// SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/namei.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/namei.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller ([email protected]), 1995 * Directory entry file type support and forward compatibility hooks * for B-tree directories by Theodore Ts'o ([email protected]), 1998 * Hash Tree Directory indexing (c) * Daniel Phillips, 2001 * Hash Tree Directory indexing porting * Christopher Li, 2002 * Hash Tree Directory indexing cleanup * Theodore Ts'o, 2002 */ #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/time.h> #include <linux/fcntl.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/quotaops.h> #include <linux/buffer_head.h> #include <linux/bio.h> #include <linux/iversion.h> #include <linux/unicode.h> #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include <trace/events/ext4.h> /* * define how far ahead to read directories while searching them. */ #define NAMEI_RA_CHUNKS … #define NAMEI_RA_BLOCKS … #define NAMEI_RA_SIZE … static struct buffer_head *ext4_append(handle_t *handle, struct inode *inode, ext4_lblk_t *block) { … } static int ext4_dx_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent); /* * Hints to ext4_read_dirblock regarding whether we expect a directory * block being read to be an index block, or a block containing * directory entries (and if the latter, whether it was found via a * logical block in an htree index block). This is used to control * what sort of sanity checkinig ext4_read_dirblock() will do on the * directory block read from the storage device. EITHER will means * the caller doesn't know what kind of directory block will be read, * so no specific verification will be done. */ dirblock_type_t; #define ext4_read_dirblock(inode, block, type) … static struct buffer_head *__ext4_read_dirblock(struct inode *inode, ext4_lblk_t block, dirblock_type_t type, const char *func, unsigned int line) { … } #ifdef DX_DEBUG #define dxtrace … #else #define dxtrace(command) … #endif struct fake_dirent { … }; struct dx_countlimit { … }; struct dx_entry { … }; /* * dx_root_info is laid out so that if it should somehow get overlaid by a * dirent the two low bits of the hash version will be zero. Therefore, the * hash version mod 4 should never be 0. Sincerely, the paranoia department. */ struct dx_root { … }; struct dx_node { … }; struct dx_frame { … }; struct dx_map_entry { … }; /* * This goes at the end of each htree block. */ struct dx_tail { … }; static inline ext4_lblk_t dx_get_block(struct dx_entry *entry); static void dx_set_block(struct dx_entry *entry, ext4_lblk_t value); static inline unsigned dx_get_hash(struct dx_entry *entry); static void dx_set_hash(struct dx_entry *entry, unsigned value); static unsigned dx_get_count(struct dx_entry *entries); static unsigned dx_get_limit(struct dx_entry *entries); static void dx_set_count(struct dx_entry *entries, unsigned value); static void dx_set_limit(struct dx_entry *entries, unsigned value); static unsigned dx_root_limit(struct inode *dir, unsigned infosize); static unsigned dx_node_limit(struct inode *dir); static struct dx_frame *dx_probe(struct ext4_filename *fname, struct inode *dir, struct dx_hash_info *hinfo, struct dx_frame *frame); static void dx_release(struct dx_frame *frames); static int dx_make_map(struct inode *dir, struct buffer_head *bh, struct dx_hash_info *hinfo, struct dx_map_entry *map_tail); static void dx_sort_map(struct dx_map_entry *map, unsigned count); static struct ext4_dir_entry_2 *dx_move_dirents(struct inode *dir, char *from, char *to, struct dx_map_entry *offsets, int count, unsigned int blocksize); static struct ext4_dir_entry_2 *dx_pack_dirents(struct inode *dir, char *base, unsigned int blocksize); static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block); static int ext4_htree_next_block(struct inode *dir, __u32 hash, struct dx_frame *frame, struct dx_frame *frames, __u32 *start_hash); static struct buffer_head * ext4_dx_find_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir); static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode); /* checksumming functions */ void ext4_initialize_dirent_tail(struct buffer_head *bh, unsigned int blocksize) { … } /* Walk through a dirent block to find a checksum "dirent" at the tail */ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, struct buffer_head *bh) { … } static __le32 ext4_dirblock_csum(struct inode *inode, void *dirent, int size) { … } #define warn_no_space_for_csum(inode) … static void __warn_no_space_for_csum(struct inode *inode, const char *func, unsigned int line) { … } int ext4_dirblock_csum_verify(struct inode *inode, struct buffer_head *bh) { … } static void ext4_dirblock_csum_set(struct inode *inode, struct buffer_head *bh) { … } int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode, struct buffer_head *bh) { … } static struct dx_countlimit *get_dx_countlimit(struct inode *inode, struct ext4_dir_entry *dirent, int *offset) { … } static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent, int count_offset, int count, struct dx_tail *t) { … } static int ext4_dx_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent) { … } static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry *dirent) { … } static inline int ext4_handle_dirty_dx_node(handle_t *handle, struct inode *inode, struct buffer_head *bh) { … } /* * p is at least 6 bytes before the end of page */ static inline struct ext4_dir_entry_2 * ext4_next_entry(struct ext4_dir_entry_2 *p, unsigned long blocksize) { … } /* * Future: use high four bits of block for coalesce-on-delete flags * Mask them off for now. */ static inline ext4_lblk_t dx_get_block(struct dx_entry *entry) { … } static inline void dx_set_block(struct dx_entry *entry, ext4_lblk_t value) { … } static inline unsigned dx_get_hash(struct dx_entry *entry) { … } static inline void dx_set_hash(struct dx_entry *entry, unsigned value) { … } static inline unsigned dx_get_count(struct dx_entry *entries) { … } static inline unsigned dx_get_limit(struct dx_entry *entries) { … } static inline void dx_set_count(struct dx_entry *entries, unsigned value) { … } static inline void dx_set_limit(struct dx_entry *entries, unsigned value) { … } static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize) { … } static inline unsigned dx_node_limit(struct inode *dir) { … } /* * Debug */ #ifdef DX_DEBUG static void dx_show_index(char * label, struct dx_entry *entries) { int i, n = dx_get_count (entries); printk(KERN_DEBUG "%s index", label); for (i = 0; i < n; i++) { printk(KERN_CONT " %x->%lu", i ? dx_get_hash(entries + i) : 0, (unsigned long)dx_get_block(entries + i)); } printk(KERN_CONT "\n"); } struct stats { unsigned names; unsigned space; unsigned bcount; }; static struct stats dx_show_leaf(struct inode *dir, struct dx_hash_info *hinfo, struct ext4_dir_entry_2 *de, int size, int show_names) { unsigned names = 0, space = 0; char *base = (char *) de; struct dx_hash_info h = *hinfo; printk("names: "); while ((char *) de < base + size) { if (de->inode) { if (show_names) { #ifdef CONFIG_FS_ENCRYPTION int len; char *name; struct fscrypt_str fname_crypto_str = FSTR_INIT(NULL, 0); int res = 0; name = de->name; len = de->name_len; if (!IS_ENCRYPTED(dir)) { /* Directory is not encrypted */ (void) ext4fs_dirhash(dir, de->name, de->name_len, &h); printk("%*.s:(U)%x.%u ", len, name, h.hash, (unsigned) ((char *) de - base)); } else { struct fscrypt_str de_name = FSTR_INIT(name, len); /* Directory is encrypted */ res = fscrypt_fname_alloc_buffer( len, &fname_crypto_str); if (res) printk(KERN_WARNING "Error " "allocating crypto " "buffer--skipping " "crypto\n"); res = fscrypt_fname_disk_to_usr(dir, 0, 0, &de_name, &fname_crypto_str); if (res) { printk(KERN_WARNING "Error " "converting filename " "from disk to usr" "\n"); name = "??"; len = 2; } else { name = fname_crypto_str.name; len = fname_crypto_str.len; } if (IS_CASEFOLDED(dir)) h.hash = EXT4_DIRENT_HASH(de); else (void) ext4fs_dirhash(dir, de->name, de->name_len, &h); printk("%*.s:(E)%x.%u ", len, name, h.hash, (unsigned) ((char *) de - base)); fscrypt_fname_free_buffer( &fname_crypto_str); } #else int len = de->name_len; char *name = de->name; (void) ext4fs_dirhash(dir, de->name, de->name_len, &h); printk("%*.s:%x.%u ", len, name, h.hash, (unsigned) ((char *) de - base)); #endif } space += ext4_dir_rec_len(de->name_len, dir); names++; } de = ext4_next_entry(de, size); } printk(KERN_CONT "(%i)\n", names); return (struct stats) { names, space, 1 }; } struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir, struct dx_entry *entries, int levels) { unsigned blocksize = dir->i_sb->s_blocksize; unsigned count = dx_get_count(entries), names = 0, space = 0, i; unsigned bcount = 0; struct buffer_head *bh; printk("%i indexed blocks...