Merge branch 'for-linus-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs updates from Chris Mason:
 "I've been running these through a longer set of load tests because my
  commits change the free space cache writeout.  It fixes commit stalls
  on large filesystems (~20T space used and up) that we have been
  triggering here.  We were seeing new writers blocked for 10 seconds or
  more during commits, which is far from good.

  Josef and I fixed up ENOSPC aborts when deleting huge files (3T or
  more), that are triggered because our metadata reservations were not
  properly accounting for crcs and were not replenishing during the
  truncate.

  Also in this series, a number of qgroup fixes from Fujitsu and Dave
  Sterba collected most of the pending cleanups from the list"

* 'for-linus-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (93 commits)
  btrfs: quota: Update quota tree after qgroup relationship change.
  btrfs: quota: Automatically update related qgroups or mark INCONSISTENT flags when assigning/deleting a qgroup relations.
  btrfs: qgroup: clear STATUS_FLAG_ON in disabling quota.
  btrfs: Update btrfs qgroup status item when rescan is done.
  btrfs: qgroup: Fix dead judgement on qgroup_rescan_leaf() return value.
  btrfs: Don't allow subvolid >= (1 << BTRFS_QGROUP_LEVEL_SHIFT) to be created
  btrfs: Check qgroup level in kernel qgroup assign.
  btrfs: qgroup: allow to remove qgroup which has parent but no child.
  btrfs: qgroup: return EINVAL if level of parent is not higher than child's.
  btrfs: qgroup: do a reservation in a higher level.
  Btrfs: qgroup, Account data space in more proper timings.
  Btrfs: qgroup: Introduce a may_use to account space_info->bytes_may_use.
  Btrfs: qgroup: free reserved in exceeding quota.
  Btrfs: qgroup: cleanup, remove an unsued parameter in btrfs_create_qgroup().
  btrfs: qgroup: fix limit args override whole limit struct
  btrfs: qgroup: update limit info in function btrfs_run_qgroups().
  btrfs: qgroup: consolidate the parameter of fucntion update_qgroup_limit_item().
  btrfs: qgroup: update qgroup in memory at the same time when we update it in btree.
  btrfs: qgroup: inherit limit info from srcgroup in creating snapshot.
  btrfs: Support busy loop of write and delete
  ...

1 files changed, 33 insertions, 32 deletions

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index faa7d390841b..467620a3b1f9 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -273,11 +273,7 @@ void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info)
 		defrag = rb_entry(node, struct inode_defrag, rb_node);
 		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
 
-		if (need_resched()) {
-			spin_unlock(&fs_info->defrag_inodes_lock);
-			cond_resched();
-			spin_lock(&fs_info->defrag_inodes_lock);
-		}
+		cond_resched_lock(&fs_info->defrag_inodes_lock);
 
 		node = rb_first(&fs_info->defrag_inodes);
 	}
@@ -868,7 +864,7 @@ next_slot:
 
 			memcpy(&new_key, &key, sizeof(new_key));
 			new_key.offset = end;
-			btrfs_set_item_key_safe(root, path, &new_key);
+			btrfs_set_item_key_safe(root->fs_info, path, &new_key);
 
 			extent_offset += end - key.offset;
 			btrfs_set_file_extent_offset(leaf, fi, extent_offset);
@@ -1126,7 +1122,7 @@ again:
 				     ino, bytenr, orig_offset,
 				     &other_start, &other_end)) {
 			new_key.offset = end;
-			btrfs_set_item_key_safe(root, path, &new_key);
+			btrfs_set_item_key_safe(root->fs_info, path, &new_key);
 			fi = btrfs_item_ptr(leaf, path->slots[0],
 					    struct btrfs_file_extent_item);
 			btrfs_set_file_extent_generation(leaf, fi,
@@ -1160,7 +1156,7 @@ again:
 							 trans->transid);
 			path->slots[0]++;
 			new_key.offset = start;
-			btrfs_set_item_key_safe(root, path, &new_key);
+			btrfs_set_item_key_safe(root->fs_info, path, &new_key);
 
 			fi = btrfs_item_ptr(leaf, path->slots[0],
 					    struct btrfs_file_extent_item);
@@ -1485,7 +1481,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 			PAGE_CACHE_SIZE / (sizeof(struct page *)));
 	nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied);
 	nrptrs = max(nrptrs, 8);
-	pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
+	pages = kmalloc_array(nrptrs, sizeof(struct page *), GFP_KERNEL);
 	if (!pages)
 		return -ENOMEM;
 
