From 7e360c38abe2c70eae3ba5a8a17f17671d8b77c5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Oct 2010 09:32:55 +0200 Subject: fs: allow for more than 2^31 files Andrew, Could you please review this patch, you probably are the right guy to take it, because it crosses fs and net trees. Note : /proc/sys/fs/file-nr is a read-only file, so this patch doesnt depend on previous patch (sysctl: fix min/max handling in __do_proc_doulongvec_minmax()) Thanks ! [PATCH V4] fs: allow for more than 2^31 files Robin Holt tried to boot a 16TB system and found af_unix was overflowing a 32bit value : We were seeing a failure which prevented boot. The kernel was incapable of creating either a named pipe or unix domain socket. This comes down to a common kernel function called unix_create1() which does: atomic_inc(&unix_nr_socks); if (atomic_read(&unix_nr_socks) > 2 * get_max_files()) goto out; The function get_max_files() is a simple return of files_stat.max_files. files_stat.max_files is a signed integer and is computed in fs/file_table.c's files_init(). n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = n; In our case, mempages (total_ram_pages) is approx 3,758,096,384 (0xe0000000). That leaves max_files at approximately 1,503,238,553. This causes 2 * get_max_files() to integer overflow. Fix is to let /proc/sys/fs/file-nr & /proc/sys/fs/file-max use long integers, and change af_unix to use an atomic_long_t instead of atomic_t. get_max_files() is changed to return an unsigned long. get_nr_files() is changed to return a long. unix_nr_socks is changed from atomic_t to atomic_long_t, while not strictly needed to address Robin problem. Before patch (on a 64bit kernel) : # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max -18446744071562067968 After patch: # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max 2147483648 # cat /proc/sys/fs/file-nr 704 0 2147483648 Reported-by: Robin Holt Signed-off-by: Eric Dumazet Acked-by: David Miller Reviewed-by: Robin Holt Tested-by: Robin Holt Signed-off-by: Al Viro --- kernel/sysctl.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3a45c224770f..694b140852c2 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1352,16 +1352,16 @@ static struct ctl_table fs_table[] = { { .procname = "file-nr", .data = &files_stat, - .maxlen = 3*sizeof(int), + .maxlen = sizeof(files_stat), .mode = 0444, .proc_handler = proc_nr_files, }, { .procname = "file-max", .data = &files_stat.max_files, - .maxlen = sizeof(int), + .maxlen = sizeof(files_stat.max_files), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_doulongvec_minmax, }, { .procname = "nr_open", -- cgit v1.2.3 From cffbc8aa334f55c9ed42d25202eb3ebf3a97c195 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Sat, 23 Oct 2010 05:03:02 -0400 Subject: fs: Convert nr_inodes and nr_unused to per-cpu counters The number of inodes allocated does not need to be tied to the addition or removal of an inode to/from a list. If we are not tied to a list lock, we could update the counters when inodes are initialised or destroyed, but to do that we need to convert the counters to be per-cpu (i.e. independent of a lock). This means that we have the freedom to change the list/locking implementation without needing to care about the counters. Based on a patch originally from Eric Dumazet. [AV: cleaned up a bit, fixed build breakage on weird configs Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/fs-writeback.c | 5 ++--- fs/inode.c | 64 ++++++++++++++++++++++++++++++++++++++---------------- fs/internal.h | 1 + include/linux/fs.h | 3 ++- kernel/sysctl.c | 4 ++-- 5 files changed, 52 insertions(+), 25 deletions(-) (limited to 'kernel') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 39f44f2e709a..f04d04af84f2 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -723,7 +723,7 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb) wb->last_old_flush = jiffies; nr_pages = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS) + - (inodes_stat.nr_inodes - inodes_stat.nr_unused); + get_nr_dirty_inodes(); if (nr_pages) { struct wb_writeback_work work = { @@ -1090,8 +1090,7 @@ void writeback_inodes_sb(struct super_block *sb) WARN_ON(!rwsem_is_locked(&sb->s_umount)); - work.nr_pages = nr_dirty + nr_unstable + - (inodes_stat.nr_inodes - inodes_stat.nr_unused); + work.nr_pages = nr_dirty + nr_unstable + get_nr_dirty_inodes(); bdi_queue_work(sb->s_bdi, &work); wait_for_completion(&done); diff --git a/fs/inode.c b/fs/inode.c index 4440cf1034ec..0d5aeccbdd90 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -103,8 +103,41 @@ static DECLARE_RWSEM(iprune_sem); */ 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 struct kmem_cache *inode_cachep __read_mostly; +static inline int get_nr_inodes(void) +{ + return percpu_counter_sum_positive(&nr_inodes); +} + +static inline int get_nr_inodes_unused(void) +{ + return percpu_counter_sum_positive(&nr_inodes_unused); +} + +int get_nr_dirty_inodes(void) +{ + int 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, + 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); +} +#endif + static void wake_up_inode(struct inode *inode) { /* @@ -192,6 +225,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_fsnotify_mask = 0; #endif + percpu_counter_inc(&nr_inodes); + return 0; out: return -ENOMEM; @@ -232,6 +267,7 @@ void __destroy_inode(struct inode *inode) 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); } EXPORT_SYMBOL(__destroy_inode); @@ -286,7 +322,7 @@ void __iget(struct inode *inode) if (!