diff options
Diffstat (limited to 'fs/dcache.c')
| -rw-r--r-- | fs/dcache.c | 308 |
1 files changed, 144 insertions, 164 deletions
diff --git a/fs/dcache.c b/fs/dcache.c index ad4a542e9bab..b90cf8e09d5b 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -104,11 +104,9 @@ static unsigned int d_hash_shift __read_mostly; static struct hlist_bl_head *dentry_hashtable __read_mostly; -static inline struct hlist_bl_head *d_hash(const struct dentry *parent, - unsigned int hash) +static inline struct hlist_bl_head *d_hash(unsigned int hash) { - hash += (unsigned long) parent / L1_CACHE_BYTES; - return dentry_hashtable + hash_32(hash, d_hash_shift); + return dentry_hashtable + (hash >> (32 - d_hash_shift)); } #define IN_LOOKUP_SHIFT 10 @@ -226,10 +224,9 @@ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount) { - const unsigned char *cs; /* * Be careful about RCU walk racing with rename: - * use ACCESS_ONCE to fetch the name pointer. + * use 'lockless_dereference' to fetch the name pointer. * * NOTE! Even if a rename will mean that the length * was not loaded atomically, we don't care. The @@ -243,8 +240,8 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c * early because the data cannot match (there can * be no NUL in the ct/tcount data) */ - cs = ACCESS_ONCE(dentry->d_name.name); - smp_read_barrier_depends(); + const unsigned char *cs = lockless_dereference(dentry->d_name.name); + return dentry_string_cmp(cs, ct, tcount); } @@ -335,44 +332,21 @@ static inline void dentry_rcuwalk_invalidate(struct dentry *dentry) /* * Release the dentry's inode, using the filesystem - * d_iput() operation if defined. Dentry has no refcount - * and is unhashed. - */ -static void dentry_iput(struct dentry * dentry) - __releases(dentry->d_lock) - __releases(dentry->d_inode->i_lock) -{ - struct inode *inode = dentry->d_inode; - if (inode) { - __d_clear_type_and_inode(dentry); - hlist_del_init(&dentry->d_u.d_alias); - spin_unlock(&dentry->d_lock); - spin_unlock(&inode->i_lock); - if (!inode->i_nlink) - fsnotify_inoderemove(inode); - if (dentry->d_op && dentry->d_op->d_iput) - dentry->d_op->d_iput(dentry, inode); - else - iput(inode); - } else { - spin_unlock(&dentry->d_lock); - } -} - -/* - * Release the dentry's inode, using the filesystem - * d_iput() operation if defined. dentry remains in-use. + * d_iput() operation if defined. */ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_lock) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; + bool hashed = !d_unhashed(dentry); - raw_write_seqcount_begin(&dentry->d_seq); + if (hashed) + raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); - raw_write_seqcount_end(&dentry->d_seq); + if (hashed) + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -488,7 +462,7 @@ void __d_drop(struct dentry *dentry) if (unlikely(IS_ROOT(dentry))) b = &dentry->d_sb->s_anon; else - b = d_hash(dentry->d_parent, dentry->d_name.hash); + b = d_hash(dentry->d_name.hash); hlist_bl_lock(b); __hlist_bl_del(&dentry->d_hash); @@ -507,6 +481,44 @@ void d_drop(struct dentry *dentry) } EXPORT_SYMBOL(d_drop); +static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent) +{ + struct dentry *next; + /* + * Inform d_walk() and shrink_dentry_list() that we are no longer + * attached to the dentry tree + */ + dentry->d_flags |= DCACHE_DENTRY_KILLED; + if (unlikely(list_empty(&dentry->d_child))) + return; + __list_del_entry(&dentry->d_child); + /* + * Cursors can move around the list of children. While we'd been + * a normal list member, it didn't matter - ->d_child.next would've + * been updated. However, from now on it won't be and for the + * things like d_walk() it might end up with a nasty surprise. + * Normally d_walk() doesn't care about cursors moving around - + * ->d_lock on parent prevents that and since a cursor has no children + * of its own, we get through it without ever unlocking the parent. + * There is one exception, though - if we ascend from a child that + * gets killed as soon as we unlock it, the next sibling is found + * using the value left in its ->d_child.next. And if _that_ + * pointed to a cursor, and cursor got moved (e.g. by lseek()) + * before d_walk() regains parent->d_lock, we'll end up skipping + * everything the cursor had been moved past. + * + * Solution: make sure that the pointer left behind in ->d_child.next + * points to something that won't be moving around. I.e. skip the + * cursors. + */ + while (dentry->d_child.next != &parent->d_subdirs) { + next = list_entry(dentry->d_child.next, struct dentry, d_child); + if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR))) + break; + dentry->d_child.next = next->d_child.next; + } +} + static void __dentry_kill(struct dentry *dentry) { struct dentry *parent = NULL; @@ -532,20 +544,13 @@ static void __dentry_kill(struct dentry *dentry) } /* if it was on the hash then remove it */ __d_drop(dentry); - __list_del_entry(&dentry->d_child); - /* - * Inform d_walk() that we are no longer attached to the - * dentry tree - */ - dentry->d_flags |= DCACHE_DENTRY_KILLED; + dentry_unlist(dentry, parent); if (parent) spin_unlock(&parent->d_lock); - dentry_iput(dentry); - /* - * dentry_iput drops the locks, at which point nobody (except - * transient RCU lookups) can reach this dentry. - */ - BUG_ON(dentry->d_lockref.count > 0); + if (dentry->d_inode) + dentry_unlink_inode(dentry); + else + spin_unlock(&dentry->d_lock); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); @@ -589,7 +594,6 @@ static struct dentry *dentry_kill(struct dentry *dentry) failed: spin_unlock(&dentry->d_lock); - cpu_relax(); return dentry; /* try again with same dentry */ } @@ -763,6 +767,8 @@ void dput(struct dentry *dentry) return; repeat: + might_sleep(); + rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); @@ -796,8 +802,10 @@ repeat: kill_it: dentry = dentry_kill(dentry); - if (dentry) + if (dentry) { + cond_resched(); goto repeat; + } } EXPORT_SYMBOL(dput); @@ -1203,6 +1211,9 @@ resume: struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; + if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) + continue; + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); ret = enter(data, dentry); @@ -1559,6 +1570,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) { struct dentry *dentry; char *dname; + int err; dentry = kmem_cache_alloc(dentry_cache, GFP_KERNEL); if (!dentry) @@ -1617,6 +1629,16 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) INIT_LIST_HEAD(&dentry->d_child); d_set_d_op(dentry, dentry->d_sb->s_d_op); + if (dentry->d_op && dentry->d_op->d_init) { + err = dentry->d_op->d_init(dentry); + if (err) { + if (dname_external(dentry)) + kfree(external_name(dentry)); + kmem_cache_free(dentry_cache, dentry); + return NULL; + } + } + this_cpu_inc(nr_dentry); return dentry; @@ -1636,7 +1658,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; - + dentry->d_flags |= DCACHE_RCUACCESS; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject @@ -1651,6 +1673,16 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) } EXPORT_SYMBOL(d_alloc); +struct dentry *d_alloc_cursor(struct dentry * parent) +{ + struct dentry *dentry = __d_alloc(parent->d_sb, NULL); + if (dentry) { + dentry->d_flags |= DCACHE_RCUACCESS | DCACHE_DENTRY_CURSOR; + dentry->d_parent = dget(parent); + } + return dentry; +} + /** * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems) * @sb: the superblock @@ -1670,7 +1702,7 @@ struct dentry *d_alloc_name(struct dentry *parent, const char *name) struct qstr q; q.name = name; - q.hash_len = hashlen_string(name); + q.hash_len = hashlen_string(parent, name); return d_alloc(parent, &q); } EXPORT_SYMBOL(d_alloc_name); @@ -1683,7 +1715,6 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE | DCACHE_OP_DELETE | - DCACHE_OP_SELECT_INODE | DCACHE_OP_REAL)); dentry->d_op = op; if (!op) @@ -1700,8 +1731,6 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) dentry->d_flags |= DCACHE_OP_DELETE; if (op->d_prune) dentry->d_flags |= DCACHE_OP_PRUNE; - if (op->d_select_inode) - dentry->d_flags |= DCACHE_OP_SELECT_INODE; if (op->d_real) dentry->d_flags |= DCACHE_OP_REAL; @@ -1769,7 +1798,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); - __fsnotify_d_instantiate(dentry); + fsnotify_update_flags(dentry); spin_unlock(&dentry->d_lock); } @@ -2021,42 +2050,19 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, } EXPORT_SYMBOL(d_add_ci); -/* - * Do the slow-case of the dentry name compare. - * - * Unlike the dentry_cmp() function, we need to atomically - * load the name and length information, so that the - * filesystem can rely on them, and can use the 'name' and - * 'len' information without worrying about walking off the - * end of memory etc. - * - * Thus the read_seqcount_retry() and the "duplicate" info - * in arguments (the low-level filesystem should not look - * at the dentry inode or name contents directly, since - * rename can change them while we're in RCU mode). - */ -enum slow_d_compare { - D_COMP_OK, - D_COMP_NOMATCH, - D_COMP_SEQRETRY, -}; -static noinline enum slow_d_compare slow_dentry_cmp( - const struct dentry *parent, - struct dentry *dentry, - unsigned int seq, - const struct qstr *name) +static inline bool d_same_name(const struct dentry *dentry, + const struct dentry *parent, + const struct qstr *name) { - int tlen = dentry->d_name.len; - const char *tname = dentry->d_name.name; - - if (read_seqcount_retry(&dentry->d_seq, seq)) { - cpu_relax(); - return D_COMP_SEQRETRY; + if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) { + if (dentry->d_name.len != name->len) + return false; + return dentry_cmp(dentry, name->name, name->len) == 0; } - if (parent->d_op->d_compare(parent, dentry, tlen, tname, name)) - return D_COMP_NOMATCH; - return D_COMP_OK; + return parent->d_op->d_compare(parent, dentry, + dentry->d_name.len, dentry->d_name.name, + name) == 0; } /** @@ -2094,7 +2100,7 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent, { u64 hashlen = name->hash_len; const unsigned char *str = name->name; - struct hlist_bl_head *b = d_hash(parent, hashlen_hash(hashlen)); + struct hlist_bl_head *b = d_hash(hashlen_hash(hashlen)); struct hlist_bl_node *node; struct dentry *dentry; @@ -2135,6 +2141,9 @@ seqretry: * dentry compare, we will do seqretries until it is stable, * and if we end up with a successful lookup, we actually * want to exit RCU lookup anyway. + * + * Note that raw_seqcount_begin still *does* smp_rmb(), so + * we are still guaranteed NUL-termination of ->d_name.name. */ seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) @@ -2143,24 +2152,28 @@ seqretry: continue; if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) { + int tlen; + const char *tname; if (dentry->d_name.hash != hashlen_hash(hashlen)) continue; - *seqp = seq; - switch (slow_dentry_cmp(parent, dentry, seq, name)) { - case D_COMP_OK: - return dentry; - case D_COMP_NOMATCH: - continue; - default: + tlen = dentry->d_name.len; + tname = dentry->d_name.name; + /* we want a consistent (name,len) pair */ + if (read_seqcount_retry(&dentry->d_seq, seq)) { + cpu_relax(); goto seqretry; } + if (parent->d_op->d_compare(parent, dentry, + tlen, tname, name) != 0) + continue; + } else { + if (dentry->d_name.hash_len != hashlen) + continue; + if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) + continue; } - - if (dentry->d_name.hash_len != hashlen) - continue; *seqp = seq; - if (!dentry_cmp(dentry, str, hashlen_len(hashlen))) - return dentry; + return dentry; } return NULL; } @@ -2208,10 +2221,8 @@ EXPORT_SYMBOL(d_lookup); */ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) { - unsigned int len = name->len; unsigned int hash = name->hash; - const unsigned char *str = name->name; - struct hlist_bl_head *b = d_hash(parent, hash); + struct hlist_bl_head *b = d_hash(hash); struct hlist_bl_node *node; struct dentry *found = NULL; struct dentry *dentry; @@ -2249,21 +2260,8 @@ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) if (d_unhashed(dentry)) goto next; - /* - * It is safe to compare names since d_move() cannot - * change the qstr (protected by d_lock). - */ - if (parent->d_flags & DCACHE_OP_COMPARE) { - int tlen = dentry->d_name.len; - const char *tname = dentry->d_name.name; - if (parent->d_op->d_compare(parent, dentry, tlen, tname, name)) - goto next; - } else { - if (dentry->d_name.len != len) - goto next; - if (dentry_cmp(dentry, str, len)) - goto next; - } + if (!d_same_name(dentry, parent, name)) + goto next; dentry->d_lockref.count++; found = dentry; @@ -2291,7 +2289,7 @@ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name) * calculate the standard hash first, as the d_op->d_hash() * routine may choose to leave the hash value unchanged. */ - name->hash = full_name_hash(name->name, name->len); + name->hash = full_name_hash(dir, name->name, name->len); if (dir->d_flags & DCACHE_OP_HASH) { int err = dir->d_op->d_hash(dir, name); if (unlikely(err < 0)) @@ -2358,14 +2356,13 @@ static void __d_rehash(struct dentry * entry, struct hlist_bl_head *b) { BUG_ON(!d_unhashed(entry)); hlist_bl_lock(b); - entry->d_flags |= DCACHE_RCUACCESS; hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b); } static void _d_rehash(struct dentry * entry) { - __d_rehash(entry, d_hash(entry->d_parent, entry->d_name.hash)); + __d_rehash(entry, d_hash(entry->d_name.hash)); } /** @@ -2417,9 +2414,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent, const struct qstr *name, wait_queue_head_t *wq) { - unsigned int len = name->len; unsigned int hash = name->hash; - const unsigned char *str = name->name; struct hlist_bl_head *b = in_lookup_hash(parent, hash); struct hlist_bl_node *node; struct dentry *new = d_alloc(parent, name); @@ -2458,7 +2453,6 @@ retry: rcu_read_unlock(); goto retry; } - rcu_read_unlock(); /* * No changes for the parent since the beginning of d_lookup(). * Since all removals from the chain happen with hlist_bl_lock(), @@ -2471,22 +2465,20 @@ retry: continue; if (dentry->d_parent != parent) continue; - if (d_unhashed(dentry)) + if (!d_same_name(dentry, parent, name)) continue; - if (parent->d_flags & DCACHE_OP_COMPARE) { - int tlen = dentry->d_name.len; - const char *tname = dentry->d_name.name; - if (parent->d_op->d_compare(parent, dentry, tlen, tname, name)) - continue; - } else { - if (dentry->d_name.len != len) - continue; - if (dentry_cmp(dentry, str, len)) - continue; - } - dget(dentry); hlist_bl_unlock(b); - /* somebody is doing lookup for it right now; wait for it */ + /* now we can try to grab a reference */ + if (!lockref_get_not_dead(&dentry->d_lockref)) { + rcu_read_unlock(); + goto retry; + } + + rcu_read_unlock(); + /* + * somebody is likely to be still doing lookup for it; + * wait for them to finish + */ spin_lock(&dentry->d_lock); d_wait_lookup(dentry); /* @@ -2501,22 +2493,14 @@ retry: goto mismatch; if (unlikely(d_unhashed(dentry))) goto mismatch; - if (parent->d_flags & DCACHE_OP_COMPARE) { - int tlen = dentry->d_name.len; - const char *tname = dentry->d_name.name; - if (parent->d_op->d_compare(parent, dentry, tlen, tname, name)) - goto mismatch; - } else { - if (unlikely(dentry->d_name.len != len)) - goto mismatch; - if (unlikely(dentry_cmp(dentry, str, len))) - goto mismatch; - } + if (unlikely(!d_same_name(dentry, parent, name))) + goto mismatch; /* OK, it *is* a hashed match; return it */ spin_unlock(&dentry->d_lock); dput(new); return dentry; } + rcu_read_unlock(); /* we can't take ->d_lock here; it's OK, though. */ new->d_flags |= DCACHE_PAR_LOOKUP; new->d_wait = wq; @@ -2563,7 +2547,7 @@ static inline void __d_add(struct dentry *dentry, struct inode *inode) raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); - __fsnotify_d_instantiate(dentry); + fsnotify_update_flags(dentry); } _d_rehash(dentry); if (dir) @@ -2606,8 +2590,6 @@ EXPORT_SYMBOL(d_add); struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) { struct dentry *alias; - int len = entry->d_name.len; - const char *name = entry->d_name.name; unsigned int hash = entry->d_name.hash; spin_lock(&inode->i_lock); @@ -2621,9 +2603,7 @@ struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) continue; if (alias->d_parent != entry->d_parent) continue; - if (alias->d_name.len != len) - continue; - if (dentry_cmp(alias, name, len)) + if (!d_same_name(alias, entry->d_parent, &entry->d_name)) continue; spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { @@ -2822,7 +2802,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target, * for the same hash queue because of how unlikely it is. */ __d_drop(dentry); - __d_rehash(dentry, d_hash(target->d_parent, target->d_name.hash)); + __d_rehash(dentry, d_hash(target->d_name.hash)); /* * Unhash the target (d_delete() is not usable here). If exchanging @@ -2830,8 +2810,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target, */ __d_drop(target); if (exchange) { - __d_rehash(target, - d_hash(dentry->d_parent, dentry->d_name.hash)); + __d_rehash(target, d_hash(dentry->d_name.hash)); } /* Switch the names.. */ @@ -2843,6 +2822,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target, /* ... and switch them in the tree */ if (IS_ROOT(dentry)) { /* splicing a tree */ + dentry->d_flags |= DCACHE_RCUACCESS; dentry->d_parent = target->d_parent; target->d_parent = target; list_del_init(&target->d_child); @@ -2853,8 +2833,8 @@ static void __d_move(struct dentry *dentry, struct dentry *target, list_move(&target->d_child, &target->d_parent->d_subdirs); list_move(&dentry->d_child, &dentry->d_parent->d_subdirs); if (exchange) - fsnotify_d_move(target); - fsnotify_d_move(dentry); + fsnotify_update_flags(target); + fsnotify_update_flags(dentry); } write_seqcount_end(&target->d_seq); |