--- zzzz-none-000/linux-3.10.107/fs/inode.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/fs/inode.c 2021-02-04 17:41:59.000000000 +0000 @@ -17,6 +17,8 @@ #include #include /* for inode_has_buffers */ #include +#include +#include #include "internal.h" /* @@ -24,26 +26,26 @@ * * inode->i_lock protects: * inode->i_state, inode->i_hash, __iget() - * inode->i_sb->s_inode_lru_lock protects: + * 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 + * inode->i_sb->s_inode_list_lock protects: + * inode->i_sb->s_inodes, inode->i_sb_list * bdi->wb.list_lock protects: - * bdi->wb.b_{dirty,io,more_io}, inode->i_wb_list + * bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list * inode_hash_lock protects: * inode_hashtable, inode->i_hash * * Lock ordering: * - * inode_sb_list_lock + * inode->i_sb->s_inode_list_lock * inode->i_lock - * inode->i_sb->s_inode_lru_lock + * Inode LRU list locks * * bdi->wb.list_lock * inode->i_lock * * inode_hash_lock - * inode_sb_list_lock + * inode->i_sb->s_inode_list_lock * inode->i_lock * * iunique_lock @@ -55,8 +57,6 @@ static struct hlist_head *inode_hashtable __read_mostly; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock); -__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock); - /* * Empty aops. Can be used for the cases where the user does not * define any of the address_space operations. @@ -70,33 +70,33 @@ */ struct inodes_stat_t inodes_stat; -static DEFINE_PER_CPU(unsigned int, nr_inodes); -static DEFINE_PER_CPU(unsigned int, nr_unused); +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 int get_nr_inodes(void) +static long get_nr_inodes(void) { int i; - int sum = 0; + 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) { int i; - int sum = 0; + 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) { /* not actually dirty inodes, but a wild approximation */ - int nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); + long nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); return nr_dirty > 0 ? nr_dirty : 0; } @@ -104,15 +104,20 @@ * 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 int no_open(struct inode *inode, struct file *file) +{ + return -ENXIO; +} + /** * inode_init_always - perform inode structure intialisation * @sb: superblock inode belongs to @@ -124,7 +129,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) { static const struct inode_operations empty_iops; - static const struct file_operations empty_fops; + static const struct file_operations no_open_fops = {.open = no_open}; struct address_space *const mapping = &inode->i_data; inode->i_sb = sb; @@ -132,7 +137,7 @@ inode->i_flags = 0; atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; - inode->i_fop = &empty_fops; + inode->i_fop = &no_open_fops; inode->__i_nlink = 1; inode->i_opflags = 0; i_uid_write(inode, 0); @@ -142,12 +147,10 @@ inode->i_blocks = 0; inode->i_bytes = 0; inode->i_generation = 0; -#ifdef CONFIG_QUOTA - memset(&inode->i_dquot, 0, sizeof(inode->i_dquot)); -#endif inode->i_pipe = NULL; inode->i_bdev = NULL; inode->i_cdev = NULL; + inode->i_link = NULL; inode->i_rdev = 0; inode->dirtied_when = 0; @@ -164,22 +167,10 @@ mapping->a_ops = &empty_aops; mapping->host = inode; mapping->flags = 0; + atomic_set(&mapping->i_mmap_writable, 0); mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); mapping->private_data = NULL; - mapping->backing_dev_info = &default_backing_dev_info; mapping->writeback_index = 0; - - /* - * If the block_device provides a backing_dev_info for client - * inodes then use that. Otherwise the inode share the bdev's - * backing_dev_info. - */ - if (sb->s_bdev) { - struct backing_dev_info *bdi; - - bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info; - mapping->backing_dev_info = bdi; - } inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ @@ -190,7 +181,7 @@ #ifdef CONFIG_FSNOTIFY inode->i_fsnotify_mask = 0; #endif - + inode->i_flctx = NULL; this_cpu_inc(nr_inodes); return 0; @@ -231,8 +222,10 @@ void __destroy_inode(struct inode *inode) { BUG_ON(inode_has_buffers(inode)); + inode_detach_wb(inode); security_inode_free(inode); fsnotify_inode_delete(inode); + locks_free_lock_context(inode->i_flctx); 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); @@ -333,8 +326,10 @@ */ void inc_nlink(struct inode *inode) { - if (WARN_ON(inode->i_nlink == 0)) + 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++; } @@ -345,11 +340,10 @@ 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_rwsem(&mapping->i_mmap_rwsem); 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); @@ -363,7 +357,7 @@ memset(inode, 0, sizeof(*inode)); INIT_HLIST_NODE(&inode->i_hash); INIT_LIST_HEAD(&inode->i_devices); - INIT_LIST_HEAD(&inode->i_wb_list); + INIT_LIST_HEAD(&inode->i_io_list); INIT_LIST_HEAD(&inode->i_lru); address_space_init_once(&inode->i_data); i_size_ordered_init(inode); @@ -399,13 +393,8 @@ static void inode_lru_list_add(struct inode *inode) { - spin_lock(&inode->i_sb->s_inode_lru_lock); - if (list_empty(&inode->i_lru)) { - list_add(&inode->i_lru, &inode->i_sb->s_inode_lru); - inode->i_sb->s_nr_inodes_unused++; + if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); - } - spin_unlock(&inode->i_sb->s_inode_lru_lock); } /* @@ -415,7 +404,8 @@ */ void inode_add_lru(struct inode *inode) { - if (!(inode->i_state & (I_DIRTY | I_SYNC | I_FREEING | I_WILL_FREE)) && + if (!(inode->i_state & (I_DIRTY_ALL | I_SYNC | + I_FREEING | I_WILL_FREE)) && !atomic_read(&inode->i_count) && inode->i_sb->s_flags & MS_ACTIVE) inode_lru_list_add(inode); } @@ -423,13 +413,9 @@ static void inode_lru_list_del(struct inode *inode) { - spin_lock(&inode->i_sb->s_inode_lru_lock); - if (!list_empty(&inode->i_lru)) { - list_del_init(&inode->i_lru); - inode->i_sb->s_nr_inodes_unused--; + + if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); - } - spin_unlock(&inode->i_sb->s_inode_lru_lock); } /** @@ -438,18 +424,18 @@ */ void inode_sb_list_add(struct inode *inode) { - spin_lock(&inode_sb_list_lock); + spin_lock(&inode->i_sb->s_inode_list_lock); list_add(&inode->i_sb_list, &inode->i_sb->s_inodes); - spin_unlock(&inode_sb_list_lock); + spin_unlock(&inode->i_sb->s_inode_list_lock); } EXPORT_SYMBOL_GPL(inode_sb_list_add); static inline void inode_sb_list_del(struct inode *inode) { if (!list_empty(&inode->i_sb_list)) { - spin_lock(&inode_sb_list_lock); + spin_lock(&inode->i_sb->s_inode_list_lock); list_del_init(&inode->i_sb_list); - spin_unlock(&inode_sb_list_lock); + spin_unlock(&inode->i_sb->s_inode_list_lock); } } @@ -509,6 +495,7 @@ */ 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)); @@ -538,8 +525,8 @@ 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); + if (!list_empty(&inode->i_io_list)) + inode_io_list_del(inode); inode_sb_list_del(inode); @@ -554,8 +541,7 @@ if (op->evict_inode) { op->evict_inode(inode); } else { - if (inode->i_data.nrpages) - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); } if (S_ISBLK(inode->i_mode) && inode->i_bdev) @@ -589,6 +575,7 @@ list_del_init(&inode->i_lru); evict(inode); + cond_resched(); } } @@ -606,7 +593,8 @@ struct inode *inode, *next; LIST_HEAD(dispose); - spin_lock(&inode_sb_list_lock); +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)) continue; @@ -621,8 +609,20 @@ inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); + + /* + * We can have a ton of inodes to evict at unmount time given + * enough memory, check to see if we need to go to sleep for a + * bit so we don't livelock. + */ + if (need_resched()) { + spin_unlock(&sb->s_inode_list_lock); + cond_resched(); + dispose_list(&dispose); + goto again; + } } - spin_unlock(&inode_sb_list_lock); + spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); } @@ -643,14 +643,14 @@ struct inode *inode, *next; LIST_HEAD(dispose); - spin_lock(&inode_sb_list_lock); + 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 (inode->i_state & I_DIRTY && !kill_dirty) { + if (inode->i_state & I_DIRTY_ALL && !kill_dirty) { spin_unlock(&inode->i_lock); busy = 1; continue; @@ -666,31 +666,15 @@ spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); } - spin_unlock(&inode_sb_list_lock); + spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); 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; -} - /* - * 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(). + * 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 @@ -704,89 +688,81 @@ * 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. */ -void prune_icache_sb(struct super_block *sb, int nr_to_scan) +static enum lru_status inode_lru_isolate(struct list_head *item, + struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { - LIST_HEAD(freeable); - int nr_scanned; - unsigned long reap = 0; + struct list_head *freeable = arg; + struct inode *inode = container_of(item, struct inode, i_lru); - spin_lock(&sb->s_inode_lru_lock); - for (nr_scanned = nr_to_scan; nr_scanned >= 0; nr_scanned--) { - struct inode *inode; + /* + * 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; - if (list_empty(&sb->s_inode_lru)) - break; + /* + * 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_lru_isolate(lru, &inode->i_lru); + spin_unlock(&inode->i_lock); + this_cpu_dec(nr_unused); + return LRU_REMOVED; + } - inode = list_entry(sb->s_inode_lru.prev, struct inode, i_lru); + /* 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; + } - /* - * we are inverting the sb->s_inode_lru_lock/inode->i_lock here, - * so use a trylock. If we fail to get the lock, just move the - * inode to the back of the list so we don't spin on it. - */ - if (!spin_trylock(&inode->i_lock)) { - list_move(&inode->i_lru, &sb->s_inode_lru); - 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; + } + iput(inode); + spin_lock(lru_lock); + return LRU_RETRY; + } - /* - * 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); - sb->s_nr_inodes_unused--; - this_cpu_dec(nr_unused); - continue; - } + WARN_ON(inode->i_state & I_NEW); + inode->i_state |= I_FREEING; + list_lru_isolate_move(lru, &inode->i_lru, freeable); + spin_unlock(&inode->i_lock); - /* recently referenced inodes get one more pass */ - if (inode->i_state & I_REFERENCED) { - inode->i_state &= ~I_REFERENCED; - list_move(&inode->i_lru, &sb->s_inode_lru); - spin_unlock(&inode->i_lock); - continue; - } - if (inode_has_buffers(inode) || inode->i_data.nrpages) { - __iget(inode); - spin_unlock(&inode->i_lock); - spin_unlock(&sb->s_inode_lru_lock); - if (remove_inode_buffers(inode)) - reap += invalidate_mapping_pages(&inode->i_data, - 0, -1); - iput(inode); - spin_lock(&sb->s_inode_lru_lock); - - if (inode != list_entry(sb->s_inode_lru.next, - struct inode, i_lru)) - continue; /* wrong inode or list_empty */ - /* avoid lock inversions with trylock */ - if (!spin_trylock(&inode->i_lock)) - continue; - if (!can_unuse(inode)) { - spin_unlock(&inode->i_lock); - continue; - } - } - WARN_ON(inode->i_state & I_NEW); - inode->i_state |= I_FREEING; - spin_unlock(&inode->i_lock); + this_cpu_dec(nr_unused); + return LRU_REMOVED; +} - list_move(&inode->i_lru, &freeable); - sb->s_nr_inodes_unused--; - this_cpu_dec(nr_unused); - } - if (current_is_kswapd()) - __count_vm_events(KSWAPD_INODESTEAL, reap); - else - __count_vm_events(PGINODESTEAL, reap); - spin_unlock(&sb->s_inode_lru_lock); - if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += reap; +/* + * 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(). + */ +long prune_icache_sb(struct super_block *sb, struct shrink_control *sc) +{ + LIST_HEAD(freeable); + long freed; + freed = list_lru_shrink_walk(&sb->s_inode_lru, sc, + inode_lru_isolate, &freeable); dispose_list(&freeable); + return freed; } static void __wait_on_freeing_inode(struct inode *inode); @@ -802,15 +778,11 @@ repeat: hlist_for_each_entry(inode, head, i_hash) { - spin_lock(&inode->i_lock); - if (inode->i_sb != sb) { - spin_unlock(&inode->i_lock); + if (inode->i_sb != sb) continue; - } - if (!test(inode, data)) { - spin_unlock(&inode->i_lock); + 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; @@ -833,15 +805,11 @@ repeat: hlist_for_each_entry(inode, head, i_hash) { - spin_lock(&inode->i_lock); - if (inode->i_ino != ino) { - spin_unlock(&inode->i_lock); + if (inode->i_ino != ino) continue; - } - if (inode->i_sb != sb) { - spin_unlock(&inode->i_lock); + 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; @@ -885,7 +853,11 @@ } #endif - *p = ++res; + res++; + /* get_next_ino should not provide a 0 inode number */ + if (unlikely(!res)) + res++; + *p = res; put_cpu_var(last_ino); return res; } @@ -930,7 +902,7 @@ { struct inode *inode; - spin_lock_prefetch(&inode_sb_list_lock); + spin_lock_prefetch(&sb->s_inode_list_lock); inode = new_inode_pseudo(sb); if (inode) @@ -980,6 +952,41 @@ EXPORT_SYMBOL(unlock_new_inode); /** + * lock_two_nondirectories - take two i_mutexes on non-directory objects + * + * 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 + */ +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 @@ -1281,6 +1288,56 @@ } EXPORT_SYMBOL(ilookup); +/** + * find_inode_nowait - find an inode in the inode cache + * @sb: super block of file system to search + * @hashval: hash value (usually inode number) to search for + * @match: callback used for comparisons between inodes + * @data: opaque data pointer to pass to @match + * + * Search for the inode specified by @hashval and @data in the inode + * cache, where the helper function @match will return 0 if the inode + * does not match, 1 if the inode does match, and -1 if the search + * should be stopped. The @match function must be responsible for + * taking the i_lock spin_lock and checking i_state for an inode being + * freed or being initialized, and incrementing the reference count + * before returning 1. It also must not sleep, since it is called with + * the inode_hash_lock spinlock held. + * + * This is a even more generalized version of ilookup5() when the + * function must never block --- find_inode() can block in + * __wait_on_freeing_inode() --- or when the caller can not increment + * the reference count because the resulting iput() might cause an + * inode eviction. The tradeoff is that the @match funtion must be + * very carefully implemented. + */ +struct inode *find_inode_nowait(struct super_block *sb, + unsigned long hashval, + int (*match)(struct inode *, unsigned long, + void *), + void *data) +{ + struct hlist_head *head = inode_hashtable + hash(sb, hashval); + struct inode *inode, *ret_inode = NULL; + int mval; + + spin_lock(&inode_hash_lock); + hlist_for_each_entry(inode, head, i_hash) { + if (inode->i_sb != sb) + continue; + mval = match(inode, hashval, data); + if (mval == 0) + continue; + if (mval == 1) + ret_inode = inode; + goto out; + } +out: + spin_unlock(&inode_hash_lock); + return ret_inode; +} +EXPORT_SYMBOL(find_inode_nowait); + int insert_inode_locked(struct inode *inode) { struct super_block *sb = inode->i_sb; @@ -1431,11 +1488,20 @@ */ void iput(struct inode *inode) { - if (inode) { - BUG_ON(inode->i_state & I_CLEAR); - - if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) - iput_final(inode); + if (!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); + inode->i_state &= ~I_DIRTY_TIME; + spin_unlock(&inode->i_lock); + trace_writeback_lazytime_iput(inode); + mark_inode_dirty_sync(inode); + goto retry; + } + iput_final(inode); } } EXPORT_SYMBOL(iput); @@ -1494,14 +1560,9 @@ 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) +int generic_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); + int iflags = I_DIRTY_TIME; if (flags & S_ATIME) inode->i_atime = *time; @@ -1511,48 +1572,78 @@ inode->i_ctime = *time; if (flags & S_MTIME) inode->i_mtime = *time; - mark_inode_dirty_sync(inode); + + if (!(inode->i_sb->s_flags & MS_LAZYTIME) || (flags & S_VERSION)) + iflags |= I_DIRTY_SYNC; + __mark_inode_dirty(inode, iflags); return 0; } +EXPORT_SYMBOL(generic_update_time); + +/* + * 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) +{ + int (*update_time)(struct inode *, struct timespec *, int); + + update_time = inode->i_op->update_time ? inode->i_op->update_time : + generic_update_time; + + return update_time(inode, time, flags); +} /** * touch_atime - update the access time * @path: the &struct path to update + * @inode: inode 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 path *path) +bool atime_needs_update(const struct path *path, struct inode *inode) { struct vfsmount *mnt = path->mnt; - struct inode *inode = path->dentry->d_inode; struct timespec now; if (inode->i_flags & S_NOATIME) - return; + return false; if (IS_NOATIME(inode)) - return; + return false; if ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode)) - return; + return false; if (mnt->mnt_flags & MNT_NOATIME) - return; + return false; if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)) - return; + return false; now = current_fs_time(inode->i_sb); if (!relatime_need_update(mnt, inode, now)) - return; + return false; if (timespec_equal(&inode->i_atime, &now)) + return