diff options
Diffstat (limited to 'fs/inode.c')
| -rw-r--r-- | fs/inode.c | 1443 |
1 files changed, 834 insertions, 609 deletions
diff --git a/fs/inode.c b/fs/inode.c index ae2727ab0c3..6eecb7ff0b9 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1,151 +1,119 @@ /* - * linux/fs/inode.c - * * (C) 1997 Linus Torvalds + * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation) */ - +#include <linux/export.h> #include <linux/fs.h> #include <linux/mm.h> -#include <linux/dcache.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/writeback.h> -#include <linux/module.h> #include <linux/backing-dev.h> -#include <linux/wait.h> -#include <linux/rwsem.h> #include <linux/hash.h> #include <linux/swap.h> #include <linux/security.h> -#include <linux/pagemap.h> #include <linux/cdev.h> #include <linux/bootmem.h> #include <linux/fsnotify.h> #include <linux/mount.h> -#include <linux/async.h> #include <linux/posix_acl.h> -#include <linux/ima.h> +#include <linux/prefetch.h> +#include <linux/buffer_head.h> /* for inode_has_buffers */ +#include <linux/ratelimit.h> +#include <linux/list_lru.h> +#include "internal.h" /* - * This is needed for the following functions: - * - inode_has_buffers - * - invalidate_bdev + * Inode locking rules: * - * FIXME: remove all knowledge of the buffer layer from this file - */ -#include <linux/buffer_head.h> - -/* - * New inode.c implementation. + * inode->i_lock protects: + * inode->i_state, inode->i_hash, __iget() + * Inode LRU list locks protect: + * inode->i_sb->s_inode_lru, inode->i_lru + * inode_sb_list_lock protects: + * sb->s_inodes, inode->i_sb_list + * bdi->wb.list_lock protects: + * bdi->wb.b_{dirty,io,more_io}, inode->i_wb_list + * inode_hash_lock protects: + * inode_hashtable, inode->i_hash * - * This implementation has the basic premise of trying - * to be extremely low-overhead and SMP-safe, yet be - * simple enough to be "obviously correct". + * Lock ordering: * - * Famous last words. - */ - -/* inode dynamic allocation 1999, Andrea Arcangeli <andrea@suse.de> */ - -/* #define INODE_PARANOIA 1 */ -/* #define INODE_DEBUG 1 */ - -/* - * Inode lookup is no longer as critical as it used to be: - * most of the lookups are going to be through the dcache. + * inode_sb_list_lock + * inode->i_lock + * Inode LRU list locks + * + * bdi->wb.list_lock + * inode->i_lock + * + * inode_hash_lock + * inode_sb_list_lock + * inode->i_lock + * + * iunique_lock + * inode_hash_lock */ -#define I_HASHBITS i_hash_shift -#define I_HASHMASK i_hash_mask static unsigned int i_hash_mask __read_mostly; static unsigned int i_hash_shift __read_mostly; - -/* - * Each inode can be on two separate lists. One is - * the hash list of the inode, used for lookups. The - * other linked list is the "type" list: - * "in_use" - valid inode, i_count > 0, i_nlink > 0 - * "dirty" - as "in_use" but also dirty - * "unused" - valid inode, i_count = 0 - * - * A "dirty" list is maintained for each super block, - * allowing for low-overhead inode sync() operations. - */ - -static LIST_HEAD(inode_lru); static struct hlist_head *inode_hashtable __read_mostly; +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock); -/* - * A simple spinlock to protect the list manipulations. - * - * NOTE! You also have to own the lock if you change - * the i_state of an inode while it is in use.. - */ -DEFINE_SPINLOCK(inode_lock); +__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock); /* - * iprune_sem provides exclusion between the kswapd or try_to_free_pages - * icache shrinking path, and the umount path. Without this exclusion, - * by the time prune_icache calls iput for the inode whose pages it has - * been invalidating, or by the time it calls clear_inode & destroy_inode - * from its final dispose_list, the struct super_block they refer to - * (for inode->i_sb->s_op) may already have been freed and reused. - * - * We make this an rwsem because the fastpath is icache shrinking. In - * some cases a filesystem may be doing a significant amount of work in - * its inode reclaim code, so this should improve parallelism. + * Empty aops. Can be used for the cases where the user does not + * define any of the address_space operations. */ -static DECLARE_RWSEM(iprune_sem); +const struct address_space_operations empty_aops = { +}; +EXPORT_SYMBOL(empty_aops); /* * Statistics gathering.. */ struct inodes_stat_t inodes_stat; -static struct percpu_counter nr_inodes __cacheline_aligned_in_smp; -static struct percpu_counter nr_inodes_unused __cacheline_aligned_in_smp; +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 inline int get_nr_inodes(void) +static long get_nr_inodes(void) { - return percpu_counter_sum_positive(&nr_inodes); + int i; + long sum = 0; + for_each_possible_cpu(i) + sum += per_cpu(nr_inodes, i); + return sum < 0 ? 0 : sum; } -static inline int get_nr_inodes_unused(void) +static inline long get_nr_inodes_unused(void) { - return percpu_counter_sum_positive(&nr_inodes_unused); + int i; + long sum = 0; + for_each_possible_cpu(i) + sum += per_cpu(nr_unused, i); + return sum < 0 ? 0 : sum; } -int get_nr_dirty_inodes(void) +long get_nr_dirty_inodes(void) { - int nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); + /* not actually dirty inodes, but a wild approximation */ + long nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); return nr_dirty > 0 ? nr_dirty : 0; - } /* * Handle nr_inode sysctl */ #ifdef CONFIG_SYSCTL -int proc_nr_inodes(ctl_table *table, int write, +int proc_nr_inodes(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { inodes_stat.nr_inodes = get_nr_inodes(); inodes_stat.nr_unused = get_nr_inodes_unused(); - return proc_dointvec(table, write, buffer, lenp, ppos); + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif -static void wake_up_inode(struct inode *inode) -{ - /* - * Prevent speculative execution through spin_unlock(&inode_lock); - */ - smp_mb(); - wake_up_bit(&inode->i_state, __I_NEW); -} - /** * inode_init_always - perform inode structure intialisation * @sb: superblock inode belongs to @@ -156,7 +124,6 @@ static void wake_up_inode(struct inode *inode) */ int inode_init_always(struct super_block *sb, struct inode *inode) { - static const struct address_space_operations empty_aops; static const struct inode_operations empty_iops; static const struct file_operations empty_fops; struct address_space *const mapping = &inode->i_data; @@ -167,9 +134,10 @@ int inode_init_always(struct super_block *sb, struct inode *inode) atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; inode->i_fop = &empty_fops; - inode->i_nlink = 1; - inode->i_uid = 0; - inode->i_gid = 0; + inode->__i_nlink = 1; + inode->i_opflags = 0; + i_uid_write(inode, 0); + i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); inode->i_size = 0; inode->i_blocks = 0; @@ -192,14 +160,13 @@ int inode_init_always(struct super_block *sb, struct inode *inode) mutex_init(&inode->i_mutex); lockdep_set_class(&inode->i_mutex, &sb->s_type->i_mutex_key); - init_rwsem(&inode->i_alloc_sem); - lockdep_set_class(&inode->i_alloc_sem, &sb->s_type->i_alloc_sem_key); + atomic_set(&inode->i_dio_count, 0); mapping->a_ops = &empty_aops; mapping->host = inode; mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); - mapping->assoc_mapping = NULL; + mapping->private_data = NULL; mapping->backing_dev_info = &default_backing_dev_info; mapping->writeback_index = 0; @@ -216,6 +183,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) } inode->i_private = NULL; inode->i_mapping = mapping; + INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ #ifdef CONFIG_FS_POSIX_ACL inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED; #endif @@ -224,7 +192,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_fsnotify_mask = 0; #endif - percpu_counter_inc(&nr_inodes); + this_cpu_inc(nr_inodes); return 0; out: @@ -255,21 +223,38 @@ static struct inode *alloc_inode(struct super_block *sb) return inode; } +void free_inode_nonrcu(struct inode *inode) +{ + kmem_cache_free(inode_cachep, inode); +} +EXPORT_SYMBOL(free_inode_nonrcu); + void __destroy_inode(struct inode *inode) { BUG_ON(inode_has_buffers(inode)); security_inode_free(inode); fsnotify_inode_delete(inode); + if (!inode->i_nlink) { + WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); + atomic_long_dec(&inode->i_sb->s_remove_count); + } + #ifdef CONFIG_FS_POSIX_ACL if (inode->i_acl && inode->i_acl != ACL_NOT_CACHED) posix_acl_release(inode->i_acl); if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED) posix_acl_release(inode->i_default_acl); #endif - percpu_counter_dec(&nr_inodes); + this_cpu_dec(nr_inodes); } EXPORT_SYMBOL(__destroy_inode); +static void i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + kmem_cache_free(inode_cachep, inode); +} + static void destroy_inode(struct inode *inode) { BUG_ON(!list_empty(&inode->i_lru)); @@ -277,8 +262,99 @@ static void destroy_inode(struct inode *inode) if (inode->i_sb->s_op->destroy_inode) inode->i_sb->s_op->destroy_inode(inode); else - kmem_cache_free(inode_cachep, (inode)); + call_rcu(&inode->i_rcu, i_callback); +} + +/** + * drop_nlink - directly drop an inode's link count + * @inode: inode + * + * This is a low-level filesystem helper to replace any + * direct filesystem manipulation of i_nlink. In cases + * where we are attempting to track writes to the + * filesystem, a decrement to zero means an imminent + * write when the file is truncated and actually unlinked + * on the filesystem. + */ +void drop_nlink(struct inode *inode) +{ + WARN_ON(inode->i_nlink == 0); + inode->__i_nlink--; + if (!inode->i_nlink) + atomic_long_inc(&inode->i_sb->s_remove_count); +} +EXPORT_SYMBOL(drop_nlink); + +/** + * clear_nlink - directly zero an inode's link count + * @inode: inode + * + * This is a low-level filesystem helper to replace any + * direct filesystem manipulation of i_nlink. See + * drop_nlink() for why we care about i_nlink hitting zero. + */ +void clear_nlink(struct inode *inode) +{ + if (inode->i_nlink) { + inode->__i_nlink = 0; + atomic_long_inc(&inode->i_sb->s_remove_count); + } +} +EXPORT_SYMBOL(clear_nlink); + +/** + * set_nlink - directly set an inode's link count + * @inode: inode + * @nlink: new nlink (should be non-zero) + * + * This is a low-level filesystem helper to replace any + * direct filesystem manipulation of i_nlink. + */ +void set_nlink(struct inode *inode, unsigned int nlink) +{ + if (!nlink) { + clear_nlink(inode); + } else { + /* Yes, some filesystems do change nlink from zero to one */ + if (inode->i_nlink == 0) + atomic_long_dec(&inode->i_sb->s_remove_count); + + inode->__i_nlink = nlink; + } } +EXPORT_SYMBOL(set_nlink); + +/** + * inc_nlink - directly increment an inode's link count + * @inode: inode + * + * This is a low-level filesystem helper to replace any + * direct filesystem manipulation of i_nlink. Currently, + * it is only here for parity with dec_nlink(). + */ +void inc_nlink(struct inode *inode) +{ + if (unlikely(inode->i_nlink == 0)) { + WARN_ON(!(inode->i_state & I_LINKABLE)); + atomic_long_dec(&inode->i_sb->s_remove_count); + } + + inode->__i_nlink++; +} +EXPORT_SYMBOL(inc_nlink); + +void address_space_init_once(struct address_space *mapping) +{ + memset(mapping, 0, sizeof(*mapping)); + INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC); + spin_lock_init(&mapping->tree_lock); + mutex_init(&mapping->i_mmap_mutex); + INIT_LIST_HEAD(&mapping->private_list); + spin_lock_init(&mapping->private_lock); + mapping->i_mmap = RB_ROOT; + INIT_LIST_HEAD(&mapping->i_mmap_nonlinear); +} +EXPORT_SYMBOL(address_space_init_once); /* * These are initializations that only need to be done @@ -289,17 +365,10 @@ void inode_init_once(struct inode *inode) { memset(inode, 0, sizeof(*inode)); INIT_HLIST_NODE(&inode->i_hash); - INIT_LIST_HEAD(&inode->i_dentry); INIT_LIST_HEAD(&inode->i_devices); INIT_LIST_HEAD(&inode->i_wb_list); INIT_LIST_HEAD(&inode->i_lru); - INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC); - spin_lock_init(&inode->i_data.tree_lock); - spin_lock_init(&inode->i_data.i_mmap_lock); - INIT_LIST_HEAD(&inode->i_data.private_list); - spin_lock_init(&inode->i_data.private_lock); - INIT_RAW_PRIO_TREE_ROOT(&inode->i_data.i_mmap); - INIT_LIST_HEAD(&inode->i_data.i_mmap_nonlinear); + address_space_init_once(&inode->i_data); i_size_ordered_init(inode); #ifdef CONFIG_FSNOTIFY INIT_HLIST_HEAD(&inode->i_fsnotify_marks); @@ -315,7 +384,7 @@ static void init_once(void *foo) } /* - * inode_lock must be held + * inode->i_lock must be held */ void __iget(struct inode *inode) { @@ -333,23 +402,28 @@ EXPORT_SYMBOL(ihold); static void inode_lru_list_add(struct inode *inode) { - if (list_empty(&inode->i_lru)) { - list_add(&inode->i_lru, &inode_lru); - percpu_counter_inc(&nr_inodes_unused); - } + if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru)) + this_cpu_inc(nr_unused); } -static void inode_lru_list_del(struct inode *inode) +/* + * Add inode to LRU if needed (inode is unused and clean). + * + * Needs inode->i_lock held. + */ +void inode_add_lru(struct inode *inode) { - if (!list_empty(&inode->i_lru)) { - list_del_init(&inode->i_lru); - percpu_counter_dec(&nr_inodes_unused); - } + if (!(inode->i_state & (I_DIRTY | I_SYNC | I_FREEING | I_WILL_FREE)) && + !atomic_read(&inode->i_count) && inode->i_sb->s_flags & MS_ACTIVE) + inode_lru_list_add(inode); } -static inline void __inode_sb_list_add(struct inode *inode) + +static void inode_lru_list_del(struct inode *inode) { - list_add(&inode->i_sb_list, &inode->i_sb->s_inodes); + + if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru)) + this_cpu_dec(nr_unused); } /** @@ -358,15 +432,19 @@ static inline void __inode_sb_list_add(struct inode *inode) */ void inode_sb_list_add(struct inode *inode) { - spin_lock(&inode_lock); - __inode_sb_list_add(inode); - spin_unlock(&inode_lock); + spin_lock(&inode_sb_list_lock); + list_add(&inode->i_sb_list, &inode->i_sb->s_inodes); + spin_unlock(&inode_sb_list_lock); } EXPORT_SYMBOL_GPL(inode_sb_list_add); -static inline void __inode_sb_list_del(struct inode *inode) +static inline void inode_sb_list_del(struct inode *inode) { - list_del_init(&inode->i_sb_list); + if (!list_empty(&inode->i_sb_list)) { + spin_lock(&inode_sb_list_lock); + list_del_init(&inode->i_sb_list); + spin_unlock(&inode_sb_list_lock); + } } static unsigned long hash(struct super_block *sb, unsigned long hashval) @@ -375,8 +453,8 @@ static unsigned long hash(struct super_block *sb, unsigned long hashval) tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) / L1_CACHE_BYTES; - tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> I_HASHBITS); - return tmp & I_HASHMASK; + tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift); + return tmp & i_hash_mask; } /** @@ -391,9 +469,11 @@ void __insert_inode_hash(struct inode *inode, unsigned long hashval) { struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval); - spin_lock(&inode_lock); + spin_lock(&inode_hash_lock); + spin_lock(&inode->i_lock); hlist_add_head(&inode->i_hash, b); - spin_unlock(&inode_lock); + spin_unlock(&inode->i_lock); + spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__insert_inode_hash); @@ -403,52 +483,88 @@ EXPORT_SYMBOL(__insert_inode_hash); * * Remove an inode from the superblock. */ -static void __remove_inode_hash(struct inode *inode) +void __remove_inode_hash(struct inode *inode) { + spin_lock(&inode_hash_lock); + spin_lock(&inode->i_lock); hlist_del_init(&inode->i_hash); + spin_unlock(&inode->i_lock); + spin_unlock(&inode_hash_lock); } +EXPORT_SYMBOL(__remove_inode_hash); -/** - * remove_inode_hash - remove an inode from the hash - * @inode: inode to unhash - * - * Remove an inode from the superblock. - */ -void remove_inode_hash(struct inode *inode) -{ - spin_lock(&inode_lock); - hlist_del_init(&inode->i_hash); - spin_unlock(&inode_lock); -} -EXPORT_SYMBOL(remove_inode_hash); - -void end_writeback(struct inode *inode) +void clear_inode(struct inode *inode) { might_sleep(); + /* + * We have to cycle tree_lock here because reclaim can be still in the + * process of removing the last page (in __delete_from_page_cache()) + * and we must not free mapping under it. + */ + spin_lock_irq(&inode->i_data.tree_lock); BUG_ON(inode->i_data.nrpages); + BUG_ON(inode->i_data.nrshadows); + spin_unlock_irq(&inode->i_data.tree_lock); BUG_ON(!list_empty(&inode->i_data.private_list)); BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(inode->i_state & I_CLEAR); - inode_sync_wait(inode); + /* don't need i_lock here, no concurrent mods to i_state */ inode->i_state = I_FREEING | I_CLEAR; } -EXPORT_SYMBOL(end_writeback); +EXPORT_SYMBOL(clear_inode); +/* + * Free the inode passed in, removing it from the lists it is still connected + * to. We remove any pages still attached to the inode and wait for any IO that + * is still in progress before finally destroying the inode. + * + * An inode must already be marked I_FREEING so that we avoid the inode being + * moved back onto lists if we race with other code that manipulates the lists + * (e.g. writeback_single_inode). The caller is responsible for setting this. + * + * An inode must already be removed from the LRU list before being evicted from + * the cache. This should occur atomically with setting the I_FREEING state + * flag, so no inodes here should ever be on the LRU when being evicted. + */ 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(!list_empty(&inode->i_lru)); + + if (!list_empty(&inode->i_wb_list)) + inode_wb_list_del(inode); + + inode_sb_list_del(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 + * the inode has I_FREEING set, flusher thread won't start new work on + * the inode. We just have to wait for running writeback to finish. + */ + inode_wait_for_writeback(inode); + if (op->evict_inode) { op->evict_inode(inode); } else { - if (inode->i_data.nrpages) - truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + truncate_inode_pages_final(&inode->i_data); + clear_inode(inode); } if (S_ISBLK(inode->i_mode) && inode->i_bdev) bd_forget(inode); if (S_ISCHR(inode->i_mode) && inode->i_cdev) cd_forget(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); + + destroy_inode(inode); } /* @@ -467,14 +583,6 @@ static void dispose_list(struct list_head *head) list_del_init(&inode->i_lru); evict(inode); - - spin_lock(&inode_lock); - __remove_inode_hash(inode); - __inode_sb_list_del(inode); - spin_unlock(&inode_lock); - - wake_up_inode(inode); - destroy_inode(inode); } } @@ -492,94 +600,75 @@ void evict_inodes(struct super_block *sb) struct inode *inode, *next; LIST_HEAD(dispose); - down_write(&iprune_sem); - - spin_lock(&inode_lock); + spin_lock(&inode_sb_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { if (atomic_read(&inode->i_count)) continue; + spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { - WARN_ON(1); + spin_unlock(&inode->i_lock); continue; } inode->i_state |= I_FREEING; - - /* - * Move the inode off the IO lists and LRU once I_FREEING is - * set so that it won't get moved back on there if it is dirty. - */ - list_move(&inode->i_lru, &dispose); - list_del_init(&inode->i_wb_list); - if (!(inode->i_state & (I_DIRTY | I_SYNC))) - percpu_counter_dec(&nr_inodes_unused); + inode_lru_list_del(inode); + spin_unlock(&inode->i_lock); + list_add(&inode->i_lru, &dispose); } - spin_unlock(&inode_lock); + spin_unlock(&inode_sb_list_lock); dispose_list(&dispose); - up_write(&iprune_sem); } /** * invalidate_inodes - attempt to free all inodes on a superblock * @sb: superblock to operate on + * @kill_dirty: flag to guide handling of dirty inodes * * Attempts to free all inodes for a given superblock. If there were any * busy inodes return a non-zero value, else zero. + * If @kill_dirty is set, discard dirty inodes too, otherwise treat + * them as busy. */ -int invalidate_inodes(struct super_block *sb) +int invalidate_inodes(struct super_block *sb, bool kill_dirty) { int busy = 0; struct inode *inode, *next; LIST_HEAD(dispose); - down_write(&iprune_sem); - - spin_lock(&inode_lock); + spin_lock(&inode_sb_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { - if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) + spin_lock(&inode->i_lock); + if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { + spin_unlock(&inode->i_lock); + continue; + } + if (inode->i_state & I_DIRTY && !kill_dirty) { + spin_unlock(&inode->i_lock); + busy = 1; continue; + } if (atomic_read(&inode->i_count)) { + spin_unlock(&inode->i_lock); busy = 1; continue; } inode->i_state |= I_FREEING; - - /* - * Move the inode off the IO lists and LRU once I_FREEING is - * set so that it won't get moved back on there if it is dirty. - */ - list_move(&inode->i_lru, &dispose); - list_del_init(&inode->i_wb_list); - if (!(inode->i_state & (I_DIRTY | I_SYNC))) - percpu_counter_dec(&nr_inodes_unused); + inode_lru_list_del(inode); + spin_unlock(&inode->i_lock); + list_add(&inode->i_lru, &dispose); } - spin_unlock(&inode_lock); + spin_unlock(&inode_sb_list_lock); dispose_list(&dispose); - up_write(&iprune_sem); return busy; } -static int can_unuse(struct inode *inode) -{ - if (inode->i_state & ~I_REFERENCED) - return 0; - if (inode_has_buffers(inode)) - return 0; - if (atomic_read(&inode->i_count)) - return 0; - if (inode->i_data.nrpages) - return 0; - return 1; -} - /* - * Scan `goal' inodes on the unused list for freeable ones. They are moved to a - * temporary list and then are freed outside inode_lock by dispose_list(). + * Isolate the inode from the LRU in preparation for freeing it. * * Any inodes which are pinned purely because of attached pagecache have their * pagecache removed. If the inode has metadata buffers attached to @@ -593,103 +682,83 @@ static int can_unuse(struct inode *inode) * LRU does not have strict ordering. Hence we don't want to reclaim inodes * with this flag set because they are the inodes that are out of order. */ -static void prune_icache(int nr_to_scan) +static enum lru_status +inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg) { - LIST_HEAD(freeable); - int nr_scanned; - unsigned long reap = 