diff options
Diffstat (limited to 'fs/inode.c')
| -rw-r--r-- | fs/inode.c | 1228 |
1 files changed, 783 insertions, 445 deletions
diff --git a/fs/inode.c b/fs/inode.c index 35fd688168c5..521383223d8a 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -20,7 +20,13 @@ #include <linux/ratelimit.h> #include <linux/list_lru.h> #include <linux/iversion.h> +#include <linux/rw_hint.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> #include <trace/events/writeback.h> +#define CREATE_TRACE_POINTS +#include <trace/events/timestamp.h> + #include "internal.h" /* @@ -54,9 +60,9 @@ * inode_hash_lock */ -static unsigned int i_hash_mask __read_mostly; -static unsigned int i_hash_shift __read_mostly; -static struct hlist_head *inode_hashtable __read_mostly; +static unsigned int i_hash_mask __ro_after_init; +static unsigned int i_hash_shift __ro_after_init; +static struct hlist_head *inode_hashtable __ro_after_init; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock); /* @@ -70,7 +76,7 @@ EXPORT_SYMBOL(empty_aops); static DEFINE_PER_CPU(unsigned long, nr_inodes); static DEFINE_PER_CPU(unsigned long, nr_unused); -static struct kmem_cache *inode_cachep __read_mostly; +static struct kmem_cache *inode_cachep __ro_after_init; static long get_nr_inodes(void) { @@ -97,6 +103,70 @@ long get_nr_dirty_inodes(void) return nr_dirty > 0 ? nr_dirty : 0; } +#ifdef CONFIG_DEBUG_FS +static DEFINE_PER_CPU(long, mg_ctime_updates); +static DEFINE_PER_CPU(long, mg_fine_stamps); +static DEFINE_PER_CPU(long, mg_ctime_swaps); + +static unsigned long get_mg_ctime_updates(void) +{ + unsigned long sum = 0; + int i; + + for_each_possible_cpu(i) + sum += data_race(per_cpu(mg_ctime_updates, i)); + return sum; +} + +static unsigned long get_mg_fine_stamps(void) +{ + unsigned long sum = 0; + int i; + + for_each_possible_cpu(i) + sum += data_race(per_cpu(mg_fine_stamps, i)); + return sum; +} + +static unsigned long get_mg_ctime_swaps(void) +{ + unsigned long sum = 0; + int i; + + for_each_possible_cpu(i) + sum += data_race(per_cpu(mg_ctime_swaps, i)); + return sum; +} + +#define mgtime_counter_inc(__var) this_cpu_inc(__var) + +static int mgts_show(struct seq_file *s, void *p) +{ + unsigned long ctime_updates = get_mg_ctime_updates(); + unsigned long ctime_swaps = get_mg_ctime_swaps(); + unsigned long fine_stamps = get_mg_fine_stamps(); + unsigned long floor_swaps = timekeeping_get_mg_floor_swaps(); + + seq_printf(s, "%lu %lu %lu %lu\n", + ctime_updates, ctime_swaps, fine_stamps, floor_swaps); + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(mgts); + +static int __init mg_debugfs_init(void) +{ + debugfs_create_file("multigrain_timestamps", S_IFREG | S_IRUGO, NULL, NULL, &mgts_fops); + return 0; +} +late_initcall(mg_debugfs_init); + +#else /* ! CONFIG_DEBUG_FS */ + +#define mgtime_counter_inc(__var) do { } while (0) + +#endif /* CONFIG_DEBUG_FS */ + /* * Handle nr_inode sysctl */ @@ -106,7 +176,7 @@ long get_nr_dirty_inodes(void) */ static struct inodes_stat_t inodes_stat; -static int proc_nr_inodes(struct ctl_table *table, int write, void *buffer, +static int proc_nr_inodes(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { inodes_stat.nr_inodes = get_nr_inodes(); @@ -114,7 +184,7 @@ static int proc_nr_inodes(struct ctl_table *table, int write, void *buffer, return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table inodes_sysctls[] = { +static const struct ctl_table inodes_sysctls[] = { { .procname = "inode-nr", .data = &inodes_stat, @@ -129,7 +199,6 @@ static struct ctl_table inodes_sysctls[] = { .mode = 0444, .proc_handler = proc_nr_inodes, }, - { } }; static int __init init_fs_inode_sysctls(void) @@ -146,14 +215,16 @@ static int no_open(struct inode *inode, struct file *file) } /** - * inode_init_always - perform inode structure initialisation + * inode_init_always_gfp - perform inode structure initialisation * @sb: superblock inode belongs to * @inode: inode to initialise + * @gfp: allocation flags * * These are initializations that need to be done on every inode * allocation as the fields are not initialised by slab allocation. + * If there are additional allocations required @gfp is used. */ -int inode_init_always(struct super_block *sb, struct inode *inode) +int inode_init_always_gfp(struct super_block *sb, struct inode *inode, gfp_t gfp) { static const struct inode_operations empty_iops; static const struct file_operations no_open_fops = {.open = no_open}; @@ -162,6 +233,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_sb = sb; inode->i_blkbits = sb->s_blocksize_bits; inode->i_flags = 0; + inode_state_assign_raw(inode, 0); atomic64_set(&inode->i_sequence, 0); atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; @@ -171,6 +243,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_opflags = 0; if (sb->s_xattr) inode->i_opflags |= IOP_XATTR; + if (sb->s_type->fs_flags & FS_MGTIME) + inode->i_opflags |= IOP_MGTIME; i_uid_write(inode, 0); i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); @@ -209,12 +283,14 @@ int inode_init_always(struct super_block *sb, struct inode *inode) atomic_set(&mapping->nr_thps, 0); #endif mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); - mapping->private_data = NULL; + mapping->i_private_data = NULL; mapping->writeback_index = 0; init_rwsem(&mapping->invalidate_lock); lockdep_set_class_and_name(&mapping->invalidate_lock, &sb->s_type->invalidate_lock_key, "mapping.invalidate_lock"); + if (sb->s_iflags & SB_I_STABLE_WRITES) + mapping_set_stable_writes(mapping); inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ @@ -227,13 +303,14 @@ int inode_init_always(struct super_block *sb, struct inode *inode) #endif inode->i_flctx = NULL; - if (unlikely(security_inode_alloc(inode))) + if (unlikely(security_inode_alloc(inode, gfp))) return -ENOMEM; + this_cpu_inc(nr_inodes); return 0; } -EXPORT_SYMBOL(inode_init_always); +EXPORT_SYMBOL(inode_init_always_gfp); void free_inode_nonrcu(struct inode *inode) { @@ -250,7 +327,17 @@ static void i_callback(struct rcu_head *head) free_inode_nonrcu(inode); } -static struct inode *alloc_inode(struct super_block *sb) +/** + * alloc_inode - obtain an inode + * @sb: superblock + * + * Allocates a new inode for given superblock. + * Inode wont be chained in superblock s_inodes list + * This means : + * - fs can't be unmount + * - quotas, fsnotify, writeback can't work + */ +struct inode *alloc_inode(struct super_block *sb) { const struct super_operations *ops = sb->s_op; struct inode *inode; @@ -384,7 +471,7 @@ EXPORT_SYMBOL(set_nlink); void inc_nlink(struct inode *inode) { if (unlikely(inode->i_nlink == 0)) { - WARN_ON(!(inode->i_state & I_LINKABLE)); + WARN_ON(!(inode_state_read_once(inode) & I_LINKABLE)); atomic_long_dec(&inode->i_sb->s_remove_count); } @@ -396,8 +483,8 @@ static void __address_space_init_once(struct address_space *mapping) { xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT); init_rwsem(&mapping->i_mmap_rwsem); - INIT_LIST_HEAD(&mapping->private_list); - spin_lock_init(&mapping->private_lock); + INIT_LIST_HEAD(&mapping->i_private_list); + spin_lock_init(&mapping->i_private_lock); mapping->i_mmap = RB_ROOT_CACHED; } @@ -435,14 +522,6 @@ static void init_once(void *foo) } /* - * inode->i_lock must be held - */ -void __iget(struct inode *inode) -{ - atomic_inc(&inode->i_count); -} - -/* * get additional reference to inode; caller must already hold one. */ void ihold(struct inode *inode) @@ -451,57 +530,144 @@ void ihold(struct inode *inode) } EXPORT_SYMBOL(ihold); -static void __inode_add_lru(struct inode *inode, bool rotate) +struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, + struct inode *inode, u32 bit) { - if (inode->i_state & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE)) + void *bit_address; + + bit_address = inode_state_wait_address(inode, bit); + init_wait_var_entry(wqe, bit_address, 0); + return __var_waitqueue(bit_address); +} +EXPORT_SYMBOL(inode_bit_waitqueue); + +void wait_on_new_inode(struct inode *inode) +{ + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; + + spin_lock(&inode->i_lock); + if (!