1 files changed, 114 insertions, 131 deletions

diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 19e4ad2f3f2e..86ec2edc05e8 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -18,10 +18,12 @@
  */
 
 #include <linux/slab.h>
+#include <linux/iversion.h>
 #include "delayed-inode.h"
 #include "disk-io.h"
 #include "transaction.h"
 #include "ctree.h"
+#include "qgroup.h"
 
 #define BTRFS_DELAYED_WRITEBACK		512
 #define BTRFS_DELAYED_BACKGROUND	128
@@ -41,7 +43,7 @@ int __init btrfs_delayed_inode_init(void)
 	return 0;
 }
 
-void btrfs_delayed_inode_exit(void)
+void __cold btrfs_delayed_inode_exit(void)
 {
 	kmem_cache_destroy(delayed_node_cache);
 }
@@ -87,6 +89,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
 
 	spin_lock(&root->inode_lock);
 	node = radix_tree_lookup(&root->delayed_nodes_tree, ino);
+
 	if (node) {
 		if (btrfs_inode->delayed_node) {
 			refcount_inc(&node->refs);	/* can be accessed */
@@ -94,9 +97,30 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
 			spin_unlock(&root->inode_lock);
 			return node;
 		}
-		btrfs_inode->delayed_node = node;
-		/* can be accessed and cached in the inode */
-		refcount_add(2, &node->refs);
+
+		/*
+		 * It's possible that we're racing into the middle of removing
+		 * this node from the radix tree.  In this case, the refcount
+		 * was zero and it should never go back to one.  Just return
+		 * NULL like it was never in the radix at all; our release
+		 * function is in the process of removing it.
+		 *
+		 * Some implementations of refcount_inc refuse to bump the
+		 * refcount once it has hit zero.  If we don't do this dance
+		 * here, refcount_inc() may decide to just WARN_ONCE() instead
+		 * of actually bumping the refcount.
+		 *
+		 * If this node is properly in the radix, we want to bump the
+		 * refcount twice, once for the inode and once for this get
+		 * operation.
+		 */
+		if (refcount_inc_not_zero(&node->refs)) {
+			refcount_inc(&node->refs);
+			btrfs_inode->delayed_node = node;
+		} else {
+			node = NULL;
+		}
+
 		spin_unlock(&root->inode_lock);
 		return node;
 	}
@@ -254,17 +278,18 @@ static void __btrfs_release_delayed_node(
 	mutex_unlock(&delayed_node->mutex);
 
 	if (refcount_dec_and_test(&delayed_node->refs)) {
-		bool free = false;
 		struct btrfs_root *root = delayed_node->root;
+
 		spin_lock(&root->inode_lock);
-		if (refcount_read(&delayed_node->refs) == 0) {
-			radix_tree_delete(&root->delayed_nodes_tree,
-					  delayed_node->inode_id);
-			free = true;
-		}
+		/*
+		 * Once our refcount goes to zero, nobody is allowed to bump it
+		 * back up.  We can delete it now.
+		 */
+		ASSERT(refcount_read(&delayed_node->refs) == 0);
+		radix_tree_delete(&root->delayed_nodes_tree,
+				  delayed_node->inode_id);
 		spin_unlock(&root->inode_lock);
-		if (free)
-			kmem_cache_free(delayed_node_cache, delayed_node);
+		kmem_cache_free(delayed_node_cache, delayed_node);
 	}
 }
 
@@ -528,11 +553,12 @@ static struct btrfs_delayed_item *__btrfs_next_delayed_item(
 }
 
 static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans,
-					       struct btrfs_fs_info *fs_info,
+					       struct btrfs_root *root,
 					       struct btrfs_delayed_item *item)
 {
 	struct btrfs_block_rsv *src_rsv;
 	struct btrfs_block_rsv *dst_rsv;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	u64 num_bytes;
 	int ret;
 