\n", count); for (i = 0; i < count; i++, entries++) { ext4_lblk_t block = dx_get_block(entries); ext4_lblk_t hash = i ? dx_get_hash(entries): 0; u32 range = i < count - 1? (dx_get_hash(entries + 1) - hash): ~hash; struct stats stats; printk("%s%3u:%03u hash %8x/%8x ",levels?"":" ", i, block, hash, range); bh = ext4_bread(NULL,dir, block, 0); if (!bh || IS_ERR(bh)) continue; stats = levels? dx_show_entries(hinfo, dir, ((struct dx_node *) bh->b_data)->entries, levels - 1): dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *) bh->b_data, blocksize, 0); names += stats.names; space += stats.space; bcount += stats.bcount; brelse(bh); } if (bcount) printk(KERN_DEBUG "%snames %u, fullness %u (%u%%)\n", levels ? "" : " ", names, space/bcount, (space/bcount)*100/blocksize); return (struct stats) { names, space, bcount}; } /* * Linear search cross check */ static inline void htree_rep_invariant_check(struct dx_entry *at, struct dx_entry *target, u32 hash, unsigned int n) { while (n--) { dxtrace(printk(KERN_CONT ",")); if (dx_get_hash(++at) > hash) { at--; break; } } ASSERT(at == target - 1); } #else /* DX_DEBUG */ static inline void htree_rep_invariant_check(struct dx_entry *at, struct dx_entry *target, u32 hash, unsigned int n) { … } #endif /* DX_DEBUG */ /* * Probe for a directory leaf block to search. * * dx_probe can return ERR_BAD_DX_DIR, which means there was a format * error in the directory index, and the caller should fall back to * searching the directory normally. The callers of dx_probe **MUST** * check for this error code, and make sure it never gets reflected * back to userspace. */ static struct dx_frame * dx_probe(struct ext4_filename *fname, struct inode *dir, struct dx_hash_info *hinfo, struct dx_frame *frame_in) { … } static void dx_release(struct dx_frame *frames) { … } /* * This function increments the frame pointer to search the next leaf * block, and reads in the necessary intervening nodes if the search * should be necessary. Whether or not the search is necessary is * controlled by the hash parameter. If the hash value is even, then * the search is only continued if the next block starts with that * hash value. This is used if we are searching for a specific file. * * If the hash value is HASH_NB_ALWAYS, then always go to the next block. * * This function returns 1 if the caller should continue to search, * or 0 if it should not. If there is an error reading one of the * index blocks, it will a negative error code. * * If start_hash is non-null, it will be filled in with the starting * hash of the next page. */ static int ext4_htree_next_block(struct inode *dir, __u32 hash, struct dx_frame *frame, struct dx_frame *frames, __u32 *start_hash) { … } /* * This function fills a red-black tree with information from a * directory block. It returns the number directory entries loaded * into the tree. If there is an error it is returned in err. */ static int htree_dirblock_to_tree(struct file *dir_file, struct inode *dir, ext4_lblk_t block, struct dx_hash_info *hinfo, __u32 start_hash, __u32 start_minor_hash) { … } /* * This function fills a red-black tree with information from a * directory. We start scanning the directory in hash order, starting * at start_hash and start_minor_hash. * * This function returns the number of entries inserted into the tree, * or a negative error code. */ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, __u32 start_minor_hash, __u32 *next_hash) { … } static inline int search_dirblock(struct buffer_head *bh, struct inode *dir, struct ext4_filename *fname, unsigned int offset, struct ext4_dir_entry_2 **res_dir) { … } /* * Directory block splitting, compacting */ /* * Create map of hash values, offsets, and sizes, stored at end of block. * Returns number of entries mapped. */ static int dx_make_map(struct inode *dir, struct buffer_head *bh, struct dx_hash_info *hinfo, struct dx_map_entry *map_tail) { … } /* Sort map by hash value */ static void dx_sort_map (struct dx_map_entry *map, unsigned count) { … } static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) { … } #if IS_ENABLED(CONFIG_UNICODE) int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, struct ext4_filename *name) { … } #endif /* * Test whether a directory entry matches the filename being searched for. * * Return: %true if the directory entry matches, otherwise %false. */ static bool ext4_match(struct inode *parent, const struct ext4_filename *fname, struct ext4_dir_entry_2 *de) { … } /* * Returns 0 if not found, -1 on failure, and 1 on success */ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, struct inode *dir, struct ext4_filename *fname, unsigned int offset, struct ext4_dir_entry_2 **res_dir) { … } static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block, struct ext4_dir_entry *de) { … } /* * __ext4_find_entry() * * finds an entry in the specified directory with the wanted name. It * returns the cache buffer in which the entry was found, and the entry * itself (as a parameter - res_dir). It does NOT read the inode of the * entry - you'll have to do that yourself if you want to. * * The returned buffer_head has ->b_count elevated. The caller is expected * to brelse() it when appropriate. */ static struct buffer_head *__ext4_find_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir, int *inlined) { … } static struct buffer_head *ext4_find_entry(struct inode *dir, const struct qstr *d_name, struct ext4_dir_entry_2 **res_dir, int *inlined) { … } static struct buffer_head *ext4_lookup_entry(struct inode *dir, struct dentry *dentry, struct ext4_dir_entry_2 **res_dir) { … } static struct buffer_head * ext4_dx_find_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir) { … } static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { … } struct dentry *ext4_get_parent(struct dentry *child) { … } /* * Move count entries from end of map between two memory locations. * Returns pointer to last entry moved. */ static struct ext4_dir_entry_2 * dx_move_dirents(struct inode *dir, char *from, char *to, struct dx_map_entry *map, int count, unsigned blocksize) { … } /* * Compact each dir entry in the range to the minimal rec_len. * Returns pointer to last entry in range. */ static struct ext4_dir_entry_2 *dx_pack_dirents(struct inode *dir, char *base, unsigned int blocksize) { … } /* * Split a full leaf block to make room for a new dir entry. * Allocate a new block, and move entries so that they are approx. equally full. * Returns pointer to de in block into which the new entry will be inserted. */ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, struct buffer_head **bh,struct dx_frame *frame, struct dx_hash_info *hinfo) { … } int ext4_find_dest_de(struct inode *dir, struct inode *inode, struct buffer_head *bh, void *buf, int buf_size, struct ext4_filename *fname, struct ext4_dir_entry_2 **dest_de) { … } void ext4_insert_dentry(struct inode *dir, struct inode *inode, struct ext4_dir_entry_2 *de, int buf_size, struct ext4_filename *fname) { … } /* * Add a new entry into a directory (leaf) block. If de is non-NULL, * it points to a directory entry which is guaranteed to be large * enough for new directory entry. If de is NULL, then * add_dirent_to_buf will attempt search the directory block for * space. It will return -ENOSPC if no space is available, and -EIO * and -EEXIST if directory entry already exists. */ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode, struct ext4_dir_entry_2 *de, struct buffer_head *bh) { … } static bool ext4_check_dx_root(struct inode *dir, struct dx_root *root) { … } /* * This converts a one block unindexed directory to a 3 block indexed * directory, and adds the dentry to the indexed directory. */ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode, struct buffer_head *bh) { … } /* * ext4_add_entry() * * adds a file entry to the specified directory, using the same * semantics as ext4_find_entry(). It returns NULL if it failed. * * NOTE!! The inode part of 'de' is left at 0 - which means you * may not sleep between calling this and putting something into * the entry, as someone else might have used it while you slept. */ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, struct inode *inode) { … } /* * Returns 0 for success, or a negative error value */ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode) { … } /* * ext4_generic_delete_entry deletes a directory entry by merging it * with the previous entry */ int ext4_generic_delete_entry(struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, void *entry_buf, int buf_size, int csum_size) { … } static int ext4_delete_entry(handle_t *handle, struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh) { … } /* * Set directory link count to 1 if nlinks > EXT4_LINK_MAX, or if nlinks == 2 * since this indicates that nlinks count was previously 1 to avoid overflowing * the 16-bit i_links_count field on disk. Directories with