diff options
author | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 15:20:36 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 15:20:36 -0700 |
commit | 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 (patch) | |
tree | 0bba044c4ce775e45a88a51686b5d9f90697ea9d /fs/ext2/inode.c |
Linux-2.6.12-rc2
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Diffstat (limited to 'fs/ext2/inode.c')
-rw-r--r-- | fs/ext2/inode.c | 1276 |
1 files changed, 1276 insertions, 0 deletions
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c new file mode 100644 index 000000000000..b890be022496 --- /dev/null +++ b/fs/ext2/inode.c @@ -0,0 +1,1276 @@ +/* + * linux/fs/ext2/inode.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * 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 + * (sct@dcs.ed.ac.uk), 1993, 1998 + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + * 64-bit file support on 64-bit platforms by Jakub Jelinek + * (jj@sunsite.ms.mff.cuni.cz) + * + * Assorted race fixes, rewrite of ext2_get_block() by Al Viro, 2000 + */ + +#include <linux/smp_lock.h> +#include <linux/time.h> +#include <linux/highuid.h> +#include <linux/pagemap.h> +#include <linux/quotaops.h> +#include <linux/module.h> +#include <linux/writeback.h> +#include <linux/buffer_head.h> +#include <linux/mpage.h> +#include "ext2.h" +#include "acl.h" + +MODULE_AUTHOR("Remy Card and others"); +MODULE_DESCRIPTION("Second Extended Filesystem"); +MODULE_LICENSE("GPL"); + +static int ext2_update_inode(struct inode * inode, int do_sync); + +/* + * Test whether an inode is a fast symlink. + */ +static inline int ext2_inode_is_fast_symlink(struct inode *inode) +{ + int ea_blocks = EXT2_I(inode)->i_file_acl ? + (inode->i_sb->s_blocksize >> 9) : 0; + + return (S_ISLNK(inode->i_mode) && + inode->i_blocks - ea_blocks == 0); +} + +/* + * Called at the last iput() if i_nlink is zero. + */ +void ext2_delete_inode (struct inode * inode) +{ + if (is_bad_inode(inode)) + goto no_delete; + EXT2_I(inode)->i_dtime = get_seconds(); + mark_inode_dirty(inode); + ext2_update_inode(inode, inode_needs_sync(inode)); + + inode->i_size = 0; + if (inode->i_blocks) + ext2_truncate (inode); + ext2_free_inode (inode); + + return; +no_delete: + clear_inode(inode); /* We must guarantee clearing of inode... */ +} + +void ext2_discard_prealloc (struct inode * inode) +{ +#ifdef EXT2_PREALLOCATE + struct ext2_inode_info *ei = EXT2_I(inode); + write_lock(&ei->i_meta_lock); + if (ei->i_prealloc_count) { + unsigned short total = ei->i_prealloc_count; + unsigned long block = ei->i_prealloc_block; + ei->i_prealloc_count = 0; + ei->i_prealloc_block = 0; + write_unlock(&ei->i_meta_lock); + ext2_free_blocks (inode, block, total); + return; + } else + write_unlock(&ei->i_meta_lock); +#endif +} + +static int ext2_alloc_block (struct inode * inode, unsigned long goal, int *err) +{ +#ifdef EXT2FS_DEBUG + static unsigned long alloc_hits, alloc_attempts; +#endif + unsigned long result; + + +#ifdef EXT2_PREALLOCATE + struct ext2_inode_info *ei = EXT2_I(inode); + write_lock(&ei->i_meta_lock); + if (ei->i_prealloc_count && + (goal == ei->i_prealloc_block || goal + 1 == ei->i_prealloc_block)) + { + result = ei->i_prealloc_block++; + ei->i_prealloc_count--; + write_unlock(&ei->i_meta_lock); + ext2_debug ("preallocation hit (%lu/%lu).\n", + ++alloc_hits, ++alloc_attempts); + } else { + write_unlock(&ei->i_meta_lock); + ext2_discard_prealloc (inode); + ext2_debug ("preallocation miss (%lu/%lu).