@@ -554,15 +580,17 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-static void btrfs_delayed_item_release_metadata(struct btrfs_fs_info *fs_info,
+static void btrfs_delayed_item_release_metadata(struct btrfs_root *root,
 						struct btrfs_delayed_item *item)
 {
 	struct btrfs_block_rsv *rsv;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	if (!item->bytes_reserved)
 		return;
 
 	rsv = &fs_info->delayed_block_rsv;
+	btrfs_qgroup_convert_reserved_meta(root, item->bytes_reserved);
 	trace_btrfs_space_reservation(fs_info, "delayed_item",
 				      item->key.objectid, item->bytes_reserved,
 				      0);
@@ -581,36 +609,15 @@ static int btrfs_delayed_inode_reserve_metadata(
 	struct btrfs_block_rsv *dst_rsv;
 	u64 num_bytes;
 	int ret;
-	bool release = false;
 
 	src_rsv = trans->block_rsv;
 	dst_rsv = &fs_info->delayed_block_rsv;
 
 	num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
 
-	/*
-	 * If our block_rsv is the delalloc block reserve then check and see if
-	 * we have our extra reservation for updating the inode.  If not fall
-	 * through and try to reserve space quickly.
-	 *
-	 * We used to try and steal from the delalloc block rsv or the global
-	 * reserve, but we'd steal a full reservation, which isn't kind.  We are
-	 * here through delalloc which means we've likely just cowed down close
-	 * to the leaf that contains the inode, so we would steal less just
-	 * doing the fallback inode update, so if we do end up having to steal
-	 * from the global block rsv we hopefully only steal one or two blocks
-	 * worth which is less likely to hurt us.
-	 */
-	if (src_rsv && src_rsv->type == BTRFS_BLOCK_RSV_DELALLOC) {
-		spin_lock(&inode->lock);
-		if (test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
-				       &inode->runtime_flags))
-			release = true;
-		else
-			src_rsv = NULL;
-		spin_unlock(&inode->lock);
-	}
-
+	ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true);
+	if (ret < 0)
+		return ret;
 	/*
 	 * btrfs_dirty_inode will update the inode under btrfs_join_transaction
 	 * which doesn't reserve space for speed.  This is a problem since we
@@ -618,7 +625,7 @@ static int btrfs_delayed_inode_reserve_metadata(
 	 * space.
 	 *
 	 * Now if src_rsv == delalloc_block_rsv we'll let it just steal since
-	 * we're accounted for.
+	 * we always reserve enough to update the inode item.
 	 */
 	if (!src_rsv || (!trans->bytes_reserved &&
 			 src_rsv->type != BTRFS_BLOCK_RSV_DELALLOC)) {
@@ -630,8 +637,10 @@ static int btrfs_delayed_inode_reserve_metadata(
 		 * EAGAIN to make us stop the transaction we have, so return
 		 * ENOSPC instead so that btrfs_dirty_inode knows what to do.
 		 */
-		if (ret == -EAGAIN)
+		if (ret == -EAGAIN) {
 			ret = -ENOSPC;
+			btrfs_qgroup_free_meta_prealloc(root, num_bytes);
+		}
 		if (!ret) {
 			node->bytes_reserved = num_bytes;
 			trace_btrfs_space_reservation(fs_info,
@@ -643,37 +652,18 @@ static int btrfs_delayed_inode_reserve_metadata(
 	}
 
 	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
-
-	/*
-	 * Migrate only takes a reservation, it doesn't touch the size of the
-	 * block_rsv.  This is to simplify people who don't normally have things
-	 * migrated from their block rsv.  If they go to release their
-	 * reservation, that will decrease the size as well, so if migrate
-	 * reduced size we'd end up with a negative size.  But for the
-	 * delalloc_meta_reserved stuff we will only know to drop 1 reservation,
-	 * but we could in fact do this reserve/migrate dance several times
-	 * between the time we did the original reservation and we'd clean it
-	 * up.  So to take care of this, release the space for the meta
-	 * reservation here.  I think it may be time for a documentation page on
-	 * how block rsvs. work.
-	 */
 	if (!ret) {
 		trace_btrfs_space_reservation(fs_info, "delayed_inode",
 					      btrfs_ino(inode), num_bytes, 1);
 		node->bytes_reserved = num_bytes;
 	}
 
-	if (release) {
-		trace_btrfs_space_reservation(fs_info, "delalloc",
-					      btrfs_ino(inode), num_bytes, 0);
-		btrfs_block_rsv_release(fs_info, src_rsv, num_bytes);
-	}
-
 	return ret;
 }
 
 static void btrfs_delayed_inode_release_metadata(struct btrfs_fs_info *fs_info,
-						struct btrfs_delayed_node *node)
+						struct btrfs_delayed_node *node,
+						bool qgroup_free)
 {
 	struct btrfs_block_rsv *rsv;
 
