Btrfs: Cache free inode numbers in memory

Currently btrfs stores the highest objectid of the fs tree, and it always
returns (highest+1) inode number when we create a file, so inode numbers
won't be reclaimed when we delete files, so we'll run out of inode numbers
as we keep create/delete files in 32bits machines.

This fixes it, and it works similarly to how we cache free space in block
cgroups.

We start a kernel thread to read the file tree. By scanning inode items,
we know which chunks of inode numbers are free, and we cache them in
an rb-tree.

Because we are searching the commit root, we have to carefully handle the
cross-transaction case.

The rb-tree is a hybrid extent+bitmap tree, so if we have too many small
chunks of inode numbers, we'll use bitmaps. Initially we allow 16K ram
of extents, and a bitmap will be used if we exceed this threshold. The
extents threshold is adjusted in runtime.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>

fs/btrfs/ctree.h

@@ -1102,6 +1102,15 @@ struct btrfs_root {
 	spinlock_t accounting_lock;
 	struct btrfs_block_rsv *block_rsv;
 
+	/* free ino cache stuff */
+	struct mutex fs_commit_mutex;
+	struct btrfs_free_space_ctl *free_ino_ctl;
+	enum btrfs_caching_type cached;
+	spinlock_t cache_lock;
+	wait_queue_head_t cache_wait;
+	struct btrfs_free_space_ctl *free_ino_pinned;
+	u64 cache_progress;
+
 	struct mutex log_mutex;
 	wait_queue_head_t log_writer_wait;
 	wait_queue_head_t log_commit_wait[2];
@@ -2408,12 +2417,6 @@ int btrfs_del_orphan_item(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root, u64 offset);
 int btrfs_find_orphan_item(struct btrfs_root *root, u64 offset);
 
-/* inode-map.c */
-int btrfs_find_free_objectid(struct btrfs_trans_handle *trans,
-			     struct btrfs_root *fs_root,
-			     u64 dirid, u64 *objectid);
-int btrfs_find_highest_inode(struct btrfs_root *fs_root, u64 *objectid);
-
 /* inode-item.c */
 int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,

fs/btrfs/disk-io.c

@@ -41,6 +41,7 @@
 #include "locking.h"
 #include "tree-log.h"
 #include "free-space-cache.h"
+#include "inode-map.h"
 
 static struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
@@ -1327,6 +1328,19 @@ struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
 	if (IS_ERR(root))
 		return root;
 
+	root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS);
+	if (!root->free_ino_ctl)
+		goto fail;
+	root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned),
+					GFP_NOFS);
+	if (!root->free_ino_pinned)
+		goto fail;
+
+	btrfs_init_free_ino_ctl(root);
+	mutex_init(&root->fs_commit_mutex);
+	spin_lock_init(&root->cache_lock);
+	init_waitqueue_head(&root->cache_wait);
+
 	set_anon_super(&root->anon_super, NULL);
 
 	if (btrfs_root_refs(&root->root_item) == 0) {
@@ -2483,6 +2497,8 @@ int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
 	if (btrfs_root_refs(&root->root_item) == 0)
 		synchronize_srcu(&fs_info->subvol_srcu);
 
+	__btrfs_remove_free_space_cache(root->free_ino_pinned);
+	__btrfs_remove_free_space_cache(root->free_ino_ctl);
 	free_fs_root(root);
 	return 0;
 }
@@ -2496,6 +2512,8 @@ static void free_fs_root(struct btrfs_root *root)
 	}
 	free_extent_buffer(root->node);
 	free_extent_buffer(root->commit_root);
+	kfree(root->free_ino_ctl);
+	kfree(root->free_ino_pinned);
 	kfree(root->name);
 	kfree(root);
 }

fs/btrfs/free-space-cache.c

@@ -25,6 +25,7 @@
 #include "transaction.h"
 #include "disk-io.h"
 #include "extent_io.h"
+#include "inode-map.h"
 
 #define BITS_PER_BITMAP		(PAGE_CACHE_SIZE * 8)
 #define MAX_CACHE_BYTES_PER_GIG	(32 * 1024)
@@ -105,7 +106,7 @@ int create_free_space_inode(struct btrfs_root *root,
 	u64 objectid;
 	int ret;
 
-	ret = btrfs_find_free_objectid(trans, root, 0, &objectid);
+	ret = btrfs_find_free_objectid(root, &objectid);
 	if (ret < 0)
 		return ret;
 