(inode_state_read(inode) & I_NEW)) { + spin_unlock(&inode->i_lock); + return; + } + + wq_head = inode_bit_waitqueue(&wqe, inode, __I_NEW); + for (;;) { + prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); + if (!(inode_state_read(inode) & I_NEW)) + break; + spin_unlock(&inode->i_lock); + schedule(); + spin_lock(&inode->i_lock); + } + finish_wait(wq_head, &wqe.wq_entry); + WARN_ON(inode_state_read(inode) & I_NEW); + spin_unlock(&inode->i_lock); +} +EXPORT_SYMBOL(wait_on_new_inode); + +static void __inode_lru_list_add(struct inode *inode, bool rotate) +{ + lockdep_assert_held(&inode->i_lock); + + if (inode_state_read(inode) & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE)) return; - if (atomic_read(&inode->i_count)) + if (icount_read(inode)) return; if (!(inode->i_sb->s_flags & SB_ACTIVE)) return; if (!mapping_shrinkable(&inode->i_data)) return; - if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru)) + if (list_lru_add_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); else if (rotate) - inode->i_state |= I_REFERENCED; + inode_state_set(inode, I_REFERENCED); } /* * Add inode to LRU if needed (inode is unused and clean). - * - * Needs inode->i_lock held. */ -void inode_add_lru(struct inode *inode) +void inode_lru_list_add(struct inode *inode) { - __inode_add_lru(inode, false); + __inode_lru_list_add(inode, false); } static void inode_lru_list_del(struct inode *inode) { - if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru)) + if (list_empty(&inode->i_lru)) + return; + + if (list_lru_del_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); } +static void inode_pin_lru_isolating(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + WARN_ON(inode_state_read(inode) & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); + inode_state_set(inode, I_LRU_ISOLATING); +} + +static void inode_unpin_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + WARN_ON(!(inode_state_read(inode) & I_LRU_ISOLATING)); + inode_state_clear(inode, I_LRU_ISOLATING); + /* Called with inode->i_lock which ensures memory ordering. */ + inode_wake_up_bit(inode, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); +} + +static void inode_wait_for_lru_isolating(struct inode *inode) +{ + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; + + lockdep_assert_held(&inode->i_lock); + if (!(inode_state_read(inode) & I_LRU_ISOLATING)) + return; + + wq_head = inode_bit_waitqueue(&wqe, inode, __I_LRU_ISOLATING); + for (;;) { + prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); + /* + * Checking I_LRU_ISOLATING with inode->i_lock guarantees + * memory ordering. + */ + if (!(inode_state_read(inode) & I_LRU_ISOLATING)) + break; + spin_unlock(&inode->i_lock); + schedule(); + spin_lock(&inode->i_lock); + } + finish_wait(wq_head, &wqe.wq_entry); + WARN_ON(inode_state_read(inode) & I_LRU_ISOLATING); +} + /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add */ void inode_sb_list_add(struct inode *inode) { - spin_lock(&inode->i_sb->s_inode_list_lock); - list_add(&inode->i_sb_list, &inode->i_sb->s_inodes); - spin_unlock(&inode->i_sb->s_inode_list_lock); + struct super_block *sb = inode->i_sb; + + spin_lock(&sb->s_inode_list_lock); + list_add(&inode->i_sb_list, &sb->s_inodes); + spin_unlock(&sb->s_inode_list_lock); } EXPORT_SYMBOL_GPL(inode_sb_list_add); static inline void inode_sb_list_del(struct inode *inode) { + struct super_block *sb = inode->i_sb; + if (!list_empty(&inode->i_sb_list)) { - spin_lock(&inode->i_sb->s_inode_list_lock); + spin_lock(&sb->s_inode_list_lock); list_del_init(&inode->i_sb_list); - spin_unlock(&inode->i_sb->s_inode_list_lock); + spin_unlock(&sb->s_inode_list_lock); } } @@ -558,6 +724,7 @@ void dump_mapping(const struct address_space *mapping) struct hlist_node *dentry_first; struct dentry *dentry_ptr; struct dentry dentry; + char fname[64] = {}; unsigned long ino; /* @@ -587,17 +754,21 @@ void dump_mapping(const struct address_space *mapping) } dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias); - if (get_kernel_nofault(dentry, dentry_ptr)) { + if (get_kernel_nofault(dentry, dentry_ptr) || + !dentry.d_parent || !dentry.d_name.name) { pr_warn("aops:%ps ino:%lx invalid dentry:%px\n", a_ops, ino, dentry_ptr); return; } + if (strncpy_from_kernel_nofault(fname, dentry.d_name.name, 63) < 0) + strscpy(fname, "<invalid>"); /* - * if dentry is corrupted, the %pd handler may still crash, - * but it's unlikely that we reach here with a corrupt mapping + * Even if strncpy_from_kernel_nofault() succeeded, + * the fname could be unreliable */ - pr_warn("aops:%ps ino:%lx dentry name:\"%pd\"\n", a_ops, ino, &dentry); + pr_warn("aops:%ps ino:%lx dentry name(?):\"%s\"\n", + a_ops, ino, fname); } void clear_inode(struct inode *inode) @@ -618,12 +789,12 @@ void clear_inode(struct inode *inode) * nor even WARN_ON(!mapping_empty). */ xa_unlock_irq(&inode->i_data.i_pages); - BUG_ON(!list_empty(&inode->i_data.private_list)); - BUG_ON(!(inode->i_state & I_FREEING)); - BUG_ON(inode->i_state & I_CLEAR); + BUG_ON(!list_empty(&inode->i_data.i_private_list)); + BUG_ON(!(inode_state_read_once(inode) & I_FREEING)); + BUG_ON(inode_state_read_once(inode) & I_CLEAR); BUG_ON(!list_empty(&inode->i_wb_list)); /* don't need i_lock here, no concurrent mods to i_state */ - inode->i_state = I_FREEING | I_CLEAR; + inode_state_assign_raw(inode, I_FREEING | I_CLEAR); } EXPORT_SYMBOL(clear_inode); @@ -644,14 +815,15 @@ static void evict(struct inode *inode) { const struct super_operations *op = inode->i_sb->s_op; - BUG_ON(!(inode->i_state & I_FREEING)); + BUG_ON(!(inode_state_read_once(inode) & I_FREEING)); BUG_ON(!list_empty(&inode->i_lru)); - if (!list_empty(&inode->i_io_list)) - inode_io_list_del(inode); - + inode_io_list_del(inode); inode_sb_list_del(inode); + spin_lock(&inode->i_lock); + inode_wait_for_lru_isolating(inode); + /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since @@ -659,6 +831,7 @@ static void evict(struct inode *inode) * the inode. We just have to wait for running writeback to finish. */ inode_wait_for_writeback(inode); + spin_unlock(&inode->i_lock); if (op->evict_inode) { op->evict_inode(inode); @@ -671,10 +844,19 @@ static void evict(struct inode *inode) remove_inode_hash(inode); - spin_lock(&inode->i_lock); - wake_up_bit(&inode->i_state, __I_NEW); - BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); - spin_unlock(&inode->i_lock); + /* + * Wake up waiters in __wait_on_freeing_inode(). + * + * It is an invariant that any thread we need to wake up is already + * accounted for before remove_inode_hash() acquires ->i_lock -- both + * sides take the lock and sleep is aborted if the inode is found + * unhashed. Thus either the sleeper wins and goes off CPU, or removal + * wins and the sleeper aborts after testing with the lock. + * + * This also means we don't need any fences for the call below. + */ + inode_wake_up_bit(inode, __I_NEW); + BUG_ON(inode_state_read_once(inode) != (I_FREEING | I_CLEAR)); destroy_inode(inode); } @@ -710,22 +892,26 @@ static void dispose_list(struct list_head *head) */ void evict_inodes(struct super_block *sb) { - struct inode *inode, *next; + struct inode *inode; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); - list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { - if (atomic_read(&inode->i_count)) + list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { + if (icount_read(inode)) continue; spin_lock(&inode->i_lock); - if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { + if (icount_read(inode)) { + spin_unlock(&inode->i_lock); + continue; + } + if (inode_state_read(inode) & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } - inode->i_state |= I_FREEING; + inode_state_set(inode, I_FREEING); inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); @@ -748,46 +934,6 @@ again: } EXPORT_SYMBOL_GPL(evict_inodes); -/** - * invalidate_inodes - attempt to free all inodes on a superblock - * @sb: superblock to operate on - * - * Attempts to free all inodes (including dirty inodes) for a given superblock. - */ -void invalidate_inodes(struct super_block *sb) -{ - struct inode *inode, *next; - LIST_HEAD(dispose); - -again: - spin_lock(&sb->s_inode_list_lock); - list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { - spin_lock(&inode->i_lock); - if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { - spin_unlock(&inode->i_lock); - continue; - } - if (atomic_read(&inode->i_count)) { - spin_unlock(&inode->i_lock); - continue; - } - - inode->i_state |= I_FREEING; - inode_lru_list_del(inode); - spin_unlock(&inode->i_lock); - list_add(&inode->i_lru, &dispose); - if (need_resched()) { - spin_unlock(&sb->s_inode_list_lock); - cond_resched(); - dispose_list(&dispose); - goto again; - } - } - spin_unlock(&sb->s_inode_list_lock); - - dispose_list(&dispose); -} - /* * Isolate the inode from the LRU in preparation for freeing it. * @@ -800,7 +946,7 @@ again: * with this flag set because they are the inodes that are out of order. */ static enum lru_status inode_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 inode *inode = container_of(item, struct inode, i_lru); @@ -818,8 +964,8 @@ static enum lru_status inode_lru_isolate(struct list_head *item, * unreclaimable for a while. Remove them lazily here; iput, * sync, or the last page cache deletion will requeue them. */ - if (atomic_read(&inode->i_count) || - (inode->i_state & ~I_REFERENCED) || + if (icount_read(inode) || + (inode_state_read(inode) & ~I_REFERENCED) || !mapping_shrinkable(&inode->i_data)) { list_lru_isolate(lru, &inode->i_lru); spin_unlock(&inode->i_lock); @@ -828,8 +974,8 @@ static enum lru_status inode_lru_isolate(struct list_head *item, } /* Recently referenced inodes get one more pass */ - if (inode->i_state & I_REFERENCED) { - inode->i_state &= ~I_REFERENCED; + if (inode_state_read(inode) & I_REFERENCED) { + inode_state_clear(inode, I_REFERENCED); spin_unlock(&inode->i_lock); return LRU_ROTATE; } @@ -840,9 +986,9 @@ static enum lru_status inode_lru_isolate(struct list_head *item, * be under pressure before the cache inside the highmem zone. */ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) { - __iget(inode); + inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); - spin_unlock(lru_lock); + spin_unlock(&lru->lock); if (remove_inode_buffers(inode)) { unsigned long reap; reap = invalidate_mapping_pages(&inode->i_data, 0, -1); @@ -852,13 +998,12 @@ static enum lru_status inode_lru_isolate(struct list_head *item, __count_vm_events(PGINODESTEAL, reap); mm_account_reclaimed_pages(reap); } - iput(inode); - spin_lock(lru_lock); + inode_unpin_lru_isolating(inode); return LRU_RETRY; } - WARN_ON(inode->i_state & I_NEW); - inode->i_state |= I_FREEING; + WARN_ON(inode_state_read(inode) & I_NEW); + inode_state_set(inode, I_FREEING); list_lru_isolate_move(lru, &inode->i_lru, freeable); spin_unlock(&inode->i_lock); @@ -883,36 +1028,47 @@ long prune_icache_sb(struct super_block *sb, struct shrink_control *sc) return freed; } -static void __wait_on_freeing_inode(struct inode *inode); +static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked); /* * Called with the inode lock held. */ static struct inode *find_inode(struct super_block *sb, struct hlist_head *head, int (*test)(struct inode *, void *), - void *data) + void *data, bool is_inode_hash_locked, + bool *isnew) { struct inode *inode = NULL; + if (is_inode_hash_locked) + lockdep_assert_held(&inode_hash_lock); + else + lockdep_assert_not_held(&inode_hash_lock); + + rcu_read_lock(); repeat: - hlist_for_each_entry(inode, head, i_hash) { + hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_sb != sb) continue; if (!test(inode, data)) continue; spin_lock(&inode->i_lock); - if (inode->i_state & (I_FREEING|I_WILL_FREE)) { - __wait_on_freeing_inode(inode); + if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE)) { + __wait_on_freeing_inode(inode, is_inode_hash_locked); goto repeat; } - if (unlikely(inode->i_state & I_CREATING)) { + if (unlikely(inode_state_read(inode) & I_CREATING)) { spin_unlock(&inode->i_lock); + rcu_read_unlock(); return ERR_PTR(-ESTALE); } __iget(inode); + *isnew = !!(inode_state_read(inode) & I_NEW); spin_unlock(&inode->i_lock); + rcu_read_unlock(); return inode; } + rcu_read_unlock(); return NULL; } @@ -921,29 +1077,40 @@ repeat: * iget_locked for details. */ static struct inode *find_inode_fast(struct super_block *sb, - struct hlist_head *head, unsigned long ino) + struct hlist_head *head, unsigned long ino, + bool is_inode_hash_locked, bool *isnew) { struct inode *inode = NULL; + if (is_inode_hash_locked) + lockdep_assert_held(&inode_hash_lock); + else + lockdep_assert_not_held(&inode_hash_lock); + + rcu_read_lock(); repeat: - hlist_for_each_entry(inode, head, i_hash) { + hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_ino != ino) continue; if (inode->i_sb != sb) continue; spin_lock(&inode->i_lock); - if (inode->i_state & (I_FREEING|I_WILL_FREE)) { - __wait_on_freeing_inode(inode); + if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE)) { + __wait_on_freeing_inode(inode, is_inode_hash_locked); goto repeat; } - if (unlikely(inode->i_state & I_CREATING)) { + if (unlikely(inode_state_read(inode) & I_CREATING)) { spin_unlock(&inode->i_lock); + rcu_read_unlock(); return ERR_PTR(-ESTALE); } __iget(inode); + *isnew = !!(inode_state_read(inode) & I_NEW); spin_unlock(&inode->i_lock); + rcu_read_unlock(); return inode; } + rcu_read_unlock(); return NULL; } @@ -990,28 +1157,6 @@ unsigned int get_next_ino(void) EXPORT_SYMBOL(get_next_ino); /** - * new_inode_pseudo - obtain an inode - * @sb: superblock - * - * Allocates a new inode for given superblock. - * Inode wont be chained in superblock s_inodes list - * This means : - * - fs can't be unmount - * - quotas, fsnotify, writeback can't work - */ -struct inode *new_inode_pseudo(struct super_block *sb) -{ - struct inode *inode = alloc_inode(sb); - - if (inode) { - spin_lock(&inode->i_lock); - inode->i_state = 0; - spin_unlock(&inode->i_lock); - } - return inode; -} - -/** * new_inode - obtain an inode * @sb: superblock * @@ -1027,7 +1172,7 @@ struct inode *new_inode(struct super_block *sb) { struct inode *inode; - inode = new_inode_pseudo(sb); + inode = alloc_inode(sb); if (inode) inode_sb_list_add(inode); return inode; @@ -1043,9 +1188,8 @@ void lockdep_annotate_inode_mutex_key(struct inode *inode) /* Set new key only if filesystem hasn't already changed it */ if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) { /* - * ensure nobody is actually holding i_mutex + * ensure nobody is actually holding i_rwsem */ - // mutex_destroy(&inode->i_mutex); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &type->i_mutex_dir_key); @@ -1066,10 +1210,9 @@ void unlock_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); - WARN_ON(!(inode->i_state & I_NEW)); - inode->i_state &= ~I_NEW & ~I_CREATING; - smp_mb(); - wake_up_bit(&inode->i_state, __I_NEW); + WARN_ON(!