= AOP_FLAG_UNINTERRUPTIBLE; + + orig_blk_offset = orig_page_offset * blocks_per_page + + data_offset_in_page; + + /* + * If orig extent is uninitialized one, + * it's not necessary force the page into memory + * and then force it to be written out again. + * Just swap data blocks between orig and donor. + */ + if (uninit) { + ret = mext_replace_branches(handle, orig_inode, + donor_inode, orig_blk_offset, + block_len_in_page); + + /* Clear the inode cache not to refer to the old data */ + ext4_ext_invalidate_cache(orig_inode); + ext4_ext_invalidate_cache(donor_inode); + goto out2; + } + + offs = (long long)orig_blk_offset << orig_inode->i_blkbits; + + /* Calculate data_len */ + if ((orig_blk_offset + block_len_in_page - 1) == + ((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) { + /* Replace the last block */ + tmp_data_len = orig_inode->i_size & (blocksize - 1); + /* + * If data_len equal zero, it shows data_len is multiples of + * blocksize. So we set appropriate value. + */ + if (tmp_data_len == 0) + tmp_data_len = blocksize; + + data_len = tmp_data_len + + ((block_len_in_page - 1) << orig_inode->i_blkbits); + } else { + data_len = block_len_in_page << orig_inode->i_blkbits; + } + + ret = a_ops->write_begin(o_filp, mapping, offs, data_len, w_flags, + &page, &fsdata); + if (unlikely(ret < 0)) + goto out; + + if (!PageUptodate(page)) { + mapping->a_ops->readpage(o_filp, page); + lock_page(page); + } + + /* + * try_to_release_page() doesn't call releasepage in writeback mode. + * We should care about the order of writing to the same file + * by multiple move extent processes. + * It needs to call wait_on_page_writeback() to wait for the + * writeback of the page. + */ + if (PageWriteback(page)) + wait_on_page_writeback(page); + + /* Release old bh and drop refs */ + try_to_release_page(page, 0); + + ret = mext_replace_branches(handle, orig_inode, donor_inode, + orig_blk_offset, block_len_in_page); + if (ret < 0) + goto out; + + /* Clear the inode cache not to refer to the old data */ + ext4_ext_invalidate_cache(orig_inode); + ext4_ext_invalidate_cache(donor_inode); + + if (!page_has_buffers(page)) + create_empty_buffers(page, 1 << orig_inode->i_blkbits, 0); + + bh = page_buffers(page); + for (i = 0; i < data_offset_in_page; i++) + bh = bh->b_this_page; + + for (i = 0; i < block_len_in_page; i++) { + ret = ext4_get_block(orig_inode, + (sector_t)(orig_blk_offset + i), bh, 0); + if (ret < 0) + goto out; + + if (bh->b_this_page != NULL) + bh = bh->b_this_page; + } + + ret = a_ops->write_end(o_filp, mapping, offs, data_len, data_len, + page, fsdata); + page = NULL; + +out: + if (unlikely(page)) { + if (PageLocked(page)) + unlock_page(page); + page_cache_release(page); + } +out2: + ext4_journal_stop(handle); + + return ret < 0 ? ret : 0; +} + +/** + * mext_check_argumants - Check whether move extent can be done + * + * @orig_inode: original inode + * @donor_inode: donor inode + * @orig_start: logical start offset in block for orig + * @donor_start: logical start offset in block for donor + * @len: the number of blocks to be moved + * @moved_len: moved block length + * + * Check the arguments of ext4_move_extents() whether the files can be + * exchanged with each other. + * Return 0 on success, or a negative error value on failure. + */ +static int +mext_check_arguments(struct inode *orig_inode, + struct inode *donor_inode, __u64 orig_start, + __u64 donor_start, __u64 *len, __u64 moved_len) +{ + /* Regular file check */ + if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) { + ext4_debug("ext4 move extent: The argument files should be " + "regular file [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + /* Ext4 move extent does not support swapfile */ + if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) { + ext4_debug("ext4 move extent: The argument files should " + "not be swapfile [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + /* Files should be in the same ext4 FS */ + if (orig_inode->i_sb != donor_inode->i_sb) { + ext4_debug("ext4 move extent: The argument files " + "should be in same FS [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + /* orig and donor should be different file */ + if (orig_inode->i_ino == donor_inode->i_ino) { + ext4_debug("ext4 move extent: The argument files should not " + "be same file [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + /* Ext4 move extent supports only extent based file */ + if (!