diff options
Diffstat (limited to 'fs/ext4/extents.c')
| -rw-r--r-- | fs/ext4/extents.c | 3478 |
1 files changed, 1863 insertions, 1615 deletions
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 240b6dea5441..2cf5759ba689 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -27,7 +27,8 @@ #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fiemap.h> -#include <linux/backing-dev.h> +#include <linux/iomap.h> +#include <linux/sched/mm.h> #include "ext4_jbd2.h" #include "ext4_extents.h" #include "xattr.h" @@ -49,10 +50,9 @@ static __le32 ext4_extent_block_csum(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_inode_info *ei = EXT4_I(inode); - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; - csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)eh, + csum = ext4_chksum(ei->i_csum_seed, (__u8 *)eh, EXT4_EXTENT_TAIL_OFFSET(eh)); return cpu_to_le32(csum); } @@ -62,7 +62,7 @@ static int ext4_extent_block_csum_verify(struct inode *inode, { struct ext4_extent_tail *et; - if (!ext4_has_metadata_csum(inode->i_sb)) + if (!ext4_has_feature_metadata_csum(inode->i_sb)) return 1; et = find_ext4_extent_tail(eh); @@ -76,53 +76,79 @@ static void ext4_extent_block_csum_set(struct inode *inode, { struct ext4_extent_tail *et; - if (!ext4_has_metadata_csum(inode->i_sb)) + if (!ext4_has_feature_metadata_csum(inode->i_sb)) return; et = find_ext4_extent_tail(eh); et->et_checksum = ext4_extent_block_csum(inode, eh); } -static int ext4_split_extent(handle_t *handle, - struct inode *inode, - struct ext4_ext_path **ppath, - struct ext4_map_blocks *map, - int split_flag, - int flags); - -static int ext4_split_extent_at(handle_t *handle, - struct inode *inode, - struct ext4_ext_path **ppath, - ext4_lblk_t split, - int split_flag, - int flags); - -static int ext4_find_delayed_extent(struct inode *inode, - struct extent_status *newes); - -static int ext4_ext_truncate_extend_restart(handle_t *handle, - struct inode *inode, - int needed) -{ - int err; +static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, + struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t split, + int split_flag, int flags); - if (!ext4_handle_valid(handle)) - return 0; - if (handle->h_buffer_credits >= needed) - return 0; +static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) +{ /* - * If we need to extend the journal get a few extra blocks - * while we're at it for efficiency's sake. + * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this + * moment, get_block can be called only for blocks inside i_size since + * page cache has been already dropped and writes are blocked by + * i_rwsem. So we can safely drop the i_data_sem here. */ - needed += 3; - err = ext4_journal_extend(handle, needed - handle->h_buffer_credits); - if (err <= 0) - return err; - err = ext4_truncate_restart_trans(handle, inode, needed); - if (err == 0) - err = -EAGAIN; + BUG_ON(EXT4_JOURNAL(inode) == NULL); + ext4_discard_preallocations(inode); + up_write(&EXT4_I(inode)->i_data_sem); + *dropped = 1; + return 0; +} - return err; +static inline void ext4_ext_path_brelse(struct ext4_ext_path *path) +{ + brelse(path->p_bh); + path->p_bh = NULL; +} + +static void ext4_ext_drop_refs(struct ext4_ext_path *path) +{ + int depth, i; + + if (IS_ERR_OR_NULL(path)) + return; + depth = path->p_depth; + for (i = 0; i <= depth; i++, path++) + ext4_ext_path_brelse(path); +} + +void ext4_free_ext_path(struct ext4_ext_path *path) +{ + if (IS_ERR_OR_NULL(path)) + return; + ext4_ext_drop_refs(path); + kfree(path); +} + +/* + * Make sure 'handle' has at least 'check_cred' credits. If not, restart + * transaction with 'restart_cred' credits. The function drops i_data_sem + * when restarting transaction and gets it after transaction is restarted. + * + * The function returns 0 on success, 1 if transaction had to be restarted, + * and < 0 in case of fatal error. + */ +int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode, + int check_cred, int restart_cred, + int revoke_cred) +{ + int ret; + int dropped = 0; + + ret = ext4_journal_ensure_credits_fn(handle, check_cred, restart_cred, + revoke_cred, ext4_ext_trunc_restart_fn(inode, &dropped)); + if (dropped) + down_write(&EXT4_I(inode)->i_data_sem); + return ret; } /* @@ -133,14 +159,25 @@ static int ext4_ext_truncate_extend_restart(handle_t *handle, static int ext4_ext_get_access(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { + int err = 0; + if (path->p_bh) { /* path points to block */ BUFFER_TRACE(path->p_bh, "get_write_access"); - return ext4_journal_get_write_access(handle, path->p_bh); + err = ext4_journal_get_write_access(handle, inode->i_sb, + path->p_bh, EXT4_JTR_NONE); + /* + * The extent buffer's verified bit will be set again in + * __ext4_ext_dirty(). We could leave an inconsistent + * buffer if the extents updating procudure break off du + * to some error happens, force to check it again. + */ + if (!err) + clear_buffer_verified(path->p_bh); } /* path points to leaf/index in inode body */ /* we use in-core data, no need to protect them */ - return 0; + return err; } /* @@ -149,8 +186,9 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode, * - ENOMEM * - EIO */ -int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, - struct inode *inode, struct ext4_ext_path *path) +static int __ext4_ext_dirty(const char *where, unsigned int line, + handle_t *handle, struct inode *inode, + struct ext4_ext_path *path) { int err; @@ -160,6 +198,9 @@ int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, /* path points to block */ err = __ext4_handle_dirty_metadata(where, line, handle, inode, path->p_bh); + /* Extents updating done, re-set verified flag */ + if (!err) + set_buffer_verified(path->p_bh); } else { /* path points to leaf/index in inode body */ err = ext4_mark_inode_dirty(handle, inode); @@ -167,6 +208,9 @@ int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, return err; } +#define ext4_ext_dirty(handle, inode, path) \ + __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path)) + static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) @@ -283,65 +327,20 @@ static inline int ext4_ext_space_root_idx(struct inode *inode, int check) return size; } -static inline int +static inline struct ext4_ext_path * ext4_force_split_extent_at(handle_t *handle, struct inode *inode, - struct ext4_ext_path **ppath, ext4_lblk_t lblk, + struct ext4_ext_path *path, ext4_lblk_t lblk, int nofail) { - struct ext4_ext_path *path = *ppath; int unwritten = ext4_ext_is_unwritten(path[path->p_depth].p_ext); + int flags = EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_SPLIT_NOMERGE; - return ext4_split_extent_at(handle, inode, ppath, lblk, unwritten ? - EXT4_EXT_MARK_UNWRIT1|EXT4_EXT_MARK_UNWRIT2 : 0, - EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO | - (nofail ? EXT4_GET_BLOCKS_METADATA_NOFAIL:0)); -} + if (nofail) + flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL | EXT4_EX_NOFAIL; -/* - * Calculate the number of metadata blocks needed - * to allocate @blocks - * Worse case is one block per extent - */ -int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock) -{ - struct ext4_inode_info *ei = EXT4_I(inode); - int idxs; - - idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) - / sizeof(struct ext4_extent_idx)); - - /* - * If the new delayed allocation block is contiguous with the - * previous da block, it can share index blocks with the - * previous block, so we only need to allocate a new index - * block every idxs leaf blocks. At ldxs**2 blocks, we need - * an additional index block, and at ldxs**3 blocks, yet - * another index blocks. - */ - if (ei->i_da_metadata_calc_len && - ei->i_da_metadata_calc_last_lblock+1 == lblock) { - int num = 0; - - if ((ei->i_da_metadata_calc_len % idxs) == 0) - num++; - if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0) - num++; - if ((ei->i_da_metadata_calc_len % (idxs*idxs*idxs)) == 0) { - num++; - ei->i_da_metadata_calc_len = 0; - } else - ei->i_da_metadata_calc_len++; - ei->i_da_metadata_calc_last_lblock++; - return num; - } - - /* - * In the worst case we need a new set of index blocks at - * every level of the inode's extent tree. - */ - ei->i_da_metadata_calc_len = 1; - ei->i_da_metadata_calc_last_lblock = lblock; - return ext_depth(inode) + 1; + return ext4_split_extent_at(handle, inode, path, lblk, unwritten ? + EXT4_EXT_MARK_UNWRIT1|EXT4_EXT_MARK_UNWRIT2 : 0, + flags); } static int @@ -377,7 +376,7 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) */ if (lblock + len <= lblock) return 0; - return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); + return ext4_inode_block_valid(inode, block, len); } static int ext4_valid_extent_idx(struct inode *inode, @@ -385,14 +384,18 @@ static int ext4_valid_extent_idx(struct inode *inode, { ext4_fsblk_t block = ext4_idx_pblock(ext_idx); - return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1); + return ext4_inode_block_valid(inode, block, 1); } static int ext4_valid_extent_entries(struct inode *inode, - struct ext4_extent_header *eh, - int depth) + struct ext4_extent_header *eh, + ext4_lblk_t lblk, ext4_fsblk_t *pblk, + int depth) { unsigned short entries; + ext4_lblk_t lblock = 0; + ext4_lblk_t cur = 0; + if (eh->eh_entries == 0) return 1; @@ -401,34 +404,51 @@ static int ext4_valid_extent_entries(struct inode *inode, if (depth == 0) { /* leaf entries */ struct ext4_extent *ext = EXT_FIRST_EXTENT(eh); - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; - ext4_fsblk_t pblock = 0; - ext4_lblk_t lblock = 0; - ext4_lblk_t prev = 0; - int len = 0; + + /* + * The logical block in the first entry should equal to + * the number in the index block. + */ + if (depth != ext_depth(inode) && + lblk != le32_to_cpu(ext->ee_block)) + return 0; while (entries) { if (!ext4_valid_extent(inode, ext)) return 0; /* Check for overlapping extents */ lblock = le32_to_cpu(ext->ee_block); - len = ext4_ext_get_actual_len(ext); - if ((lblock <= prev) && prev) { - pblock = ext4_ext_pblock(ext); - es->s_last_error_block = cpu_to_le64(pblock); + if (lblock < cur) { + *pblk = ext4_ext_pblock(ext); return 0; } + cur = lblock + ext4_ext_get_actual_len(ext); ext++; entries--; - prev = lblock + len - 1; } } else { struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh); + + /* + * The logical block in the first entry should equal to + * the number in the parent index block. + */ + if (depth != ext_depth(inode) && + lblk != le32_to_cpu(ext_idx->ei_block)) + return 0; while (entries) { if (!ext4_valid_extent_idx(inode, ext_idx)) return 0; + + /* Check for overlapping index extents */ + lblock = le32_to_cpu(ext_idx->ei_block); + if (lblock < cur) { + *pblk = ext4_idx_pblock(ext_idx); + return 0; + } ext_idx++; entries--; + cur = lblock + 1; } } return 1; @@ -436,7 +456,7 @@ static int ext4_valid_extent_entries(struct inode *inode, static int __ext4_ext_check(const char *function, unsigned int line, struct inode *inode, struct ext4_extent_header *eh, - int depth, ext4_fsblk_t pblk) + int depth, ext4_fsblk_t pblk, ext4_lblk_t lblk) { const char *error_msg; int max = 0, err = -EFSCORRUPTED; @@ -462,7 +482,11 @@ static int __ext4_ext_check(const char *function, unsigned int line, error_msg = "invalid eh_entries"; goto corrupted; } - if (!ext4_valid_extent_entries(inode, eh, depth)) { + if (unlikely((eh->eh_entries == 0) && (depth > 0))) { + error_msg = "eh_entries is 0 but eh_depth is > 0"; + goto corrupted; + } + if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) { error_msg = "invalid extent entries"; goto corrupted; } @@ -480,46 +504,77 @@ static int __ext4_ext_check(const char *function, unsigned int line, return 0; corrupted: - ext4_error_inode(inode, function, line, 0, - "pblk %llu bad header/extent: %s - magic %x, " - "entries %u, max %u(%u), depth %u(%u)", - (unsigned long long) pblk, error_msg, - le16_to_cpu(eh->eh_magic), - le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max), - max, le16_to_cpu(eh->eh_depth), depth); + ext4_error_inode_err(inode, function, line, 0, -err, + "pblk %llu bad header/extent: %s - magic %x, " + "entries %u, max %u(%u), depth %u(%u)", + (unsigned long long) pblk, error_msg, + le16_to_cpu(eh->eh_magic), + le16_to_cpu(eh->eh_entries), + le16_to_cpu(eh->eh_max), + max, le16_to_cpu(eh->eh_depth), depth); return err; } #define ext4_ext_check(inode, eh, depth, pblk) \ - __ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk)) + __ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk), 0) int ext4_ext_check_inode(struct inode *inode) { return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0); } +static void ext4_cache_extents(struct inode *inode, + struct ext4_extent_header *eh) +{ + struct ext4_extent *ex = EXT_FIRST_EXTENT(eh); + ext4_lblk_t prev = 0; + int i; + + for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) { + unsigned int status = EXTENT_STATUS_WRITTEN; + ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); + int len = ext4_ext_get_actual_len(ex); + + if (prev && (prev != lblk)) + ext4_es_cache_extent(inode, prev, lblk - prev, ~0, + EXTENT_STATUS_HOLE); + + if (ext4_ext_is_unwritten(ex)) + status = EXTENT_STATUS_UNWRITTEN; + ext4_es_cache_extent(inode, lblk, len, + ext4_ext_pblock(ex), status); + prev = lblk + len; + } +} + static struct buffer_head * __read_extent_tree_block(const char *function, unsigned int line, - struct inode *inode, ext4_fsblk_t pblk, int depth, - int flags) + struct inode *inode, struct ext4_extent_idx *idx, + int depth, int flags) { struct buffer_head *bh; int err; + gfp_t gfp_flags = __GFP_MOVABLE | GFP_NOFS; + ext4_fsblk_t pblk; + + if (flags & EXT4_EX_NOFAIL) + gfp_flags |= __GFP_NOFAIL; - bh = sb_getblk_gfp(inode->i_sb, pblk, __GFP_MOVABLE | GFP_NOFS); + pblk = ext4_idx_pblock(idx); + bh = sb_getblk_gfp(inode->i_sb, pblk, gfp_flags); if (unlikely(!bh)) return ERR_PTR(-ENOMEM); if (!bh_uptodate_or_lock(bh)) { trace_ext4_ext_load_extent(inode, pblk, _RET_IP_); - err = bh_submit_read(bh); + err = ext4_read_bh(bh, 0, NULL, false); if (err < 0) goto errout; } if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) return bh; - err = __ext4_ext_check(function, line, inode, - ext_block_hdr(bh), depth, pblk); + err = __ext4_ext_check(function, line, inode, ext_block_hdr(bh), + depth, pblk, le32_to_cpu(idx->ei_block)); if (err) goto errout; set_buffer_verified(bh); @@ -528,26 +583,7 @@ __read_extent_tree_block(const char *function, unsigned int line, */ if (!(flags & EXT4_EX_NOCACHE) && depth == 0) { struct ext4_extent_header *eh = ext_block_hdr(bh); - struct ext4_extent *ex = EXT_FIRST_EXTENT(eh); - ext4_lblk_t prev = 0; - int i; - - for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) { - unsigned int status = EXTENT_STATUS_WRITTEN; - ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); - int len = ext4_ext_get_actual_len(ex); - - if (prev && (prev != lblk)) - ext4_es_cache_extent(inode, prev, - lblk - prev, ~0, - EXTENT_STATUS_HOLE); - - if (ext4_ext_is_unwritten(ex)) - status = EXTENT_STATUS_UNWRITTEN; - ext4_es_cache_extent(inode, lblk, len, - ext4_ext_pblock(ex), status); - prev = lblk + len; - } + ext4_cache_extents(inode, eh); } return bh; errout: @@ -556,8 +592,8 @@ errout: } -#define read_extent_tree_block(inode, pblk, depth, flags) \ - __read_extent_tree_block(__func__, __LINE__, (inode), (pblk), \ +#define read_extent_tree_block(inode, idx, depth, flags) \ + __read_extent_tree_block(__func__, __LINE__, (inode), (idx), \ (depth), (flags)) /* @@ -574,9 +610,17 @@ int ext4_ext_precache(struct inode *inode) if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return 0; /* not an extent-mapped inode */ + ext4_check_map_extents_env(inode); + down_read(&ei->i_data_sem); depth = ext_depth(inode); + /* Don't cache anything if there are no external extent blocks */ + if (!depth) { + up_read(&ei->i_data_sem); + return ret; + } + path = kcalloc(depth + 1, sizeof(struct ext4_ext_path), GFP_NOFS); if (path == NULL) { @@ -584,9 +628,6 @@ int ext4_ext_precache(struct inode *inode) return -ENOMEM; } - /* Don't cache anything if there are no external extent blocks */ - if (depth == 0) - goto out; path[0].p_hdr = ext_inode_hdr(inode); ret = ext4_ext_check(inode, path[0].p_hdr, depth, 0); if (ret) @@ -599,13 +640,11 @@ int ext4_ext_precache(struct inode *inode) */ if ((i == depth) || path[i].p_idx > EXT_LAST_INDEX(path[i].p_hdr)) { - brelse(path[i].p_bh); - path[i].p_bh = NULL; + ext4_ext_path_brelse(path + i); i--; continue; } - bh = read_extent_tree_block(inode, - ext4_idx_pblock(path[i].p_idx++), + bh = read_extent_tree_block(inode, path[i].p_idx++, depth - i - 1, EXT4_EX_FORCE_CACHE); if (IS_ERR(bh)) { @@ -620,8 +659,7 @@ int ext4_ext_precache(struct inode *inode) ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED); out: up_read(&ei->i_data_sem); - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); return ret; } @@ -630,21 +668,22 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) { int k, l = path->p_depth; - ext_debug("path:"); + ext_debug(inode, "path:"); for (k = 0; k <= l; k++, path++) { if (path->p_idx) { - ext_debug(" %d->%llu", le32_to_cpu(path->p_idx->ei_block), - ext4_idx_pblock(path->p_idx)); + ext_debug(inode, " %d->%llu", + le32_to_cpu(path->p_idx->ei_block), + ext4_idx_pblock(path->p_idx)); } else if (path->p_ext) { - ext_debug(" %d:[%d]%d:%llu ", + ext_debug(inode, " %d:[%d]%d:%llu ", le32_to_cpu(path->p_ext->ee_block), ext4_ext_is_unwritten(path->p_ext), ext4_ext_get_actual_len(path->p_ext), ext4_ext_pblock(path->p_ext)); } else - ext_debug(" []"); + ext_debug(inode, " []"); } - ext_debug("\n"); + ext_debug(inode, "\n"); } static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) @@ -654,20 +693,20 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) struct ext4_extent *ex; int i; - if (!path) + if (IS_ERR_OR_NULL(path)) return; eh = path[depth].p_hdr; ex = EXT_FIRST_EXTENT(eh); - ext_debug("Displaying leaf extents for inode %lu\n", inode->i_ino); + ext_debug(inode, "Displaying leaf extents\n"); for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) { - ext_debug("%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block), + ext_debug(inode, "%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); } - ext_debug("\n"); + ext_debug(inode, "\n"); } static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path, @@ -680,10 +719,9 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path, struct ext4_extent_idx *idx; idx = path[level].p_idx; while (idx <= EXT_MAX_INDEX(path[level].p_hdr)) { - ext_debug("%d: move %d:%llu in new index %llu\n", level, - le32_to_cpu(idx->ei_block), - ext4_idx_pblock(idx), - newblock); + ext_debug(inode, "%d: move %d:%llu in new index %llu\n", + level, le32_to_cpu(idx->ei_block), + ext4_idx_pblock(idx), newblock); idx++; } @@ -692,7 +730,7 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path, ex = path[depth].p_ext; while (ex <= EXT_MAX_EXTENT(path[depth].p_hdr)) { - ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n", + ext_debug(inode, "move %d:%llu:[%d]%d in new leaf %llu\n", le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex), ext4_ext_is_unwritten(ex), @@ -708,20 +746,6 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path, #define ext4_ext_show_move(inode, path, newblock, level) #endif -void ext4_ext_drop_refs(struct ext4_ext_path *path) -{ - int depth, i; - - if (!path) - return; - depth = path->p_depth; - for (i = 0; i <= depth; i++, path++) - if (path->p_bh) { - brelse(path->p_bh); - path->p_bh = NULL; - } -} - /* * ext4_ext_binsearch_idx: * binary search for the closest index of the given block @@ -735,23 +759,24 @@ ext4_ext_binsearch_idx(struct inode *inode, struct ext4_extent_idx *r, *l, *m; - ext_debug("binsearch for %u(idx): ", block); + ext_debug(inode, "binsearch for %u(idx): ", block); l = EXT_FIRST_INDEX(eh) + 1; r = EXT_LAST_INDEX(eh); while (l <= r) { m = l + (r - l) / 2; + ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, + le32_to_cpu(l->ei_block), m, le32_to_cpu(m->ei_block), + r, le32_to_cpu(r->ei_block)); + if (block < le32_to_cpu(m->ei_block)) r = m - 1; else l = m + 1; - ext_debug("%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ei_block), - m, le32_to_cpu(m->ei_block), - r, le32_to_cpu(r->ei_block)); } path->p_idx = l - 1; - ext_debug(" -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block), + ext_debug(inode, " -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block), ext4_idx_pblock(path->p_idx)); #ifdef CHECK_BINSEARCH @@ -761,8 +786,8 @@ ext4_ext_binsearch_idx(struct inode *inode, chix = ix = EXT_FIRST_INDEX(eh); for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) { - if (k != 0 && - le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) { + if (k != 0 && le32_to_cpu(ix->ei_block) <= + le32_to_cpu(ix[-1].ei_block)) { printk(KERN_DEBUG "k=%d, ix=0x%p, " "first=0x%p\n", k, ix, EXT_FIRST_INDEX(eh)); @@ -802,24 +827,25 @@ ext4_ext_binsearch(struct inode *inode, return; } - ext_debug("binsearch for %u: ", block); + ext_debug(inode, "binsearch for %u: ", block); l = EXT_FIRST_EXTENT(eh) + 1; r = EXT_LAST_EXTENT(eh); while (l <= r) { m = l + (r - l) / 2; + ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, + le32_to_cpu(l->ee_block), m, le32_to_cpu(m->ee_block), + r, le32_to_cpu(r->ee_block)); + if (block < le32_to_cpu(m->ee_block)) r = m - 1; else l = m + 1; - ext_debug("%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ee_block), - m, le32_to_cpu(m->ee_block), - r, le32_to_cpu(r->ee_block)); } path->p_ext = l - 1; - ext_debug(" -> %d:%llu:[%d]%d ", + ext_debug(inode, " -> %d:%llu:[%d]%d ", le32_to_cpu(path->p_ext->ee_block), ext4_ext_pblock(path->p_ext), ext4_ext_is_unwritten(path->p_ext), @@ -844,7 +870,7 @@ ext4_ext_binsearch(struct inode *inode, } -int ext4_ext_tree_init(handle_t *handle, struct inode *inode) +void ext4_ext_tree_init(handle_t *handle, struct inode *inode) { struct ext4_extent_header *eh; @@ -853,19 +879,22 @@ int ext4_ext_tree_init(handle_t *handle, struct inode *inode) eh->eh_entries = 0; eh->eh_magic = EXT4_EXT_MAGIC; eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); + eh->eh_generation = 0; ext4_mark_inode_dirty(handle, inode); - return 0; } struct ext4_ext_path * ext4_find_extent(struct inode *inode, ext4_lblk_t block, - struct ext4_ext_path **orig_path, int flags) + struct ext4_ext_path *path, int flags) { struct ext4_extent_header *eh; struct buffer_head *bh; - struct ext4_ext_path *path = orig_path ? *orig_path : NULL; short int depth, i, ppos = 0; int ret; + gfp_t gfp_flags = GFP_NOFS; + + if (flags & EXT4_EX_NOFAIL) + gfp_flags |= __GFP_NOFAIL; eh = ext_inode_hdr(inode); depth = ext_depth(inode); @@ -880,13 +909,13 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, ext4_ext_drop_refs(path); if (depth > path[0].p_maxdepth) { kfree(path); - *orig_path = path = NULL; + path = NULL; } } if (!path) { /* account possible depth increase */ path = kcalloc(depth + 2, sizeof(struct ext4_ext_path), - GFP_NOFS); + gfp_flags); if (unlikely(!path)) return ERR_PTR(-ENOMEM); path[0].p_maxdepth = depth + 1; @@ -895,9 +924,11 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, path[0].p_bh = NULL; i = depth; + if (!(flags & EXT4_EX_NOCACHE) && depth == 0) + ext4_cache_extents(inode, eh); /* walk through the tree */ while (i) { - ext_debug("depth %d: num %d, max %d\n", + ext_debug(inode, "depth %d: num %d, max %d\n", ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); ext4_ext_binsearch_idx(inode, path + ppos, block); @@ -905,8 +936,7 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, path[ppos].p_depth = i; path[ppos].p_ext = NULL; - bh = read_extent_tree_block(inode, path[ppos].p_block, --i, - flags); + bh = read_extent_tree_block(inode, path[ppos].p_idx, --i, flags); if (IS_ERR(bh)) { ret = PTR_ERR(bh); goto err; @@ -933,10 +963,7 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, return path; err: - ext4_ext_drop_refs(path); - kfree(path); - if (orig_path) - *orig_path = NULL; + ext4_free_ext_path(path); return ERR_PTR(ret); } @@ -974,28 +1001,30 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, if (logical > le32_to_cpu(curp->p_idx->ei_block)) { /* insert after */ - ext_debug("insert new index %d after: %llu\n", logical, ptr); + ext_debug(inode, "insert new index %d after: %llu\n", + logical, ptr); ix = curp->p_idx + 1; } else { /* insert before */ - ext_debug("insert new index %d before: %llu\n", logical, ptr); + ext_debug(inode, "insert new index %d before: %llu\n", + logical, ptr); ix = curp->p_idx; } + if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { + EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); + return -EFSCORRUPTED; + } + len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1; BUG_ON(len < 0); if (len > 0) { - ext_debug("insert new index %d: " + ext_debug(inode, "insert new index %d: " "move %d indices from 0x%p to 0x%p\n", logical, len, ix, ix + 1); memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx)); } - if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { - EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); - return -EFSCORRUPTED; - } - ix->ei_block = cpu_to_le32(logical); ext4_idx_store_pblock(ix, ptr); le16_add_cpu(&curp->p_hdr->eh_entries, 1); @@ -1034,7 +1063,12 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, ext4_fsblk_t newblock, oldblock; __le32 border; ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */ + gfp_t gfp_flags = GFP_NOFS; int err = 0; + size_t ext_size = 0; + + if (flags & EXT4_EX_NOFAIL) + gfp_flags |= __GFP_NOFAIL; /* make decision: where to split? */ /* FIXME: now decision is simplest: at current extent */ @@ -1047,12 +1081,12 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, } if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) { border = path[depth].p_ext[1].ee_block; - ext_debug("leaf will be split." + ext_debug(inode, "leaf will be split." " next leaf starts at %d\n", le32_to_cpu(border)); } else { border = newext->ee_block; - ext_debug("leaf will be added." + ext_debug(inode, "leaf will be added." " next leaf starts at %d\n", le32_to_cpu(border)); } @@ -1069,12 +1103,12 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, * We need this to handle errors and free blocks * upon them. */ - ablocks = kcalloc(depth, sizeof(ext4_fsblk_t), GFP_NOFS); + ablocks = kcalloc(depth, sizeof(ext4_fsblk_t), gfp_flags); if (!ablocks) return -ENOMEM; /* allocate all needed blocks */ - ext_debug("allocate %d blocks for indexes/leaf\n", depth - at); + ext_debug(inode, "allocate %d blocks for indexes/leaf\n", depth - at); for (a = 0; a < depth - at; a++) { newblock = ext4_ext_new_meta_block(handle, inode, path, newext, &err, flags); @@ -1097,7 +1131,8 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, } lock_buffer(bh); - err = ext4_journal_get_create_access(handle, bh); + err = ext4_journal_get_create_access(handle, inode->i_sb, bh, + EXT4_JTR_NONE); if (err) goto cleanup; @@ -1106,6 +1141,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_depth = 0; + neh->eh_generation = 0; /* move remainder of path[depth] to the new leaf */ if (unlikely(path[depth].p_hdr->eh_entries != @@ -1126,6 +1162,10 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, le16_add_cpu(&neh->eh_entries, m); } + /* zero out unused area in the extent block */ + ext_size = sizeof(struct ext4_extent_header) + + sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries); + memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1156,7 +1196,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, goto cleanup; } if (k) - ext_debug("create %d intermediate indices\n", k); + ext_debug(inode, "create %d intermediate indices\n", k); /* insert new index into current index block */ /* current depth stored in i var */ i = depth - 1; @@ -1170,7 +1210,8 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, } lock_buffer(bh); - err = ext4_journal_get_create_access(handle, bh); + err = ext4_journal_get_create_access(handle, inode->i_sb, bh, + EXT4_JTR_NONE); if (err) goto cleanup; @@ -1179,11 +1220,12 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); neh->eh_depth = cpu_to_le16(depth - i); + neh->eh_generation = 0; fidx = EXT_FIRST_INDEX(neh); fidx->ei_block = border; ext4_idx_store_pblock(fidx, oldblock); - ext_debug("int.index at %d (block %llu): %u -> %llu\n", + ext_debug(inode, "int.index at %d (block %llu): %u -> %llu\n", i, newblock, le32_to_cpu(border), oldblock); /* move remainder of path[i] to the new index block */ @@ -1197,7 +1239,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, } /* start copy indexes */ m = EXT_MAX_INDEX(path[i].p_hdr) - path[i].p_idx++; - ext_debug("cur 0x%p, last 0x%p\n", path[i].p_idx, + ext_debug(inode, "cur 0x%p, last 0x%p\n", path[i].p_idx, EXT_MAX_INDEX(path[i].p_hdr)); ext4_ext_show_move(inode, path, newblock, i); if (m) { @@ -1205,6 +1247,11 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, sizeof(struct ext4_extent_idx) * m); le16_add_cpu(&neh->eh_entries, m); } + /* zero out unused area in the extent block */ + ext_size = sizeof(struct ext4_extent_header) + + (sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries)); + memset(bh->b_data + ext_size, 0, + inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1270,6 +1317,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, ext4_fsblk_t newblock, goal = 0; struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; int err = 0; + size_t ext_size = 0; /* Try to prepend new index to old one */ if (ext_depth(inode)) @@ -1289,15 +1337,18 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, return -ENOMEM; lock_buffer(bh); - err = ext4_journal_get_create_access(handle, bh); + err = ext4_journal_get_create_access(handle, inode->i_sb, bh, + EXT4_JTR_NONE); if (err) { unlock_buffer(bh); goto out; } + ext_size = sizeof(EXT4_I(inode)->i_data); /* move top-level index/leaf into new block */ - memmove(bh->b_data, EXT4_I(inode)->i_data, - sizeof(EXT4_I(inode)->i_data)); + memmove(bh->b_data, EXT4_I(inode)->i_data, ext_size); + /* zero out unused area in the extent block */ + memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); /* set size of new block */ neh = ext_block_hdr(bh); @@ -1310,6 +1361,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, neh->eh_magic = EXT4_EXT_MAGIC; ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); + set_buffer_verified(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); @@ -1326,13 +1378,13 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, EXT_FIRST_INDEX(neh)->ei_block = EXT_FIRST_EXTENT(neh)->ee_block; } - ext_debug("new root: num %d(%d), lblock %d, ptr %llu\n", + ext_debug(inode, "new root: num %d(%d), lblock %d, ptr %llu\n", le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max), le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block), ext4_idx_pblock(EXT_FIRST_INDEX(neh))); le16_add_cpu(&neh->eh_depth, 1); - ext4_mark_inode_dirty(handle, inode); + err = ext4_mark_inode_dirty(handle, inode); out: brelse(bh); @@ -1344,15 +1396,15 @@ out: * finds empty index and adds new leaf. * if no free index is found, then it requests in-depth growing. */ -static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode, - unsigned int mb_flags, - unsigned int gb_flags, - struct ext4_ext_path **ppath, - struct ext4_extent *newext) +static struct ext4_ext_path * +ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode, + unsigned int mb_flags, unsigned int gb_flags, + struct ext4_ext_path *path, + struct ext4_extent *newext) { - struct ext4_ext_path *path = *ppath; struct ext4_ext_path *curp; int depth, i, err = 0; + ext4_lblk_t ee_block = le32_to_cpu(newext->ee_block); repeat: i = depth = ext_depth(inode); @@ -1371,42 +1423,38 @@ repeat: * entry: create all needed subtree and add new leaf */ err = ext4_ext_split(handle, inode, mb_flags, path, newext, i); if (err) - goto out; + goto errout; /* refill path */ - path = ext4_find_extent(inode, - (ext4_lblk_t)le32_to_cpu(newext->ee_block), - ppath, gb_flags); - if (IS_ERR(path)) - err = PTR_ERR(path); - } else { - /* tree is full, time to grow in depth */ - err = ext4_ext_grow_indepth(handle, inode, mb_flags); - if (err) - goto out; + path = ext4_find_extent(inode, ee_block, path, gb_flags); + return path; + } - /* refill path */ - path = ext4_find_extent(inode, - (ext4_lblk_t)le32_to_cpu(newext->ee_block), - ppath, gb_flags); - if (IS_ERR(path)) { - err = PTR_ERR(path); - goto out; - } + /* tree is full, time to grow in depth */ + err = ext4_ext_grow_indepth(handle, inode, mb_flags); + if (err) + goto errout; - /* - * only first (depth 0 -> 1) produces free space; - * in all other cases we have to split the grown tree - */ - depth = ext_depth(inode); - if (path[depth].p_hdr->eh_entries == path[depth].p_hdr->eh_max) { - /* now we need to split */ - goto repeat; - } + /* refill path */ + path = ext4_find_extent(inode, ee_block, path, gb_flags); + if (IS_ERR(path)) + return path; + + /* + * only first (depth 0 -> 1) produces free space; + * in all other cases we have to split the grown tree + */ + depth = ext_depth(inode); + if (path[depth].p_hdr->eh_entries == path[depth].p_hdr->eh_max) { + /* now we need to split */ + goto repeat; } -out: - return err; + return path; + +errout: + ext4_free_ext_path(path); + return ERR_PTR(err); } /* @@ -1453,8 +1501,7 @@ static int ext4_ext_search_left(struct inode *inode, EXT4_ERROR_INODE(inode, "ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!", ix != NULL ? le32_to_cpu(ix->ei_block) : 0, - EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ? - le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block) : 0, + le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block), depth); return -EFSCORRUPTED; } @@ -1475,22 +1522,21 @@ static int ext4_ext_search_left(struct inode *inode, } /* - * search the closest allocated block to the right for *logical - * and returns it at @logical + it's physical address at @phys - * if *logical is the largest allocated block, the function - * returns 0 at @phys - * return value contains 0 (success) or error code + * Search the closest allocated block to the right for *logical + * and returns it at @logical + it's physical address at @phys. + * If not exists, return 0 and @phys is set to 0. We will return + * 1 which means we found an allocated block and ret_ex is valid. + * Or return a (< 0) error code. */ static int ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t *logical, ext4_fsblk_t *phys, - struct ext4_extent **ret_ex) + struct ext4_extent *ret_ex, int flags) { struct buffer_head *bh = NULL; struct ext4_extent_header *eh; struct ext4_extent_idx *ix; struct ext4_extent *ex; - ext4_fsblk_t block; int depth; /* Note, NOT eh_depth; depth from top of tree */ int ee_len; @@ -1557,20 +1603,18 @@ got_index: * follow it and find the closest allocated * block to the right */ ix++; - block = ext4_idx_pblock(ix); while (++depth < path->p_depth) { /* subtract from p_depth to get proper eh_depth */ - bh = read_extent_tree_block(inode, block, - path->p_depth - depth, 0); + bh = read_extent_tree_block(inode, ix, path->p_depth - depth, + flags); if (IS_ERR(bh)) return PTR_ERR(bh); eh = ext_block_hdr(bh); ix = EXT_FIRST_INDEX(eh); - block = ext4_idx_pblock(ix); put_bh(bh); } - bh = read_extent_tree_block(inode, block, path->p_depth - depth, 0); + bh = read_extent_tree_block(inode, ix, path->p_depth - depth, flags); if (IS_ERR(bh)) return PTR_ERR(bh); eh = ext_block_hdr(bh); @@ -1578,10 +1622,11 @@ got_index: found_extent: *logical = le32_to_cpu(ex->ee_block); *phys = ext4_ext_pblock(ex); - *ret_ex = ex; + if (ret_ex) + *ret_ex = *ex; if (bh) put_bh(bh); - return 0; + return 1; } /* @@ -1603,17 +1648,16 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path) return EXT_MAX_BLOCKS; while (depth >= 0) { + struct ext4_ext_path *p = &path[depth]; + if (depth == path->p_depth) { /* leaf */ - if (path[depth].p_ext && - path[depth].p_ext != - EXT_LAST_EXTENT(path[depth].p_hdr)) - return le32_to_cpu(path[depth].p_ext[1].ee_block); + if (p->p_ext && p->p_ext != EXT_LAST_EXTENT(p->p_hdr)) + return le32_to_cpu(p->p_ext[1].ee_block); } else { /* index */ - if (path[depth].p_idx != - EXT_LAST_INDEX(path[depth].p_hdr)) - return le32_to_cpu(path[depth].p_idx[1].ei_block); + if (p->p_idx != EXT_LAST_INDEX(p->p_hdr)) + return le32_to_cpu(p->p_idx[1].ei_block); } depth--; } @@ -1703,19 +1747,30 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, break; err = ext4_ext_get_access(handle, inode, path + k); if (err) - break; + goto clean; path[k].p_idx->ei_block = border; err = ext4_ext_dirty(handle, inode, path + k); if (err) - break; + goto clean; } + return 0; + +clean: + /* + * The path[k].p_bh is either unmodified or with no verified bit + * set (see ext4_ext_get_access()). So just clear the verified bit + * of the successfully modified extents buffers, which will force + * these extents to be checked to avoid using inconsistent data. + */ + while (++k < depth) + clear_buffer_verified(path[k].p_bh); return err; } -int -ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, - struct ext4_extent *ex2) +static int ext4_can_extents_be_merged(struct inode *inode, + struct ext4_extent *ex1, + struct ext4_extent *ex2) { unsigned short ext1_ee_len, ext2_ee_len; @@ -1729,23 +1784,11 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, le32_to_cpu(ex2->ee_block)) return 0; - /* - * To allow future support for preallocated extents to be added - * as an RO_COMPAT feature, refuse to merge to extents if - * this can result in the top bit of ee_len being set. - */ if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN) return 0; - /* - * The check for IO to unwritten extent is somewhat racy as we - * increment i_unwritten / set EXT4_STATE_DIO_UNWRITTEN only after - * dropping i_data_sem. But reserved blocks should save us in that - * case. - */ + if (ext4_ext_is_unwritten(ex1) && - (ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) || - atomic_read(&EXT4_I(inode)->i_unwritten) || - (ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN))) + ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN) return 0; #ifdef AGGRESSIVE_TEST if (ext1_ee_len >= 4) @@ -1823,7 +1866,8 @@ static void ext4_ext_try_to_merge_up(handle_t *handle, * group descriptor to release the extent tree block. If we * can't get the journal credits, give up. */ - if (ext4_journal_extend(handle, 2)) + if (ext4_journal_extend(handle, 2, + ext4_free_metadata_revoke_credits(inode->i_sb, 1))) return; /* @@ -1841,19 +1885,20 @@ static void ext4_ext_try_to_merge_up(handle_t *handle, (path[1].p_ext - EXT_FIRST_EXTENT(path[1].p_hdr)); path[0].p_hdr->eh_max = cpu_to_le16(max_root); - brelse(path[1].p_bh); + ext4_ext_path_brelse(path + 1); ext4_free_blocks(handle, inode, NULL, blk, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); } /* - * This function tries to merge the @ex extent to neighbours in the tree. - * return 1 if merge left else 0. + * This function tries to merge the @ex extent to neighbours in the tree, then + * tries to collapse the extent tree into the inode. */ static void ext4_ext_try_to_merge(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, - struct ext4_extent *ex) { + struct ext4_extent *ex) +{ struct ext4_extent_header *eh; unsigned int depth; int merge_done = 0; @@ -1924,20 +1969,19 @@ out: /* * ext4_ext_insert_extent: - * tries to merge requsted extent into the existing extent or + * tries to merge requested extent into the existing extent or * inserts requested extent as new one into the tree, * creating new leaf in the no-space case. */ -int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, - struct ext4_ext_path **ppath, - struct ext4_extent *newext, int gb_flags) +struct ext4_ext_path * +ext4_ext_insert_extent(handle_t *handle, struct inode *inode, + struct ext4_ext_path *path, + struct ext4_extent *newext, int gb_flags) { - struct ext4_ext_path *path = *ppath; struct ext4_extent_header *eh; struct ext4_extent *ex, *fex; struct ext4_extent *nearex; /* nearest extent */ - struct ext4_ext_path *npath = NULL; - int depth, len, err; + int depth, len, err = 0; ext4_lblk_t next; int mb_flags = 0, unwritten; @@ -1945,18 +1989,20 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, mb_flags |= EXT4_MB_DELALLOC_RESERVED; if (unlikely(ext4_ext_get_actual_len(newext) == 0)) { EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0"); - return -EFSCORRUPTED; + err = -EFSCORRUPTED; + goto errout; } depth = ext_depth(inode); ex = path[depth].p_ext; eh = path[depth].p_hdr; if (unlikely(path[depth].p_hdr == NULL)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); - return -EFSCORRUPTED; + err = -EFSCORRUPTED; + goto errout; } /* try to insert block into found extent and return */ - if (ex && !