(inode->i_state & (I_DIRTY|I_SYNC))) list_move(&inode->i_list, &inode_in_use); - inodes_stat.nr_unused--; + percpu_counter_dec(&nr_inodes_unused); } void end_writeback(struct inode *inode) @@ -327,8 +363,6 @@ static void evict(struct inode *inode) */ static void dispose_list(struct list_head *head) { - int nr_disposed = 0; - while (!list_empty(head)) { struct inode *inode; @@ -344,11 +378,7 @@ static void dispose_list(struct list_head *head) wake_up_inode(inode); destroy_inode(inode); - nr_disposed++; } - spin_lock(&inode_lock); - inodes_stat.nr_inodes -= nr_disposed; - spin_unlock(&inode_lock); } /* @@ -357,7 +387,7 @@ static void dispose_list(struct list_head *head) static int invalidate_list(struct list_head *head, struct list_head *dispose) { struct list_head *next; - int busy = 0, count = 0; + int busy = 0; next = head->next; for (;;) { @@ -383,13 +413,11 @@ static int invalidate_list(struct list_head *head, struct list_head *dispose) list_move(&inode->i_list, dispose); WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; - count++; + percpu_counter_dec(&nr_inodes_unused); continue; } busy = 1; } - /* only unused inodes may be cached with i_count zero */ - inodes_stat.nr_unused -= count; return busy; } @@ -447,7 +475,6 @@ static int can_unuse(struct inode *inode) static void prune_icache(int nr_to_scan) { LIST_HEAD(freeable); - int nr_pruned = 0; int nr_scanned; unsigned long reap = 0; @@ -483,9 +510,8 @@ static void prune_icache(int nr_to_scan) list_move(&inode->i_list, &freeable); WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; - nr_pruned++; + percpu_counter_dec(&nr_inodes_unused); } - inodes_stat.nr_unused -= nr_pruned; if (current_is_kswapd()) __count_vm_events(KSWAPD_INODESTEAL, reap); else @@ -517,7 +543,7 @@ static int shrink_icache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) return -1; prune_icache(nr); } - return (inodes_stat.nr_unused / 100) * sysctl_vfs_cache_pressure; + return (get_nr_inodes_unused() / 100) * sysctl_vfs_cache_pressure; } static struct shrinker icache_shrinker = { @@ -594,7 +620,6 @@ static inline void __inode_add_to_lists(struct super_block *sb, struct hlist_head *head, struct inode *inode) { - inodes_stat.nr_inodes++; list_add(&inode->i_list, &inode_in_use); list_add(&inode->i_sb_list, &sb->s_inodes); if (head) @@ -1214,7 +1239,7 @@ static void iput_final(struct inode *inode) if (!drop) { if (!(inode->i_state & (I_DIRTY|I_SYNC))) list_move(&inode->i_list, &inode_unused); - inodes_stat.nr_unused++; + percpu_counter_inc(&nr_inodes_unused); if (sb->s_flags & MS_ACTIVE) { spin_unlock(&inode_lock); return; @@ -1226,14 +1251,13 @@ static void iput_final(struct inode *inode) spin_lock(&inode_lock); WARN_ON(inode->i_state & I_NEW); inode->i_state &= ~I_WILL_FREE; - inodes_stat.nr_unused--; + percpu_counter_dec(&nr_inodes_unused); hlist_del_init(&inode->i_hash); } list_del_init(&inode->i_list); list_del_init(&inode->i_sb_list); WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; - inodes_stat.nr_inodes--; spin_unlock(&inode_lock); evict(inode); spin_lock(&inode_lock); @@ -1502,6 +1526,8 @@ void __init inode_init(void) 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) diff --git a/fs/internal.h b/fs/internal.h index f6dce46d80dc..4cc67eb6ed56 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -105,4 +105,5 @@ extern void release_open_intent(struct nameidata *); /* * inode.c */ +extern int get_nr_dirty_inodes(void); extern int invalidate_inodes(struct super_block *); diff --git a/include/linux/fs.h b/include/linux/fs.h index 78043da85e1f..a3937a8ee95e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2486,7 +2486,8 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, struct ctl_table; int proc_nr_files(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); - +int proc_nr_inodes(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 694b140852c2..99a510cbfbb3 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1340,14 +1340,14 @@ static struct ctl_table fs_table[] = { .data = &inodes_stat, .maxlen = 2*sizeof(int), .mode = 0444, - .proc_handler = proc_dointvec, + .proc_handler = proc_nr_inodes, }, { .procname = "inode-state", .data = &inodes_stat, .maxlen = 7*sizeof(int), .mode = 0444, - .proc_handler = proc_dointvec, + .proc_handler = proc_nr_inodes, }, { .procname = "file-nr", -- cgit v1.2.3 From 7de9c6ee3ecffd99e1628e81a5ea5468f7581a1f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Oct 2010 11:11:40 -0400 Subject: new helper: ihold() Clones an existing reference to inode; caller must already hold one. Signed-off-by: Al Viro --- fs/9p/vfs_inode.c | 5 +++-- fs/affs/inode.c | 2 +- fs/afs/dir.c | 2 +- fs/aio.c | 5 ++--- fs/anon_inodes.c | 5 ++--- fs/bfs/dir.c | 2 +- fs/block_dev.c | 8 ++++---- fs/btrfs/inode.c | 2 +- fs/coda/dir.c | 2 +- fs/exofs/namei.c | 2 +- fs/ext2/namei.c | 2 +- fs/ext3/namei.c | 2 +- fs/ext4/namei.c | 2 +- fs/gfs2/ops_inode.c | 2 +- fs/hfsplus/dir.c | 2 +- fs/inode.c | 9 +++++++++ fs/jffs2/dir.c | 4 ++-- fs/jfs/jfs_txnmgr.c | 2 +- fs/jfs/namei.c | 2 +- fs/libfs.c | 2 +- fs/logfs/dir.c | 2 +- fs/minix/namei.c | 2 +- fs/namei.c | 2 +- fs/nfs/dir.c | 2 +- fs/nfs/getroot.c | 3 +-- fs/nilfs2/namei.c | 2 +- fs/ntfs/super.c | 4 ++-- fs/ocfs2/namei.c | 2 +- fs/reiserfs/namei.c | 2 +- fs/sysv/namei.c | 2 +- fs/ubifs/dir.c | 2 +- fs/udf/namei.c | 2 +- fs/ufs/namei.c | 2 +- fs/xfs/linux-2.6/xfs_iops.c | 2 +- fs/xfs/xfs_inode.h | 2 +- include/linux/fs.h | 1 + ipc/mqueue.c | 2 +- kernel/futex.c | 2 +- mm/shmem.c | 2 +- net/socket.c | 2 +- 40 files changed, 57 insertions(+), 49 deletions(-) (limited to 'kernel') diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 9e670d527646..ef5905f7c8a3 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1789,9 +1789,10 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir, kfree(st); } else { /* Caching disabled. No need to get upto date stat info. - * This dentry will be released immediately. So, just i_count++ + * This dentry will be released immediately. So, just hold the + * inode */ - atomic_inc(&old_dentry->d_inode->i_count); + ihold(old_dentry->d_inode); } dentry->d_op = old_dentry->d_op; diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 3a0fdec175ba..5d828903ac69 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -388,7 +388,7 @@ affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s3 affs_adjust_checksum(inode_bh, block - be32_to_cpu(chain)); mark_buffer_dirty_inode(inode_bh, inode); inode->i_nlink = 2; - atomic_inc(&inode->i_count); + ihold(inode); } affs_fix_checksum(sb, bh); mark_buffer_dirty_inode(bh, inode); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 0d38c09bd55e..5439e1bc9a86 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1045,7 +1045,7 @@ static int afs_link(struct dentry *from, struct inode *dir, if (ret < 0) goto link_error; - atomic_inc(&vnode->vfs_inode.i_count); + ihold(&vnode->vfs_inode); d_instantiate(dentry, &vnode->vfs_inode); key_put(key); _leave(" = 0"); diff --git a/fs/aio.c b/fs/aio.c index 9e319a04780e..8c8f6c5b6d79 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1553,10 +1553,9 @@ static void aio_batch_add(struct address_space *mapping, * * When we're called, we always have a reference * on the file, so we must always have a reference - * on the inode, so igrab must always just - * bump the count and move on. + * on the inode, so ihold() is safe here. */ - atomic_inc(&mapping->host->i_count); + ihold(mapping->host); abe->mapping = mapping; hlist_add_head(&abe->list, &batch_hash[bucket]); return; diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index e4b75d6eda83..9c8e87b0361f 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -111,10 +111,9 @@ struct file *anon_inode_getfile(const char *name, path.mnt = mntget(anon_inode_mnt); /* * We know the anon_inode inode count is always greater than zero, - * so we can avoid doing an igrab() and we can use an open-coded - * atomic_inc(). + * so ihold() is safe. */ - atomic_inc(&anon_inode_inode->i_count); + ihold(anon_inode_inode); path.dentry->d_op = &anon_inodefs_dentry_operations; d_instantiate(path.dentry, anon_inode_inode); diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index d967e052b779..685ecff3ab31 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -176,7 +176,7 @@ static int bfs_link(struct dentry *old, struct inode *dir, inc_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(new, inode); mutex_unlock(&info->bfs_lock); return 0; diff --git a/fs/block_dev.c b/fs/block_dev.c index b737451e2e9d..81972eb34b39 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -550,7 +550,7 @@ EXPORT_SYMBOL(bdget); */ struct block_device *bdgrab(struct block_device *bdev) { - atomic_inc(&bdev->bd_inode->i_count); + ihold(bdev->bd_inode); return bdev; } @@ -580,7 +580,7 @@ static struct block_device *bd_acquire(struct inode *inode) spin_lock(&bdev_lock); bdev = inode->i_bdev; if (bdev) { - atomic_inc(&bdev->bd_inode->i_count); + ihold(bdev->bd_inode); spin_unlock(&bdev_lock); return bdev; } @@ -591,12 +591,12 @@ static struct block_device *bd_acquire(struct inode *inode) spin_lock(&bdev_lock); if (!inode->i_bdev) { /* - * We take an additional bd_inode->i_count for inode, + * We take an additional reference to bd_inode, * and it's released in clear_inode() of inode. * So, we can access it via ->i_mapping always * without igrab(). */ - atomic_inc(&bdev->bd_inode->i_count); + ihold(bdev->bd_inode); inode->i_bdev = bdev; inode->i_mapping = bdev->bd_inode->i_mapping; list_add(&inode->i_devices, &bdev->bd_inodes); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f6f2a0da2695..64f99cf69ce0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4758,7 +4758,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, } btrfs_set_trans_block_group(trans, dir); - atomic_inc(&inode->i_count); + ihold(inode); err = btrfs_add_nondir(trans, dentry, inode, 1, index); diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 96fbeab77f2f..5d8b35539601 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -276,7 +276,7 @@ static int coda_link(struct dentry *source_de, struct inode *dir_inode, } coda_dir_update_mtime(dir_inode); - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(de, inode); inc_nlink(inode); return 0; diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c index b7dd0c236863..264e95d02830 100644 --- a/fs/exofs/namei.c +++ b/fs/exofs/namei.c @@ -153,7 +153,7 @@ static int exofs_link(struct dentry *old_dentry, struct inode *dir, inode->i_ctime = CURRENT_TIME; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); return exofs_add_nondir(dentry, inode); } diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 71efb0e9a3f2..f8aecd2e3297 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -206,7 +206,7 @@ static int ext2_link (struct dentry * old_dentry, struct inode * dir, inode->i_ctime = CURRENT_TIME_SEC; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); err = ext2_add_link(dentry, inode); if (!err) { diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 2b35ddb70d65..bce9dce639b8 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -2260,7 +2260,7 @@ retry: inode->i_ctime = CURRENT_TIME_SEC; inc_nlink(inode); - atomic_inc(&inode->i_count); + ihold(inode); err = ext3_add_entry(handle, dentry, inode); if (!err) { diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 314c0d3b3fa9..bd39885b5998 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2312,7 +2312,7 @@ retry: inode->i_ctime = ext4_current_time(inode); ext4_inc_count(handle, inode); - atomic_inc(&inode->i_count); + ihold(inode); err = ext4_add_entry(handle, dentry, inode); if (!err) { diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index 48a274f1674c..12cbea7502c2 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -255,7 +255,7 @@ out_parent: gfs2_holder_uninit(ghs); gfs2_holder_uninit(ghs + 1); if (!error) { - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(dentry, inode); mark_inode_dirty(inode); } diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index d236d85ec9d7..e318bbc0daf6 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -286,7 +286,7 