\n", + alloc_hits, ++alloc_attempts); + if (S_ISREG(inode->i_mode)) + result = ext2_new_block (inode, goal, + &ei->i_prealloc_count, + &ei->i_prealloc_block, err); + else + result = ext2_new_block(inode, goal, NULL, NULL, err); + } +#else + result = ext2_new_block (inode, goal, 0, 0, err); +#endif + return result; +} + +typedef struct { + __le32 *p; + __le32 key; + struct buffer_head *bh; +} Indirect; + +static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v) +{ + p->key = *(p->p = v); + p->bh = bh; +} + +static inline int verify_chain(Indirect *from, Indirect *to) +{ + while (from <= to && from->key == *from->p) + from++; + return (from > to); +} + +/** + * ext2_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 ext2 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 ext2_block_to_path(struct inode *inode, + long i_block, int offsets[4], int *boundary) +{ + int ptrs = EXT2_ADDR_PER_BLOCK(inode->i_sb); + int ptrs_bits = EXT2_ADDR_PER_BLOCK_BITS(inode->i_sb); + const long direct_blocks = EXT2_NDIR_BLOCKS, + indirect_blocks = ptrs, + double_blocks = (1 << (ptrs_bits * 2)); + int n = 0; + int final = 0; + + if (i_block < 0) { + ext2_warning (inode->i_sb, "ext2_block_to_path", "block < 0"); + } else if (i_block < direct_blocks) { + offsets[n++] = i_block; + final = direct_blocks; + } else if ( (i_block -= direct_blocks) < indirect_blocks) { + offsets[n++] = EXT2_IND_BLOCK; + offsets[n++] = i_block; + final = ptrs; + } else if ((i_block -= indirect_blocks) < double_blocks) { + offsets[n++] = EXT2_DIND_BLOCK; + offsets[n++] = i_block >> ptrs_bits; + offsets[n++] = i_block & (ptrs - 1); + final = ptrs; + } else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) { + offsets[n++] = EXT2_TIND_BLOCK; + offsets[n++] = i_block >> (ptrs_bits * 2); + offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1); + offsets[n++] = i_block & (ptrs - 1); + final = ptrs; + } else { + ext2_warning (inode->i_sb, "ext2_block_to_path", "block > big"); + } + if (boundary) + *boundary = (i_block & (ptrs - 1)) == (final - 1); + return n; +} + +/** + * ext2_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 notices that chain had been changed while it was reading + * (ditto, *@err == -EAGAIN) + * or when it reads all @depth-1 indirect blocks successfully and finds + * the whole chain, all way to the data (returns %NULL, *err == 0). + */ +static Indirect *ext2_get_branch(struct inode *inode, + int depth, + int *offsets, + Indirect chain[4], + int *err) +{ + struct super_block *sb = inode->i_sb; + Indirect *p = chain; + struct buffer_head *bh; + + *err = 0; + /* i_data is not going away, no lock needed */ + add_chain (chain, NULL, EXT2_I(inode)->i_data + *offsets); + if (!p->key) + goto no_block; + while (--depth) { + bh = sb_bread(sb, le32_to_cpu(p->key)); + if (!bh) + goto failure; + read_lock(&EXT2_I(inode)->i_meta_lock); + if (!verify_chain(chain, p)) + goto changed; + add_chain(++p, bh, (__le32*)bh->b_data + *++offsets); + read_unlock(&EXT2_I(inode)->i_meta_lock); + if (!p->key) + goto no_block; + } + return NULL; + +changed: + read_unlock(&EXT2_I(inode)->i_meta_lock); + brelse(bh); + *err = -EAGAIN; + goto no_block; +failure: + *err = -EIO; +no_block: + return p; +} + +/** + * ext2_find_near - find a place for allocation with sufficient locality + * @inode: owner + * @ind: descriptor of indirect block. + * + * This function returns the prefered 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 unsigned long ext2_find_near(struct inode *inode, Indirect *ind) +{ + struct ext2_inode_info *ei = EXT2_I(inode); + __le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data; + __le32 *p; + unsigned long bg_start; + unsigned long colour; + + /* Try to find previous block */ + for (p = ind->p - 1; p >= start; p--) + if (*p) + return le32_to_cpu(*p); + + /* No such thing, so let's try location of indirect block */ + if (ind->bh) + return ind->bh->b_blocknr; + + /* + * It is going to be refered from inode itself? OK, just put it into + * the same cylinder group then. + */ + bg_start = (ei->i_block_group * EXT2_BLOCKS_PER_GROUP(inode->i_sb)) + + le32_to_cpu(EXT2_SB(inode->i_sb)->s_es->s_first_data_block); + colour = (current->pid % 16) * + (EXT2_BLOCKS_PER_GROUP(inode->i_sb) / 16); + return