@@ -1496,10 +1497,9 @@ bool try_merge_free_space(struct btrfs_free_space_ctl *ctl,
 	return merged;
 }
 
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
-			 u64 offset, u64 bytes)
+int __btrfs_add_free_space(struct btrfs_free_space_ctl *ctl,
+			   u64 offset, u64 bytes)
 {
-	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *info;
 	int ret = 0;
 
@@ -1751,11 +1751,29 @@ __btrfs_return_cluster_to_free_space(
 	return 0;
 }
 
-void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
+void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl)
 {
-	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *info;
 	struct rb_node *node;
+
+	spin_lock(&ctl->tree_lock);
+	while ((node = rb_last(&ctl->free_space_offset)) != NULL) {
+		info = rb_entry(node, struct btrfs_free_space, offset_index);
+		unlink_free_space(ctl, info);
+		kfree(info->bitmap);
+		kmem_cache_free(btrfs_free_space_cachep, info);
+		if (need_resched()) {
+			spin_unlock(&ctl->tree_lock);
+			cond_resched();
+			spin_lock(&ctl->tree_lock);
+		}
+	}
+	spin_unlock(&ctl->tree_lock);
+}
+
+void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
+{
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_cluster *cluster;
 	struct list_head *head;
 
@@ -1773,21 +1791,9 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
 			spin_lock(&ctl->tree_lock);
 		}
 	}
-
-	while ((node = rb_last(&ctl->free_space_offset)) != NULL) {
-		info = rb_entry(node, struct btrfs_free_space, offset_index);
-		unlink_free_space(ctl, info);
-		if (info->bitmap)
-			kfree(info->bitmap);
-		kmem_cache_free(btrfs_free_space_cachep, info);
-		if (need_resched()) {
-			spin_unlock(&ctl->tree_lock);
-			cond_resched();
-			spin_lock(&ctl->tree_lock);
-		}
-	}
-
 	spin_unlock(&ctl->tree_lock);
+
+	__btrfs_remove_free_space_cache(ctl);
 }
 
 u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
@@ -2352,3 +2358,53 @@ int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
 
 	return ret;
 }
+
+/*
+ * Find the left-most item in the cache tree, and then return the
+ * smallest inode number in the item.
+ *
+ * Note: the returned inode number may not be the smallest one in
+ * the tree, if the left-most item is a bitmap.
+ */
+u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root)
+{
+	struct btrfs_free_space_ctl *ctl = fs_root->free_ino_ctl;
+	struct btrfs_free_space *entry = NULL;
+	u64 ino = 0;
+
+	spin_lock(&ctl->tree_lock);
+
+	if (RB_EMPTY_ROOT(&ctl->free_space_offset))
+		goto out;
+
+	entry = rb_entry(rb_first(&ctl->free_space_offset),
+			 struct btrfs_free_space, offset_index);
+
+	if (!entry->bitmap) {
+		ino = entry->offset;
+
+		unlink_free_space(ctl, entry);
+		entry->offset++;
+		entry->bytes--;
+		if (!entry->bytes)
+			kmem_cache_free(btrfs_free_space_cachep, entry);
+		else
+			link_free_space(ctl, entry);
+	} else {
+		u64 offset = 0;
+		u64 count = 1;
+		int ret;
+
+		ret = search_bitmap(ctl, entry, &offset, &count);
+		BUG_ON(ret);
+
+		ino = offset;
+		bitmap_clear_bits(ctl, entry, offset, 1);
+		if (entry->bytes == 0)
+			free_bitmap(ctl, entry);
+	}
+out:
+	spin_unlock(&ctl->tree_lock);
+
+	return ino;
+}

fs/btrfs/free-space-cache.h

@@ -64,15 +64,25 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 			  struct btrfs_trans_handle *trans,
 			  struct btrfs_block_group_cache *block_group,
 			  struct btrfs_path *path);
+
 void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group);
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
-			 u64 bytenr, u64 size);
+int __btrfs_add_free_space(struct btrfs_free_space_ctl *ctl,
+			   u64 bytenr, u64 size);
+static inline int
+btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
+		     u64 bytenr, u64 size)
+{
+	return __btrfs_add_free_space(block_group->free_space_ctl,
+				      bytenr, size);
+}
 int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
 			    u64 bytenr, u64 size);
+void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl);
 void btrfs_remove_free_space_cache(struct btrfs_block_group_cache
-				   *block_group);
+				     *block_group);
 u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
 			       u64 offset, u64 bytes, u64 empty_size);
+u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root);
 void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
 			   u64 bytes);
 int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,