*/
static struct kmem_cache *ext4_pspace_cachep;
static struct kmem_cache *ext4_ac_cachep;
+static struct kmem_cache *ext4_free_ext_cachep;
static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
ext4_group_t group);
static int ext4_mb_init_per_dev_proc(struct super_block *sb);
INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
init_rwsem(&meta_group_info[i]->alloc_sem);
+ meta_group_info[i]->bb_free_root.rb_node = NULL;;
#ifdef DOUBLE_CHECK
{
static noinline_for_stack void
ext4_mb_free_committed_blocks(struct super_block *sb)
{
- struct ext4_sb_info *sbi = EXT4_SB(sb);
- int err;
- int i;
- int count = 0;
- int count2 = 0;
- struct ext4_free_metadata *md;
struct ext4_buddy e4b;
+ struct ext4_group_info *db;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ int err, count = 0, count2 = 0;
+ struct ext4_free_data *entry;
if (list_empty(&sbi->s_committed_transaction))
return;
/* there is committed blocks to be freed yet */
do {
/* get next array of blocks */
- md = NULL;
+ entry = NULL;
spin_lock(&sbi->s_md_lock);
if (!list_empty(&sbi->s_committed_transaction)) {
- md = list_entry(sbi->s_committed_transaction.next,
- struct ext4_free_metadata, list);
- list_del(&md->list);
+ entry = list_entry(sbi->s_committed_transaction.next,
+ struct ext4_free_data, list);
+ list_del(&entry->list);
}
spin_unlock(&sbi->s_md_lock);
- if (md == NULL)
+ if (entry == NULL)
break;
mb_debug("gonna free %u blocks in group %lu (0x%p):",
- md->num, md->group, md);
+ entry->count, entry->group, entry);
- err = ext4_mb_load_buddy(sb, md->group, &e4b);
+ err = ext4_mb_load_buddy(sb, entry->group, &e4b);
/* we expect to find existing buddy because it's pinned */
BUG_ON(err != 0);
+ db = e4b.bd_info;
/* there are blocks to put in buddy to make them really free */
- count += md->num;
+ count += entry->count;
count2++;
- ext4_lock_group(sb, md->group);
- for (i = 0; i < md->num; i++) {
- mb_debug(" %u", md->blocks[i]);
- mb_free_blocks(NULL, &e4b, md->blocks[i], 1);
+ ext4_lock_group(sb, entry->group);
+ /* Take it out of per group rb tree */
+ rb_erase(&entry->node, &(db->bb_free_root));
+ mb_free_blocks(NULL, &e4b, entry->start_blk, entry->count);
+
+ if (!db->bb_free_root.rb_node) {
+ /* No more items in the per group rb tree
+ * balance refcounts from ext4_mb_free_metadata()
+ */
+ page_cache_release(e4b.bd_buddy_page);
+ page_cache_release(e4b.bd_bitmap_page);
}
- mb_debug("\n");
- ext4_unlock_group(sb, md->group);
-
- /* balance refcounts from ext4_mb_free_metadata() */
- page_cache_release(e4b.bd_buddy_page);
- page_cache_release(e4b.bd_bitmap_page);
+ ext4_unlock_group(sb, entry->group);
- kfree(md);
+ kmem_cache_free(ext4_free_ext_cachep, entry);
ext4_mb_release_desc(&e4b);
-
- } while (md);
+ } while (1);
mb_debug("freed %u blocks in %u structures\n", count, count2);
}
kmem_cache_destroy(ext4_pspace_cachep);
return -ENOMEM;
}
+
+ ext4_free_ext_cachep =
+ kmem_cache_create("ext4_free_block_extents",
+ sizeof(struct ext4_free_data),
+ 0, SLAB_RECLAIM_ACCOUNT, NULL);
+ if (ext4_free_ext_cachep == NULL) {
+ kmem_cache_destroy(ext4_pspace_cachep);
+ kmem_cache_destroy(ext4_ac_cachep);
+ return -ENOMEM;
+ }
#ifdef CONFIG_PROC_FS
proc_root_ext4 = proc_mkdir("fs/ext4", NULL);
if (proc_root_ext4 == NULL)
#ifdef CONFIG_PROC_FS
remove_proc_entry("fs/ext4", NULL);
#endif
+ kmem_cache_destroy(ext4_free_ext_cachep);
}
ac->ac_criteria = 20;
return 1;
}
+
return 0;
}
ext4_mb_free_committed_blocks(sb);
}
+/*
+ * We can merge two free data extents only if the physical blocks
+ * are contiguous, AND the extents were freed by the same transaction,
+ * AND the blocks are associated with the same group.
