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/sysctl.c') 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/sysctl.c') 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 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/sysctl.c') 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