@@ -685,6 +675,12 @@ static void btrfs_delayed_inode_release_metadata(struct btrfs_fs_info *fs_info,
 				      node->inode_id, node->bytes_reserved, 0);
 	btrfs_block_rsv_release(fs_info, rsv,
 				node->bytes_reserved);
+	if (qgroup_free)
+		btrfs_qgroup_free_meta_prealloc(node->root,
+				node->bytes_reserved);
+	else
+		btrfs_qgroup_convert_reserved_meta(node->root,
+				node->bytes_reserved);
 	node->bytes_reserved = 0;
 }
 
@@ -786,7 +782,7 @@ static int btrfs_batch_insert_items(struct btrfs_root *root,
 				    curr->data_len);
 		slot++;
 
-		btrfs_delayed_item_release_metadata(fs_info, curr);
+		btrfs_delayed_item_release_metadata(root, curr);
 
 		list_del(&curr->tree_list);
 		btrfs_release_delayed_item(curr);
@@ -808,7 +804,6 @@ static int btrfs_insert_delayed_item(struct btrfs_trans_handle *trans,
 				     struct btrfs_path *path,
 				     struct btrfs_delayed_item *delayed_item)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *leaf;
 	char *ptr;
 	int ret;
@@ -826,7 +821,7 @@ static int btrfs_insert_delayed_item(struct btrfs_trans_handle *trans,
 			    delayed_item->data_len);
 	btrfs_mark_buffer_dirty(leaf);
 
-	btrfs_delayed_item_release_metadata(fs_info, delayed_item);
+	btrfs_delayed_item_release_metadata(root, delayed_item);
 	return 0;
 }
 
@@ -878,7 +873,6 @@ static int btrfs_batch_delete_items(struct btrfs_trans_handle *trans,
 				    struct btrfs_path *path,
 				    struct btrfs_delayed_item *item)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_delayed_item *curr, *next;
 	struct extent_buffer *leaf;
 	struct btrfs_key key;
@@ -928,7 +922,7 @@ static int btrfs_batch_delete_items(struct btrfs_trans_handle *trans,
 		goto out;
 
 	list_for_each_entry_safe(curr, next, &head, tree_list) {
-		btrfs_delayed_item_release_metadata(fs_info, curr);
+		btrfs_delayed_item_release_metadata(root, curr);
 		list_del(&curr->tree_list);
 		btrfs_release_delayed_item(curr);
 	}
@@ -1071,7 +1065,7 @@ out:
 no_iref:
 	btrfs_release_path(path);
 err_out:
-	btrfs_delayed_inode_release_metadata(fs_info, node);
+	btrfs_delayed_inode_release_metadata(fs_info, node, (ret < 0));
 	btrfs_release_delayed_inode(node);
 
 	return ret;
@@ -1135,9 +1129,9 @@ __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
  * Returns < 0 on error and returns with an aborted transaction with any
  * outstanding delayed items cleaned up.
  */
-static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
-				     struct btrfs_fs_info *fs_info, int nr)
+static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans, int nr)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_root *delayed_root;
 	struct btrfs_delayed_node *curr_node, *prev_node;
 	struct btrfs_path *path;
@@ -1182,16 +1176,14 @@ static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info)
+int btrfs_run_delayed_items(struct btrfs_trans_handle *trans)
 {
-	return __btrfs_run_delayed_items(trans, fs_info, -1);
+	return __btrfs_run_delayed_items(trans, -1);
 }
 
-int btrfs_run_delayed_items_nr(struct btrfs_trans_handle *trans,
-			       struct btrfs_fs_info *fs_info, int nr)
+int btrfs_run_delayed_items_nr(struct btrfs_trans_handle *trans, int nr)
 {
-	return __btrfs_run_delayed_items(trans, fs_info, nr);
+	return __btrfs_run_delayed_items(trans, nr);
 }
 
 int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
@@ -1323,40 +1315,42 @@ static void btrfs_async_run_delayed_root(struct btrfs_work *work)
 	if (!path)
 		goto out;
 
