// SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/indirect.c * * from * * linux/fs/ext4/inode.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card ([email protected]) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/inode.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Goal-directed block allocation by Stephen Tweedie * ([email protected]), 1993, 1998 */ #include "ext4_jbd2.h" #include "truncate.h" #include <linux/dax.h> #include <linux/uio.h> #include <trace/events/ext4.h> Indirect; static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v) { … } /** * ext4_block_to_path - parse the block number into array of offsets * @inode: inode in question (we are only interested in its superblock) * @i_block: block number to be parsed * @offsets: array to store the offsets in * @boundary: set this non-zero if the referred-to block is likely to be * followed (on disk) by an indirect block. * * To store the locations of file's data ext4 uses a data structure common * for UNIX filesystems - tree of pointers anchored in the inode, with * data blocks at leaves and indirect blocks in intermediate nodes. * This function translates the block number into path in that tree - * return value is the path length and @offsets[n] is the offset of * pointer to (n+1)th node in the nth one. If @block is out of range * (negative or too large) warning is printed and zero returned. * * Note: function doesn't find node addresses, so no IO is needed. All * we need to know is the capacity of indirect blocks (taken from the * inode->i_sb). */ /* * Portability note: the last comparison (check that we fit into triple * indirect block) is spelled differently, because otherwise on an * architecture with 32-bit longs and 8Kb pages we might get into trouble * if our filesystem had 8Kb blocks. We might use long long, but that would * kill us on x86. Oh, well, at least the sign propagation does not matter - * i_block would have to be negative in the very beginning, so we would not * get there at all. */ static int ext4_block_to_path(struct inode *inode, ext4_lblk_t i_block, ext4_lblk_t offsets[4], int *boundary) { … } /** * ext4_get_branch - read the chain of indirect blocks leading to data * @inode: inode in question * @depth: depth of the chain (1 - direct pointer, etc.) * @offsets: offsets of pointers in inode/indirect blocks * @chain: place to store the result * @err: here we store the error value * * Function fills the array of triples <key, p, bh> and returns %NULL * if everything went OK or the pointer to the last filled triple * (incomplete one) otherwise. Upon the return chain[i].key contains * the number of (i+1)-th block in the chain (as it is stored in memory, * i.e. little-endian 32-bit), chain[i].p contains the address of that * number (it points into struct inode for i==0 and into the bh->b_data * for i>0) and chain[i].bh points to the buffer_head of i-th indirect * block for i>0 and NULL for i==0. In other words, it holds the block * numbers of the chain, addresses they were taken from (and where we can * verify that chain did not change) and buffer_heads hosting these * numbers. * * Function stops when it stumbles upon zero pointer (absent block) * (pointer to last triple returned, *@err == 0) * or when it gets an IO error reading an indirect block * (ditto, *@err == -EIO) * or when it reads all @depth-1 indirect blocks successfully and finds * the whole chain, all way to the data (returns %NULL, *err == 0). * * Need to be called with * down_read(&EXT4_I(inode)->i_data_sem) */ static Indirect *ext4_get_branch(struct inode *inode, int depth, ext4_lblk_t *offsets, Indirect chain[4], int *err) { … } /** * ext4_find_near - find a place for allocation with sufficient locality * @inode: owner * @ind: descriptor of indirect block. * * This function returns the preferred place for block allocation. * It is used when heuristic for sequential allocation fails. * Rules are: * + if there is a block to the left of our position - allocate near it. * + if pointer will live in indirect block - allocate near that block. * + if pointer will live in inode - allocate in the same * cylinder group. * * In the latter case we colour the starting block by the callers PID to * prevent it from clashing with concurrent allocations for a different inode * in the same block group. The PID is used here so that functionally related * files will be close-by on-disk. * * Caller must make sure that @ind is valid and will stay that way. */ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) { … } /** * ext4_find_goal - find a preferred place for allocation. * @inode: owner * @block: block we