i_nlink == 1 mean * that subdirectory link counts are not being maintained accurately. * * The caller has already checked for i_nlink overflow in case the DIR_LINK * feature is not enabled and returned -EMLINK. The is_dx() check is a proxy * for checking S_ISDIR(inode) (since the INODE_INDEX feature will not be set * on regular files) and to avoid creating huge/slow non-HTREE directories. */ static void ext4_inc_count(struct inode *inode) { … } /* * If a directory had nlink == 1, then we should let it be 1. This indicates * directory has >EXT4_LINK_MAX subdirs. */ static void ext4_dec_count(struct inode *inode) { … } /* * Add non-directory inode to a directory. On success, the inode reference is * consumed by dentry is instantiation. This is also indicated by clearing of * *inodep pointer. On failure, the caller is responsible for dropping the * inode reference in the safe context. */ static int ext4_add_nondir(handle_t *handle, struct dentry *dentry, struct inode **inodep) { … } /* * By the time this is called, we already have created * the directory cache entry for the new file, but it * is so far negative - it has no inode. * * If the create succeeds, we fill in the inode information * with d_instantiate(). */ static int ext4_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { … } static int ext4_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { … } static int ext4_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { … } struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode, struct ext4_dir_entry_2 *de, int blocksize, int csum_size, unsigned int parent_ino, int dotdot_real_len) { … } int ext4_init_new_dir(handle_t *handle, struct inode *dir, struct inode *inode) { … } static int ext4_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { … } /* * routine to check that the specified directory is empty (for rmdir) */ bool ext4_empty_dir(struct inode *inode) { … } static int ext4_rmdir(struct inode *dir, struct dentry *dentry) { … } int __ext4_unlink(struct inode *dir, const struct qstr *d_name, struct inode *inode, struct dentry *dentry /* NULL during fast_commit recovery */) { … } static int ext4_unlink(struct inode *dir, struct dentry *dentry) { … } static int ext4_init_symlink_block(handle_t *handle, struct inode *inode, struct fscrypt_str *disk_link) { … } static int ext4_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { … } int __ext4_link(struct inode *dir, struct inode *inode, struct dentry *dentry) { … } static int ext4_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { … } /* * Try to find buffer head where contains the parent block. * It should be the inode block if it is inlined or the 1st block * if it is a normal dir. */ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle, struct inode *inode, int *retval, struct ext4_dir_entry_2 **parent_de, int *inlined) { … } struct ext4_renament { … }; static int ext4_rename_dir_prepare(handle_t *handle, struct ext4_renament *ent, bool is_cross) { … } static int ext4_rename_dir_finish(handle_t *handle, struct ext4_renament *ent, unsigned dir_ino) { … } static int ext4_setent(handle_t *handle, struct ext4_renament *ent, unsigned ino, unsigned file_type) { … } static void ext4_resetent(handle_t *handle, struct ext4_renament *ent, unsigned ino, unsigned file_type) { … } static int ext4_find_delete_entry(handle_t *handle, struct inode *dir, const struct qstr *d_name) { … } static void ext4_rename_delete(handle_t *handle, struct ext4_renament *ent, int force_reread) { … } static void ext4_update_dir_count(handle_t *handle, struct ext4_renament *ent) { … } static struct inode *ext4_whiteout_for_rename(struct mnt_idmap *idmap, struct ext4_renament *ent, int credits, handle_t **h) { … } /* * Anybody can rename anything with this: the permission checks are left to the * higher-level routines. * * n.b. old_{dentry,inode) refers to the source dentry/inode * while new_{dentry,inode) refers to the destination dentry/inode * This comes from rename(const char *oldpath, const char *newpath) */ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { … } static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { … } static int ext4_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { … } /* * directories can handle most operations... */ const struct inode_operations ext4_dir_inode_operations = …; const struct inode_operations ext4_special_inode_operations = …;
Codebase Browser
linux