static struct kmem_cache *ext4_es_cachep;
-static int __es_insert_extent(struct ext4_es_tree *tree,
- struct extent_status *newes);
-static int __es_remove_extent(struct ext4_es_tree *tree, ext4_lblk_t lblk,
+static int __es_insert_extent(struct inode *inode, struct extent_status *newes);
+static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t end);
+static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
+ int nr_to_scan);
int __init ext4_init_es(void)
{
- ext4_es_cachep = KMEM_CACHE(extent_status, SLAB_RECLAIM_ACCOUNT);
+ ext4_es_cachep = kmem_cache_create("ext4_extent_status",
+ sizeof(struct extent_status),
+ 0, (SLAB_RECLAIM_ACCOUNT), NULL);
if (ext4_es_cachep == NULL)
return -ENOMEM;
return 0;
read_unlock(&EXT4_I(inode)->i_es_lock);
+ ext4_es_lru_add(inode);
trace_ext4_es_find_delayed_extent_exit(inode, es);
}
static struct extent_status *
-ext4_es_alloc_extent(ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk)
+ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len,
+ ext4_fsblk_t pblk)
{
struct extent_status *es;
es = kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC);
es->es_lblk = lblk;
es->es_len = len;
es->es_pblk = pblk;
+
+ /*
+ * We don't count delayed extent because we never try to reclaim them
+ */
+ if (!ext4_es_is_delayed(es)) {
+ EXT4_I(inode)->i_es_lru_nr++;
+ percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
+ }
+
return es;
}
-static void ext4_es_free_extent(struct extent_status *es)
+static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
{
+ /* Decrease the lru counter when this es is not delayed */
+ if (!ext4_es_is_delayed(es)) {
+ BUG_ON(EXT4_I(inode)->i_es_lru_nr == 0);
+ EXT4_I(inode)->i_es_lru_nr--;
+ percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
+ }
+
kmem_cache_free(ext4_es_cachep, es);
}
}
static struct extent_status *
-ext4_es_try_to_merge_left(struct ext4_es_tree *tree, struct extent_status *es)
+ext4_es_try_to_merge_left(struct inode *inode, struct extent_status *es)
{
+ struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
struct extent_status *es1;
struct rb_node *node;
if (ext4_es_can_be_merged(es1, es)) {
es1->es_len += es->es_len;
rb_erase(&es->rb_node, &tree->root);
- ext4_es_free_extent(es);
+ ext4_es_free_extent(inode, es);
es = es1;
}
}
static struct extent_status *
-ext4_es_try_to_merge_right(struct ext4_es_tree *tree, struct extent_status *es)
+ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es)
{
+ struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
struct extent_status *es1;
struct rb_node *node;
if (ext4_es_can_be_merged(es, es1)) {
es->es_len += es1->es_len;
rb_erase(node, &tree->root);
- ext4_es_free_extent(es1);
+ ext4_es_free_extent(inode, es1);
}
return es;
}
-static int __es_insert_extent(struct ext4_es_tree *tree,
- struct extent_status *newes)
+static int __es_insert_extent(struct inode *inode, struct extent_status *newes)
{
+ struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
struct rb_node **p = &tree->root.rb_node;
struct rb_node *parent = NULL;
struct extent_status *es;
ext4_es_is_unwritten(es))
ext4_es_store_pblock(es,
newes->es_pblk);
- es = ext4_es_try_to_merge_left(tree, es);
+ es = ext4_es_try_to_merge_left(inode, es);
goto out;
}
p = &(*p)->rb_left;
} else if (newes->es_lblk > ext4_es_end(es)) {
if (ext4_es_can_be_merged(es, newes)) {
es->es_len += newes->es_len;
- es = ext4_es_try_to_merge_right(tree, es);
+ es = ext4_es_try_to_merge_right(inode, es);
goto out;
}
p = &(*p)->rb_right;
}
}
- es = ext4_es_alloc_extent(newes->es_lblk, newes->es_len,
+ es = ext4_es_alloc_extent(inode, newes->es_lblk, newes->es_len,
newes->es_pblk);
if (!es)
return -ENOMEM;
ext4_lblk_t len, ext4_fsblk_t pblk,
unsigned long long status)
{
- struct ext4_es_tree *tree;
struct extent_status newes;
ext4_lblk_t end = lblk + len - 1;
int err = 0;
es_debug("add [%u/%u) %llu %llx to extent status tree of inode %lu\n",
lblk, len, pblk, status, inode->i_ino);
+ if (!len)
+ return 0;
+
BUG_ON(end < lblk);
newes.es_lblk = lblk;
trace_ext4_es_insert_extent(inode, &newes);
write_lock(&EXT4_I(inode)->i_es_lock);
- tree = &EXT4_I(inode)->i_es_tree;
- err = __es_remove_extent(tree, lblk, end);
+ err = __es_remove_extent(inode, lblk, end);
if (err != 0)
goto error;
- err = __es_insert_extent(tree, &newes);
+ err = __es_insert_extent(inode, &newes);
error:
write_unlock(&EXT4_I(inode)->i_es_lock);
+ ext4_es_lru_add(inode);
ext4_es_print_tree(inode);
return err;
}
-static int __es_remove_extent(struct ext4_es_tree *tree, ext4_lblk_t lblk,
- ext4_lblk_t end)
+/*
+ * ext4_es_lookup_extent() looks up an extent in extent status tree.