want * @partial: pointer to the last triple within a chain * * Normally this function find the preferred place for block allocation, * returns it. * Because this is only used for non-extent files, we limit the block nr * to 32 bits. */ static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block, Indirect *partial) { … } /** * ext4_blks_to_allocate - Look up the block map and count the number * of direct blocks need to be allocated for the given branch. * * @branch: chain of indirect blocks * @k: number of blocks need for indirect blocks * @blks: number of data blocks to be mapped. * @blocks_to_boundary: the offset in the indirect block * * return the total number of blocks to be allocate, including the * direct and indirect blocks. */ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks, int blocks_to_boundary) { … } /** * ext4_alloc_branch() - allocate and set up a chain of blocks * @handle: handle for this transaction * @ar: structure describing the allocation request * @indirect_blks: number of allocated indirect blocks * @offsets: offsets (in the blocks) to store the pointers to next. * @branch: place to store the chain in. * * This function allocates blocks, zeroes out all but the last one, * links them into chain and (if we are synchronous) writes them to disk. * In other words, it prepares a branch that can be spliced onto the * inode. It stores the information about that chain in the branch[], in * the same format as ext4_get_branch() would do. We are calling it after * we had read the existing part of chain and partial points to the last * triple of that (one with zero ->key). Upon the exit we have the same * picture as after the successful ext4_get_block(), except that in one * place chain is disconnected - *branch->p is still zero (we did not * set the last link), but branch->key contains the number that should * be placed into *branch->p to fill that gap. * * If allocation fails we free all blocks we've allocated (and forget * their buffer_heads) and return the error value the from failed * ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain * as described above and return 0. */ static int ext4_alloc_branch(handle_t *handle, struct ext4_allocation_request *ar, int indirect_blks, ext4_lblk_t *offsets, Indirect *branch) { … } /** * ext4_splice_branch() - splice the allocated branch onto inode. * @handle: handle for this transaction * @ar: structure describing the allocation request * @where: location of missing link * @num: number of indirect blocks we are adding * * This function fills the missing link and does all housekeeping needed in * inode (->i_blocks, etc.). In case of success we end up with the full * chain to new block and return 0. */ static int ext4_splice_branch(handle_t *handle, struct ext4_allocation_request *ar, Indirect *where, int num) { … } /* * The ext4_ind_map_blocks() function handles non-extents inodes * (i.e., using the traditional indirect/double-indirect i_blocks * scheme) for ext4_map_blocks(). * * Allocation strategy is simple: if we have to allocate something, we will * have to go the whole way to leaf. So let's do it before attaching anything * to tree, set linkage between the newborn blocks, write them if sync is * required, recheck the path, free and repeat if check fails, otherwise * set the last missing link (that will protect us from any truncate-generated * removals - all blocks on the path are immune now) and possibly force the * write on the parent block. * That has a nice additional property: no special recovery from the failed * allocations is needed - we simply release blocks and do not touch anything * reachable from inode. * * `handle' can be NULL if create == 0. * * return > 0, # of blocks mapped or allocated. * return = 0, if plain lookup failed. * return < 0, error case. * * The ext4_ind_get_blocks() function should be called with * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system * blocks. */ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { … } /* * Calculate number of indirect blocks touched by mapping @nrblocks logically * contiguous blocks */ int ext4_ind_trans_blocks(struct inode *inode, int nrblocks) { … } static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode, struct buffer_head *bh, int *dropped) { … } /* * Truncate transactions can be complex and absolutely huge. So we need to * be able to restart the transaction at a convenient checkpoint to make * sure we don't overflow the journal. * * Try to extend this transaction for the purposes of truncation. If * extend fails, we restart transaction. */ static int ext4_ind_truncate_ensure_credits(handle_t *handle, struct