-again:
-	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND / 2)
-		goto free_path;
+	do {
+		if (atomic_read(&delayed_root->items) <
+		    BTRFS_DELAYED_BACKGROUND / 2)
+			break;
 
-	delayed_node = btrfs_first_prepared_delayed_node(delayed_root);
-	if (!delayed_node)
-		goto free_path;
+		delayed_node = btrfs_first_prepared_delayed_node(delayed_root);
+		if (!delayed_node)
+			break;
 
-	path->leave_spinning = 1;
-	root = delayed_node->root;
+		path->leave_spinning = 1;
+		root = delayed_node->root;
 
-	trans = btrfs_join_transaction(root);
-	if (IS_ERR(trans))
-		goto release_path;
+		trans = btrfs_join_transaction(root);
+		if (IS_ERR(trans)) {
+			btrfs_release_path(path);
+			btrfs_release_prepared_delayed_node(delayed_node);
+			total_done++;
+			continue;
+		}
 
-	block_rsv = trans->block_rsv;
-	trans->block_rsv = &root->fs_info->delayed_block_rsv;
+		block_rsv = trans->block_rsv;
+		trans->block_rsv = &root->fs_info->delayed_block_rsv;
 
-	__btrfs_commit_inode_delayed_items(trans, path, delayed_node);
+		__btrfs_commit_inode_delayed_items(trans, path, delayed_node);
 
-	trans->block_rsv = block_rsv;
-	btrfs_end_transaction(trans);
-	btrfs_btree_balance_dirty_nodelay(root->fs_info);
+		trans->block_rsv = block_rsv;
+		btrfs_end_transaction(trans);
+		btrfs_btree_balance_dirty_nodelay(root->fs_info);
 
-release_path:
-	btrfs_release_path(path);
-	total_done++;
+		btrfs_release_path(path);
+		btrfs_release_prepared_delayed_node(delayed_node);
+		total_done++;
 
-	btrfs_release_prepared_delayed_node(delayed_node);
-	if ((async_work->nr == 0 && total_done < BTRFS_DELAYED_WRITEBACK) ||
-	    total_done < async_work->nr)
-		goto again;
+	} while ((async_work->nr == 0 && total_done < BTRFS_DELAYED_WRITEBACK)
+		 || total_done < async_work->nr);
 
-free_path:
 	btrfs_free_path(path);
 out:
 	wake_up(&delayed_root->wait);
@@ -1369,10 +1363,6 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
 {
 	struct btrfs_async_delayed_work *async_work;
 
-	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND ||
-	    btrfs_workqueue_normal_congested(fs_info->delayed_workers))
-		return 0;
-
 	async_work = kmalloc(sizeof(*async_work), GFP_NOFS);
 	if (!async_work)
 		return -ENOMEM;
@@ -1408,7 +1398,8 @@ void btrfs_balance_delayed_items(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_delayed_root *delayed_root = fs_info->delayed_root;
 
-	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND)
+	if ((atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND) ||
+		btrfs_workqueue_normal_congested(fs_info->delayed_workers))
 		return;
 
 	if (atomic_read(&delayed_root->items) >= BTRFS_DELAYED_WRITEBACK) {
@@ -1464,7 +1455,7 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 	btrfs_set_stack_dir_type(dir_item, type);
 	memcpy((char *)(dir_item + 1), name, name_len);
 
-	ret = btrfs_delayed_item_reserve_metadata(trans, fs_info, delayed_item);
+	ret = btrfs_delayed_item_reserve_metadata(trans, dir->root, delayed_item);
 	/*
 	 * we have reserved enough space when we start a new transaction,
 	 * so reserving metadata failure is impossible
@@ -1501,7 +1492,7 @@ static int btrfs_delete_delayed_insertion_item(struct btrfs_fs_info *fs_info,
 		return 1;
 	}
 
-	btrfs_delayed_item_release_metadata(fs_info, item);
+	btrfs_delayed_item_release_metadata(node->root, item);
 	btrfs_release_delayed_item(item);
 	mutex_unlock(&node->mutex);
 	return 0;
@@ -1536,7 +1527,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 
 	item->key = item_key;
 