(inode_state_read(inode) & I_NEW)); + inode_state_clear(inode, I_NEW | I_CREATING); + inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(unlock_new_inode); @@ -1078,58 +1221,15 @@ void discard_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); - WARN_ON(!(inode->i_state & I_NEW)); - inode->i_state &= ~I_NEW; - smp_mb(); - wake_up_bit(&inode->i_state, __I_NEW); + WARN_ON(!(inode_state_read(inode) & I_NEW)); + inode_state_clear(inode, I_NEW); + inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); iput(inode); } EXPORT_SYMBOL(discard_new_inode); /** - * lock_two_inodes - lock two inodes (may be regular files but also dirs) - * - * Lock any non-NULL argument. The caller must make sure that if he is passing - * in two directories, one is not ancestor of the other. Zero, one or two - * objects may be locked by this function. - * - * @inode1: first inode to lock - * @inode2: second inode to lock - * @subclass1: inode lock subclass for the first lock obtained - * @subclass2: inode lock subclass for the second lock obtained - */ -void lock_two_inodes(struct inode *inode1, struct inode *inode2, - unsigned subclass1, unsigned subclass2) -{ - if (!inode1 || !inode2) { - /* - * Make sure @subclass1 will be used for the acquired lock. - * This is not strictly necessary (no current caller cares) but - * let's keep things consistent. - */ - if (!inode1) - swap(inode1, inode2); - goto lock; - } - - /* - * If one object is directory and the other is not, we must make sure - * to lock directory first as the other object may be its child. - */ - if (S_ISDIR(inode2->i_mode) == S_ISDIR(inode1->i_mode)) { - if (inode1 > inode2) - swap(inode1, inode2); - } else if (!S_ISDIR(inode1->i_mode)) - swap(inode1, inode2); -lock: - if (inode1) - inode_lock_nested(inode1, subclass1); - if (inode2 && inode2 != inode1) - inode_lock_nested(inode2, subclass2); -} - -/** * lock_two_nondirectories - take two i_mutexes on non-directory objects * * Lock any non-NULL argument. Passed objects must not be directories. @@ -1144,7 +1244,12 @@ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2) WARN_ON_ONCE(S_ISDIR(inode1->i_mode)); if (inode2) WARN_ON_ONCE(S_ISDIR(inode2->i_mode)); - lock_two_inodes(inode1, inode2, I_MUTEX_NORMAL, I_MUTEX_NONDIR2); + if (inode1 > inode2) + swap(inode1, inode2); + if (inode1) + inode_lock(inode1); + if (inode2 && inode2 != inode1) + inode_lock_nested(inode2, I_MUTEX_NONDIR2); } EXPORT_SYMBOL(lock_two_nondirectories); @@ -1173,18 +1278,18 @@ EXPORT_SYMBOL(unlock_two_nondirectories); * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set + * @isnew: pointer to a bool which will indicate whether I_NEW is set * * Search for the inode specified by @hashval and @data in the inode cache, - * and if present it is return it with an increased reference count. This is - * a variant of iget5_locked() for callers that don't want to fail on memory - * allocation of inode. + * and if present return it with an increased reference count. This is a + * variant of iget5_locked() that doesn't allocate an inode. * - * If the inode is not in cache, insert the pre-allocated inode to cache and + * If the inode is not present in the cache, insert the pre-allocated inode and * return it locked, hashed, and with the I_NEW flag set. The file system gets * to fill it in before unlocking it via unlock_new_inode(). * - * Note both @test and @set are called with the inode_hash_lock held, so can't - * sleep. + * Note that both @test and @set are called with the inode_hash_lock held, so + * they can't sleep. */ struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), @@ -1192,10 +1297,13 @@ struct inode *inode_insert5(struct inode *inode, unsigned long hashval, { struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval); struct inode *old; + bool isnew; + + might_sleep(); again: spin_lock(&inode_hash_lock); - old = find_inode(inode->i_sb, head, test, data); + old = find_inode(inode->i_sb, head, test, data, true, &isnew); if (unlikely(old)) { /* * Uhhuh, somebody else created the same inode under us. @@ -1204,7 +1312,8 @@ again: spin_unlock(&inode_hash_lock); if (IS_ERR(old)) return NULL; - wait_on_inode(old); + if (unlikely(isnew)) + wait_on_new_inode(old); if (unlikely(inode_unhashed(old))) { iput(old); goto again; @@ -1213,8 +1322,8 @@ again: } if (set && unlikely(set(inode, data))) { - inode = NULL; - goto unlock; + spin_unlock(&inode_hash_lock); + return NULL; } /* @@ -1222,18 +1331,18 @@ again: * caller is responsible for filling in the contents */ spin_lock(&inode->i_lock); - inode->i_state |= I_NEW; + inode_state_set(inode, I_NEW); hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); + spin_unlock(&inode_hash_lock); + /* * Add inode to the sb list if it's not already. It has I_NEW at this * point, so it should be safe to test i_sb_list locklessly. */ if (list_empty(&inode->i_sb_list)) inode_sb_list_add(inode); -unlock: - spin_unlock(&inode_hash_lock); return inode; } @@ -1248,16 +1357,16 @@ EXPORT_SYMBOL(inode_insert5); * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, - * and if present it is return it with an increased reference count. This is - * a generalized version of iget_locked() for file systems where the inode + * and if present return it with an increased reference count. This is a + * generalized version of iget_locked() for file systems where the inode * number is not sufficient for unique identification of an inode. * - * If the inode is not in cache, allocate a new inode and return it locked, - * hashed, and with the I_NEW flag set. The file system gets to fill it in - * before unlocking it via unlock_new_inode(). + * If the inode is not present in the cache, allocate and insert a new inode + * and return it locked, hashed, and with the I_NEW flag set. The file system + * gets to fill it in before unlocking it via unlock_new_inode(). * - * Note both @test and @set are called with the inode_hash_lock held, so can't - * sleep. + * Note that both @test and @set are called with the inode_hash_lock held, so + * they can't sleep. */ struct inode *iget5_locked(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), @@ -1269,7 +1378,6 @@ struct inode *iget5_locked(struct super_block *sb, unsigned long hashval, struct inode *new = alloc_inode(sb); if (new) { - new->i_state = 0; inode = inode_insert5(new, hashval, test, set, data); if (unlikely(inode != new)) destroy_inode(new); @@ -1280,6 +1388,51 @@ struct inode *iget5_locked(struct super_block *sb, unsigned long hashval, EXPORT_SYMBOL(iget5_locked); /** + * iget5_locked_rcu - obtain an inode from a mounted file system + * @sb: super block of file system + * @hashval: hash value (usually inode number) to get + * @test: callback used for comparisons between inodes + * @set: callback used to initialize a new struct inode + * @data: opaque data pointer to pass to @test and @set + * + * This is equivalent to iget5_locked, except the @test callback must + * tolerate the inode not being stable, including being mid-teardown. + */ +struct inode *iget5_locked_rcu(struct super_block *sb, unsigned long hashval, + int (*test)(struct inode *, void *), + int (*set)(struct inode *, void *), void *data) +{ + struct hlist_head *head = inode_hashtable + hash(sb, hashval); + struct inode *inode, *new; + bool isnew; + + might_sleep(); + +again: + inode = find_inode(sb, head, test, data, false, &isnew); + if (inode) { + if (IS_ERR(inode)) + return NULL; + if (unlikely(isnew)) + wait_on_new_inode(inode); + if (unlikely(inode_unhashed(inode))) { + iput(inode); + goto again; + } + return inode; + } + + new = alloc_inode(sb); + if (new) { + inode = inode_insert5(new, hashval, test, set, data); + if (unlikely(inode != new)) + destroy_inode(new); + } + return inode; +} +EXPORT_SYMBOL_GPL(iget5_locked_rcu); + +/** * iget_locked - obtain an inode from a mounted file system * @sb: super block of file system * @ino: inode number to get @@ -1296,14 +1449,17 @@ struct inode *iget_locked(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; + bool isnew; + + might_sleep(); + again: - spin_lock(&inode_hash_lock); - inode = find_inode_fast(sb, head, ino); - spin_unlock(&inode_hash_lock); + inode = find_inode_fast(sb, head, ino, false, &isnew); if (inode) { if (IS_ERR(inode)) return NULL; - wait_on_inode(inode); + if (unlikely(isnew)) + wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; @@ -1317,15 +1473,15 @@ again: spin_lock(&inode_hash_lock); /* We released the lock, so.. */ - old = find_inode_fast(sb, head, ino); + old = find_inode_fast(sb, head, ino, true, &isnew); if (!old) { inode->i_ino = ino; spin_lock(&inode->i_lock); - inode->i_state = I_NEW; + inode_state_assign(inode, I_NEW); hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); - inode_sb_list_add(inode); spin_unlock(&inode_hash_lock); + inode_sb_list_add(inode); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents @@ -1343,7 +1499,8 @@ again: if (IS_ERR(old)) return NULL; inode = old; - wait_on_inode(inode); + if (unlikely(isnew)) + wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; @@ -1414,7 +1571,7 @@ EXPORT_SYMBOL(iunique); struct inode *igrab(struct inode *inode) { spin_lock(&inode->i_lock); - if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) { + if (!(inode_state_read(inode) & (I_FREEING | I_WILL_FREE))) { __iget(inode); spin_unlock(&inode->i_lock); } else { @@ -1447,13 +1604,13 @@ EXPORT_SYMBOL(igrab); * Note2: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, - int (*test)(struct inode *, void *), void *data) + int (*test)(struct inode *, void *), void *data, bool *isnew) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; spin_lock(&inode_hash_lock); - inode = find_inode(sb, head, test, data); + inode = find_inode(sb, head, test, data, true, isnew); spin_unlock(&inode_hash_lock); return IS_ERR(inode) ? NULL : inode; @@ -1481,10 +1638,15 @@ struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *inode; + bool isnew; + + might_sleep(); + again: - inode = ilookup5_nowait(sb, hashval, test, data); + inode = ilookup5_nowait(sb, hashval, test, data, &isnew); if (inode) { - wait_on_inode(inode); + if (unlikely(isnew)) + wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; @@ -1506,15 +1668,18 @@ struct inode *ilookup(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; + bool isnew; + + might_sleep(); + again: - spin_lock(&inode_hash_lock); - inode = find_inode_fast(sb, head, ino); - spin_unlock(&inode_hash_lock); + inode = find_inode_fast(sb, head, ino, false, &isnew); if (inode) { if (IS_ERR(inode)) return NULL; - wait_on_inode(inode); + if (unlikely(isnew)) + wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; @@ -1606,7 +1771,7 @@ struct inode *find_inode_rcu(struct super_block *sb, unsigned long hashval, hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_sb == sb && - !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE)) && + !(inode_state_read_once(inode) & (I_FREEING | I_WILL_FREE)) && test(inode, data)) return inode; } @@ -1645,7 +1810,7 @@ struct inode *find_inode_by_ino_rcu(struct super_block *sb, hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb && - !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE))) + !(inode_state_read_once(inode) & (I_FREEING | I_WILL_FREE))) return inode; } return NULL; @@ -1657,6 +1822,9 @@ int insert_inode_locked(struct inode *inode) struct super_block *sb = inode->i_sb; ino_t ino = inode->i_ino; struct hlist_head *head = inode_hashtable + hash(sb, ino); + bool isnew; + + might_sleep(); while (1) { struct inode *old = NULL; @@ -1667,7 +1835,7 @@ int insert_inode_locked(struct inode *inode) if (old->i_sb != sb) continue; spin_lock(&old->i_lock); - if (old->i_state & (I_FREEING|I_WILL_FREE)) { + if (inode_state_read(old) & (I_FREEING | I_WILL_FREE)) { spin_unlock(&old->i_lock); continue; } @@ -1675,21 +1843,23 @@ int insert_inode_locked(struct inode *inode) } if (likely(!old)) { spin_lock(&inode->i_lock); - inode->i_state |= I_NEW | I_CREATING; + inode_state_set(inode, I_NEW | I_CREATING); hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); return 0; } - if (unlikely(old->i_state & I_CREATING)) { + if (unlikely(inode_state_read(old) & I_CREATING)) { spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); return -EBUSY; } __iget(old); + isnew = !!(inode_state_read(old) & I_NEW); spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); - wait_on_inode(old); + if (isnew) + wait_on_new_inode(old); if (unlikely(!inode_unhashed(old))) { iput(old); return -EBUSY; @@ -1704,7 +1874,9 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, { struct inode *old; - inode->i_state |= I_CREATING; + might_sleep(); + + inode_state_set_raw(inode, I_CREATING); old = inode_insert5(inode, hashval, test, NULL, data); if (old != inode) { @@ -1716,11 +1888,11 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, EXPORT_SYMBOL(insert_inode_locked4); -int generic_delete_inode(struct inode *inode) +int inode_just_drop(struct inode *inode) { return 1; } -EXPORT_SYMBOL(generic_delete_inode); +EXPORT_SYMBOL(inode_just_drop); /* * Called when we're dropping the last reference @@ -1736,40 +1908,44 @@ static void iput_final(struct inode *inode) { struct super_block *sb = inode->i_sb; const struct super_operations *op = inode->i_sb->s_op; - unsigned long state; int drop; - WARN_ON(inode->i_state & I_NEW); + WARN_ON(inode_state_read(inode) & I_NEW); + VFS_BUG_ON_INODE(atomic_read(&inode->i_count) != 0, inode); if (op->drop_inode) drop = op->drop_inode(inode); else - drop = generic_drop_inode(inode); + drop = inode_generic_drop(inode); if (!drop && - !(inode->i_state & I_DONTCACHE) && + !(inode_state_read(inode) & I_DONTCACHE) && (sb->s_flags & SB_ACTIVE)) { - __inode_add_lru(inode, true); + __inode_lru_list_add(inode, true); spin_unlock(&inode->i_lock); return; } - state = inode->i_state; - if (!drop) { - WRITE_ONCE(inode->i_state, state | I_WILL_FREE); + /* + * Re-check ->i_count in case the ->drop_inode() hooks played games. + * Note we only execute this if the verdict was to drop the inode. + */ + VFS_BUG_ON_INODE(atomic_read(&inode->i_count) != 0, inode); + + if (drop) { + inode_state_set(inode, I_FREEING); + } else { + inode_state_set(inode, I_WILL_FREE); spin_unlock(&inode->i_lock); write_inode_now(inode, 1); spin_lock(&inode->i_lock); - state = inode->i_state; - WARN_ON(state & I_NEW); - state &= ~I_WILL_FREE; + WARN_ON(inode_state_read(inode) & I_NEW); + inode_state_replace(inode, I_WILL_FREE, I_FREEING); } - WRITE_ONCE(inode->i_state, state | I_FREEING); - if (!list_empty(&inode->i_lru)) - inode_lru_list_del(inode); + inode_lru_list_del(inode); spin_unlock(&inode->i_lock); evict(inode); @@ -1786,23 +1962,61 @@ static void iput_final(struct inode *inode) */ void iput(struct inode *inode) { - if (!inode) + might_sleep(); + if (unlikely(!inode)) return; - BUG_ON(inode->i_state & I_CLEAR); + retry: - if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) { - if (inode->i_nlink && (inode->i_state & I_DIRTY_TIME)) { - atomic_inc(&inode->i_count); - spin_unlock(&inode->i_lock); - trace_writeback_lazytime_iput(inode); - mark_inode_dirty_sync(inode); - goto retry; - } - iput_final(inode); + lockdep_assert_not_held(&inode->i_lock); + VFS_BUG_ON_INODE(inode_state_read_once(inode) & (I_FREEING | I_CLEAR), inode); + /* + * Note this assert is technically racy as if the count is bogusly + * equal to one, then two CPUs racing to further drop it can both + * conclude it's fine. + */ + VFS_BUG_ON_INODE(atomic_read(&inode->i_count) < 