(EXT4_I(orig_inode)->i_flags & EXT4_EXTENTS_FL)) { + ext4_debug("ext4 move extent: orig file is not extents " + "based file [ino:orig %lu]\n", orig_inode->i_ino); + return -EOPNOTSUPP; + } else if (!(EXT4_I(donor_inode)->i_flags & EXT4_EXTENTS_FL)) { + ext4_debug("ext4 move extent: donor file is not extents " + "based file [ino:donor %lu]\n", donor_inode->i_ino); + return -EOPNOTSUPP; + } + + if ((!orig_inode->i_size) || (!donor_inode->i_size)) { + ext4_debug("ext4 move extent: File size is 0 byte\n"); + return -EINVAL; + } + + /* Start offset should be same */ + if (orig_start != donor_start) { + ext4_debug("ext4 move extent: orig and donor's start " + "offset are not same [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + if (moved_len) { + ext4_debug("ext4 move extent: moved_len should be 0 " + "[ino:orig %lu, donor %lu]\n", orig_inode->i_ino, + donor_inode->i_ino); + return -EINVAL; + } + + if ((orig_start > MAX_DEFRAG_SIZE) || + (donor_start > MAX_DEFRAG_SIZE) || + (*len > MAX_DEFRAG_SIZE) || + (orig_start + *len > MAX_DEFRAG_SIZE)) { + ext4_debug("ext4 move extent: Can't handle over [%lu] blocks " + "[ino:orig %lu, donor %lu]\n", MAX_DEFRAG_SIZE, + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + if (orig_inode->i_size > donor_inode->i_size) { + if (orig_start >= donor_inode->i_size) { + ext4_debug("ext4 move extent: orig start offset " + "[%llu] should be less than donor file size " + "[%lld] [ino:orig %lu, donor_inode %lu]\n", + orig_start, donor_inode->i_size, + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + if (orig_start + *len > donor_inode->i_size) { + ext4_debug("ext4 move extent: End offset [%llu] should " + "be less than donor file size [%lld]." + "So adjust length from %llu to %lld " + "[ino:orig %lu, donor %lu]\n", + orig_start + *len, donor_inode->i_size, + *len, donor_inode->i_size - orig_start, + orig_inode->i_ino, donor_inode->i_ino); + *len = donor_inode->i_size - orig_start; + } + } else { + if (orig_start >= orig_inode->i_size) { + ext4_debug("ext4 move extent: start offset [%llu] " + "should be less than original file size " + "[%lld] [inode:orig %lu, donor %lu]\n", + orig_start, orig_inode->i_size, + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + if (orig_start + *len > orig_inode->i_size) { + ext4_debug("ext4 move extent: Adjust length " + "from %llu to %lld. Because it should be " + "less than original file size " + "[ino:orig %lu, donor %lu]\n", + *len, orig_inode->i_size - orig_start, + orig_inode->i_ino, donor_inode->i_ino); + *len = orig_inode->i_size - orig_start; + } + } + + if (!*len) { + ext4_debug("ext4 move extent: len shoudld not be 0 " + "[ino:orig %lu, donor %lu]\n", orig_inode->i_ino, + donor_inode->i_ino); + return -EINVAL; + } + + return 0; +} + +/** + * mext_inode_double_lock - Lock i_mutex on both @inode1 and @inode2 + * + * @inode1: the inode structure + * @inode2: the inode structure + * + * Lock two inodes' i_mutex by i_ino order. This function is moved from + * fs/inode.c. + */ +static void +mext_inode_double_lock(struct inode *inode1, struct inode *inode2) +{ + if (inode1 == NULL || inode2 == NULL || inode1 == inode2) { + if (inode1) + mutex_lock(&inode1->i_mutex); + else if (inode2) + mutex_lock(&inode2->i_mutex); + return; + } + + if (inode1->i_ino < inode2->i_ino) { + mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD); + } else { + mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD); + } +} + +/** + * mext_inode_double_unlock - Release i_mutex on both @inode1 and @inode2 + * + * @inode1: the inode that is released first + * @inode2: the inode that is released second + * + * This function is moved from fs/inode.c. + */ + +static void +mext_inode_double_unlock(struct inode *inode1, struct inode *inode2) +{ + if (inode1) + mutex_unlock(&inode1->i_mutex); + + if (inode2 && inode2 != inode1) + mutex_unlock(&inode2->i_mutex); +} + +/** + * ext4_move_extents - Exchange the specified range of a file + * + * @o_filp: file structure of the original file + * @d_filp: file structure of the donor file + * @orig_start: start offset in block for orig + * @donor_start: start offset in block for donor + * @len: the number of blocks to be moved + * @moved_len: moved block length + * + * This function returns 0 and moved block length is set in moved_len + * if succeed, otherwise returns error value. + * + * Note: ext4_move_extents() proceeds the following order. + * 1:ext4_move_extents() calculates the last block number of moving extent + * function by the start block number (orig_start) and the number of blocks + * to be moved (len) specified as arguments. + * If the {orig, donor}_start points a hole, the extent's start offset + * pointed by ext_cur (current extent), holecheck_path, orig_path are set + * after hole behind. + * 2:Continue step 3 to step 5, until the holecheck_path points to last_extent + * or the ext_cur exceeds the block_end which is last logical block number. + * 3:To get the length of continues area, call mext_next_extent() + * specified with the ext_cur (initial value is holecheck_path) re-cursive, + * until find un-continuous extent, the start logical block number exceeds + * the block_end or the extent points to the last extent. + * 4:Exchange the original inode data with donor inode data + * from orig_page_offset to seq_end_page. + * The start indexes of data are specified as arguments. + * That of the original inode is orig_page_offset, + * and the donor inode is also orig_page_offset + * (To easily handle blocksize != pagesize case, the offset for the + * donor inode is block unit). + * 5:Update holecheck_path and orig_path to points a next proceeding extent, + * then returns to step 2. + * 6:Release holecheck_path, orig_path and set the len to moved_len + * which shows the number of moved blocks. + * The moved_len is useful for the command to calculate the file offset + * for starting next move extent ioctl. + * 7:Return 0 on success, or a negative error value on failure. + */ +int +ext4_move_extents(struct file *o_filp, struct file *d_filp, + __u64 orig_start, __u64 donor_start, __u64 len, + __u64 *moved_len) +{ + struct inode *orig_inode = o_filp->f_dentry->d_inode; + struct inode *donor_inode = d_filp->f_dentry->d_inode; + struct ext4_ext_path *orig_path = NULL, *holecheck_path = NULL; + struct ext4_extent *ext_prev, *ext_cur, *ext_dummy; + ext4_lblk_t block_start = orig_start; + ext4_lblk_t block_end, seq_start, add_blocks, file_end, seq_blocks = 0; + ext4_lblk_t rest_blocks; + pgoff_t orig_page_offset = 0, seq_end_page; + int ret, depth, last_extent = 0; + int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; + int data_offset_in_page; + int block_len_in_page; + int uninit; + + /* protect orig and donor against a truncate */ + mext_inode_double_lock(orig_inode, donor_inode); + + mext_double_down_read(orig_inode, donor_inode); + /* Check the filesystem environment whether move_extent can be done */ + ret = mext_check_arguments(orig_inode, donor_inode, orig_start, + donor_start, &len, *moved_len); + mext_double_up_read(orig_inode, donor_inode); + if (ret) + goto out2; + + file_end = (i_size_read(orig_inode) - 1) >> orig_inode->i_blkbits; + block_end = block_start + len - 1; + if (file_end < block_end) + len -= block_end - file_end; + + get_ext_path(orig_path, orig_inode, block_start, ret); + if (orig_path == NULL) + goto out2; + + /* Get path structure to check the hole */ + get_ext_path(holecheck_path, orig_inode, block_start, ret); + if (holecheck_path == NULL) + goto out; + + depth = ext_depth(orig_inode); + ext_cur = holecheck_path[depth].p_ext; + if (ext_cur == NULL) { + ret = -EINVAL; + goto out; + } + + /* + * Get proper extent whose ee_block is beyond block_start + * if