(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) { + if (ex && !(gb_flags & EXT4_GET_BLOCKS_SPLIT_NOMERGE)) { /* * Try to see whether we should rather test the extent on @@ -1979,7 +2025,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, /* Try to append newex to the ex */ if (ext4_can_extents_be_merged(inode, ex, newext)) { - ext_debug("append [%d]%d block to %u:[%d]%d" + ext_debug(inode, "append [%d]%d block to %u:[%d]%d" "(from %llu)\n", ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), @@ -1990,13 +2036,12 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, err = ext4_ext_get_access(handle, inode, path + depth); if (err) - return err; + goto errout; unwritten = ext4_ext_is_unwritten(ex); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(newext)); if (unwritten) ext4_ext_mark_unwritten(ex); - eh = path[depth].p_hdr; nearex = ex; goto merge; } @@ -2004,7 +2049,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, prepend: /* Try to prepend newex to the ex */ if (ext4_can_extents_be_merged(inode, newext, ex)) { - ext_debug("prepend %u[%d]%d block to %u:[%d]%d" + ext_debug(inode, "prepend %u[%d]%d block to %u:[%d]%d" "(from %llu)\n", le32_to_cpu(newext->ee_block), ext4_ext_is_unwritten(newext), @@ -2016,7 +2061,7 @@ prepend: err = ext4_ext_get_access(handle, inode, path + depth); if (err) - return err; + goto errout; unwritten = ext4_ext_is_unwritten(ex); ex->ee_block = newext->ee_block; @@ -2025,7 +2070,6 @@ prepend: + ext4_ext_get_actual_len(newext)); if (unwritten) ext4_ext_mark_unwritten(ex); - eh = path[depth].p_hdr; nearex = ex; goto merge; } @@ -2042,21 +2086,26 @@ prepend: if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block)) next = ext4_ext_next_leaf_block(path); if (next != EXT_MAX_BLOCKS) { - ext_debug("next leaf block - %u\n", next); - BUG_ON(npath != NULL); - npath = ext4_find_extent(inode, next, NULL, 0); - if (IS_ERR(npath)) - return PTR_ERR(npath); + struct ext4_ext_path *npath; + + ext_debug(inode, "next leaf block - %u\n", next); + npath = ext4_find_extent(inode, next, NULL, gb_flags); + if (IS_ERR(npath)) { + err = PTR_ERR(npath); + goto errout; + } BUG_ON(npath->p_depth != path->p_depth); eh = npath[depth].p_hdr; if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) { - ext_debug("next leaf isn't full(%d)\n", + ext_debug(inode, "next leaf isn't full(%d)\n", le16_to_cpu(eh->eh_entries)); + ext4_free_ext_path(path); path = npath; goto has_space; } - ext_debug("next leaf has no free space(%d,%d)\n", + ext_debug(inode, "next leaf has no free space(%d,%d)\n", le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); + ext4_free_ext_path(npath); } /* @@ -2065,10 +2114,10 @@ prepend: */ if (gb_flags & EXT4_GET_BLOCKS_METADATA_NOFAIL) mb_flags |= EXT4_MB_USE_RESERVED; - err = ext4_ext_create_new_leaf(handle, inode, mb_flags, gb_flags, - ppath, newext); - if (err) - goto cleanup; + path = ext4_ext_create_new_leaf(handle, inode, mb_flags, gb_flags, + path, newext); + if (IS_ERR(path)) + return path; depth = ext_depth(inode); eh = path[depth].p_hdr; @@ -2077,11 +2126,11 @@ has_space: err = ext4_ext_get_access(handle, inode, path + depth); if (err) - goto cleanup; + goto errout; if (!nearex) { /* there is no extent in this leaf, create first one */ - ext_debug("first extent in the leaf: %u:%llu:[%d]%d\n", + ext_debug(inode, "first extent in the leaf: %u:%llu:[%d]%d\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), @@ -2091,7 +2140,7 @@ has_space: if (le32_to_cpu(newext->ee_block) > le32_to_cpu(nearex->ee_block)) { /* Insert after */ - ext_debug("insert %u:%llu:[%d]%d before: " + ext_debug(inode, "insert %u:%llu:[%d]%d before: " "nearest %p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), @@ -2102,7 +2151,7 @@ has_space: } else { /* Insert before */ BUG_ON(newext->ee_block == nearex->ee_block); - ext_debug("insert %u:%llu:[%d]%d after: " + ext_debug(inode, "insert %u:%llu:[%d]%d after: " "nearest %p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), @@ -2112,7 +2161,7 @@ has_space: } len = EXT_LAST_EXTENT(eh) - nearex + 1; if (len > 0) { - ext_debug("insert %u:%llu:[%d]%d: " + ext_debug(inode, "insert %u:%llu:[%d]%d: " "move %d extents from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), @@ -2132,174 +2181,73 @@ has_space: merge: /* try to merge extents */ - if (!(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) + if (!(gb_flags & EXT4_GET_BLOCKS_SPLIT_NOMERGE)) ext4_ext_try_to_merge(handle, inode, path, nearex); - /* time to correct all indexes above */ err = ext4_ext_correct_indexes(handle, inode, path); if (err) - goto cleanup; + goto errout; err = ext4_ext_dirty(handle, inode, path + path->p_depth); + if (err) + goto errout; -cleanup: - ext4_ext_drop_refs(npath); - kfree(npath); - return err; + return path; + +errout: + ext4_free_ext_path(path); + return ERR_PTR(err); } -static int ext4_fill_fiemap_extents(struct inode *inode, - ext4_lblk_t block, ext4_lblk_t num, - struct fiemap_extent_info *fieinfo) +static int ext4_fill_es_cache_info(struct inode *inode, + ext4_lblk_t block, ext4_lblk_t num, + struct fiemap_extent_info *fieinfo) { - struct ext4_ext_path *path = NULL; - struct ext4_extent *ex; + ext4_lblk_t next, end = block + num - 1; struct extent_status es; - ext4_lblk_t next, next_del, start = 0, end = 0; - ext4_lblk_t last = block + num; - int exists, depth = 0, err = 0; - unsigned int flags = 0; unsigned char blksize_bits = inode->i_sb->s_blocksize_bits; + unsigned int flags; + int err; - while (block < last && block != EXT_MAX_BLOCKS) { - num = last - block; - /* find extent for this block */ - down_read(&EXT4_I(inode)->i_data_sem); - - path = ext4_find_extent(inode, block, &path, 0); - if (IS_ERR(path)) { - up_read(&EXT4_I(inode)->i_data_sem); - err = PTR_ERR(path); - path = NULL; - break; - } - - depth = ext_depth(inode); - if (unlikely(path[depth].p_hdr == NULL)) { - up_read(&EXT4_I(inode)->i_data_sem); - EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); - err = -EFSCORRUPTED; - break; - } - ex = path[depth].p_ext; - next = ext4_ext_next_allocated_block(path); - + while (block <= end) { + next = 0; flags = 0; - exists = 0; - if (!ex) { - /* there is no extent yet, so try to allocate - * all requested space */ - start = block; - end = block + num; - } else if (le32_to_cpu(ex->ee_block) > block) { - /* need to allocate space before found extent */ - start = block; - end = le32_to_cpu(ex->ee_block); - if (block + num < end) - end = block + num; - } else if (block >= le32_to_cpu(ex->ee_block) - + ext4_ext_get_actual_len(ex)) { - /* need to allocate space after found extent */ - start = block; - end = block + num; - if (end >= next) - end = next; - } else if (block >= le32_to_cpu(ex->ee_block)) { - /* - * some part of requested space is covered - * by found extent - */ - start = block; - end = le32_to_cpu(ex->ee_block) - + ext4_ext_get_actual_len(ex); - if (block + num < end) - end = block + num; - exists = 1; - } else { - BUG(); - } - BUG_ON(end <= start); - - if (!exists) { - es.es_lblk = start; - es.es_len = end - start; - es.es_pblk = 0; - } else { - es.es_lblk = le32_to_cpu(ex->ee_block); - es.es_len = ext4_ext_get_actual_len(ex); - es.es_pblk = ext4_ext_pblock(ex); - if (ext4_ext_is_unwritten(ex)) - flags |= FIEMAP_EXTENT_UNWRITTEN; - } - - /* - * Find delayed extent and update es accordingly. We call - * it even in !exists case to find out whether es is the - * last existing extent or not. - */ - next_del = ext4_find_delayed_extent(inode, &es); - if (!exists && next_del) { - exists = 1; + if (!ext4_es_lookup_extent(inode, block, &next, &es, NULL)) + break; + if (ext4_es_is_unwritten(&es)) + flags |= FIEMAP_EXTENT_UNWRITTEN; + if (ext4_es_is_delayed(&es)) flags |= (FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN); - } - up_read(&EXT4_I(inode)->i_data_sem); - - if (unlikely(es.es_len == 0)) { - EXT4_ERROR_INODE(inode, "es.es_len == 0"); - err = -EFSCORRUPTED; - break; - } - - /* - * This is possible iff next == next_del == EXT_MAX_BLOCKS. - * we need to check next == EXT_MAX_BLOCKS because it is - * possible that an extent is with unwritten and delayed - * status due to when an extent is delayed allocated and - * is allocated by fallocate status tree will track both of - * them in a extent. - * - * So we could return a unwritten and delayed extent, and - * its block is equal to 'next'. - */ - if (next == next_del && next == EXT_MAX_BLOCKS) { + if (ext4_es_is_hole(&es)) + flags |= EXT4_FIEMAP_EXTENT_HOLE; + if (next == 0) flags |= FIEMAP_EXTENT_LAST; - if (unlikely(next_del != EXT_MAX_BLOCKS || - next != EXT_MAX_BLOCKS)) { - EXT4_ERROR_INODE(inode, - "next extent == %u, next " - "delalloc extent = %u", - next, next_del); - err = -EFSCORRUPTED; - break; - } - } - - if (exists) { - err = fiemap_fill_next_extent(fieinfo, + if (flags & (FIEMAP_EXTENT_DELALLOC| + EXT4_FIEMAP_EXTENT_HOLE)) + es.es_pblk = 0; + else + es.es_pblk = ext4_es_pblock(&es); + err = fiemap_fill_next_extent(fieinfo, (__u64)es.es_lblk << blksize_bits, (__u64)es.es_pblk << blksize_bits, (__u64)es.es_len << blksize_bits, flags); - if (err < 0) - break; - if (err == 1) { - err = 0; - break; - } - } - - block = es.es_lblk + es.es_len; + if (next == 0) + break; + block = next; + if (err < 0) + return err; + if (err == 1) + return 0; } - - ext4_ext_drop_refs(path); - kfree(path); - return err; + return 0; } + /* - * ext4_ext_determine_hole - determine hole around given block + * ext4_ext_find_hole - find hole around given block according to the given path * @inode: inode we lookup in * @path: path in extent tree to @lblk * @lblk: pointer to logical block around which we want to determine hole @@ -2311,9 +2259,9 @@ static int ext4_fill_fiemap_extents(struct inode *inode, * The function returns the length of a hole starting at @lblk. We update @lblk * to the beginning of the hole if we managed to find it. */ -static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, - struct ext4_ext_path *path, - ext4_lblk_t *lblk) +static ext4_lblk_t ext4_ext_find_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t *lblk) { int depth = ext_depth(inode); struct ext4_extent *ex; @@ -2341,30 +2289,6 @@ static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, } /* - * ext4_ext_put_gap_in_cache: - * calculate boundaries of the gap that the requested block fits into - * and cache this gap - */ -static void -ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start, - ext4_lblk_t hole_len) -{ - struct extent_status es; - - ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, - hole_start + hole_len - 1, &es); - if (es.es_len) { - /* There's delayed extent containing lblock? */ - if (es.es_lblk <= hole_start) - return; - hole_len = min(es.es_lblk - hole_start, hole_len); - } - ext_debug(" -> %u:%u\n", hole_start, hole_len); - ext4_es_insert_extent(inode, hole_start, hole_len, ~0, - EXTENT_STATUS_HOLE); -} - -/* * ext4_ext_rm_idx: * removes index from the index block. */ @@ -2373,47 +2297,57 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, { int err; ext4_fsblk_t leaf; + int k = depth - 1; /* free index block */ - depth--; - path = path + depth; - leaf = ext4_idx_pblock(path->p_idx); - if (unlikely(path->p_hdr->eh_entries == 0)) { - EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0"); + leaf = ext4_idx_pblock(path[k].p_idx); + if (unlikely(path[k].p_hdr->eh_entries == 0)) { + EXT4_ERROR_INODE(inode, "path[%d].p_hdr->eh_entries == 0", k); return -EFSCORRUPTED; } - err = ext4_ext_get_access(handle, inode, path); + err = ext4_ext_get_access(handle, inode, path + k); if (err) return err; - if (path->p_idx != EXT_LAST_INDEX(path->p_hdr)) { - int len = EXT_LAST_INDEX(path->p_hdr) - path->p_idx; + if (path[k].p_idx != EXT_LAST_INDEX(path[k].p_hdr)) { + int len = EXT_LAST_INDEX(path[k].p_hdr) - path[k].p_idx; len *= sizeof(struct ext4_extent_idx); - memmove(path->p_idx, path->p_idx + 1, len); + memmove(path[k].p_idx, path[k].p_idx + 1, len); } - le16_add_cpu(&path->p_hdr->eh_entries, -1); - err = ext4_ext_dirty(handle, inode, path); + le16_add_cpu(&path[k].p_hdr->eh_entries, -1); + err = ext4_ext_dirty(handle, inode, path + k); if (err) return err; - ext_debug("index is empty, remove it, free block %llu\n", leaf); + ext_debug(inode, "index is empty, remove it, free block %llu\n", leaf); trace_ext4_ext_rm_idx(inode, leaf); ext4_free_blocks(handle, inode, NULL, leaf, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); - while (--depth >= 0) { - if (path->p_idx != EXT_FIRST_INDEX(path->p_hdr)) + while (--k >= 0) { + if (path[k + 1].p_idx != EXT_FIRST_INDEX(path[k + 1].p_hdr)) break; - path--; - err = ext4_ext_get_access(handle, inode, path); + err = ext4_ext_get_access(handle, inode, path + k); if (err) - break; - path->p_idx->ei_block = (path+1)->p_idx->ei_block; - err = ext4_ext_dirty(handle, inode, path); + goto clean; + path[k].p_idx->ei_block = path[k + 1].p_idx->ei_block; + err = ext4_ext_dirty(handle, inode, path + k); if (err) - break; + goto clean; } + return 0; + +clean: + /* + * The path[k].p_bh is either unmodified or with no verified bit + * set (see ext4_ext_get_access()). So just clear the verified bit + * of the successfully modified extents buffers, which will force + * these extents to be checked to avoid using inconsistent data. + */ + while (++k < depth) + clear_buffer_verified(path[k].p_bh); + return err; } @@ -2464,18 +2398,20 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks, int ext4_ext_index_trans_blocks(struct inode *inode, int extents) { int index; - int depth; /* If we are converting the inline data, only one is needed here. */ if (ext4_has_inline_data(inode)) return 1; - depth = ext_depth(inode); - + /* + * Extent tree can change between the time we estimate credits and + * the time we actually modify the tree. Assume the worst case. + */ if (extents <= 1) - index = depth * 2; + index = (EXT4_MAX_EXTENT_DEPTH * 2) + extents; else - index = depth * 3; + index = (EXT4_MAX_EXTENT_DEPTH * 3) + + DIV_ROUND_UP(extents, ext4_ext_space_block(inode, 0)); return index; } @@ -2664,7 +2600,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int err = 0, correct_index = 0; - int depth = ext_depth(inode), credits; + int depth = ext_depth(inode), credits, revoke_credits; struct ext4_extent_header *eh; ext4_lblk_t a, b; unsigned num; @@ -2675,7 +2611,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, ext4_fsblk_t pblk; /* the header must be checked already in ext4_ext_remove_space() */ - ext_debug("truncate since %u in leaf to %u\n", start, end); + ext_debug(inode, "truncate since %u in leaf to %u\n", start, end); if (!path[depth].p_hdr) path[depth].p_hdr = ext_block_hdr(path[depth].p_bh); eh = path[depth].p_hdr; @@ -2701,15 +2637,14 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, else unwritten = 0; - ext_debug("remove ext %u:[%d]%d\n", ex_ee_block, + ext_debug(inode, "remove ext %u:[%d]%d\n", ex_ee_block, unwritten, ex_ee_len); path[depth].p_ext = ex; - a = ex_ee_block > start ? ex_ee_block : start; - b = ex_ee_block+ex_ee_len - 1 < end ? - ex_ee_block+ex_ee_len - 1 : end; + a = max(ex_ee_block, start); + b = min(ex_ee_block + ex_ee_len - 1, end); - ext_debug(" border %u:%u\n", a, b); + ext_debug(inode, " border %u:%u\n", a, b); /* If this extent is beyond the end of the hole, skip it */ if (end < ex_ee_block) { @@ -2756,10 +2691,23 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, credits += (ext_depth(inode)) + 1; } credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb); - - err = ext4_ext_truncate_extend_restart(handle, inode, credits); - if (err) + /* + * We may end up freeing some index blocks and data from the + * punched range. Note that partial clusters are accounted for + * by ext4_free_data_revoke_credits(). + */ + revoke_credits = + ext4_free_metadata_revoke_credits(inode->i_sb, + ext_depth(inode)) + + ext4_free_data_revoke_credits(inode, b - a + 1); + + err = ext4_datasem_ensure_credits(handle, inode, credits, + credits, revoke_credits); + if (err) { + if (err > 0) + err = -EAGAIN; goto out; + } err = ext4_ext_get_access(handle, inode, path + depth); if (err) @@ -2805,7 +2753,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, if (err) goto out; - ext_debug("new extent: %u:%u:%llu\n", ex_ee_block, num, + ext_debug(inode, "new extent: %u:%u:%llu\n", ex_ee_block, num, ext4_ext_pblock(ex)); ex--; ex_ee_block = le32_to_cpu(ex->ee_block); @@ -2877,15 +2825,18 @@ int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, struct partial_cluster partial; handle_t *handle; int i = 0, err = 0; + int flags = EXT4_EX_NOCACHE | EXT4_EX_NOFAIL; partial.pclu = 0; partial.lblk = 0; partial.state = initial; - ext_debug("truncate since %u to %u\n", start, end); + ext_debug(inode, "truncate since %u to %u\n", start, end); /* probably first extent we're gonna free will be last in block */ - handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, depth + 1); + handle = ext4_journal_start_with_revoke(inode, EXT4_HT_TRUNCATE, + depth + 1, + ext4_free_metadata_revoke_credits(inode->i_sb, depth)); if (IS_ERR(handle)) return PTR_ERR(handle); @@ -2905,7 +2856,7 @@ again: ext4_fsblk_t pblk; /* find extent for or closest extent to this block */ - path = ext4_find_extent(inode, end, NULL, EXT4_EX_NOCACHE); + path = ext4_find_extent(inode, end, NULL, flags); if (IS_ERR(path)) { ext4_journal_stop(handle); return PTR_ERR(path); @@ -2940,7 +2891,7 @@ again: * in use to avoid freeing it when removing blocks. */ if (sbi->s_cluster_ratio > 1) { - pblk = ext4_ext_pblock(ex) + end - ee_block + 2; + pblk = ext4_ext_pblock(ex) + end - ee_block + 1; partial.pclu = EXT4_B2C(sbi, pblk); partial.state = nofree; } @@ -2951,24 +2902,28 @@ again: * fail removing space due to ENOSPC so try to use * reserved block if that happens. */ - err = ext4_force_split_extent_at(handle, inode, &path, - end + 1, 1); - if (err < 0) + path = ext4_force_split_extent_at(handle, inode, path, + end + 1, 1); + if (IS_ERR(path)) { + err = PTR_ERR(path); goto out; - - } else if (sbi->s_cluster_ratio > 1 && end >= ex_end) { + } + } else if (sbi->s_cluster_ratio > 1 && end >= ex_end && + partial.state == initial) { /* - * If there's an extent to the right its first cluster - * contains