false; + + return true; +} + +void touch_atime(const struct path *path) +{ + struct vfsmount *mnt = path->mnt; + struct inode *inode = d_inode(path->dentry); + struct timespec now; + + if (!atime_needs_update(path, inode)) return; if (!sb_start_write_trylock(inode->i_sb)) return; - if (__mnt_want_write(mnt)) + if (__mnt_want_write(mnt) != 0) goto skip_update; /* * File systems can error out when updating inodes if they need to @@ -1563,6 +1654,7 @@ * We may also fail on filesystems that have the ability to make parts * of the fs read only, e.g. subvolumes in Btrfs. */ + now = current_fs_time(inode->i_sb); update_time(inode, &now, S_ATIME); __mnt_drop_write(mnt); skip_update: @@ -1578,7 +1670,7 @@ */ int should_remove_suid(struct dentry *dentry) { - umode_t mode = dentry->d_inode->i_mode; + umode_t mode = d_inode(dentry)->i_mode; int kill = 0; /* suid always must be killed */ @@ -1599,41 +1691,68 @@ } EXPORT_SYMBOL(should_remove_suid); -static int __remove_suid(struct dentry *dentry, int kill) +/* + * Return mask of changes for notify_change() that need to be done as a + * response to write or truncate. Return 0 if nothing has to be changed. + * Negative value on error (change should be denied). + */ +int dentry_needs_remove_privs(struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + int mask = 0; + int ret; + + if (IS_NOSEC(inode)) + return 0; + + mask = should_remove_suid(dentry); + ret = security_inode_need_killpriv(dentry); + if (ret < 0) + return ret; + if (ret) + mask |= ATTR_KILL_PRIV; + return mask; +} +EXPORT_SYMBOL(dentry_needs_remove_privs); + +static int __remove_privs(struct dentry *dentry, int kill) { struct iattr newattrs; newattrs.ia_valid = ATTR_FORCE | kill; - return notify_change(dentry, &newattrs); + /* + * 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) +/* + * Remove special file priviledges (suid, capabilities) when file is written + * to or truncated. + */ +int file_remove_privs(struct file *file) { - struct dentry *dentry = file->f_path.dentry; - struct inode *inode = dentry->d_inode; - int killsuid; - int killpriv; + struct dentry *dentry = file_dentry(file); + struct inode *inode = file_inode(file); + int kill; 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); + kill = dentry_needs_remove_privs(dentry); + if (kill < 0) + return kill; + if (kill) + error = __remove_privs(dentry, kill); if (!error) inode_has_no_xattr(inode); return error; } -EXPORT_SYMBOL(file_remove_suid); +EXPORT_SYMBOL(file_remove_privs); /** * file_update_time - update mtime and ctime time @@ -1693,13 +1812,6 @@ } EXPORT_SYMBOL(inode_needs_sync); -int inode_wait(void *word) -{ - schedule(); - return 0; -} -EXPORT_SYMBOL(inode_wait); - /* * If we try to find an inode in the inode hash while it is being * deleted, we have to wait until the filesystem completes its @@ -1805,7 +1917,7 @@ } else if (S_ISFIFO(mode)) inode->i_fop = &pipefifo_fops; else if (S_ISSOCK(mode)) - inode->i_fop = &bad_sock_fops; + ; /* leave it no_open_fops */ else printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for" " inode %s:%lu\n", mode, inode->i_sb->s_id, @@ -1825,8 +1937,14 @@ inode->i_uid = current_fsuid(); if (dir && dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; + + /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; + else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) && + !in_group_p(inode->i_gid) && + !capable_wrt_inode_uidgid(dir, CAP_FSETID)) + mode &= ~S_ISGID; } else inode->i_gid = current_fsgid(); inode->i_mode = mode; @@ -1888,15 +2006,31 @@ EXPORT_SYMBOL(inode_dio_wait); /* - * inode_dio_done - signal finish of a direct I/O requests - * @inode: inode the direct I/O happens on + * inode_set_flags - atomically set some inode flags * - * 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. + * 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 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_dio_done(struct inode *inode) +void inode_set_flags(struct inode *inode, unsigned int flags, + unsigned int mask) { - if (atomic_dec_and_test(&inode->i_dio_count)) - wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); + 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_dio_done); +EXPORT_SYMBOL(inode_set_flags);