0; - - down_read(&iprune_sem); - spin_lock(&inode_lock); - for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) { - struct inode *inode; + struct list_head *freeable = arg; + struct inode *inode = container_of(item, struct inode, i_lru); - if (list_empty(&inode_lru)) - break; + /* + * we are inverting the lru lock/inode->i_lock here, so use a trylock. + * If we fail to get the lock, just skip it. + */ + if (!spin_trylock(&inode->i_lock)) + return LRU_SKIP; - inode = list_entry(inode_lru.prev, struct inode, i_lru); + /* + * Referenced or dirty inodes are still in use. Give them another pass + * through the LRU as we canot reclaim them now. + */ + if (atomic_read(&inode->i_count) || + (inode->i_state & ~I_REFERENCED)) { + list_del_init(&inode->i_lru); + spin_unlock(&inode->i_lock); + this_cpu_dec(nr_unused); + return LRU_REMOVED; + } - /* - * Referenced or dirty inodes are still in use. Give them - * another pass through the LRU as we canot reclaim them now. - */ - if (atomic_read(&inode->i_count) || - (inode->i_state & ~I_REFERENCED)) { - list_del_init(&inode->i_lru); - percpu_counter_dec(&nr_inodes_unused); - continue; - } + /* recently referenced inodes get one more pass */ + if (inode->i_state & I_REFERENCED) { + inode->i_state &= ~I_REFERENCED; + spin_unlock(&inode->i_lock); + return LRU_ROTATE; + } - /* recently referenced inodes get one more pass */ - if (inode->i_state & I_REFERENCED) { - list_move(&inode->i_lru, &inode_lru); - inode->i_state &= ~I_REFERENCED; - continue; - } - if (inode_has_buffers(inode) || inode->i_data.nrpages) { - __iget(inode); - spin_unlock(&inode_lock); - if (remove_inode_buffers(inode)) - reap += invalidate_mapping_pages(&inode->i_data, - 0, -1); - iput(inode); - spin_lock(&inode_lock); - - if (inode != list_entry(inode_lru.next, - struct inode, i_lru)) - continue; /* wrong inode or list_empty */ - if (!can_unuse(inode)) - continue; + if (inode_has_buffers(inode) || inode->i_data.nrpages) { + __iget(inode); + spin_unlock(&inode->i_lock); + spin_unlock(lru_lock); + if (remove_inode_buffers(inode)) { + unsigned long reap; + reap = invalidate_mapping_pages(&inode->i_data, 0, -1); + if (current_is_kswapd()) + __count_vm_events(KSWAPD_INODESTEAL, reap); + else + __count_vm_events(PGINODESTEAL, reap); + if (current->reclaim_state) + current->reclaim_state->reclaimed_slab += reap; } - WARN_ON(inode->i_state & I_NEW); - inode->i_state |= I_FREEING; - - /* - * Move the inode off the IO lists and LRU once I_FREEING is - * set so that it won't get moved back on there if it is dirty. - */ - list_move(&inode->i_lru, &freeable); - list_del_init(&inode->i_wb_list); - percpu_counter_dec(&nr_inodes_unused); + iput(inode); + spin_lock(lru_lock); + return LRU_RETRY; } - if (current_is_kswapd()) - __count_vm_events(KSWAPD_INODESTEAL, reap); - else - __count_vm_events(PGINODESTEAL, reap); - spin_unlock(&inode_lock); - dispose_list(&freeable); - up_read(&iprune_sem); + WARN_ON(inode->i_state & I_NEW); + inode->i_state |= I_FREEING; + list_move(&inode->i_lru, freeable); + spin_unlock(&inode->i_lock); + + this_cpu_dec(nr_unused); + return LRU_REMOVED; } /* - * shrink_icache_memory() will attempt to reclaim some unused inodes. Here, - * "unused" means that no dentries are referring to the inodes: the files are - * not open and the dcache references to those inodes have already been - * reclaimed. - * - * This function is passed the number of inodes to scan, and it returns the - * total number of remaining possibly-reclaimable inodes. + * Walk the superblock inode LRU for freeable inodes and attempt to free them. + * This is called from the superblock shrinker function with a number of inodes + * to trim from the LRU. Inodes to be freed are moved to a temporary list and + * then are freed outside inode_lock by dispose_list(). */ -static int shrink_icache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) +long prune_icache_sb(struct super_block *sb, unsigned long nr_to_scan, + int nid) { - if (nr) { - /* - * Nasty deadlock avoidance. We may hold various FS locks, - * and we don't want to recurse into the FS that called us - * in clear_inode() and friends.. - */ - if (!(gfp_mask & __GFP_FS)) - return -1; - prune_icache(nr); - } - return (get_nr_inodes_unused() / 100) * sysctl_vfs_cache_pressure; -} + LIST_HEAD(freeable); + long freed; -static struct shrinker icache_shrinker = { - .shrink = shrink_icache_memory, - .seeks = DEFAULT_SEEKS, -}; + freed = list_lru_walk_node(&sb->s_inode_lru, nid, inode_lru_isolate, + &freeable, &nr_to_scan); + dispose_list(&freeable); + return freed; +} static void __wait_on_freeing_inode(struct inode *inode); /* @@ -700,20 +769,21 @@ static struct inode *find_inode(struct super_block *sb, int (*test)(struct inode *, void *), void *data) { - struct hlist_node *node; struct inode *inode = NULL; repeat: - hlist_for_each_entry(inode, node, head, i_hash) { + hlist_for_each_entry(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); goto repeat; } __iget(inode); + spin_unlock(&inode->i_lock); return inode; } return NULL; @@ -726,20 +796,21 @@ repeat: static struct inode *find_inode_fast(struct super_block *sb, struct hlist_head *head, unsigned long ino) { - struct hlist_node *node; struct inode *inode = NULL; repeat: - hlist_for_each_entry(inode, node, head, i_hash) { + hlist_for_each_entry(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); goto repeat; } __iget(inode); + spin_unlock(&inode->i_lock); return inode; } return NULL; @@ -784,6 +855,29 @@ 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); + INIT_LIST_HEAD(&inode->i_sb_list); + } + return inode; +} + +/** * new_inode - obtain an inode * @sb: superblock * @@ -799,28 +893,23 @@ struct inode *new_inode(struct super_block *sb) { struct inode *inode; - spin_lock_prefetch(&inode_lock); + spin_lock_prefetch(&inode_sb_list_lock); - inode = alloc_inode(sb); - if (inode) { - spin_lock(&inode_lock); - __inode_sb_list_add(inode); - inode->i_state = 0; - spin_unlock(&inode_lock); - } + inode = new_inode_pseudo(sb); + if (inode) + inode_sb_list_add(inode); return inode; } EXPORT_SYMBOL(new_inode); -void unlock_new_inode(struct inode *inode) -{ #ifdef CONFIG_DEBUG_LOCK_ALLOC +void lockdep_annotate_inode_mutex_key(struct inode *inode) +{ if (S_ISDIR(inode->i_mode)) { struct file_system_type *type = inode->i_sb->s_type; /* Set new key only if filesystem hasn't already changed it */ - if (!lockdep_match_class(&inode->i_mutex, - &type->i_mutex_key)) { + if (lockdep_match_class(&inode->i_mutex, &type->i_mutex_key)) { /* * ensure nobody is actually holding i_mutex */ @@ -830,52 +919,117 @@ void unlock_new_inode(struct inode *inode) &type->i_mutex_dir_key); } } +} +EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key); #endif - /* - * This is special! We do not need the spinlock when clearing I_NEW, - * because we're guaranteed that nobody else tries to do anything about - * the state of the inode when it is locked, as we just created it (so - * there can be no old holders that haven't tested I_NEW). - * However we must emit the memory barrier so that other CPUs reliably - * see the clearing of I_NEW after the other inode initialisation has - * completed. - */ - smp_mb(); + +/** + * unlock_new_inode - clear the I_NEW state and wake up any waiters + * @inode: new inode to unlock + * + * Called when the inode is fully initialised to clear the new state of the + * inode and wake