the immediate right boundary of the - * truncated/punched region. Set partial_cluster to - * its negative value so it won't be freed if shared - * with the current extent. The end < ee_block case - * is handled in ext4_ext_rm_leaf(). + * If we're punching, there's an extent to the right. + * If the partial cluster hasn't been set, set it to + * that extent's first cluster and its state to nofree + * so it won't be freed should it contain blocks to be + * removed. If it's already set (tofree/nofree), we're + * retrying and keep the original partial cluster info + * so a cluster marked tofree as a result of earlier + * extent removal is not lost. */ lblk = ex_end + 1; err = ext4_ext_search_right(inode, path, &lblk, &pblk, - &ex); - if (err) + NULL, flags); + if (err < 0) goto out; if (pblk) { partial.pclu = EXT4_B2C(sbi, pblk); @@ -2988,7 +2943,7 @@ again: le16_to_cpu(path[k].p_hdr->eh_entries)+1; } else { path = kcalloc(depth + 1, sizeof(struct ext4_ext_path), - GFP_NOFS); + GFP_NOFS | __GFP_NOFAIL); if (path == NULL) { ext4_journal_stop(handle); return -ENOMEM; @@ -3010,15 +2965,14 @@ again: err = ext4_ext_rm_leaf(handle, inode, path, &partial, start, end); /* root level has p_bh == NULL, brelse() eats this */ - brelse(path[i].p_bh); - path[i].p_bh = NULL; + ext4_ext_path_brelse(path + i); i--; continue; } /* this is index block */ if (!path[i].p_hdr) { - ext_debug("initialize header\n"); + ext_debug(inode, "initialize header\n"); path[i].p_hdr = ext_block_hdr(path[i].p_bh); } @@ -3026,7 +2980,7 @@ again: /* this level hasn't been touched yet */ path[i].p_idx = EXT_LAST_INDEX(path[i].p_hdr); path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries)+1; - ext_debug("init index ptr: hdr 0x%p, num %d\n", + ext_debug(inode, "init index ptr: hdr 0x%p, num %d\n", path[i].p_hdr, le16_to_cpu(path[i].p_hdr->eh_entries)); } else { @@ -3034,18 +2988,17 @@ again: path[i].p_idx--; } - ext_debug("level %d - index, first 0x%p, cur 0x%p\n", + ext_debug(inode, "level %d - index, first 0x%p, cur 0x%p\n", i, EXT_FIRST_INDEX(path[i].p_hdr), path[i].p_idx); if (ext4_ext_more_to_rm(path + i)) { struct buffer_head *bh; /* go to the next level */ - ext_debug("move to level %d (block %llu)\n", + ext_debug(inode, "move to level %d (block %llu)\n", i + 1, ext4_idx_pblock(path[i].p_idx)); memset(path + i + 1, 0, sizeof(*path)); - bh = read_extent_tree_block(inode, - ext4_idx_pblock(path[i].p_idx), depth - i - 1, - EXT4_EX_NOCACHE); + bh = read_extent_tree_block(inode, path[i].p_idx, + depth - i - 1, flags); if (IS_ERR(bh)) { /* should we reset i_size? */ err = PTR_ERR(bh); @@ -3073,10 +3026,9 @@ again: err = ext4_ext_rm_idx(handle, inode, path, i); } /* root level has p_bh == NULL, brelse() eats this */ - brelse(path[i].p_bh); - path[i].p_bh = NULL; + ext4_ext_path_brelse(path + i); i--; - ext_debug("return to level %d\n", i); + ext_debug(inode, "return to level %d\n", i); } } @@ -3115,8 +3067,7 @@ again: } } out: - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); path = NULL; if (err == -EAGAIN) goto again; @@ -3176,7 +3127,7 @@ void ext4_ext_release(struct super_block *sb) #endif } -static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex) +static void ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex) { ext4_lblk_t ee_block; ext4_fsblk_t ee_pblock; @@ -3187,10 +3138,10 @@ static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex) ee_pblock = ext4_ext_pblock(ex); if (ee_len == 0) - return 0; + return; - return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock, - EXTENT_STATUS_WRITTEN); + ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock, + EXTENT_STATUS_WRITTEN, false); } /* FIXME!! we need to try to merge to left or right after zero-out */ @@ -3218,22 +3169,20 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) * * * Splits extent [a, b] into two extents [a, @split) and [@split, b], states - * of which are deterimined by split_flag. + * of which are determined by split_flag. * * There are two cases: * a> the extent are splitted into two extent. * b> split is not needed, and just mark the extent. * - * return 0 on success. + * Return an extent path pointer on success, or an error pointer on failure. */ -static int ext4_split_extent_at(handle_t *handle, - struct inode *inode, - struct ext4_ext_path **ppath, - ext4_lblk_t split, - int split_flag, - int flags) +static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, + struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t split, + int split_flag, int flags) { - struct ext4_ext_path *path = *ppath; ext4_fsblk_t newblock; ext4_lblk_t ee_block; struct ext4_extent *ex, newex, orig_ex, zero_ex; @@ -3244,8 +3193,7 @@ static int ext4_split_extent_at(handle_t *handle, BUG_ON((split_flag & (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)) == (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)); - ext_debug("ext4_split_extents_at: inode %lu, logical" - "block %llu\n", inode->i_ino, (unsigned long long)split); + ext_debug(inode, "logical block %llu\n", (unsigned long long)split); ext4_ext_show_leaf(inode, path); @@ -3276,7 +3224,7 @@ static int ext4_split_extent_at(handle_t *handle, else ext4_ext_mark_initialized(ex); - if (!(flags & EXT4_GET_BLOCKS_PRE_IO)) + if (!(flags & EXT4_GET_BLOCKS_SPLIT_NOMERGE)) ext4_ext_try_to_merge(handle, inode, path, ex); err = ext4_ext_dirty(handle, inode, path + path->p_depth); @@ -3304,8 +3252,32 @@ static int ext4_split_extent_at(handle_t *handle, if (split_flag & EXT4_EXT_MARK_UNWRIT2) ext4_ext_mark_unwritten(ex2); - err = ext4_ext_insert_extent(handle, inode, ppath, &newex, flags); - if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) { + path = ext4_ext_insert_extent(handle, inode, path, &newex, flags); + if (!IS_ERR(path)) + goto out; + + err = PTR_ERR(path); + if (err != -ENOSPC && err != -EDQUOT && err != -ENOMEM) + return path; + + /* + * Get a new path to try to zeroout or fix the extent length. + * Using EXT4_EX_NOFAIL guarantees that ext4_find_extent() + * will not return -ENOMEM, otherwise -ENOMEM will cause a + * retry in do_writepages(), and a WARN_ON may be triggered + * in ext4_da_update_reserve_space() due to an incorrect + * ee_len causing the i_reserved_data_blocks exception. + */ + path = ext4_find_extent(inode, ee_block, NULL, flags | EXT4_EX_NOFAIL); + if (IS_ERR(path)) { + EXT4_ERROR_INODE(inode, "Failed split extent on %u, err %ld", + split, PTR_ERR(path)); + return path; + } + depth = ext_depth(inode); + ex = path[depth].p_ext; + + if (EXT4_EXT_MAY_ZEROOUT & split_flag) { if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) { if (split_flag & EXT4_EXT_DATA_VALID1) { err = ext4_ext_zeroout(inode, ex2); @@ -3331,34 +3303,41 @@ static int ext4_split_extent_at(handle_t *handle, ext4_ext_pblock(&orig_ex)); } - if (err) - goto fix_extent_len; - /* update the extent length and mark as initialized */ - ex->ee_len = cpu_to_le16(ee_len); - ext4_ext_try_to_merge(handle, inode, path, ex); - err = ext4_ext_dirty(handle, inode, path + path->p_depth); - if (err) - goto fix_extent_len; - - /* update extent status tree */ - err = ext4_zeroout_es(inode, &zero_ex); - - goto out; - } else if (err) - goto fix_extent_len; - -out: - ext4_ext_show_leaf(inode, path); - return err; + if (!err) { + /* update the extent length and mark as initialized */ + ex->ee_len = cpu_to_le16(ee_len); + ext4_ext_try_to_merge(handle, inode, path, ex); + err = ext4_ext_dirty(handle, inode, path + path->p_depth); + if (!err) + /* update extent status tree */ + ext4_zeroout_es(inode, &zero_ex); + /* If we failed at this point, we don't know in which + * state the extent tree exactly is so don't try to fix + * length of the original extent as it may do even more + * damage. + */ + goto out; + } + } fix_extent_len: ex->ee_len = orig_ex.ee_len; + /* + * Ignore ext4_ext_dirty return value since we are already in error path + * and err is a non-zero error code. + */ ext4_ext_dirty(handle, inode, path + path->p_depth); - return err; +out: + if (err) { + ext4_free_ext_path(path); + path = ERR_PTR(err); + } + ext4_ext_show_leaf(inode, path); + return path; } /* - * ext4_split_extents() splits an extent and mark extent which is covered + * ext4_split_extent() splits an extent and mark extent which is covered * by @map as split_flags indicates * * It may result in splitting the extent into multiple extents (up to three) @@ -3368,21 +3347,18 @@ fix_extent_len: * c> Splits in three extents: Somone is splitting in middle of the extent * */ -static int ext4_split_extent(handle_t *handle, - struct inode *inode, - struct ext4_ext_path **ppath, - struct ext4_map_blocks *map, - int split_flag, - int flags) +static struct ext4_ext_path *ext4_split_extent(handle_t *handle, + struct inode *inode, + struct ext4_ext_path *path, + struct ext4_map_blocks *map, + int split_flag, int flags, + unsigned int *allocated) { - struct ext4_ext_path *path = *ppath; ext4_lblk_t ee_block; struct ext4_extent *ex; unsigned int ee_len, depth; - int err = 0; int unwritten; int split_flag1, flags1; - int allocated = map->m_len; depth = ext_depth(inode); ex = path[depth].p_ext; @@ -3392,35 +3368,33 @@ static int ext4_split_extent(handle_t *handle, if (map->m_lblk + map->m_len < ee_block + ee_len) { split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT; - flags1 = flags | EXT4_GET_BLOCKS_PRE_IO; + flags1 = flags | EXT4_GET_BLOCKS_SPLIT_NOMERGE; if (unwritten) split_flag1 |= EXT4_EXT_MARK_UNWRIT1 | EXT4_EXT_MARK_UNWRIT2; if (split_flag & EXT4_EXT_DATA_VALID2) split_flag1 |= EXT4_EXT_DATA_VALID1; - err = ext4_split_extent_at(handle, inode, ppath, + path = ext4_split_extent_at(handle, inode, path, map->m_lblk + map->m_len, split_flag1, flags1); - if (err) - goto out; - } else { - allocated = ee_len - (map->m_lblk - ee_block); - } - /* - * Update path is required because previous ext4_split_extent_at() may - * result in split of original leaf or extent zeroout. - */ - path = ext4_find_extent(inode, map->m_lblk, ppath, 0); - if (IS_ERR(path)) - return PTR_ERR(path); - depth = ext_depth(inode); - ex = path[depth].p_ext; - if (!ex) { - EXT4_ERROR_INODE(inode, "unexpected hole at %lu", - (unsigned long) map->m_lblk); - return -EFSCORRUPTED; + if (IS_ERR(path)) + return path; + /* + * Update path is required because previous ext4_split_extent_at + * may result in split of original leaf or extent zeroout. + */ + path = ext4_find_extent(inode, map->m_lblk, path, flags); + if (IS_ERR(path)) + return path; + depth = ext_depth(inode); + ex = path[depth].p_ext; + if (!ex) { + EXT4_ERROR_INODE(inode, "unexpected hole at %lu", + (unsigned long) map->m_lblk); + ext4_free_ext_path(path); + return ERR_PTR(-EFSCORRUPTED); + } + unwritten = ext4_ext_is_unwritten(ex); } - unwritten = ext4_ext_is_unwritten(ex); - split_flag1 = 0; if (map->m_lblk >= ee_block) { split_flag1 = split_flag & EXT4_EXT_DATA_VALID2; @@ -3429,15 +3403,20 @@ static int ext4_split_extent(handle_t *handle, split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT | EXT4_EXT_MARK_UNWRIT2); } - err = ext4_split_extent_at(handle, inode, ppath, + path = ext4_split_extent_at(handle, inode, path, map->m_lblk, split_flag1, flags); - if (err) - goto out; + if (IS_ERR(path)) + return path; } + if (allocated) { + if (map->m_lblk + map->m_len > ee_block + ee_len) + *allocated = ee_len - (map->m_lblk - ee_block); + else + *allocated = map->m_len; + } ext4_ext_show_leaf(inode, path); -out: - return err ? err : allocated; + return path; } /* @@ -3460,13 +3439,11 @@ out: * that are allocated and initialized. * It is guaranteed to be >= map->m_len. */ -static int ext4_ext_convert_to_initialized(handle_t *handle, - struct inode *inode, - struct ext4_map_blocks *map, - struct ext4_ext_path **ppath, - int flags) +static struct ext4_ext_path * +ext4_ext_convert_to_initialized(handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map, struct ext4_ext_path *path, + int flags, unsigned int *allocated) { - struct ext4_ext_path *path = *ppath; struct ext4_sb_info *sbi; struct ext4_extent_header *eh; struct ext4_map_blocks split_map; @@ -3474,17 +3451,16 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, struct ext4_extent *ex, *abut_ex; ext4_lblk_t ee_block, eof_block; unsigned int ee_len, depth, map_len = map->m_len; - int allocated = 0, max_zeroout = 0; int err = 0; int split_flag = EXT4_EXT_DATA_VALID2; + unsigned int max_zeroout = 0; - ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical" - "block %llu, max_blocks %u\n", inode->i_ino, - (unsigned long long)map->m_lblk, map_len); + ext_debug(inode, "logical block %llu, max_blocks %u\n", + (unsigned long long)map->m_lblk, map_len); sbi = EXT4_SB(inode->i_sb); - eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >> - inode->i_sb->s_blocksize_bits; + eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) + >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map_len) eof_block = map->m_lblk + map_len; @@ -3517,6 +3493,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, * - L2: we only attempt to merge with an extent stored in the * same extent tree node. */ + *allocated = 0; if ((map->m_lblk == ee_block) && /* See if we can merge left */ (map_len < ee_len) && /*L1*/ @@ -3546,7 +3523,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, (prev_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ err = ext4_ext_get_access(handle, inode, path + depth); if (err) - goto out; + goto errout; trace_ext4_ext_convert_to_initialized_fastpath(inode, map, ex, abut_ex); @@ -3561,7 +3538,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, abut_ex->ee_len = cpu_to_le16(prev_len + map_len); /* Result: number of initialized blocks past m_lblk */ - allocated = map_len; + *allocated = map_len; } } else if (((map->m_lblk + map_len) == (ee_block + ee_len)) && (map_len < ee_len) && /*L1*/ @@ -3592,7 +3569,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, (next_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ err = ext4_ext_get_access(handle, inode, path + depth); if (err) - goto out; + goto errout; trace_ext4_ext_convert_to_initialized_fastpath(inode, map, ex, abut_ex); @@ -3607,18 +3584,20 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, abut_ex->ee_len = cpu_to_le16(next_len + map_len); /* Result: number of initialized blocks past m_lblk */ - allocated = map_len; + *allocated = map_len; } } - if (allocated) { + if (*allocated) { /* Mark the block containing both extents as dirty */ - ext4_ext_dirty(handle, inode, path + depth); + err = ext4_ext_dirty(handle, inode, path + depth); /* Update path to point to the right extent */ path[depth].p_ext = abut_ex; + if (err) + goto errout; goto out; } else - allocated = ee_len - (map->m_lblk - ee_block); + *allocated = ee_len - (map->m_lblk - ee_block); WARN_ON(map->m_lblk < ee_block); /* @@ -3631,9 +3610,6 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, max_zeroout = sbi->s_extent_max_zeroout_kb >> (inode->i_sb->s_blocksize_bits - 10); - if (ext4_encrypted_inode(inode)) - max_zeroout = 0; - /* * five cases: * 1. split the extent into three extents. @@ -3648,21 +3624,21 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, split_map.m_lblk = map->m_lblk; split_map.m_len = map->m_len; - if (max_zeroout && (allocated > split_map.m_len)) { - if (allocated <= max_zeroout) { + if (max_zeroout && (*allocated > split_map.m_len)) { + if (*allocated <= max_zeroout) { /* case 3 or 5 */ zero_ex1.ee_block = cpu_to_le32(split_map.m_lblk + split_map.m_len); zero_ex1.ee_len = - cpu_to_le16(allocated - split_map.m_len); + cpu_to_le16(*allocated - split_map.m_len); ext4_ext_store_pblock(&zero_ex1, ext4_ext_pblock(ex) + split_map.m_lblk + split_map.m_len - ee_block); err = ext4_ext_zeroout(inode, &zero_ex1); if (err) - goto out; - split_map.m_len = allocated; + goto fallback; + split_map.m_len = *allocated; } if (split_map.m_lblk - ee_block + split_map.m_len < max_zeroout) { @@ -3675,27 +3651,29 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, ext4_ext_pblock(ex)); err = ext4_ext_zeroout(inode, &zero_ex2); if (err) - goto out; + goto fallback; } split_map.m_len += split_map.m_lblk - ee_block; split_map.m_lblk = ee_block; - allocated = map->m_len; + *allocated = map->m_len; } } - err = ext4_split_extent(handle, inode, ppath, &split_map, split_flag, - flags); - if (err > 0) - err = 0; +fallback: + path = ext4_split_extent(handle, inode, path, &split_map, split_flag, + flags, NULL); + if (IS_ERR(path)) + return path; out: /* If we have gotten a failure, don't zero out status tree */ - if (!err) { - err = ext4_zeroout_es(inode, &zero_ex1); - if (!err) - err = ext4_zeroout_es(inode, &zero_ex2); - } - return err ? err : allocated; + ext4_zeroout_es(inode, &zero_ex1); + ext4_zeroout_es(inode, &zero_ex2); + return path; + +errout: + ext4_free_ext_path(path); + return ERR_PTR(err); } /* @@ -3720,33 +3698,29 @@ out: * being filled will be convert to initialized by the end_io callback function * via ext4_convert_unwritten_extents(). * - * Returns the size of unwritten extent to be written on success. + * The size of unwritten extent to be written is passed to the caller via the + * allocated pointer. Return an extent path pointer on success, or an error + * pointer on failure. */ -static int ext4_split_convert_extents(handle_t *handle, +static struct ext4_ext_path *ext4_split_convert_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, - struct ext4_ext_path **ppath, - int flags) + struct ext4_ext_path *path, + int flags, unsigned int *allocated) { - struct ext4_ext_path *path = *ppath; ext4_lblk_t eof_block; ext4_lblk_t ee_block; struct ext4_extent *ex; unsigned int ee_len; int split_flag = 0, depth; - ext_debug("%s: inode %lu, logical block %llu, max_blocks %u\n", - __func__, inode->i_ino, + ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)map->m_lblk, map->m_len); - eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >> - inode->i_sb->s_blocksize_bits; + eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) + >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map->m_len) eof_block = map->m_lblk + map->m_len; - /* - * It is safe to convert extent to initialized via explicit - * zeroout only if extent is fully insde i_size or new_size. - */ depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); @@ -3757,20 +3731,24 @@ static int ext4_split_convert_extents(handle_t *handle, split_flag |= EXT4_EXT_DATA_VALID1; /* Convert to initialized */ } else if (flags & EXT4_GET_BLOCKS_CONVERT) { + /* + * It is safe to convert extent to initialized via explicit + * zeroout only if extent is fully inside i_size or new_size. + */ split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0; split_flag |= (EXT4_EXT_MARK_UNWRIT2 | EXT4_EXT_DATA_VALID2); } - flags |= EXT4_GET_BLOCKS_PRE_IO; - return ext4_split_extent(handle, inode, ppath, map, split_flag, flags); + flags |= EXT4_GET_BLOCKS_SPLIT_NOMERGE; + return ext4_split_extent(handle, inode, path, map, split_flag, flags, + allocated); } -static int ext4_convert_unwritten_extents_endio(handle_t *handle, - struct inode *inode, - struct ext4_map_blocks *map, - struct ext4_ext_path **ppath) +static struct ext4_ext_path * +ext4_convert_unwritten_extents_endio(handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map, + struct ext4_ext_path *path) { - struct ext4_ext_path *path = *ppath; struct ext4_extent *ex; ext4_lblk_t ee_block; unsigned int ee_len; @@ -3782,8 +3760,7 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); - ext_debug("ext4_convert_unwritten_extents_endio: inode %lu, logical" - "block %llu, max_blocks %u\n", inode->i_ino, + ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)ee_block, ee_len); /* If extent is larger than requested it is a clear sign that we still @@ -3793,26 +3770,27 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, * illegal. */ if (ee_block != map->m_lblk || ee_len > map->m_len) { -#ifdef EXT4_DEBUG - ext4_warning("Inode (%ld) finished: extent logical block %llu," +#ifdef CONFIG_EXT4_DEBUG + ext4_warning(inode->i_sb, "Inode (%ld) finished: extent logical block %llu," " len %u; IO logical block %llu, len %u", inode->i_ino, (unsigned long long)ee_block, ee_len, (unsigned long long)map->m_lblk, map->m_len); #endif - err = ext4_split_convert_extents(handle, inode, map, ppath, - EXT4_GET_BLOCKS_CONVERT); - if (err < 0) - return err; - path = ext4_find_extent(inode, map->m_lblk, ppath, 0); + path = ext4_split_convert_extents(handle, inode, map, path, + EXT4_GET_BLOCKS_CONVERT, NULL); if (IS_ERR(path)) - return PTR_ERR(path); + return path; + + path = ext4_find_extent(inode, map->m_lblk, path, 0); + if (IS_ERR(path)) + return path; depth = ext_depth(inode); ex = path[depth].p_ext; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) - goto out; + goto errout; /* first mark the extent as initialized */ ext4_ext_mark_initialized(ex); @@ -3823,71 +3801,23 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, /* Mark modified extent as dirty */ err = ext4_ext_dirty(handle, inode, path + path->p_depth); -out: - ext4_ext_show_leaf(inode, path); - return err; -} - -/* - * Handle EOFBLOCKS_FL flag, clearing it if necessary - */ -static int check_eofblocks_fl(handle_t *handle, struct inode *inode, - ext4_lblk_t lblk, - struct ext4_ext_path *path, - unsigned int len) -{ - int i, depth; - struct ext4_extent_header *eh; - struct ext4_extent *last_ex; - - if (!ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)) - return 0; + if (err) + goto errout; - depth = ext_depth(inode); - eh = path[depth].p_hdr; + ext4_ext_show_leaf(inode, path); + return path; - /* - * We're going to remove EOFBLOCKS_FL entirely in future so we - * do not care for this case anymore. Simply remove the flag - * if there are no extents. - */ - if (unlikely(!eh->eh_entries)) - goto out; - last_ex = EXT_LAST_EXTENT(eh); - /* - * We should clear the EOFBLOCKS_FL flag if we are writing the - * last block in the last extent in the file. We test this by - * first checking to see if the caller to - * ext4_ext_get_blocks() was interested in the last block (or - * a block beyond the last block) in the current extent. If - * this turns out to be false, we can bail out from this - * function immediately. - */ - if (lblk + len < le32_to_cpu(last_ex->ee_block) + - ext4_ext_get_actual_len(last_ex)) - return 0; - /* - * If the caller does appear to be planning to write at or - * beyond the end of the current extent, we then test to see - * if the current extent is the last extent in the file, by - * checking to make sure it was reached via the rightmost node - * at each level of the tree. - */ - for (i = depth-1; i >= 0; i--) - if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr)) - return 0; -out: - ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS); - return ext4_mark_inode_dirty(handle, inode); +errout: + ext4_free_ext_path(path); + return ERR_PTR(err); } -static int +static struct ext4_ext_path * convert_initialized_extent(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, - struct ext4_ext_path **ppath, - unsigned int allocated) + struct ext4_ext_path *path, + unsigned int *allocated) { - struct ext4_ext_path *path = *ppath; struct ext4_extent *ex; ext4_lblk_t ee_block; unsigned int ee_len; @@ -3906,30 +3836,31 @@ convert_initialized_extent(handle_t *handle, struct inode *inode, ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); - ext_debug("%s: inode %lu, logical" - "block %llu, max_blocks %u\n", __func__, inode->i_ino, + ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)ee_block, ee_len); if (ee_block != map->m_lblk || ee_len > map->m_len) { - err = ext4_split_convert_extents(handle, inode, map, ppath, - EXT4_GET_BLOCKS_CONVERT_UNWRITTEN); - if (err < 0) - return err; - path = ext4_find_extent(inode, map->m_lblk, ppath, 0); + path = ext4_split_convert_extents(handle, inode, map, path, + EXT4_GET_BLOCKS_CONVERT_UNWRITTEN, NULL); if (IS_ERR(path)) - return PTR_ERR(path); + return path; + + path = ext4_find_extent(inode, map->m_lblk, path, 0); + if (IS_ERR(path)) + return path; depth = ext_depth(inode); ex = path[depth].p_ext; if (!ex) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) map->m_lblk); - return -EFSCORRUPTED; + err = -EFSCORRUPTED; + goto errout; } } err = ext4_ext_get_access(handle, inode, path + depth); if (err) - return err; + goto errout; /* first mark the extent as unwritten */ ext4_ext_mark_unwritten(ex); @@ -3941,34 +3872,33 @@ convert_initialized_extent(handle_t *handle, struct inode *inode, /* Mark modified extent as dirty */ err = ext4_ext_dirty(handle, inode, path + path->p_depth); if (err) - return err; + goto errout; ext4_ext_show_leaf(inode, path); ext4_update_inode_fsync_trans(handle, inode, 1); - err = check_eofblocks_fl(handle, inode, map->m_lblk, path, map->m_len); - if (err) - return err; + map->m_flags |= EXT4_MAP_UNWRITTEN; - if (allocated > map->m_len) - allocated = map->m_len; - map->m_len = allocated; - return allocated; + if (*allocated > map->m_len) + *allocated = map->m_len; + map->m_len = *allocated; + return path; + +errout: + ext4_free_ext_path(path); + return ERR_PTR(err); } -static int +static struct ext4_ext_path * ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, - struct ext4_ext_path **ppath, int flags, - unsigned int allocated, ext4_fsblk_t newblock) + struct ext4_ext_path *path, int flags, + unsigned int *allocated, ext4_fsblk_t newblock) { - struct ext4_ext_path *path = *ppath; - int ret = 0; int err = 0; - ext_debug("ext4_ext_handle_unwritten_extents: inode %lu, logical " - "block %llu, max_blocks %u, flags %x, allocated %u\n", - inode->i_ino, (unsigned long long)map->m_lblk, map->m_len, - flags, allocated); + ext_debug(inode, "logical block %llu, max_blocks %u, flags 0x%x, allocated %u\n", + (unsigned long long)map->m_lblk, map->m_len, flags, + *allocated); ext4_ext_show_leaf(inode, path); /* @@ -3978,43 +3908,38 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL; trace_ext4_ext_handle_unwritten_extents(inode, map, flags, - allocated, newblock); + *allocated, newblock); - /* get_block() before submit the IO, split the extent */ - if (flags & EXT4_GET_BLOCKS_PRE_IO) { - ret = ext4_split_convert_extents(handle, inode, map, ppath, - flags | EXT4_GET_BLOCKS_CONVERT); - if (ret <= 0) - goto out; + /* get_block() before submitting IO, split the extent */ + if (flags & EXT4_GET_BLOCKS_SPLIT_NOMERGE) { + path = ext4_split_convert_extents(handle, inode, map, path, + flags | EXT4_GET_BLOCKS_CONVERT, allocated); + if (IS_ERR(path)) + return path; + /* + * shouldn't get a 0 allocated when splitting an extent unless + * m_len is 0 (bug) or extent has been corrupted + */ + if (unlikely(*allocated == 0)) { + EXT4_ERROR_INODE(inode, + "unexpected allocated == 0, m_len = %u", + map->m_len); + err = -EFSCORRUPTED; + goto errout; + } map->m_flags |= EXT4_MAP_UNWRITTEN; goto out; } /* IO end_io complete, convert the filled extent to written */ if (flags & EXT4_GET_BLOCKS_CONVERT) { - if (flags & EXT4_GET_BLOCKS_ZERO) { - if (allocated > map->m_len) - allocated = map->m_len; - err = ext4_issue_zeroout(inode, map->m_lblk, newblock, - allocated); - if (err < 0) - goto out2; - } - ret = ext4_convert_unwritten_extents_endio(handle, inode, map, - ppath); - if (ret >= 0) { - ext4_update_inode_fsync_trans(handle, inode, 1); - err = check_eofblocks_fl(handle, inode, map->m_lblk, - path, map->m_len); - } else - err = ret; - map->m_flags |= EXT4_MAP_MAPPED; - map->m_pblk = newblock; - if (allocated > map->m_len) - allocated = map->m_len; - map->m_len = allocated; - goto out2; - } - /* buffered IO case */ + path = ext4_convert_unwritten_extents_endio(handle, inode, + map, path); + if (IS_ERR(path)) + return path; + ext4_update_inode_fsync_trans(handle, inode, 1); + goto map_out; + } + /* buffered IO cases */ /* * repeat fallocate creation request * we already have an unwritten extent @@ -4037,47 +3962,42 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, goto out1; } - /* buffered write, writepage time, convert*/ - ret = ext4_ext_convert_to_initialized(handle, inode, map, ppath, flags); - if (ret >= 0) - ext4_update_inode_fsync_trans(handle, inode, 1); -out: - if (ret <= 0) { - err = ret; - goto out2; - } else - allocated = ret; - map->m_flags |= EXT4_MAP_NEW; /* - * if we allocated more blocks than requested - * we need to make sure we unmap the extra block - * allocated. The actual needed block will get - * unmapped later when we find the buffer_head marked - * new. + * Default case when (flags & EXT4_GET_BLOCKS_CREATE) == 1. + * For buffered writes, at writepage time, etc. Convert a + * discovered unwritten extent to written. */ - if (allocated > map->m_len) { - clean_bdev_aliases(inode->i_sb->s_bdev, newblock + map->m_len, - allocated - map->m_len); - allocated = map->m_len; + path = ext4_ext_convert_to_initialized(handle, inode, map, path, + flags, allocated); + if (IS_ERR(path)) + return path; + ext4_update_inode_fsync_trans(handle, inode, 1); + /* + * shouldn't get a 0 allocated when converting an unwritten extent + * unless m_len is 0 (bug) or extent has been corrupted + */ + if (unlikely(*allocated == 0)) { + EXT4_ERROR_INODE(inode, "unexpected allocated == 0, m_len = %u", + map->m_len); + err = -EFSCORRUPTED; + goto errout; } - map->m_len = allocated; +out: + map->m_flags |= EXT4_MAP_NEW; map_out: map->m_flags |= EXT4_MAP_MAPPED; - if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) { - err = check_eofblocks_fl(handle, inode, map->m_lblk, path, - map->m_len); - if (err < 0) - goto out2; - } out1: - if (allocated > map->m_len) - allocated = map->m_len; - ext4_ext_show_leaf(inode, path); map->m_pblk = newblock; - map->m_len = allocated; -out2: - return err ? err : allocated; + if (*allocated > map->m_len) + *allocated = map->m_len; + map->m_len = *allocated; + ext4_ext_show_leaf(inode, path); + return path; + +errout: + ext4_free_ext_path(path); + return ERR_PTR(err); } /* @@ -4182,6 +4102,73 @@ static int get_implied_cluster_alloc(struct super_block *sb, return 0; } +/* + * Determine hole length around the given logical block, first try to + * locate and expand the hole from the given @path, and then adjust it + * if it's partially or completely converted to delayed extents, insert + * it into the extent cache tree if it's indeed a hole, finally return + * the length of the determined extent. + */ +static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t lblk) +{ + ext4_lblk_t hole_start, len; + struct extent_status es; + + hole_start = lblk; + len = ext4_ext_find_hole(inode, path, &hole_start); +again: + ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, + hole_start + len - 1, &es); + if (!es.es_len) + goto insert_hole; + + /* + * There's a delalloc extent in the hole, handle it if the delalloc + * extent is in front of, behind and straddle the queried range. + */ + if (lblk >= es.es_lblk + es.es_len) { + /* + * The delalloc extent is in front of the queried range, + * find again from the queried start block. + */ + len -= lblk - hole_start; + hole_start = lblk; + goto again; + } else if (in_range(lblk, es.es_lblk, es.es_len)) { + /* + * The delalloc extent containing lblk, it must have been + * added after ext4_map_blocks() checked the extent status + * tree so we are not holding i_rwsem and delalloc info is + * only stabilized by i_data_sem we are going to release + * soon. Don't modify the extent status tree and report + * extent as a hole, just adjust the length to the delalloc + * extent's after lblk. + */ + len = es.es_lblk + es.es_len - lblk; + return len; + } else { + /* + * The delalloc extent is partially or completely behind + * the queried range, update hole length until the + * beginning of the delalloc extent. + */ + len = min(es.es_lblk - hole_start, len); + } + +insert_hole: + /* Put just found gap into cache to speed up subsequent requests */ + ext_debug(inode, " -> %u:%u\n", hole_start, len); + ext4_es_insert_extent(inode, hole_start, len, ~0, + EXTENT_STATUS_HOLE, false); + + /* Update hole_len to reflect hole size after lblk */ + if (hole_start != lblk) + len -= lblk - hole_start; + + return len; +} /* * Block allocation/map/preallocation routine for extents based files @@ -4189,10 +4176,10 @@ static int get_implied_cluster_alloc(struct super_block *sb, * * Need to be called with * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block - * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem) + * (ie, flags is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem) * - * return > 0, number of of blocks already mapped/allocated - * if create == 0 and these are pre-allocated blocks + * return > 0, number of blocks already mapped/allocated + * if flags doesn't contain EXT4_GET_BLOCKS_CREATE and these are pre-allocated blocks * buffer head is unmapped * otherwise blocks are mapped * @@ -4205,26 +4192,23 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { struct ext4_ext_path *path = NULL; - struct ext4_extent newex, *ex, *ex2; + struct ext4_extent newex, *ex, ex2; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - ext4_fsblk_t newblock = 0; - int free_on_err = 0, err = 0, depth, ret; + ext4_fsblk_t newblock = 0, pblk; + int err = 0, depth; unsigned int allocated = 0, offset = 0; unsigned int allocated_clusters = 0; struct ext4_allocation_request ar; ext4_lblk_t cluster_offset; - bool map_from_cluster = false; - ext_debug("blocks %u/%u requested for inode %lu\n", - map->m_lblk, map->m_len, inode->i_ino); + ext_debug(inode, "blocks %u/%u requested\n", map->m_lblk, map->m_len); trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); /* find extent for this block */ - path = ext4_find_extent(inode, map->m_lblk, NULL, 0); + path = ext4_find_extent(inode, map->m_lblk, NULL, flags); if (IS_ERR(path)) { err = PTR_ERR(path); - path = NULL; - goto out2; + goto out; } depth = ext_depth(inode); @@ -4240,7 +4224,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, (unsigned long) map->m_lblk, depth, path[depth].p_block); err = -EFSCORRUPTED; - goto out2; + goto out; } ex = path[depth].p_ext; @@ -4263,8 +4247,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, newblock = map->m_lblk - ee_block + ee_start; /* number of remaining blocks in the extent */ allocated = ee_len - (map->m_lblk - ee_block); - ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk, - ee_block, ee_len, newblock); + ext_debug(inode, "%u fit into %u:%d -> %llu\n", + map->m_lblk, ee_block, ee_len, newblock); /* * If the extent is initialized check whether the @@ -4272,46 +4256,42 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, */ if ((!ext4_ext_is_unwritten(ex)) && (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) { - allocated = convert_initialized_extent( - handle, inode, map, &path, - allocated); - goto out2; - } else if (!ext4_ext_is_unwritten(ex)) + path = convert_initialized_extent(handle, + inode, map, path, &allocated); + if (IS_ERR(path)) + err = PTR_ERR(path); + goto out; + } else if (!ext4_ext_is_unwritten(ex)) { + map->m_flags |= EXT4_MAP_MAPPED; + map->m_pblk = newblock; + if (allocated > map->m_len) + allocated = map->m_len; + map->m_len = allocated; + ext4_ext_show_leaf(inode, path); goto out; + } - ret = ext4_ext_handle_unwritten_extents( - handle, inode, map, &path, flags, - allocated, newblock); - if (ret < 0) - err = ret; - else - allocated = ret; - goto out2; + path = ext4_ext_handle_unwritten_extents( + handle, inode, map, path, flags, + &allocated, newblock); + if (IS_ERR(path)) + err = PTR_ERR(path); + goto out; } } /* * requested block isn't allocated yet; - * we couldn't try to create block if create flag is zero + * we couldn't try to create block if flags doesn't contain EXT4_GET_BLOCKS_CREATE */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { - ext4_lblk_t hole_start, hole_len; + ext4_lblk_t len; - hole_start = map->m_lblk; - hole_len = ext4_ext_determine_hole(inode, path, &hole_start); - /* - * put just found gap into cache to speed up - * subsequent requests - */ - ext4_ext_put_gap_in_cache(inode, hole_start, hole_len); + len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk); - /* Update hole_len to reflect hole size after map->m_lblk */ - if (hole_start != map->m_lblk) - hole_len -= map->m_lblk - hole_start; map->m_pblk = 0; - map->m_len = min_t(unsigned int, map->m_len, hole_len); - - goto out2; + map->m_len = min_t(unsigned int, map->m_len, len); + goto out; } /* @@ -4328,7 +4308,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, get_implied_cluster_alloc(inode->i_sb, map, ex, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; - map_from_cluster = true; goto got_allocated_blocks; } @@ -4336,20 +4315,20 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ar.lleft = map->m_lblk; err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft); if (err) - goto out2; + goto out; ar.lright = map->m_lblk; - ex2 = NULL; - err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2); - if (err) - goto out2; + err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, + &ex2, flags); + if (err < 0) + goto out; /* Check if the extent after searching to the right implies a * cluster we can use. */ - if ((sbi->s_cluster_ratio > 1) && ex2 && - get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) { + if ((sbi->s_cluster_ratio > 1) && err && + get_implied_cluster_alloc(inode->i_sb, map, &ex2, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; - map_from_cluster = true; + err = 0; goto got_allocated_blocks; } @@ -4403,87 +4382,44 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ar.flags |= EXT4_MB_USE_RESERVED; newblock = ext4_mb_new_blocks(handle, &ar, &err); if (!newblock) - goto out2; - ext_debug("allocate new block: goal %llu, found %llu/%u\n", - ar.goal, newblock, allocated); - free_on_err = 1; + goto out; allocated_clusters = ar.len; ar.len = EXT4_C2B(sbi, ar.len) - offset; + ext_debug(inode, "allocate new block: goal %llu, found %llu/%u, requested %u\n", + ar.goal, newblock, ar.len, allocated); if (ar.len > allocated) ar.len = allocated; got_allocated_blocks: /* try to insert new extent into found leaf and return */ - ext4_ext_store_pblock(&newex, newblock + offset); + pblk = newblock + offset; + ext4_ext_store_pblock(&newex, pblk); newex.ee_len = cpu_to_le16(ar.len); /* Mark unwritten */ - if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT){ + if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) { ext4_ext_mark_unwritten(&newex); map->m_flags |= EXT4_MAP_UNWRITTEN; } - err = 0; - if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) - err = check_eofblocks_fl(handle, inode, map->m_lblk, - path, ar.len); - if (!err) - err = ext4_ext_insert_extent(handle, inode, &path, - &newex, flags); - - if (err && free_on_err) { - int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ? - EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0; - /* free data blocks we just allocated */ - /* not a good idea to call discard here directly, - * but otherwise we'd need to call it every free() */ - ext4_discard_preallocations(inode); - ext4_free_blocks(handle, inode, NULL, newblock, - EXT4_C2B(sbi, allocated_clusters), fb_flags); - goto out2; - } - - /* previous routine could use block we allocated */ - newblock = ext4_ext_pblock(&newex); - allocated = ext4_ext_get_actual_len(&newex); - if (allocated > map->m_len) - allocated = map->m_len; - map->m_flags |= EXT4_MAP_NEW; - - /* - * Reduce the reserved cluster count to reflect successful deferred - * allocation of delayed allocated clusters or direct allocation of - * clusters discovered to be delayed allocated. Once allocated, a - * cluster is not included in the reserved count. - */ - if (test_opt(inode->i_sb, DELALLOC) && !map_from_cluster) { - if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { - /* - * When allocating delayed allocated clusters, simply - * reduce the reserved cluster count and claim quota - */ - ext4_da_update_reserve_space(inode, allocated_clusters, - 1); - } else { - ext4_lblk_t lblk, len; - unsigned int n; + path = ext4_ext_insert_extent(handle, inode, path, &newex, flags); + if (IS_ERR(path)) { + err = PTR_ERR(path); + if (allocated_clusters) { + int fb_flags = 0; /* - * When allocating non-delayed allocated clusters - * (from fallocate, filemap, DIO, or clusters - * allocated when delalloc has been disabled by - * ext4_nonda_switch), reduce the reserved cluster - * count by the number of allocated clusters that - * have previously been delayed allocated. Quota - * has been claimed by ext4_mb_new_blocks() above, - * so release the quota reservations made for any - * previously delayed allocated clusters. + * free data blocks we just allocated. + * not a good idea to call discard here directly, + * but otherwise we'd need to call it every free(). */ - lblk = EXT4_LBLK_CMASK(sbi, map->m_lblk); - len = allocated_clusters << sbi->s_cluster_bits; - n = ext4_es_delayed_clu(inode, lblk, len); - if (n > 0) - ext4_da_update_reserve_space(inode, (int) n, 0); + ext4_discard_preallocations(inode); + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) + fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE; + ext4_free_blocks(handle, inode, NULL, newblock, + EXT4_C2B(sbi, allocated_clusters), + fb_flags); } + goto out; } /* @@ -4494,16 +4430,28 @@ got_allocated_blocks: ext4_update_inode_fsync_trans(handle, inode, 1); else ext4_update_inode_fsync_trans(handle, inode, 0); -out: - if (allocated > map->m_len) - allocated = map->m_len; + + map->m_flags |= (EXT4_MAP_NEW | EXT4_MAP_MAPPED); + map->m_pblk = pblk; + map->m_len = ar.len; + allocated = map->m_len; ext4_ext_show_leaf(inode, path); - map->m_flags |= EXT4_MAP_MAPPED; - map->m_pblk = newblock; - map->m_len = allocated; -out2: - ext4_ext_drop_refs(path); - kfree(path); +out: + /* + * We never use EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF with CREATE flag. + * So we know that the depth used here is correct, since there was no + * block allocation done if EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF is set. + * If tomorrow we start using this QUERY flag with CREATE, then we will + * need to re-calculate the depth as it might have changed due to block + * allocation. + */ + if (flags & EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF) { + WARN_ON_ONCE(flags & EXT4_GET_BLOCKS_CREATE); + if (!err && ex && (ex == EXT_LAST_EXTENT(path[depth].p_hdr))) + map->m_flags |= EXT4_MAP_QUERY_LAST_IN_LEAF; + } + + ext4_free_ext_path(path); trace_ext4_ext_map_blocks_exit(inode, flags, map, err ? err : allocated); @@ -4530,17 +4478,15 @@ int ext4_ext_truncate(handle_t *handle, struct inode *inode) last_block = (inode->i_size + sb->s_blocksize - 1) >> EXT4_BLOCK_SIZE_BITS(sb); -retry: - err = ext4_es_remove_extent(inode, last_block, - EXT_MAX_BLOCKS - last_block); + ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); + +retry_remove_space: + err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); if (err == -ENOMEM) { - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); - goto retry; + memalloc_retry_wait(GFP_ATOMIC); + goto retry_remove_space; } - if (err) - return err; - return ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); + return err; } static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, @@ -4549,13 +4495,14 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, { struct inode *inode = file_inode(file); handle_t *handle; - int ret = 0; - int ret2 = 0; + int ret = 0, ret2 = 0, ret3 = 0; int retries = 0; int depth = 0; struct ext4_map_blocks map; unsigned int credits; - loff_t epos; + loff_t epos, old_size = i_size_read(inode); + unsigned int blkbits = inode->i_blkbits; + bool alloc_zero = false; BUG_ON(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)); map.m_lblk = offset; @@ -4569,13 +4516,24 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, flags |= EXT4_GET_BLOCKS_NO_NORMALIZE; /* + * Do the actual write zero during a running journal transaction + * costs a lot. First allocate an unwritten extent and then + * convert it to written after zeroing it out. + */ + if (flags & EXT4_GET_BLOCKS_ZERO) { + flags &= ~EXT4_GET_BLOCKS_ZERO; + flags |= EXT4_GET_BLOCKS_UNWRIT_EXT; + alloc_zero = true; + } + + /* * credits to insert 1 extent into extent tree */ credits = ext4_chunk_trans_blocks(inode, len); depth = ext_depth(inode); retry: - while (ret >= 0 && len) { + while (len) { /* * Recalculate credits when extent tree depth changes. */ @@ -4597,158 +4555,126 @@ retry: inode->i_ino, map.m_lblk, map.m_len, ret); ext4_mark_inode_dirty(handle, inode); - ret2 = ext4_journal_stop(handle); + ext4_journal_stop(handle); break; } - map.m_lblk += ret; - map.m_len = len = len - ret; - epos = (loff_t)map.m_lblk << inode->i_blkbits; - inode->i_ctime = current_time(inode); + /* + * allow a full retry cycle for any remaining allocations + */ + retries = 0; + epos = EXT4_LBLK_TO_B(inode, map.m_lblk + ret); + inode_set_ctime_current(inode); if (new_size) { if (epos > new_size) epos = new_size; if (ext4_update_inode_size(inode, epos) & 0x1) - inode->i_mtime = inode->i_ctime; - } else { - if (epos > inode->i_size) - ext4_set_inode_flag(inode, - EXT4_INODE_EOFBLOCKS); + inode_set_mtime_to_ts(inode, + inode_get_ctime(inode)); + if (epos > old_size) { + pagecache_isize_extended(inode, old_size, epos); + ext4_zero_partial_blocks(handle, inode, + old_size, epos - old_size); + } } - ext4_mark_inode_dirty(handle, inode); + ret2 = ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); - ret2 = ext4_journal_stop(handle); - if (ret2) + ret3 = ext4_journal_stop(handle); + ret2 = ret3 ? ret3 : ret2; + if (unlikely(ret2)) break; + + if (alloc_zero && + (map.m_flags & (EXT4_MAP_MAPPED | EXT4_MAP_UNWRITTEN))) { + ret2 = ext4_issue_zeroout(inode, map.m_lblk, map.m_pblk, + map.m_len); + if (likely(!ret2)) + ret2 = ext4_convert_unwritten_extents(NULL, + inode, (loff_t)map.m_lblk << blkbits, + (loff_t)map.m_len << blkbits); + if (ret2) + break; + } + + map.m_lblk += ret; + map.m_len = len = len - ret; } - if (ret == -ENOSPC && - ext4_should_retry_alloc(inode->i_sb, &retries)) { - ret = 0; + if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; - } return ret > 0 ? ret2 : ret; } +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len); + +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len); + static long ext4_zero_range(struct file *file, loff_t offset, loff_t len, int mode) { struct inode *inode = file_inode(file); handle_t *handle = NULL; - unsigned int max_blocks; loff_t new_size = 0; - int ret = 0; - int flags; - int credits; - int partial_begin, partial_end; - loff_t start, end; - ext4_lblk_t lblk; + loff_t end = offset + len; + ext4_lblk_t start_lblk, end_lblk; + unsigned int blocksize = i_blocksize(inode); unsigned int blkbits = inode->i_blkbits; + int ret, flags, credits; trace_ext4_zero_range(inode, offset, len, mode); + WARN_ON_ONCE(!inode_is_locked(inode)); - if (!S_ISREG(inode->i_mode)) - return -EINVAL; - - /* Call ext4_force_commit to flush all data in case of data=journal. */ - if (ext4_should_journal_data(inode)) { - ret = ext4_force_commit(inode->i_sb); - if (ret) - return ret; - } - - /* - * Round up offset. This is not fallocate, we neet to zero out - * blocks, so convert interior block aligned part of the range to - * unwritten and possibly manually zero out unaligned parts of the - * range. - */ - start = round_up(offset, 1 << blkbits); - end = round_down((offset + len), 1 << blkbits); - - if (start < offset || end > offset + len) - return -EINVAL; - partial_begin = offset & ((1 << blkbits) - 1); - partial_end = (offset + len) & ((1 << blkbits) - 1); - - lblk = start >> blkbits; - max_blocks = (end >> blkbits); - if (max_blocks < lblk) - max_blocks = 0; - else - max_blocks -= lblk; - - inode_lock(inode); - - /* - * Indirect files do not support unwritten extnets - */ - if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { - ret = -EOPNOTSUPP; - goto out_mutex; - } + /* Indirect files do not support unwritten extents */ + if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) + return -EOPNOTSUPP; if (!(mode & FALLOC_FL_KEEP_SIZE) && - (offset + len > i_size_read(inode) || - offset + len > EXT4_I(inode)->i_disksize)) { - new_size = offset + len; + (end > inode->i_size || end > EXT4_I(inode)->i_disksize)) { + new_size = end; ret = inode_newsize_ok(inode, new_size); if (ret) - goto out_mutex; + return ret; } flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; - if (mode & FALLOC_FL_KEEP_SIZE) - flags |= EXT4_GET_BLOCKS_KEEP_SIZE; - - /* Wait all existing dio workers, newcomers will block on i_mutex */ - inode_dio_wait(inode); - /* Preallocate the range including the unaligned edges */ - if (partial_begin || partial_end) { - ret = ext4_alloc_file_blocks(file, - round_down(offset, 1 << blkbits) >> blkbits, - (round_up((offset + len), 1 << blkbits) - - round_down(offset, 1 << blkbits)) >> blkbits, - new_size, flags); - if (ret) - goto out_mutex; + if (!IS_ALIGNED(offset | end, blocksize)) { + ext4_lblk_t alloc_lblk = offset >> blkbits; + ext4_lblk_t len_lblk = EXT4_MAX_BLOCKS(len, offset, blkbits); + ret = ext4_alloc_file_blocks(file, alloc_lblk, len_lblk, + new_size, flags); + if (ret) + return ret; } - /* Zero range excluding the unaligned edges */ - if (max_blocks > 0) { - flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | - EXT4_EX_NOCACHE); - - /* - * Prevent page faults from reinstantiating pages we have - * released from page cache. - */ - down_write(&EXT4_I(inode)->i_mmap_sem); + ret = ext4_update_disksize_before_punch(inode, offset, len); + if (ret) + return ret; - ret = ext4_break_layouts(inode); - if (ret) { - up_write(&EXT4_I(inode)->i_mmap_sem); - goto out_mutex; - } + /* Now release the pages and zero block aligned part of pages */ + ret = ext4_truncate_page_cache_block_range(inode, offset, end); + if (ret) + return ret; - ret = ext4_update_disksize_before_punch(inode, offset, len); - if (ret) { - up_write(&EXT4_I(inode)->i_mmap_sem); - goto out_mutex; - } - /* Now release the pages and zero block aligned part of pages */ - truncate_pagecache_range(inode, start, end - 1); - inode->i_mtime = inode->i_ctime = current_time(inode); + /* Zero range excluding the unaligned edges */ + start_lblk = EXT4_B_TO_LBLK(inode, offset); + end_lblk = end >> blkbits; + if (end_lblk > start_lblk) { + ext4_lblk_t zero_blks = end_lblk - start_lblk; - ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, - flags); - up_write(&EXT4_I(inode)->i_mmap_sem); + if (mode & FALLOC_FL_WRITE_ZEROES) + flags = EXT4_GET_BLOCKS_CREATE_ZERO | EXT4_EX_NOCACHE; + else + flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | + EXT4_EX_NOCACHE); + ret = ext4_alloc_file_blocks(file, start_lblk, zero_blks, + new_size, flags); if (ret) - goto out_mutex; + return ret; } - if (!partial_begin && !partial_end) - goto out_mutex; + /* Finish zeroing out if it doesn't contain partial block */ + if (IS_ALIGNED(offset | end, blocksize)) + return ret; /* * In worst case we have to writeout two nonadjacent unwritten @@ -4761,33 +4687,69 @@ static long ext4_zero_range(struct file *file, loff_t offset, if (IS_ERR(handle)) { ret = PTR_ERR(handle); ext4_std_error(inode->i_sb, ret); - goto out_mutex; - } - - inode->i_mtime = inode->i_ctime = current_time(inode); - if (new_size) { - ext4_update_inode_size(inode, new_size); - } else { - /* - * Mark that we allocate beyond EOF so the subsequent truncate - * can proceed even if the new size is the same as i_size. - */ - if ((offset + len) > i_size_read(inode)) - ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS); + return ret; } - ext4_mark_inode_dirty(handle, inode); /* Zero out partial block at the edges of the range */ ret = ext4_zero_partial_blocks(handle, inode, offset, len); - if (ret >= 0) - ext4_update_inode_fsync_trans(handle, inode, 1); + if (ret) + goto out_handle; + + if (new_size) + ext4_update_inode_size(inode, new_size); + ret = ext4_mark_inode_dirty(handle, inode); + if (unlikely(ret)) + goto out_handle; + ext4_update_inode_fsync_trans(handle, inode, 1); if (file->f_flags & O_SYNC) ext4_handle_sync(handle); +out_handle: ext4_journal_stop(handle); -out_mutex: - inode_unlock(inode); + return ret; +} + +static long ext4_do_fallocate(struct file *file, loff_t offset, + loff_t len, int mode) +{ + struct inode *inode = file_inode(file); + loff_t end = offset + len; + loff_t new_size = 0; + ext4_lblk_t start_lblk, len_lblk; + int ret; + + trace_ext4_fallocate_enter(inode, offset, len, mode); + WARN_ON_ONCE(!inode_is_locked(inode)); + + start_lblk = offset >> inode->i_blkbits; + len_lblk = EXT4_MAX_BLOCKS(len, offset, inode->i_blkbits); + + /* We only support preallocation for extent-based files only. */ + if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { + ret = -EOPNOTSUPP; + goto out; + } + + if (!(mode & FALLOC_FL_KEEP_SIZE) && + (end > inode->i_size || end > EXT4_I(inode)->i_disksize)) { + new_size = end; + ret = inode_newsize_ok(inode, new_size); + if (ret) + goto out; + } + + ret = ext4_alloc_file_blocks(file, start_lblk, len_lblk, new_size, + EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT); + if (ret) + goto out; + + if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) { + ret = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal, + EXT4_I(inode)->i_sync_tid); + } +out: + trace_ext4_fallocate_exit(inode, offset, len_lblk, ret); return ret; } @@ -4801,92 +4763,170 @@ out_mutex: long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); - loff_t new_size = 0; - unsigned int max_blocks; - int ret = 0; - int flags; - ext4_lblk_t lblk; - unsigned int blkbits = inode->i_blkbits; + struct address_space *mapping = file->f_mapping; + int ret; /* * Encrypted inodes can't handle collapse range or insert * range since we would need to re-encrypt blocks with a * different IV or XTS tweak (which are based on the logical * block number). - * - * XXX It's not clear why zero range isn't working, but we'll - * leave it disabled for encrypted inodes for now. This is a - * bug we should fix.... */ - if (ext4_encrypted_inode(inode) && - (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE | - FALLOC_FL_ZERO_RANGE))) + if (IS_ENCRYPTED(inode) && + (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))) + return -EOPNOTSUPP; + /* + * Don't allow writing zeroes if the underlying device does not + * enable the unmap write zeroes operation. + */ + if ((mode & FALLOC_FL_WRITE_ZEROES) && + !bdev_write_zeroes_unmap_sectors(inode->i_sb->s_bdev)) return -EOPNOTSUPP; /* Return error if mode is not supported */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | - FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | - FALLOC_FL_INSERT_RANGE)) + FALLOC_FL_ZERO_RANGE | FALLOC_FL_COLLAPSE_RANGE | + FALLOC_FL_INSERT_RANGE | FALLOC_FL_WRITE_ZEROES)) return -EOPNOTSUPP; - if (mode & FALLOC_FL_PUNCH_HOLE) - return ext4_punch_hole(inode, offset, len); - + inode_lock(inode); ret = ext4_convert_inline_data(inode); if (ret) - return ret; - - if (mode & FALLOC_FL_COLLAPSE_RANGE) - return ext4_collapse_range(inode, offset, len); + goto out_inode_lock; - if (mode & FALLOC_FL_INSERT_RANGE) - return ext4_insert_range(inode, offset, len); - - if (mode & FALLOC_FL_ZERO_RANGE) - return ext4_zero_range(file, offset, len, mode); - - trace_ext4_fallocate_enter(inode, offset, len, mode); - lblk = offset >> blkbits; + /* Wait all existing dio workers, newcomers will block on i_rwsem */ + inode_dio_wait(inode); - max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); - flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; - if (mode & FALLOC_FL_KEEP_SIZE) - flags |= EXT4_GET_BLOCKS_KEEP_SIZE; + ret = file_modified(file); + if (ret) + goto out_inode_lock; - inode_lock(inode); + if ((mode & FALLOC_FL_MODE_MASK) == FALLOC_FL_ALLOCATE_RANGE) { + ret = ext4_do_fallocate(file, offset, len, mode); + goto out_inode_lock; + } /* - * We only support preallocation for extent-based files only + * Follow-up operations will drop page cache, hold invalidate lock + * to prevent page faults from reinstantiating pages we have + * released from page cache. */ - if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { + filemap_invalidate_lock(mapping); + + ret = ext4_break_layouts(inode); + if (ret) + goto out_invalidate_lock; + + switch (mode & FALLOC_FL_MODE_MASK) { + case FALLOC_FL_PUNCH_HOLE: + ret = ext4_punch_hole(file, offset, len); + break; + case FALLOC_FL_COLLAPSE_RANGE: + ret = ext4_collapse_range(file, offset, len); + break; + case FALLOC_FL_INSERT_RANGE: + ret = ext4_insert_range(file, offset, len); + break; + case FALLOC_FL_ZERO_RANGE: + case FALLOC_FL_WRITE_ZEROES: + ret = ext4_zero_range(file, offset, len, mode); + break; + default: ret = -EOPNOTSUPP; - goto out; } - if (!