@@ -1514,7 +1510,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		}
 
 		reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
-		ret = btrfs_check_data_free_space(inode, reserve_bytes);
+		ret = btrfs_check_data_free_space(inode, reserve_bytes, write_bytes);
 		if (ret == -ENOSPC &&
 		    (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
 					      BTRFS_INODE_PREALLOC))) {
@@ -1635,8 +1631,8 @@ again:
 			btrfs_end_write_no_snapshoting(root);
 
 		if (only_release_metadata && copied > 0) {
-			u64 lockstart = round_down(pos, root->sectorsize);
-			u64 lockend = lockstart +
+			lockstart = round_down(pos, root->sectorsize);
+			lockend = lockstart +
 				(dirty_pages << PAGE_CACHE_SHIFT) - 1;
 
 			set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
@@ -1809,7 +1805,9 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	 * otherwise subsequent syncs to a file that's been synced in this
 	 * transaction will appear to have already occured.
 	 */
+	spin_lock(&BTRFS_I(inode)->lock);
 	BTRFS_I(inode)->last_sub_trans = root->log_transid;
+	spin_unlock(&BTRFS_I(inode)->lock);
 	if (num_written > 0) {
 		err = generic_write_sync(file, pos, num_written);
 		if (err < 0)
@@ -2162,7 +2160,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 		u64 num_bytes;
 
 		key.offset = offset;
-		btrfs_set_item_key_safe(root, path, &key);
+		btrfs_set_item_key_safe(root->fs_info, path, &key);
 		fi = btrfs_item_ptr(leaf, path->slots[0],
 				    struct btrfs_file_extent_item);
 		num_bytes = btrfs_file_extent_num_bytes(leaf, fi) + end -
@@ -2545,7 +2543,6 @@ static long btrfs_fallocate(struct file *file, int mode,
 {
 	struct inode *inode = file_inode(file);
 	struct extent_state *cached_state = NULL;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
 	u64 cur_offset;
 	u64 last_byte;
 	u64 alloc_start;
@@ -2570,14 +2567,9 @@ static long btrfs_fallocate(struct file *file, int mode,
 	 * Make sure we have enough space before we do the
 	 * allocation.
 	 */
-	ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
+	ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start, alloc_end - alloc_start);
 	if (ret)
 		return ret;
-	if (root->fs_info->quota_enabled) {
-		ret = btrfs_qgroup_reserve(root, alloc_end - alloc_start);
-		if (ret)
-			goto out_reserve_fail;
-	}
 
 	mutex_lock(&inode->i_mutex);
 	ret = inode_newsize_ok(inode, alloc_end);
@@ -2667,23 +2659,35 @@ static long btrfs_fallocate(struct file *file, int mode,
 							1 << inode->i_blkbits,
 							offset + len,
 							&alloc_hint);
-
-			if (ret < 0) {
-				free_extent_map(em);
-				break;
-			}
 		} else if (actual_end > inode->i_size &&
 			   !(mode & FALLOC_FL_KEEP_SIZE)) {
+			struct btrfs_trans_handle *trans;
+			struct btrfs_root *root = BTRFS_I(inode)->root;
+
 			/*
 			 * We didn't need to allocate any more space, but we
 			 * still extended the size of the file so we need to
-			 * update i_size.
+			 * update i_size and the inode item.
 			 */
-			inode->i_ctime = CURRENT_TIME;
-			i_size_write(inode, actual_end);
-			btrfs_ordered_update_i_size(inode, actual_end, NULL);
+			trans = btrfs_start_transaction(root, 1);
+			if (IS_ERR(trans)) {
+				ret = PTR_ERR(trans);
+			} else {
+				inode->i_ctime = CURRENT_TIME;
+				i_size_write(inode, actual_end);
+				btrfs_ordered_update_i_size(inode, actual_end,
+							    NULL);
+				ret = btrfs_update_inode(trans, root, inode);
+				if (ret)
+					btrfs_end_transaction(trans, root);
+				else
+					ret = btrfs_end_transaction(trans,
+								    root);
+			}
 		}
 		free_extent_map(em);
+		if (ret < 0)
+			break;
 
 		cur_offset = last_byte;
 		if (cur_offset >= alloc_end) {
@@ -2695,9 +2699,6 @@ static long btrfs_fallocate(struct file *file, int mode,
 			     &cached_state, GFP_NOFS);
 out:
 	mutex_unlock(&inode->i_mutex);
-	if (root->fs_info->quota_enabled)
-		btrfs_qgroup_free(root, alloc_end - alloc_start);
-out_reserve_fail:
 	/* Let go of our reservation. */
 	btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
 	return ret;