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir, inc_nlink(inode); hfsplus_instantiate(dst_dentry, inode, cnid); - atomic_inc(&inode->i_count); + ihold(inode); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); sbi->file_count++; diff --git a/fs/inode.c b/fs/inode.c index 430d70f2abe7..05ea293d5f32 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -320,6 +320,15 @@ 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) +{ + WARN_ON(atomic_inc_return(&inode->i_count) < 2); +} +EXPORT_SYMBOL(ihold); + static void inode_lru_list_add(struct inode *inode) { if (list_empty(&inode->i_list)) { diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index ed78a3cf3cb0..79121aa5858b 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -289,7 +289,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de mutex_unlock(&f->sem); d_instantiate(dentry, old_dentry->d_inode); dir_i->i_mtime = dir_i->i_ctime = ITIME(now); - atomic_inc(&old_dentry->d_inode->i_count); + ihold(old_dentry->d_inode); } return ret; } @@ -864,7 +864,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, printk(KERN_NOTICE "jffs2_rename(): Link succeeded, unlink failed (err %d). You now have a hard link\n", ret); /* Might as well let the VFS know */ d_instantiate(new_dentry, old_dentry->d_inode); - atomic_inc(&old_dentry->d_inode->i_count); + ihold(old_dentry->d_inode); new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now); return ret; } diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index d945ea76b445..9466957ec841 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -1279,7 +1279,7 @@ int txCommit(tid_t tid, /* transaction identifier */ * lazy commit thread finishes processing */ if (tblk->xflag & COMMIT_DELETE) { - atomic_inc(&tblk->u.ip->i_count); + ihold(tblk->u.ip); /* * Avoid a rare deadlock * diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index a9cf8e8675be..231ca4af9bce 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -839,7 +839,7 @@ static int jfs_link(struct dentry *old_dentry, ip->i_ctime = CURRENT_TIME; dir->i_ctime = dir->i_mtime = CURRENT_TIME; mark_inode_dirty(dir); - atomic_inc(&ip->i_count); + ihold(ip); iplist[0] = ip; iplist[1] = dir; diff --git a/fs/libfs.c b/fs/libfs.c index 2dbf4877d7ef..304a5132ca27 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -255,7 +255,7 @@ int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *den inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; inc_nlink(inode); - atomic_inc(&inode->i_count); + ihold(inode); dget(dentry); d_instantiate(dentry, inode); return 0; diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c index 1eb4e89e045b..409dfd65e9a1 100644 --- a/fs/logfs/dir.c +++ b/fs/logfs/dir.c @@ -569,7 +569,7 @@ static int logfs_link(struct dentry *old_dentry, struct inode *dir, return -EMLINK; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - atomic_inc(&inode->i_count); + ihold(inode); inode->i_nlink++; mark_inode_dirty_sync(inode); diff --git a/fs/minix/namei.c b/fs/minix/namei.c index f3f3578393a4..c0d35a3accef 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -101,7 +101,7 @@ static int minix_link(struct dentry * old_dentry, struct inode * dir, inode->i_ctime = CURRENT_TIME_SEC; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); return add_nondir(dentry, inode); } diff --git a/fs/namei.c b/fs/namei.c index f1ef97dbc6c4..f7dbc06857ab 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2285,7 +2285,7 @@ static long do_unlinkat(int dfd, const char __user *pathname) goto slashes; inode = dentry->d_inode; if (inode) - atomic_inc(&inode->i_count); + ihold(inode); error = mnt_want_write(nd.path.mnt); if (error) goto exit2; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index e257172d438c..0fac7fea18ef 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1580,7 +1580,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) d_drop(dentry); error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); if (error == 0) { - atomic_inc(&inode->i_count); + ihold(inode); d_add(dentry, inode); } return error; diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index a70e446e1605..ac7b814ce162 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -54,8 +54,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i iput(inode); return -ENOMEM; } - /* Circumvent igrab(): we know the inode is not being freed */ - atomic_inc(&inode->i_count); + ihold(inode); /* * Ensure that this dentry is invisible to d_find_alias(). * Otherwise, it may be spliced into the tree by diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 185d1607cb00..6e9557ecf161 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -207,7 +207,7 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir, inode->i_ctime = CURRENT_TIME; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); err = nilfs_add_nondir(dentry, inode); if (!err) diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index d4dec2d32117..d3fbe5730bfc 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -2911,8 +2911,8 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent) goto unl_upcase_iput_tmp_ino_err_out_now; } if ((sb->s_root = d_alloc_root(vol->root_ino))) { - /* We increment i_count simulating an ntfs_iget(). */ - atomic_inc(&vol->root_ino->i_count); + /* We grab a reference, simulating an ntfs_iget(). */ + ihold(vol->root_ino); ntfs_debug("Exiting, status successful."); /* Release the default upcase if it has no users. */ mutex_lock(&ntfs_lock); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index e7bde21149ae..ff5744e1e36f 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -742,7 +742,7 @@ static int ocfs2_link(struct dentry *old_dentry, goto out_commit; } - atomic_inc(&inode->i_count); + ihold(inode); dentry->d_op = &ocfs2_dentry_ops; d_instantiate(dentry, inode); diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index ee78d4a0086a..ba5f51ec3458 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -1156,7 +1156,7 @@ static int