inode *inode, struct buffer_head *bh, int revoke_creds) { … } /* * Probably it should be a library function... search for first non-zero word * or memcmp with zero_page, whatever is better for particular architecture. * Linus? */ static inline int all_zeroes(__le32 *p, __le32 *q) { … } /** * ext4_find_shared - find the indirect blocks for partial truncation. * @inode: inode in question * @depth: depth of the affected branch * @offsets: offsets of pointers in that branch (see ext4_block_to_path) * @chain: place to store the pointers to partial indirect blocks * @top: place to the (detached) top of branch * * This is a helper function used by ext4_truncate(). * * When we do truncate() we may have to clean the ends of several * indirect blocks but leave the blocks themselves alive. Block is * partially truncated if some data below the new i_size is referred * from it (and it is on the path to the first completely truncated * data block, indeed). We have to free the top of that path along * with everything to the right of the path. Since no allocation * past the truncation point is possible until ext4_truncate() * finishes, we may safely do the latter, but top of branch may * require special attention - pageout below the truncation point * might try to populate it. * * We atomically detach the top of branch from the tree, store the * block number of its root in *@top, pointers to buffer_heads of * partially truncated blocks - in @chain[].bh and pointers to * their last elements that should not be removed - in * @chain[].p. Return value is the pointer to last filled element * of @chain. * * The work left to caller to do the actual freeing of subtrees: * a) free the subtree starting from *@top * b) free the subtrees whose roots are stored in * (@chain[i].p+1 .. end of @chain[i].bh->b_data) * c) free the subtrees growing from the inode past the @chain[0]. * (no partially truncated stuff there). */ static Indirect *ext4_find_shared(struct inode *inode, int depth, ext4_lblk_t offsets[4], Indirect chain[4], __le32 *top) { … } /* * Zero a number of block pointers in either an inode or an indirect block. * If we restart the transaction we must again get write access to the * indirect block for further modification. * * We release `count' blocks on disk, but (last - first) may be greater * than `count' because there can be holes in there. * * Return 0 on success, 1 on invalid block range * and < 0 on fatal error. */ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block_to_free, unsigned long count, __le32 *first, __le32 *last) { … } /** * ext4_free_data - free a list of data blocks * @handle: handle for this transaction * @inode: inode we are dealing with * @this_bh: indirect buffer_head which contains *@first and *@last * @first: array of block numbers * @last: points immediately past the end of array * * We are freeing all blocks referred from that array (numbers are stored as * little-endian 32-bit) and updating @inode->i_blocks appropriately. * * We accumulate contiguous runs of blocks to free. Conveniently, if these * blocks are contiguous then releasing them at one time will only affect one * or two bitmap blocks (+ group descriptor(s) and superblock) and we won't * actually use a lot of journal space. * * @this_bh will be %NULL if @first and @last point into the inode's direct * block pointers. */ static void ext4_free_data(handle_t *handle, struct inode *inode, struct buffer_head *this_bh, __le32 *first, __le32 *last) { … } /** * ext4_free_branches - free an array of branches * @handle: JBD handle for this transaction * @inode: inode we are dealing with * @parent_bh: the buffer_head which contains *@first and *@last * @first: array of block numbers * @last: pointer immediately past the end of array * @depth: depth of the branches to free * * We are freeing all blocks referred from these branches (numbers are * stored as little-endian 32-bit) and updating @inode->i_blocks * appropriately. */ static void ext4_free_branches(handle_t *handle, struct inode *inode, struct buffer_head *parent_bh, __le32 *first, __le32 *last, int depth) { … } void ext4_ind_truncate(handle_t *handle, struct inode *inode) { … } /** * ext4_ind_remove_space - remove space from the range * @handle: JBD handle for this transaction * @inode: inode we are dealing with * @start: First block to remove * @end: One block after the last block to remove (exclusive) * * Free the blocks in the defined range (end is exclusive endpoint of * range). This is used by ext4_punch_hole(). */ int ext4_ind_remove_space(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { … }
Codebase Browser
linux