(mode & FALLOC_FL_KEEP_SIZE) && - (offset + len > i_size_read(inode) || - offset + len > EXT4_I(inode)->i_disksize)) { - new_size = offset + len; - ret = inode_newsize_ok(inode, new_size); - if (ret) - goto out; +out_invalidate_lock: + filemap_invalidate_unlock(mapping); +out_inode_lock: + inode_unlock(inode); + return ret; +} + +/* + * This function converts a range of blocks to written extents. The caller of + * this function will pass the start offset and the size. all unwritten extents + * within this range will be converted to written extents. + * + * This function is called from the direct IO end io call back function for + * atomic writes, to convert the unwritten extents after IO is completed. + * + * Note that the requirement for atomic writes is that all conversion should + * happen atomically in a single fs journal transaction. We mainly only allocate + * unwritten extents either on a hole on a pre-exiting unwritten extent range in + * ext4_map_blocks_atomic_write(). The only case where we can have multiple + * unwritten extents in a range [offset, offset+len) is when there is a split + * unwritten extent between two leaf nodes which was cached in extent status + * cache during ext4_iomap_alloc() time. That will allow + * ext4_map_blocks_atomic_write() to return the unwritten extent range w/o going + * into the slow path. That means we might need a loop for conversion of this + * unwritten extent split across leaf block within a single journal transaction. + * Split extents across leaf nodes is a rare case, but let's still handle that + * to meet the requirements of multi-fsblock atomic writes. + * + * Returns 0 on success. + */ +int ext4_convert_unwritten_extents_atomic(handle_t *handle, struct inode *inode, + loff_t offset, ssize_t len) +{ + unsigned int max_blocks; + int ret = 0, ret2 = 0, ret3 = 0; + struct ext4_map_blocks map; + unsigned int blkbits = inode->i_blkbits; + unsigned int credits = 0; + int flags = EXT4_GET_BLOCKS_IO_CONVERT_EXT | EXT4_EX_NOCACHE; + + map.m_lblk = offset >> blkbits; + max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); + + if (!handle) { + /* + * TODO: An optimization can be added later by having an extent + * status flag e.g. EXTENT_STATUS_SPLIT_LEAF. If we query that + * it can tell if the extent in the cache is a split extent. + * But for now let's assume pextents as 2 always. + */ + credits = ext4_meta_trans_blocks(inode, max_blocks, 2); } - /* Wait all existing dio workers, newcomers will block on i_mutex */ - inode_dio_wait(inode); + if (credits) { + handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + return ret; + } + } - ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); - if (ret) - goto out; + while (ret >= 0 && ret < max_blocks) { + map.m_lblk += ret; + map.m_len = (max_blocks -= ret); + ret = ext4_map_blocks(handle, inode, &map, flags); + if (ret != max_blocks) + ext4_msg(inode->i_sb, KERN_INFO, + "inode #%lu: block %u: len %u: " + "split block mapping found for atomic write, " + "ret = %d", + inode->i_ino, map.m_lblk, + map.m_len, ret); + if (ret <= 0) + break; + } - if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) { - ret = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal, - EXT4_I(inode)->i_sync_tid); + ret2 = ext4_mark_inode_dirty(handle, inode); + + if (credits) { + ret3 = ext4_journal_stop(handle); + if (unlikely(ret3)) + ret2 = ret3; } -out: - inode_unlock(inode); - trace_ext4_fallocate_exit(inode, offset, max_blocks, ret); - return ret; + + if (ret <= 0 || ret2) + ext4_warning(inode->i_sb, + "inode #%lu: block %u: len %u: " + "returned %d or %d", + inode->i_ino, map.m_lblk, + map.m_len, ret, ret2); + + return ret > 0 ? ret2 : ret; } /* @@ -4903,26 +4943,15 @@ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, loff_t offset, ssize_t len) { unsigned int max_blocks; - int ret = 0; - int ret2 = 0; + int ret = 0, ret2 = 0, ret3 = 0; struct ext4_map_blocks map; - unsigned int credits, blkbits = inode->i_blkbits; + unsigned int blkbits = inode->i_blkbits; + unsigned int credits = 0; map.m_lblk = offset >> blkbits; max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); - /* - * This is somewhat ugly but the idea is clear: When transaction is - * reserved, everything goes into it. Otherwise we rather start several - * smaller transactions for conversion of each extent separately. - */ - if (handle) { - handle = ext4_journal_start_reserved(handle, - EXT4_HT_EXT_CONVERT); - if (IS_ERR(handle)) - return PTR_ERR(handle); - credits = 0; - } else { + if (!handle) { /* * credits to insert 1 extent into extent tree */ @@ -4939,85 +4968,71 @@ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, break; } } + /* + * Do not cache any unrelated extents, as it does not hold the + * i_rwsem or invalidate_lock, which could corrupt the extent + * status tree. + */ ret = ext4_map_blocks(handle, inode, &map, - EXT4_GET_BLOCKS_IO_CONVERT_EXT); + EXT4_GET_BLOCKS_IO_CONVERT_EXT | + EXT4_EX_NOCACHE); if (ret <= 0) ext4_warning(inode->i_sb, "inode #%lu: block %u: len %u: " "ext4_ext_map_blocks returned %d", inode->i_ino, map.m_lblk, map.m_len, ret); - ext4_mark_inode_dirty(handle, inode); - if (credits) - ret2 = ext4_journal_stop(handle); + ret2 = ext4_mark_inode_dirty(handle, inode); + if (credits) { + ret3 = ext4_journal_stop(handle); + if (unlikely(ret3)) + ret2 = ret3; + } + if (ret <= 0 || ret2) break; } - if (!credits) - ret2 = ext4_journal_stop(handle); return ret > 0 ? ret2 : ret; } -/* - * If newes is not existing extent (newes->ec_pblk equals zero) find - * delayed extent at start of newes and update newes accordingly and - * return start of the next delayed extent. - * - * If newes is existing extent (newes->ec_pblk is not equal zero) - * return start of next delayed extent or EXT_MAX_BLOCKS if no delayed - * extent found. Leave newes unmodified. - */ -static int ext4_find_delayed_extent(struct inode *inode, - struct extent_status *newes) +int ext4_convert_unwritten_io_end_vec(handle_t *handle, ext4_io_end_t *io_end) { - struct extent_status es; - ext4_lblk_t block, next_del; - - if (newes->es_pblk == 0) { - ext4_es_find_extent_range(inode, &ext4_es_is_delayed, - newes->es_lblk, - newes->es_lblk + newes->es_len - 1, - &es); - - /* - * No extent in extent-tree contains block @newes->es_pblk, - * then the block may stay in 1)a hole or 2)delayed-extent. - */ - if (es.es_len == 0) - /* A hole found. */ - return 0; + int ret = 0, err = 0; + struct ext4_io_end_vec *io_end_vec; - if (es.es_lblk > newes->es_lblk) { - /* A hole found. */ - newes->es_len = min(es.es_lblk - newes->es_lblk, - newes->es_len); - return 0; - } + /* + * This is somewhat ugly but the idea is clear: When transaction is + * reserved, everything goes into it. Otherwise we rather start several + * smaller transactions for conversion of each extent separately. + */ + if (handle) { + handle = ext4_journal_start_reserved(handle, + EXT4_HT_EXT_CONVERT); + if (IS_ERR(handle)) + return PTR_ERR(handle); + } - newes->es_len = es.es_lblk + es.es_len - newes->es_lblk; + list_for_each_entry(io_end_vec, &io_end->list_vec, list) { + ret = ext4_convert_unwritten_extents(handle, io_end->inode, + io_end_vec->offset, + io_end_vec->size); + if (ret) + break; } - block = newes->es_lblk + newes->es_len; - ext4_es_find_extent_range(inode, &ext4_es_is_delayed, block, - EXT_MAX_BLOCKS, &es); - if (es.es_len == 0) - next_del = EXT_MAX_BLOCKS; - else - next_del = es.es_lblk; + if (handle) + err = ext4_journal_stop(handle); - return next_del; + return ret < 0 ? ret : err; } -/* fiemap flags we can handle specified here */ -#define EXT4_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR) -static int ext4_xattr_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo) +static int ext4_iomap_xattr_fiemap(struct inode *inode, struct iomap *iomap) { __u64 physical = 0; - __u64 length; - __u32 flags = FIEMAP_EXTENT_LAST; + __u64 length = 0; int blockbits = inode->i_sb->s_blocksize_bits; int error = 0; + u16 iomap_type; /* in-inode? */ if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { @@ -5032,102 +5047,140 @@ static int ext4_xattr_fiemap(struct inode *inode, EXT4_I(inode)->i_extra_isize; physical += offset; length = EXT4_SB(inode->i_sb)->s_inode_size - offset; - flags |= FIEMAP_EXTENT_DATA_INLINE; brelse(iloc.bh); - } else { /* external block */ + iomap_type = IOMAP_INLINE; + } else if (EXT4_I(inode)->i_file_acl) { /* external block */ physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits; length = inode->i_sb->s_blocksize; + iomap_type = IOMAP_MAPPED; + } else { + /* no in-inode or external block for xattr, so return -ENOENT */ + error = -ENOENT; + goto out; } - if (physical) - error = fiemap_fill_next_extent(fieinfo, 0, physical, - length, flags); - return (error < 0 ? error : 0); + iomap->addr = physical; + iomap->offset = 0; + iomap->length = length; + iomap->type = iomap_type; + iomap->flags = 0; +out: + return error; } -int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, - __u64 start, __u64 len) +static int ext4_iomap_xattr_begin(struct inode *inode, loff_t offset, + loff_t length, unsigned flags, + struct iomap *iomap, struct iomap *srcmap) { - ext4_lblk_t start_blk; - int error = 0; + int error; - if (ext4_has_inline_data(inode)) { - int has_inline = 1; + error = ext4_iomap_xattr_fiemap(inode, iomap); + if (error == 0 && (offset >= iomap->length)) + error = -ENOENT; + return error; +} - error = ext4_inline_data_fiemap(inode, fieinfo, &has_inline, - start, len); +static const struct iomap_ops ext4_iomap_xattr_ops = { + .iomap_begin = ext4_iomap_xattr_begin, +}; - if (has_inline) - return error; - } +static int ext4_fiemap_check_ranges(struct inode *inode, u64 start, u64 *len) +{ + u64 maxbytes = ext4_get_maxbytes(inode); + if (*len == 0) + return -EINVAL; + if (start > maxbytes) + return -EFBIG; + + /* + * Shrink request scope to what the fs can actually handle. + */ + if (*len > maxbytes || (maxbytes - *len) < start) + *len = maxbytes - start; + return 0; +} + +int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len) +{ + int error = 0; + + inode_lock_shared(inode); if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { error = ext4_ext_precache(inode); if (error) - return error; + goto unlock; + fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; } - /* fallback to generic here if not in extents fmt */ - if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) - return generic_block_fiemap(inode, fieinfo, start, len, - ext4_get_block); - - if (fiemap_check_flags(fieinfo, EXT4_FIEMAP_FLAGS)) - return -EBADR; + /* + * For bitmap files the maximum size limit could be smaller than + * s_maxbytes, so check len here manually instead of just relying on the + * generic check. + */ + error = ext4_fiemap_check_ranges(inode, start, &len); + if (error) + goto unlock; if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) { - error = ext4_xattr_fiemap(inode, fieinfo); + fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR; + error = iomap_fiemap(inode, fieinfo, start, len, + &ext4_iomap_xattr_ops); } else { - ext4_lblk_t len_blks; - __u64 last_blk; - - start_blk = start >> inode->i_sb->s_blocksize_bits; - last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits; - if (last_blk >= EXT_MAX_BLOCKS) - last_blk = EXT_MAX_BLOCKS-1; - len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1; - - /* - * Walk the extent tree gathering extent information - * and pushing extents back to the user. - */ - error = ext4_fill_fiemap_extents(inode, start_blk, - len_blks, fieinfo); + error = iomap_fiemap(inode, fieinfo, start, len, + &ext4_iomap_report_ops); } +unlock: + inode_unlock_shared(inode); return error; } -/* - * ext4_access_path: - * Function to access the path buffer for marking it dirty. - * It also checks if there are sufficient credits left in the journal handle - * to update path. - */ -static int -ext4_access_path(handle_t *handle, struct inode *inode, - struct ext4_ext_path *path) +int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo, + __u64 start, __u64 len) { - int credits, err; + ext4_lblk_t start_blk, len_blks; + __u64 last_blk; + int error = 0; - if (!ext4_handle_valid(handle)) - return 0; + if (ext4_has_inline_data(inode)) { + int has_inline; - /* - * Check if need to extend journal credits - * 3 for leaf, sb, and inode plus 2 (bmap and group - * descriptor) for each block group; assume two block - * groups - */ - if (handle->h_buffer_credits < 7) { - credits = ext4_writepage_trans_blocks(inode); - err = ext4_ext_truncate_extend_restart(handle, inode, credits); - /* EAGAIN is success */ - if (err && err != -EAGAIN) - return err; + down_read(&EXT4_I(inode)->xattr_sem); + has_inline = ext4_has_inline_data(inode); + up_read(&EXT4_I(inode)->xattr_sem); + if (has_inline) + return 0; } - err = ext4_ext_get_access(handle, inode, path); - return err; + if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { + inode_lock_shared(inode); + error = ext4_ext_precache(inode); + inode_unlock_shared(inode); + if (error) + return error; + fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; + } + + error = fiemap_prep(inode, fieinfo, start, &len, 0); + if (error) + return error; + + error = ext4_fiemap_check_ranges(inode, start, &len); + if (error) + return error; + + start_blk = start >> inode->i_sb->s_blocksize_bits; + last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits; + if (last_blk >= EXT_MAX_BLOCKS) + last_blk = EXT_MAX_BLOCKS-1; + len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1; + + /* + * Walk the extent tree gathering extent information + * and pushing extents back to the user. + */ + return ext4_fill_es_cache_info(inode, start_blk, len_blks, fieinfo); } /* @@ -5143,7 +5196,8 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, { int depth, err = 0; struct ext4_extent *ex_start, *ex_last; - bool update = 0; + bool update = false; + int credits, restart_credits; depth = path->p_depth; while (depth >= 0) { @@ -5153,13 +5207,26 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, return -EFSCORRUPTED; ex_last = EXT_LAST_EXTENT(path[depth].p_hdr); + /* leaf + sb + inode */ + credits = 3; + if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr)) { + update = true; + /* extent tree + sb + inode */ + credits = depth + 2; + } - err = ext4_access_path(handle, inode, path + depth); - if (err) + restart_credits = ext4_chunk_trans_extent(inode, 0); + err = ext4_datasem_ensure_credits(handle, inode, credits, + restart_credits, 0); + if (err) { + if (err > 0) + err = -EAGAIN; goto out; + } - if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr)) - update = 1; + err = ext4_ext_get_access(handle, inode, path + depth); + if (err) + goto out; while (ex_start <= ex_last) { if (SHIFT == SHIFT_LEFT) { @@ -5190,7 +5257,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, } /* Update index too */ - err = ext4_access_path(handle, inode, path + depth); + err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; @@ -5229,6 +5296,7 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, int ret = 0, depth; struct ext4_extent *extent; ext4_lblk_t stop, *iterator, ex_start, ex_end; + ext4_lblk_t tmp = EXT_MAX_BLOCKS; /* Let path point to the last extent */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, @@ -5249,7 +5317,7 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, * won't be shifted beyond EXT_MAX_BLOCKS. */ if (SHIFT == SHIFT_LEFT) { - path = ext4_find_extent(inode, start - 1, &path, + path = ext4_find_extent(inode, start - 1, path, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); @@ -5282,18 +5350,23 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, * till we reach stop. In case of right shift, iterator points to stop * and it is decreased till we reach start. */ +again: + ret = 0; if (SHIFT == SHIFT_LEFT) iterator = &start; else iterator = &stop; + if (tmp != EXT_MAX_BLOCKS) + *iterator = tmp; + /* * Its safe to start updating extents. Start and stop are unsigned, so * in case of right shift if extent with 0 block is reached, iterator * becomes NULL to indicate the end of the loop. */ while (iterator && start <= stop) { - path = ext4_find_extent(inode, *iterator, &path, + path = ext4_find_extent(inode, *iterator, path, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); @@ -5315,30 +5388,40 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, } } + tmp = *iterator; if (SHIFT == SHIFT_LEFT) { extent = EXT_LAST_EXTENT(path[depth].p_hdr); *iterator = le32_to_cpu(extent->ee_block) + ext4_ext_get_actual_len(extent); } else { extent = EXT_FIRST_EXTENT(path[depth].p_hdr); - if (le32_to_cpu(extent->ee_block) > 0) + if (le32_to_cpu(extent->ee_block) > start) *iterator = le32_to_cpu(extent->ee_block) - 1; - else - /* Beginning is reached, end of the loop */ + else if (le32_to_cpu(extent->ee_block) == start) iterator = NULL; - /* Update path extent in case we need to stop */ - while (le32_to_cpu(extent->ee_block) < start) + else { + extent = EXT_LAST_EXTENT(path[depth].p_hdr); + while (le32_to_cpu(extent->ee_block) >= start) + extent--; + + if (extent == EXT_LAST_EXTENT(path[depth].p_hdr)) + break; + extent++; + iterator = NULL; + } path[depth].p_ext = extent; } ret = ext4_ext_shift_path_extents(path, shift, inode, handle, SHIFT); + /* iterator can be NULL which means we should break */ + if (ret == -EAGAIN) + goto again; if (ret) break; } out: - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); return ret; } @@ -5347,143 +5430,96 @@ out: * This implements the fallocate's collapse range functionality for ext4 * Returns: 0 and non-zero on error. */ -int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; - ext4_lblk_t punch_start, punch_stop; + struct address_space *mapping = inode->i_mapping; + loff_t end = offset + len; + ext4_lblk_t start_lblk, end_lblk; handle_t *handle; unsigned int credits; - loff_t new_size, ioffset; + loff_t start, new_size; int ret; - /* - * We need to test this early because xfstests assumes that a - * collapse range of (0, 1) will return EOPNOTSUPP if the file - * system does not support collapse range. - */ + trace_ext4_collapse_range(inode, offset, len); + WARN_ON_ONCE(!inode_is_locked(inode)); + + /* Currently just for extent based files */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return -EOPNOTSUPP; - - /* Collapse range works only on fs block size aligned offsets. */ - if (offset & (EXT4_CLUSTER_SIZE(sb) - 1) || - len & (EXT4_CLUSTER_SIZE(sb) - 1)) - return -EINVAL; - - if (!S_ISREG(inode->i_mode)) + /* Collapse range works only on fs cluster size aligned regions. */ + if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) return -EINVAL; - - trace_ext4_collapse_range(inode, offset, len); - - punch_start = offset >> EXT4_BLOCK_SIZE_BITS(sb); - punch_stop = (offset + len) >> EXT4_BLOCK_SIZE_BITS(sb); - - /* Call ext4_force_commit to flush all data in case of data=journal. */ - if (ext4_should_journal_data(inode)) { - ret = ext4_force_commit(inode->i_sb); - if (ret) - return ret; - } - - inode_lock(inode); /* * There is no need to overlap collapse range with EOF, in which case * it is effectively a truncate operation */ - if (offset + len >= i_size_read(inode)) { - ret = -EINVAL; - goto out_mutex; - } - - /* Currently just for extent based files */ - if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { - ret = -EOPNOTSUPP; - goto out_mutex; - } - - /* Wait for existing dio to complete */ - inode_dio_wait(inode); - - /* - * Prevent page faults from reinstantiating pages we have released from - * page cache. - */ - down_write(&EXT4_I(inode)->i_mmap_sem); - - ret = ext4_break_layouts(inode); - if (ret) - goto out_mmap; + if (end >= inode->i_size) + return -EINVAL; /* + * Write tail of the last page before removed range and data that + * will be shifted since they will get removed from the page cache + * below. We are also protected from pages becoming dirty by + * i_rwsem and invalidate_lock. * Need to round down offset to be aligned with page size boundary * for page size > block size. */ - ioffset = round_down(offset, PAGE_SIZE); - /* - * Write tail of the last page before removed range since it will get - * removed from the page cache below. - */ - ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset); + start = round_down(offset, PAGE_SIZE); + ret = filemap_write_and_wait_range(mapping, start, offset); + if (!ret) + ret = filemap_write_and_wait_range(mapping, end, LLONG_MAX); if (ret) - goto out_mmap; - /* - * Write data that will be shifted to preserve them when discarding - * page cache below. We are also protected from pages becoming dirty - * by i_mmap_sem. - */ - ret = filemap_write_and_wait_range(inode->i_mapping, offset + len, - LLONG_MAX); - if (ret) - goto out_mmap; - truncate_pagecache(inode, ioffset); + return ret; - credits = ext4_writepage_trans_blocks(inode); + truncate_pagecache(inode, start); + + credits = ext4_chunk_trans_extent(inode, 0); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out_mmap; - } + if (IS_ERR(handle)) + return PTR_ERR(handle); + + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); + + start_lblk = offset >> inode->i_blkbits; + end_lblk = (offset + len) >> inode->i_blkbits; + + ext4_check_map_extents_env(inode); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); + ext4_es_remove_extent(inode, start_lblk, EXT_MAX_BLOCKS - start_lblk); - ret = ext4_es_remove_extent(inode, punch_start, - EXT_MAX_BLOCKS - punch_start); - if (ret) { - up_write(&EXT4_I(inode)->i_data_sem); - goto out_stop; - } - - ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1); + ret = ext4_ext_remove_space(inode, start_lblk, end_lblk - 1); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); - goto out_stop; + goto out_handle; } ext4_discard_preallocations(inode); - ret = ext4_ext_shift_extents(inode, handle, punch_stop, - punch_stop - punch_start, SHIFT_LEFT); + ret = ext4_ext_shift_extents(inode, handle, end_lblk, + end_lblk - start_lblk, SHIFT_LEFT); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); - goto out_stop; + goto out_handle; } - new_size = i_size_read(inode) - len; + new_size = inode->i_size - len; i_size_write(inode, new_size); EXT4_I(inode)->i_disksize = new_size; up_write(&EXT4_I(inode)->i_data_sem); + ret = ext4_mark_inode_dirty(handle, inode); + if (ret) + goto out_handle; + + ext4_update_inode_fsync_trans(handle, inode, 1); if (IS_SYNC(inode)) ext4_handle_sync(handle); - inode->i_mtime = inode->i_ctime = current_time(inode); - ext4_mark_inode_dirty(handle, inode); - ext4_update_inode_fsync_trans(handle, inode, 1); -out_stop: +out_handle: ext4_journal_stop(handle); -out_mmap: - up_write(&EXT4_I(inode)->i_mmap_sem); -out_mutex: - inode_unlock(inode); return ret; } @@ -5495,111 +5531,73 @@ out_mutex: * by len bytes. * Returns 0 on success, error otherwise. */ -int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; + struct address_space *mapping = inode->i_mapping; handle_t *handle; struct ext4_ext_path *path; struct ext4_extent *extent; - ext4_lblk_t offset_lblk, len_lblk, ee_start_lblk = 0; + ext4_lblk_t start_lblk, len_lblk, ee_start_lblk = 0; unsigned int credits, ee_len; - int ret = 0, depth, split_flag = 0; - loff_t ioffset; - - /* - * We need to test this early because xfstests assumes that an - * insert range of (0, 1) will return EOPNOTSUPP if the file - * system does not support insert range. - */ - if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - return -EOPNOTSUPP; - - /* Insert range works only on fs block size aligned offsets. */ - if (offset & (EXT4_CLUSTER_SIZE(sb) - 1) || - len & (EXT4_CLUSTER_SIZE(sb) - 1)) - return -EINVAL; - - if (!S_ISREG(inode->i_mode)) - return -EOPNOTSUPP; + int ret, depth, split_flag = 0; + loff_t start; trace_ext4_insert_range(inode, offset, len); + WARN_ON_ONCE(!inode_is_locked(inode)); - offset_lblk = offset >> EXT4_BLOCK_SIZE_BITS(sb); - len_lblk = len >> EXT4_BLOCK_SIZE_BITS(sb); - - /* Call ext4_force_commit to flush all data in case of data=journal */ - if (ext4_should_journal_data(inode)) { - ret = ext4_force_commit(inode->i_sb); - if (ret) - return ret; - } - - inode_lock(inode); /* Currently just for extent based files */ - if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { - ret = -EOPNOTSUPP; - goto out_mutex; - } - - /* Check for wrap through zero */ - if (inode->i_size + len > inode->i_sb->s_maxbytes) { - ret = -EFBIG; - goto out_mutex; - } - - /* Offset should be less than i_size */ - if (offset >= i_size_read(inode)) { - ret = -EINVAL; - goto out_mutex; - } - - /* Wait for existing dio to complete */ - inode_dio_wait(inode); + if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + return -EOPNOTSUPP; + /* Insert range works only on fs cluster size aligned regions. */ + if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) + return -EINVAL; + /* Offset must be less than i_size */ + if (offset >= inode->i_size) + return -EINVAL; + /* Check whether the maximum file size would be exceeded */ + if (len > inode->i_sb->s_maxbytes - inode->i_size) + return -EFBIG; /* - * Prevent page faults from reinstantiating pages we have released from - * page cache. + * Write out all dirty pages. Need to round down to align start offset + * to page size boundary for page size > block size. */ - down_write(&EXT4_I(inode)->i_mmap_sem); - - ret = ext4_break_layouts(inode); + start = round_down(offset, PAGE_SIZE); + ret = filemap_write_and_wait_range(mapping, start, LLONG_MAX); if (ret) - goto out_mmap; + return ret; - /* - * Need to round down to align start offset to page size boundary - * for page size > block size. - */ - ioffset = round_down(offset, PAGE_SIZE); - /* Write out all dirty pages */ - ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, - LLONG_MAX); - if (ret) - goto out_mmap; - truncate_pagecache(inode, ioffset); + truncate_pagecache(inode, start); - credits = ext4_writepage_trans_blocks(inode); + credits = ext4_chunk_trans_extent(inode, 0); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out_mmap; - } + if (IS_ERR(handle)) + return PTR_ERR(handle); + + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); /* Expand file to avoid data loss if there is error while shifting */ inode->i_size += len; EXT4_I(inode)->i_disksize += len; - inode->i_mtime = inode->i_ctime = current_time(inode); ret = ext4_mark_inode_dirty(handle, inode); if (ret) - goto out_stop; + goto out_handle; + + start_lblk = offset >> inode->i_blkbits; + len_lblk = len >> inode->i_blkbits; + + ext4_check_map_extents_env(inode); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); - path = ext4_find_extent(inode, offset_lblk, NULL, 0); + path = ext4_find_extent(inode, start_lblk, NULL, 0); if (IS_ERR(path)) { up_write(&EXT4_I(inode)->i_data_sem); - goto out_stop; + ret = PTR_ERR(path); + goto out_handle; } depth = ext_depth(inode); @@ -5609,65 +5607,53 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) ee_len = ext4_ext_get_actual_len(extent); /* - * If offset_lblk is not the starting block of extent, split - * the extent @offset_lblk + * If start_lblk is not the starting block of extent, split + * the extent @start_lblk */ - if ((offset_lblk > ee_start_lblk) && - (offset_lblk < (ee_start_lblk + ee_len))) { + if ((start_lblk > ee_start_lblk) && + (start_lblk < (ee_start_lblk + ee_len))) { if (ext4_ext_is_unwritten(extent)) split_flag = EXT4_EXT_MARK_UNWRIT1 | EXT4_EXT_MARK_UNWRIT2; - ret = ext4_split_extent_at(handle, inode, &path, - offset_lblk, split_flag, + path = ext4_split_extent_at(handle, inode, path, + start_lblk, split_flag, EXT4_EX_NOCACHE | - EXT4_GET_BLOCKS_PRE_IO | + EXT4_GET_BLOCKS_SPLIT_NOMERGE | EXT4_GET_BLOCKS_METADATA_NOFAIL); } - ext4_ext_drop_refs(path); - kfree(path); - if (ret < 0) { + if (IS_ERR(path)) { up_write(&EXT4_I(inode)->i_data_sem); - goto out_stop; + ret = PTR_ERR(path); + goto out_handle; } - } else { - ext4_ext_drop_refs(path); - kfree(path); } - ret = ext4_es_remove_extent(inode, offset_lblk, - EXT_MAX_BLOCKS - offset_lblk); - if (ret) { - up_write(&EXT4_I(inode)->i_data_sem); - goto out_stop; - } + ext4_free_ext_path(path); + ext4_es_remove_extent(inode, start_lblk, EXT_MAX_BLOCKS - start_lblk); /* - * if offset_lblk lies in a hole which is at start of file, use + * if start_lblk lies in a hole which is at start of file, use * ee_start_lblk to shift extents */ ret = ext4_ext_shift_extents(inode, handle, - ee_start_lblk > offset_lblk ? ee_start_lblk : offset_lblk, - len_lblk, SHIFT_RIGHT); - + max(ee_start_lblk, start_lblk), len_lblk, SHIFT_RIGHT); up_write(&EXT4_I(inode)->i_data_sem); + if (ret) + goto out_handle; + + ext4_update_inode_fsync_trans(handle, inode, 1); if (IS_SYNC(inode)) ext4_handle_sync(handle); - if (ret >= 0) - ext4_update_inode_fsync_trans(handle, inode, 1); -out_stop: +out_handle: ext4_journal_stop(handle); -out_mmap: - up_write(&EXT4_I(inode)->i_mmap_sem); -out_mutex: - inode_unlock(inode); return ret; } /** - * ext4_swap_extents - Swap extents between two inodes - * + * ext4_swap_extents() - Swap extents between two inodes + * @handle: handle for this transaction * @inode1: First inode * @inode2: Second inode * @lblk1: Start block for first inode @@ -5680,7 +5666,7 @@ out_mutex: * stuff such as page-cache locking consistency, bh mapping consistency or * extent's data copying must be performed by caller. * Locking: - * i_mutex is held for both inodes + * i_rwsem is held for both inodes * i_data_sem is locked for write for both inodes * Assumptions: * All pages from requested range are locked for both inodes @@ -5699,12 +5685,8 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, BUG_ON(!inode_is_locked(inode1)); BUG_ON(!inode_is_locked(inode2)); - *erp = ext4_es_remove_extent(inode1, lblk1, count); - if (unlikely(*erp)) - return 0; - *erp = ext4_es_remove_extent(inode2, lblk2, count); - if (unlikely(*erp)) - return 0; + ext4_es_remove_extent(inode1, lblk1, count); + ext4_es_remove_extent(inode2, lblk2, count); while (count) { struct ext4_extent *ex1, *ex2, tmp_ex; @@ -5712,25 +5694,21 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, int e1_len, e2_len, len; int split = 0; - path1 = ext4_find_extent(inode1, lblk1, NULL, EXT4_EX_NOCACHE); + path1 = ext4_find_extent(inode1, lblk1, path1, EXT4_EX_NOCACHE); if (IS_ERR(path1)) { *erp = PTR_ERR(path1); - path1 = NULL; - finish: - count = 0; - goto repeat; + goto errout; } - path2 = ext4_find_extent(inode2, lblk2, NULL, EXT4_EX_NOCACHE); + path2 = ext4_find_extent(inode2, lblk2, path2, EXT4_EX_NOCACHE); if (IS_ERR(path2)) { *erp = PTR_ERR(path2); - path2 = NULL; - goto finish; + goto errout; } ex1 = path1[path1->p_depth].p_ext; ex2 = path2[path2->p_depth].p_ext; - /* Do we have somthing to swap ? */ + /* Do we have something to swap ? */ if (unlikely(!ex2 || !ex1)) - goto finish; + goto errout; e1_blk = le32_to_cpu(ex1->ee_block); e2_blk = le32_to_cpu(ex2->ee_block); @@ -5752,7 +5730,7 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, next2 = e2_blk; /* Do we have something to swap */ if (next1 == EXT_MAX_BLOCKS || next2 == EXT_MAX_BLOCKS) - goto finish; + goto errout; /* Move to the rightest boundary */ len = next1 - lblk1; if (len < next2 - lblk2) @@ -5762,28 +5740,32 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, lblk1 += len; lblk2 += len; count -= len; - goto repeat; + continue; } /* Prepare left boundary */ if (e1_blk < lblk1) { split = 1; - *erp = ext4_force_split_extent_at(handle, inode1, - &path1, lblk1, 0); - if (unlikely(*erp)) - goto finish; + path1 = ext4_force_split_extent_at(handle, inode1, + path1, lblk1, 0); + if (IS_ERR(path1)) { + *erp = PTR_ERR(path1); + goto errout; + } } if (e2_blk < lblk2) { split = 1; - *erp = ext4_force_split_extent_at(handle, inode2, - &path2, lblk2, 0); - if (unlikely(*erp)) - goto finish; + path2 = ext4_force_split_extent_at(handle, inode2, + path2, lblk2, 0); + if (IS_ERR(path2)) { + *erp = PTR_ERR(path2); + goto errout; + } } /* ext4_split_extent_at() may result in leaf extent split, * path must to be revalidated. */ if (split) - goto repeat; + continue; /* Prepare right boundary */ len = count; @@ -5794,30 +5776,34 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, if (len != e1_len) { split = 1; - *erp = ext4_force_split_extent_at(handle, inode1, - &path1, lblk1 + len, 0); - if (unlikely(*erp)) - goto finish; + path1 = ext4_force_split_extent_at(handle, inode1, + path1, lblk1 + len, 0); + if (IS_ERR(path1)) { + *erp = PTR_ERR(path1); + goto errout; + } } if (len != e2_len) { split = 1; - *erp = ext4_force_split_extent_at(handle, inode2, - &path2, lblk2 + len, 0); - if (*erp) - goto finish; + path2 = ext4_force_split_extent_at(handle, inode2, + path2, lblk2 + len, 0); + if (IS_ERR(path2)) { + *erp = PTR_ERR(path2); + goto errout; + } } /* ext4_split_extent_at() may result in leaf extent split, * path must to be revalidated. */ if (split) - goto repeat; + continue; BUG_ON(e2_len != e1_len); *erp = ext4_ext_get_access(handle, inode1, path1 + path1->p_depth); if (unlikely(*erp)) - goto finish; + goto errout; *erp = ext4_ext_get_access(handle, inode2, path2 + path2->p_depth); if (unlikely(*erp)) - goto finish; + goto errout; /* Both extents are fully inside boundaries. Swap it now */ tmp_ex = *ex1; @@ -5835,7 +5821,7 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, *erp = ext4_ext_dirty(handle, inode2, path2 + path2->p_depth); if (unlikely(*erp)) - goto finish; + goto errout; *erp = ext4_ext_dirty(handle, inode1, path1 + path1->p_depth); /* @@ -5845,19 +5831,17 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, * aborted anyway. */ if (unlikely(*erp)) - goto finish; + goto errout; + lblk1 += len; lblk2 += len; replaced_count += len; count -= len; - - repeat: - ext4_ext_drop_refs(path1); - kfree(path1); - ext4_ext_drop_refs(path2); - kfree(path2); - path1 = path2 = NULL; } + +errout: + ext4_free_ext_path(path1); + ext4_free_ext_path(path2); return replaced_count; } @@ -5881,13 +5865,19 @@ int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu) struct ext4_extent *extent; ext4_lblk_t first_lblk, first_lclu, last_lclu; + /* + * if data can be stored inline, the logical cluster isn't + * mapped - no physical clusters have been allocated, and the + * file has no extents + */ + if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) || + ext4_has_inline_data(inode)) + return 0; + /* search for the extent closest to the first block in the cluster */ path = ext4_find_extent(inode, EXT4_C2B(sbi, lclu), NULL, 0); - if (IS_ERR(path)) { - err = PTR_ERR(path); - path = NULL; - goto out; - } + if (IS_ERR(path)) + return PTR_ERR(path); depth = ext_depth(inode); @@ -5934,8 +5924,266 @@ int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu) } out: - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); return err ? err : mapped; } + +/* + * Updates physical block address and unwritten status of extent + * starting at lblk start and of len. If such an extent doesn't exist, + * this function splits the extent tree appropriately to create an + * extent like this. This function is called in the fast commit + * replay path. Returns 0 on success and error on failure. + */ +int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start, + int len, int unwritten, ext4_fsblk_t pblk) +{ + struct ext4_ext_path *path; + struct ext4_extent *ex; + int ret; + + path = ext4_find_extent(inode, start, NULL, 0); + if (IS_ERR(path)) + return PTR_ERR(path); + ex = path[path->p_depth].p_ext; + if (!ex) { + ret = -EFSCORRUPTED; + goto out; + } + + if (le32_to_cpu(ex->ee_block) != start || + ext4_ext_get_actual_len(ex) != len) { + /* We need to split this extent to match our extent first */ + down_write(&EXT4_I(inode)->i_data_sem); + path = ext4_force_split_extent_at(NULL, inode, path, start, 1); + up_write(&EXT4_I(inode)->i_data_sem); + if (IS_ERR(path)) { + ret = PTR_ERR(path); + goto out; + } + + path = ext4_find_extent(inode, start, path, 0); + if (IS_ERR(path)) + return PTR_ERR(path); + + ex = path[path->p_depth].p_ext; + WARN_ON(le32_to_cpu(ex->ee_block) != start); + + if (ext4_ext_get_actual_len(ex) != len) { + down_write(&EXT4_I(inode)->i_data_sem); + path = ext4_force_split_extent_at(NULL, inode, path, + start + len, 1); + up_write(&EXT4_I(inode)->i_data_sem); + if (IS_ERR(path)) { + ret = PTR_ERR(path); + goto out; + } + + path = ext4_find_extent(inode, start, path, 0); + if (IS_ERR(path)) + return PTR_ERR(path); + ex = path[path->p_depth].p_ext; + } + } + if (unwritten) + ext4_ext_mark_unwritten(ex); + else + ext4_ext_mark_initialized(ex); + ext4_ext_store_pblock(ex, pblk); + down_write(&EXT4_I(inode)->i_data_sem); + ret = ext4_ext_dirty(NULL, inode, &path[path->p_depth]); + up_write(&EXT4_I(inode)->i_data_sem); +out: + ext4_free_ext_path(path); + ext4_mark_inode_dirty(NULL, inode); + return ret; +} + +/* Try to shrink the extent tree */ +void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end) +{ + struct ext4_ext_path *path = NULL; + struct ext4_extent *ex; + ext4_lblk_t old_cur, cur = 0; + + while (cur < end) { + path = ext4_find_extent(inode, cur, NULL, 0); + if (IS_ERR(path)) + return; + ex = path[path->p_depth].p_ext; + if (!ex) { + ext4_free_ext_path(path); + ext4_mark_inode_dirty(NULL, inode); + return; + } + old_cur = cur; + cur = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); + if (cur <= old_cur) + cur = old_cur + 1; + ext4_ext_try_to_merge(NULL, inode, path, ex); + down_write(&EXT4_I(inode)->i_data_sem); + ext4_ext_dirty(NULL, inode, &path[path->p_depth]); + up_write(&EXT4_I(inode)->i_data_sem); + ext4_mark_inode_dirty(NULL, inode); + ext4_free_ext_path(path); + } +} + +/* Check if *cur is a hole and if it is, skip it */ +static int skip_hole(struct inode *inode, ext4_lblk_t *cur) +{ + int ret; + struct ext4_map_blocks map; + + map.m_lblk = *cur; + map.m_len = ((inode->i_size) >> inode->i_sb->s_blocksize_bits) - *cur; + + ret = ext4_map_blocks(NULL, inode, &map, 0); + if (ret < 0) + return ret; + if (ret != 0) + return 0; + *cur = *cur + map.m_len; + return 0; +} + +/* Count number of blocks used by this inode and update i_blocks */ +int ext4_ext_replay_set_iblocks(struct inode *inode) +{ + struct ext4_ext_path *path = NULL, *path2 = NULL; + struct ext4_extent *ex; + ext4_lblk_t cur = 0, end; + int numblks = 0, i, ret = 0; + ext4_fsblk_t cmp1, cmp2; + struct ext4_map_blocks map; + + /* Determin the size of the file first */ + path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, + EXT4_EX_NOCACHE); + if (IS_ERR(path)) + return PTR_ERR(path); + ex = path[path->p_depth].p_ext; + if (!ex) + goto out; + end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); + + /* Count the number of data blocks */ + cur = 0; + while (cur < end) { + map.m_lblk = cur; + map.m_len = end - cur; + ret = ext4_map_blocks(NULL, inode, &map, 0); + if (ret < 0) + break; + if (ret > 0) + numblks += ret; + cur = cur + map.m_len; + } + + /* + * Count the number of extent tree blocks. We do it by looking up + * two successive extents and determining the difference between + * their paths. When path is different for 2 successive extents + * we compare the blocks in the path at each level and increment + * iblocks by total number of differences found. + */ + cur = 0; + ret = skip_hole(inode, &cur); + if (ret < 0) + goto out; + path = ext4_find_extent(inode, cur, path, 0); + if (IS_ERR(path)) + goto out; + numblks += path->p_depth; + while (cur < end) { + path = ext4_find_extent(inode, cur, path, 0); + if (IS_ERR(path)) + break; + ex = path[path->p_depth].p_ext; + if (!ex) + goto cleanup; + + cur = max(cur + 1, le32_to_cpu(ex->ee_block) + + ext4_ext_get_actual_len(ex)); + ret = skip_hole(inode, &cur); + if (ret < 0) + break; + + path2 = ext4_find_extent(inode, cur, path2, 0); + if (IS_ERR(path2)) + break; + + for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) { + cmp1 = cmp2 = 0; + if (i <= path->p_depth) + cmp1 = path[i].p_bh ? + path[i].p_bh->b_blocknr : 0; + if (i <= path2->p_depth) + cmp2 = path2[i].p_bh ? + path2[i].p_bh->b_blocknr : 0; + if (cmp1 != cmp2 && cmp2 != 0) + numblks++; + } + } + +out: + inode->i_blocks = numblks << (inode->i_sb->s_blocksize_bits - 9); + ext4_mark_inode_dirty(NULL, inode); +cleanup: + ext4_free_ext_path(path); + ext4_free_ext_path(path2); + return 0; +} + +int ext4_ext_clear_bb(struct inode *inode) +{ + struct ext4_ext_path *path = NULL; + struct ext4_extent *ex; + ext4_lblk_t cur = 0, end; + int j, ret = 0; + struct ext4_map_blocks map; + + if (ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA)) + return 0; + + /* Determin the size of the file first */ + path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, + EXT4_EX_NOCACHE); + if (IS_ERR(path)) + return PTR_ERR(path); + ex = path[path->p_depth].p_ext; + if (!ex) + goto out; + end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); + + cur = 0; + while (cur < end) { + map.m_lblk = cur; + map.m_len = end - cur; + ret = ext4_map_blocks(NULL, inode, &map, 0); + if (ret < 0) + break; + if (ret > 0) { + path = ext4_find_extent(inode, map.m_lblk, path, 0); + if (!IS_ERR(path)) { + for (j = 0; j < path->p_depth; j++) { + ext4_mb_mark_bb(inode->i_sb, + path[j].p_block, 1, false); + ext4_fc_record_regions(inode->i_sb, inode->i_ino, + 0, path[j].p_block, 1, 1); + } + } else { + path = NULL; + } + ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, false); + ext4_fc_record_regions(inode->i_sb, inode->i_ino, + map.m_lblk, map.m_pblk, map.m_len, 1); + } + cur = cur + map.m_len; + } + +out: + ext4_free_ext_path(path); + return 0; +} |