*
* inode->i_lock protects:
* inode->i_state, inode->i_hash, __iget()
- * inode_lru_lock protects:
- * inode_lru, inode->i_lru
+ * inode->i_sb->s_inode_lru_lock protects:
+ * inode->i_sb->s_inode_lru, inode->i_lru
* inode_sb_list_lock protects:
* sb->s_inodes, inode->i_sb_list
* inode_wb_list_lock protects:
*
* inode_sb_list_lock
* inode->i_lock
- * inode_lru_lock
+ * inode->i_sb->s_inode_lru_lock
*
* inode_wb_list_lock
* inode->i_lock
static struct hlist_head *inode_hashtable __read_mostly;
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
-static LIST_HEAD(inode_lru);
-static DEFINE_SPINLOCK(inode_lru_lock);
-
__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);
__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_wb_list_lock);
struct inodes_stat_t inodes_stat;
static DEFINE_PER_CPU(unsigned int, nr_inodes);
+static DEFINE_PER_CPU(unsigned int, nr_unused);
static struct kmem_cache *inode_cachep __read_mostly;
static inline int get_nr_inodes_unused(void)
{
- return inodes_stat.nr_unused;
+ int i;
+ int sum = 0;
+ for_each_possible_cpu(i)
+ sum += per_cpu(nr_unused, i);
+ return sum < 0 ? 0 : sum;
}
int get_nr_dirty_inodes(void)
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 inode_lru_list_add(struct inode *inode)
{
- spin_lock(&inode_lru_lock);
+ spin_lock(&inode->i_sb->s_inode_lru_lock);
if (list_empty(&inode->i_lru)) {
- list_add(&inode->i_lru, &inode_lru);
- inodes_stat.nr_unused++;
+ list_add(&inode->i_lru, &inode->i_sb->s_inode_lru);
+ inode->i_sb->s_nr_inodes_unused++;
+ this_cpu_inc(nr_unused);
}
- spin_unlock(&inode_lru_lock);
+ spin_unlock(&inode->i_sb->s_inode_lru_lock);
}
static void inode_lru_list_del(struct inode *inode)
{
- spin_lock(&inode_lru_lock);
+ spin_lock(&inode->i_sb->s_inode_lru_lock);
if (!list_empty(&inode->i_lru)) {
list_del_init(&inode->i_lru);
- inodes_stat.nr_unused--;
+ inode->i_sb->s_nr_inodes_unused--;
+ this_cpu_dec(nr_unused);
}
- spin_unlock(&inode_lru_lock);
+ spin_unlock(&inode->i_sb->s_inode_lru_lock);
}
/**
/*
* Scan `goal' inodes on the unused list for freeable ones. They are moved to a
- * temporary list and then are freed outside inode_lru_lock by dispose_list().
+ * temporary list and then are freed outside sb->s_inode_lru_lock by
+ * dispose_list().
*
* Any inodes which are pinned purely because of attached pagecache have their
* pagecache removed. If the inode has metadata buffers attached to
* LRU does not have strict ordering. Hence we don't want to reclaim inodes
* with this flag set because they are the inodes that are out of order.
*/
-static void prune_icache(int nr_to_scan)
+static void shrink_icache_sb(struct super_block *sb, int *nr_to_scan)
{
LIST_HEAD(freeable);
int nr_scanned;
unsigned long reap = 0;
- down_read(&iprune_sem);
- spin_lock(&inode_lru_lock);
- for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) {
+ spin_lock(&sb->s_inode_lru_lock);
+ for (nr_scanned = *nr_to_scan; nr_scanned >= 0; nr_scanned--) {
struct inode *inode;
- if (list_empty(&inode_lru))
+ if (list_empty(&sb->s_inode_lru))
break;
- inode = list_entry(inode_lru.prev, struct inode, i_lru);
+ inode = list_entry(sb->s_inode_lru.prev, struct inode, i_lru);
/*
- * we are inverting the inode_lru_lock/inode->i_lock here,
+ * 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, &inode_lru);
+ list_move(&inode->i_lru, &sb->s_inode_lru);
continue;
}
(inode->i_state & ~I_REFERENCED)) {
list_del_init(&inode->i_lru);
spin_unlock(&inode->i_lock);
- inodes_stat.nr_unused--;
+ sb->s_nr_inodes_unused--;
+ this_cpu_dec(nr_unused);
continue;
}
/* recently referenced inodes get one more pass */
if (inode->i_state & I_REFERENCED) {
inode->i_state &= ~I_REFERENCED;
- list_move(&inode->i_lru, &inode_lru);
+ 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(&inode_lru_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(&inode_lru_lock);
+ spin_lock(&sb->s_inode_lru_lock);
- if (inode != list_entry(inode_lru.next,
+ if (inode != list_entry(sb->s_inode_lru.next,
struct inode, i_lru))
continue; /* wrong inode or list_empty */
/* avoid lock inversions with trylock */
spin_unlock(&inode->i_lock);
list_move(&inode->i_lru, &freeable);
- inodes_stat.nr_unused--;
+ 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(&inode_lru_lock);
+ spin_unlock(&sb->s_inode_lru_lock);
+ *nr_to_scan = nr_scanned;
dispose_list(&freeable);
+}
+
+static void prune_icache(int count)
+{
+ struct super_block *sb, *p = NULL;
+ int w_count;
+ int unused = inodes_stat.nr_unused;
+ int prune_ratio;
+ int pruned;
+
+ if (unused == 0 || count == 0)
+ return;
+ down_read(&iprune_sem);
+ if (count >= unused)
+ prune_ratio = 1;
+ else
+ prune_ratio = unused / count;
+ spin_lock(&sb_lock);
+ list_for_each_entry(sb, &super_blocks, s_list) {
+ if (list_empty(&sb->s_instances))
+ continue;
+ if (sb->s_nr_inodes_unused == 0)
+ continue;
+ sb->s_count++;
+ /* Now, we reclaim unused dentrins with fairness.
+ * We reclaim them same percentage from each superblock.
+ * We calculate number of dentries to scan on this sb
+ * as follows, but the implementation is arranged to avoid
+ * overflows:
+ * number of dentries to scan on this sb =
+ * count * (number of dentries on this sb /
+ * number of dentries in the machine)
+ */
+ spin_unlock(&sb_lock);
+ if (prune_ratio != 1)
+ w_count = (sb->s_nr_inodes_unused / prune_ratio) + 1;
+ else
+ w_count = sb->s_nr_inodes_unused;
+ pruned = w_count;
+ /*
+ * We need to be sure this filesystem isn't being unmounted,
+ * otherwise we could race with generic_shutdown_super(), and
+ * end up holding a reference to an inode while the filesystem
+ * is unmounted. So we try to get s_umount, and make sure
+ * s_root isn't NULL.
+ */
+ if (down_read_trylock(&sb->s_umount)) {
+ if ((sb->s_root != NULL) &&
+ (!list_empty(&sb->s_dentry_lru))) {
+ shrink_icache_sb(sb, &w_count);
+ pruned -= w_count;
+ }
+ up_read(&sb->s_umount);
+ }
+ spin_lock(&sb_lock);
+ if (p)
+ __put_super(p);
+ count -= pruned;
+ p = sb;
+ /* more work left to do? */
+ if (count <= 0)
+ break;
+ }
+ if (p)
+ __put_super(p);
+ spin_unlock(&sb_lock);
up_read(&iprune_sem);
}
WARN_ON(inode->i_state & I_NEW);
- if (op && op->drop_inode)
+ if (op->drop_inode)
drop = op->drop_inode(inode);
else
drop = generic_drop_inode(inode);