1, inode); + + if (atomic_add_unless(&inode->i_count, -1, 1)) + return; + + if ((inode_state_read_once(inode) & I_DIRTY_TIME) && inode->i_nlink) { + trace_writeback_lazytime_iput(inode); + mark_inode_dirty_sync(inode); + goto retry; } + + spin_lock(&inode->i_lock); + if (unlikely((inode_state_read(inode) & I_DIRTY_TIME) && inode->i_nlink)) { + spin_unlock(&inode->i_lock); + goto retry; + } + + if (!atomic_dec_and_test(&inode->i_count)) { + spin_unlock(&inode->i_lock); + return; + } + + /* + * iput_final() drops ->i_lock, we can't assert on it as the inode may + * be deallocated by the time the call returns. + */ + iput_final(inode); } EXPORT_SYMBOL(iput); +/** + * iput_not_last - put an inode assuming this is not the last reference + * @inode: inode to put + */ +void iput_not_last(struct inode *inode) +{ + VFS_BUG_ON_INODE(inode_state_read_once(inode) & (I_FREEING | I_CLEAR), inode); + VFS_BUG_ON_INODE(atomic_read(&inode->i_count) < 2, inode); + + WARN_ON(atomic_sub_return(1, &inode->i_count) == 0); +} +EXPORT_SYMBOL(iput_not_last); + #ifdef CONFIG_BLOCK /** * bmap - find a block number in a file @@ -1834,35 +2048,37 @@ EXPORT_SYMBOL(bmap); * earlier than or equal to either the ctime or mtime, * or if at least a day has passed since the last atime update. */ -static int relatime_need_update(struct vfsmount *mnt, struct inode *inode, +static bool relatime_need_update(struct vfsmount *mnt, struct inode *inode, struct timespec64 now) { - struct timespec64 ctime; + struct timespec64 atime, mtime, ctime; if (!(mnt->mnt_flags & MNT_RELATIME)) - return 1; + return true; /* * Is mtime younger than or equal to atime? If yes, update atime: */ - if (timespec64_compare(&inode->i_mtime, &inode->i_atime) >= 0) - return 1; + atime = inode_get_atime(inode); + mtime = inode_get_mtime(inode); + if (timespec64_compare(&mtime, &atime) >= 0) + return true; /* * Is ctime younger than or equal to atime? If yes, update atime: */ ctime = inode_get_ctime(inode); - if (timespec64_compare(&ctime, &inode->i_atime) >= 0) - return 1; + if (timespec64_compare(&ctime, &atime) >= 0) + return true; /* * Is the previous atime value older than a day? If yes, * update atime: */ - if ((long)(now.tv_sec - inode->i_atime.tv_sec) >= 24*60*60) - return 1; + if ((long)(now.tv_sec - atime.tv_sec) >= 24*60*60) + return true; /* * Good, we can skip the atime update: */ - return 0; + return false; } /** @@ -1888,12 +2104,13 @@ int inode_update_timestamps(struct inode *inode, int flags) if (flags & (S_MTIME|S_CTIME|S_VERSION)) { struct timespec64 ctime = inode_get_ctime(inode); + struct timespec64 mtime = inode_get_mtime(inode); now = inode_set_ctime_current(inode); if (!timespec64_equal(&now, &ctime)) updated |= S_CTIME; - if (!timespec64_equal(&now, &inode->i_mtime)) { - inode->i_mtime = now; + if (!timespec64_equal(&now, &mtime)) { + inode_set_mtime_to_ts(inode, now); updated |= S_MTIME; } if (IS_I_VERSION(inode) && inode_maybe_inc_iversion(inode, updated)) @@ -1903,8 +2120,10 @@ int inode_update_timestamps(struct inode *inode, int flags) } if (flags & S_ATIME) { - if (!timespec64_equal(&now, &inode->i_atime)) { - inode->i_atime = now; + struct timespec64 atime = inode_get_atime(inode); + + if (!timespec64_equal(&now, &atime)) { + inode_set_atime_to_ts(inode, now); updated |= S_ATIME; } } @@ -1963,7 +2182,7 @@ EXPORT_SYMBOL(inode_update_time); bool atime_needs_update(const struct path *path, struct inode *inode) { struct vfsmount *mnt = path->mnt; - struct timespec64 now; + struct timespec64 now, atime; if (inode->i_flags & S_NOATIME) return false; @@ -1989,7 +2208,8 @@ bool atime_needs_update(const struct path *path, struct inode *inode) if (!relatime_need_update(mnt, inode, now)) return false; - if (timespec64_equal(&inode->i_atime, &now)) + atime = inode_get_atime(inode); + if (timespec64_equal(&atime, &now)) return false; return true; @@ -2006,7 +2226,7 @@ void touch_atime(const struct path *path) if (!sb_start_write_trylock(inode->i_sb)) return; - if (__mnt_want_write(mnt) != 0) + if (mnt_get_write_access(mnt) != 0) goto skip_update; /* * File systems can error out when updating inodes if they need to @@ -2018,7 +2238,7 @@ void touch_atime(const struct path *path) * of the fs read only, e.g. subvolumes in Btrfs. */ inode_update_time(inode, S_ATIME); - __mnt_drop_write(mnt); + mnt_put_write_access(mnt); skip_update: sb_end_write(inode->i_sb); } @@ -2061,7 +2281,7 @@ static int __remove_privs(struct mnt_idmap *idmap, return notify_change(idmap, dentry, &newattrs, NULL); } -static int __file_remove_privs(struct file *file, unsigned int flags) +static int file_remove_privs_flags(struct file *file, unsigned int flags) { struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); @@ -2098,86 +2318,82 @@ static int __file_remove_privs(struct file *file, unsigned int flags) */ int file_remove_privs(struct file *file) { - return __file_remove_privs(file, 0); + return file_remove_privs_flags(file, 0); } EXPORT_SYMBOL(file_remove_privs); /** - * current_mgtime - Return FS time (possibly fine-grained) + * current_time - Return FS time (possibly fine-grained) * @inode: inode. * * Return the current time truncated to the time granularity supported by * the fs, as suitable for a ctime/mtime change. If the ctime is flagged - * as having been QUERIED, get a fine-grained timestamp. + * as having been QUERIED, get a fine-grained timestamp, but don't update + * the floor. + * + * For a multigrain inode, this is effectively an estimate of the timestamp + * that a file would receive. An actual update must go through + * inode_set_ctime_current(). */ -struct timespec64 current_mgtime(struct inode *inode) +struct timespec64 current_time(struct inode *inode) { - struct timespec64 now, ctime; - atomic_long_t *pnsec = (atomic_long_t *)&inode->__i_ctime.tv_nsec; - long nsec = atomic_long_read(pnsec); - - if (nsec & I_CTIME_QUERIED) { - ktime_get_real_ts64(&now); - return timestamp_truncate(now, inode); - } - - ktime_get_coarse_real_ts64(&now); - now = timestamp_truncate(now, inode); + struct timespec64 now; + u32 cns; - /* - * If we've recently fetched a fine-grained timestamp - * then the coarse-grained one may still be earlier than the - * existing ctime. Just keep the existing value if so. - */ - ctime = inode_get_ctime(inode); - if (timespec64_compare(&ctime, &now) > 0) - now = ctime; + ktime_get_coarse_real_ts64_mg(&now); - return now; -} -EXPORT_SYMBOL(current_mgtime); + if (!is_mgtime(inode)) + goto out; -static struct timespec64 current_ctime(struct inode *inode) -{ - if (is_mgtime(inode)) - return current_mgtime(inode); - return current_time(inode); + /* If nothing has queried it, then coarse time is fine */ + cns = smp_load_acquire(&inode->i_ctime_nsec); + if (cns & I_CTIME_QUERIED) { + /* + * If there is no apparent change, then get a fine-grained + * timestamp. + */ + if (now.tv_nsec == (cns & ~I_CTIME_QUERIED)) + ktime_get_real_ts64(&now); + } +out: + return timestamp_truncate(now, inode); } +EXPORT_SYMBOL(current_time); -static int inode_needs_update_time(struct inode *inode) +static int file_update_time_flags(struct file *file, unsigned int flags) { - int sync_it = 0; - struct timespec64 now = current_ctime(inode); - struct timespec64 ctime; + struct inode *inode = file_inode(file); + struct timespec64 now, ts; + int sync_mode = 0; + int ret = 0; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) return 0; + if (unlikely(file->f_mode & FMODE_NOCMTIME)) + return 0; - if (!timespec64_equal(&inode->i_mtime, &now)) - sync_it = S_MTIME; - - ctime = inode_get_ctime(inode); - if (!timespec64_equal(&ctime, &now)) - sync_it |= S_CTIME; + now = current_time(inode); + ts = inode_get_mtime(inode); + if (!timespec64_equal(&ts, &now)) + sync_mode |= S_MTIME; + ts = inode_get_ctime(inode); + if (!timespec64_equal(&ts, &now)) + sync_mode |= S_CTIME; if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode)) - sync_it |= S_VERSION; + sync_mode |= S_VERSION; - return sync_it; -} - -static int __file_update_time(struct file *file, int sync_mode) -{ - int ret = 0; - struct inode *inode = file_inode(file); + if (!sync_mode) + return 0; - /* try to update time settings */ - if (!