+ *
+ * ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks.
+ *
+ * Return: 1 on found, 0 on not
+ */
+int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
+ struct extent_status *es)
+{
+ struct ext4_es_tree *tree;
+ struct extent_status *es1 = NULL;
+ struct rb_node *node;
+ int found = 0;
+
+ trace_ext4_es_lookup_extent_enter(inode, lblk);
+ es_debug("lookup extent in block %u\n", lblk);
+
+ tree = &EXT4_I(inode)->i_es_tree;
+ read_lock(&EXT4_I(inode)->i_es_lock);
+
+ /* find extent in cache firstly */
+ es->es_lblk = es->es_len = es->es_pblk = 0;
+ if (tree->cache_es) {
+ es1 = tree->cache_es;
+ if (in_range(lblk, es1->es_lblk, es1->es_len)) {
+ es_debug("%u cached by [%u/%u)\n",
+ lblk, es1->es_lblk, es1->es_len);
+ found = 1;
+ goto out;
+ }
+ }
+
+ node = tree->root.rb_node;
+ while (node) {
+ es1 = rb_entry(node, struct extent_status, rb_node);
+ if (lblk < es1->es_lblk)
+ node = node->rb_left;
+ else if (lblk > ext4_es_end(es1))
+ node = node->rb_right;
+ else {
+ found = 1;
+ break;
+ }
+ }
+
+out:
+ if (found) {
+ BUG_ON(!es1);
+ es->es_lblk = es1->es_lblk;
+ es->es_len = es1->es_len;
+ es->es_pblk = es1->es_pblk;
+ }
+
+ read_unlock(&EXT4_I(inode)->i_es_lock);
+
+ ext4_es_lru_add(inode);
+ trace_ext4_es_lookup_extent_exit(inode, es, found);
+ return found;
+}
+
+static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t end)
{
+ struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
struct rb_node *node;
struct extent_status *es;
struct extent_status orig_es;
ext4_es_store_pblock(&newes, block);
}
ext4_es_store_status(&newes, ext4_es_status(&orig_es));
- err = __es_insert_extent(tree, &newes);
+ err = __es_insert_extent(inode, &newes);
if (err) {
es->es_lblk = orig_es.es_lblk;
es->es_len = orig_es.es_len;
while (es && ext4_es_end(es) <= end) {
node = rb_next(&es->rb_node);
rb_erase(&es->rb_node, &tree->root);
- ext4_es_free_extent(es);
+ ext4_es_free_extent(inode, es);
if (!node) {
es = NULL;
break;
int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len)
{
- struct ext4_es_tree *tree;
ext4_lblk_t end;
int err = 0;
es_debug("remove [%u/%u) from extent status tree of inode %lu\n",
lblk, len, inode->i_ino);
+ if (!len)
+ return err;
+
end = lblk + len - 1;
BUG_ON(end < lblk);
- tree = &EXT4_I(inode)->i_es_tree;
-
write_lock(&EXT4_I(inode)->i_es_lock);
- err = __es_remove_extent(tree, lblk, end);
+ err = __es_remove_extent(inode, lblk, end);
write_unlock(&EXT4_I(inode)->i_es_lock);
ext4_es_print_tree(inode);
return err;
}
+
+static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
+{
+ struct ext4_sb_info *sbi = container_of(shrink,
+ struct ext4_sb_info, s_es_shrinker);
+ struct ext4_inode_info *ei;
+ struct list_head *cur, *tmp, scanned;