bg_start + colour; +} + +/** + * ext2_find_goal - find a prefered place for allocation. + * @inode: owner + * @block: block we want + * @chain: chain of indirect blocks + * @partial: pointer to the last triple within a chain + * @goal: place to store the result. + * + * Normally this function find the prefered place for block allocation, + * stores it in *@goal and returns zero. If the branch had been changed + * under us we return -EAGAIN. + */ + +static inline int ext2_find_goal(struct inode *inode, + long block, + Indirect chain[4], + Indirect *partial, + unsigned long *goal) +{ + struct ext2_inode_info *ei = EXT2_I(inode); + write_lock(&ei->i_meta_lock); + if ((block == ei->i_next_alloc_block + 1) && ei->i_next_alloc_goal) { + ei->i_next_alloc_block++; + ei->i_next_alloc_goal++; + } + if (verify_chain(chain, partial)) { + /* + * try the heuristic for sequential allocation, + * failing that at least try to get decent locality. + */ + if (block == ei->i_next_alloc_block) + *goal = ei->i_next_alloc_goal; + if (!*goal) + *goal = ext2_find_near(inode, partial); + write_unlock(&ei->i_meta_lock); + return 0; + } + write_unlock(&ei->i_meta_lock); + return -EAGAIN; +} + +/** + * ext2_alloc_branch - allocate and set up a chain of blocks. + * @inode: owner + * @num: depth of the chain (number of blocks to allocate) + * @offsets: offsets (in the blocks) to store the pointers to next. + * @branch: place to store the chain in. + * + * This function allocates @num 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 ext2_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 ext2_get_block(), excpet 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 + * ext2_alloc_block() (normally -ENOSPC). Otherwise we set the chain + * as described above and return 0. + */ + +static int ext2_alloc_branch(struct inode *inode, + int num, + unsigned long goal, + int *offsets, + Indirect *branch) +{ + int blocksize = inode->i_sb->s_blocksize; + int n = 0; + int err; + int i; + int parent = ext2_alloc_block(inode, goal, &err); + + branch[0].key = cpu_to_le32(parent); + if (parent) for (n = 1; n < num; n++) { + struct buffer_head *bh; + /* Allocate the next block */ + int nr = ext2_alloc_block(inode, parent, &err); + if (!nr) + break; + branch[n].key = cpu_to_le32(nr); + /* + * Get buffer_head for parent block, zero it out and set + * the pointer to new one, then send parent to disk. + */ + bh = sb_getblk(inode->i_sb, parent); + lock_buffer(bh); + memset(bh->b_data, 0, blocksize); + branch[n].bh = bh; + branch[n].p = (__le32 *) bh->b_data + offsets[n]; + *branch[n].p = branch[n].key; + set_buffer_uptodate(bh); + unlock_buffer(bh); + mark_buffer_dirty_inode(bh, inode); + /* We used to sync bh here if IS_SYNC(inode). + * But we now rely upon generic_osync_inode() + * and b_inode_buffers. But not for directories. + */ + if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode)) + sync_dirty_buffer(bh); + parent = nr; + } + if (n == num) + return 0; + + /* Allocation failed, free what we already allocated */ + for (i = 1; i < n; i++) + bforget(branch[i].bh); + for (i = 0; i < n; i++) + ext2_free_blocks(inode, le32_to_cpu(branch[i].key), 1); + return err; +} + +/** + * ext2_splice_branch - splice the allocated branch onto inode. + * @inode: owner + * @block: (logical) number of block we are adding + * @chain: chain of indirect blocks (with a missing link - see + * ext2_alloc_branch) + * @where: location of missing link + * @num: number of blocks we are adding + * + * This function verifies that chain (up to the missing link) had not + * changed, 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. Otherwise (== chain had been changed) + * we free the new blocks (forgetting their buffer_heads, indeed) and + * return -EAGAIN. + */ + +static inline int ext2_splice_branch(struct inode *inode, + long block, + Indirect chain[4], + Indirect *where, + int num) +{ + struct ext2_inode_info *ei = EXT2_I(inode); + int i; + + /* Verify that place we are splicing to is still there and vacant */ + + write_lock(&ei->i_meta_lock); + if (!verify_chain(chain, where-1) || *where->p) + goto changed; + + /* That's it */ + + *where->p = where->key; + ei->i_next_alloc_block = block; + ei->i_next_alloc_goal = le32_to_cpu(where[num-1].key); + + write_unlock(&ei->i_meta_lock); + + /* We are done with atomic stuff, now do the rest of housekeeping */ + + inode->i_ctime = CURRENT_TIME_SEC; + + /* had we spliced it onto indirect block? */ + if (where->bh) + mark_buffer_dirty_inode(where->bh, inode); + + mark_inode_dirty(inode); + return 0; + +changed: + write_unlock(&ei->i_meta_lock); + for (i = 1; i < num; i++) + bforget(where[i].bh); + for (i = 0; i < num; i++) + ext2_free_blocks(inode, le32_to_cpu(where[i].key), 1); + return -EAGAIN; +} + +/* + * 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. + */ + +int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) +{ + int err = -EIO; + int offsets[4]; + Indirect chain[4]; + Indirect *partial; + unsigned long goal; + int left; + int boundary = 0; + int depth = ext2_block_to_path(inode, iblock, offsets, &boundary); + + if (depth == 0) + goto out; + +reread: + partial = ext2_get_branch(inode, depth, offsets, chain, &err); + + /* Simplest case - block found, no allocation needed */ + if (!partial) { +got_it: + map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key)); + if (boundary) + set_buffer_boundary(bh_result); + /* Clean up and exit */ + partial = chain+depth-1; /* the whole chain */ + goto cleanup; + } + + /* Next simple case - plain lookup or failed read of indirect block */ + if (!create || err == -EIO) { +cleanup: + while (partial > chain) { + brelse(partial->bh); + partial--; + } +out: + return err; + } + + /* + * Indirect block might be removed by truncate while we were + * reading it. Handling of that case (forget what we've got and + * reread) is taken out of the main path. + */ + if (err == -EAGAIN) + goto changed; + + goal = 0; + if (ext2_find_goal(inode, iblock, chain, partial, &goal) < 0) + goto changed; + + left = (chain + depth) - partial; + err = ext2_alloc_branch(inode, left, goal, + offsets+(partial-chain), partial); + if (err) + goto cleanup; + + if (ext2_splice_branch(inode, iblock, chain, partial, left) < 0) + goto changed; + + set_buffer_new(bh_result); + goto got_it; + +changed: + while (partial > chain) { + brelse(partial->bh); + partial--; + } + goto reread; +} + +static int ext2_writepage(struct page *page, struct writeback_control *wbc) +{ + return block_write_full_page(page, ext2_get_block, wbc); +} + +static int ext2_readpage(struct file *file, struct page *page) +{ + return mpage_readpage(page, ext2_get_block); +} + +static int +ext2_readpages(struct file *file, struct address_space *mapping, + struct list_head *pages, unsigned nr_pages) +{ + return mpage_readpages(mapping, pages, nr_pages, ext2_get_block); +} + +static int +ext2_prepare_write(struct file *file, struct page *page, + unsigned from, unsigned to) +{ + return block_prepare_write(page,from,to,ext2_get_block); +} + +static int +ext2_nobh_prepare_write(struct file *file, struct page *page, + unsigned from, unsigned to) +{ + return nobh_prepare_write(page,from,to,ext2_get_block); +} + +static int ext2_nobh_writepage(struct page *page, + struct writeback_control *wbc) +{ + return nobh_writepage(page, ext2_get_block, wbc); +} + +static sector_t ext2_bmap(struct address_space *mapping, sector_t block) +{ + return generic_block_bmap(mapping,block,ext2_get_block); +} + +static int +ext2_get_blocks(struct inode *inode, sector_t iblock, unsigned long max_blocks, + struct buffer_head *bh_result, int create) +{ + int ret; + + ret = ext2_get_block(inode, iblock, bh_result, create); + if (ret == 