__mnt_want_write_file(file)) { - ret = inode_update_time(inode, sync_mode); - __mnt_drop_write_file(file); - } + if (flags & IOCB_NOWAIT) + return -EAGAIN; + if (mnt_get_write_access_file(file)) + return 0; + ret = inode_update_time(inode, sync_mode); + mnt_put_write_access_file(file); return ret; } @@ -2197,14 +2413,7 @@ static int __file_update_time(struct file *file, int sync_mode) */ int file_update_time(struct file *file) { - int ret; - struct inode *inode = file_inode(file); - - ret = inode_needs_update_time(inode); - if (ret <= 0) - return ret; - - return __file_update_time(file, ret); + return file_update_time_flags(file, 0); } EXPORT_SYMBOL(file_update_time); @@ -2226,26 +2435,15 @@ EXPORT_SYMBOL(file_update_time); static int file_modified_flags(struct file *file, int flags) { int ret; - struct inode *inode = file_inode(file); /* * Clear the security bits if the process is not being run by root. * This keeps people from modifying setuid and setgid binaries. */ - ret = __file_remove_privs(file, flags); + ret = file_remove_privs_flags(file, flags); if (ret) return ret; - - if (unlikely(file->f_mode & FMODE_NOCMTIME)) - return 0; - - ret = inode_needs_update_time(inode); - if (ret <= 0) - return ret; - if (flags & IOCB_NOWAIT) - return -EAGAIN; - - return __file_update_time(file, ret); + return file_update_time_flags(file, flags); } /** @@ -2303,17 +2501,31 @@ EXPORT_SYMBOL(inode_needs_sync); * wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list * will DTRT. */ -static void __wait_on_freeing_inode(struct inode *inode) +static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked) { - wait_queue_head_t *wq; - DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW); - wq = bit_waitqueue(&inode->i_state, __I_NEW); - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; + + /* + * Handle racing against evict(), see that routine for more details. + */ + if (unlikely(inode_unhashed(inode))) { + WARN_ON(is_inode_hash_locked); + spin_unlock(&inode->i_lock); + return; + } + + wq_head = inode_bit_waitqueue(&wqe, inode, __I_NEW); + prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); - spin_unlock(&inode_hash_lock); + rcu_read_unlock(); + if (is_inode_hash_locked) + spin_unlock(&inode_hash_lock); schedule(); - finish_wait(wq, &wait.wq_entry); - spin_lock(&inode_hash_lock); + finish_wait(wq_head, &wqe.wq_entry); + if (is_inode_hash_locked) + spin_lock(&inode_hash_lock); + rcu_read_lock(); } static __initdata unsigned long ihash_entries; @@ -2356,7 +2568,7 @@ void __init inode_init(void) sizeof(struct inode), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| - SLAB_MEM_SPREAD|SLAB_ACCOUNT), + SLAB_ACCOUNT), init_once); /* Hash may have been set up in inode_init_early */ @@ -2378,21 +2590,28 @@ void __init inode_init(void) void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) { inode->i_mode = mode; - if (S_ISCHR(mode)) { + switch (inode->i_mode & S_IFMT) { + case S_IFCHR: inode->i_fop = &def_chr_fops; inode->i_rdev = rdev; - } else if (S_ISBLK(mode)) { + break; + case S_IFBLK: if (IS_ENABLED(CONFIG_BLOCK)) inode->i_fop = &def_blk_fops; inode->i_rdev = rdev; - } else if (S_ISFIFO(mode)) + break; + case S_IFIFO: inode->i_fop = &pipefifo_fops; - else if (S_ISSOCK(mode)) - ; /* leave it no_open_fops */ - else + break; + case S_IFSOCK: + /* leave it no_open_fops */ + break; + default: printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for" " inode %s:%lu\n", mode, inode->i_sb->s_id, inode->i_ino); + break; + } } EXPORT_SYMBOL(init_special_inode); @@ -2437,7 +2656,7 @@ EXPORT_SYMBOL(inode_init_owner); * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the - * raw inode simply passs @nop_mnt_idmap. + * raw inode simply pass @nop_mnt_idmap. */ bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode) @@ -2459,18 +2678,11 @@ EXPORT_SYMBOL(inode_owner_or_capable); /* * Direct i/o helper functions */ -static void __inode_dio_wait(struct inode *inode) +bool inode_dio_finished(const struct inode *inode) { - wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP); - DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); - - do { - prepare_to_wait(wq, &q.wq_entry, TASK_UNINTERRUPTIBLE); - if (atomic_read(&inode->i_dio_count)) - schedule(); - } while (atomic_read(&inode->i_dio_count)); - finish_wait(wq, &q.wq_entry); + return atomic_read(&inode->i_dio_count) == 0; } +EXPORT_SYMBOL(inode_dio_finished); /** * inode_dio_wait - wait for outstanding DIO requests to finish @@ -2480,19 +2692,25 @@ static void __inode_dio_wait(struct inode *inode) * proceed with a truncate or equivalent operation. * * Must be called under a lock that serializes taking new references - * to i_dio_count, usually by inode->i_mutex. + * to i_dio_count, usually by inode->i_rwsem. */ void inode_dio_wait(struct inode *inode) { - if (atomic_read(&inode->i_dio_count)) - __inode_dio_wait(inode); + wait_var_event(&inode->i_dio_count, inode_dio_finished(inode)); } EXPORT_SYMBOL(inode_dio_wait); +void inode_dio_wait_interruptible(struct inode *inode) +{ + wait_var_event_interruptible(&inode->i_dio_count, + inode_dio_finished(inode)); +} +EXPORT_SYMBOL(inode_dio_wait_interruptible); + /* * inode_set_flags - atomically set some inode flags * - * Note: the caller should be holding i_mutex, or else be sure that + * Note: the caller should be holding i_rwsem exclusively, or else be sure that * they have exclusive access to the inode structure (i.e., while the * inode is being instantiated). The reason for the cmpxchg() loop * --- which wouldn't be necessary if all code paths which modify @@ -2500,7 +2718,7 @@ EXPORT_SYMBOL(inode_dio_wait); * code path which doesn't today so we use cmpxchg() out of an abundance * of caution. * - * In the long run, i_mutex is overkill, and we should probably look + * In the long run, i_rwsem is overkill, and we should probably look * at using the i_lock spinlock to protect i_flags, and then make sure * it is so documented in include/linux/fs.h and that all code follows * the locking convention!! @@ -2519,6 +2737,16 @@ void inode_nohighmem(struct inode *inode) } EXPORT_SYMBOL(inode_nohighmem); +struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) +{ + trace_inode_set_ctime_to_ts(inode, &ts); + set_normalized_timespec64(&ts, ts.tv_sec, ts.tv_nsec); + inode->i_ctime_sec = ts.tv_sec; + inode->i_ctime_nsec = ts.tv_nsec; + return ts; +} +EXPORT_SYMBOL(inode_set_ctime_to_ts); + /** * timestamp_truncate - Truncate timespec to a granularity * @t: Timespec @@ -2551,73 +2779,159 @@ struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode) EXPORT_SYMBOL(timestamp_truncate); /** - * current_time - Return FS time - * @inode: inode. + * inode_set_ctime_current - set the ctime to current_time + * @inode: inode * - * Return the current time truncated to the time granularity supported by - * the fs. + * Set the inode's ctime to the current value for the inode. Returns the + * current value that was assigned. If this is not a multigrain inode, then we + * set it to the later of the coarse time and floor value. * - * Note that inode and inode->sb cannot be NULL. - * Otherwise, the function warns and returns time without truncation. + * If it is multigrain, then we first see if the coarse-grained