up anyone waiting for the inode to finish initialisation. + */ +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; - wake_up_inode(inode); + smp_mb(); + wake_up_bit(&inode->i_state, __I_NEW); + spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(unlock_new_inode); -/* - * This is called without the inode lock held.. Be careful. +/** + * lock_two_nondirectories - take two i_mutexes on non-directory objects * - * We no longer cache the sb_flags in i_flags - see fs.h - * -- rmk@arm.uk.linux.org + * Lock any non-NULL argument that is not a directory. + * Zero, one or two objects may be locked by this function. + * + * @inode1: first inode to lock + * @inode2: second inode to lock */ -static struct inode *get_new_inode(struct super_block *sb, - struct hlist_head *head, - int (*test)(struct inode *, void *), - int (*set)(struct inode *, void *), - void *data) +void lock_two_nondirectories(struct inode *inode1, struct inode *inode2) +{ + if (inode1 > inode2) + swap(inode1, inode2); + + if (inode1 && !S_ISDIR(inode1->i_mode)) + mutex_lock(&inode1->i_mutex); + if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1) + mutex_lock_nested(&inode2->i_mutex, I_MUTEX_NONDIR2); +} +EXPORT_SYMBOL(lock_two_nondirectories); + +/** + * unlock_two_nondirectories - release locks from lock_two_nondirectories() + * @inode1: first inode to unlock + * @inode2: second inode to unlock + */ +void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2) +{ + if (inode1 && !S_ISDIR(inode1->i_mode)) + mutex_unlock(&inode1->i_mutex); + if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1) + mutex_unlock(&inode2->i_mutex); +} +EXPORT_SYMBOL(unlock_two_nondirectories); + +/** + * iget5_locked - 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 + * + * 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 + * 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(). + * + * Note both @test and @set are called with the inode_hash_lock held, so can't + * sleep. + */ +struct inode *iget5_locked(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; + spin_lock(&inode_hash_lock); + inode = find_inode(sb, head, test, data); + spin_unlock(&inode_hash_lock); + + if (inode) { + wait_on_inode(inode); + return inode; + } + inode = alloc_inode(sb); if (inode) { struct inode *old; - spin_lock(&inode_lock); + spin_lock(&inode_hash_lock); /* We released the lock, so.. */ old = find_inode(sb, head, test, data); if (!old) { if (set(inode, data)) goto set_failed; - hlist_add_head(&inode->i_hash, head); - __inode_sb_list_add(inode); + spin_lock(&inode->i_lock); inode->i_state = I_NEW; - spin_unlock(&inode_lock); + hlist_add_head(&inode->i_hash, head); + spin_unlock(&inode->i_lock); + inode_sb_list_add(inode); + spin_unlock(&inode_hash_lock); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents @@ -888,7 +1042,7 @@ static struct inode *get_new_inode(struct super_block *sb, * us. Use the old inode instead of the one we just * allocated. */ - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); destroy_inode(inode); inode = old; wait_on_inode(inode); @@ -896,33 +1050,53 @@ static struct inode *get_new_inode(struct super_block *sb, return inode; set_failed: - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); destroy_inode(inode); return NULL; } +EXPORT_SYMBOL(iget5_locked); -/* - * get_new_inode_fast is the fast path version of get_new_inode, see the - * comment at iget_locked for details. +/** + * iget_locked - obtain an inode from a mounted file system + * @sb: super block of file system + * @ino: inode number to get + * + * Search for the inode specified by @ino in the inode cache and if present + * return it with an increased reference count. This is for file systems + * where the inode number is 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(). */ -static struct inode *get_new_inode_fast(struct super_block *sb, - struct hlist_head *head, unsigned long ino) +struct inode *iget_locked(struct super_block *sb, unsigned long ino) { + struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; + spin_lock(&inode_hash_lock); + inode = find_inode_fast(sb, head, ino); + spin_unlock(&inode_hash_lock); + if (inode) { + wait_on_inode(inode); + return inode; + } + inode = alloc_inode(sb); if (inode) { struct inode *old; - spin_lock(&inode_lock); + spin_lock(&inode_hash_lock); /* We released the lock, so.. */ old = find_inode_fast(sb, head, ino); if (!old) { inode->i_ino = ino; - hlist_add_head(&inode->i_hash, head); - __inode_sb_list_add(inode); + spin_lock(&inode->i_lock); inode->i_state = I_NEW; - spin_unlock(&inode_lock); + hlist_add_head(&inode->i_hash, head); + spin_unlock(&inode->i_lock); + inode_sb_list_add(inode); + spin_unlock(&inode_hash_lock); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents @@ -935,13 +1109,14 @@ static struct inode *get_new_inode_fast(struct super_block *sb, * us. Use the old inode instead of the one we just * allocated. */ - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); destroy_inode(inode); inode = old; wait_on_inode(inode); } return inode; } +EXPORT_SYMBOL(iget_locked); /* * search the inode cache for a matching inode number. @@ -953,13 +1128,16 @@ static struct inode *get_new_inode_fast(struct super_block *sb, static int test_inode_iunique(struct super_block *sb, unsigned long ino) { struct hlist_head *b = inode_hashtable + hash(sb, ino); - struct hlist_node *node; struct inode *inode; - hlist_for_each_entry(inode, node, b, i_hash) { - if (inode->i_ino == ino && inode->i_sb == sb) + spin_lock(&inode_hash_lock); + hlist_for_each_entry(inode, b, i_hash) { + if (inode->i_ino == ino && inode->i_sb == sb) { + spin_unlock(&inode_hash_lock); return 0; + } } + spin_unlock(&inode_hash_lock); return 1; } @@ -989,7 +1167,6 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved) static unsigned int counter; ino_t res; - spin_lock(&inode_lock); spin_lock(&iunique_lock); do { if (counter <= max_reserved) @@ -997,7 +1174,6 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved) res = counter++; } while (!test_inode_iunique(sb, res)); spin_unlock(&iunique_lock); - spin_unlock(&inode_lock); return res; } @@ -1005,116 +1181,50 @@ EXPORT_SYMBOL(iunique); struct inode *igrab(struct inode *inode) { - spin_lock(&inode_lock); - if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) + spin_lock(&inode->i_lock); + if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) { __iget(inode); - else + spin_unlock(&inode->i_lock); + } else { + spin_unlock(&inode->i_lock); /* * Handle the case where s_op->clear_inode is not been * called yet, and somebody is calling igrab * while the inode is getting freed. */ inode = NULL; - spin_unlock(&inode_lock); + } return inode; } EXPORT_SYMBOL(igrab); /** - * ifind - internal function, you want ilookup5() or iget5(). - * @sb: super block of file system to search - * @head: the head of the list to search - * @test: callback used for comparisons between inodes - * @data: opaque data pointer to pass to @test - * @wait: if true wait for the inode to be unlocked, if false do not - * - * ifind() searches for the inode specified by @data in the inode - * cache. This is a generalized version of ifind_fast() for file systems where - * the inode number is not sufficient for unique identification of an inode. - * - * If the inode is in the cache, the inode is returned with an incremented - * reference