+ */
+static int can_merge(struct ext4_free_data *entry1,
+ struct ext4_free_data *entry2)
+{
+ if ((entry1->t_tid == entry2->t_tid) &&
+ (entry1->group == entry2->group) &&
+ ((entry1->start_blk + entry1->count) == entry2->start_blk))
+ return 1;
+ return 0;
+}
+
static noinline_for_stack int
ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
ext4_group_t group, ext4_grpblk_t block, int count)
struct ext4_group_info *db = e4b->bd_info;
struct super_block *sb = e4b->bd_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_free_metadata *md;
- int i;
+ struct ext4_free_data *entry, *new_entry;
+ struct rb_node **n = &db->bb_free_root.rb_node, *node;
+ struct rb_node *parent = NULL, *new_node;
+
BUG_ON(e4b->bd_bitmap_page == NULL);
BUG_ON(e4b->bd_buddy_page == NULL);
+ new_entry = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
+ new_entry->start_blk = block;
+ new_entry->group = group;
+ new_entry->count = count;
+ new_entry->t_tid = handle->h_transaction->t_tid;
+ new_node = &new_entry->node;
+
ext4_lock_group(sb, group);
- for (i = 0; i < count; i++) {
- md = db->bb_md_cur;
- if (md && db->bb_tid != handle->h_transaction->t_tid) {
- db->bb_md_cur = NULL;
- md = NULL;
+ if (!*n) {
+ /* first free block exent. We need to
+ protect buddy cache from being freed,
+ * otherwise we'll refresh it from
+ * on-disk bitmap and lose not-yet-available
+ * blocks */
+ page_cache_get(e4b->bd_buddy_page);
+ page_cache_get(e4b->bd_bitmap_page);
+ }
+ while (*n) {
+ parent = *n;
+ entry = rb_entry(parent, struct ext4_free_data, node);
+ if (block < entry->start_blk)
+ n = &(*n)->rb_left;
+ else if (block >= (entry->start_blk + entry->count))
+ n = &(*n)->rb_right;
+ else {
+ ext4_error(sb, __func__,
+ "Double free of blocks %d (%d %d)\n",
+ block, entry->start_blk, entry->count);
+ return 0;
}
+ }
- if (md == NULL) {
- ext4_unlock_group(sb, group);
- md = kmalloc(sizeof(*md), GFP_NOFS);
- if (md == NULL)
- return -ENOMEM;
- md->num = 0;
- md->group = group;
-
- ext4_lock_group(sb, group);
- if (db->bb_md_cur == NULL) {
- spin_lock(&sbi->s_md_lock);
- list_add(&md->list, &sbi->s_active_transaction);
- spin_unlock(&sbi->s_md_lock);
- /* protect buddy cache from being freed,
- * otherwise we'll refresh it from
- * on-disk bitmap and lose not-yet-available
- * blocks */
- page_cache_get(e4b->bd_buddy_page);
- page_cache_get(e4b->bd_bitmap_page);
- db->bb_md_cur = md;
- db->bb_tid = handle->h_transaction->t_tid;
- mb_debug("new md 0x%p for group %lu\n",
- md, md->group);
- } else {
- kfree(md);
- md = db->bb_md_cur;
- }
+ rb_link_node(new_node, parent, n);
+ rb_insert_color(new_node, &db->bb_free_root);
+
+ /* Now try to see the extent can be merged to left and right */
+ node = rb_prev(new_node);
+ if (node) {
+ entry = rb_entry(node, struct ext4_free_data, node);
+ if (can_merge(entry, new_entry)) {
+ new_entry->start_blk = entry->start_blk;
+ new_entry->count += entry->count;
+ rb_erase(node, &(db->bb_free_root));
+ spin_lock(&sbi->s_md_lock);
+ list_del(&entry->list);
+ spin_unlock(&sbi->s_md_lock);
+ kmem_cache_free(ext4_free_ext_cachep, entry);
}
+ }
- BUG_ON(md->num >= EXT4_BB_MAX_BLOCKS);
- md->blocks[md->num] = block + i;
- md->num++;
- if (md->num == EXT4_BB_MAX_BLOCKS) {
- /* no more space, put full container on a sb's list */
- db->bb_md_cur = NULL;
+ node = rb_next(new_node);
+ if (node) {
+ entry = rb_entry(node, struct ext4_free_data, node);
+ if (can_merge(new_entry, entry)) {
+ new_entry->count += entry->count;
+ rb_erase(node, &(db->bb_free_root));
+ spin_lock(&sbi->s_md_lock);
+ list_del(&entry->list);
+ spin_unlock(&sbi->s_md_lock);
+ kmem_cache_free(ext4_free_ext_cachep, entry);
}
}
+ /* Add the extent to active_transaction list */
+ spin_lock(&sbi->s_md_lock);
+ list_add(&new_entry->list, &sbi->s_active_transaction);
+ spin_unlock(&sbi->s_md_lock);
ext4_unlock_group(sb, group);
return 0;
}
projects / linux / commitdiff