timestamp is + * distinct from what is already there. If so, then use that. Otherwise, get a + * fine-grained timestamp. + * + * After that, try to swap the new value into i_ctime_nsec. Accept the + * resulting ctime, regardless of the outcome of the swap. If it has + * already been replaced, then that timestamp is later than the earlier + * unacceptable one, and is thus acceptable. */ -struct timespec64 current_time(struct inode *inode) +struct timespec64 inode_set_ctime_current(struct inode *inode) { struct timespec64 now; + u32 cns, cur; - ktime_get_coarse_real_ts64(&now); - return timestamp_truncate(now, inode); + ktime_get_coarse_real_ts64_mg(&now); + now = timestamp_truncate(now, inode); + + /* Just return that if this is not a multigrain fs */ + if (!is_mgtime(inode)) { + inode_set_ctime_to_ts(inode, now); + goto out; + } + + /* + * A fine-grained time is only needed if someone has queried + * for timestamps, and the current coarse grained time isn't + * later than what's already there. + */ + cns = smp_load_acquire(&inode->i_ctime_nsec); + if (cns & I_CTIME_QUERIED) { + struct timespec64 ctime = { .tv_sec = inode->i_ctime_sec, + .tv_nsec = cns & ~I_CTIME_QUERIED }; + + if (timespec64_compare(&now, &ctime) <= 0) { + ktime_get_real_ts64_mg(&now); + now = timestamp_truncate(now, inode); + mgtime_counter_inc(mg_fine_stamps); + } + } + mgtime_counter_inc(mg_ctime_updates); + + /* No need to cmpxchg if it's exactly the same */ + if (cns == now.tv_nsec && inode->i_ctime_sec == now.tv_sec) { + trace_ctime_xchg_skip(inode, &now); + goto out; + } + cur = cns; +retry: + /* Try to swap the nsec value into place. */ + if (try_cmpxchg(&inode->i_ctime_nsec, &cur, now.tv_nsec)) { + /* If swap occurred, then we're (mostly) done */ + inode->i_ctime_sec = now.tv_sec; + trace_ctime_ns_xchg(inode, cns, now.tv_nsec, cur); + mgtime_counter_inc(mg_ctime_swaps); + } else { + /* + * Was the change due to someone marking the old ctime QUERIED? + * If so then retry the swap. This can only happen once since + * the only way to clear I_CTIME_QUERIED is to stamp the inode + * with a new ctime. + */ + if (!(cns & I_CTIME_QUERIED) && (cns | I_CTIME_QUERIED) == cur) { + cns = cur; + goto retry; + } + /* Otherwise, keep the existing ctime */ + now.tv_sec = inode->i_ctime_sec; + now.tv_nsec = cur & ~I_CTIME_QUERIED; + } +out: + return now; } -EXPORT_SYMBOL(current_time); +EXPORT_SYMBOL(inode_set_ctime_current); /** - * inode_set_ctime_current - set the ctime to current_time - * @inode: inode + * inode_set_ctime_deleg - try to update the ctime on a delegated inode + * @inode: inode to update + * @update: timespec64 to set the ctime + * + * Attempt to atomically update the ctime on behalf of a delegation holder. * - * Set the inode->i_ctime to the current value for the inode. Returns - * the current value that was assigned to i_ctime. + * The nfs server can call back the holder of a delegation to get updated + * inode attributes, including the mtime. When updating the mtime, update + * the ctime to a value at least equal to that. + * + * This can race with concurrent updates to the inode, in which + * case the update is skipped. + * + * Note that this works even when multigrain timestamps are not enabled, + * so it is used in either case. */ -struct timespec64 inode_set_ctime_current(struct inode *inode) +struct timespec64 inode_set_ctime_deleg(struct inode *inode, struct timespec64 update) { - struct timespec64 now; - struct timespec64 ctime; + struct timespec64 now, cur_ts; + u32 cur, old; - ctime.tv_nsec = READ_ONCE(inode->__i_ctime.tv_nsec); - if (!(ctime.tv_nsec & I_CTIME_QUERIED)) { - now = current_time(inode); + /* pairs with try_cmpxchg below */ + cur = smp_load_acquire(&inode->i_ctime_nsec); + cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED; + cur_ts.tv_sec = inode->i_ctime_sec; - /* Just copy it into place if it's not multigrain */ - if (!is_mgtime(inode)) { - inode_set_ctime_to_ts(inode, now); - return now; - } + /* If the update is older than the existing value, skip it. */ + if (timespec64_compare(&update, &cur_ts) <= 0) + return cur_ts; - /* - * If we've recently updated with a fine-grained timestamp, - * then the coarse-grained one may still be earlier than the - * existing ctime. Just keep the existing value if so. - */ - ctime.tv_sec = inode->__i_ctime.tv_sec; - if (timespec64_compare(&ctime, &now) > 0) - return ctime; + ktime_get_coarse_real_ts64_mg(&now); - /* - * Ctime updates are usually protected by the inode_lock, but - * we can still race with someone setting the QUERIED flag. - * Try to swap the new nsec value into place. If it's changed - * in the interim, then just go with a fine-grained timestamp. - */ - if (cmpxchg(&inode->__i_ctime.tv_nsec, ctime.tv_nsec, - now.tv_nsec) != ctime.tv_nsec) - goto fine_grained; - inode->__i_ctime.tv_sec = now.tv_sec; - return now; + /* Clamp the update to "now" if it's in the future */ + if (timespec64_compare(&update, &now) > 0) + update = now; + + update = timestamp_truncate(update, inode); + + /* No need to update if the values are already the same */ + if (timespec64_equal(&update, &cur_ts)) + return cur_ts; + + /* + * Try to swap the nsec value into place. If it fails, that means + * it raced with an update due to a write or similar activity. That + * stamp takes precedence, so just skip the update. + */ +retry: + old = cur; + if (try_cmpxchg(&inode->i_ctime_nsec, &cur, update.tv_nsec)) { + inode->i_ctime_sec = update.tv_sec; + mgtime_counter_inc(mg_ctime_swaps); + return update; } -fine_grained: - ktime_get_real_ts64(&now); - inode_set_ctime_to_ts(inode, timestamp_truncate(now, inode)); - return now; + + /* + * Was the change due to another task marking the old ctime QUERIED? + * + * If so, then retry the swap. This can only happen once since + * the only way to clear I_CTIME_QUERIED is to stamp the inode + * with a new ctime. + */ + if (!(old & I_CTIME_QUERIED) && (cur == (old | I_CTIME_QUERIED))) + goto retry; + + /* Otherwise, it was a new timestamp. */ + cur_ts.tv_sec = inode->i_ctime_sec; + cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED; + return cur_ts; } -EXPORT_SYMBOL(inode_set_ctime_current); +EXPORT_SYMBOL(inode_set_ctime_deleg); /** * in_group_or_capable - check whether caller is CAP_FSETID privileged @@ -2625,7 +2939,7 @@ EXPORT_SYMBOL(inode_set_ctime_current); * @inode: inode to check * @vfsgid: the new/current vfsgid of @inode * - * Check wether @vfsgid is in the caller's group list or if the caller is + * Check whether @vfsgid is in the caller's group list or if the caller is * privileged with CAP_FSETID over @inode. This can be used to determine * whether the setgid bit can be kept or must be dropped. * @@ -2640,6 +2954,7 @@ bool in_group_or_capable(struct mnt_idmap *idmap, return true; return false; } +EXPORT_SYMBOL(in_group_or_capable); /** * mode_strip_sgid - handle the sgid bit for non-directories @@ -2667,3 +2982,26 @@ umode_t mode_strip_sgid(struct mnt_idmap *idmap, return mode & ~S_ISGID; } EXPORT_SYMBOL(mode_strip_sgid); + +#ifdef CONFIG_DEBUG_VFS +/* + * Dump an inode. + * + * TODO: add a proper inode dumping routine, this is a stub to get debug off the + * ground. + * + * TODO: handle getting to fs type with get_kernel_nofault()? + * See dump_mapping() above. + */ +void dump_inode(struct inode *inode, const char *reason) +{ + struct super_block *sb = inode->i_sb; + + pr_warn("%s encountered for inode %px\n" + "fs %s mode %ho opflags 0x%hx flags 0x%x state 0x%x count %d\n", + reason, inode, sb->s_type->name, inode->i_mode, inode->i_opflags, + inode->i_flags, inode_state_read_once(inode), atomic_read(&inode->i_count)); +} + +EXPORT_SYMBOL(dump_inode); +#endif |