reiserfs_link(struct dentry *old_dentry, struct inode *dir, inode->i_ctime = CURRENT_TIME_SEC; reiserfs_update_sd(&th, inode); - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(dentry, inode); retval = journal_end(&th, dir->i_sb, jbegin_count); reiserfs_write_unlock(dir->i_sb); diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index 33e047b59b8d..11e7f7d11cd0 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -126,7 +126,7 @@ static int sysv_link(struct dentry * old_dentry, struct inode * dir, inode->i_ctime = CURRENT_TIME_SEC; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); return add_nondir(dentry, inode); } diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 87ebcce72213..14f64b689d7f 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -550,7 +550,7 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir, lock_2_inodes(dir, inode); inc_nlink(inode); - atomic_inc(&inode->i_count); + ihold(inode); inode->i_ctime = ubifs_current_time(inode); dir->i_size += sz_change; dir_ui->ui_size = dir->i_size; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index bf5fc674193c..6d8dc02baebb 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -1101,7 +1101,7 @@ static int udf_link(struct dentry *old_dentry, struct inode *dir, inc_nlink(inode); inode->i_ctime = current_fs_time(inode->i_sb); mark_inode_dirty(inode); - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(dentry, inode); unlock_kernel(); diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index b056f02b1fb3..12f39b9e4437 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -180,7 +180,7 @@ static int ufs_link (struct dentry * old_dentry, struct inode * dir, inode->i_ctime = CURRENT_TIME_SEC; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); error = ufs_add_nondir(dentry, inode); unlock_kernel(); diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c index 71d83c93621c..96107efc0c61 100644 --- a/fs/xfs/linux-2.6/xfs_iops.c +++ b/fs/xfs/linux-2.6/xfs_iops.c @@ -317,7 +317,7 @@ xfs_vn_link( if (unlikely(error)) return -error; - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(dentry, inode); return 0; } diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index fac52290de90..fb2ca2e4cdc9 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -500,7 +500,7 @@ void xfs_mark_inode_dirty_sync(xfs_inode_t *); #define IHOLD(ip) \ do { \ ASSERT(atomic_read(&VFS_I(ip)->i_count) > 0) ; \ - atomic_inc(&(VFS_I(ip)->i_count)); \ + ihold(VFS_I(ip)); \ trace_xfs_ihold(ip, _THIS_IP_); \ } while (0) diff --git a/include/linux/fs.h b/include/linux/fs.h index d43e8b6685a2..bd6ae6c71fc8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2171,6 +2171,7 @@ extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin); extern int inode_init_always(struct super_block *, struct inode *); extern void inode_init_once(struct inode *); +extern void ihold(struct inode * inode); extern void iput(struct inode *); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index e1e7b9635f5d..80b35ffca25d 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -769,7 +769,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) inode = dentry->d_inode; if (inode) - atomic_inc(&inode->i_count); + ihold(inode); err = mnt_want_write(ipc_ns->mq_mnt); if (err) goto out_err; diff --git a/kernel/futex.c b/kernel/futex.c index a118bf160e0b..6c683b37f2ce 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -169,7 +169,7 @@ static void get_futex_key_refs(union futex_key *key) switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: - atomic_inc(&key->shared.inode->i_count); + ihold(key->shared.inode); break; case FUT_OFF_MMSHARED: atomic_inc(&key->private.mm->mm_count); diff --git a/mm/shmem.c b/mm/shmem.c index 27a58120dbd5..d4e2852526e6 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1903,7 +1903,7 @@ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentr dir->i_size += BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; inc_nlink(inode); - atomic_inc(&inode->i_count); /* New dentry reference */ + ihold(inode); /* New dentry reference */ dget(dentry); /* Extra pinning count for the created dentry */ d_instantiate(dentry, inode); out: diff --git a/net/socket.c b/net/socket.c index abf3e2561521..d223725f99e5 100644 --- a/net/socket.c +++ b/net/socket.c @@ -377,7 +377,7 @@ static int sock_alloc_file(struct socket *sock, struct file **f, int flags) &socket_file_ops); if (unlikely(!file)) { /* drop dentry, keep inode */ - atomic_inc(&path.dentry->d_inode->i_count); + ihold(path.dentry->d_inode); path_put(&path); put_unused_fd(fd); return -ENFILE; -- cgit v1.2.3 From 85fe4025c616a7c0ed07bc2fc8c5371b07f3888c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 Oct 2010 11:19:54 -0400 Subject: fs: do not assign default i_ino in new_inode Instead of always assigning an increasing inode number in new_inode move the call to assign it into those callers that actually need it. For now callers that need it is estimated conservatively, that is the call is added to all filesystems that do not assign an i_ino by themselves. For a few more filesystems we can avoid assigning any inode number given that they aren't user visible, and for others it could be done lazily when an inode number is actually needed, but that's left for later patches. Signed-off-by: Christoph Hellwig Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- drivers/infiniband/hw/ipath/ipath_fs.c | 1 + drivers/infiniband/hw/qib/qib_fs.c | 1 + drivers/misc/ibmasm/ibmasmfs.c | 1 + drivers/oprofile/oprofilefs.c | 1 + drivers/usb/core/inode.c | 1 + drivers/usb/gadget/f_fs.c | 1 + drivers/usb/gadget/inode.c | 1 + fs/anon_inodes.c | 1 + fs/autofs4/inode.c | 1 + fs/binfmt_misc.c | 1 + fs/configfs/inode.c | 1 + fs/debugfs/inode.c | 1 + fs/ext4/mballoc.c | 1 + fs/freevxfs/vxfs_inode.c | 1 + fs/fuse/control.c | 1 + fs/hugetlbfs/inode.c | 1 + fs/inode.c | 4 ++-- fs/ocfs2/dlmfs/dlmfs.c | 2 ++ fs/pipe.c | 2 ++ fs/proc/base.c | 2 ++ fs/proc/proc_sysctl.c | 2 ++ fs/ramfs/inode.c | 1 + fs/xfs/linux-2.6/xfs_buf.c | 1 + include/linux/fs.h | 1 + ipc/mqueue.c | 1 + kernel/cgroup.c | 1 + mm/shmem.c | 1 + net/socket.c | 1 + net/sunrpc/rpc_pipe.c | 1 + security/inode.c | 1 + security/selinux/selinuxfs.c | 1 + 31 files changed, 36 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c index d13e72685dcf..12d5bf76302c 100644 --- a/drivers/infiniband/hw/ipath/ipath_fs.c +++ b/drivers/infiniband/hw/ipath/ipath_fs.c @@ -57,6 +57,7 @@ static int ipathfs_mknod(struct inode *dir, struct dentry *dentry, goto bail; } + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_private = data; diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c index a0e6613e8be6..7e433d75c775 100644 --- a/drivers/infiniband/hw/qib/qib_fs.c +++ b/drivers/infiniband/hw/qib/qib_fs.c @@ -58,6 +58,7 @@ static int qibfs_mknod(struct inode *dir, struct dentry *dentry, goto bail; } + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = 0; inode->i_gid = 0; diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c index af2497ae5fe3..0a53500636c9 100644 --- a/drivers/misc/ibmasm/ibmasmfs.c +++ b/drivers/misc/ibmasm/ibmasmfs.c @@ -146,6 +146,7 @@ static struct inode *ibmasmfs_make_inode(struct super_block *sb, int mode) struct inode *ret = new_inode(sb); if (ret) { + ret->i_ino = get_next_ino(); ret->i_mode = mode; ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME; } diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c index 95f711b251ad..449de59bf35b 100644 --- a/drivers/oprofile/oprofilefs.c +++ b/drivers/oprofile/oprofilefs.c @@ -28,6 +28,7 @@ static struct inode *oprofilefs_get_inode(struct super_block *sb, int mode) struct inode *inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; } diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c index 095fa5366690..e2f63c0ea09d 100644 --- a/drivers/usb/core/inode.c +++ b/drivers/usb/core/inode.c @@ -276,6 +276,7 @@ static struct inode *usbfs_get_inode (struct super_block *sb, int mode, dev_t de struct inode *inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c index e4f595055208..e093fd8d04d3 100644 --- a/drivers/usb/gadget/f_fs.c +++ b/drivers/usb/gadget/f_fs.c @@ -980,6 +980,7 @@ ffs_sb_make_inode(struct super_block *sb, void *data, if (likely(inode)) { struct timespec current_time = CURRENT_TIME; + inode->i_ino = usbfs_get_inode(); inode->i_mode = perms->mode; inode->i_uid = perms->uid; inode->i_gid = perms->gid; diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index d1d72d946b04..ba145e7fbe03 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -1991,6 +1991,7 @@ gadgetfs_make_inode (struct super_block *sb, struct inode *inode = new_inode (sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = default_uid; inode->i_gid = default_gid; diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 9c8e87b0361f..5365527ca43f 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -193,6 +193,7 @@ static struct inode *anon_inode_mkinode(void) if (!inode) return ERR_PTR(-ENOMEM); + inode->i_ino = get_next_ino(); inode->i_fop = &anon_inode_fops; inode->i_mapping->a_ops = &anon_aops; diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index 821b2b955dac..ac87e49fa706 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -398,6 +398,7 @@ struct inode *autofs4_get_inode(struct super_block *sb, inode->i_gid = sb->s_root->d_inode->i_gid; } inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + inode->i_ino = get_next_ino(); if (S_ISDIR(inf->mode)) { inode->i_nlink = 2; diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 139fc8083f53..29990f0eee0c 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -495,6 +495,7 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) struct inode * inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = current_fs_time(inode->i_sb); diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index cf78d44a8d6a..253476d78ed8 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -135,6 +135,7 @@ struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent * sd) { struct inode * inode = new_inode(configfs_sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mapping->a_ops = &configfs_aops; inode->i_mapping->backing_dev_info = &configfs_backing_dev_info; inode->i_op = &configfs_inode_operations; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 30a87b3dbcac..a4ed8380e98a 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -40,6 +40,7 @@ static struct inode *debugfs_get_inode(struct super_block *sb, int mode, dev_t d struct inode *inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 19aa0d44d822..42f77b1dc72d 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2373,6 +2373,7 @@ static int ext4_mb_init_backend(struct super_block *sb) printk(KERN_ERR "EXT4-fs: can't get new inode\n"); goto err_freesgi; } + sbi->s_buddy_cache->i_ino = get_next_ino(); EXT4_I(sbi->s_buddy_cache)->i_disksize = 0; for (i = 0; i < ngroups; i++) { desc = ext4_get_group_desc(sb, i, NULL); diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index 79d1b4ea13e7..8c04eac5079d 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -260,6 +260,7 @@ vxfs_get_fake_inode(struct super_block *sbp, struct vxfs_inode_info *vip) struct inode *ip = NULL; if ((ip = new_inode(sbp))) { + ip->i_ino = get_next_ino(); vxfs_iinit(ip, vip); ip->i_mapping->a_ops = &vxfs_aops; } diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 7367e177186f..4eba07661e5c 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -222,6 +222,7 @@ static struct dentry *fuse_ctl_add_dentry(struct dentry *parent, if (!inode) return NULL; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = fc->user_id; inode->i_gid = fc->group_id; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 113eba3d3c38..8d0607b37266 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -455,6 +455,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, inode = new_inode(sb); if (inode) { struct hugetlbfs_inode_info *info; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = uid; inode->i_gid = gid; diff --git a/fs/inode.c b/fs/inode.c index 46a3e120b196..2cd2e48f7a20 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -735,7 +735,7 @@ repeat: #define LAST_INO_BATCH 1024 static DEFINE_PER_CPU(unsigned int, last_ino); -static unsigned int get_next_ino(void) +unsigned int get_next_ino(void) { unsigned int *p = &get_cpu_var(last_ino); unsigned int res = *p; @@ -753,6 +753,7 @@ static unsigned int get_next_ino(void) put_cpu_var(last_ino); return res; } +EXPORT_SYMBOL(get_next_ino); /** * new_inode - obtain an inode @@ -776,7 +777,6 @@ struct inode *new_inode(struct super_block *sb) if (inode) { spin_lock(&inode_lock); __inode_sb_list_add(inode); - inode->i_ino = get_next_ino(); inode->i_state = 0; spin_unlock(&inode_lock); } diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index a7ebd9d42dc8..75e115f1bd73 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -400,6 +400,7 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) if (inode) { ip = DLMFS_I(inode); + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); @@ -425,6 +426,7 @@ static struct inode *dlmfs_get_inode(struct inode *parent, if (!inode) return NULL; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); diff --git a/fs/pipe.c b/fs/pipe.c index 37eb1ebeaa90..d2d7566ce68e 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -954,6 +954,8 @@ static struct inode * get_pipe_inode(void) if (!inode) goto fail_inode; + inode->i_ino = get_next_ino(); + pipe = alloc_pipe_info(inode); if (!pipe) goto fail_iput; diff --git a/fs/proc/base.c b/fs/proc/base.c index fb2a5abd4e4f..9883f1e18332 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1603,6 +1603,7 @@ static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_st /* Common stuff */ ei = PROC_I(inode); + inode->i_ino = get_next_ino(); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; inode->i_op = &proc_def_inode_operations; @@ -2549,6 +2550,7 @@ static struct dentry *proc_base_instantiate(struct inode *dir, /* Initialize the inode */ ei = PROC_I(inode); + inode->i_ino = get_next_ino(); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; /* diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 2fc52552271d..b652cb00906b 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -23,6 +23,8 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, if (!inode) goto out; + inode->i_ino = get_next_ino(); + sysctl_head_get(head); ei = PROC_I(inode); ei->sysctl = head; diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index a5ebae70dc6d..67fadb1ad2c1 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -58,6 +58,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, struct inode * inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode_init_owner(inode, dir, mode); inode->i_mapping->a_ops = &ramfs_aops; inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info; diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index ba5312802aa9..63fd2c07cb57 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -1580,6 +1580,7 @@ xfs_mapping_buftarg( XFS_BUFTARG_NAME(btp)); return ENOMEM; } + inode->i_ino = get_next_ino(); inode->i_mode = S_IFBLK; inode->i_bdev = bdev; inode->i_rdev = bdev->bd_dev; diff --git a/include/linux/fs.h b/include/linux/fs.h index bd6ae6c71fc8..4a573cf13f51 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2191,6 +2191,7 @@ extern struct inode * iget_locked(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); extern void unlock_new_inode(struct inode *); +extern unsigned int get_next_ino(void); extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 80b35ffca25d..3a61ffefe884 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -116,6 +116,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb, inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7b69b8d0313d..9270d532ec3c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -777,6 +777,7 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) struct inode *inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); diff --git a/mm/shmem.c b/mm/shmem.c index d4e2852526e6..f6d350e8adc5 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1586,6 +1586,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode_init_owner(inode, dir, mode); inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &shmem_backing_dev_info; diff --git a/net/socket.c b/net/socket.c index d223725f99e5..5cac1c707755 100644 --- a/net/socket.c +++ b/net/socket.c @@ -480,6 +480,7 @@ static struct socket *sock_alloc(void) sock = SOCKET_I(inode); kmemcheck_annotate_bitfield(sock, type); + inode->i_ino = get_next_ino(); inode->i_mode = S_IFSOCK | S_IRWXUGO; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 52f252432144..7df92d237cb8 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -445,6 +445,7 @@ rpc_get_inode(struct super_block *sb, umode_t mode) struct inode *inode = new_inode(sb); if (!inode) return NULL; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch(mode & S_IFMT) { diff --git a/security/inode.c b/security/inode.c index 88839866cbcd..cb8f47c66a58 100644 --- a/security/inode.c +++ b/security/inode.c @@ -61,6 +61,7 @@ static struct inode *get_inode(struct super_block *sb, int mode, dev_t dev) struct inode *inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 87e0556bae70..55a755c1a1bd 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -978,6 +978,7 @@ static struct inode *sel_make_inode(struct super_block *sb, int mode) struct inode *ret = new_inode(sb); if (ret) { + ret->i_ino = get_next_ino(); ret->i_mode = mode; ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME; } -- cgit v1.2.3 From 312d3ca856d369bb04d0443846b85b4cdde6fa8a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 10 Oct 2010 05:36:23 -0400 Subject: fs: use percpu counter for nr_dentry and nr_dentry_unused The nr_dentry stat is a globally touched cacheline and atomic operation twice over the lifetime of a dentry. It is used for the benfit of userspace only. Turn it into a per-cpu counter and always decrement it in d_free instead of doing various batching operations to reduce lock hold times in the callers. Based on an earlier patch from Nick Piggin . Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/dcache.c | 51 ++++++++++++++++++++++++++++++++------------------- include/linux/fs.h | 2 ++ kernel/sysctl.c | 2 +- 3 files changed, 35 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/fs/dcache.c b/fs/dcache.c index 028753951e95..c37a656802b0 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -67,6 +67,19 @@ struct dentry_stat_t dentry_stat = { .age_limit = 45, }; +static struct percpu_counter nr_dentry __cacheline_aligned_in_smp; +static struct percpu_counter nr_dentry_unused __cacheline_aligned_in_smp; + +#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) +int proc_nr_dentry(ctl_table *table, int write, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + dentry_stat.nr_dentry = percpu_counter_sum_positive(&nr_dentry); + dentry_stat.nr_unused = percpu_counter_sum_positive(&nr_dentry_unused); + return proc_dointvec(table, write, buffer, lenp, ppos); +} +#endif + static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); @@ -78,13 +91,14 @@ static void __d_free(struct rcu_head *head) } /* - * no dcache_lock, please. The caller must decrement dentry_stat.nr_dentry - * inside dcache_lock. + * no dcache_lock, please. */ static void d_free(struct dentry *dentry) { + percpu_counter_dec(&nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); + /* if dentry was never inserted into hash, immediate free is OK */ if (hlist_unhashed(&dentry->d_hash)) __d_free(&dentry->d_u.d_rcu); @@ -125,14 +139,14 @@ static void dentry_lru_add(struct dentry *dentry) { list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru); dentry->d_sb->s_nr_dentry_unused++; - dentry_stat.nr_unused++; + percpu_counter_inc(&nr_dentry_unused); } static void dentry_lru_add_tail(struct dentry *dentry) { list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru); dentry->d_sb->s_nr_dentry_unused++; - dentry_stat.nr_unused++; + percpu_counter_inc(&nr_dentry_unused); } static void dentry_lru_del(struct dentry *dentry) @@ -140,7 +154,7 @@ static void dentry_lru_del(struct dentry *dentry) if (!list_empty(&dentry->d_lru)) { list_del(&dentry->d_lru); dentry->d_sb->s_nr_dentry_unused--; - dentry_stat.nr_unused--; + percpu_counter_dec(&nr_dentry_unused); } } @@ -149,7 +163,7 @@ static void dentry_lru_del_init(struct dentry *dentry) if (likely(!list_empty(&dentry->d_lru))) { list_del_init(&dentry->d_lru); dentry->d_sb->s_nr_dentry_unused--; - dentry_stat.nr_unused--; + percpu_counter_dec(&nr_dentry_unused); } } @@ -168,7 +182,6 @@ static struct dentry *d_kill(struct dentry *dentry) struct dentry *parent; list_del(&dentry->d_u.d_child); - dentry_stat.nr_dentry--; /* For d_free, below */ /*drops the locks, at that point nobody can reach this dentry */ dentry_iput(dentry); if (IS_ROOT(dentry)) @@ -314,7 +327,6 @@ int d_invalidate(struct dentry * dentry) EXPORT_SYMBOL(d_invalidate); /* This should be called _only_ with dcache_lock held */ - static inline struct dentry * __dget_locked(struct dentry *dentry) { atomic_inc(&dentry->d_count); @@ -534,7 +546,7 @@ static void prune_dcache(int count) { struct super_block *sb, *p = NULL; int w_count; - int unused = dentry_stat.nr_unused; + int unused = percpu_counter_sum_positive(&nr_dentry_unused); int prune_ratio; int pruned; @@ -699,20 +711,13 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) * otherwise we ascend to the parent and move to the * next sibling if there is one */ if (!parent) - goto out; - + return; dentry = parent; - } while (list_empty(&dentry->d_subdirs)); dentry = list_entry(dentry->d_subdirs.next, struct dentry, d_u.d_child); } -out: - /* several dentries were freed, need to correct nr_dentry */ - spin_lock(&dcache_lock); - dentry_stat.nr_dentry -= detached; - spin_unlock(&dcache_lock); } /* @@ -896,12 +901,16 @@ EXPORT_SYMBOL(shrink_dcache_parent); */ static int shrink_dcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) { + int nr_unused; + if (nr) { if (!(gfp_mask & __GFP_FS)) return -1; prune_dcache(nr); } - return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure; + + nr_unused = percpu_counter_sum_positive(&nr_dentry_unused); + return (nr_unused / 100) * sysctl_vfs_cache_pressure; } static struct shrinker dcache_shrinker = { @@ -968,9 +977,10 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) spin_lock(&dcache_lock); if (parent) list_add(&dentry->d_u.d_child, &parent->d_subdirs); - dentry_stat.nr_dentry++; spin_unlock(&dcache_lock); + percpu_counter_inc(&nr_dentry); + return dentry; } EXPORT_SYMBOL(d_alloc); @@ -2417,6 +2427,9 @@ static void __init dcache_init(void) { int loop; + percpu_counter_init(&nr_dentry, 0); + percpu_counter_init(&nr_dentry_unused, 0); + /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature diff --git a/include/linux/fs.h b/include/linux/fs.h index 4a573cf13f51..d58059944801 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2490,6 +2490,8 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, struct ctl_table; int proc_nr_files(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +int proc_nr_dentry(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); int proc_nr_inodes(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 99a510cbfbb3..8b77ff5c502c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1377,7 +1377,7 @@ static struct ctl_table fs_table[] = { .data = &dentry_stat, .maxlen = 6*sizeof(int), .mode = 0444, - .proc_handler = proc_dointvec, + .proc_handler = proc_nr_dentry, }, { .procname = "overflowuid", -- cgit v1.2.3