diff options
Diffstat (limited to 'fs/dcache.c')
-rw-r--r-- | fs/dcache.c | 319 |
1 files changed, 187 insertions, 132 deletions
diff --git a/fs/dcache.c b/fs/dcache.c index 71a8e943a0fa..03d58b2d4fa3 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -35,6 +35,8 @@ #include "internal.h" #include "mount.h" +#include <asm/runtime-const.h> + /* * Usage: * dcache->d_inode->i_lock protects: @@ -71,8 +73,14 @@ * If no ancestor relationship: * arbitrary, since it's serialized on rename_lock */ -int sysctl_vfs_cache_pressure __read_mostly = 100; -EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure); +static int sysctl_vfs_cache_pressure __read_mostly = 100; +static int sysctl_vfs_cache_pressure_denom __read_mostly = 100; + +unsigned long vfs_pressure_ratio(unsigned long val) +{ + return mult_frac(val, sysctl_vfs_cache_pressure, sysctl_vfs_cache_pressure_denom); +} +EXPORT_SYMBOL_GPL(vfs_pressure_ratio); __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); @@ -94,15 +102,21 @@ EXPORT_SYMBOL(dotdot_name); * * This hash-function tries to avoid losing too many bits of hash * information, yet avoid using a prime hash-size or similar. + * + * Marking the variables "used" ensures that the compiler doesn't + * optimize them away completely on architectures with runtime + * constant infrastructure, this allows debuggers to see their + * values. But updating these values has no effect on those arches. */ -static unsigned int d_hash_shift __ro_after_init; +static unsigned int d_hash_shift __ro_after_init __used; -static struct hlist_bl_head *dentry_hashtable __ro_after_init; +static struct hlist_bl_head *dentry_hashtable __ro_after_init __used; -static inline struct hlist_bl_head *d_hash(unsigned int hash) +static inline struct hlist_bl_head *d_hash(unsigned long hashlen) { - return dentry_hashtable + (hash >> d_hash_shift); + return runtime_const_ptr(dentry_hashtable) + + runtime_const_shift_right_32(hashlen, d_hash_shift); } #define IN_LOOKUP_SHIFT 10 @@ -127,6 +141,7 @@ struct dentry_stat_t { static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); static DEFINE_PER_CPU(long, nr_dentry_negative); +static int dentry_negative_policy; #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* Statistics gathering. */ @@ -174,7 +189,7 @@ static long get_nr_dentry_negative(void) return sum < 0 ? 0 : sum; } -static int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, +static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); @@ -183,7 +198,7 @@ static int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table fs_dcache_sysctls[] = { +static const struct ctl_table fs_dcache_sysctls[] = { { .procname = "dentry-state", .data = &dentry_stat, @@ -191,10 +206,39 @@ static struct ctl_table fs_dcache_sysctls[] = { .mode = 0444, .proc_handler = proc_nr_dentry, }, + { + .procname = "dentry-negative", + .data = &dentry_negative_policy, + .maxlen = sizeof(dentry_negative_policy), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +}; + +static const struct ctl_table vm_dcache_sysctls[] = { + { + .procname = "vfs_cache_pressure", + .data = &sysctl_vfs_cache_pressure, + .maxlen = sizeof(sysctl_vfs_cache_pressure), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + }, + { + .procname = "vfs_cache_pressure_denom", + .data = &sysctl_vfs_cache_pressure_denom, + .maxlen = sizeof(sysctl_vfs_cache_pressure_denom), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE_HUNDRED, + }, }; static int __init init_fs_dcache_sysctls(void) { + register_sysctl_init("vm", vm_dcache_sysctls); register_sysctl_init("fs", fs_dcache_sysctls); return 0; } @@ -277,12 +321,16 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c return dentry_string_cmp(cs, ct, tcount); } +/* + * long names are allocated separately from dentry and never modified. + * Refcounted, freeing is RCU-delayed. See take_dentry_name_snapshot() + * for the reason why ->count and ->head can't be combined into a union. + * dentry_string_cmp() relies upon ->name[] being word-aligned. + */ struct external_name { - union { - atomic_t count; - struct rcu_head head; - } u; - unsigned char name[]; + atomic_t count; + struct rcu_head head; + unsigned char name[] __aligned(sizeof(unsigned long)); }; static inline struct external_name *external_name(struct dentry *dentry) @@ -306,31 +354,45 @@ static void __d_free_external(struct rcu_head *head) static inline int dname_external(const struct dentry *dentry) { - return dentry->d_name.name != dentry->d_iname; + return dentry->d_name.name != dentry->d_shortname.string; } void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { - spin_lock(&dentry->d_lock); - name->name = dentry->d_name; - if (unlikely(dname_external(dentry))) { - atomic_inc(&external_name(dentry)->u.count); + unsigned seq; + const unsigned char *s; + + rcu_read_lock(); +retry: + seq = read_seqcount_begin(&dentry->d_seq); + s = READ_ONCE(dentry->d_name.name); + name->name.hash_len = dentry->d_name.hash_len; + name->name.name = name->inline_name.string; + if (likely(s == dentry->d_shortname.string)) { + name->inline_name = dentry->d_shortname; } else { - memcpy(name->inline_name, dentry->d_iname, - dentry->d_name.len + 1); - name->name.name = name->inline_name; + struct external_name *p; + p = container_of(s, struct external_name, name[0]); + // get a valid reference + if (unlikely(!atomic_inc_not_zero(&p->count))) + goto retry; + name->name.name = s; } - spin_unlock(&dentry->d_lock); + if (read_seqcount_retry(&dentry->d_seq, seq)) { + release_dentry_name_snapshot(name); + goto retry; + } + rcu_read_unlock(); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { - if (unlikely(name->name.name != name->inline_name)) { + if (unlikely(name->name.name != name->inline_name.string)) { struct external_name *p; p = container_of(name->name.name, struct external_name, name[0]); - if (unlikely(atomic_dec_and_test(&p->u.count))) - kfree_rcu(p, u.head); + if (unlikely(atomic_dec_and_test(&p->count))) + kfree_rcu(p, head); } } EXPORT_SYMBOL(release_dentry_name_snapshot); @@ -355,7 +417,11 @@ static inline void __d_clear_type_and_inode(struct dentry *dentry) flags &= ~DCACHE_ENTRY_TYPE; WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; - if (dentry->d_flags & DCACHE_LRU_LIST) + /* + * The negative counter only tracks dentries on the LRU. Don't inc if + * d_lru is on another list. + */ + if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative); } @@ -364,7 +430,7 @@ static void dentry_free(struct dentry *dentry) WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); - if (likely(atomic_dec_and_test(&p->u.count))) { + if (likely(atomic_dec_and_test(&p->count))) { call_rcu(&dentry->d_u.d_rcu, __d_free_external); return; } @@ -1077,7 +1143,7 @@ void shrink_dentry_list(struct list_head *list) } static enum lru_status dentry_lru_isolate(struct list_head *item, - struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) + struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); @@ -1158,7 +1224,7 @@ long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc) } static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, - struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) + struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); @@ -1548,7 +1614,7 @@ void shrink_dcache_for_umount(struct super_block *sb) { struct dentry *dentry; - WARN(down_read_trylock(&sb->s_umount), "s_umount should've been locked"); + rwsem_assert_held_write(&sb->s_umount); dentry = sb->s_root; sb->s_root = NULL; @@ -1632,10 +1698,10 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) * will still always have a NUL at the end, even if we might * be overwriting an internal NUL character */ - dentry->d_iname[DNAME_INLINE_LEN-1] = 0; + dentry->d_shortname.string[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { name = &slash_name; - dname = dentry->d_iname; + dname = dentry->d_shortname.string; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, @@ -1645,10 +1711,10 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) kmem_cache_free(dentry_cache, dentry); return NULL; } - atomic_set(&p->u.count, 1); + atomic_set(&p->count, 1); dname = p->name; } else { - dname = dentry->d_iname; + dname = dentry->d_shortname.string; } dentry->d_name.len = name->len; @@ -1659,9 +1725,8 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) /* Make sure we always see the terminating NUL character */ smp_store_release(&dentry->d_name.name, dname); /* ^^^ */ - dentry->d_lockref.count = 1; dentry->d_flags = 0; - spin_lock_init(&dentry->d_lock); + lockref_init(&dentry->d_lockref); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; @@ -1844,9 +1909,11 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) spin_lock(&dentry->d_lock); /* - * Decrement negative dentry count if it was in the LRU list. + * The negative counter only tracks dentries on the LRU. Don't dec if + * d_lru is on another list. */ - if (dentry->d_flags & DCACHE_LRU_LIST) + if ((dentry->d_flags & + (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); @@ -1899,8 +1966,13 @@ void d_instantiate_new(struct dentry *entry, struct inode *inode) __d_instantiate(entry, inode); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; + /* + * Pairs with the barrier in prepare_to_wait_event() to make sure + * ___wait_var_event() either sees the bit cleared or + * waitqueue_active() check in wake_up_var() sees the waiter. + */ smp_mb(); - wake_up_bit(&inode->i_state, __I_NEW); + inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_instantiate_new); @@ -2020,8 +2092,8 @@ EXPORT_SYMBOL(d_obtain_root); /** * d_add_ci - lookup or allocate new dentry with case-exact name - * @inode: the inode case-insensitive lookup has found * @dentry: the negative dentry that was passed to the parent's lookup func + * @inode: the inode case-insensitive lookup has found * @name: the case-exact name to be associated with the returned dentry * * This is to avoid filling the dcache with case-insensitive names to the @@ -2074,8 +2146,8 @@ EXPORT_SYMBOL(d_add_ci); /** * d_same_name - compare dentry name with case-exact name - * @parent: parent dentry * @dentry: the negative dentry that was passed to the parent's lookup func + * @parent: parent dentry * @name: the case-exact name to be associated with the returned dentry * * Return: true if names are same, or false @@ -2104,7 +2176,7 @@ static noinline struct dentry *__d_lookup_rcu_op_compare( unsigned *seqp) { u64 hashlen = name->hash_len; - struct hlist_bl_head *b = d_hash(hashlen_hash(hashlen)); + struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; @@ -2154,9 +2226,6 @@ seqretry: * without taking d_lock and checking d_seq sequence count against @seq * returned here. * - * A refcount may be taken on the found dentry with the d_rcu_to_refcount - * function. - * * Alternatively, __d_lookup_rcu may be called again to look up the child of * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks @@ -2171,7 +2240,7 @@ 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(hashlen_hash(hashlen)); + struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; @@ -2352,7 +2421,6 @@ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name) } return d_lookup(dir, name); } -EXPORT_SYMBOL(d_hash_and_lookup); /* * When a file is deleted, we have two options: @@ -2385,6 +2453,8 @@ void d_delete(struct dentry * dentry) * Are we the only user? */ if (dentry->d_lockref.count == 1) { + if (dentry_negative_policy) + __d_drop(dentry); dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); } else { @@ -2435,7 +2505,8 @@ static inline void end_dir_add(struct inode *dir, unsigned int n, { smp_store_release(&dir->i_dir_seq, n + 2); preempt_enable_nested(); - wake_up_all(d_wait); + if (wq_has_sleeper(d_wait)) + wake_up_all(d_wait); } static void d_wait_lookup(struct dentry *dentry) @@ -2642,52 +2713,6 @@ void d_add(struct dentry *entry, struct inode *inode) } EXPORT_SYMBOL(d_add); -/** - * d_exact_alias - find and hash an exact unhashed alias - * @entry: dentry to add - * @inode: The inode to go with this dentry - * - * If an unhashed dentry with the same name/parent and desired - * inode already exists, hash and return it. Otherwise, return - * NULL. - * - * Parent directory should be locked. - */ -struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) -{ - struct dentry *alias; - unsigned int hash = entry->d_name.hash; - - spin_lock(&inode->i_lock); - hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { - /* - * Don't need alias->d_lock here, because aliases with - * d_parent == entry->d_parent are not subject to name or - * parent changes, because the parent inode i_mutex is held. - */ - if (alias->d_name.hash != hash) - continue; - if (alias->d_parent != entry->d_parent) - continue; - if (!d_same_name(alias, entry->d_parent, &entry->d_name)) - continue; - spin_lock(&alias->d_lock); - if (!d_unhashed(alias)) { - spin_unlock(&alias->d_lock); - alias = NULL; - } else { - dget_dlock(alias); - __d_rehash(alias); - spin_unlock(&alias->d_lock); - } - spin_unlock(&inode->i_lock); - return alias; - } - spin_unlock(&inode->i_lock); - return NULL; -} -EXPORT_SYMBOL(d_exact_alias); - static void swap_names(struct dentry *dentry, struct dentry *target) { if (unlikely(dname_external(target))) { @@ -2701,10 +2726,9 @@ static void swap_names(struct dentry *dentry, struct dentry *target) * dentry:internal, target:external. Steal target's * storage and make target internal. */ - memcpy(target->d_iname, dentry->d_name.name, - dentry->d_name.len + 1); dentry->d_name.name = target->d_name.name; - target->d_name.name = target->d_iname; + target->d_shortname = dentry->d_shortname; + target->d_name.name = target->d_shortname.string; } } else { if (unlikely(dname_external(dentry))) { @@ -2712,20 +2736,16 @@ static void swap_names(struct dentry *dentry, struct dentry *target) * dentry:external, target:internal. Give dentry's * storage to target and make dentry internal */ - memcpy(dentry->d_iname, target->d_name.name, - target->d_name.len + 1); target->d_name.name = dentry->d_name.name; - dentry->d_name.name = dentry->d_iname; + dentry->d_shortname = target->d_shortname; + dentry->d_name.name = dentry->d_shortname.string; } else { /* * Both are internal. */ - unsigned int i; - BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long))); - for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) { - swap(((long *) &dentry->d_iname)[i], - ((long *) &target->d_iname)[i]); - } + for (int i = 0; i < DNAME_INLINE_WORDS; i++) + swap(dentry->d_shortname.words[i], + target->d_shortname.words[i]); } } swap(dentry->d_name.hash_len, target->d_name.hash_len); @@ -2737,16 +2757,15 @@ static void copy_name(struct dentry *dentry, struct dentry *target) if (unlikely(dname_external(dentry))) old_name = external_name(dentry); if (unlikely(dname_external(target))) { - atomic_inc(&external_name(target)->u.count); + atomic_inc(&external_name(target)->count); dentry->d_name = target->d_name; } else { - memcpy(dentry->d_iname, target->d_name.name, - target->d_name.len + 1); - dentry->d_name.name = dentry->d_iname; + dentry->d_shortname = target->d_shortname; + dentry->d_name.name = dentry->d_shortname.string; dentry->d_name.hash_len = target->d_name.hash_len; } - if (old_name && likely(atomic_dec_and_test(&old_name->u.count))) - kfree_rcu(old_name, u.head); + if (old_name && likely(atomic_dec_and_test(&old_name->count))) + kfree_rcu(old_name, head); } /* @@ -2927,7 +2946,12 @@ static int __d_unalias(struct dentry *dentry, struct dentry *alias) goto out_err; m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: + if (alias->d_op && alias->d_op->d_unalias_trylock && + !alias->d_op->d_unalias_trylock(alias)) + goto out_err; __d_move(alias, dentry, false); + if (alias->d_op && alias->d_op->d_unalias_unlock) + alias->d_op->d_unalias_unlock(alias); ret = 0; out_err: if (m2) @@ -3029,28 +3053,25 @@ EXPORT_SYMBOL(d_splice_alias); bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { - bool result; + bool subdir; unsigned seq; if (new_dentry == old_dentry) return true; - do { - /* for restarting inner loop in case of seq retry */ - seq = read_seqbegin(&rename_lock); - /* - * Need rcu_readlock to protect against the d_parent trashing - * due to d_move - */ - rcu_read_lock(); - if (d_ancestor(old_dentry, new_dentry)) - result = true; - else - result = false; - rcu_read_unlock(); - } while (read_seqretry(&rename_lock, seq)); - - return result; + /* Access d_parent under rcu as d_move() may change it. */ + rcu_read_lock(); + seq = read_seqbegin(&rename_lock); + subdir = d_ancestor(old_dentry, new_dentry); + /* Try lockless once... */ + if (read_seqretry(&rename_lock, seq)) { + /* ...else acquire lock for progress even on deep chains. */ + read_seqlock_excl(&rename_lock); + subdir = d_ancestor(old_dentry, new_dentry); + read_sequnlock_excl(&rename_lock); + } + rcu_read_unlock(); + return subdir; } EXPORT_SYMBOL(is_subdir); @@ -3078,12 +3099,12 @@ void d_mark_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; - BUG_ON(dentry->d_name.name != dentry->d_iname || + BUG_ON(dname_external(dentry) || !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - dentry->d_name.len = sprintf(dentry->d_iname, "#%llu", + dentry->d_name.len = sprintf(dentry->d_shortname.string, "#%llu", (unsigned long long)inode->i_ino); spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); @@ -3100,6 +3121,34 @@ void d_tmpfile(struct file *file, struct inode *inode) } EXPORT_SYMBOL(d_tmpfile); +/* + * Obtain inode number of the parent dentry. + */ +ino_t d_parent_ino(struct dentry *dentry) +{ + struct dentry *parent; + struct inode *iparent; + unsigned seq; + ino_t ret; + + scoped_guard(rcu) { + seq = raw_seqcount_begin(&dentry->d_seq); + parent = READ_ONCE(dentry->d_parent); + iparent = d_inode_rcu(parent); + if (likely(iparent)) { + ret = iparent->i_ino; + if (!read_seqcount_retry(&dentry->d_seq, seq)) + return ret; + } + } + + spin_lock(&dentry->d_lock); + ret = dentry->d_parent->d_inode->i_ino; + spin_unlock(&dentry->d_lock); + return ret; +} +EXPORT_SYMBOL(d_parent_ino); + static __initdata unsigned long dhash_entries; static int __init set_dhash_entries(char *str) { @@ -3129,6 +3178,9 @@ static void __init dcache_init_early(void) 0, 0); d_hash_shift = 32 - d_hash_shift; + + runtime_const_init(shift, d_hash_shift); + runtime_const_init(ptr, dentry_hashtable); } static void __init dcache_init(void) @@ -3140,7 +3192,7 @@ static void __init dcache_init(void) */ dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT, - d_iname); + d_shortname.string); /* Hash may have been set up in dcache_init_early */ if (!hashdist) @@ -3157,6 +3209,9 @@ static void __init dcache_init(void) 0, 0); d_hash_shift = 32 - d_hash_shift; + + runtime_const_init(shift, d_hash_shift); + runtime_const_init(ptr, dentry_hashtable); } /* SLAB cache for __getname() consumers */ |