-	ret = btrfs_delayed_item_reserve_metadata(trans, fs_info, item);
+	ret = btrfs_delayed_item_reserve_metadata(trans, dir->root, item);
 	/*
 	 * we have reserved enough space when we start a new transaction,
 	 * so reserving metadata failure is impossible.
@@ -1654,28 +1645,18 @@ void btrfs_readdir_put_delayed_items(struct inode *inode,
 int btrfs_should_delete_dir_index(struct list_head *del_list,
 				  u64 index)
 {
-	struct btrfs_delayed_item *curr, *next;
-	int ret;
-
-	if (list_empty(del_list))
-		return 0;
+	struct btrfs_delayed_item *curr;
+	int ret = 0;
 
-	list_for_each_entry_safe(curr, next, del_list, readdir_list) {
+	list_for_each_entry(curr, del_list, readdir_list) {
 		if (curr->key.offset > index)
 			break;
-
-		list_del(&curr->readdir_list);
-		ret = (curr->key.offset == index);
-
-		if (refcount_dec_and_test(&curr->refs))
-			kfree(curr);
-
-		if (ret)
-			return 1;
-		else
-			continue;
+		if (curr->key.offset == index) {
+			ret = 1;
+			break;
+		}
 	}
-	return 0;
+	return ret;
 }
 
 /*
@@ -1744,7 +1725,8 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans,
 	btrfs_set_stack_inode_nbytes(inode_item, inode_get_bytes(inode));
 	btrfs_set_stack_inode_generation(inode_item,
 					 BTRFS_I(inode)->generation);
-	btrfs_set_stack_inode_sequence(inode_item, inode->i_version);
+	btrfs_set_stack_inode_sequence(inode_item,
+				       inode_peek_iversion(inode));
 	btrfs_set_stack_inode_transid(inode_item, trans->transid);
 	btrfs_set_stack_inode_rdev(inode_item, inode->i_rdev);
 	btrfs_set_stack_inode_flags(inode_item, BTRFS_I(inode)->flags);
@@ -1798,7 +1780,8 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev)
 	BTRFS_I(inode)->generation = btrfs_stack_inode_generation(inode_item);
         BTRFS_I(inode)->last_trans = btrfs_stack_inode_transid(inode_item);
 
-	inode->i_version = btrfs_stack_inode_sequence(inode_item);
+	inode_set_iversion_queried(inode,
+				   btrfs_stack_inode_sequence(inode_item));
 	inode->i_rdev = 0;
 	*rdev = btrfs_stack_inode_rdev(inode_item);
 	BTRFS_I(inode)->flags = btrfs_stack_inode_flags(inode_item);
@@ -1909,7 +1892,7 @@ static void __btrfs_kill_delayed_node(struct btrfs_delayed_node *delayed_node)
 	mutex_lock(&delayed_node->mutex);
 	curr_item = __btrfs_first_delayed_insertion_item(delayed_node);
 	while (curr_item) {
-		btrfs_delayed_item_release_metadata(fs_info, curr_item);
+		btrfs_delayed_item_release_metadata(root, curr_item);
 		prev_item = curr_item;
 		curr_item = __btrfs_next_delayed_item(prev_item);
 		btrfs_release_delayed_item(prev_item);
@@ -1917,7 +1900,7 @@ static void __btrfs_kill_delayed_node(struct btrfs_delayed_node *delayed_node)
 
 	curr_item = __btrfs_first_delayed_deletion_item(delayed_node);
 	while (curr_item) {
-		btrfs_delayed_item_release_metadata(fs_info, curr_item);
+		btrfs_delayed_item_release_metadata(root, curr_item);
 		prev_item = curr_item;
 		curr_item = __btrfs_next_delayed_item(prev_item);
 		btrfs_release_delayed_item(prev_item);
@@ -1927,7 +1910,7 @@ static void __btrfs_kill_delayed_node(struct btrfs_delayed_node *delayed_node)
 		btrfs_release_delayed_iref(delayed_node);
 
 	if (test_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags)) {
-		btrfs_delayed_inode_release_metadata(fs_info, delayed_node);
+		btrfs_delayed_inode_release_metadata(fs_info, delayed_node, false);
 		btrfs_release_delayed_inode(delayed_node);
 	}
 	mutex_unlock(&delayed_node->mutex);