0) + bh_result->b_size = (1 << inode->i_blkbits); + return ret; +} + +static ssize_t +ext2_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, + loff_t offset, unsigned long nr_segs) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + + return blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, + offset, nr_segs, ext2_get_blocks, NULL); +} + +static int +ext2_writepages(struct address_space *mapping, struct writeback_control *wbc) +{ + return mpage_writepages(mapping, wbc, ext2_get_block); +} + +struct address_space_operations ext2_aops = { + .readpage = ext2_readpage, + .readpages = ext2_readpages, + .writepage = ext2_writepage, + .sync_page = block_sync_page, + .prepare_write = ext2_prepare_write, + .commit_write = generic_commit_write, + .bmap = ext2_bmap, + .direct_IO = ext2_direct_IO, + .writepages = ext2_writepages, +}; + +struct address_space_operations ext2_nobh_aops = { + .readpage = ext2_readpage, + .readpages = ext2_readpages, + .writepage = ext2_nobh_writepage, + .sync_page = block_sync_page, + .prepare_write = ext2_nobh_prepare_write, + .commit_write = nobh_commit_write, + .bmap = ext2_bmap, + .direct_IO = ext2_direct_IO, + .writepages = ext2_writepages, +}; + +/* + * 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) +{ + while (p < q) + if (*p++) + return 0; + return 1; +} + +/** + * ext2_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 ext2_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 ext2_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 refered 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 ext2_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].p + * (no partially truncated stuff there). + */ + +static Indirect *ext2_find_shared(struct inode *inode, + int depth, + int offsets[4], + Indirect chain[4], + __le32 *top) +{ + Indirect *partial, *p; + int k, err; + + *top = 0; + for (k = depth; k > 1 && !offsets[k-1]; k--) + ; + partial = ext2_get_branch(inode, k, offsets, chain, &err); + if (!partial) + partial = chain + k-1; + /* + * If the branch acquired continuation since we've looked at it - + * fine, it should all survive and (new) top doesn't belong to us. + */ + write_lock(&EXT2_I(inode)->i_meta_lock); + if (!partial->key && *partial->p) { + write_unlock(&EXT2_I(inode)->i_meta_lock); + goto no_top; + } + for (p=partial; p>chain && all_zeroes((__le32*)p->bh->b_data,p->p); p--) + ; + /* + * OK, we've found the last block that must survive. The rest of our + * branch should be detached before unlocking. However, if that rest + * of branch is all ours and does not grow immediately from the inode + * it's easier to cheat and just decrement partial->p. + */ + if (p == chain + k - 1 && p > chain) { + p->p--; + } else { + *top = *p->p; + *p->p = 0; + } + write_unlock(&EXT2_I(inode)->i_meta_lock); + + while(partial > p) + { + brelse(partial->bh); + partial--; + } +no_top: + return partial; +} + +/** + * ext2_free_data - free a list of data blocks + * @inode: inode we are dealing with + * @p: array of block numbers + * @q: points immediately past the end of array + * + * We are freeing all blocks refered from that array (numbers are + * stored as little-endian 32-bit) and updating @inode->i_blocks + * appropriately. + */ +static inline void ext2_free_data(struct inode *inode, __le32 *p, __le32 *q) +{ + unsigned long block_to_free = 0, count = 0; + unsigned long nr; + + for ( ; p < q ; p++) { + nr = le32_to_cpu(*p); + if (nr) { + *p = 0; + /* accumulate blocks to free if they're contiguous */ + if (count == 0) + goto free_this; + else if (block_to_free == nr - count) + count++; + else { + mark_inode_dirty(inode); + ext2_free_blocks (inode, block_to_free, count); + free_this: + block_to_free = nr; + count = 1; + } + } + } + if (count > 0) { + mark_inode_dirty(inode); + ext2_free_blocks (inode, block_to_free, count); + } +} + +/** + * ext2_free_branches - free an array of branches + * @inode: inode we are dealing with + * @p: array of block numbers + * @q: pointer immediately past the end of array + * @depth: depth of the branches to free + * + * We are freeing all blocks refered from these branches (numbers are + * stored as little-endian 32-bit) and updating @inode->i_blocks + * appropriately. + */ +static void ext2_free_branches(struct inode *inode, __le32 *p, __le32 *q, int depth) +{ + struct buffer_head * bh; + unsigned long nr; + + if (depth--) { + int addr_per_block = EXT2_ADDR_PER_BLOCK(inode->i_sb); + for ( ; p < q ; p++) { + nr = le32_to_cpu(*p); + if (!nr) + continue; + *p = 0; + bh = sb_bread(inode->i_sb, nr); + /* + * A read failure? Report error and clear slot + * (should be rare). + */ + if (!bh) { + ext2_error(inode->i_sb, "ext2_free_branches", + "Read failure, inode=%ld, block=%ld", + inode->i_ino, nr); + continue; + } + ext2_free_branches(inode, + (__le32*)bh->b_data, + (__le32*)bh->b_data + addr_per_block, + depth); + bforget(bh); + ext2_free_blocks(inode, nr, 1); + mark_inode_dirty(inode); + } + } else + ext2_free_data(inode, p, q); +} + +void ext2_truncate (struct inode * inode) +{ + __le32 *i_data = EXT2_I(inode)->i_data; + int addr_per_block = EXT2_ADDR_PER_BLOCK(inode->i_sb); + int offsets[4]; + Indirect chain[4]; + Indirect *partial; + __le32 nr = 0; + int n; + long iblock; + unsigned blocksize; + + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode))) + return; + if (ext2_inode_is_fast_symlink(inode)) + return; + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + return; + + ext2_discard_prealloc(inode); + + blocksize = inode->i_sb->s_blocksize; + iblock = (inode->i_size + blocksize-1) + >> EXT2_BLOCK_SIZE_BITS(inode->i_sb); + + if (test_opt(inode->i_sb, NOBH)) + nobh_truncate_page(inode->i_mapping, inode->i_size); + else + block_truncate_page(inode->i_mapping, + inode->i_size, ext2_get_block); + + n = ext2_block_to_path(inode, iblock, offsets, NULL); + if (n == 0) + return; + + if (n == 1) { + ext2_free_data(inode, i_data+offsets[0], + i_data + EXT2_NDIR_BLOCKS); + goto do_indirects; + } + + partial = ext2_find_shared(inode, n, offsets, chain, &nr); + /* Kill the top of shared branch (already detached) */ + if (nr) { + if (partial == chain) + mark_inode_dirty(inode); + else + mark_buffer_dirty_inode(partial->bh, inode); + ext2_free_branches(inode, &nr, &nr+1, (chain+n-1) - partial); + } + /* Clear the ends of indirect blocks on the shared branch */ + while (partial > chain) { + ext2_free_branches(inode, + partial->p + 1, + (__le32*)partial->bh->b_data+addr_per_block, + (chain+n-1) - partial); + mark_buffer_dirty_inode(partial->bh, inode); + brelse (partial->bh); + partial--; + } +do_indirects: + /* Kill the remaining (whole) subtrees */ + switch (offsets[0]) { + default: + nr = i_data[EXT2_IND_BLOCK]; + if (nr) { + i_data[EXT2_IND_BLOCK] = 0; + mark_inode_dirty(inode); + ext2_free_branches(inode, &nr, &nr+1, 1); + } + case EXT2_IND_BLOCK: + nr = i_data[EXT2_DIND_BLOCK]; + if (nr) { + i_data[EXT2_DIND_BLOCK] = 0; + mark_inode_dirty(inode); + ext2_free_branches(inode, &nr, &nr+1, 2); + } + case EXT2_DIND_BLOCK: + nr = i_data[EXT2_TIND_BLOCK]; + if (nr) { + i_data[EXT2_TIND_BLOCK] = 0; + mark_inode_dirty(inode); + ext2_free_branches(inode, &nr, &nr+1, 3); + } + case EXT2_TIND_BLOCK: + ; + } + inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; + if (inode_needs_sync(inode)) { + sync_mapping_buffers(inode->i_mapping); + ext2_sync_inode (inode); + } else { + mark_inode_dirty(inode); + } +} + +static struct ext2_inode *ext2_get_inode(struct super_block *sb, ino_t ino, + struct buffer_head **p) +{ + struct buffer_head * bh; + unsigned long block_group; + unsigned long block; + unsigned long offset; + struct ext2_group_desc * gdp; + + *p = NULL; + if ((ino != EXT2_ROOT_INO && ino < EXT2_FIRST_INO(sb)) || + ino > le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count)) + goto Einval; + + block_group = (ino - 1) / EXT2_INODES_PER_GROUP(sb); + gdp = ext2_get_group_desc(sb, block_group, &bh); + if (!gdp) + goto Egdp; + /* + * Figure out the offset within the block group inode table + */ + offset = ((ino - 1) % EXT2_INODES_PER_GROUP(sb)) * EXT2_INODE_SIZE(sb); + block = le32_to_cpu(gdp->bg_inode_table) + + (offset >> EXT2_BLOCK_SIZE_BITS(sb)); + if (!