block_start was within the hole. + */ + if (le32_to_cpu(ext_cur->ee_block) + + ext4_ext_get_actual_len(ext_cur) - 1 < block_start) { + last_extent = mext_next_extent(orig_inode, + holecheck_path, &ext_cur); + if (last_extent < 0) { + ret = last_extent; + goto out; + } + last_extent = mext_next_extent(orig_inode, orig_path, + &ext_dummy); + if (last_extent < 0) { + ret = last_extent; + goto out; + } + } + seq_start = block_start; + + /* No blocks within the specified range. */ + if (le32_to_cpu(ext_cur->ee_block) > block_end) { + ext4_debug("ext4 move extent: The specified range of file " + "may be the hole\n"); + ret = -EINVAL; + goto out; + } + + /* Adjust start blocks */ + add_blocks = min(le32_to_cpu(ext_cur->ee_block) + + ext4_ext_get_actual_len(ext_cur), block_end + 1) - + max(le32_to_cpu(ext_cur->ee_block), block_start); + + while (!last_extent && le32_to_cpu(ext_cur->ee_block) <= block_end) { + seq_blocks += add_blocks; + + /* Adjust tail blocks */ + if (seq_start + seq_blocks - 1 > block_end) + seq_blocks = block_end - seq_start + 1; + + ext_prev = ext_cur; + last_extent = mext_next_extent(orig_inode, holecheck_path, + &ext_cur); + if (last_extent < 0) { + ret = last_extent; + break; + } + add_blocks = ext4_ext_get_actual_len(ext_cur); + + /* + * Extend the length of contiguous block (seq_blocks) + * if extents are contiguous. + */ + if (ext4_can_extents_be_merged(orig_inode, + ext_prev, ext_cur) && + block_end >= le32_to_cpu(ext_cur->ee_block) && + !last_extent) + continue; + + /* Is original extent is uninitialized */ + uninit = ext4_ext_is_uninitialized(ext_prev); + + data_offset_in_page = seq_start % blocks_per_page; + + /* + * Calculate data blocks count that should be swapped + * at the first page. + */ + if (data_offset_in_page + seq_blocks > blocks_per_page) { + /* Swapped blocks are across pages */ + block_len_in_page = + blocks_per_page - data_offset_in_page; + } else { + /* Swapped blocks are in a page */ + block_len_in_page = seq_blocks; + } + + orig_page_offset = seq_start >> + (PAGE_CACHE_SHIFT - orig_inode->i_blkbits); + seq_end_page = (seq_start + seq_blocks - 1) >> + (PAGE_CACHE_SHIFT - orig_inode->i_blkbits); + seq_start = le32_to_cpu(ext_cur->ee_block); + rest_blocks = seq_blocks; + + /* Discard preallocations of two inodes */ + down_write(&EXT4_I(orig_inode)->i_data_sem); + ext4_discard_preallocations(orig_inode); + up_write(&EXT4_I(orig_inode)->i_data_sem); + + down_write(&EXT4_I(donor_inode)->i_data_sem); + ext4_discard_preallocations(donor_inode); + up_write(&EXT4_I(donor_inode)->i_data_sem); + + while (orig_page_offset <= seq_end_page) { + + /* Swap original branches with new branches */ + ret = move_extent_par_page(o_filp, donor_inode, + orig_page_offset, + data_offset_in_page, + block_len_in_page, uninit); + if (ret < 0) + goto out; + orig_page_offset++; + /* Count how many blocks we have exchanged */ + *moved_len += block_len_in_page; + BUG_ON(*moved_len > len); + + data_offset_in_page = 0; + rest_blocks -= block_len_in_page; + if (rest_blocks > blocks_per_page) + block_len_in_page = blocks_per_page; + else + block_len_in_page = rest_blocks; + } + + /* Decrease buffer counter */ + if (holecheck_path) + ext4_ext_drop_refs(holecheck_path); + get_ext_path(holecheck_path, orig_inode, + seq_start, ret); + if (holecheck_path == NULL) + break; + depth = holecheck_path->p_depth; + + /* Decrease buffer counter */ + if (orig_path) + ext4_ext_drop_refs(orig_path); + get_ext_path(orig_path, orig_inode, seq_start, ret); + if (orig_path == NULL) + break; + + ext_cur = holecheck_path[depth].p_ext; + add_blocks = ext4_ext_get_actual_len(ext_cur); + seq_blocks = 0; + + } +out: + if (orig_path) { + ext4_ext_drop_refs(orig_path); + kfree(orig_path); + } + if (holecheck_path) { + ext4_ext_drop_refs(holecheck_path); + kfree(holecheck_path); + } +out2: + mext_inode_double_unlock(orig_inode, donor_inode); + + if (ret) + return ret; + + /* All of the specified blocks must be exchanged in succeed */ + BUG_ON(*moved_len != len); + + return 0; +} -- cgit v1.2.3-70-g09d2