+ int nr_to_scan = sc->nr_to_scan;
+ int ret, nr_shrunk = 0;
+
+ ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
+ trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret);
+
+ if (!nr_to_scan)
+ return ret;
+
+ INIT_LIST_HEAD(&scanned);
+
+ spin_lock(&sbi->s_es_lru_lock);
+ list_for_each_safe(cur, tmp, &sbi->s_es_lru) {
+ list_move_tail(cur, &scanned);
+
+ ei = list_entry(cur, struct ext4_inode_info, i_es_lru);
+
+ read_lock(&ei->i_es_lock);
+ if (ei->i_es_lru_nr == 0) {
+ read_unlock(&ei->i_es_lock);
+ continue;
+ }
+ read_unlock(&ei->i_es_lock);
+
+ write_lock(&ei->i_es_lock);
+ ret = __es_try_to_reclaim_extents(ei, nr_to_scan);
+ write_unlock(&ei->i_es_lock);
+
+ nr_shrunk += ret;
+ nr_to_scan -= ret;
+ if (nr_to_scan == 0)
+ break;
+ }
+ list_splice_tail(&scanned, &sbi->s_es_lru);
+ spin_unlock(&sbi->s_es_lru_lock);
+
+ ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
+ trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret);
+ return ret;
+}
+
+void ext4_es_register_shrinker(struct super_block *sb)
+{
+ struct ext4_sb_info *sbi;
+
+ sbi = EXT4_SB(sb);
+ INIT_LIST_HEAD(&sbi->s_es_lru);
+ spin_lock_init(&sbi->s_es_lru_lock);
+ sbi->s_es_shrinker.shrink = ext4_es_shrink;
+ sbi->s_es_shrinker.seeks = DEFAULT_SEEKS;
+ register_shrinker(&sbi->s_es_shrinker);
+}
+
+void ext4_es_unregister_shrinker(struct super_block *sb)
+{
+ unregister_shrinker(&EXT4_SB(sb)->s_es_shrinker);
+}
+
+void ext4_es_lru_add(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ spin_lock(&sbi->s_es_lru_lock);
+ if (list_empty(&ei->i_es_lru))
+ list_add_tail(&ei->i_es_lru, &sbi->s_es_lru);
+ else
+ list_move_tail(&ei->i_es_lru, &sbi->s_es_lru);
+ spin_unlock(&sbi->s_es_lru_lock);
+}
+
+void ext4_es_lru_del(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ spin_lock(&sbi->s_es_lru_lock);
+ if (!list_empty(&ei->i_es_lru))
+ list_del_init(&ei->i_es_lru);
+ spin_unlock(&sbi->s_es_lru_lock);
+}
+
+static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
+ int nr_to_scan)
+{
+ struct inode *inode = &ei->vfs_inode;
+ struct ext4_es_tree *tree = &ei->i_es_tree;
+ struct rb_node *node;
+ struct extent_status *es;
+ int nr_shrunk = 0;
+
+ if (ei->i_es_lru_nr == 0)
+ return 0;
+
+ node = rb_first(&tree->root);
+ while (node != NULL) {
+ es = rb_entry(node, struct extent_status, rb_node);
+ node = rb_next(&es->rb_node);
+ /*
+ * We can't reclaim delayed extent from status tree because
+ * fiemap, bigallic, and seek_data/hole need to use it.
+ */
+ if (!ext4_es_is_delayed(es)) {
+ rb_erase(&es->rb_node, &tree->root);
+ ext4_es_free_extent(inode, es);
+ nr_shrunk++;
+ if (--nr_to_scan == 0)
+ break;
+ }
+ }
+ tree->cache_es = NULL;
+ return nr_shrunk;
+}
projects / karo-tx-linux.git / blobdiff