(bh = sb_bread(sb, block))) + goto Eio; + + *p = bh; + offset &= (EXT2_BLOCK_SIZE(sb) - 1); + return (struct ext2_inode *) (bh->b_data + offset); + +Einval: + ext2_error(sb, "ext2_get_inode", "bad inode number: %lu", + (unsigned long) ino); + return ERR_PTR(-EINVAL); +Eio: + ext2_error(sb, "ext2_get_inode", + "unable to read inode block - inode=%lu, block=%lu", + (unsigned long) ino, block); +Egdp: + return ERR_PTR(-EIO); +} + +void ext2_set_inode_flags(struct inode *inode) +{ + unsigned int flags = EXT2_I(inode)->i_flags; + + inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC); + if (flags & EXT2_SYNC_FL) + inode->i_flags |= S_SYNC; + if (flags & EXT2_APPEND_FL) + inode->i_flags |= S_APPEND; + if (flags & EXT2_IMMUTABLE_FL) + inode->i_flags |= S_IMMUTABLE; + if (flags & EXT2_NOATIME_FL) + inode->i_flags |= S_NOATIME; + if (flags & EXT2_DIRSYNC_FL) + inode->i_flags |= S_DIRSYNC; +} + +void ext2_read_inode (struct inode * inode) +{ + struct ext2_inode_info *ei = EXT2_I(inode); + ino_t ino = inode->i_ino; + struct buffer_head * bh; + struct ext2_inode * raw_inode = ext2_get_inode(inode->i_sb, ino, &bh); + int n; + +#ifdef CONFIG_EXT2_FS_POSIX_ACL + ei->i_acl = EXT2_ACL_NOT_CACHED; + ei->i_default_acl = EXT2_ACL_NOT_CACHED; +#endif + if (IS_ERR(raw_inode)) + goto bad_inode; + + inode->i_mode = le16_to_cpu(raw_inode->i_mode); + inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); + inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); + if (!(test_opt (inode->i_sb, NO_UID32))) { + inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; + inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; + } + inode->i_nlink = le16_to_cpu(raw_inode->i_links_count); + inode->i_size = le32_to_cpu(raw_inode->i_size); + inode->i_atime.tv_sec = le32_to_cpu(raw_inode->i_atime); + inode->i_ctime.tv_sec = le32_to_cpu(raw_inode->i_ctime); + inode->i_mtime.tv_sec = le32_to_cpu(raw_inode->i_mtime); + inode->i_atime.tv_nsec = inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = 0; + ei->i_dtime = le32_to_cpu(raw_inode->i_dtime); + /* We now have enough fields to check if the inode was active or not. + * This is needed because nfsd might try to access dead inodes + * the test is that same one that e2fsck uses + * NeilBrown 1999oct15 + */ + if (inode->i_nlink == 0 && (inode->i_mode == 0 || ei->i_dtime)) { + /* this inode is deleted */ + brelse (bh); + goto bad_inode; + } + inode->i_blksize = PAGE_SIZE; /* This is the optimal IO size (for stat), not the fs block size */ + inode->i_blocks = le32_to_cpu(raw_inode->i_blocks); + ei->i_flags = le32_to_cpu(raw_inode->i_flags); + ei->i_faddr = le32_to_cpu(raw_inode->i_faddr); + ei->i_frag_no = raw_inode->i_frag; + ei->i_frag_size = raw_inode->i_fsize; + ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl); + ei->i_dir_acl = 0; + if (S_ISREG(inode->i_mode)) + inode->i_size |= ((__u64)le32_to_cpu(raw_inode->i_size_high)) << 32; + else + ei->i_dir_acl = le32_to_cpu(raw_inode->i_dir_acl); + ei->i_dtime = 0; + inode->i_generation = le32_to_cpu(raw_inode->i_generation); + ei->i_state = 0; + ei->i_next_alloc_block = 0; + ei->i_next_alloc_goal = 0; + ei->i_prealloc_count = 0; + ei->i_block_group = (ino - 1) / EXT2_INODES_PER_GROUP(inode->i_sb); + ei->i_dir_start_lookup = 0; + + /* + * NOTE! The in-memory inode i_data array is in little-endian order + * even on big-endian machines: we do NOT byteswap the block numbers! |