count. - * - * Otherwise NULL is returned. - * - * Note, @test is called with the inode_lock held, so can't sleep. - */ -static struct inode *ifind(struct super_block *sb, - struct hlist_head *head, int (*test)(struct inode *, void *), - void *data, const int wait) -{ - struct inode *inode; - - spin_lock(&inode_lock); - inode = find_inode(sb, head, test, data); - if (inode) { - spin_unlock(&inode_lock); - if (likely(wait)) - wait_on_inode(inode); - return inode; - } - spin_unlock(&inode_lock); - return NULL; -} - -/** - * ifind_fast - internal function, you want ilookup() or iget(). - * @sb: super block of file system to search - * @head: head of the list to search - * @ino: inode number to search for - * - * ifind_fast() searches for the inode @ino in the inode cache. This is for - * file systems where the inode number is sufficient for unique identification - * of an inode. - * - * If the inode is in the cache, the inode is returned with an incremented - * reference count. - * - * Otherwise NULL is returned. - */ -static struct inode *ifind_fast(struct super_block *sb, - struct hlist_head *head, unsigned long ino) -{ - struct inode *inode; - - spin_lock(&inode_lock); - inode = find_inode_fast(sb, head, ino); - if (inode) { - spin_unlock(&inode_lock); - wait_on_inode(inode); - return inode; - } - spin_unlock(&inode_lock); - return NULL; -} - -/** * ilookup5_nowait - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * - * ilookup5() uses ifind() to search for the inode specified by @hashval and - * @data in the inode cache. This is a generalized version of ilookup() for - * file systems where the inode number is not sufficient for unique - * identification of an inode. - * + * Search for the inode specified by @hashval and @data in the inode cache. * If the inode is in the cache, the inode is returned with an incremented - * reference count. Note, the inode lock is not waited upon so you have to be - * very careful what you do with the returned inode. You probably should be - * using ilookup5() instead. + * reference count. * - * Otherwise NULL is returned. + * Note: I_NEW is not waited upon so you have to be very careful what you do + * with the returned inode. You probably should be using ilookup5() instead. * - * Note, @test is called with the inode_lock held, so can't sleep. + * 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) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); + struct inode *inode; + + spin_lock(&inode_hash_lock); + inode = find_inode(sb, head, test, data); + spin_unlock(&inode_hash_lock); - return ifind(sb, head, test, data, 0); + return inode; } EXPORT_SYMBOL(ilookup5_nowait); @@ -1125,24 +1235,24 @@ EXPORT_SYMBOL(ilookup5_nowait); * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * - * ilookup5() uses ifind() to search for the inode specified by @hashval and - * @data in the inode cache. This is a generalized version of ilookup() for - * file systems where the inode number is not sufficient for unique - * identification of an inode. - * - * If the inode is in the cache, the inode lock is waited upon and the inode is + * Search for the inode specified by @hashval and @data in the inode cache, + * and if the inode is in the cache, return the inode with an incremented + * reference count. Waits on I_NEW before returning the inode. * returned with an incremented reference count. * - * Otherwise NULL is returned. + * This is a generalized version of ilookup() for file systems where the + * inode number is not sufficient for unique identification of an inode. * - * Note, @test is called with the inode_lock held, so can't sleep. + * Note: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { - struct hlist_head *head = inode_hashtable + hash(sb, hashval); + struct inode *inode = ilookup5_nowait(sb, hashval, test, data); - return ifind(sb, head, test, data, 1); + if (inode) + wait_on_inode(inode); + return inode; } EXPORT_SYMBOL(ilookup5); @@ -1151,91 +1261,23 @@ EXPORT_SYMBOL(ilookup5); * @sb: super block of file system to search * @ino: inode number to search for * - * ilookup() uses ifind_fast() to search for the inode @ino in the inode cache. - * This is for file systems where the inode number is sufficient for unique - * identification of an inode. - * - * If the inode is in the cache, the inode is returned with an incremented - * reference count. - * - * Otherwise NULL is returned. + * Search for the inode @ino in the inode cache, and if the inode is in the + * cache, the inode is returned with an incremented reference count. */ struct inode *ilookup(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); - - return ifind_fast(sb, head, ino); -} -EXPORT_SYMBOL(ilookup); - -/** - * iget5_locked - 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 - * - * iget5_locked() uses ifind() to search for the inode specified by @hashval - * and @data in the inode cache and if present it is returned 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, get_new_inode() is called to allocate a new - * inode and this is returned 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_lock held, so can't sleep. - */ -struct inode *iget5_locked(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; - inode = ifind(sb, head, test, data, 1); - if (inode) - return inode; - /* - * get_new_inode() will do the right thing, re-trying the search - * in case it had to block at any point. - */ - return get_new_inode(sb, head, test, set, data); -} -EXPORT_SYMBOL(iget5_locked); - -/** - * iget_locked - obtain an inode from a mounted file system - * @sb: super block of file system - * @ino: inode number to get - * - * iget_locked() uses ifind_fast() to search for the inode specified by @ino in - * the inode cache and if present it is returned with an increased reference - * count. This is for file systems where the inode number is sufficient for - * unique identification of an inode. - * - * If the inode is not in cache, get_new_inode_fast() is called to allocate a - * new inode and this is returned locked, hashed, and with the I_NEW flag set. - * The file system gets to fill it in before unlocking it via - * unlock_new_inode(). - */ -struct inode *iget_locked(struct super_block *sb, unsigned long ino) -{ - struct hlist_head *head = inode_hashtable + hash(sb, ino); - struct inode *inode; + spin_lock(&inode_hash_lock); + inode = find_inode_fast(sb, head, ino); + spin_unlock(&inode_hash_lock); - inode = ifind_fast(sb, head, ino); if (inode) - return inode; - /* - * get_new_inode_fast() will do the right thing, re-trying the search - * in case it had to block at any point. - */ - return get_new_inode_fast(sb, head, ino); + wait_on_inode(inode); + return inode; } -EXPORT_SYMBOL(iget_locked); +EXPORT_SYMBOL(ilookup); int insert_inode_locked(struct inode *inode) { @@ -1243,27 +1285,32 @@ int insert_inode_locked(struct inode *inode) ino_t ino = inode->i_ino; struct hlist_head *head = inode_hashtable + hash(sb, ino); - inode->i_state |= I_NEW; while (1) { - struct hlist_node *node; struct inode *old = NULL; - spin_lock(&inode_lock); - hlist_for_each_entry(old, node, head, i_hash) { + spin_lock(&inode_hash_lock); + hlist_for_each_entry(old, head, i_hash) { if (old->i_ino != ino) continue; if (old->i_sb != sb) continue; - if (old->i_state & (I_FREEING|I_WILL_FREE)) + spin_lock(&old->i_lock); + if (old->i_state & (I_FREEING|I_WILL_FREE)) { + spin_unlock(&old->i_lock); continue; + } break; } - if (likely(!node)) { + if (likely(!old)) { + spin_lock(&inode->i_lock); + inode->i_state |= I_NEW; hlist_add_head(&inode->i_hash, head); - spin_unlock(&inode_lock); + spin_unlock(&inode->i_lock); + spin_unlock(&inode_hash_lock); return 0; } __iget(old); - spin_unlock(&inode_lock); + spin_unlock(&old->i_lock); + spin_unlock(&inode_hash_lock); wait_on_inode(old); if (unlikely(!inode_unhashed(old))) { iput(old); @@ -1280,29 +1327,33 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, struct super_block *sb = inode->i_sb; struct hlist_head *head = inode_hashtable + hash(sb, hashval); - inode->i_state |= I_NEW; - while (1) { - struct hlist_node *node; struct inode *old = NULL; - spin_lock(&inode_lock); - hlist_for_each_entry(old, node, head, i_hash) { + spin_lock(&inode_hash_lock); + hlist_for_each_entry(old, head, i_hash) { if (old->i_sb != sb) continue; if (!test(old, data)) continue; - if (old->i_state & (I_FREEING|I_WILL_FREE)) + spin_lock(&old->i_lock); + if (old->i_state & (I_FREEING|I_WILL_FREE)) { + spin_unlock(&old->i_lock); continue; + } break; } - if (likely(!node)) { + if (likely(!old)) { + spin_lock(&inode->i_lock); + inode->i_state |= I_NEW; hlist_add_head(&inode->i_hash, head); - spin_unlock(&inode_lock); + spin_unlock(&inode->i_lock); + spin_unlock(&inode_hash_lock); return 0; } __iget(old); - spin_unlock(&inode_lock); + spin_unlock(&old->i_lock); + spin_unlock(&inode_hash_lock); wait_on_inode(old); if (unlikely(!inode_unhashed(old))) { iput(old); @@ -1321,17 +1372,6 @@ int generic_delete_inode(struct inode *inode) EXPORT_SYMBOL(generic_delete_inode); /* - * Normal UNIX filesystem behaviour: delete the - * inode when the usage count drops to zero, and - * i_nlink is zero. - */ -int generic_drop_inode(struct inode *inode) -{ - return !inode->i_nlink || inode_unhashed(inode); -} -EXPORT_SYMBOL_GPL(generic_drop_inode); - -/* * Called when we're dropping the last reference * to an inode. * @@ -1347,47 +1387,35 @@ static void iput_final(struct inode *inode) const struct super_operations *op = inode->i_sb->s_op; int drop; - if (op && op->drop_inode) + WARN_ON(inode->i_state & I_NEW); + + if (op->drop_inode) drop = op->drop_inode(inode); else drop = generic_drop_inode(inode); + if (!drop && (sb->s_flags & MS_ACTIVE)) { + inode->i_state |= I_REFERENCED; + inode_add_lru(inode); + spin_unlock(&inode->i_lock); + return; + } + if (!drop) { - if (sb->s_flags & MS_ACTIVE) { - inode->i_state |= I_REFERENCED; - if (!(inode->i_state & (I_DIRTY|I_SYNC))) { - inode_lru_list_add(inode); - } - spin_unlock(&inode_lock); - return; - } - WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_WILL_FREE; - spin_unlock(&inode_lock); + spin_unlock(&inode->i_lock); write_inode_now(inode, 1); - spin_lock(&inode_lock); + spin_lock(&inode->i_lock); WARN_ON(inode->i_state & I_NEW); inode->i_state &= ~I_WILL_FREE; - __remove_inode_hash(inode); } - WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; + if (!list_empty(&inode->i_lru)) + inode_lru_list_del(inode); + spin_unlock(&inode->i_lock); - /* - * Move the inode off the IO lists and LRU once I_FREEING is - * set so that it won't get moved back on there if it is dirty. - */ - inode_lru_list_del(inode); - list_del_init(&inode->i_wb_list); - - __inode_sb_list_del(inode); - spin_unlock(&inode_lock); evict(inode); - remove_inode_hash(inode); - wake_up_inode(inode); - BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); - destroy_inode(inode); } /** @@ -1404,7 +1432,7 @@ void iput(struct inode *inode) if (inode) { BUG_ON(inode->i_state & I_CLEAR); - if (atomic_dec_and_lock(&inode->i_count, &inode_lock)) + if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) iput_final(inode); } } @@ -1464,18 +1492,39 @@ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode, return 0; } +/* + * This does the actual work of updating an inodes time or version. Must have + * had called mnt_want_write() before calling this. + */ +static int update_time(struct inode *inode, struct timespec *time, int flags) +{ + if (inode->i_op->update_time) + return inode->i_op->update_time(inode, time, flags); + + if (flags & S_ATIME) + inode->i_atime = *time; + if (flags & S_VERSION) + inode_inc_iversion(inode); + if (flags & S_CTIME) + inode->i_ctime = *time; + if (flags & S_MTIME) + inode->i_mtime = *time; + mark_inode_dirty_sync(inode); + return 0; +} + /** * touch_atime - update the access time - * @mnt: mount the inode is accessed on - * @dentry: dentry accessed + * @path: the &struct path to update * * Update the accessed time on an inode and mark it for writeback. * This function automatically handles read only file systems and media, * as well as the "noatime" flag and inode specific "noatime" markers. */ -void touch_atime(struct vfsmount *mnt, struct dentry *dentry) +void touch_atime(const struct path *path) { - struct inode *inode = dentry->d_inode; + struct vfsmount *mnt = path->mnt; + struct inode *inode = path->dentry->d_inode; struct timespec now; if (inode->i_flags & S_NOATIME) @@ -1498,15 +1547,96 @@ void touch_atime(struct vfsmount *mnt, struct dentry *dentry) if (timespec_equal(&inode->i_atime, &now)) return; - if (mnt_want_write(mnt)) + if (!sb_start_write_trylock(inode->i_sb)) return; - inode->i_atime = now; - mark_inode_dirty_sync(inode); - mnt_drop_write(mnt); + if (__mnt_want_write(mnt)) + goto skip_update; + /* + * File systems can error out when updating inodes if they need to + * allocate new space to modify an inode (such is the case for + * Btrfs), but since we touch atime while walking down the path we + * really don't care if we failed to update the atime of the file, + * so just ignore the return value. + * We may also fail on filesystems that have the ability to make parts + * of the fs read only, e.g. subvolumes in Btrfs. + */ + update_time(inode, &now, S_ATIME); + __mnt_drop_write(mnt); +skip_update: + sb_end_write(inode->i_sb); } EXPORT_SYMBOL(touch_atime); +/* + * The logic we want is + * + * if suid or (sgid and xgrp) + * remove privs + */ +int should_remove_suid(struct dentry *dentry) +{ + umode_t mode = dentry->d_inode->i_mode; + int kill = 0; + + /* suid always must be killed */ + if (unlikely(mode & S_ISUID)) + kill = ATTR_KILL_SUID; + + /* + * sgid without any exec bits is just a mandatory locking mark; leave + * it alone. If some exec bits are set, it's a real sgid; kill it. + */ + if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) + kill |= ATTR_KILL_SGID; + + if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) + return kill; + + return 0; +} +EXPORT_SYMBOL(should_remove_suid); + +static int __remove_suid(struct dentry *dentry, int kill) +{ + struct iattr newattrs; + + newattrs.ia_valid = ATTR_FORCE | kill; + /* + * Note we call this on write, so notify_change will not + * encounter any conflicting delegations: + */ + return notify_change(dentry, &newattrs, NULL); +} + +int file_remove_suid(struct file *file) +{ + struct dentry *dentry = file->f_path.dentry; + struct inode *inode = dentry->d_inode; + int killsuid; + int killpriv; + int error = 0; + + /* Fast path for nothing security related */ + if (IS_NOSEC(inode)) + return 0; + + killsuid = should_remove_suid(dentry); + killpriv = security_inode_need_killpriv(dentry); + + if (killpriv < 0) + return killpriv; + if (killpriv) + error = security_inode_killpriv(dentry); + if (!error && killsuid) + error = __remove_suid(dentry, killsuid); + if (!error && (inode->i_sb->s_flags & MS_NOSEC)) + inode->i_flags |= S_NOSEC; + + return error; +} +EXPORT_SYMBOL(file_remove_suid); + /** * file_update_time - update mtime and ctime time * @file: file accessed @@ -1516,18 +1646,20 @@ EXPORT_SYMBOL(touch_atime); * usage in the file write path of filesystems, and filesystems may * choose to explicitly ignore update via this function with the * S_NOCMTIME inode flag, e.g. for network filesystem where these - * timestamps are handled by the server. + * timestamps are handled by the server. This can return an error for + * file systems who need to allocate space in order to update an inode. */ -void file_update_time(struct file *file) +int file_update_time(struct file *file) { - struct inode *inode = file->f_path.dentry->d_inode; + struct inode *inode = file_inode(file); struct timespec now; - enum { S_MTIME = 1, S_CTIME = 2, S_VERSION = 4 } sync_it = 0; + int sync_it = 0; + int ret; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) - return; + return 0; now = current_fs_time(inode->i_sb); if (!timespec_equal(&inode->i_mtime, &now)) @@ -1540,21 +1672,16 @@ void file_update_time(struct file *file) sync_it |= S_VERSION; if (!sync_it) - return; + return 0; /* Finally allowed to write? Takes lock. */ - if (mnt_want_write_file(file)) - return; + if (__mnt_want_write_file(file)) + return 0; - /* Only change inode inside the lock region */ - if (sync_it & S_VERSION) - inode_inc_iversion(inode); - if (sync_it & S_CTIME) - inode->i_ctime = now; - if (sync_it & S_MTIME) - inode->i_mtime = now; - mark_inode_dirty_sync(inode); - mnt_drop_write(file->f_path.mnt); + ret = update_time(inode, &now, sync_it); + __mnt_drop_write_file(file); + + return ret; } EXPORT_SYMBOL(file_update_time); @@ -1583,9 +1710,8 @@ EXPORT_SYMBOL(inode_wait); * to recheck inode state. * * It doesn't matter if I_NEW is not set initially, a call to - * wake_up_inode() after removing from the hash list will DTRT. - * - * This is called with inode_lock held. + * 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) { @@ -1593,10 +1719,11 @@ static void __wait_on_freeing_inode(struct inode *inode) DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW); wq = bit_waitqueue(&inode->i_state, __I_NEW); prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); - spin_unlock(&inode_lock); + spin_unlock(&inode->i_lock); + spin_unlock(&inode_hash_lock); schedule(); finish_wait(wq, &wait.wait); - spin_lock(&inode_lock); + spin_lock(&inode_hash_lock); } static __initdata unsigned long ihash_entries; @@ -1614,7 +1741,7 @@ __setup("ihash_entries=", set_ihash_entries); */ void __init inode_init_early(void) { - int loop; + unsigned int loop; /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. @@ -1630,15 +1757,16 @@ void __init inode_init_early(void) HASH_EARLY, &i_hash_shift, &i_hash_mask, + 0, 0); - for (loop = 0; loop < (1 << i_hash_shift); loop++) + for (loop = 0; loop < (1U << i_hash_shift); loop++) INIT_HLIST_HEAD(&inode_hashtable[loop]); } void __init inode_init(void) { - int loop; + unsigned int loop; /* inode slab cache */ inode_cachep = kmem_cache_create("inode_cache", @@ -1647,9 +1775,6 @@ void __init inode_init(void) (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_MEM_SPREAD), init_once); - register_shrinker(&icache_shrinker); - percpu_counter_init(&nr_inodes, 0); - percpu_counter_init(&nr_inodes_unused, 0); /* Hash may have been set up in inode_init_early */ if (!hashdist) @@ -1663,9 +1788,10 @@ void __init inode_init(void) 0, &i_hash_shift, &i_hash_mask, + 0, 0); - for (loop = 0; loop < (1 << i_hash_shift); loop++) + for (loop = 0; loop < (1U << i_hash_shift); loop++) INIT_HLIST_HEAD(&inode_hashtable[loop]); } @@ -1679,7 +1805,7 @@ void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) inode->i_fop = &def_blk_fops; inode->i_rdev = rdev; } else if (S_ISFIFO(mode)) - inode->i_fop = &def_fifo_fops; + inode->i_fop = &pipefifo_fops; else if (S_ISSOCK(mode)) inode->i_fop = &bad_sock_fops; else @@ -1690,13 +1816,13 @@ void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) EXPORT_SYMBOL(init_special_inode); /** - * Init uid,gid,mode for new inode according to posix standards + * inode_init_owner - Init uid,gid,mode for new inode according to posix standards * @inode: New inode * @dir: Directory inode * @mode: mode of the new inode */ void inode_init_owner(struct inode *inode, const struct inode *dir, - mode_t mode) + umode_t mode) { inode->i_uid = current_fsuid(); if (dir && dir->i_mode & S_ISGID) { @@ -1708,3 +1834,102 @@ void inode_init_owner(struct inode *inode, const struct inode *dir, inode->i_mode = mode; } EXPORT_SYMBOL(inode_init_owner); + +/** + * inode_owner_or_capable - check current task permissions to inode + * @inode: inode being checked + * + * Return true if current either has CAP_FOWNER in a namespace with the + * inode owner uid mapped, or owns the file. + */ +bool inode_owner_or_capable(const struct inode *inode) +{ + struct user_namespace *ns; + + if (uid_eq(current_fsuid(), inode->i_uid)) + return true; + + ns = current_user_ns(); + if (ns_capable(ns, CAP_FOWNER) && kuid_has_mapping(ns, inode->i_uid)) + return true; + return false; +} +EXPORT_SYMBOL(inode_owner_or_capable); + +/* + * Direct i/o helper functions + */ +static void __inode_dio_wait(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.wait, TASK_UNINTERRUPTIBLE); + if (atomic_read(&inode->i_dio_count)) + schedule(); + } while (atomic_read(&inode->i_dio_count)); + finish_wait(wq, &q.wait); +} + +/** + * inode_dio_wait - wait for outstanding DIO requests to finish + * @inode: inode to wait for + * + * Waits for all pending direct I/O requests to finish so that we can + * 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. + */ +void inode_dio_wait(struct inode *inode) +{ + if (atomic_read(&inode->i_dio_count)) + __inode_dio_wait(inode); +} +EXPORT_SYMBOL(inode_dio_wait); + +/* + * inode_dio_done - signal finish of a direct I/O requests + * @inode: inode the direct I/O happens on + * + * This is called once we've finished processing a direct I/O request, + * and is used to wake up callers waiting for direct I/O to be quiesced. + */ +void inode_dio_done(struct inode *inode) +{ + if (atomic_dec_and_test(&inode->i_dio_count)) + wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); +} +EXPORT_SYMBOL(inode_dio_done); + +/* + * inode_set_flags - atomically set some inode flags + * + * Note: the caller should be holding i_mutex, 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 + * i_flags actually followed this rule, is that there is at least one + * code path which doesn't today --- for example, + * __generic_file_aio_write() calls file_remove_suid() without holding + * i_mutex --- so we use cmpxchg() out of an abundance of caution. + * + * In the long run, i_mutex 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!! + */ +void inode_set_flags(struct inode *inode, unsigned int flags, + unsigned int mask) +{ + unsigned int old_flags, new_flags; + + WARN_ON_ONCE(flags & ~mask); + do { + old_flags = ACCESS_ONCE(inode->i_flags); + new_flags = (old_flags & ~mask) | flags; + } while (unlikely(cmpxchg(&inode->i_flags, old_flags, + new_flags) != old_flags)); +} +EXPORT_SYMBOL(inode_set_flags); |